allow for alpha releases in travis

1.2.0+2

.gitignore

@@ -0,0 +1,12 @@
+/.idea/
+/nbproject/
+/dist
+*.pyc
+/.vscode
+venv
+*.o
+*.a
+*.so
+build/
+ctversion.py
+.eggs

.travis.yml

@@ -0,0 +1,52 @@
+language: python
+branches:
+  only:
+    - develop
+    - /^\d+\.\d+\.\d+.*$/
+env:
+  global:
+    - PYTHON=python
+    - PIP=pip
+    - SETUPTOOLS_SCM_PRETEND_VERSION=$TRAVIS_TAG
+    - MAKE=make
+matrix:
+  include:
+    - os: linux
+    - os: osx
+      language: generic
+      osx_image: xcode8.3
+      env: PYTHON=python3 PIP=pip3 MACOSX_DEPLOYMENT_TARGET=10.11
+    - os: windows
+      language: bash
+      env: PATH=/C/Python37:/C/Python37/Scripts:$PATH MAKE=mingw32-make
+before_install:
+  - if [ "$TRAVIS_OS_NAME" = "windows" ]; then choco install -y python mingw zip; fi
+  - if [ "$TRAVIS_OS_NAME" = "osx" ]; then brew upgrade python3 ; fi
+install:
+  - $PIP install --upgrade setuptools
+  - $PIP install -r requirements.txt
+script:
+  - if [ "$TRAVIS_OS_NAME" != "linux" ]; then $MAKE dist ; fi
+
+deploy:
+  - name: "$TRAVIS_TAG"
+    body: Released ComicTagger $TRAVIS_TAG
+    provider: releases
+    skip_cleanup: true
+    api_key:
+      secure: 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
+    file_glob: true
+    file: dist/*.zip
+    draft: true
+    on:
+      tags: true
+      condition: $TRAVIS_OS_NAME != "linux"
+  - provider: pypi
+    user: __token__
+    password:
+      secure: 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
+    skip_existing: true
+    skip_cleanup: true
+    on:
+      tags: true
+      condition: $TRAVIS_OS_NAME = "linux"

MANIFEST.in

@@ -0,0 +1,7 @@
+include README.md
+include release_notes.txt
+include requirements.txt
+recursive-include scripts *.py *.txt
+recursive-include desktop-integration *
+include windows/app.ico
+include mac/app.icns

Makefile

@@ -1,24 +1,48 @@
-TAGGER_BASE := $(HOME)/Dropbox/tagger/comictagger
-VERSION_STR := $(shell grep version $(TAGGER_BASE)/ctversion.py| cut -d= -f2 | sed 's/\"//g')
+PIP ?= pip
+VERSION_STR := $(shell python setup.py --version)
 
-all: clean
+ifeq ($(OS),Windows_NT)
+	OS_VERSION=win-$(PROCESSOR_ARCHITECTURE)
+	APP_NAME=comictagger.exe
+	FINAL_NAME=ComicTagger-$(VERSION_STR)-$(OS_VERSION).exe
+else ifeq ($(shell uname -s),Darwin)
+	OS_VERSION=osx-$(shell defaults read loginwindow SystemVersionStampAsString)-$(shell uname -m)
+	APP_NAME=ComicTagger.app
+	FINAL_NAME=ComicTagger-$(VERSION_STR)-$(OS_VERSION).app
+else
+	APP_NAME=comictagger
+	FINAL_NAME=ComicTagger-$(VERSION_STR)
+endif
+
+.PHONY: all clean pydist upload dist
+	
+all: clean dist
 
 clean:
-	rm -f *~ *.pyc *.pyo
-	rm -f logdict*.log
-	
-	
-zip:
-	cd release; \
-		rm -rf *zip comictagger-src-$(VERSION_STR) ;  \
-		svn checkout https://comictagger.googlecode.com/svn/trunk/ comictagger-src-$(VERSION_STR); \
-		zip -r comictagger-src-$(VERSION_STR).zip comictagger-src-$(VERSION_STR); \
-		rm -rf comictagger-src-$(VERSION_STR)
-	
-	@echo When satisfied with release, do this:
-	@echo make svn_tag
-	
-svn_tag:
-	svn copy https://comictagger.googlecode.com/svn/trunk \
-      https://comictagger.googlecode.com/svn/tags/$(VERSION_STR) -m "Release $(VERSION_STR)"
-	
+	rm -rf *~ *.pyc *.pyo
+	rm -rf scripts/*.pyc
+	cd comictaggerlib; rm -f *~ *.pyc *.pyo
+	rm -rf dist MANIFEST
+	rm -rf *.deb
+	rm -rf logdict*.log
+	$(MAKE) -C mac clean   
+	rm -rf build
+	rm -rf comictaggerlib/ui/__pycache__
+	rm comitaggerlib/ctversion.py
+
+pydist:
+	make clean
+	mkdir -p piprelease
+	rm -f comictagger-$(VERSION_STR).zip
+	python setup.py sdist --formats=zip  #,gztar
+	mv dist/comictagger-$(VERSION_STR).zip piprelease
+	rm -rf comictagger.egg-info dist
+		
+upload:
+	python setup.py register
+	python setup.py sdist --formats=zip upload
+
+dist:
+	$(PIP) install .
+	pyinstaller -y comictagger.spec
+	cd dist && zip -r $(FINAL_NAME).zip $(APP_NAME)

README.md

@@ -0,0 +1,48 @@
+[![Build Status](https://travis-ci.org/comictagger/comictagger.svg?branch=develop)](https://travis-ci.org/comictagger/comictagger)
+[![Gitter chat](https://badges.gitter.im/gitterHQ/gitter.png)](https://gitter.im/comictagger/community)
+[![Google Group](https://img.shields.io/badge/discuss-on%20groups-%23207de5)](https://groups.google.com/forum/#!forum/comictagger)
+[![Twitter](https://img.shields.io/badge/%40comictagger-twitter-lightgrey)](https://twitter.com/comictagger)
+[![Facebook](https://img.shields.io/badge/comictagger-facebook-lightgrey)](https://www.facebook.com/ComicTagger-139615369550787/)
+
+# ComicTagger
+
+ComicTagger is a **multi-platform** app for **writing metadata to digital comics**, written in Python and PyQt.
+
+![ComicTagger logo](https://raw.githubusercontent.com/comictagger/comictagger/develop/comictaggerlib/graphics/app.png)
+
+## Features
+
+* Runs on macOS, Microsoft Windows, and Linux systems
+* Get comic information from [Comic Vine](https://comicvine.gamespot.com/)
+* **Automatic issue matching** using advanced image processing techniques
+* **Batch processing** in the GUI for tagging hundreds or more comics at a time
+* Support for **ComicRack** and **ComicBookLover** tagging formats
+* Native full support for **CBZ** digital comics
+* Native read only support for **CBR** digital comics: full support enabled installing additional [rar tools](https://www.rarlab.com/download.htm)
+* Command line interface (CLI) enabling **custom scripting** and **batch operations on large collections**
+
+For details, screen-shots, release notes, and more, visit [the Wiki](https://github.com/comictagger/comictagger/wiki)
+
+
+## Installation
+
+### Binaries
+
+Windows and macOS binaries are provided in the [Releases Page](https://github.com/comictagger/comictagger/releases). 
+
+Just unzip the archive in any folder and run, no additional installation steps are required.
+
+### PIP installation
+
+A pip package is provided, you can install it with:
+
+```
+ $ pip install comictagger
+```
+
+### From source
+
+ 1. ensure you have a recent version of python3 and setuptools installed
+ 2. clone this repository `git clone https://github.com/comictagger/comictagger.git`
+ 3. `pip install -r requirements.txt`
+ 4. `python comictagger.py`

UnRAR2/UnRARDLL/license.txt

@@ -1,18 +0,0 @@
-      The unrar.dll library is freeware. This means:
-
-   1. All copyrights to RAR and the unrar.dll are exclusively
-      owned by the author - Alexander Roshal.
-
-   2. The unrar.dll library may be used in any software to handle RAR
-      archives without limitations free of charge.
-
-   3. THE RAR ARCHIVER AND THE UNRAR.DLL LIBRARY ARE DISTRIBUTED "AS IS".
-      NO WARRANTY OF ANY KIND IS EXPRESSED OR IMPLIED.  YOU USE AT 
-      YOUR OWN RISK. THE AUTHOR WILL NOT BE LIABLE FOR DATA LOSS, 
-      DAMAGES, LOSS OF PROFITS OR ANY OTHER KIND OF LOSS WHILE USING
-      OR MISUSING THIS SOFTWARE.
-
-      Thank you for your interest in RAR and unrar.dll.
-
-
-                                            Alexander L. Roshal

UnRAR2/UnRARDLL/unrar.h

@@ -1,140 +0,0 @@
-#ifndef _UNRAR_DLL_
-#define _UNRAR_DLL_
-
-#define ERAR_END_ARCHIVE        10
-#define ERAR_NO_MEMORY          11
-#define ERAR_BAD_DATA           12
-#define ERAR_BAD_ARCHIVE        13
-#define ERAR_UNKNOWN_FORMAT     14
-#define ERAR_EOPEN              15
-#define ERAR_ECREATE            16
-#define ERAR_ECLOSE             17
-#define ERAR_EREAD              18
-#define ERAR_EWRITE             19
-#define ERAR_SMALL_BUF          20
-#define ERAR_UNKNOWN            21
-#define ERAR_MISSING_PASSWORD   22
-
-#define RAR_OM_LIST              0
-#define RAR_OM_EXTRACT           1
-#define RAR_OM_LIST_INCSPLIT     2
-
-#define RAR_SKIP              0
-#define RAR_TEST              1
-#define RAR_EXTRACT           2
-
-#define RAR_VOL_ASK           0
-#define RAR_VOL_NOTIFY        1
-
-#define RAR_DLL_VERSION       4
-
-#ifdef _UNIX
-#define CALLBACK
-#define PASCAL
-#define LONG long
-#define HANDLE void *
-#define LPARAM long
-#define UINT unsigned int
-#endif
-
-struct RARHeaderData
-{
-  char         ArcName[260];
-  char         FileName[260];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int UnpSize;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-};
-
-
-struct RARHeaderDataEx
-{
-  char         ArcName[1024];
-  wchar_t      ArcNameW[1024];
-  char         FileName[1024];
-  wchar_t      FileNameW[1024];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int PackSizeHigh;
-  unsigned int UnpSize;
-  unsigned int UnpSizeHigh;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Reserved[1024];
-};
-
-
-struct RAROpenArchiveData
-{
-  char         *ArcName;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-};
-
-struct RAROpenArchiveDataEx
-{
-  char         *ArcName;
-  wchar_t      *ArcNameW;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Flags;
-  unsigned int Reserved[32];
-};
-
-enum UNRARCALLBACK_MESSAGES {
-  UCM_CHANGEVOLUME,UCM_PROCESSDATA,UCM_NEEDPASSWORD
-};
-
-typedef int (CALLBACK *UNRARCALLBACK)(UINT msg,LPARAM UserData,LPARAM P1,LPARAM P2);
-
-typedef int (PASCAL *CHANGEVOLPROC)(char *ArcName,int Mode);
-typedef int (PASCAL *PROCESSDATAPROC)(unsigned char *Addr,int Size);
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-HANDLE PASCAL RAROpenArchive(struct RAROpenArchiveData *ArchiveData);
-HANDLE PASCAL RAROpenArchiveEx(struct RAROpenArchiveDataEx *ArchiveData);
-int    PASCAL RARCloseArchive(HANDLE hArcData);
-int    PASCAL RARReadHeader(HANDLE hArcData,struct RARHeaderData *HeaderData);
-int    PASCAL RARReadHeaderEx(HANDLE hArcData,struct RARHeaderDataEx *HeaderData);
-int    PASCAL RARProcessFile(HANDLE hArcData,int Operation,char *DestPath,char *DestName);
-int    PASCAL RARProcessFileW(HANDLE hArcData,int Operation,wchar_t *DestPath,wchar_t *DestName);
-void   PASCAL RARSetCallback(HANDLE hArcData,UNRARCALLBACK Callback,LPARAM UserData);
-void   PASCAL RARSetChangeVolProc(HANDLE hArcData,CHANGEVOLPROC ChangeVolProc);
-void   PASCAL RARSetProcessDataProc(HANDLE hArcData,PROCESSDATAPROC ProcessDataProc);
-void   PASCAL RARSetPassword(HANDLE hArcData,char *Password);
-int    PASCAL RARGetDllVersion();
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

UnRAR2/UnRARDLL/unrardll.txt

@@ -1,606 +0,0 @@
-
-    UnRAR.dll Manual
-    ~~~~~~~~~~~~~~~~
-
-    UnRAR.dll is a 32-bit Windows dynamic-link library which provides
- file extraction from RAR archives.
-
-
-    Exported functions
-
-====================================================================
-HANDLE PASCAL RAROpenArchive(struct RAROpenArchiveData *ArchiveData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Open RAR archive and allocate memory structures
-
-Parameters
-~~~~~~~~~~
-ArchiveData       Points to RAROpenArchiveData structure
-
-struct RAROpenArchiveData
-{
-  char *ArcName;
-  UINT OpenMode;
-  UINT OpenResult;
-  char *CmtBuf;
-  UINT CmtBufSize;
-  UINT CmtSize;
-  UINT CmtState;
-};
-
-Structure fields:
-
-ArcName
-  Input parameter which should point to zero terminated string 
-  containing the archive name. 
-
-OpenMode
-  Input parameter.
-
-  Possible values
-
-  RAR_OM_LIST
-    Open archive for reading file headers only.
-
-  RAR_OM_EXTRACT
-    Open archive for testing and extracting files.
-
-  RAR_OM_LIST_INCSPLIT
-    Open archive for reading file headers only. If you open an archive
-    in such mode, RARReadHeader[Ex] will return all file headers,
-    including those with "file continued from previous volume" flag.
-    In case of RAR_OM_LIST such headers are automatically skipped.
-    So if you process RAR volumes in RAR_OM_LIST_INCSPLIT mode, you will
-    get several file header records for same file if file is split between
-    volumes. For such files only the last file header record will contain
-    the correct file CRC and if you wish to get the correct packed size,
-    you need to sum up packed sizes of all parts.
-
-OpenResult
-  Output parameter.
-
-  Possible values
-
-  0                     Success
-  ERAR_NO_MEMORY        Not enough memory to initialize data structures
-  ERAR_BAD_DATA         Archive header broken
-  ERAR_BAD_ARCHIVE      File is not valid RAR archive
-  ERAR_UNKNOWN_FORMAT   Unknown encryption used for archive headers
-  ERAR_EOPEN            File open error
-
-CmtBuf
-  Input parameter which should point to the buffer for archive 
-  comments. Maximum comment size is limited to 64Kb. Comment text is 
-  zero terminated. If the comment text is larger than the buffer 
-  size, the comment text will be truncated. If CmtBuf is set to 
-  NULL, comments will not be read. 
-
-CmtBufSize
-  Input parameter which should contain size of buffer for archive
-  comments.
-
-CmtSize
-  Output parameter containing size of comments actually read into the
-  buffer, cannot exceed CmtBufSize.
-
-CmtState
-  Output parameter.
-
-  Possible values
-
-  0                     comments not present
-  1                     Comments read completely
-  ERAR_NO_MEMORY        Not enough memory to extract comments
-  ERAR_BAD_DATA         Broken comment
-  ERAR_UNKNOWN_FORMAT   Unknown comment format
-  ERAR_SMALL_BUF        Buffer too small, comments not completely read
-
-Return values
-~~~~~~~~~~~~~
-  Archive handle or NULL in case of error
-
-
-========================================================================
-HANDLE PASCAL RAROpenArchiveEx(struct RAROpenArchiveDataEx *ArchiveData)
-========================================================================
-
-Description
-~~~~~~~~~~~
-  Similar to RAROpenArchive, but uses RAROpenArchiveDataEx structure
-  allowing to specify Unicode archive name and returning information
-  about archive flags.
-
-Parameters
-~~~~~~~~~~
-ArchiveData       Points to RAROpenArchiveDataEx structure
-
-struct RAROpenArchiveDataEx
-{
-  char         *ArcName;
-  wchar_t      *ArcNameW;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Flags;
-  unsigned int Reserved[32];
-};
-
-Structure fields:
-
-ArcNameW
-  Input parameter which should point to zero terminated Unicode string
-  containing the archive name or NULL if Unicode name is not specified.
-
-Flags
-  Output parameter. Combination of bit flags.
-
-  Possible values
-
-    0x0001  - Volume attribute (archive volume)
-    0x0002  - Archive comment present
-    0x0004  - Archive lock attribute
-    0x0008  - Solid attribute (solid archive)
-    0x0010  - New volume naming scheme ('volname.partN.rar')
-    0x0020  - Authenticity information present
-    0x0040  - Recovery record present
-    0x0080  - Block headers are encrypted
-    0x0100  - First volume (set only by RAR 3.0 and later)
-
-Reserved[32]
-  Reserved for future use. Must be zero.
-
-Information on other structure fields and function return values
-is available above, in RAROpenArchive function description.
-
-
-====================================================================
-int PASCAL RARCloseArchive(HANDLE hArcData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Close RAR archive and release allocated memory. It must be called when
-  archive processing is finished, even if the archive processing was stopped
-  due to an error.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Return values
-~~~~~~~~~~~~~
-  0                     Success
-  ERAR_ECLOSE           Archive close error
-
-
-====================================================================
-int PASCAL RARReadHeader(HANDLE hArcData,
-                         struct RARHeaderData *HeaderData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Read header of file in archive.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-HeaderData
-  It should point to RARHeaderData structure:
-
-struct RARHeaderData
-{
-  char ArcName[260];
-  char FileName[260];
-  UINT Flags;
-  UINT PackSize;
-  UINT UnpSize;
-  UINT HostOS;
-  UINT FileCRC;
-  UINT FileTime;
-  UINT UnpVer;
-  UINT Method;
-  UINT FileAttr;
-  char *CmtBuf;
-  UINT CmtBufSize;
-  UINT CmtSize;
-  UINT CmtState;
-};
-
-Structure fields:
-
-ArcName
-  Output parameter which contains a zero terminated string of the
-  current archive name.  May be used to determine the current volume 
-  name. 
-
-FileName
-  Output parameter which contains a zero terminated string of the 
-  file name in OEM (DOS) encoding.
-
-Flags
-  Output parameter which contains file flags:
-
-  0x01 - file continued from previous volume
-  0x02 - file continued on next volume
-  0x04 - file encrypted with password
-  0x08 - file comment present
-  0x10 - compression of previous files is used (solid flag)
-
-  bits 7 6 5
-
-       0 0 0    - dictionary size   64 Kb
-       0 0 1    - dictionary size  128 Kb
-       0 1 0    - dictionary size  256 Kb
-       0 1 1    - dictionary size  512 Kb
-       1 0 0    - dictionary size 1024 Kb
-       1 0 1    - dictionary size 2048 KB
-       1 1 0    - dictionary size 4096 KB
-       1 1 1    - file is directory
-
-  Other bits are reserved.
-
-PackSize
-  Output parameter means packed file size or size of the
-  file part if file was split between volumes.
-
-UnpSize
-  Output parameter - unpacked file size.
-
-HostOS
-  Output parameter - operating system used for archiving:
-
-  0 - MS DOS;
-  1 - OS/2.
-  2 - Win32
-  3 - Unix
-
-FileCRC
-  Output parameter which contains unpacked file CRC. In case of file parts
-  split between volumes only the last part contains the correct CRC
-  and it is accessible only in RAR_OM_LIST_INCSPLIT listing mode.
-
-FileTime
-  Output parameter - contains date and time in standard MS DOS format.
-
-UnpVer
-  Output parameter - RAR version needed to extract file.
-  It is encoded as 10 * Major version + minor version.
-
-Method
-  Output parameter - packing method.
-
-FileAttr
-  Output parameter - file attributes.
-
-CmtBuf
-  File comments support is not implemented in the new DLL version yet.
-  Now CmtState is always 0.
-
-/*
- * Input parameter which should point to the buffer for file
- * comments. Maximum comment size is limited to 64Kb. Comment text is 
- * a zero terminated string in OEM encoding. If the comment text is
- * larger than the buffer size, the comment text will be truncated.
- * If CmtBuf is set to NULL, comments will not be read. 
- */
-
-CmtBufSize
-  Input parameter which should contain size of buffer for archive
-  comments.
-
-CmtSize
-  Output parameter containing size of comments actually read into the
-  buffer, should not exceed CmtBufSize.
-
-CmtState
-  Output parameter.
-
-  Possible values
-
-  0                     Absent comments
-  1                     Comments read completely
-  ERAR_NO_MEMORY        Not enough memory to extract comments
-  ERAR_BAD_DATA         Broken comment
-  ERAR_UNKNOWN_FORMAT   Unknown comment format
-  ERAR_SMALL_BUF        Buffer too small, comments not completely read
-
-Return values
-~~~~~~~~~~~~~
-
-  0                     Success
-  ERAR_END_ARCHIVE      End of archive
-  ERAR_BAD_DATA         File header broken
-
-
-====================================================================
-int PASCAL RARReadHeaderEx(HANDLE hArcData,
-                           struct RARHeaderDataEx *HeaderData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Similar to RARReadHeader, but uses RARHeaderDataEx structure,
-containing information about Unicode file names and 64 bit file sizes.
-
-struct RARHeaderDataEx
-{
-  char         ArcName[1024];
-  wchar_t      ArcNameW[1024];
-  char         FileName[1024];
-  wchar_t      FileNameW[1024];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int PackSizeHigh;
-  unsigned int UnpSize;
-  unsigned int UnpSizeHigh;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Reserved[1024];
-};
-
-
-====================================================================
-int PASCAL RARProcessFile(HANDLE hArcData,
-                          int Operation,
-                          char *DestPath,
-                          char *DestName)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Performs action and moves the current position in the archive to 
-  the next file. Extract or test the current file from the archive 
-  opened in RAR_OM_EXTRACT mode. If the mode RAR_OM_LIST is set, 
-  then a call to this function will simply skip the archive position 
-  to the next file. 
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Operation
-  File operation.
-
-  Possible values
-
-  RAR_SKIP              Move to the next file in the archive. If the 
-                        archive is solid and RAR_OM_EXTRACT mode was set 
-                        when the archive was opened, the current file will 
-                        be processed - the operation will be performed 
-                        slower than a simple seek. 
-
-  RAR_TEST              Test the current file and move to the next file in 
-                        the archive. If the archive was opened with 
-                        RAR_OM_LIST mode, the operation is equal to 
-                        RAR_SKIP. 
-
-  RAR_EXTRACT           Extract the current file and move to the next file.
-                        If the archive was opened with RAR_OM_LIST mode,
-                        the operation is equal to RAR_SKIP.
-
-
-DestPath
-  This parameter should point to a zero terminated string containing the 
-  destination directory to which to extract files to. If DestPath is equal 
-  to NULL, it means extract to the current directory. This parameter has 
-  meaning only if DestName is NULL. 
-
-DestName
-  This parameter should point to a string containing the full path and name
-  to assign to extracted file or it can be NULL to use the default name.
-  If DestName is defined (not NULL), it overrides both the original file
-  name saved in the archive and path specigied in DestPath setting. 
-
-  Both DestPath and DestName must be in OEM encoding. If necessary,
-  use CharToOem to convert text to OEM before passing to this function.
-
-Return values
-~~~~~~~~~~~~~
-  0                     Success
-  ERAR_BAD_DATA         File CRC error
-  ERAR_BAD_ARCHIVE      Volume is not valid RAR archive
-  ERAR_UNKNOWN_FORMAT   Unknown archive format
-  ERAR_EOPEN            Volume open error
-  ERAR_ECREATE          File create error
-  ERAR_ECLOSE           File close error
-  ERAR_EREAD            Read error
-  ERAR_EWRITE           Write error
-
-
-Note: if you wish to cancel extraction, return -1 when processing
-      UCM_PROCESSDATA callback message.
-
-
-====================================================================
-int PASCAL RARProcessFileW(HANDLE hArcData,
-                           int Operation,
-                           wchar_t *DestPath,
-                           wchar_t *DestName)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Unicode version of RARProcessFile. It uses Unicode DestPath
-  and DestName parameters, other parameters and return values
-  are the same as in RARProcessFile.
-
-
-====================================================================
-void PASCAL RARSetCallback(HANDLE hArcData,
-            int PASCAL (*CallbackProc)(UINT msg,LPARAM UserData,LPARAM P1,LPARAM P2),
-            LPARAM UserData);
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Set a user-defined callback function to process Unrar events.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-CallbackProc
-  It should point to a user-defined callback function.
-
-  The function will be passed four parameters:
-
-
-  msg                    Type of event. Described below.
-
-  UserData               User defined value passed to RARSetCallback.
-
-  P1 and P2              Event dependent parameters. Described below.
-
-
-  Possible events
-
-    UCM_CHANGEVOLUME     Process volume change.
-
-      P1                   Points to the zero terminated name
-                           of the next volume.
-
-      P2                   The function call mode:
-
-        RAR_VOL_ASK          Required volume is absent. The function should
-                             prompt user and return a positive value
-                             to retry or return -1 value to terminate 
-                             operation. The function may also specify a new 
-                             volume name, placing it to the address specified
-                             by P1 parameter. 
-
-        RAR_VOL_NOTIFY       Required volume is successfully opened.
-                             This is a notification call and volume name
-                             modification is not allowed. The function should 
-                             return a positive value to continue or -1
-                             to terminate operation. 
-
-    UCM_PROCESSDATA          Process unpacked data. It may be used to read
-                             a file while it is being extracted or tested
-                             without actual extracting file to disk.
-                             Return a positive value to continue process
-                             or -1 to cancel the archive operation
-
-      P1                   Address pointing to the unpacked data.
-                           Function may refer to the data but must not
-                           change it.
-
-      P2                   Size of the unpacked data. It is guaranteed
-                           only that the size will not exceed the maximum
-                           dictionary size (4 Mb in RAR 3.0).
-
-    UCM_NEEDPASSWORD         DLL needs a password to process archive.
-                             This message must be processed if you wish
-                             to be able to handle archives with encrypted
-                             file names. It can be also used as replacement
-                             of RARSetPassword function even for usual
-                             encrypted files with non-encrypted names.
-
-      P1                   Address pointing to the buffer for a password.
-                           You need to copy a password here.
-
-      P2                   Size of the password buffer.
-
-
-UserData
-  User data passed to callback function.
-
-  Other functions of UnRAR.dll should not be called from the callback
-  function.
-
-Return values
-~~~~~~~~~~~~~
-  None
-
-
-
-====================================================================
-void PASCAL RARSetChangeVolProc(HANDLE hArcData,
-            int PASCAL (*ChangeVolProc)(char *ArcName,int Mode));
-====================================================================
-
-Obsoleted, use RARSetCallback instead.
-
-
-
-====================================================================
-void PASCAL RARSetProcessDataProc(HANDLE hArcData,
-            int PASCAL (*ProcessDataProc)(unsigned char *Addr,int Size))
-====================================================================
-
-Obsoleted, use RARSetCallback instead.
-
-
-====================================================================
-void PASCAL RARSetPassword(HANDLE hArcData,
-                           char *Password);
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Set a password to decrypt files.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Password
-  It should point to a string containing a zero terminated password.
-
-Return values
-~~~~~~~~~~~~~
-  None
-
-
-====================================================================
-void PASCAL RARGetDllVersion();
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Returns API version.
-
-Parameters
-~~~~~~~~~~
-  None.
-
-Return values
-~~~~~~~~~~~~~
-  Returns an integer value denoting UnRAR.dll API version, which is also
-defined in unrar.h as RAR_DLL_VERSION. API version number is incremented
-only in case of noticeable changes in UnRAR.dll API. Do not confuse it
-with version of UnRAR.dll stored in DLL resources, which is incremented
-with every DLL rebuild.
-
-  If RARGetDllVersion() returns a value lower than UnRAR.dll which your
-application was designed for, it may indicate that DLL version is too old
-and it will fail to provide all necessary functions to your application.
-
-  This function is absent in old versions of UnRAR.dll, so it is safer
-to use LoadLibrary and GetProcAddress to access this function.
-

UnRAR2/UnRARDLL/whatsnew.txt

@@ -1,80 +0,0 @@
-List of unrar.dll API changes. We do not include performance and reliability
-improvements into this list, but this library and RAR/UnRAR tools share
-the same source code. So the latest version of unrar.dll usually contains
-same decompression algorithm changes as the latest UnRAR version.
-============================================================================
-
---  18 January 2008
-
-all LONG parameters of CallbackProc function were changed
-to LPARAM type for 64 bit mode compatibility.
-
-
---  12 December 2007
-
-Added new RAR_OM_LIST_INCSPLIT open mode for function RAROpenArchive.
-
-
---  14 August 2007
-
-Added NoCrypt\unrar_nocrypt.dll without decryption code for those
-applications where presence of encryption or decryption code is not
-allowed because of legal restrictions.
-
-
---  14 December 2006
-
-Added ERAR_MISSING_PASSWORD error type. This error is returned
-if empty password is specified for encrypted file.
-
-
---  12 June 2003
-
-Added RARProcessFileW function, Unicode version of RARProcessFile
-
-
---  9 August 2002
-
-Added RAROpenArchiveEx function allowing to specify Unicode archive
-name and get archive flags.
-
-
---  24 January 2002
-
-Added RARReadHeaderEx function allowing to read Unicode file names
-and 64 bit file sizes.
-
-
---  23 January 2002
-
-Added ERAR_UNKNOWN error type (it is used for all errors which
-do not have special ERAR code yet) and UCM_NEEDPASSWORD callback
-message.
-
-Unrar.dll automatically opens all next volumes not only when extracting,
-but also in RAR_OM_LIST mode.
-
-
---  27 November 2001
-
-RARSetChangeVolProc and RARSetProcessDataProc are replaced by
-the single callback function installed with RARSetCallback.
-Unlike old style callbacks, the new function accepts the user defined
-parameter. Unrar.dll still supports RARSetChangeVolProc and
-RARSetProcessDataProc for compatibility purposes, but if you write
-a new application, better use RARSetCallback.
-
-File comments support is not implemented in the new DLL version yet.
-Now CmtState is always 0.
-
-
---  13 August 2001
-
-Added RARGetDllVersion function, so you may distinguish old unrar.dll,
-which used C style callback functions and the new one with PASCAL callbacks.
-
-
---  10 May 2001
-
-Callback functions in RARSetChangeVolProc and RARSetProcessDataProc
-use PASCAL style call convention now.

UnRAR2/UnRARDLL/x64/readme.txt

@@ -1 +0,0 @@
-This is x64 version of unrar.dll.

UnRAR2/__init__.py

@@ -1,177 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-"""
-pyUnRAR2 is a ctypes based wrapper around the free UnRAR.dll. 
-
-It is an modified version of Jimmy Retzlaff's pyUnRAR - more simple,
-stable and foolproof.
-Notice that it has INCOMPATIBLE interface.
-
-It enables reading and unpacking of archives created with the
-RAR/WinRAR archivers. There is a low-level interface which is very
-similar to the C interface provided by UnRAR. There is also a
-higher level interface which makes some common operations easier.
-"""
-
-__version__ = '0.99.2'
-
-try:
-    WindowsError
-    in_windows = True
-except NameError:
-    in_windows = False
-
-if in_windows:
-    from windows import RarFileImplementation
-else:
-    from unix import RarFileImplementation
-    
-    
-import fnmatch, time, weakref
-
-class RarInfo(object):
-    """Represents a file header in an archive. Don't instantiate directly.
-    Use only to obtain information about file.
-    YOU CANNOT EXTRACT FILE CONTENTS USING THIS OBJECT.
-    USE METHODS OF RarFile CLASS INSTEAD.
-
-    Properties:
-        index - index of file within the archive
-        filename - name of the file in the archive including path (if any)
-        datetime - file date/time as a struct_time suitable for time.strftime
-        isdir - True if the file is a directory
-        size - size in bytes of the uncompressed file
-        comment - comment associated with the file
-        
-    Note - this is not currently intended to be a Python file-like object.
-    """
-
-    def __init__(self, rarfile, data):
-        self.rarfile = weakref.proxy(rarfile)
-        self.index = data['index']
-        self.filename = data['filename']
-        self.isdir = data['isdir']
-        self.size = data['size']
-        self.datetime = data['datetime']
-        self.comment = data['comment']
-            
-
-
-    def __str__(self):
-        try :
-            arcName = self.rarfile.archiveName
-        except ReferenceError:
-            arcName = "[ARCHIVE_NO_LONGER_LOADED]"
-        return '<RarInfo "%s" in "%s">' % (self.filename, arcName)
-
-class RarFile(RarFileImplementation):
-
-    def __init__(self, archiveName, password=None):
-        """Instantiate the archive.
-
-        archiveName is the name of the RAR file.
-        password is used to decrypt the files in the archive.
-
-        Properties:
-            comment - comment associated with the archive
-
-        >>> print RarFile('test.rar').comment
-        This is a test.
-        """
-        self.archiveName = archiveName
-        RarFileImplementation.init(self, password)
-
-    def __del__(self):
-        self.destruct()
-
-    def infoiter(self):
-        """Iterate over all the files in the archive, generating RarInfos.
-
-        >>> import os
-        >>> for fileInArchive in RarFile('test.rar').infoiter():
-        ...     print os.path.split(fileInArchive.filename)[-1],
-        ...     print fileInArchive.isdir,
-        ...     print fileInArchive.size,
-        ...     print fileInArchive.comment,
-        ...     print tuple(fileInArchive.datetime)[0:5],
-        ...     print time.strftime('%a, %d %b %Y %H:%M', fileInArchive.datetime)
-        test True 0 None (2003, 6, 30, 1, 59) Mon, 30 Jun 2003 01:59
-        test.txt False 20 None (2003, 6, 30, 2, 1) Mon, 30 Jun 2003 02:01
-        this.py False 1030 None (2002, 2, 8, 16, 47) Fri, 08 Feb 2002 16:47
-        """
-        for params in RarFileImplementation.infoiter(self):
-            yield RarInfo(self, params)
-
-    def infolist(self):
-        """Return a list of RarInfos, descripting the contents of the archive."""
-        return list(self.infoiter())
-
-    def read_files(self, condition='*'):
-        """Read specific files from archive into memory.
-        If "condition" is a list of numbers, then return files which have those positions in infolist.
-        If "condition" is a string, then it is treated as a wildcard for names of files to extract.
-        If "condition" is a function, it is treated as a callback function, which accepts a RarInfo object 
-            and returns boolean True (extract) or False (skip).
-        If "condition" is omitted, all files are returned.
-        
-        Returns list of tuples (RarInfo info, str contents)
-        """
-        checker = condition2checker(condition)
-        return RarFileImplementation.read_files(self, checker)
-        
-
-    def extract(self,  condition='*', path='.', withSubpath=True, overwrite=True):
-        """Extract specific files from archive to disk.
-        
-        If "condition" is a list of numbers, then extract files which have those positions in infolist.
-        If "condition" is a string, then it is treated as a wildcard for names of files to extract.
-        If "condition" is a function, it is treated as a callback function, which accepts a RarInfo object
-            and returns either boolean True (extract) or boolean False (skip).
-        DEPRECATED: If "condition" callback returns string (only supported for Windows) - 
-            that string will be used as a new name to save the file under.
-        If "condition" is omitted, all files are extracted.
-        
-        "path" is a directory to extract to
-        "withSubpath" flag denotes whether files are extracted with their full path in the archive.
-        "overwrite" flag denotes whether extracted files will overwrite old ones. Defaults to true.
-        
-        Returns list of RarInfos for extracted files."""
-        checker = condition2checker(condition)
-        return RarFileImplementation.extract(self, checker, path, withSubpath, overwrite)
-
-def condition2checker(condition):
-    """Converts different condition types to callback"""
-    if type(condition) in [str, unicode]:
-        def smatcher(info):
-            return fnmatch.fnmatch(info.filename, condition)
-        return smatcher
-    elif type(condition) in [list, tuple] and type(condition[0]) in [int, long]:
-        def imatcher(info):
-            return info.index in condition
-        return imatcher
-    elif callable(condition):
-        return condition
-    else:
-        raise TypeError
-
-

UnRAR2/rar_exceptions.py

@@ -1,30 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Low level interface - see UnRARDLL\UNRARDLL.TXT
-
-
-class ArchiveHeaderBroken(Exception): pass
-class InvalidRARArchive(Exception): pass
-class FileOpenError(Exception): pass
-class IncorrectRARPassword(Exception): pass
-class InvalidRARArchiveUsage(Exception): pass

UnRAR2/test_UnRAR2.py

@@ -1,139 +0,0 @@
-import os, sys
-
-import UnRAR2
-from UnRAR2.rar_exceptions import *
-
-
-def cleanup(dir='test'):
-    for path, dirs, files in os.walk(dir):
-        for fn in files:
-            os.remove(os.path.join(path, fn))
-        for dir in dirs:
-            os.removedirs(os.path.join(path, dir))
-
-
-
-
-
-# reuse RarArchive object, en
-cleanup()
-rarc = UnRAR2.RarFile('test.rar')
-rarc.infolist()
-for info in rarc.infoiter():
-    saveinfo = info
-    assert (str(info)=="""<RarInfo "test" in "test.rar">""")
-    break
-rarc.extract()
-assert os.path.exists('test'+os.sep+'test.txt')
-assert os.path.exists('test'+os.sep+'this.py')
-del rarc
-assert (str(saveinfo)=="""<RarInfo "test" in "[ARCHIVE_NO_LONGER_LOADED]">""")
-cleanup()
-
-# extract all the files in test.rar
-cleanup()
-UnRAR2.RarFile('test.rar').extract()
-assert os.path.exists('test'+os.sep+'test.txt')
-assert os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-# extract all the files in test.rar matching the wildcard *.txt
-cleanup()
-UnRAR2.RarFile('test.rar').extract('*.txt')
-assert os.path.exists('test'+os.sep+'test.txt')
-assert not os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-
-# check the name and size of each file, extracting small ones
-cleanup()
-archive = UnRAR2.RarFile('test.rar')
-assert archive.comment == 'This is a test.'
-archive.extract(lambda rarinfo: rarinfo.size <= 1024)
-for rarinfo in archive.infoiter():
-    if rarinfo.size <= 1024 and not rarinfo.isdir:
-        assert rarinfo.size == os.stat(rarinfo.filename).st_size
-assert file('test'+os.sep+'test.txt', 'rt').read() == 'This is only a test.'
-assert not os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-
-# extract this.py, overriding it's destination
-cleanup('test2')
-archive = UnRAR2.RarFile('test.rar')
-archive.extract('*.py', 'test2', False)
-assert os.path.exists('test2'+os.sep+'this.py')
-cleanup('test2')
-
-
-# extract test.txt to memory
-cleanup()
-archive = UnRAR2.RarFile('test.rar')
-entries = UnRAR2.RarFile('test.rar').read_files('*test.txt')
-assert len(entries)==1
-assert entries[0][0].filename.endswith('test.txt')
-assert entries[0][1]=='This is only a test.'
-
-
-# extract all the files in test.rar with overwriting
-cleanup()
-fo = open('test'+os.sep+'test.txt',"wt")
-fo.write("blah")
-fo.close()
-UnRAR2.RarFile('test.rar').extract('*.txt')
-assert open('test'+os.sep+'test.txt',"rt").read()!="blah"
-cleanup()
-
-# extract all the files in test.rar without overwriting
-cleanup()
-fo = open('test'+os.sep+'test.txt',"wt")
-fo.write("blahblah")
-fo.close()
-UnRAR2.RarFile('test.rar').extract('*.txt', overwrite = False)
-assert open('test'+os.sep+'test.txt',"rt").read()=="blahblah"
-cleanup()
-
-# list big file in an archive
-list(UnRAR2.RarFile('test_nulls.rar').infoiter())
-
-# extract files from an archive with protected files
-cleanup()
-UnRAR2.RarFile('test_protected_files.rar', password="protected").extract()
-assert os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-cleanup()
-errored = False
-try:
-    UnRAR2.RarFile('test_protected_files.rar', password="proteqted").extract()
-except IncorrectRARPassword:
-    errored = True
-assert not os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-assert errored
-cleanup()
-
-# extract files from an archive with protected headers
-cleanup()
-UnRAR2.RarFile('test_protected_headers.rar', password="secret").extract()
-assert os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-cleanup()
-errored = False
-try:
-    UnRAR2.RarFile('test_protected_headers.rar', password="seqret").extract()
-except IncorrectRARPassword:
-    errored = True
-assert not os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-assert errored
-cleanup()
-
-# make sure docstring examples are working
-import doctest
-doctest.testmod(UnRAR2)
-
-# update documentation
-import pydoc
-pydoc.writedoc(UnRAR2)
-
-# cleanup
-try:
-    os.remove('__init__.pyc')
-except:
-    pass

UnRAR2/unix.py

@@ -1,175 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Unix version uses unrar command line executable
-
-import subprocess
-import gc
-
-import os, os.path
-import time, re
-
-from rar_exceptions import *
-
-class UnpackerNotInstalled(Exception): pass
-
-rar_executable_cached = None
-
-def call_unrar(params):
-    "Calls rar/unrar command line executable, returns stdout pipe"
-    global rar_executable_cached
-    if rar_executable_cached is None:
-        for command in ('unrar', 'rar'):
-            try:
-                subprocess.Popen([command], stdout=subprocess.PIPE)
-                rar_executable_cached = command
-                break
-            except OSError:
-                pass
-        if rar_executable_cached is None:
-            raise UnpackerNotInstalled("No suitable RAR unpacker installed")
-            
-    assert type(params) == list, "params must be list"
-    args = [rar_executable_cached] + params
-    try:
-        gc.disable() # See http://bugs.python.org/issue1336
-        return subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-    finally:
-        gc.enable()
-
-class RarFileImplementation(object):
-
-    def init(self, password=None):
-        self.password = password
-        
-        
-
-        stdoutdata, stderrdata = self.call('v', []).communicate()
-        
-        for line in stderrdata.splitlines():
-            if line.strip().startswith("Cannot open"):
-                raise FileOpenError
-            if line.find("CRC failed")>=0:
-                raise IncorrectRARPassword   
-        accum = []
-        source = iter(stdoutdata.splitlines())
-        line = ''
-        while not (line.startswith('Comment:') or line.startswith('Pathname/Comment')):
-            if line.strip().endswith('is not RAR archive'):
-                raise InvalidRARArchive
-            line = source.next()
-        while not line.startswith('Pathname/Comment'):
-            accum.append(line.rstrip('\n'))
-            line = source.next()
-        if len(accum):
-            accum[0] = accum[0][9:]
-            self.comment = '\n'.join(accum[:-1])
-        else:
-            self.comment = None
-                
-    def escaped_password(self):
-        return '-' if self.password == None else self.password
-        
-        
-    def call(self, cmd, options=[], files=[]):
-        options2 = options + ['p'+self.escaped_password()]
-        soptions = ['-'+x for x in options2]
-        return call_unrar([cmd]+soptions+['--',self.archiveName]+files)
-
-    def infoiter(self):
-        
-        stdoutdata, stderrdata = self.call('v', ['c-']).communicate()
-        
-        for line in stderrdata.splitlines():
-            if line.strip().startswith("Cannot open"):
-                raise FileOpenError
-            
-        accum = []
-        source = iter(stdoutdata.splitlines())
-        line = ''
-        while not line.startswith('--------------'):
-            if line.strip().endswith('is not RAR archive'):
-                raise InvalidRARArchive
-            if line.find("CRC failed")>=0:
-                raise IncorrectRARPassword  
-            line = source.next()
-        line = source.next()
-        i = 0
-        re_spaces = re.compile(r"\s+")
-        while not line.startswith('--------------'):
-            accum.append(line)
-            if len(accum)==2:
-                data = {}
-                data['index'] = i
-                data['filename'] = accum[0].strip()
-                info = re_spaces.split(accum[1].strip())
-                data['size'] = int(info[0])
-                attr = info[5]
-                data['isdir'] = 'd' in attr.lower()
-                data['datetime'] = time.strptime(info[3]+" "+info[4], '%d-%m-%y %H:%M')
-                data['comment'] = None
-                yield data
-                accum = []
-                i += 1
-            line = source.next()
-
-    def read_files(self, checker):
-        res = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if checkres==True and not info.isdir:
-                pipe = self.call('p', ['inul'], [info.filename]).stdout
-                res.append((info, pipe.read()))
-        return res            
-
-          
-    def extract(self, checker, path, withSubpath, overwrite):
-        res = []
-        command = 'x'
-        if not withSubpath:
-            command = 'e'
-        options = []
-        if overwrite:
-            options.append('o+')
-        else:
-			options.append('o-')
-        if not path.endswith(os.sep):
-            path += os.sep
-        names = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if type(checkres) in [str, unicode]:
-                raise NotImplementedError("Condition callbacks returning strings are deprecated and only supported in Windows")
-            if checkres==True and not info.isdir:
-                names.append(info.filename)
-                res.append(info)
-        names.append(path)
-        proc = self.call(command, options, names)
-        stdoutdata, stderrdata = proc.communicate()
-        if stderrdata.find("CRC failed")>=0:
-            raise IncorrectRARPassword  
-        return res            
-            
-    def destruct(self):
-        pass
-
-    

UnRAR2/windows.py

@@ -1,309 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Low level interface - see UnRARDLL\UNRARDLL.TXT
-
-from __future__ import generators
-
-import ctypes, ctypes.wintypes
-import os, os.path, sys
-import Queue
-import time
-
-from rar_exceptions import *
-
-ERAR_END_ARCHIVE = 10
-ERAR_NO_MEMORY = 11
-ERAR_BAD_DATA = 12
-ERAR_BAD_ARCHIVE = 13
-ERAR_UNKNOWN_FORMAT = 14
-ERAR_EOPEN = 15
-ERAR_ECREATE = 16
-ERAR_ECLOSE = 17
-ERAR_EREAD = 18
-ERAR_EWRITE = 19
-ERAR_SMALL_BUF = 20
-ERAR_UNKNOWN = 21
-
-RAR_OM_LIST = 0
-RAR_OM_EXTRACT = 1
-
-RAR_SKIP = 0
-RAR_TEST = 1
-RAR_EXTRACT = 2
-
-RAR_VOL_ASK = 0
-RAR_VOL_NOTIFY = 1
-
-RAR_DLL_VERSION = 3
-
-# enum UNRARCALLBACK_MESSAGES
-UCM_CHANGEVOLUME = 0
-UCM_PROCESSDATA = 1
-UCM_NEEDPASSWORD = 2
-
-architecture_bits = ctypes.sizeof(ctypes.c_voidp)*8
-dll_name = "unrar.dll"
-if architecture_bits == 64:
-    dll_name = "x64\\unrar64.dll"
-    
-    
-try:
-    unrar = ctypes.WinDLL(os.path.join(os.path.split(__file__)[0], 'UnRARDLL', dll_name))
-except WindowsError:
-    unrar = ctypes.WinDLL(dll_name)
-
-
-class RAROpenArchiveDataEx(ctypes.Structure):
-    def __init__(self, ArcName=None, ArcNameW=u'', OpenMode=RAR_OM_LIST):
-        self.CmtBuf = ctypes.c_buffer(64*1024)
-        ctypes.Structure.__init__(self, ArcName=ArcName, ArcNameW=ArcNameW, OpenMode=OpenMode, _CmtBuf=ctypes.addressof(self.CmtBuf), CmtBufSize=ctypes.sizeof(self.CmtBuf))
-
-    _fields_ = [
-                ('ArcName', ctypes.c_char_p),
-                ('ArcNameW', ctypes.c_wchar_p),
-                ('OpenMode', ctypes.c_uint),
-                ('OpenResult', ctypes.c_uint),
-                ('_CmtBuf', ctypes.c_voidp),
-                ('CmtBufSize', ctypes.c_uint),
-                ('CmtSize', ctypes.c_uint),
-                ('CmtState', ctypes.c_uint),
-                ('Flags', ctypes.c_uint),
-                ('Reserved', ctypes.c_uint*32),
-               ]
-
-class RARHeaderDataEx(ctypes.Structure):
-    def __init__(self):
-        self.CmtBuf = ctypes.c_buffer(64*1024)
-        ctypes.Structure.__init__(self, _CmtBuf=ctypes.addressof(self.CmtBuf), CmtBufSize=ctypes.sizeof(self.CmtBuf))
-
-    _fields_ = [
-                ('ArcName', ctypes.c_char*1024),
-                ('ArcNameW', ctypes.c_wchar*1024),
-                ('FileName', ctypes.c_char*1024),
-                ('FileNameW', ctypes.c_wchar*1024),
-                ('Flags', ctypes.c_uint),
-                ('PackSize', ctypes.c_uint),
-                ('PackSizeHigh', ctypes.c_uint),
-                ('UnpSize', ctypes.c_uint),
-                ('UnpSizeHigh', ctypes.c_uint),
-                ('HostOS', ctypes.c_uint),
-                ('FileCRC', ctypes.c_uint),
-                ('FileTime', ctypes.c_uint),
-                ('UnpVer', ctypes.c_uint),
-                ('Method', ctypes.c_uint),
-                ('FileAttr', ctypes.c_uint),
-                ('_CmtBuf', ctypes.c_voidp),
-                ('CmtBufSize', ctypes.c_uint),
-                ('CmtSize', ctypes.c_uint),
-                ('CmtState', ctypes.c_uint),
-                ('Reserved', ctypes.c_uint*1024),
-               ]
-
-def DosDateTimeToTimeTuple(dosDateTime):
-    """Convert an MS-DOS format date time to a Python time tuple.
-    """
-    dosDate = dosDateTime >> 16
-    dosTime = dosDateTime & 0xffff
-    day = dosDate & 0x1f
-    month = (dosDate >> 5) & 0xf
-    year = 1980 + (dosDate >> 9)
-    second = 2*(dosTime & 0x1f)
-    minute = (dosTime >> 5) & 0x3f
-    hour = dosTime >> 11
-    return time.localtime(time.mktime((year, month, day, hour, minute, second, 0, 1, -1)))
-
-def _wrap(restype, function, argtypes):
-    result = function
-    result.argtypes = argtypes
-    result.restype = restype
-    return result
-
-RARGetDllVersion = _wrap(ctypes.c_int, unrar.RARGetDllVersion, [])
-
-RAROpenArchiveEx = _wrap(ctypes.wintypes.HANDLE, unrar.RAROpenArchiveEx, [ctypes.POINTER(RAROpenArchiveDataEx)])
-
-RARReadHeaderEx = _wrap(ctypes.c_int, unrar.RARReadHeaderEx, [ctypes.wintypes.HANDLE, ctypes.POINTER(RARHeaderDataEx)])
-
-_RARSetPassword = _wrap(ctypes.c_int, unrar.RARSetPassword, [ctypes.wintypes.HANDLE, ctypes.c_char_p])
-def RARSetPassword(*args, **kwargs):
-    _RARSetPassword(*args, **kwargs)
-
-RARProcessFile = _wrap(ctypes.c_int, unrar.RARProcessFile, [ctypes.wintypes.HANDLE, ctypes.c_int, ctypes.c_char_p, ctypes.c_char_p])
-
-RARCloseArchive = _wrap(ctypes.c_int, unrar.RARCloseArchive, [ctypes.wintypes.HANDLE])
-
-UNRARCALLBACK = ctypes.WINFUNCTYPE(ctypes.c_int, ctypes.c_uint, ctypes.c_long, ctypes.c_long, ctypes.c_long)
-RARSetCallback = _wrap(ctypes.c_int, unrar.RARSetCallback, [ctypes.wintypes.HANDLE, UNRARCALLBACK, ctypes.c_long])
-
-
-
-RARExceptions = {
-                 ERAR_NO_MEMORY : MemoryError,
-                 ERAR_BAD_DATA : ArchiveHeaderBroken,
-                 ERAR_BAD_ARCHIVE : InvalidRARArchive,
-                 ERAR_EOPEN : FileOpenError,
-                }
-
-class PassiveReader:
-    """Used for reading files to memory"""
-    def __init__(self, usercallback = None):
-        self.buf = []
-        self.ucb = usercallback
-    
-    def _callback(self, msg, UserData, P1, P2):
-        if msg == UCM_PROCESSDATA:
-            data = (ctypes.c_char*P2).from_address(P1).raw
-            if self.ucb!=None:
-                self.ucb(data)
-            else:
-                self.buf.append(data)
-        return 1
-    
-    def get_result(self):
-        return ''.join(self.buf)
-
-class RarInfoIterator(object):
-    def __init__(self, arc):
-        self.arc = arc
-        self.index = 0
-        self.headerData = RARHeaderDataEx()
-        self.res = RARReadHeaderEx(self.arc._handle, ctypes.byref(self.headerData))
-        if self.res==ERAR_BAD_DATA:
-            raise IncorrectRARPassword
-        self.arc.lockStatus = "locked"
-        self.arc.needskip = False
-        
-    def __iter__(self):
-        return self
-        
-    def next(self):
-        if self.index>0:
-            if self.arc.needskip:
-                RARProcessFile(self.arc._handle, RAR_SKIP, None, None)
-            self.res = RARReadHeaderEx(self.arc._handle, ctypes.byref(self.headerData))
-
-        if self.res:
-            raise StopIteration 
-        self.arc.needskip = True
-        
-        data = {}
-        data['index'] = self.index
-        data['filename'] = self.headerData.FileName
-        data['datetime'] = DosDateTimeToTimeTuple(self.headerData.FileTime)
-        data['isdir'] = ((self.headerData.Flags & 0xE0) == 0xE0)
-        data['size'] = self.headerData.UnpSize + (self.headerData.UnpSizeHigh << 32)
-        if self.headerData.CmtState == 1:
-            data['comment'] = self.headerData.CmtBuf.value
-        else:
-            data['comment'] = None
-        self.index += 1
-        return data
-
-            
-    def __del__(self):
-        self.arc.lockStatus = "finished"
-
-def generate_password_provider(password):
-    def password_provider_callback(msg, UserData, P1, P2):
-        if msg == UCM_NEEDPASSWORD and password!=None:
-            (ctypes.c_char*P2).from_address(P1).value = password
-        return 1
-    return password_provider_callback
-
-class RarFileImplementation(object):
-
-    def init(self, password=None):
-        self.password = password
-        archiveData = RAROpenArchiveDataEx(ArcNameW=self.archiveName, OpenMode=RAR_OM_EXTRACT)
-        self._handle = RAROpenArchiveEx(ctypes.byref(archiveData))
-        self.c_callback = UNRARCALLBACK(generate_password_provider(self.password))
-        RARSetCallback(self._handle, self.c_callback, 1)
-
-        if archiveData.OpenResult != 0:
-            raise RARExceptions[archiveData.OpenResult]
-
-        if archiveData.CmtState == 1:
-            self.comment = archiveData.CmtBuf.value
-        else:
-            self.comment = None
-
-        if password:
-            RARSetPassword(self._handle, password)
-            
-        self.lockStatus = "ready"
-            
-
-
-    def destruct(self):
-        if self._handle and RARCloseArchive:
-            RARCloseArchive(self._handle)
-
-    def make_sure_ready(self):
-        if self.lockStatus == "locked":
-            raise InvalidRARArchiveUsage("cannot execute infoiter() without finishing previous one")
-        if self.lockStatus == "finished":
-            self.destruct()
-            self.init(self.password)
-
-    def infoiter(self):
-        self.make_sure_ready()
-        return RarInfoIterator(self)
-
-    def read_files(self, checker):
-        res = []
-        for info in self.infoiter():
-            if checker(info) and not info.isdir:
-                reader = PassiveReader()
-                c_callback = UNRARCALLBACK(reader._callback)
-                RARSetCallback(self._handle, c_callback, 1)
-                tmpres = RARProcessFile(self._handle, RAR_TEST, None, None)
-                if tmpres==ERAR_BAD_DATA:
-                    raise IncorrectRARPassword
-                self.needskip = False
-                res.append((info, reader.get_result()))
-        return res
-        
-
-    def extract(self,  checker, path, withSubpath, overwrite):
-        res = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if checkres!=False and not info.isdir:
-                if checkres==True:
-                    fn = info.filename
-                    if not withSubpath:
-                        fn = os.path.split(fn)[-1]
-                    target = os.path.join(path, fn)
-                else:
-                    raise DeprecationWarning, "Condition callbacks returning strings are deprecated and only supported in Windows"                    
-                    target = checkres
-                if overwrite or (not os.path.exists(target)):
-                    tmpres = RARProcessFile(self._handle, RAR_EXTRACT, None, target)
-                    if tmpres==ERAR_BAD_DATA:
-                        raise IncorrectRARPassword
-
-                self.needskip = False
-                res.append(info)
-        return res
-
-

autotagmatchwindow.py

@@ -1,202 +0,0 @@
-"""
-A PyQT4 dialog to select from automated issue matches
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-import sys
-import os
-from PyQt4 import QtCore, QtGui, uic
-
-from PyQt4.QtCore import QUrl, pyqtSignal, QByteArray
-
-from imagefetcher import  ImageFetcher
-from settings import ComicTaggerSettings
-
-class AutoTagMatchWindow(QtGui.QDialog):
-	
-	volume_id = 0
-	
-	def __init__(self, parent, match_set_list, style, fetch_func):
-		super(AutoTagMatchWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagmatchwindow.ui' ), self)
-
-		self.skipButton = QtGui.QPushButton(self.tr("Skip"))
-		self.buttonBox.addButton(self.skipButton, QtGui.QDialogButtonBox.ActionRole)		
-		self.buttonBox.button(QtGui.QDialogButtonBox.Ok).setText("Accept and Next")		
-
-		self.match_set_list = match_set_list
-		self.style = style
-		self.fetch_func = fetch_func
-
-		self.current_match_set_idx = 0
-		
-		self.twList.currentItemChanged.connect(self.currentItemChanged)	
-		self.twList.cellDoubleClicked.connect(self.cellDoubleClicked)
-		self.skipButton.clicked.connect(self.skipToNext)
-		
-		self.updateData()		
-
-	def updateData( self):
-
-		self.current_match_set = self.match_set_list[ self.current_match_set_idx ]
-
-
-		if self.current_match_set_idx + 1 == len( self.match_set_list ):
-			self.skipButton.setDisabled(True)
-			
-		self.setCoverImage()
-		self.populateTable()
-		self.twList.resizeColumnsToContents()	
-		self.current_row = 0
-		self.twList.selectRow( 0 )
-		
-		path = self.current_match_set.ca.path
-		self.setWindowTitle( "Select correct match ({0} of {1}): {2}".format(
-						self.current_match_set_idx+1,
-						len( self.match_set_list ),
-						os.path.split(path)[1] ))
-		
-	def populateTable( self  ):
-
-		while self.twList.rowCount() > 0:
-			self.twList.removeRow(0)
-		
-		self.twList.setSortingEnabled(False)
-
-		row = 0
-		for match in self.current_match_set.matches: 
-			self.twList.insertRow(row)
-			
-			item_text = match['series']  
-			item = QtGui.QTableWidgetItem(item_text)			
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 0, item)
-
-			if match['publisher'] is not None:
-				item_text = u"{0}".format(match['publisher'])
-			else:
-				item_text = u"Unknown"
-			item = QtGui.QTableWidgetItem(item_text)
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 1, item)
-			
-			item_text = ""
-			if match['month'] is not None:
-				item_text = u"{0}/".format(match['month'])
-			if match['year'] is not None:
-				item_text += u"{0}".format(match['year'])
-			else:
-				item_text += u"????"
-			item = QtGui.QTableWidgetItem(item_text)			
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 2, item)
-			
-			row += 1
-			
-
-	def cellDoubleClicked( self, r, c ):
-		self.accept()
-			
-	def currentItemChanged( self, curr, prev ):
-
-		if curr is None:
-			return
-		if prev is not None and prev.row() == curr.row():
-				return
-
-		self.current_row = curr.row()
-		
-		# list selection was changed, update the the issue cover				
-		self.labelThumbnail.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-				
-		self.cover_fetcher = ImageFetcher( )
-		self.cover_fetcher.fetchComplete.connect(self.coverFetchComplete)
-		self.cover_fetcher.fetch( self.current_match_set.matches[self.current_row]['img_url'] )
-				
-	# called when the image is done loading
-	def coverFetchComplete( self, image_data, issue_id ):
-		img = QtGui.QImage()
-		img.loadFromData( image_data )
-		self.labelThumbnail.setPixmap(QtGui.QPixmap(img))
-		
-	def setCoverImage( self ):
-		ca = self.current_match_set.ca
-		cover_idx = ca.readMetadata(self.style).getCoverPageIndexList()[0]
-		image_data = ca.getPage( cover_idx )		
-		self.labelCover.setScaledContents(True)
-		if image_data is not None:
-			img = QtGui.QImage()
-			img.loadFromData( image_data )
-			self.labelCover.setPixmap(QtGui.QPixmap(img))
-		else:
-			self.labelCover.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-
-	def accept(self):
-
-		self.saveMatch()
-		self.current_match_set_idx += 1
-		
-		if self.current_match_set_idx == len( self.match_set_list ):
-			# no more items
-			QtGui.QDialog.accept(self)				
-		else:
-			self.updateData()
-
-	def skipToNext( self ):
-		self.current_match_set_idx += 1
-		
-		if self.current_match_set_idx == len( self.match_set_list ):
-			# no more items
-			QtGui.QDialog.reject(self)				
-		else:
-			self.updateData()
-		
-	def reject(self):
-		reply = QtGui.QMessageBox.question(self, 
-			 self.tr("Cancel Matching"), 
-			 self.tr("Are you sure you wish to cancel the matching process?"),
-			 QtGui.QMessageBox.Yes, QtGui.QMessageBox.No )
-			 
-		if reply == QtGui.QMessageBox.No:
-			return
-
-		QtGui.QDialog.reject(self)				
-			
-	def saveMatch( self ):
-		
-		match = self.current_match_set.matches[self.current_row]
-		ca = self.current_match_set.ca
-
-		md = ca.readMetadata( self.style )
-		if md.isEmpty:
-			md = ca.metadataFromFilename()		
-		
-		# now get the particular issue data
-		cv_md = self.fetch_func( match )
-		if cv_md is None:
-			QtGui.QMessageBox.critical(self, self.tr("Network Issue"), self.tr("Could not connect to ComicVine to get issue details!"))
-			return
-
-		QtGui.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.WaitCursor))			
-		md.overlay( cv_md )
-		success = ca.writeMetadata( md, self.style )
-		QtGui.QApplication.restoreOverrideCursor()
-		
-		if not success:		
-			QtGui.QMessageBox.warning(self, self.tr("Write Error"), self.tr("Saving the tags to the archive seemed to fail!"))

autotagmatchwindow.ui

@@ -1,161 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<ui version="4.0">
- <class>dialogMatchSelect</class>
- <widget class="QDialog" name="dialogMatchSelect">
-  <property name="geometry">
-   <rect>
-    <x>0</x>
-    <y>0</y>
-    <width>831</width>
-    <height>506</height>
-   </rect>
-  </property>
-  <property name="windowTitle">
-   <string>Select Match</string>
-  </property>
-  <layout class="QGridLayout" name="gridLayout">
-   <item row="0" column="1">
-    <layout class="QVBoxLayout" name="verticalLayout">
-     <item>
-      <layout class="QHBoxLayout" name="horizontalLayout">
-       <item>
-        <widget class="QLabel" name="labelCover">
-         <property name="minimumSize">
-          <size>
-           <width>200</width>
-           <height>0</height>
-          </size>
-         </property>
-         <property name="maximumSize">
-          <size>
-           <width>200</width>
-           <height>300</height>
-          </size>
-         </property>
-         <property name="text">
-          <string>TextLabel</string>
-         </property>
-        </widget>
-       </item>
-       <item>
-        <widget class="QTableWidget" name="twList">
-         <property name="font">
-          <font>
-           <pointsize>9</pointsize>
-          </font>
-         </property>
-         <property name="selectionMode">
-          <enum>QAbstractItemView::SingleSelection</enum>
-         </property>
-         <property name="selectionBehavior">
-          <enum>QAbstractItemView::SelectRows</enum>
-         </property>
-         <property name="rowCount">
-          <number>0</number>
-         </property>
-         <property name="columnCount">
-          <number>3</number>
-         </property>
-         <attribute name="horizontalHeaderStretchLastSection">
-          <bool>true</bool>
-         </attribute>
-         <attribute name="verticalHeaderVisible">
-          <bool>false</bool>
-         </attribute>
-         <column>
-          <property name="text">
-           <string>Series</string>
-          </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Publisher</string>
-          </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Date</string>
-          </property>
-         </column>
-        </widget>
-       </item>
-       <item>
-        <widget class="QLabel" name="labelThumbnail">
-         <property name="minimumSize">
-          <size>
-           <width>200</width>
-           <height>0</height>
-          </size>
-         </property>
-         <property name="maximumSize">
-          <size>
-           <width>200</width>
-           <height>300</height>
-          </size>
-         </property>
-         <property name="frameShape">
-          <enum>QFrame::Panel</enum>
-         </property>
-         <property name="frameShadow">
-          <enum>QFrame::Sunken</enum>
-         </property>
-         <property name="text">
-          <string/>
-         </property>
-         <property name="scaledContents">
-          <bool>true</bool>
-         </property>
-        </widget>
-       </item>
-      </layout>
-     </item>
-     <item>
-      <widget class="QDialogButtonBox" name="buttonBox">
-       <property name="orientation">
-        <enum>Qt::Horizontal</enum>
-       </property>
-       <property name="standardButtons">
-        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
-       </property>
-      </widget>
-     </item>
-    </layout>
-   </item>
-  </layout>
- </widget>
- <resources/>
- <connections>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>accepted()</signal>
-   <receiver>dialogMatchSelect</receiver>
-   <slot>accept()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>248</x>
-     <y>254</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>157</x>
-     <y>274</y>
-    </hint>
-   </hints>
-  </connection>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>rejected()</signal>
-   <receiver>dialogMatchSelect</receiver>
-   <slot>reject()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>316</x>
-     <y>260</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>286</x>
-     <y>274</y>
-    </hint>
-   </hints>
-  </connection>
- </connections>
-</ui>

autotagprogresswindow.py

@@ -1,67 +0,0 @@
-"""
-A PyQT4 dialog to show ID log and progress
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-import sys
-from PyQt4 import QtCore, QtGui, uic
-import os
-from settings import ComicTaggerSettings
-
-
-class AutoTagProgressWindow(QtGui.QDialog):
-	
-	
-	def __init__(self, parent):
-		super(AutoTagProgressWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagprogresswindow.ui' ), self)
-		self.lblTest.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-		self.lblArchive.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-		self.isdone = False
-		
-		# we can't specify relative font sizes in the UI designer, so
-		# make font for scroll window a smidge smaller
-		f = self.textEdit.font()
-		if f.pointSize() > 10:
-			f.setPointSize( f.pointSize() - 2 )
-		self.textEdit.setFont( f )		
-		
-	def setArchiveImage( self, img_data):
-		self.setCoverImage( img_data, self.lblArchive )
-
-	def setTestImage( self, img_data):
-		self.setCoverImage( img_data, self.lblTest )
-
-	def setCoverImage( self, img_data , label):
-		if img_data is not None:
-			img = QtGui.QImage()
-			img.loadFromData( img_data )
-			label.setPixmap(QtGui.QPixmap(img))
-			label.setScaledContents(True)
-		else:
-			label.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-			label.setScaledContents(True)
-		QtCore.QCoreApplication.processEvents()
-		QtCore.QCoreApplication.processEvents()
-			
-	def reject(self):
-		QtGui.QDialog.reject(self)		
-		self.isdone = True
-
-		

autotagstartwindow.py

@@ -1,55 +0,0 @@
-"""
-A PyQT4 dialog to confirm and set options for auto-tag
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-
-from PyQt4 import QtCore, QtGui, uic
-from settings import ComicTaggerSettings
-from settingswindow import SettingsWindow
-from filerenamer import FileRenamer
-import os
-import utils
-
-	
-class AutoTagStartWindow(QtGui.QDialog):
-		
-	def __init__( self, parent,  settings, msg ):
-		super(AutoTagStartWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagstartwindow.ui' ), self)
-		self.label.setText( msg )
-
-		self.settings = settings
-		
-		self.cbxSaveOnLowConfidence.setCheckState( QtCore.Qt.Unchecked )
-		self.cbxDontUseYear.setCheckState( QtCore.Qt.Unchecked )
-		self.cbxAssumeIssueOne.setCheckState( QtCore.Qt.Unchecked )
-		
-		self.autoSaveOnLow = False
-		self.dontUseYear = False
-		self.assumeIssueOne = False
-
-
-	def accept( self ):
-		QtGui.QDialog.accept(self)		
-
-		self.autoSaveOnLow = self.cbxSaveOnLowConfidence.isChecked()
-		self.dontUseYear = self.cbxDontUseYear.isChecked()
-		self.assumeIssueOne = self.cbxAssumeIssueOne.isChecked()
-	

autotagstartwindow.ui

@@ -1,124 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<ui version="4.0">
- <class>dialogExport</class>
- <widget class="QDialog" name="dialogExport">
-  <property name="windowModality">
-   <enum>Qt::NonModal</enum>
-  </property>
-  <property name="geometry">
-   <rect>
-    <x>0</x>
-    <y>0</y>
-    <width>524</width>
-    <height>248</height>
-   </rect>
-  </property>
-  <property name="windowTitle">
-   <string>Auto-Tag</string>
-  </property>
-  <property name="modal">
-   <bool>false</bool>
-  </property>
-  <layout class="QGridLayout" name="gridLayout_3">
-   <item row="0" column="0">
-    <layout class="QVBoxLayout" name="verticalLayout">
-     <item>
-      <widget class="QLabel" name="label">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
-       </property>
-       <property name="text">
-        <string/>
-       </property>
-       <property name="wordWrap">
-        <bool>true</bool>
-       </property>
-      </widget>
-     </item>
-     <item>
-      <layout class="QFormLayout" name="formLayout">
-       <property name="fieldGrowthPolicy">
-        <enum>QFormLayout::AllNonFixedFieldsGrow</enum>
-       </property>
-       <item row="1" column="1">
-        <widget class="QCheckBox" name="cbxDontUseYear">
-         <property name="text">
-          <string>Don't use publication year in indentification process</string>
-         </property>
-        </widget>
-       </item>
-       <item row="0" column="1">
-        <widget class="QCheckBox" name="cbxSaveOnLowConfidence">
-         <property name="sizePolicy">
-          <sizepolicy hsizetype="Minimum" vsizetype="Preferred">
-           <horstretch>0</horstretch>
-           <verstretch>0</verstretch>
-          </sizepolicy>
-         </property>
-         <property name="text">
-          <string>Save on low confidence match</string>
-         </property>
-        </widget>
-       </item>
-       <item row="2" column="1">
-        <widget class="QCheckBox" name="cbxAssumeIssueOne">
-         <property name="text">
-          <string>If no issue number, assume &quot;1&quot;</string>
-         </property>
-        </widget>
-       </item>
-      </layout>
-     </item>
-     <item>
-      <widget class="QDialogButtonBox" name="buttonBox">
-       <property name="orientation">
-        <enum>Qt::Horizontal</enum>
-       </property>
-       <property name="standardButtons">
-        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
-       </property>
-      </widget>
-     </item>
-    </layout>
-   </item>
-  </layout>
- </widget>
- <resources/>
- <connections>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>accepted()</signal>
-   <receiver>dialogExport</receiver>
-   <slot>accept()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>346</x>
-     <y>187</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>277</x>
-     <y>104</y>
-    </hint>
-   </hints>
-  </connection>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>rejected()</signal>
-   <receiver>dialogExport</receiver>
-   <slot>reject()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>346</x>
-     <y>187</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>277</x>
-     <y>104</y>
-    </hint>
-   </hints>
-  </connection>
- </connections>
-</ui>

cbltransformer.py

@@ -1,99 +0,0 @@
-"""
-Class to manage modifying metadata specifically for CBL/CBI
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-import os
-import utils
-
-
-class CBLTransformer:
-	def __init__( self, metadata, settings ):
-		self.metadata = metadata
-		self.settings = settings
-
-	
-	def apply( self ):
-		# helper funcs
-		def append_to_tags_if_unique( item ):
-			if item.lower() not in (tag.lower() for tag in self.metadata.tags):
-				self.metadata.tags.append( item )
-				
-		def add_string_list_to_tags( str_list ):
-			if str_list is not None and str_list != "":
-				items = [ s.strip() for s in str_list.split(',') ]
-				for item in items:
-					append_to_tags_if_unique( item )
-
-		if self.settings.assume_lone_credit_is_primary:
-		
-			# helper
-			def setLonePrimary( role_list ):
-				lone_credit = None
-				count = 0
-				for c in self.metadata.credits:
-					if c['role'].lower() in role_list:
-						count += 1
-						lone_credit = c
-					if count > 1:
-						lone_credit = None
-						break
-				if lone_credit is not None:
-					lone_credit['primary'] = True
-				return lone_credit, count
-				
-			#need to loop three times, once for 'writer', 'artist', and then 'penciler' if no artist
-			setLonePrimary( ['writer'] )
-			c, count = setLonePrimary( ['artist'] )
-			if c is None and count == 0:
-				c, count = setLonePrimary( ['penciler', 'penciller'] )
-				if c is not None:
-					c['primary'] = False
-					self.metadata.addCredit( c['person'], 'Artist', True )		
-
-		if self.settings.copy_characters_to_tags:
-			add_string_list_to_tags( self.metadata.characters )
-
-		if self.settings.copy_teams_to_tags:
-			add_string_list_to_tags( self.metadata.teams )
-			
-		if self.settings.copy_locations_to_tags:
-			add_string_list_to_tags( self.metadata.locations )
-			
-		if self.settings.copy_notes_to_comments:
-			if self.metadata.notes is not None:
-				if self.metadata.comments is None:
-					self.metadata.comments = ""
-				else:
-					self.metadata.comments += "\n\n"
-				if self.metadata.notes not in self.metadata.comments:
-					self.metadata.comments += self.metadata.notes
-
-		if self.settings.copy_weblink_to_comments:
-			if self.metadata.webLink is not None:
-				if self.metadata.comments is None:
-					self.metadata.comments = ""
-				else:
-					self.metadata.comments += "\n\n"
-				if self.metadata.webLink not in self.metadata.comments:
-					self.metadata.comments += self.metadata.webLink
-
-		return self.metadata
-
-	
-	

comet.py

@@ -1,260 +0,0 @@
-"""
-A python class to encapsulate CoMet data 
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-from datetime import datetime
-import zipfile
-from pprint import pprint 
-import xml.etree.ElementTree as ET
-from genericmetadata import GenericMetadata
-import utils
-
-class CoMet:
-	
-	writer_synonyms = ['writer', 'plotter', 'scripter']
-	penciller_synonyms = [ 'artist', 'penciller', 'penciler', 'breakdowns' ]
-	inker_synonyms = [ 'inker', 'artist', 'finishes' ]
-	colorist_synonyms = [ 'colorist', 'colourist', 'colorer', 'colourer' ]
-	letterer_synonyms = [ 'letterer']
-	cover_synonyms = [ 'cover', 'covers', 'coverartist', 'cover artist' ]
-	editor_synonyms = [ 'editor']
-		
-	def metadataFromString( self, string ):
-
-		tree = ET.ElementTree(ET.fromstring( string ))
-		return self.convertXMLToMetadata( tree )
-
-	def stringFromMetadata( self, metadata ):
-
-		header = '<?xml version="1.0" encoding="UTF-8"?>\n'
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		return header + ET.tostring(tree.getroot())
-
-	def indent( self, elem, level=0 ):
-		# for making the XML output readable
-		i = "\n" + level*"  "
-		if len(elem):
-			if not elem.text or not elem.text.strip():
-				elem.text = i + "  "
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-			for elem in elem:
-				self.indent( elem, level+1 )
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-		else:
-			if level and (not elem.tail or not elem.tail.strip()):
-				elem.tail = i
-	
-	def convertMetadataToXML( self, filename, metadata ):
-
-		#shorthand for the metadata
-		md = metadata
-
-		# build a tree structure
-		root = ET.Element("comet")
-		root.attrib['xmlns:comet'] = "http://www.denvog.com/comet/"
-		root.attrib['xmlns:xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
-		root.attrib['xsi:schemaLocation'] = "http://www.denvog.com http://www.denvog.com/comet/comet.xsd"
-		
-		#helper func
-		def assign( comet_entry, md_entry):
-			if md_entry is not None:
-				ET.SubElement(root, comet_entry).text = u"{0}".format(md_entry)
-		
-		# title is manditory
-		if md.title is None:
-			md.title = ""
-		assign( 'title', md.title )
-		assign( 'series', md.series )
-		assign( 'issue', md.issue )  #must be int??
-		assign( 'volume', md.volume )
-		assign( 'description', md.comments )
-		assign( 'publisher', md.publisher )
-		assign( 'pages', md.pageCount )
-		assign( 'format', md.format )
-		assign( 'language', md.language )
-		assign( 'rating', md.maturityRating )
-		assign( 'price', md.price )
-		assign( 'isVersionOf', md.isVersionOf )
-		assign( 'rights', md.rights )
-		assign( 'identifier', md.identifier )
-		assign( 'lastMark', md.lastMark )		
-		assign( 'genre', md.genre )   # TODO repeatable
-
-		if md.characters is not None:
-			char_list = [ c.strip() for c in md.characters.split(',') ]
-			for c in char_list:
-				assign( 'character', c ) 
-			
-		if md.manga is not None and md.manga == "YesAndRightToLeft":
-			assign( 'readingDirection', "rtl")
-		
-		date_str = ""
-		if md.year is not None:
-			date_str = str(md.year).zfill(4) 
-			if md.month is not None:
-				date_str += "-" + str(md.month).zfill(2)
-			assign( 'date', date_str )  
-
-		assign( 'coverImage', md.coverImage )
-
-		# need to specially process the credits, since they are structured differently than CIX	
-		credit_writer_list    = list()
-		credit_penciller_list = list()
-		credit_inker_list     = list()
-		credit_colorist_list  = list()
-		credit_letterer_list  = list()
-		credit_cover_list     = list()
-		credit_editor_list    = list()
-		
-		#  loop thru credits, and build a list for each role that CoMet supports
-		for credit in metadata.credits:
-
-			if credit['role'].lower() in set( self.writer_synonyms ):
-				ET.SubElement(root, 'writer').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.penciller_synonyms ):
-				ET.SubElement(root, 'penciller').text = u"{0}".format(credit['person'])
-				
-			if credit['role'].lower() in set( self.inker_synonyms ):
-				ET.SubElement(root, 'inker').text = u"{0}".format(credit['person'])
-				
-			if credit['role'].lower() in set( self.colorist_synonyms ):
-				ET.SubElement(root, 'colorist').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.letterer_synonyms ):
-				ET.SubElement(root, 'letterer').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.cover_synonyms ):
-				ET.SubElement(root, 'coverDesigner').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.editor_synonyms ):
-				ET.SubElement(root, 'editor').text = u"{0}".format(credit['person'])
-		
-
-		# self pretty-print
-		self.indent(root)
-
-		# wrap it in an ElementTree instance, and save as XML
-		tree = ET.ElementTree(root)
-		return tree
-				 
-
-	def convertXMLToMetadata( self, tree ):
-			
-		root = tree.getroot()
-
-		if root.tag != 'comet':
-			raise 1
-			return None
-
-		metadata = GenericMetadata()
-		md = metadata
-	
-		# Helper function
-		def xlate( tag ):
-			node = root.find( tag )
-			if node is not None:
-				return node.text
-			else:
-				return None
-				
-		md.series =           xlate( 'series' )
-		md.title =            xlate( 'title' )
-		md.issue =            xlate( 'issue' )
-		md.volume =           xlate( 'volume' )
-		md.comments =         xlate( 'description' )
-		md.publisher =        xlate( 'publisher' )
-		md.language =         xlate( 'language' )
-		md.format =           xlate( 'format' )
-		md.pageCount =        xlate( 'pages' )
-		md.maturityRating =   xlate( 'rating' )
-		md.price =            xlate( 'price' )
-		md.isVersionOf =      xlate( 'isVersionOf' )
-		md.rights =           xlate( 'rights' )
-		md.identifier =       xlate( 'identifier' )
-		md.lastMark =         xlate( 'lastMark' )
-		md.genre =            xlate( 'genre' ) # TODO - repeatable field
-
-		date = xlate( 'date' )
-		if date is not None:
-			parts = date.split('-')
-			if len( parts) > 0:
-				md.year = parts[0]
-			if len( parts) > 1:
-				md.month = parts[1]
-				
-		md.coverImage = xlate( 'coverImage' )
-		
-		readingDirection = xlate( 'readingDirection' )
-		if readingDirection is not None and readingDirection == "rtl":
-			md.manga = "YesAndRightToLeft"
-	
-		# loop for character tags		
-		char_list =  []
-		for n in root:
-			if n.tag == 'character':
-				char_list.append(n.text.strip())
-		md.characters = utils.listToString( char_list )
-
-		# Now extract the credit info
-		for n in root:
-			if (  n.tag == 'writer' or 
-				n.tag == 'penciller' or
-				n.tag == 'inker' or
-				n.tag == 'colorist' or
-				n.tag == 'letterer' or
-				n.tag == 'editor' 
-			):
-				metadata.addCredit( n.text.strip(), n.tag.title() )
-
-			if n.tag == 'coverDesigner':
-				metadata.addCredit( n.text.strip(), "Cover" )
-
-
-		metadata.isEmpty = False
-		
-		return metadata
-
-	#verify that the string actually contains CoMet data in XML format
-	def validateString( self, string ):
-		try:
-			tree = ET.ElementTree(ET.fromstring( string ))
-			root = tree.getroot()
-			if root.tag != 'comet':
-				raise Exception
-		except:
-			return False
-		
-		return True
-
-
-	def writeToExternalFile( self, filename, metadata ):
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		#ET.dump(tree)		
-		tree.write(filename, encoding='utf-8')
-	
-	def readFromExternalFile( self, filename ):
-
-		tree = ET.parse( filename )
-		return self.convertXMLToMetadata( tree )
-

comicapi/__init__.py

@@ -0,0 +1 @@
+__author__ = 'dromanin'

comicapi/comet.py

@@ -0,0 +1,276 @@
+"""A class to encapsulate CoMet data"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import xml.etree.ElementTree as ET
+#from datetime import datetime
+#from pprint import pprint
+#import zipfile
+
+from .genericmetadata import GenericMetadata
+from . import utils
+
+
+class CoMet:
+
+    writer_synonyms = ['writer', 'plotter', 'scripter']
+    penciller_synonyms = ['artist', 'penciller', 'penciler', 'breakdowns']
+    inker_synonyms = ['inker', 'artist', 'finishes']
+    colorist_synonyms = ['colorist', 'colourist', 'colorer', 'colourer']
+    letterer_synonyms = ['letterer']
+    cover_synonyms = ['cover', 'covers', 'coverartist', 'cover artist']
+    editor_synonyms = ['editor']
+
+    def metadataFromString(self, string):
+
+        tree = ET.ElementTree(ET.fromstring(string))
+        return self.convertXMLToMetadata(tree)
+
+    def stringFromMetadata(self, metadata):
+
+        header = '<?xml version="1.0" encoding="UTF-8"?>\n'
+
+        tree = self.convertMetadataToXML(self, metadata)
+        return header + ET.tostring(tree.getroot())
+
+    def indent(self, elem, level=0):
+        # for making the XML output readable
+        i = "\n" + level * "  "
+        if len(elem):
+            if not elem.text or not elem.text.strip():
+                elem.text = i + "  "
+            if not elem.tail or not elem.tail.strip():
+                elem.tail = i
+            for elem in elem:
+                self.indent(elem, level + 1)
+            if not elem.tail or not elem.tail.strip():
+                elem.tail = i
+        else:
+            if level and (not elem.tail or not elem.tail.strip()):
+                elem.tail = i
+
+    def convertMetadataToXML(self, filename, metadata):
+
+        # shorthand for the metadata
+        md = metadata
+
+        # build a tree structure
+        root = ET.Element("comet")
+        root.attrib['xmlns:comet'] = "http://www.denvog.com/comet/"
+        root.attrib['xmlns:xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
+        root.attrib[
+            'xsi:schemaLocation'] = "http://www.denvog.com http://www.denvog.com/comet/comet.xsd"
+
+        # helper func
+        def assign(comet_entry, md_entry):
+            if md_entry is not None:
+                ET.SubElement(root, comet_entry).text = "{0}".format(md_entry)
+
+        # title is manditory
+        if md.title is None:
+            md.title = ""
+        assign('title', md.title)
+        assign('series', md.series)
+        assign('issue', md.issue)  # must be int??
+        assign('volume', md.volume)
+        assign('description', md.comments)
+        assign('publisher', md.publisher)
+        assign('pages', md.pageCount)
+        assign('format', md.format)
+        assign('language', md.language)
+        assign('rating', md.maturityRating)
+        assign('price', md.price)
+        assign('isVersionOf', md.isVersionOf)
+        assign('rights', md.rights)
+        assign('identifier', md.identifier)
+        assign('lastMark', md.lastMark)
+        assign('genre', md.genre)   # TODO repeatable
+
+        if md.characters is not None:
+            char_list = [c.strip() for c in md.characters.split(',')]
+            for c in char_list:
+                assign('character', c)
+
+        if md.manga is not None and md.manga == "YesAndRightToLeft":
+            assign('readingDirection', "rtl")
+
+        date_str = ""
+        if md.year is not None:
+            date_str = str(md.year).zfill(4)
+            if md.month is not None:
+                date_str += "-" + str(md.month).zfill(2)
+            assign('date', date_str)
+
+        assign('coverImage', md.coverImage)
+
+        # need to specially process the credits, since they are structured
+        # differently than CIX
+        credit_writer_list = list()
+        credit_penciller_list = list()
+        credit_inker_list = list()
+        credit_colorist_list = list()
+        credit_letterer_list = list()
+        credit_cover_list = list()
+        credit_editor_list = list()
+
+        # loop thru credits, and build a list for each role that CoMet supports
+        for credit in metadata.credits:
+
+            if credit['role'].lower() in set(self.writer_synonyms):
+                ET.SubElement(
+                    root,
+                    'writer').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.penciller_synonyms):
+                ET.SubElement(
+                    root,
+                    'penciller').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.inker_synonyms):
+                ET.SubElement(
+                    root,
+                    'inker').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.colorist_synonyms):
+                ET.SubElement(
+                    root,
+                    'colorist').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.letterer_synonyms):
+                ET.SubElement(
+                    root,
+                    'letterer').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.cover_synonyms):
+                ET.SubElement(
+                    root,
+                    'coverDesigner').text = "{0}".format(
+                    credit['person'])
+
+            if credit['role'].lower() in set(self.editor_synonyms):
+                ET.SubElement(
+                    root,
+                    'editor').text = "{0}".format(
+                    credit['person'])
+
+        # self pretty-print
+        self.indent(root)
+
+        # wrap it in an ElementTree instance, and save as XML
+        tree = ET.ElementTree(root)
+        return tree
+
+    def convertXMLToMetadata(self, tree):
+
+        root = tree.getroot()
+
+        if root.tag != 'comet':
+            raise 1
+            return None
+
+        metadata = GenericMetadata()
+        md = metadata
+
+        # Helper function
+        def xlate(tag):
+            node = root.find(tag)
+            if node is not None:
+                return node.text
+            else:
+                return None
+
+        md.series = xlate('series')
+        md.title = xlate('title')
+        md.issue = xlate('issue')
+        md.volume = xlate('volume')
+        md.comments = xlate('description')
+        md.publisher = xlate('publisher')
+        md.language = xlate('language')
+        md.format = xlate('format')
+        md.pageCount = xlate('pages')
+        md.maturityRating = xlate('rating')
+        md.price = xlate('price')
+        md.isVersionOf = xlate('isVersionOf')
+        md.rights = xlate('rights')
+        md.identifier = xlate('identifier')
+        md.lastMark = xlate('lastMark')
+        md.genre = xlate('genre')  # TODO - repeatable field
+
+        date = xlate('date')
+        if date is not None:
+            parts = date.split('-')
+            if len(parts) > 0:
+                md.year = parts[0]
+            if len(parts) > 1:
+                md.month = parts[1]
+
+        md.coverImage = xlate('coverImage')
+
+        readingDirection = xlate('readingDirection')
+        if readingDirection is not None and readingDirection == "rtl":
+            md.manga = "YesAndRightToLeft"
+
+        # loop for character tags
+        char_list = []
+        for n in root:
+            if n.tag == 'character':
+                char_list.append(n.text.strip())
+        md.characters = utils.listToString(char_list)
+
+        # Now extract the credit info
+        for n in root:
+            if (n.tag == 'writer' or
+                n.tag == 'penciller' or
+                n.tag == 'inker' or
+                n.tag == 'colorist' or
+                n.tag == 'letterer' or
+                n.tag == 'editor'
+                ):
+                metadata.addCredit(n.text.strip(), n.tag.title())
+
+            if n.tag == 'coverDesigner':
+                metadata.addCredit(n.text.strip(), "Cover")
+
+        metadata.isEmpty = False
+
+        return metadata
+
+    # verify that the string actually contains CoMet data in XML format
+    def validateString(self, string):
+        try:
+            tree = ET.ElementTree(ET.fromstring(string))
+            root = tree.getroot()
+            if root.tag != 'comet':
+                raise Exception
+        except:
+            return False
+
+        return True
+
+    def writeToExternalFile(self, filename, metadata):
+
+        tree = self.convertMetadataToXML(self, metadata)
+        # ET.dump(tree)
+        tree.write(filename, encoding='utf-8')
+
+    def readFromExternalFile(self, filename):
+
+        tree = ET.parse(filename)
+        return self.convertXMLToMetadata(tree)

comicapi/comicbookinfo.py

@@ -0,0 +1,144 @@
+"""A class to encapsulate the ComicBookInfo data"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import json
+from datetime import datetime
+#import zipfile
+
+from .genericmetadata import GenericMetadata
+from . import utils
+#import ctversion
+
+
+class ComicBookInfo:
+
+    def metadataFromString(self, string):
+
+        cbi_container = json.loads(str(string, 'utf-8'))
+
+        metadata = GenericMetadata()
+
+        cbi = cbi_container['ComicBookInfo/1.0']
+
+        # helper func
+        # If item is not in CBI, return None
+        def xlate(cbi_entry):
+            if cbi_entry in cbi:
+                return cbi[cbi_entry]
+            else:
+                return None
+
+        metadata.series = xlate('series')
+        metadata.title = xlate('title')
+        metadata.issue = xlate('issue')
+        metadata.publisher = xlate('publisher')
+        metadata.month = xlate('publicationMonth')
+        metadata.year = xlate('publicationYear')
+        metadata.issueCount = xlate('numberOfIssues')
+        metadata.comments = xlate('comments')
+        metadata.credits = xlate('credits')
+        metadata.genre = xlate('genre')
+        metadata.volume = xlate('volume')
+        metadata.volumeCount = xlate('numberOfVolumes')
+        metadata.language = xlate('language')
+        metadata.country = xlate('country')
+        metadata.criticalRating = xlate('rating')
+        metadata.tags = xlate('tags')
+
+        # make sure credits and tags are at least empty lists and not None
+        if metadata.credits is None:
+            metadata.credits = []
+        if metadata.tags is None:
+            metadata.tags = []
+
+        # need to massage the language string to be ISO
+        if metadata.language is not None:
+            # reverse look-up
+            pattern = metadata.language
+            metadata.language = None
+            for key in utils.getLanguageDict():
+                if utils.getLanguageDict()[key] == pattern.encode('utf-8'):
+                    metadata.language = key
+                    break
+
+        metadata.isEmpty = False
+
+        return metadata
+
+    def stringFromMetadata(self, metadata):
+
+        cbi_container = self.createJSONDictionary(metadata)
+        return json.dumps(cbi_container)
+
+    def validateString(self, string):
+        """Verify that the string actually contains CBI data in JSON format"""
+
+        try:
+            cbi_container = json.loads(string)
+        except:
+            return False
+
+        return ('ComicBookInfo/1.0' in cbi_container)
+
+    def createJSONDictionary(self, metadata):
+        """Create the dictionary that we will convert to JSON text"""
+
+        cbi = dict()
+        cbi_container = {'appID': 'ComicTagger/' + '1.0.0',  # ctversion.version,
+                         'lastModified': str(datetime.now()),
+                         'ComicBookInfo/1.0': cbi}
+
+        # helper func
+        def assign(cbi_entry, md_entry):
+            if md_entry is not None:
+                cbi[cbi_entry] = md_entry
+
+        # helper func
+        def toInt(s):
+            i = None
+            if type(s) in [str, str, int]:
+                try:
+                    i = int(s)
+                except ValueError:
+                    pass
+            return i
+
+        assign('series', metadata.series)
+        assign('title', metadata.title)
+        assign('issue', metadata.issue)
+        assign('publisher', metadata.publisher)
+        assign('publicationMonth', toInt(metadata.month))
+        assign('publicationYear', toInt(metadata.year))
+        assign('numberOfIssues', toInt(metadata.issueCount))
+        assign('comments', metadata.comments)
+        assign('genre', metadata.genre)
+        assign('volume', toInt(metadata.volume))
+        assign('numberOfVolumes', toInt(metadata.volumeCount))
+        assign('language', utils.getLanguageFromISO(metadata.language))
+        assign('country', metadata.country)
+        assign('rating', metadata.criticalRating)
+        assign('credits', metadata.credits)
+        assign('tags', metadata.tags)
+
+        return cbi_container
+
+    def writeToExternalFile(self, filename, metadata):
+
+        cbi_container = self.createJSONDictionary(metadata)
+
+        f = open(filename, 'w')
+        f.write(json.dumps(cbi_container, indent=4))
+        f.close

comicapi/comicinfoxml.py

@@ -0,0 +1,291 @@
+"""A class to encapsulate ComicRack's ComicInfo.xml data"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import xml.etree.ElementTree as ET
+#from datetime import datetime
+#from pprint import pprint
+#import zipfile
+
+from .genericmetadata import GenericMetadata
+from . import utils
+
+
+class ComicInfoXml:
+
+    writer_synonyms = ['writer', 'plotter', 'scripter']
+    penciller_synonyms = ['artist', 'penciller', 'penciler', 'breakdowns']
+    inker_synonyms = ['inker', 'artist', 'finishes']
+    colorist_synonyms = ['colorist', 'colourist', 'colorer', 'colourer']
+    letterer_synonyms = ['letterer']
+    cover_synonyms = ['cover', 'covers', 'coverartist', 'cover artist']
+    editor_synonyms = ['editor']
+
+    def getParseableCredits(self):
+        parsable_credits = []
+        parsable_credits.extend(self.writer_synonyms)
+        parsable_credits.extend(self.penciller_synonyms)
+        parsable_credits.extend(self.inker_synonyms)
+        parsable_credits.extend(self.colorist_synonyms)
+        parsable_credits.extend(self.letterer_synonyms)
+        parsable_credits.extend(self.cover_synonyms)
+        parsable_credits.extend(self.editor_synonyms)
+        return parsable_credits
+
+    def metadataFromString(self, string):
+
+        tree = ET.ElementTree(ET.fromstring(string))
+        return self.convertXMLToMetadata(tree)
+
+    def stringFromMetadata(self, metadata):
+
+        header = '<?xml version="1.0"?>\n'
+
+        tree = self.convertMetadataToXML(self, metadata)
+        tree_str = ET.tostring(tree.getroot()).decode()
+        return header + tree_str
+
+    def indent(self, elem, level=0):
+        # for making the XML output readable
+        i = "\n" + level * "  "
+        if len(elem):
+            if not elem.text or not elem.text.strip():
+                elem.text = i + "  "
+            if not elem.tail or not elem.tail.strip():
+                elem.tail = i
+            for elem in elem:
+                self.indent(elem, level + 1)
+            if not elem.tail or not elem.tail.strip():
+                elem.tail = i
+        else:
+            if level and (not elem.tail or not elem.tail.strip()):
+                elem.tail = i
+
+    def convertMetadataToXML(self, filename, metadata):
+
+        # shorthand for the metadata
+        md = metadata
+
+        # build a tree structure
+        root = ET.Element("ComicInfo")
+        root.attrib['xmlns:xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
+        root.attrib['xmlns:xsd'] = "http://www.w3.org/2001/XMLSchema"
+        # helper func
+
+        def assign(cix_entry, md_entry):
+            if md_entry is not None:
+                ET.SubElement(root, cix_entry).text = "{0}".format(md_entry)
+
+        assign('Title', md.title)
+        assign('Series', md.series)
+        assign('Number', md.issue)
+        assign('Count', md.issueCount)
+        assign('Volume', md.volume)
+        assign('AlternateSeries', md.alternateSeries)
+        assign('AlternateNumber', md.alternateNumber)
+        assign('StoryArc', md.storyArc)
+        assign('SeriesGroup', md.seriesGroup)
+        assign('AlternateCount', md.alternateCount)
+        assign('Summary', md.comments)
+        assign('Notes', md.notes)
+        assign('Year', md.year)
+        assign('Month', md.month)
+        assign('Day', md.day)
+
+        # need to specially process the credits, since they are structured
+        # differently than CIX
+        credit_writer_list = list()
+        credit_penciller_list = list()
+        credit_inker_list = list()
+        credit_colorist_list = list()
+        credit_letterer_list = list()
+        credit_cover_list = list()
+        credit_editor_list = list()
+
+        # first, loop thru credits, and build a list for each role that CIX
+        # supports
+        for credit in metadata.credits:
+
+            if credit['role'].lower() in set(self.writer_synonyms):
+                credit_writer_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.penciller_synonyms):
+                credit_penciller_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.inker_synonyms):
+                credit_inker_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.colorist_synonyms):
+                credit_colorist_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.letterer_synonyms):
+                credit_letterer_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.cover_synonyms):
+                credit_cover_list.append(credit['person'].replace(",", ""))
+
+            if credit['role'].lower() in set(self.editor_synonyms):
+                credit_editor_list.append(credit['person'].replace(",", ""))
+
+        # second, convert each list to string, and add to XML struct
+        if len(credit_writer_list) > 0:
+            node = ET.SubElement(root, 'Writer')
+            node.text = utils.listToString(credit_writer_list)
+
+        if len(credit_penciller_list) > 0:
+            node = ET.SubElement(root, 'Penciller')
+            node.text = utils.listToString(credit_penciller_list)
+
+        if len(credit_inker_list) > 0:
+            node = ET.SubElement(root, 'Inker')
+            node.text = utils.listToString(credit_inker_list)
+
+        if len(credit_colorist_list) > 0:
+            node = ET.SubElement(root, 'Colorist')
+            node.text = utils.listToString(credit_colorist_list)
+
+        if len(credit_letterer_list) > 0:
+            node = ET.SubElement(root, 'Letterer')
+            node.text = utils.listToString(credit_letterer_list)
+
+        if len(credit_cover_list) > 0:
+            node = ET.SubElement(root, 'CoverArtist')
+            node.text = utils.listToString(credit_cover_list)
+
+        if len(credit_editor_list) > 0:
+            node = ET.SubElement(root, 'Editor')
+            node.text = utils.listToString(credit_editor_list)
+
+        assign('Publisher', md.publisher)
+        assign('Imprint', md.imprint)
+        assign('Genre', md.genre)
+        assign('Web', md.webLink)
+        assign('PageCount', md.pageCount)
+        assign('LanguageISO', md.language)
+        assign('Format', md.format)
+        assign('AgeRating', md.maturityRating)
+        if md.blackAndWhite is not None and md.blackAndWhite:
+            ET.SubElement(root, 'BlackAndWhite').text = "Yes"
+        assign('Manga', md.manga)
+        assign('Characters', md.characters)
+        assign('Teams', md.teams)
+        assign('Locations', md.locations)
+        assign('ScanInformation', md.scanInfo)
+
+        #  loop and add the page entries under pages node
+        if len(md.pages) > 0:
+            pages_node = ET.SubElement(root, 'Pages')
+            for page_dict in md.pages:
+                page_node = ET.SubElement(pages_node, 'Page')
+                page_node.attrib = page_dict
+
+        # self pretty-print
+        self.indent(root)
+
+        # wrap it in an ElementTree instance, and save as XML
+        tree = ET.ElementTree(root)
+        return tree
+
+    def convertXMLToMetadata(self, tree):
+
+        root = tree.getroot()
+
+        if root.tag != 'ComicInfo':
+            raise 1
+            return None
+
+        metadata = GenericMetadata()
+        md = metadata
+
+        # Helper function
+        def xlate(tag):
+            node = root.find(tag)
+            if node is not None:
+                return node.text
+            else:
+                return None
+
+        md.series = xlate('Series')
+        md.title = xlate('Title')
+        md.issue = xlate('Number')
+        md.issueCount = xlate('Count')
+        md.volume = xlate('Volume')
+        md.alternateSeries = xlate('AlternateSeries')
+        md.alternateNumber = xlate('AlternateNumber')
+        md.alternateCount = xlate('AlternateCount')
+        md.comments = xlate('Summary')
+        md.notes = xlate('Notes')
+        md.year = xlate('Year')
+        md.month = xlate('Month')
+        md.day = xlate('Day')
+        md.publisher = xlate('Publisher')
+        md.imprint = xlate('Imprint')
+        md.genre = xlate('Genre')
+        md.webLink = xlate('Web')
+        md.language = xlate('LanguageISO')
+        md.format = xlate('Format')
+        md.manga = xlate('Manga')
+        md.characters = xlate('Characters')
+        md.teams = xlate('Teams')
+        md.locations = xlate('Locations')
+        md.pageCount = xlate('PageCount')
+        md.scanInfo = xlate('ScanInformation')
+        md.storyArc = xlate('StoryArc')
+        md.seriesGroup = xlate('SeriesGroup')
+        md.maturityRating = xlate('AgeRating')
+
+        tmp = xlate('BlackAndWhite')
+        md.blackAndWhite = False
+        if tmp is not None and tmp.lower() in ["yes", "true", "1"]:
+            md.blackAndWhite = True
+        # Now extract the credit info
+        for n in root:
+            if (n.tag == 'Writer' or
+                n.tag == 'Penciller' or
+                n.tag == 'Inker' or
+                n.tag == 'Colorist' or
+                n.tag == 'Letterer' or
+                n.tag == 'Editor'
+                ):
+                if n.text is not None:
+                    for name in n.text.split(','):
+                        metadata.addCredit(name.strip(), n.tag)
+
+            if n.tag == 'CoverArtist':
+                if n.text is not None:
+                    for name in n.text.split(','):
+                        metadata.addCredit(name.strip(), "Cover")
+
+        # parse page data now
+        pages_node = root.find("Pages")
+        if pages_node is not None:
+            for page in pages_node:
+                metadata.pages.append(page.attrib)
+                # print page.attrib
+
+        metadata.isEmpty = False
+
+        return metadata
+
+    def writeToExternalFile(self, filename, metadata):
+
+        tree = self.convertMetadataToXML(self, metadata)
+        # ET.dump(tree)
+        tree.write(filename, encoding='utf-8')
+
+    def readFromExternalFile(self, filename):
+
+        tree = ET.parse(filename)
+        return self.convertXMLToMetadata(tree)

comicapi/filenameparser.py

@@ -0,0 +1,292 @@
+"""Functions for parsing comic info from filename
+
+This should probably be re-written, but, well, it mostly works!
+"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Some portions of this code were modified from pyComicMetaThis project
+# http://code.google.com/p/pycomicmetathis/
+
+import re
+import os
+from urllib.parse import unquote
+
+
+class FileNameParser:
+
+    def repl(self, m):
+        return ' ' * len(m.group())
+
+    def fixSpaces(self, string, remove_dashes=True):
+        if remove_dashes:
+            placeholders = ['[-_]', '  +']
+        else:
+            placeholders = ['[_]', '  +']
+        for ph in placeholders:
+            string = re.sub(ph, self.repl, string)
+        return string  # .strip()
+
+    def getIssueCount(self, filename, issue_end):
+
+        count = ""
+        filename = filename[issue_end:]
+
+        # replace any name separators with spaces
+        tmpstr = self.fixSpaces(filename)
+        found = False
+
+        match = re.search('(?<=\sof\s)\d+(?=\s)', tmpstr, re.IGNORECASE)
+        if match:
+            count = match.group()
+            found = True
+
+        if not found:
+            match = re.search('(?<=\(of\s)\d+(?=\))', tmpstr, re.IGNORECASE)
+            if match:
+                count = match.group()
+                found = True
+
+        count = count.lstrip("0")
+
+        return count
+
+    def getIssueNumber(self, filename):
+        """Returns a tuple of issue number string, and start and end indexes in the filename
+        (The indexes will be used to split the string up for further parsing)
+        """
+
+        found = False
+        issue = ''
+        start = 0
+        end = 0
+
+        # first, look for multiple "--", this means it's formatted differently
+        # from most:
+        if "--" in filename:
+            # the pattern seems to be that anything to left of the first "--"
+            # is the series name followed by issue
+            filename = re.sub("--.*", self.repl, filename)
+
+        elif "__" in filename:
+            # the pattern seems to be that anything to left of the first "__"
+            # is the series name followed by issue
+            filename = re.sub("__.*", self.repl, filename)
+
+        filename = filename.replace("+", " ")
+
+        # replace parenthetical phrases with spaces
+        filename = re.sub("\(.*?\)", self.repl, filename)
+        filename = re.sub("\[.*?\]", self.repl, filename)
+
+        # replace any name separators with spaces
+        filename = self.fixSpaces(filename)
+
+        # remove any "of NN" phrase with spaces (problem: this could break on
+        # some titles)
+        filename = re.sub("of [\d]+", self.repl, filename)
+
+        # print u"[{0}]".format(filename)
+
+        # we should now have a cleaned up filename version with all the words in
+        # the same positions as original filename
+
+        # make a list of each word and its position
+        word_list = list()
+        for m in re.finditer("\S+", filename):
+            word_list.append((m.group(0), m.start(), m.end()))
+
+        # remove the first word, since it can't be the issue number
+        if len(word_list) > 1:
+            word_list = word_list[1:]
+        else:
+            # only one word??  just bail.
+            return issue, start, end
+
+        # Now try to search for the likely issue number word in the list
+
+        # first look for a word with "#" followed by digits with optional suffix
+        # this is almost certainly the issue number
+        for w in reversed(word_list):
+            if re.match("#[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+                found = True
+                break
+
+        # same as above but w/o a '#', and only look at the last word in the
+        # list
+        if not found:
+            w = word_list[-1]
+            if re.match("[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+                found = True
+
+        # now try to look for a # followed by any characters
+        if not found:
+            for w in reversed(word_list):
+                if re.match("#\S+", w[0]):
+                    found = True
+                    break
+
+        if found:
+            issue = w[0]
+            start = w[1]
+            end = w[2]
+            if issue[0] == '#':
+                issue = issue[1:]
+
+        return issue, start, end
+
+    def getSeriesName(self, filename, issue_start):
+        """Use the issue number string index to split the filename string"""
+
+        if issue_start != 0:
+            filename = filename[:issue_start]
+
+        # in case there is no issue number, remove some obvious stuff
+        if "--" in filename:
+            # the pattern seems to be that anything to left of the first "--"
+            # is the series name followed by issue
+            filename = re.sub("--.*", self.repl, filename)
+
+        elif "__" in filename:
+            # the pattern seems to be that anything to left of the first "__"
+            # is the series name followed by issue
+            filename = re.sub("__.*", self.repl, filename)
+
+        filename = filename.replace("+", " ")
+        tmpstr = self.fixSpaces(filename, remove_dashes=False)
+
+        series = tmpstr
+        volume = ""
+
+        # save the last word
+        try:
+            last_word = series.split()[-1]
+        except:
+            last_word = ""
+
+        # remove any parenthetical phrases
+        series = re.sub("\(.*?\)", "", series)
+
+        # search for volume number
+        match = re.search('(.+)([vV]|[Vv][oO][Ll]\.?\s?)(\d+)\s*$', series)
+        if match:
+            series = match.group(1)
+            volume = match.group(3)
+
+        # if a volume wasn't found, see if the last word is a year in parentheses
+        # since that's a common way to designate the volume
+        if volume == "":
+            # match either (YEAR), (YEAR-), or (YEAR-YEAR2)
+            match = re.search("(\()(\d{4})(-(\d{4}|)|)(\))", last_word)
+            if match:
+                volume = match.group(2)
+
+        series = series.strip()
+
+        # if we don't have an issue number (issue_start==0), look
+        # for hints i.e. "TPB", "one-shot", "OS", "OGN", etc that might
+        # be removed to help search online
+        if issue_start == 0:
+            one_shot_words = ["tpb", "os", "one-shot", "ogn", "gn"]
+            try:
+                last_word = series.split()[-1]
+                if last_word.lower() in one_shot_words:
+                    series = series.rsplit(' ', 1)[0]
+            except:
+                pass
+
+        return series, volume.strip()
+
+    def getYear(self, filename, issue_end):
+
+        filename = filename[issue_end:]
+
+        year = ""
+        # look for four digit number with "(" ")" or "--" around it
+        match = re.search('(\(\d\d\d\d\))|(--\d\d\d\d--)', filename)
+        if match:
+            year = match.group()
+            # remove non-digits
+            year = re.sub("[^0-9]", "", year)
+        return year
+
+    def getRemainder(self, filename, year, count, volume, issue_end):
+        """Make a guess at where the the non-interesting stuff begins"""
+
+        remainder = ""
+
+        if "--" in filename:
+            remainder = filename.split("--", 1)[1]
+        elif "__" in filename:
+            remainder = filename.split("__", 1)[1]
+        elif issue_end != 0:
+            remainder = filename[issue_end:]
+
+        remainder = self.fixSpaces(remainder, remove_dashes=False)
+        if volume != "":
+            remainder = remainder.replace("Vol." + volume, "", 1)
+        if year != "":
+            remainder = remainder.replace(year, "", 1)
+        if count != "":
+            remainder = remainder.replace("of " + count, "", 1)
+
+        remainder = remainder.replace("()", "")
+        remainder = remainder.replace(
+            "  ",
+            " ")    # cleans some whitespace mess
+
+        return remainder.strip()
+
+    def parseFilename(self, filename):
+
+        # remove the path
+        filename = os.path.basename(filename)
+
+        # remove the extension
+        filename = os.path.splitext(filename)[0]
+
+        # url decode, just in case
+        filename = unquote(filename)
+
+        # sometimes archives get messed up names from too many decodes
+        # often url encodings will break and leave "_28" and "_29" in place
+        # of "(" and ")"  see if there are a number of these, and replace them
+        if filename.count("_28") > 1 and filename.count("_29") > 1:
+            filename = filename.replace("_28", "(")
+            filename = filename.replace("_29", ")")
+
+        self.issue, issue_start, issue_end = self.getIssueNumber(filename)
+        self.series, self.volume = self.getSeriesName(filename, issue_start)
+
+        # provides proper value when the filename doesn't have a issue number
+        if issue_end == 0:
+            issue_end = len(self.series)
+
+        self.year = self.getYear(filename, issue_end)
+        self.issue_count = self.getIssueCount(filename, issue_end)
+        self.remainder = self.getRemainder(
+            filename,
+            self.year,
+            self.issue_count,
+            self.volume,
+            issue_end)
+
+        if self.issue != "":
+            # strip off leading zeros
+            self.issue = self.issue.lstrip("0")
+            if self.issue == "":
+                self.issue = "0"
+            if self.issue[0] == ".":
+                self.issue = "0" + self.issue

comicapi/genericmetadata.py

@@ -0,0 +1,321 @@
+"""A class for internal metadata storage
+
+The goal of this class is to handle ALL the data that might come from various
+tagging schemes and databases, such as ComicVine or GCD.  This makes conversion
+possible, however lossy it might be
+
+"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from . import utils
+
+
+class PageType:
+
+    """
+    These page info classes are exactly the same as the CIX scheme, since
+    it's unique
+    """
+
+    FrontCover = "FrontCover"
+    InnerCover = "InnerCover"
+    Roundup = "Roundup"
+    Story = "Story"
+    Advertisement = "Advertisement"
+    Editorial = "Editorial"
+    Letters = "Letters"
+    Preview = "Preview"
+    BackCover = "BackCover"
+    Other = "Other"
+    Deleted = "Deleted"
+
+"""
+class PageInfo:
+	Image = 0
+	Type = PageType.Story
+	DoublePage = False
+	ImageSize = 0
+	Key = ""
+	ImageWidth = 0
+	ImageHeight = 0
+"""
+
+
+class GenericMetadata:
+
+    def __init__(self):
+
+        self.isEmpty = True
+        self.tagOrigin = None
+
+        self.series = None
+        self.issue = None
+        self.title = None
+        self.publisher = None
+        self.month = None
+        self.year = None
+        self.day = None
+        self.issueCount = None
+        self.volume = None
+        self.genre = None
+        self.language = None  # 2 letter iso code
+        self.comments = None  # use same way as Summary in CIX
+
+        self.volumeCount = None
+        self.criticalRating = None
+        self.country = None
+
+        self.alternateSeries = None
+        self.alternateNumber = None
+        self.alternateCount = None
+        self.imprint = None
+        self.notes = None
+        self.webLink = None
+        self.format = None
+        self.manga = None
+        self.blackAndWhite = None
+        self.pageCount = None
+        self.maturityRating = None
+
+        self.storyArc = None
+        self.seriesGroup = None
+        self.scanInfo = None
+
+        self.characters = None
+        self.teams = None
+        self.locations = None
+
+        self.credits = list()
+        self.tags = list()
+        self.pages = list()
+
+        # Some CoMet-only items
+        self.price = None
+        self.isVersionOf = None
+        self.rights = None
+        self.identifier = None
+        self.lastMark = None
+        self.coverImage = None
+
+    def overlay(self, new_md):
+        """Overlay a metadata object on this one
+
+        That is, when the new object has non-None values, over-write them
+        to this one.
+        """
+
+        def assign(cur, new):
+            if new is not None:
+                if isinstance(new, str) and len(new) == 0:
+                    setattr(self, cur, None)
+                else:
+                    setattr(self, cur, new)
+
+        if not new_md.isEmpty:
+            self.isEmpty = False
+
+        assign('series', new_md.series)
+        assign("issue", new_md.issue)
+        assign("issueCount", new_md.issueCount)
+        assign("title", new_md.title)
+        assign("publisher", new_md.publisher)
+        assign("day", new_md.day)
+        assign("month", new_md.month)
+        assign("year", new_md.year)
+        assign("volume", new_md.volume)
+        assign("volumeCount", new_md.volumeCount)
+        assign("genre", new_md.genre)
+        assign("language", new_md.language)
+        assign("country", new_md.country)
+        assign("criticalRating", new_md.criticalRating)
+        assign("alternateSeries", new_md.alternateSeries)
+        assign("alternateNumber", new_md.alternateNumber)
+        assign("alternateCount", new_md.alternateCount)
+        assign("imprint", new_md.imprint)
+        assign("webLink", new_md.webLink)
+        assign("format", new_md.format)
+        assign("manga", new_md.manga)
+        assign("blackAndWhite", new_md.blackAndWhite)
+        assign("maturityRating", new_md.maturityRating)
+        assign("storyArc", new_md.storyArc)
+        assign("seriesGroup", new_md.seriesGroup)
+        assign("scanInfo", new_md.scanInfo)
+        assign("characters", new_md.characters)
+        assign("teams", new_md.teams)
+        assign("locations", new_md.locations)
+        assign("comments", new_md.comments)
+        assign("notes", new_md.notes)
+
+        assign("price", new_md.price)
+        assign("isVersionOf", new_md.isVersionOf)
+        assign("rights", new_md.rights)
+        assign("identifier", new_md.identifier)
+        assign("lastMark", new_md.lastMark)
+
+        self.overlayCredits(new_md.credits)
+        # TODO
+
+        # not sure if the tags and pages should broken down, or treated
+        # as whole lists....
+
+        # For now, go the easy route, where any overlay
+        # value wipes out the whole list
+        if len(new_md.tags) > 0:
+            assign("tags", new_md.tags)
+
+        if len(new_md.pages) > 0:
+            assign("pages", new_md.pages)
+
+    def overlayCredits(self, new_credits):
+        for c in new_credits:
+            if 'primary' in c and c['primary']:
+                primary = True
+            else:
+                primary = False
+
+            # Remove credit role if person is blank
+            if c['person'] == "":
+                for r in reversed(self.credits):
+                    if r['role'].lower() == c['role'].lower():
+                        self.credits.remove(r)
+            # otherwise, add it!
+            else:
+                self.addCredit(c['person'], c['role'], primary)
+
+    def setDefaultPageList(self, count):
+        # generate a default page list, with the first page marked as the cover
+        for i in range(count):
+            page_dict = dict()
+            page_dict['Image'] = str(i)
+            if i == 0:
+                page_dict['Type'] = PageType.FrontCover
+            self.pages.append(page_dict)
+
+    def getArchivePageIndex(self, pagenum):
+        # convert the displayed page number to the page index of the file in
+        # the archive
+        if pagenum < len(self.pages):
+            return int(self.pages[pagenum]['Image'])
+        else:
+            return 0
+
+    def getCoverPageIndexList(self):
+        # return a list of archive page indices of cover pages
+        coverlist = []
+        for p in self.pages:
+            if 'Type' in p and p['Type'] == PageType.FrontCover:
+                coverlist.append(int(p['Image']))
+
+        if len(coverlist) == 0:
+            coverlist.append(0)
+
+        return coverlist
+
+    def addCredit(self, person, role, primary=False):
+
+        credit = dict()
+        credit['person'] = person
+        credit['role'] = role
+        if primary:
+            credit['primary'] = primary
+
+        # look to see if it's not already there...
+        found = False
+        for c in self.credits:
+            if (c['person'].lower() == person.lower() and
+                    c['role'].lower() == role.lower()):
+                # no need to add it. just adjust the "primary" flag as needed
+                c['primary'] = primary
+                found = True
+                break
+
+        if not found:
+            self.credits.append(credit)
+
+    def __str__(self):
+        vals = []
+        if self.isEmpty:
+            return "No metadata"
+
+        def add_string(tag, val):
+            if val is not None and "{0}".format(val) != "":
+                vals.append((tag, val))
+
+        def add_attr_string(tag):
+            val = getattr(self, tag)
+            add_string(tag, getattr(self, tag))
+
+        add_attr_string("series")
+        add_attr_string("issue")
+        add_attr_string("issueCount")
+        add_attr_string("title")
+        add_attr_string("publisher")
+        add_attr_string("year")
+        add_attr_string("month")
+        add_attr_string("day")
+        add_attr_string("volume")
+        add_attr_string("volumeCount")
+        add_attr_string("genre")
+        add_attr_string("language")
+        add_attr_string("country")
+        add_attr_string("criticalRating")
+        add_attr_string("alternateSeries")
+        add_attr_string("alternateNumber")
+        add_attr_string("alternateCount")
+        add_attr_string("imprint")
+        add_attr_string("webLink")
+        add_attr_string("format")
+        add_attr_string("manga")
+
+        add_attr_string("price")
+        add_attr_string("isVersionOf")
+        add_attr_string("rights")
+        add_attr_string("identifier")
+        add_attr_string("lastMark")
+
+        if self.blackAndWhite:
+            add_attr_string("blackAndWhite")
+        add_attr_string("maturityRating")
+        add_attr_string("storyArc")
+        add_attr_string("seriesGroup")
+        add_attr_string("scanInfo")
+        add_attr_string("characters")
+        add_attr_string("teams")
+        add_attr_string("locations")
+        add_attr_string("comments")
+        add_attr_string("notes")
+
+        add_string("tags", utils.listToString(self.tags))
+
+        for c in self.credits:
+            primary = ""
+            if 'primary' in c and c['primary']:
+                primary = " [P]"
+            add_string("credit", c['role'] + ": " + c['person'] + primary)
+
+        # find the longest field name
+        flen = 0
+        for i in vals:
+            flen = max(flen, len(i[0]))
+        flen += 1
+
+        # format the data nicely
+        outstr = ""
+        fmt_str = "{0: <" + str(flen) + "} {1}\n"
+        for i in vals:
+            outstr += fmt_str.format(i[0] + ":", i[1])
+
+        return outstr

comicapi/issuestring.py

@@ -0,0 +1,133 @@
+# coding=utf-8
+"""Support for mixed digit/string type Issue field
+
+Class for handling the odd permutations of an 'issue number' that the
+comics industry throws at us.
+  e.g.: "12", "12.1", "0", "-1", "5AU", "100-2"
+"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import utils
+#import math
+#import re
+
+
+class IssueString:
+
+    def __init__(self, text):
+
+        # break up the issue number string into 2 parts: the numeric and suffix string.
+        # (assumes that the numeric portion is always first)
+
+        self.num = None
+        self.suffix = ""
+
+        if text is None:
+            return
+
+        if isinstance(text, int):
+            text = str(text)
+
+        if len(text) == 0:
+            return
+
+        text = str(text)
+
+        # skip the minus sign if it's first
+        if text[0] == '-':
+            start = 1
+        else:
+            start = 0
+
+        # if it's still not numeric at start skip it
+        if text[start].isdigit() or text[start] == ".":
+            # walk through the string, look for split point (the first
+            # non-numeric)
+            decimal_count = 0
+            for idx in range(start, len(text)):
+                if text[idx] not in "0123456789.":
+                    break
+                # special case: also split on second "."
+                if text[idx] == ".":
+                    decimal_count += 1
+                    if decimal_count > 1:
+                        break
+            else:
+                idx = len(text)
+
+            # move trailing numeric decimal to suffix
+            # (only if there is other junk after )
+            if text[idx - 1] == "." and len(text) != idx:
+                idx = idx - 1
+
+            # if there is no numeric after the minus, make the minus part of
+            # the suffix
+            if idx == 1 and start == 1:
+                idx = 0
+
+            part1 = text[0:idx]
+            part2 = text[idx:len(text)]
+
+            if part1 != "":
+                self.num = float(part1)
+            self.suffix = part2
+        else:
+            self.suffix = text
+
+        # print "num: {0} suf: {1}".format(self.num, self.suffix)
+
+    def asString(self, pad=0):
+        # return the float, left side zero-padded, with suffix attached
+        if self.num is None:
+            return self.suffix
+
+        negative = self.num < 0
+
+        num_f = abs(self.num)
+
+        num_int = int(num_f)
+        num_s = str(num_int)
+        if float(num_int) != num_f:
+            num_s = str(num_f)
+
+        num_s += self.suffix
+
+        # create padding
+        padding = ""
+        l = len(str(num_int))
+        if l < pad:
+            padding = "0" * (pad - l)
+
+        num_s = padding + num_s
+        if negative:
+            num_s = "-" + num_s
+
+        return num_s
+
+    def asFloat(self):
+        # return the float, with no suffix
+        if self.suffix == "½":
+            if self.num is not None:
+                return self.num + .5
+            else:
+                return .5
+        return self.num
+
+    def asInt(self):
+        # return the int version of the float
+        if self.num is None:
+            return None
+        return int(self.num)

comicapi/utils.py

@@ -0,0 +1,594 @@
+# coding=utf-8
+"""Some generic utilities"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sys
+import os
+import re
+import platform
+import locale
+import codecs
+
+
+class UtilsVars:
+    already_fixed_encoding = False
+
+
+def get_actual_preferred_encoding():
+    preferred_encoding = locale.getpreferredencoding()
+    if platform.system() == "Darwin":
+        preferred_encoding = "utf-8"
+    return preferred_encoding
+
+
+def fix_output_encoding():
+    if not UtilsVars.already_fixed_encoding:
+        # this reads the environment and inits the right locale
+        locale.setlocale(locale.LC_ALL, "")
+
+        # try to make stdout/stderr encodings happy for unicode printing
+        preferred_encoding = get_actual_preferred_encoding()
+        sys.stdout = codecs.getwriter(preferred_encoding)(sys.stdout)
+        sys.stderr = codecs.getwriter(preferred_encoding)(sys.stderr)
+        UtilsVars.already_fixed_encoding = True
+
+
+def get_recursive_filelist(pathlist):
+    """Get a recursive list of of all files under all path items in the list"""
+
+    filename_encoding = sys.getfilesystemencoding()
+    filelist = []
+    for p in pathlist:
+        # if path is a folder, walk it recursively, and all files underneath
+        if isinstance(p, str):
+            # make sure string is unicode
+            #p = p.decode(filename_encoding)  # , 'replace')
+            pass
+        elif not isinstance(p, str):
+            # it's probably a QString
+            p = str(p)
+
+        if os.path.isdir(p):
+            for root, dirs, files in os.walk(p):
+                for f in files:
+                    if isinstance(f, str):
+                        # make sure string is unicode
+                        #f = f.decode(filename_encoding, 'replace')
+                        pass
+                    elif not isinstance(f, str):
+                        # it's probably a QString
+                        f = str(f)
+                    filelist.append(os.path.join(root, f))
+        else:
+            filelist.append(p)
+
+    return filelist
+
+
+def listToString(l):
+    string = ""
+    if l is not None:
+        for item in l:
+            if len(string) > 0:
+                string += ", "
+            string += item
+    return string
+
+
+def addtopath(dirname):
+    if dirname is not None and dirname != "":
+
+        # verify that path doesn't already contain the given dirname
+        tmpdirname = re.escape(dirname)
+        pattern = r"{sep}{dir}$|^{dir}{sep}|{sep}{dir}{sep}|^{dir}$".format(
+            dir=tmpdirname,
+            sep=os.pathsep)
+
+        match = re.search(pattern, os.environ['PATH'])
+        if not match:
+            os.environ['PATH'] = dirname + os.pathsep + os.environ['PATH']
+
+
+def which(program):
+    """Returns path of the executable, if it exists"""
+
+    def is_exe(fpath):
+        return os.path.isfile(fpath) and os.access(fpath, os.X_OK)
+
+    fpath, fname = os.path.split(program)
+    if fpath:
+        if is_exe(program):
+            return program
+    else:
+        for path in os.environ["PATH"].split(os.pathsep):
+            exe_file = os.path.join(path, program)
+            if is_exe(exe_file):
+                return exe_file
+
+    return None
+
+
+def removearticles(text):
+    text = text.lower()
+    articles = ['and', 'a', '&', 'issue', 'the']
+    newText = ''
+    for word in text.split(' '):
+        if word not in articles:
+            newText += word + ' '
+
+    newText = newText[:-1]
+
+    # now get rid of some other junk
+    newText = newText.replace(":", "")
+    newText = newText.replace(",", "")
+    newText = newText.replace("-", " ")
+
+    # since the CV API changed, searches for series names with periods
+    # now explicitly require the period to be in the search key,
+    # so the line below is removed (for now)
+    #newText = newText.replace(".", "")
+
+    return newText
+
+
+def unique_file(file_name):
+    counter = 1
+    # returns ('/path/file', '.ext')
+    file_name_parts = os.path.splitext(file_name)
+    while True:
+        if not os.path.lexists(file_name):
+            return file_name
+        file_name = file_name_parts[
+            0] + ' (' + str(counter) + ')' + file_name_parts[1]
+        counter += 1
+
+
+# -o- coding: utf-8 -o-
+# ISO639 python dict
+# official list in http://www.loc.gov/standards/iso639-2/php/code_list.php
+
+lang_dict = {
+    'ab': 'Abkhaz',
+    'aa': 'Afar',
+    'af': 'Afrikaans',
+    'ak': 'Akan',
+    'sq': 'Albanian',
+    'am': 'Amharic',
+    'ar': 'Arabic',
+    'an': 'Aragonese',
+    'hy': 'Armenian',
+    'as': 'Assamese',
+    'av': 'Avaric',
+    'ae': 'Avestan',
+    'ay': 'Aymara',
+    'az': 'Azerbaijani',
+    'bm': 'Bambara',
+    'ba': 'Bashkir',
+    'eu': 'Basque',
+    'be': 'Belarusian',
+    'bn': 'Bengali',
+    'bh': 'Bihari',
+    'bi': 'Bislama',
+    'bs': 'Bosnian',
+    'br': 'Breton',
+    'bg': 'Bulgarian',
+    'my': 'Burmese',
+    'ca': 'Catalan; Valencian',
+    'ch': 'Chamorro',
+    'ce': 'Chechen',
+    'ny': 'Chichewa; Chewa; Nyanja',
+    'zh': 'Chinese',
+    'cv': 'Chuvash',
+    'kw': 'Cornish',
+    'co': 'Corsican',
+    'cr': 'Cree',
+    'hr': 'Croatian',
+    'cs': 'Czech',
+    'da': 'Danish',
+    'dv': 'Divehi; Maldivian;',
+    'nl': 'Dutch',
+    'dz': 'Dzongkha',
+    'en': 'English',
+    'eo': 'Esperanto',
+    'et': 'Estonian',
+    'ee': 'Ewe',
+    'fo': 'Faroese',
+    'fj': 'Fijian',
+    'fi': 'Finnish',
+    'fr': 'French',
+    'ff': 'Fula',
+    'gl': 'Galician',
+    'ka': 'Georgian',
+    'de': 'German',
+    'el': 'Greek, Modern',
+    'gn': 'Guaraní',
+    'gu': 'Gujarati',
+    'ht': 'Haitian',
+    'ha': 'Hausa',
+    'he': 'Hebrew (modern)',
+    'hz': 'Herero',
+    'hi': 'Hindi',
+    'ho': 'Hiri Motu',
+    'hu': 'Hungarian',
+    'ia': 'Interlingua',
+    'id': 'Indonesian',
+    'ie': 'Interlingue',
+    'ga': 'Irish',
+    'ig': 'Igbo',
+    'ik': 'Inupiaq',
+    'io': 'Ido',
+    'is': 'Icelandic',
+    'it': 'Italian',
+    'iu': 'Inuktitut',
+    'ja': 'Japanese',
+    'jv': 'Javanese',
+    'kl': 'Kalaallisut',
+    'kn': 'Kannada',
+    'kr': 'Kanuri',
+    'ks': 'Kashmiri',
+    'kk': 'Kazakh',
+    'km': 'Khmer',
+    'ki': 'Kikuyu, Gikuyu',
+    'rw': 'Kinyarwanda',
+    'ky': 'Kirghiz, Kyrgyz',
+    'kv': 'Komi',
+    'kg': 'Kongo',
+    'ko': 'Korean',
+    'ku': 'Kurdish',
+    'kj': 'Kwanyama, Kuanyama',
+    'la': 'Latin',
+    'lb': 'Luxembourgish',
+    'lg': 'Luganda',
+    'li': 'Limburgish',
+    'ln': 'Lingala',
+    'lo': 'Lao',
+    'lt': 'Lithuanian',
+    'lu': 'Luba-Katanga',
+    'lv': 'Latvian',
+    'gv': 'Manx',
+    'mk': 'Macedonian',
+    'mg': 'Malagasy',
+    'ms': 'Malay',
+    'ml': 'Malayalam',
+    'mt': 'Maltese',
+    'mi': 'Māori',
+    'mr': 'Marathi (Marāṭhī)',
+    'mh': 'Marshallese',
+    'mn': 'Mongolian',
+    'na': 'Nauru',
+    'nv': 'Navajo, Navaho',
+    'nb': 'Norwegian Bokmål',
+    'nd': 'North Ndebele',
+    'ne': 'Nepali',
+    'ng': 'Ndonga',
+    'nn': 'Norwegian Nynorsk',
+    'no': 'Norwegian',
+    'ii': 'Nuosu',
+    'nr': 'South Ndebele',
+    'oc': 'Occitan',
+    'oj': 'Ojibwe, Ojibwa',
+    'cu': 'Old Church Slavonic',
+    'om': 'Oromo',
+    'or': 'Oriya',
+    'os': 'Ossetian, Ossetic',
+    'pa': 'Panjabi, Punjabi',
+    'pi': 'Pāli',
+    'fa': 'Persian',
+    'pl': 'Polish',
+    'ps': 'Pashto, Pushto',
+    'pt': 'Portuguese',
+    'qu': 'Quechua',
+    'rm': 'Romansh',
+    'rn': 'Kirundi',
+    'ro': 'Romanian, Moldavan',
+    'ru': 'Russian',
+    'sa': 'Sanskrit (Saṁskṛta)',
+    'sc': 'Sardinian',
+    'sd': 'Sindhi',
+    'se': 'Northern Sami',
+    'sm': 'Samoan',
+    'sg': 'Sango',
+    'sr': 'Serbian',
+    'gd': 'Scottish Gaelic',
+    'sn': 'Shona',
+    'si': 'Sinhala, Sinhalese',
+    'sk': 'Slovak',
+    'sl': 'Slovene',
+    'so': 'Somali',
+    'st': 'Southern Sotho',
+    'es': 'Spanish; Castilian',
+    'su': 'Sundanese',
+    'sw': 'Swahili',
+    'ss': 'Swati',
+    'sv': 'Swedish',
+    'ta': 'Tamil',
+    'te': 'Telugu',
+    'tg': 'Tajik',
+    'th': 'Thai',
+    'ti': 'Tigrinya',
+    'bo': 'Tibetan',
+    'tk': 'Turkmen',
+    'tl': 'Tagalog',
+    'tn': 'Tswana',
+    'to': 'Tonga',
+    'tr': 'Turkish',
+    'ts': 'Tsonga',
+    'tt': 'Tatar',
+    'tw': 'Twi',
+    'ty': 'Tahitian',
+    'ug': 'Uighur, Uyghur',
+    'uk': 'Ukrainian',
+    'ur': 'Urdu',
+    'uz': 'Uzbek',
+    've': 'Venda',
+    'vi': 'Vietnamese',
+    'vo': 'Volapük',
+    'wa': 'Walloon',
+    'cy': 'Welsh',
+    'wo': 'Wolof',
+    'fy': 'Western Frisian',
+    'xh': 'Xhosa',
+    'yi': 'Yiddish',
+    'yo': 'Yoruba',
+    'za': 'Zhuang, Chuang',
+    'zu': 'Zulu',
+}
+
+
+countries = [
+    ('AF', 'Afghanistan'),
+    ('AL', 'Albania'),
+    ('DZ', 'Algeria'),
+    ('AS', 'American Samoa'),
+    ('AD', 'Andorra'),
+    ('AO', 'Angola'),
+    ('AI', 'Anguilla'),
+    ('AQ', 'Antarctica'),
+    ('AG', 'Antigua And Barbuda'),
+    ('AR', 'Argentina'),
+    ('AM', 'Armenia'),
+    ('AW', 'Aruba'),
+    ('AU', 'Australia'),
+    ('AT', 'Austria'),
+    ('AZ', 'Azerbaijan'),
+    ('BS', 'Bahamas'),
+    ('BH', 'Bahrain'),
+    ('BD', 'Bangladesh'),
+    ('BB', 'Barbados'),
+    ('BY', 'Belarus'),
+    ('BE', 'Belgium'),
+    ('BZ', 'Belize'),
+    ('BJ', 'Benin'),
+    ('BM', 'Bermuda'),
+    ('BT', 'Bhutan'),
+    ('BO', 'Bolivia'),
+    ('BA', 'Bosnia And Herzegowina'),
+    ('BW', 'Botswana'),
+    ('BV', 'Bouvet Island'),
+    ('BR', 'Brazil'),
+    ('BN', 'Brunei Darussalam'),
+    ('BG', 'Bulgaria'),
+    ('BF', 'Burkina Faso'),
+    ('BI', 'Burundi'),
+    ('KH', 'Cambodia'),
+    ('CM', 'Cameroon'),
+    ('CA', 'Canada'),
+    ('CV', 'Cape Verde'),
+    ('KY', 'Cayman Islands'),
+    ('CF', 'Central African Rep'),
+    ('TD', 'Chad'),
+    ('CL', 'Chile'),
+    ('CN', 'China'),
+    ('CX', 'Christmas Island'),
+    ('CC', 'Cocos Islands'),
+    ('CO', 'Colombia'),
+    ('KM', 'Comoros'),
+    ('CG', 'Congo'),
+    ('CK', 'Cook Islands'),
+    ('CR', 'Costa Rica'),
+    ('CI', 'Cote D`ivoire'),
+    ('HR', 'Croatia'),
+    ('CU', 'Cuba'),
+    ('CY', 'Cyprus'),
+    ('CZ', 'Czech Republic'),
+    ('DK', 'Denmark'),
+    ('DJ', 'Djibouti'),
+    ('DM', 'Dominica'),
+    ('DO', 'Dominican Republic'),
+    ('TP', 'East Timor'),
+    ('EC', 'Ecuador'),
+    ('EG', 'Egypt'),
+    ('SV', 'El Salvador'),
+    ('GQ', 'Equatorial Guinea'),
+    ('ER', 'Eritrea'),
+    ('EE', 'Estonia'),
+    ('ET', 'Ethiopia'),
+    ('FK', 'Falkland Islands (Malvinas)'),
+    ('FO', 'Faroe Islands'),
+    ('FJ', 'Fiji'),
+    ('FI', 'Finland'),
+    ('FR', 'France'),
+    ('GF', 'French Guiana'),
+    ('PF', 'French Polynesia'),
+    ('TF', 'French S. Territories'),
+    ('GA', 'Gabon'),
+    ('GM', 'Gambia'),
+    ('GE', 'Georgia'),
+    ('DE', 'Germany'),
+    ('GH', 'Ghana'),
+    ('GI', 'Gibraltar'),
+    ('GR', 'Greece'),
+    ('GL', 'Greenland'),
+    ('GD', 'Grenada'),
+    ('GP', 'Guadeloupe'),
+    ('GU', 'Guam'),
+    ('GT', 'Guatemala'),
+    ('GN', 'Guinea'),
+    ('GW', 'Guinea-bissau'),
+    ('GY', 'Guyana'),
+    ('HT', 'Haiti'),
+    ('HN', 'Honduras'),
+    ('HK', 'Hong Kong'),
+    ('HU', 'Hungary'),
+    ('IS', 'Iceland'),
+    ('IN', 'India'),
+    ('ID', 'Indonesia'),
+    ('IR', 'Iran'),
+    ('IQ', 'Iraq'),
+    ('IE', 'Ireland'),
+    ('IL', 'Israel'),
+    ('IT', 'Italy'),
+    ('JM', 'Jamaica'),
+    ('JP', 'Japan'),
+    ('JO', 'Jordan'),
+    ('KZ', 'Kazakhstan'),
+    ('KE', 'Kenya'),
+    ('KI', 'Kiribati'),
+    ('KP', 'Korea (North)'),
+    ('KR', 'Korea (South)'),
+    ('KW', 'Kuwait'),
+    ('KG', 'Kyrgyzstan'),
+    ('LA', 'Laos'),
+    ('LV', 'Latvia'),
+    ('LB', 'Lebanon'),
+    ('LS', 'Lesotho'),
+    ('LR', 'Liberia'),
+    ('LY', 'Libya'),
+    ('LI', 'Liechtenstein'),
+    ('LT', 'Lithuania'),
+    ('LU', 'Luxembourg'),
+    ('MO', 'Macau'),
+    ('MK', 'Macedonia'),
+    ('MG', 'Madagascar'),
+    ('MW', 'Malawi'),
+    ('MY', 'Malaysia'),
+    ('MV', 'Maldives'),
+    ('ML', 'Mali'),
+    ('MT', 'Malta'),
+    ('MH', 'Marshall Islands'),
+    ('MQ', 'Martinique'),
+    ('MR', 'Mauritania'),
+    ('MU', 'Mauritius'),
+    ('YT', 'Mayotte'),
+    ('MX', 'Mexico'),
+    ('FM', 'Micronesia'),
+    ('MD', 'Moldova'),
+    ('MC', 'Monaco'),
+    ('MN', 'Mongolia'),
+    ('MS', 'Montserrat'),
+    ('MA', 'Morocco'),
+    ('MZ', 'Mozambique'),
+    ('MM', 'Myanmar'),
+    ('NA', 'Namibia'),
+    ('NR', 'Nauru'),
+    ('NP', 'Nepal'),
+    ('NL', 'Netherlands'),
+    ('AN', 'Netherlands Antilles'),
+    ('NC', 'New Caledonia'),
+    ('NZ', 'New Zealand'),
+    ('NI', 'Nicaragua'),
+    ('NE', 'Niger'),
+    ('NG', 'Nigeria'),
+    ('NU', 'Niue'),
+    ('NF', 'Norfolk Island'),
+    ('MP', 'Northern Mariana Islands'),
+    ('NO', 'Norway'),
+    ('OM', 'Oman'),
+    ('PK', 'Pakistan'),
+    ('PW', 'Palau'),
+    ('PA', 'Panama'),
+    ('PG', 'Papua New Guinea'),
+    ('PY', 'Paraguay'),
+    ('PE', 'Peru'),
+    ('PH', 'Philippines'),
+    ('PN', 'Pitcairn'),
+    ('PL', 'Poland'),
+    ('PT', 'Portugal'),
+    ('PR', 'Puerto Rico'),
+    ('QA', 'Qatar'),
+    ('RE', 'Reunion'),
+    ('RO', 'Romania'),
+    ('RU', 'Russian Federation'),
+    ('RW', 'Rwanda'),
+    ('KN', 'Saint Kitts And Nevis'),
+    ('LC', 'Saint Lucia'),
+    ('VC', 'St Vincent/Grenadines'),
+    ('WS', 'Samoa'),
+    ('SM', 'San Marino'),
+    ('ST', 'Sao Tome'),
+    ('SA', 'Saudi Arabia'),
+    ('SN', 'Senegal'),
+    ('SC', 'Seychelles'),
+    ('SL', 'Sierra Leone'),
+    ('SG', 'Singapore'),
+    ('SK', 'Slovakia'),
+    ('SI', 'Slovenia'),
+    ('SB', 'Solomon Islands'),
+    ('SO', 'Somalia'),
+    ('ZA', 'South Africa'),
+    ('ES', 'Spain'),
+    ('LK', 'Sri Lanka'),
+    ('SH', 'St. Helena'),
+    ('PM', 'St.Pierre'),
+    ('SD', 'Sudan'),
+    ('SR', 'Suriname'),
+    ('SZ', 'Swaziland'),
+    ('SE', 'Sweden'),
+    ('CH', 'Switzerland'),
+    ('SY', 'Syrian Arab Republic'),
+    ('TW', 'Taiwan'),
+    ('TJ', 'Tajikistan'),
+    ('TZ', 'Tanzania'),
+    ('TH', 'Thailand'),
+    ('TG', 'Togo'),
+    ('TK', 'Tokelau'),
+    ('TO', 'Tonga'),
+    ('TT', 'Trinidad And Tobago'),
+    ('TN', 'Tunisia'),
+    ('TR', 'Turkey'),
+    ('TM', 'Turkmenistan'),
+    ('TV', 'Tuvalu'),
+    ('UG', 'Uganda'),
+    ('UA', 'Ukraine'),
+    ('AE', 'United Arab Emirates'),
+    ('UK', 'United Kingdom'),
+    ('US', 'United States'),
+    ('UY', 'Uruguay'),
+    ('UZ', 'Uzbekistan'),
+    ('VU', 'Vanuatu'),
+    ('VA', 'Vatican City State'),
+    ('VE', 'Venezuela'),
+    ('VN', 'Viet Nam'),
+    ('VG', 'Virgin Islands (British)'),
+    ('VI', 'Virgin Islands (U.S.)'),
+    ('EH', 'Western Sahara'),
+    ('YE', 'Yemen'),
+    ('YU', 'Yugoslavia'),
+    ('ZR', 'Zaire'),
+    ('ZM', 'Zambia'),
+    ('ZW', 'Zimbabwe')
+]
+
+
+def getLanguageDict():
+    return lang_dict
+
+
+def getLanguageFromISO(iso):
+    if iso is None:
+        return None
+    else:
+        return lang_dict[iso]

comicarchive.py

@@ -1,941 +0,0 @@
-"""
-A python class to represent a single comic, be it file or folder of images
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-import zipfile
-import os
-import struct
-import sys
-import tempfile
-import subprocess
-import platform
-if platform.system() == "Windows":
-	import _subprocess
-import time
-
-import StringIO
-try: 
-	import Image
-	pil_available = True
-except ImportError:
-	pil_available = False
-	
-sys.path.insert(0, os.path.abspath(".") )
-import UnRAR2
-from UnRAR2.rar_exceptions import *
-
-from options import Options, MetaDataStyle
-from comicinfoxml import ComicInfoXml
-from comicbookinfo import ComicBookInfo
-from comet import CoMet
-from genericmetadata import GenericMetadata, PageType
-from filenameparser import FileNameParser
-
-
-class ZipArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-	
-	def getArchiveComment( self ):
-		zf = zipfile.ZipFile( self.path, 'r' )
-		comment = zf.comment
-		zf.close()
-		return comment
-
-	def setArchiveComment( self, comment ):
-		return self.writeZipComment( self.path, comment )
-
-	def readArchiveFile( self, archive_file ):
-		data = ""
-		zf = zipfile.ZipFile( self.path, 'r' )
-		try:
-			data = zf.read( archive_file )
-		except zipfile.BadZipfile:
-			print "bad zipfile: {0} :: {1}".format(self.path, archive_file)
-		except Exception:
-			print "bad zipfile: {0} :: {1}".format(self.path, archive_file)
-		finally:
-			zf.close()
-		return data
-
-	def removeArchiveFile( self, archive_file ):
-		try:
-			self.rebuildZipFile(  [ archive_file ] )
-		except:
-			return False
-		else:
-			return True
-			
-	def writeArchiveFile( self, archive_file, data ):
-		#  At the moment, no other option but to rebuild the whole 
-		#  zip archive w/o the indicated file. Very sucky, but maybe 
-		# another solution can be found
-		try:
-			self.rebuildZipFile(  [ archive_file ] )
-			
-			#now just add the archive file as a new one
-			zf = zipfile.ZipFile(self.path, mode='a', compression=zipfile.ZIP_DEFLATED ) 
-			zf.writestr( archive_file, data )
-			zf.close()
-			return True
-		except:
-			return False
-			
-	def getArchiveFilenameList( self ):		
-		zf = zipfile.ZipFile( self.path, 'r' )
-		namelist = zf.namelist()
-		zf.close()
-		return namelist
-	
-	# zip helper func
-	def rebuildZipFile( self, exclude_list ):
-		
-		# this recompresses the zip archive, without the files in the exclude_list
-		#print "Rebuilding zip {0} without {1}".format( self.path, exclude_list )
-		
-		# generate temp file
-		tmp_fd, tmp_name = tempfile.mkstemp( dir=os.path.dirname(self.path) )
-		os.close( tmp_fd )
-		
-		zin = zipfile.ZipFile (self.path, 'r')
-		zout = zipfile.ZipFile (tmp_name, 'w')
-		for item in zin.infolist():
-			buffer = zin.read(item.filename)
-			if ( item.filename not in exclude_list ):
-				zout.writestr(item, buffer)
-		
-		#preserve the old comment
-		zout.comment = zin.comment
-		
-		zout.close()
-		zin.close()
-		
-		# replace with the new file 
-		os.remove( self.path )
-		os.rename( tmp_name, self.path )
-
-
-	def writeZipComment( self, filename, comment ):
-		"""
-		This is a custom function for writing a comment to a zip file,
-		since the built-in one doesn't seem to work on Windows and Mac OS/X
-
-		Fortunately, the zip comment is at the end of the file, and it's
-		easy to manipulate.  See this website for more info:
-		see: http://en.wikipedia.org/wiki/Zip_(file_format)#Structure
-		"""
-
-		#get file size
-		statinfo = os.stat(filename)
-		file_length = statinfo.st_size
-
-		try:
-			fo = open(filename, "r+b")
-
-			#the starting position, relative to EOF
-			pos = -4
-
-			found = False
-			value = bytearray()
-		
-			# walk backwards to find the "End of Central Directory" record
-			while ( not found ) and ( -pos != file_length ):
-				# seek, relative to EOF	
-				fo.seek( pos,  2)
-
-				value = fo.read( 4 )
-
-				#look for the end of central directory signature
-				if bytearray(value) == bytearray([ 0x50, 0x4b, 0x05, 0x06 ]):
-					found = True
-				else:
-					# not found, step back another byte
-					pos = pos - 1
-				#print pos,"{1} int: {0:x}".format(bytearray(value)[0], value)
-			
-			if found:
-				
-				# now skip forward 20 bytes to the comment length word
-				pos += 20
-				fo.seek( pos,  2)
-
-				# Pack the length of the comment string
-				format = "H"                   # one 2-byte integer
-				comment_length = struct.pack(format, len(comment)) # pack integer in a binary string
-				
-				# write out the length
-				fo.write( comment_length )
-				fo.seek( pos+2,  2)
-				
-				# write out the comment itself
-				fo.write( comment )
-				fo.truncate()
-				fo.close()
-			else:
-				raise Exception('Failed to write comment to zip file!')
-		except:
-			return False
-		else:
-			return True
-
-	def copyFromArchive( self, otherArchive ):
-		# Replace the current zip with one copied from another archive
-		try:		
-			zout = zipfile.ZipFile (self.path, 'w')
-			for fname in otherArchive.getArchiveFilenameList():
-				data = otherArchive.readArchiveFile( fname )
-				if data is not None:
-					zout.writestr( fname, data )
-			zout.close()
-			
-			#preserve the old comment
-			comment = otherArchive.getArchiveComment()
-			if comment is not None:
-				if not self.writeZipComment( self.path, comment ):
-					return False
-		except  Exception as e:
-			print "Error while copying to {0}: {1}".format(self.path, e)
-			return False
-		else:
-			return True
-
-		
-#------------------------------------------
-# RAR implementation
-	
-class RarArchiver:
-	
-	devnull = None
-	def __init__( self, path ):
-		self.path = path
-		self.rar_exe_path = None
-
-		if RarArchiver.devnull is None:
-			RarArchiver.devnull = open(os.devnull, "w")
-
-		# windows only, keeps the cmd.exe from popping up
-		if platform.system() == "Windows":
-			self.startupinfo = subprocess.STARTUPINFO()
-			self.startupinfo.dwFlags |= _subprocess.STARTF_USESHOWWINDOW
-		else:
-			self.startupinfo = None
-
-	def __del__(self):
-		#RarArchiver.devnull.close()
-		pass
-
-	def getArchiveComment( self ):
-		
-		rarc = self.getRARObj()
-		return rarc.comment		
-
-	def setArchiveComment( self, comment ):
-
-		if self.rar_exe_path is not None:
-			try:
-				# write comment to temp file
-				tmp_fd, tmp_name = tempfile.mkstemp()
-				f = os.fdopen(tmp_fd, 'w+b')
-				f.write( comment )		
-				f.close()
-
-				working_dir = os.path.dirname( os.path.abspath( self.path ) )
-
-				# use external program to write comment to Rar archive
-				subprocess.call([self.rar_exe_path, 'c', '-w' + working_dir , '-c-', '-z' + tmp_name, self.path], 
-					startupinfo=self.startupinfo, 
-					stdout=RarArchiver.devnull)
-				
-				if platform.system() == "Darwin":
-					time.sleep(1)
-					
-				os.remove( tmp_name)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def readArchiveFile( self, archive_file ):
-
-		# Make sure to escape brackets, since some funky stuff is going on
-		# underneath with "fnmatch"
-		archive_file = archive_file.replace("[", '[[]')
-		entries = []
-
-		rarc = self.getRARObj()
-
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				entries = rarc.read_files( archive_file )
-			
-			except (OSError, IOError) as e:
-				print e, "in readArchiveFile! try %s" % tries
-				time.sleep(1)
-			except Exception as e:
-				print "Unexpected exception in readArchiveFile! {0}".format( e )  
-				break
-
-			else:
-				#Success"
-				#entries is a list of of tuples:  ( rarinfo, filedata)
-				if (len(entries) == 1):
-					return entries[0][1]
-				else:
-					return None
-			
-		return None
-		
-
-		
-	def writeArchiveFile( self, archive_file, data ):
-
-		if self.rar_exe_path is not None:
-			try:
-				tmp_folder = tempfile.mkdtemp()
-
-				tmp_file = os.path.join( tmp_folder, archive_file )
-				
-				working_dir = os.path.dirname( os.path.abspath( self.path ) )
-
-				# TODO: will this break if 'archive_file' is in a subfolder. i.e. "foo/bar.txt"
-				# will need to create the subfolder above, I guess...
-				f = open(tmp_file, 'w')
-				f.write( data )		
-				f.close()
-				
-				# use external program to write file to Rar archive
-				subprocess.call([self.rar_exe_path, 'a', '-w' + working_dir ,'-c-', '-ep', self.path, tmp_file], 
-					startupinfo=self.startupinfo,
-					stdout=RarArchiver.devnull)
-
-				if platform.system() == "Darwin":
-					time.sleep(1)
-				os.remove( tmp_file)
-				os.rmdir( tmp_folder)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def removeArchiveFile( self, archive_file ):
-		if self.rar_exe_path is not None:
-			try:
-				# use external program to remove file from Rar archive
-				subprocess.call([self.rar_exe_path, 'd','-c-', self.path, archive_file], 
-					startupinfo=self.startupinfo, 				   
-					stdout=RarArchiver.devnull)
-
-				if platform.system() == "Darwin":
-					time.sleep(1)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def getArchiveFilenameList( self ):
-
-		rarc = self.getRARObj()
-		#namelist = [ item.filename for item in rarc.infolist() ]
-		#return namelist
-
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				namelist = [ item.filename for item in rarc.infolist() ]
-			
-			except (OSError, IOError) as e:
-				print e, "in getArchiveFilenameList! try %s" % tries
-				time.sleep(1)
-
-			else:
-				#Success"
-				return namelist
-			
-		raise e
-			
-		
-	def getRARObj( self ):
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				rarc = UnRAR2.RarFile( self.path )
-			
-			except (OSError, IOError) as e:
-				print e, "in getRARObj! try %s" % tries
-				time.sleep(1)
-
-			else:
-				#Success"
-				return rarc
-			
-		raise e
-		
-#------------------------------------------
-# Folder implementation
-class FolderArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-		self.comment_file_name = "ComicTaggerFolderComment.txt" 
-
-	def getArchiveComment( self ):
-		return self.readArchiveFile( self.comment_file_name )
-	
-	def setArchiveComment( self, comment ):
-		return self.writeArchiveFile( self.comment_file_name, comment )
-		
-	def readArchiveFile( self, archive_file ):
-		
-		data = ""
-		fname = os.path.join( self.path, archive_file )
-		try:
-			with open( fname, 'rb' ) as f: 
-				data = f.read()
-				f.close()			
-		except IOError as e:
-			pass
-		
-		return data
-
-	def writeArchiveFile( self, archive_file, data ):
-
-		fname = os.path.join( self.path, archive_file )
-		try:
-			with open(fname, 'w+') as f: 
-				f.write( data )
-				f.close()
-		except:
-			return False
-		else:
-			return True
-		
-	def removeArchiveFile( self, archive_file ):
-
-		fname = os.path.join( self.path, archive_file )
-		try:
-			os.remove( fname )
-		except:
-			return False
-		else:
-			return True
-		
-	def getArchiveFilenameList( self ):
-		return self.listFiles( self.path )
-		
-	def listFiles( self, folder ):
-		
-		itemlist = list()
-
-		for item in os.listdir( folder ):
-			itemlist.append( item )
-			if os.path.isdir( item ):
-				itemlist.extend( self.listFiles( os.path.join( folder, item ) ))
-
-		return itemlist
-
-#------------------------------------------
-# Unknown implementation
-class UnknownArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-
-	def getArchiveComment( self ):
-		return ""
-	def setArchiveComment( self, comment ):
-		return False
-	def readArchiveFilen( self ):
-		return ""
-	def writeArchiveFile( self, archive_file, data ):
-		return False
-	def removeArchiveFile( self, archive_file ):
-		return False
-	def getArchiveFilenameList( self ):
-		return []
-
-#------------------------------------------------------------------
-class ComicArchive:
-	
-	class ArchiveType:
-		Zip, Rar, Folder, Unknown = range(4)
-    
-	def __init__( self, path ):
-		self.path = path
-		self.ci_xml_filename = 'ComicInfo.xml'
-		self.comet_default_filename = 'CoMet.xml'
-		self.resetCache()
-		
-		if self.zipTest():
-			self.archive_type =  self.ArchiveType.Zip
-			self.archiver = ZipArchiver( self.path )
-			
-		elif self.rarTest(): 
-			self.archive_type =  self.ArchiveType.Rar
-			self.archiver = RarArchiver( self.path )
-			
-		elif os.path.isdir( self.path ):
-			self.archive_type =  self.ArchiveType.Folder
-			self.archiver = FolderArchiver( self.path )			
-		else:
-			self.archive_type =  self.ArchiveType.Unknown
-			self.archiver = UnknownArchiver( self.path )
-
-	# Clears the cached data
-	def resetCache( self ):
-		self.has_cix = None
-		self.has_cbi = None
-		self.has_comet = None
-		self.comet_filename = None
-		self.page_count  = None
-		self.page_list  = None
-		self.cix_md  = None
-		self.cbi_md  = None
-		self.comet_md  = None
-	
-	def rename( self, path ):
-		self.path = path
-		self.archiver.path = path
-		
-	def setExternalRarProgram( self, rar_exe_path ):
-		if self.isRar():
-			self.archiver.rar_exe_path = rar_exe_path
-
-	def zipTest( self ):
-		return zipfile.is_zipfile( self.path )
-
-	def rarTest( self ):
-		try:
-			rarc = UnRAR2.RarFile( self.path )
-		except: # InvalidRARArchive:
-			return False
-		else:
-			return True
-
-			
-	def isZip( self ):
-		return self.archive_type ==  self.ArchiveType.Zip
-		
-	def isRar( self ):
-		return self.archive_type ==  self.ArchiveType.Rar
-	
-	def isFolder( self ):
-		return self.archive_type ==  self.ArchiveType.Folder
-
-	def isWritable( self, check_rar_status=True ):	
-		if self.archive_type == self.ArchiveType.Unknown :
-			return False
-		
-		elif check_rar_status and self.isRar() and self.archiver.rar_exe_path is None:
-			return False
-			
-		elif not os.access(self.path, os.W_OK):
-			return False
-		
-		elif ((self.archive_type != self.ArchiveType.Folder) and 
-		        (not os.access( os.path.dirname( os.path.abspath(self.path)), os.W_OK ))):
-			return False
-
-		return True
-
-	def isWritableForStyle( self, data_style ):
-
-		if self.isRar() and data_style == MetaDataStyle.CBI:
-			return False
-
-		return self.isWritable()
-
-	def seemsToBeAComicArchive( self ):
-
-		# Do we even care about extensions??
-		ext = os.path.splitext(self.path)[1].lower()
-
-		if ( 
-		      ( self.isZip() or  self.isRar() or self.isFolder() )
-		      and
-		      ( self.getNumberOfPages() > 2)
-
-			):
-			return True
-		else:	
-			return False
-
-	def readMetadata( self, style ):
-		
-		if style == MetaDataStyle.CIX:
-			return self.readCIX()
-		elif style == MetaDataStyle.CBI:
-			return self.readCBI()
-		elif style == MetaDataStyle.COMET:
-			return self.readCoMet()
-		else:
-			return GenericMetadata()
-
-	def writeMetadata( self, metadata, style ):
-		
-		retcode = None
-		if style == MetaDataStyle.CIX:
-			retcode = self.writeCIX( metadata )
-		elif style == MetaDataStyle.CBI:
-			retcode = self.writeCBI( metadata )
-		elif style == MetaDataStyle.COMET:
-			retcode = self.writeCoMet( metadata )
-		return retcode
-		
-
-	def hasMetadata( self, style ):
-		
-		if style == MetaDataStyle.CIX:
-			return self.hasCIX()
-		elif style == MetaDataStyle.CBI:
-			return self.hasCBI()
-		elif style == MetaDataStyle.COMET:
-			return self.hasCoMet()
-		else:
-			return False
-	
-	def removeMetadata( self, style ):
-		retcode = True
-		if style == MetaDataStyle.CIX:
-			retcode = self.removeCIX()
-		elif style == MetaDataStyle.CBI:
-			retcode = self.removeCBI()
-		elif style == MetaDataStyle.COMET:
-			retcode = self.removeCoMet()
-		return retcode
-
-	def getPage( self, index ):
-		
-		image_data = None
-		
-		filename = self.getPageName( index )
-
-		if filename is not None:
-			image_data = self.archiver.readArchiveFile( filename )
-
-		return image_data
-
-	def getPageName( self, index ):
-		
-		page_list = self.getPageNameList()
-		
-		num_pages = len( page_list )
-		if num_pages == 0 or index >= num_pages:
-			return None
-	
-		return  page_list[index]
-
-	def getPageNameList( self , sort_list=True):
-		
-		if self.page_list is None:
-			# get the list file names in the archive, and sort
-			files = self.archiver.getArchiveFilenameList()
-			
-			# seems like some archive creators are on  Windows, and don't know about case-sensitivity!
-			if sort_list:
-				files.sort(key=lambda x: x.lower())
-			
-			# make a sub-list of image files
-			self.page_list = []
-			for name in files:
-				if ( name[-4:].lower() in [ ".jpg", "jpeg", ".png" ] and os.path.basename(name)[0] != "." ):
-					self.page_list.append(name)
-				
-		return self.page_list
-
-	def getNumberOfPages( self ):
-		
-		if self.page_count is None:
-			self.page_count = len( self.getPageNameList( ) )
-		return self.page_count
-
-	def readCBI( self ):
-		if self.cbi_md is None:
-			raw_cbi = self.readRawCBI()
-			if raw_cbi is None:
-				self.cbi_md = GenericMetadata()
-			else:
-				self.cbi_md = ComicBookInfo().metadataFromString( raw_cbi )
-			
-			self.cbi_md.setDefaultPageList( self.getNumberOfPages() )
-				
-		return self.cbi_md
-	
-	def readRawCBI( self ):
-		if ( not self.hasCBI() ):
-			return None
-
-		return self.archiver.getArchiveComment()
-
-	def hasCBI(self):
-		if self.has_cbi is None:
-
-			#if ( not ( self.isZip() or self.isRar()) or not self.seemsToBeAComicArchive() ): 
-			if not self.seemsToBeAComicArchive(): 
-				self.has_cbi = False
-			else:
-				comment = self.archiver.getArchiveComment()
-				self.has_cbi = ComicBookInfo().validateString( comment )
-			
-		return self.has_cbi
-	
-	def writeCBI( self, metadata ):
-		if metadata is not None:
-			self.applyArchiveInfoToMetadata( metadata )
-			cbi_string = ComicBookInfo().stringFromMetadata( metadata )
-			write_success =  self.archiver.setArchiveComment( cbi_string )
-			if write_success:
-				self.has_cbi = True
-				self.cbi_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-		
-	def removeCBI( self ):
-		if self.hasCBI():
-			write_success = self.archiver.setArchiveComment( "" )
-			if write_success:
-				self.has_cbi = False
-				self.cbi_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True	
-		
-	def readCIX( self ):
-		if self.cix_md is None:
-			raw_cix = self.readRawCIX()
-			if raw_cix is None:
-				self.cix_md = GenericMetadata()
-			else:
-				self.cix_md = ComicInfoXml().metadataFromString( raw_cix )
-
-			#validate the existing page list (make sure count is correct)
-			if len ( self.cix_md.pages ) !=  0 :
-				if len ( self.cix_md.pages ) != self.getNumberOfPages():
-					# pages array doesn't match the actual number of images we're seeing
-					# in the archive, so discard the data
-					self.cix_md.pages = []
-				
-			if len( self.cix_md.pages ) == 0:
-				self.cix_md.setDefaultPageList( self.getNumberOfPages() )
-			
-		return self.cix_md
-
-	def readRawCIX( self ):
-		if not self.hasCIX():
-			return None
-
-		return  self.archiver.readArchiveFile( self.ci_xml_filename )
-		
-	def writeCIX(self, metadata):
-
-		if metadata is not None:
-			self.applyArchiveInfoToMetadata( metadata, calc_page_sizes=True )
-			cix_string = ComicInfoXml().stringFromMetadata( metadata )
-			write_success = self.archiver.writeArchiveFile( self.ci_xml_filename, cix_string )
-			if write_success:
-				self.has_cix = True
-				self.cix_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-			
-	def removeCIX( self ):
-		if self.hasCIX():
-			write_success = self.archiver.removeArchiveFile( self.ci_xml_filename )
-			if write_success:
-				self.has_cix = False
-				self.cix_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True
-		
-		
-	def hasCIX(self):
-		if self.has_cix is None:
-
-			if not self.seemsToBeAComicArchive():
-				self.has_cix = False
-			elif self.ci_xml_filename in self.archiver.getArchiveFilenameList():
-				self.has_cix = True
-			else:
-				self.has_cix = False
-		return self.has_cix
-
-
-	def readCoMet( self ):
-		if self.comet_md is None:
-			raw_comet = self.readRawCoMet()
-			if raw_comet is None:
-				self.comet_md = GenericMetadata()
-			else:
-				self.comet_md = CoMet().metadataFromString( raw_comet )
-			
-			self.comet_md.setDefaultPageList( self.getNumberOfPages() )
-			#use the coverImage value from the comet_data to mark the cover in this struct
-			# walk through list of images in file, and find the matching one for md.coverImage
-			# need to remove the existing one in the default
-			if self.comet_md.coverImage is not None:
-				cover_idx = 0
-				for idx,f in enumerate(self.getPageNameList()):
-					if self.comet_md.coverImage == f:
-						cover_idx = idx
-						break
-				if cover_idx != 0:
-					del (self.comet_md.pages[0]['Type'] )
-					self.comet_md.pages[ cover_idx ]['Type'] = PageType.FrontCover
-
-		return self.comet_md	
-
-	def readRawCoMet( self ):
-		if not self.hasCoMet():
-			print self.path, "doesn't have CoMet data!"
-			return None
-
-		return self.archiver.readArchiveFile( self.comet_filename )
-		
-	def writeCoMet(self, metadata):
-
-		if metadata is not None:
-			if not self.hasCoMet():
-				self.comet_filename = self.comet_default_filename
-			
-			self.applyArchiveInfoToMetadata( metadata )
-			# Set the coverImage value, if it's not the first page
-			cover_idx = int(metadata.getCoverPageIndexList()[0])
-			if cover_idx != 0:
-				metadata.coverImage = self.getPageName( cover_idx )
-		
-			comet_string = CoMet().stringFromMetadata( metadata )
-			write_success = self.archiver.writeArchiveFile( self.comet_filename, comet_string )
-			if write_success:
-				self.has_comet = True
-				self.comet_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-			
-	def removeCoMet( self ):
-		if self.hasCoMet():
-			write_success = self.archiver.removeArchiveFile( self.comet_filename )
-			if write_success:
-				self.has_comet = False
-				self.comet_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True
-		
-	def hasCoMet(self):
-		if self.has_comet is None:
-			self.has_comet = False
-			if not self.seemsToBeAComicArchive():
-				return self.has_comet
-			
-			#look at all xml files in root, and search for CoMet data, get first
-			for n in self.archiver.getArchiveFilenameList():
-				if ( os.path.dirname(n) == "" and
-					os.path.splitext(n)[1].lower() == '.xml'):
-					# read in XML file, and validate it
-					data = self.archiver.readArchiveFile( n )
-					if CoMet().validateString( data ):
-						# since we found it, save it!
-						self.comet_filename = n
-						self.has_comet = True
-						break
-						
-			return self.has_comet
-				
-
-
-	def applyArchiveInfoToMetadata( self, md, calc_page_sizes=False):
-		md.pageCount = self.getNumberOfPages()
-		
-		if calc_page_sizes:
-			for p in md.pages:
-				idx = int( p['Image'] )
-				if pil_available:
-					if 'ImageSize' not in p or 'ImageHeight' not in p or 'ImageWidth' not in p:
-						data = self.getPage( idx )
-						if data is not None:
-							try:
-								im = Image.open(StringIO.StringIO(data))
-								w,h = im.size
-								
-								p['ImageSize'] = str(len(data))
-								p['ImageHeight'] = str(h)
-								p['ImageWidth'] = str(w)
-							except IOError:
-								p['ImageSize'] = str(len(data))
-									
-				else:
-					if 'ImageSize' not in p:
-						data = self.getPage( idx )
-						p['ImageSize'] = str(len(data))
-
-
-			
-	def metadataFromFilename( self ):
-		 
-		metadata = GenericMetadata()
-		
-		fnp = FileNameParser()
-		fnp.parseFilename( self.path )
-
-		if fnp.issue != "":
-			metadata.issue = fnp.issue
-		if fnp.series != "":
-			metadata.series = fnp.series
-		if fnp.volume != "":
-			metadata.volume = fnp.volume
-		if fnp.year != "":
-			metadata.year = fnp.year
-		if fnp.issue_count != "":
-			metadata.issueCount = fnp.issue_count
-
-		metadata.isEmpty = False
-
-		return metadata
-
-	def exportAsZip( self, zipfilename ):
-		if self.archive_type == self.ArchiveType.Zip:
-			# nothing to do, we're already a zip
-			return True
-		
-		zip_archiver = ZipArchiver( zipfilename )
-		return zip_archiver.copyFromArchive( self.archiver )
-		

comicbookinfo.py

@@ -1,152 +0,0 @@
-"""
-A python class to encapsulate the ComicBookInfo data 
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-
-import json
-from datetime import datetime
-import zipfile
-
-from genericmetadata import GenericMetadata
-import utils
-import ctversion
-
-class ComicBookInfo:
-		 
-
-	def metadataFromString( self, string ):
-	
-		cbi_container = json.loads( unicode(string, 'utf-8') )
-
-		metadata = GenericMetadata()
-
-		cbi = cbi_container[ 'ComicBookInfo/1.0' ]
-
-		#helper func 
-		# If item is not in CBI, return None
-		def xlate( cbi_entry):
-			if cbi_entry in cbi:
-				return cbi[cbi_entry] 
-			else:	
-				return None 
-		
-		metadata.series =            xlate( 'series' )
-		metadata.title =             xlate( 'title' )
-		metadata.issue =             xlate( 'issue' )
-		metadata.publisher =         xlate( 'publisher' )
-		metadata.month =             xlate( 'publicationMonth' )
-		metadata.year =              xlate( 'publicationYear' )
-		metadata.issueCount =        xlate( 'numberOfIssues' )
-		metadata.comments =          xlate( 'comments' )
-		metadata.credits =           xlate( 'credits' )
-		metadata.genre =             xlate( 'genre' )
-		metadata.volume =            xlate( 'volume' )
-		metadata.volumeCount =       xlate( 'numberOfVolumes' )
-		metadata.language =          xlate( 'language' )
-		metadata.country =           xlate( 'country' )
-		metadata.criticalRating =    xlate( 'rating' )
-		metadata.tags =              xlate( 'tags' )
-		
-		# make sure credits and tags are at least empty lists and not None
-		if metadata.credits is None:
-			metadata.credits = []
-		if metadata.tags is None:
-			metadata.tags = []
-			
-		#need to massage the language string to be ISO
-		if metadata.language is not None:
-			# reverse look-up
-			pattern = metadata.language
-			metadata.language = None
-			for key in utils.getLanguageDict():
-				if utils.getLanguageDict()[ key ] == pattern.encode('utf-8'):
-					metadata.language = key
-					break
-		
-		metadata.isEmpty = False
-		
-		return metadata
-
-	def stringFromMetadata( self, metadata ):
-
-		cbi_container = self.createJSONDictionary( metadata )
-		return json.dumps( cbi_container )
-	
-	#verify that the string actually contains CBI data in JSON format
-	def validateString( self, string ):
-		
-		try:
-			cbi_container = json.loads( string )
-		except:
-			return False
-			
-		return ( 'ComicBookInfo/1.0' in cbi_container )
-
-
-	def createJSONDictionary( self, metadata ):
-		
-		# Create the dictionary that we will convert to JSON text
-		cbi = dict()
-		cbi_container = {'appID' : 'ComicTagger/' + ctversion.version, 
-		                 'lastModified' : str(datetime.now()), 
-		                 'ComicBookInfo/1.0' : cbi }
-		
-		#helper func
-		def assign( cbi_entry, md_entry):
-			if md_entry is not None:
-				cbi[cbi_entry] = md_entry
-			
-		#helper func
-		def toInt(s):
-			i = None
-			if type(s) == str or type(s) == int:
-				try:
-					i = int(s)
-				except ValueError:
-					pass
-			return i
-				
-		assign( 'series', metadata.series )
-		assign( 'title', metadata.title )
-		assign( 'issue', metadata.issue )
-		assign( 'publisher', metadata.publisher )
-		assign( 'publicationMonth', toInt(metadata.month) )
-		assign( 'publicationYear', toInt(metadata.year) )
-		assign( 'numberOfIssues', toInt(metadata.issueCount) )
-		assign( 'comments', metadata.comments )
-		assign( 'genre', metadata.genre )
-		assign( 'volume', toInt(metadata.volume) )
-		assign( 'numberOfVolumes', toInt(metadata.volumeCount) )
-		assign( 'language', utils.getLanguageFromISO(metadata.language) )
-		assign( 'country', metadata.country )
-		assign( 'rating', metadata.criticalRating )
-		assign( 'credits', metadata.credits )
-		assign( 'tags', metadata.tags )
-		
-		return cbi_container
-	
-
-	def writeToExternalFile( self, filename,  metadata ):
-
-		cbi_container = self.createJSONDictionary(metadata)
-
-		f = open(filename, 'w')
-		f.write(json.dumps(cbi_container, indent=4))
-		f.close
-

comicinfoxml.py

@@ -1,289 +0,0 @@
-"""
-A python class to encapsulate ComicRack's ComicInfo.xml data 
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-from datetime import datetime
-import zipfile
-from pprint import pprint 
-import xml.etree.ElementTree as ET
-from genericmetadata import GenericMetadata
-import utils
-
-class ComicInfoXml:
-	
-	writer_synonyms = ['writer', 'plotter', 'scripter']
-	penciller_synonyms = [ 'artist', 'penciller', 'penciler', 'breakdowns' ]
-	inker_synonyms = [ 'inker', 'artist', 'finishes' ]
-	colorist_synonyms = [ 'colorist', 'colourist', 'colorer', 'colourer' ]
-	letterer_synonyms = [ 'letterer']
-	cover_synonyms = [ 'cover', 'covers', 'coverartist', 'cover artist' ]
-	editor_synonyms = [ 'editor']
-
-
-	def getParseableCredits( self ):
-		parsable_credits =  []
-		parsable_credits.extend( self.writer_synonyms )
-		parsable_credits.extend( self.penciller_synonyms )
-		parsable_credits.extend( self.inker_synonyms )
-		parsable_credits.extend( self.colorist_synonyms )
-		parsable_credits.extend( self.letterer_synonyms )
-		parsable_credits.extend( self.cover_synonyms )
-		parsable_credits.extend( self.editor_synonyms )		
-		return parsable_credits
-		
-	def metadataFromString( self, string ):
-
-		tree = ET.ElementTree(ET.fromstring( string ))
-		return self.convertXMLToMetadata( tree )
-
-	def stringFromMetadata( self, metadata ):
-
-		header = '<?xml version="1.0"?>\n'
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		return header + ET.tostring(tree.getroot())
-
-	def indent( self, elem, level=0 ):
-		# for making the XML output readable
-		i = "\n" + level*"  "
-		if len(elem):
-			if not elem.text or not elem.text.strip():
-				elem.text = i + "  "
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-			for elem in elem:
-				self.indent( elem, level+1 )
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-		else:
-			if level and (not elem.tail or not elem.tail.strip()):
-				elem.tail = i
-	
-	def convertMetadataToXML( self, filename, metadata ):
-
-		#shorthand for the metadata
-		md = metadata
-
-		# build a tree structure
-		root = ET.Element("ComicInfo")
-		root.attrib['xmlns:xsi']="http://www.w3.org/2001/XMLSchema-instance"
-		root.attrib['xmlns:xsd']="http://www.w3.org/2001/XMLSchema"
-		#helper func
-		def assign( cix_entry, md_entry):
-			if md_entry is not None:
-				ET.SubElement(root, cix_entry).text = u"{0}".format(md_entry)
-
-		assign( 'Series', md.series )
-		assign( 'Number', md.issue )
-		assign( 'Title', md.title )
-		assign( 'Count', md.issueCount )
-		assign( 'Volume', md.volume )
-		assign( 'AlternateSeries', md.alternateSeries )
-		assign( 'AlternateNumber', md.alternateNumber )
-		assign( 'AlternateCount', md.alternateCount )
-		assign( 'Summary', md.comments )
-		assign( 'Notes', md.notes )
-		assign( 'Year', md.year )
-		assign( 'Month', md.month )
-		assign( 'Publisher', md.publisher )
-		assign( 'Imprint', md.imprint )
-		assign( 'Genre', md.genre )
-		assign( 'Web', md.webLink )
-		assign( 'PageCount', md.pageCount )
-		assign( 'Format', md.format )
-		assign( 'LanguageISO', md.language )
-		assign( 'Manga', md.manga )
-		assign( 'Characters', md.characters )
-		assign( 'Teams', md.teams )
-		assign( 'Locations', md.locations )
-		assign( 'ScanInformation', md.scanInfo )
-		assign( 'StoryArc', md.storyArc )
-		assign( 'SeriesGroup', md.seriesGroup )
-		assign( 'AgeRating', md.maturityRating )
-
-		if md.blackAndWhite is not None and md.blackAndWhite:
-			ET.SubElement(root, 'BlackAndWhite').text = "Yes"
-
-		# need to specially process the credits, since they are structured differently than CIX	
-		credit_writer_list    = list()
-		credit_penciller_list = list()
-		credit_inker_list     = list()
-		credit_colorist_list  = list()
-		credit_letterer_list  = list()
-		credit_cover_list     = list()
-		credit_editor_list    = list()
-		
-		# first, loop thru credits, and build a list for each role that CIX supports
-		for credit in metadata.credits:
-
-			if credit['role'].lower() in set( self.writer_synonyms ):
-				credit_writer_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.penciller_synonyms ):
-				credit_penciller_list.append(credit['person'].replace(",",""))
-				
-			if credit['role'].lower() in set( self.inker_synonyms ):
-				credit_inker_list.append(credit['person'].replace(",",""))
-				
-			if credit['role'].lower() in set( self.colorist_synonyms ):
-				credit_colorist_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.letterer_synonyms ):
-				credit_letterer_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.cover_synonyms ):
-				credit_cover_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.editor_synonyms ):
-				credit_editor_list.append(credit['person'].replace(",",""))
-				
-		# second, convert each list to string, and add to XML struct
-		if len( credit_writer_list ) > 0:
-			node = ET.SubElement(root, 'Writer')
-			node.text = utils.listToString( credit_writer_list )
-
-		if len( credit_penciller_list ) > 0:
-			node = ET.SubElement(root, 'Penciller')
-			node.text = utils.listToString( credit_penciller_list )
-
-		if len( credit_inker_list ) > 0:
-			node = ET.SubElement(root, 'Inker')
-			node.text = utils.listToString( credit_inker_list )
-
-		if len( credit_colorist_list ) > 0:
-			node = ET.SubElement(root, 'Colorist')
-			node.text = utils.listToString( credit_colorist_list )
-
-		if len( credit_letterer_list ) > 0:
-			node = ET.SubElement(root, 'Letterer')
-			node.text = utils.listToString( credit_letterer_list )
-
-		if len( credit_cover_list ) > 0:
-			node = ET.SubElement(root, 'CoverArtist')
-			node.text = utils.listToString( credit_cover_list )
-		
-		if len( credit_editor_list ) > 0:
-			node = ET.SubElement(root, 'Editor')
-			node.text = utils.listToString( credit_editor_list )
-		
-		#  loop and add the page entries under pages node
-		if len( md.pages ) > 0:
-			pages_node = ET.SubElement(root, 'Pages')
-			for page_dict in md.pages:
-				page_node = ET.SubElement(pages_node, 'Page')
-				page_node.attrib = page_dict
-
-		# self pretty-print
-		self.indent(root)
-
-		# wrap it in an ElementTree instance, and save as XML
-		tree = ET.ElementTree(root)
-		return tree
-				 
-
-	def convertXMLToMetadata( self, tree ):
-			
-		root = tree.getroot()
-
-		if root.tag != 'ComicInfo':
-			raise 1
-			return None
-
-		metadata = GenericMetadata()
-		md = metadata
-	
-		
-		# Helper function
-		def xlate( tag ):
-			node = root.find( tag )
-			if node is not None:
-				return node.text
-			else:
-				return None
-				
-		md.series =           xlate( 'Series' )
-		md.title =            xlate( 'Title' )
-		md.issue =            xlate( 'Number' )
-		md.issueCount =       xlate( 'Count' )
-		md.volume =           xlate( 'Volume' )
-		md.alternateSeries =  xlate( 'AlternateSeries' )
-		md.alternateNumber =  xlate( 'AlternateNumber' )
-		md.alternateCount =   xlate( 'AlternateCount' )
-		md.comments =         xlate( 'Summary' )
-		md.notes =            xlate( 'Notes' )
-		md.year =             xlate( 'Year' )
-		md.month =            xlate( 'Month' )
-		md.publisher =        xlate( 'Publisher' )
-		md.imprint =          xlate( 'Imprint' )
-		md.genre =            xlate( 'Genre' )
-		md.webLink =          xlate( 'Web' )
-		md.language =         xlate( 'LanguageISO' )
-		md.format =           xlate( 'Format' )
-		md.manga =            xlate( 'Manga' )
-		md.characters =       xlate( 'Characters' )
-		md.teams =            xlate( 'Teams' )
-		md.locations =        xlate( 'Locations' )
-		md.pageCount =        xlate( 'PageCount' )
-		md.scanInfo =         xlate( 'ScanInformation' )
-		md.storyArc =         xlate( 'StoryArc' )
-		md.seriesGroup =      xlate( 'SeriesGroup' )
-		md.maturityRating =   xlate( 'AgeRating' )
-
-		tmp = xlate( 'BlackAndWhite' )
-		md.blackAndWhite = False
-		if tmp is not None and tmp.lower() in [ "yes", "true", "1" ]:
-			md.blackAndWhite = True
-		# Now extract the credit info
-		for n in root:
-			if (  n.tag == 'Writer' or 
-				n.tag == 'Penciller' or
-				n.tag == 'Inker' or
-				n.tag == 'Colorist' or
-				n.tag == 'Letterer' or
-				n.tag == 'Editor' 
-			):
-				for name in n.text.split(','):
-					metadata.addCredit( name.strip(), n.tag )
-
-			if n.tag == 'CoverArtist':
-				for name in n.text.split(','):
-					metadata.addCredit( name.strip(), "Cover" )
-
-		# parse page data now	
-		pages_node = root.find( "Pages" )
-		if pages_node is not None:			
-			for page in pages_node:
-				metadata.pages.append( page.attrib )
-				#print page.attrib
-
-		metadata.isEmpty = False
-		
-		return metadata
-
-	def writeToExternalFile( self, filename, metadata ):
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		#ET.dump(tree)		
-		tree.write(filename, encoding='utf-8')
-	
-	def readFromExternalFile( self, filename ):
-
-		tree = ET.parse( filename )
-		return self.convertXMLToMetadata( tree )
-

comictagger.py

@@ -1,506 +1,5 @@
-#!/usr/bin/python
+#!/usr/bin/env python3
+from comictaggerlib.main import ctmain
 
-"""
-A python script to tag comic archives
-"""
-
-"""
-Copyright 2012  Anthony Beville
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-	http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-"""
-
-import sys
-import signal
-import os
-import traceback
-import time
-from pprint import pprint
-import json
-import platform
-import locale
-
-filename_encoding = sys.getfilesystemencoding()
-	
-try:
-	qt_available = True
-	from PyQt4 import QtCore, QtGui
-	from taggerwindow import TaggerWindow
-except ImportError as e:
-	qt_available = False
-
-
-from settings import ComicTaggerSettings
-from options import Options, MetaDataStyle
-from comicarchive import ComicArchive
-from issueidentifier import IssueIdentifier
-from genericmetadata import GenericMetadata
-from comicvinetalker import ComicVineTalker, ComicVineTalkerException
-from filerenamer import FileRenamer
-from cbltransformer import CBLTransformer
-
-import utils
-import codecs
-
-class MultipleMatch():
-	def __init__( self, filename, match_list):
-		self.filename = filename  
-		self.matches = match_list  
-
-class OnlineMatchResults():
-	def __init__(self):
-		self.goodMatches = []  
-		self.noMatches = []    
-		self.multipleMatches = []  
-		self.writeFailures = []  
-
-#-----------------------------
-
-def actual_issue_data_fetch( match, settings ):
-
-	# now get the particular issue data
-	try:
-		cv_md = ComicVineTalker().fetchIssueData( match['volume_id'],  match['issue_number'], settings )
-	except ComicVineTalkerException:
-		print "Network error while getting issue details.  Save aborted"
-		return None
-
-	if settings.apply_cbl_transform_on_cv_import:
-		cv_md = CBLTransformer( cv_md, settings ).apply()
-		
-	return cv_md
-
-def actual_metadata_save( ca, opts, md ):
-
-	if not opts.dryrun:
-		# write out the new data
-		if not ca.writeMetadata( md, opts.data_style ):
-			print "The tag save seemed to fail!"
-			return False
-		else:
-			print "Save complete."				
-	else:
-		if opts.terse:
-			print "dry-run option was set, so nothing was written"
-		else:
-			print "dry-run option was set, so nothing was written, but here is the final set of tags:"
-			print u"{0}".format(md)
-	return True
-		
-
-def post_process_matches( match_results, opts, settings ):
-	# now go through the match results
-	if opts.show_save_summary:
-		if len( match_results.goodMatches ) > 0:
-			print "\nSuccessful matches:"
-			print "------------------"
-			for f in match_results.goodMatches:
-				print f
-				
-		if len( match_results.noMatches ) > 0:
-			print "\nNo matches:"
-			print "------------------"
-			for f in match_results.noMatches:
-				print f
-	
-		if len( match_results.writeFailures ) > 0:
-			print "\nFile Write Failures:"
-			print "------------------"
-			for f in match_results.writeFailures:
-				print f
-
-	if not opts.show_save_summary and not opts.interactive:
-		#jusr quit if we're not interactive or showing the summary
-		return
-	
-	if len( match_results.multipleMatches ) > 0:
-		print "\nMultiple matches:"
-		print "------------------"
-		for mm in match_results.multipleMatches:
-			print mm.filename
-			for (counter,m) in enumerate(mm.matches):
-				print u"  {0}. {1} #{2} [{3}] ({4}/{5}) - {6}".format(counter,
-											   m['series'],
-											   m['issue_number'],
-											   m['publisher'],
-											   m['month'],
-											   m['year'],
-											   m['issue_title'])
-			if opts.interactive:
-				while True:
-					i = raw_input("Choose a match #, or 's' to skip: ")
-					if (i.isdigit() and int(i) in range(len(mm.matches))) or i == 's':
-						break
-				if i != 's':
-					# save the data!
-					# we know at this point, that the file is all good to go
-					ca = ComicArchive( mm.filename )
-					md = create_local_metadata( opts, ca, ca.hasMetadata(opts.data_style) )
-					cv_md = actual_issue_data_fetch(mm.matches[int(i)], settings)
-					md.overlay( cv_md )
-					actual_metadata_save( ca, opts, md )
-					
-					
-			print
-
-
-def cli_mode( opts, settings ):
-	if len( opts.file_list ) < 1:
-		print "You must specify at least one filename.  Use the -h option for more info"
-		return
-	
-	match_results = OnlineMatchResults()
-	
-	for f in opts.file_list:
-		f = f.decode(filename_encoding, 'replace')
-		process_file_cli( f, opts, settings, match_results )
-		sys.stdout.flush()
-		
-	post_process_matches( match_results, opts, settings )	
-
-
-def create_local_metadata( opts, ca, has_desired_tags ):
-	
-	md = GenericMetadata()
-	md.setDefaultPageList( ca.getNumberOfPages() )
-	
-	if has_desired_tags:
-		md = ca.readMetadata( opts.data_style )
-		
-	# now, overlay the parsed filename info	
-	if opts.parse_filename:
-		md.overlay( ca.metadataFromFilename() )
-	
-	# finally, use explicit stuff	
-	if opts.metadata is not None:
-		md.overlay( opts.metadata )
-
-	return md
-
-def process_file_cli( filename, opts, settings, match_results ):
-
-	batch_mode = len( opts.file_list ) > 1
-		
-	ca = ComicArchive(filename)
-	if settings.rar_exe_path != "":
-		ca.setExternalRarProgram( settings.rar_exe_path )	
-	
-	if not ca.seemsToBeAComicArchive():
-		print "Sorry, but "+ filename + "  is not a comic archive!"
-		return
-	
-	#if not ca.isWritableForStyle( opts.data_style ) and ( opts.delete_tags or opts.save_tags or opts.rename_file ):
-	if not ca.isWritable(  ) and ( opts.delete_tags or opts.copy_tags or opts.save_tags or opts.rename_file ):
-		print "This archive is not writable for that tag type"
-		return
-
-	has = [ False, False, False ]
-	if ca.hasCIX(): has[ MetaDataStyle.CIX ] = True
-	if ca.hasCBI(): has[ MetaDataStyle.CBI ] = True
-	if ca.hasCoMet(): has[ MetaDataStyle.COMET ] = True
-
-	if opts.print_tags:
-
-
-		if opts.data_style is None:
-			page_count = ca.getNumberOfPages()
-
-			brief = ""
-
-			if batch_mode:
-				brief = "{0}: ".format(filename)
-
-			if ca.isZip():      brief += "ZIP archive    "
-			elif ca.isRar():    brief += "RAR archive    "
-			elif ca.isFolder(): brief += "Folder archive "
-				
-			brief += "({0: >3} pages)".format(page_count)			
-			brief += "  tags:[ "
-
-			if not ( has[ MetaDataStyle.CBI ] or has[ MetaDataStyle.CIX ] or has[ MetaDataStyle.COMET ] ):
-				brief += "none "
-			else:
-				if has[ MetaDataStyle.CBI ]: brief += "CBL "
-				if has[ MetaDataStyle.CIX ]: brief += "CR "
-				if has[ MetaDataStyle.COMET ]: brief += "CoMet "
-			brief += "]"
-				
-			print brief
-
-		if opts.terse:
-			return
-
-		print
-		
-		if opts.data_style is None or opts.data_style == MetaDataStyle.CIX:
-			if has[ MetaDataStyle.CIX ]:
-				print "------ComicRack tags--------"
-				if opts.raw:
-					print u"{0}".format(unicode(ca.readRawCIX(), errors='ignore'))
-				else:
-					print u"{0}".format(ca.readCIX())
-				
-		if opts.data_style is None or opts.data_style == MetaDataStyle.CBI:
-			if has[ MetaDataStyle.CBI ]:
-				print "------ComicBookLover tags--------"
-				if opts.raw:
-					pprint(json.loads(ca.readRawCBI()))
-				else:
-					print u"{0}".format(ca.readCBI())
-					
-		if opts.data_style is None or opts.data_style == MetaDataStyle.COMET:
-			if has[ MetaDataStyle.COMET ]:
-				print "------CoMet tags--------"
-				if opts.raw:
-					print u"{0}".format(ca.readRawCoMet())
-				else:
-					print u"{0}".format(ca.readCoMet())
-			
-			
-	elif opts.delete_tags:
-		style_name = MetaDataStyle.name[ opts.data_style ]
-		if has[ opts.data_style ]:
-			if not opts.dryrun:
-				if not ca.removeMetadata( opts.data_style ):
-					print "{0}: Tag removal seemed to fail!".format( filename )
-				else:
-					print "{0}: Removed {1} tags.".format( filename, style_name )
-			else:
-				print "{0}: dry-run.  {1} tags not removed".format( filename, style_name )		
-		else:
-			print "{0}: This archive doesn't have {1} tags to remove.".format( filename, style_name )
-
-	elif opts.copy_tags:
-		dst_style_name = MetaDataStyle.name[ opts.data_style ]
-		if opts.no_overwrite and has[ opts.data_style ]:
-			print "{0}: Already has {1} tags.  Not overwriting.".format(filename, dst_style_name)
-			return
-		if opts.copy_source == opts.data_style:
-			print "{0}: Destination and source are same: {1}.  Nothing to do.".format(filename, dst_style_name)
-			return
-			
-		src_style_name = MetaDataStyle.name[ opts.copy_source ]
-		if has[ opts.copy_source ]:
-			if not opts.dryrun:
-				md = ca.readMetadata( opts.copy_source )
-				
-				if settings.apply_cbl_transform_on_bulk_operation and opts.data_style == MetaDataStyle.CBI:
-					md = CBLTransformer( md, settings ).apply()
-				
-				if not ca.writeMetadata( md, opts.data_style ):
-					print u"{0}: Tag copy seemed to fail!".format( filename )
-				else:
-					print u"{0}: Copied {1} tags to {2} .".format( filename, src_style_name, dst_style_name )
-			else:
-				print u"{0}: dry-run.  {1} tags not copied".format( filename, src_style_name )		
-		else:
-			print u"{0}: This archive doesn't have {1} tags to copy.".format( filename, src_style_name )
-
-		
-	elif opts.save_tags:
-
-		if opts.no_overwrite and has[ opts.data_style ]:
-			print u"{0}: Already has {1} tags.  Not overwriting.".format(filename, MetaDataStyle.name[ opts.data_style ])
-			return
-		
-		if batch_mode:
-			print u"Processing {0}: ".format(filename)
-			
-		md = create_local_metadata( opts, ca, has[ opts.data_style ] )
-
-		# now, search online
-		if opts.search_online:
-			if opts.issue_id is not None:
-				# we were given the actual ID to search with
-				try:
-					cv_md = ComicVineTalker().fetchIssueDataByIssueID( opts.issue_id, settings )
-				except ComicVineTalkerException:
-					print "Network error while getting issue details.  Save aborted"
-					return None
-				
-				if cv_md is None:
-					print "No match for ID {0} was found.".format(opts.issue_id)
-					return None
-				
-				if settings.apply_cbl_transform_on_cv_import:
-					cv_md = CBLTransformer( cv_md, settings ).apply()
-			else:
-				ii = IssueIdentifier( ca, settings )
-	
-				if md is None or md.isEmpty:
-					print "No metadata given to search online with!"
-					return
-	
-				def myoutput( text ):
-					if opts.verbose:
-						IssueIdentifier.defaultWriteOutput( text )
-					
-				# use our overlayed MD struct to search
-				ii.setAdditionalMetadata( md )
-				ii.onlyUseAdditionalMetaData = True
-				ii.setOutputFunction( myoutput )
-				ii.cover_page_index = md.getCoverPageIndexList()[0]
-				matches = ii.search()
-				
-				result = ii.search_result
-				
-				found_match = False
-				choices = False
-				low_confidence = False
-				
-				if result == ii.ResultNoMatches:
-					pass
-				elif result == ii.ResultFoundMatchButBadCoverScore:
-					low_confidence = True
-					found_match = True
-				elif result == ii.ResultFoundMatchButNotFirstPage :
-					found_match = True
-				elif result == ii.ResultMultipleMatchesWithBadImageScores:
-					low_confidence = True
-					choices = True
-				elif result == ii.ResultOneGoodMatch:
-					found_match = True
-				elif result == ii.ResultMultipleGoodMatches:
-					choices = True
-	
-				if choices:
-					print "Online search: Multiple matches.  Save aborted"
-					match_results.multipleMatches.append(MultipleMatch(filename,matches))
-					return
-				if low_confidence and opts.abortOnLowConfidence:
-					print "Online search: Low confidence match.  Save aborted"
-					match_results.noMatches.append(filename)
-					return
-				if not found_match:
-					print "Online search: No match found.  Save aborted"
-					match_results.noMatches.append(filename)
-					return
-	
-	
-				# we got here, so we have a single match
-				
-				# now get the particular issue data
-				cv_md = actual_issue_data_fetch(matches[0], settings)
-				if cv_md is None:
-					return
-			
-			md.overlay( cv_md )
-			
-		# ok, done building our metadata. time to save
-		if not actual_metadata_save( ca, opts, md ):
-				match_results.writeFailures.append(filename)
-		else:
-				match_results.goodMatches.append(filename)
-
-	elif opts.rename_file:
-
-		msg_hdr = ""
-		if batch_mode:
-			msg_hdr = u"{0}: ".format(filename)
-
-		if opts.data_style is not None:
-			use_tags = has[ opts.data_style ]
-		else:
-			use_tags = False
-			
-		md = create_local_metadata( opts, ca, use_tags )
-		
-		if md.series is None:
-			print msg_hdr + "Can't rename without series name"
-			return
-
-		new_ext = None  # default
-		if settings.rename_extension_based_on_archive:
-			if ca.isZip():
-				new_ext = ".cbz"
-			elif ca.isRar():
-				new_ext = ".cbr"
-			
-		renamer = FileRenamer( md )
-		renamer.setTemplate( settings.rename_template )
-		renamer.setIssueZeroPadding( settings.rename_issue_number_padding )
-		renamer.setSmartCleanup( settings.rename_use_smart_string_cleanup )
-		
-		new_name = renamer.determineName( filename, ext=new_ext )
-			
-		if new_name == os.path.basename(filename):
-			print msg_hdr + "Filename is already good!"
-			return
-		
-		folder = os.path.dirname( os.path.abspath( filename ) )
-		new_abs_path = utils.unique_file( os.path.join( folder, new_name ) )
-
-		suffix = ""
-		if not opts.dryrun:
-			# rename the file
-			os.rename( filename, new_abs_path )
-		else:
-			suffix = " (dry-run, no change)"
-
-		print u"renamed '{0}' -> '{1}' {2}".format(os.path.basename(filename), new_name, suffix)
-
-
-			
-		
-#-----------------------------
-
-def main():
-	
-	# try to make stdout encodings happy for unicode
-	sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
-
-	opts = Options()
-	opts.parseCmdLineArgs()
-
-	settings = ComicTaggerSettings()
-	# make sure unrar program is in the path for the UnRAR class
-	utils.addtopath(os.path.dirname(settings.unrar_exe_path))
-	
-	signal.signal(signal.SIGINT, signal.SIG_DFL)
-	
-	if not qt_available and not opts.no_gui:
-		opts.no_gui = True
-		print "QT is not available."
-	
-	if opts.no_gui:
-		cli_mode( opts, settings )
-		
-	else:
-
-		app = QtGui.QApplication(sys.argv)
-		
-		if platform.system() != "Linux":
-			img =  QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/tags.png' ))
-			splash = QtGui.QSplashScreen(img)
-			splash.show()
-			splash.raise_()
-			app.processEvents()
-	
-		try:			
-			tagger_window = TaggerWindow( opts.file_list, settings )
-			tagger_window.show()
-
-			if platform.system() != "Linux":
-				splash.finish( tagger_window )
-
-			sys.exit(app.exec_())
-		except Exception, e:
-			QtGui.QMessageBox.critical(QtGui.QMainWindow(), "Error", "Unhandled exception in app:\n" + traceback.format_exc() )
-			
-			
-if __name__ == "__main__":
-	main()
-    
-    
-    
-    
+if __name__ == '__main__':
+    ctmain()

comictagger.spec

@@ -0,0 +1,57 @@
+# -*- mode: python -*-
+
+import platform
+from os.path import join
+from comictaggerlib import ctversion
+
+enable_console = False
+binaries = []
+block_cipher = None
+
+if platform.system() == "Windows":
+    from site import getsitepackages
+    sitepackages = getsitepackages()[1]
+    # add ssl qt libraries not discovered automatically
+    binaries.extend([
+        (join(sitepackages, "PyQt5/Qt/bin/libeay32.dll"), "./PyQt5/Qt/bin"),
+        (join(sitepackages, "PyQt5/Qt/bin/ssleay32.dll"), "./PyQt5/Qt/bin")
+    ])
+    enable_console = True
+
+a = Analysis(['comictagger.py'],
+             binaries=binaries,
+             datas=[('comictaggerlib/ui/*.ui', 'ui'), ('comictaggerlib/graphics', 'graphics')],
+             hiddenimports=['PIL'],
+             hookspath=[],
+             runtime_hooks=[],
+             excludes=[],
+             win_no_prefer_redirects=False,
+             win_private_assemblies=False,
+             cipher=block_cipher)
+pyz = PYZ(a.pure, a.zipped_data,
+             cipher=block_cipher)
+exe = EXE(pyz,
+          a.scripts,
+          a.binaries,
+          a.zipfiles,
+          a.datas,
+          # single file setup
+          exclude_binaries=False,
+          name='comictagger',
+          debug=False,
+          strip=False,
+          upx=True,
+          console=enable_console,
+          icon="windows/app.ico" )
+
+app = BUNDLE(exe,
+            name='ComicTagger.app',
+            icon='mac/app.icns',
+            info_plist={
+                'NSHighResolutionCapable': 'True',
+                'NSRequiresAquaSystemAppearance': 'False',
+                'CFBundleDisplayName': 'ComicTagger',
+                'CFBundleShortVersionString': ctversion.version,
+                'CFBundleVersion': ctversion.version
+            },
+            bundle_identifier=None)

comictaggerlib/autotagmatchwindow.py

@@ -0,0 +1,245 @@
+"""A PyQT4 dialog to select from automated issue matches"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+#import sys
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+#from PyQt5.QtCore import QUrl, pyqtSignal, QByteArray
+
+from .settings import ComicTaggerSettings
+from .comicarchive import MetaDataStyle
+from .coverimagewidget import CoverImageWidget
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize
+#from imagefetcher import ImageFetcher
+#from comicvinetalker import ComicVineTalker
+#import utils
+
+
+class AutoTagMatchWindow(QtWidgets.QDialog):
+
+    volume_id = 0
+
+    def __init__(self, parent, match_set_list, style, fetch_func):
+        super(AutoTagMatchWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('matchselectionwindow.ui'), self)
+
+        self.altCoverWidget = CoverImageWidget(
+            self.altCoverContainer, CoverImageWidget.AltCoverMode)
+        gridlayout = QtWidgets.QGridLayout(self.altCoverContainer)
+        gridlayout.addWidget(self.altCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.archiveCoverWidget = CoverImageWidget(
+            self.archiveCoverContainer, CoverImageWidget.ArchiveMode)
+        gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
+        gridlayout.addWidget(self.archiveCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        reduceWidgetFontSize(self.twList)
+        reduceWidgetFontSize(self.teDescription, 1)
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        self.skipButton = QtWidgets.QPushButton(self.tr("Skip to Next"))
+        self.buttonBox.addButton(
+            self.skipButton, QtWidgets.QDialogButtonBox.ActionRole)
+        self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText(
+            "Accept and Write Tags")
+
+        self.match_set_list = match_set_list
+        self.style = style
+        self.fetch_func = fetch_func
+
+        self.current_match_set_idx = 0
+
+        self.twList.currentItemChanged.connect(self.currentItemChanged)
+        self.twList.cellDoubleClicked.connect(self.cellDoubleClicked)
+        self.skipButton.clicked.connect(self.skipToNext)
+
+        self.updateData()
+
+    def updateData(self):
+
+        self.current_match_set = self.match_set_list[
+            self.current_match_set_idx]
+
+        if self.current_match_set_idx + 1 == len(self.match_set_list):
+            self.buttonBox.button(
+                QtWidgets.QDialogButtonBox.Cancel).setDisabled(True)
+            # self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText("Accept")
+            self.skipButton.setText(self.tr("Skip"))
+
+        self.setCoverImage()
+        self.populateTable()
+        self.twList.resizeColumnsToContents()
+        self.twList.selectRow(0)
+
+        path = self.current_match_set.ca.path
+        self.setWindowTitle(
+            "Select correct match or skip ({0} of {1}): {2}".format(
+                self.current_match_set_idx + 1,
+                len(self.match_set_list),
+                os.path.split(path)[1])
+        )
+
+    def populateTable(self):
+
+        while self.twList.rowCount() > 0:
+            self.twList.removeRow(0)
+
+        self.twList.setSortingEnabled(False)
+
+        row = 0
+        for match in self.current_match_set.matches:
+            self.twList.insertRow(row)
+
+            item_text = match['series']
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setData(QtCore.Qt.UserRole, (match,))
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 0, item)
+
+            if match['publisher'] is not None:
+                item_text = "{0}".format(match['publisher'])
+            else:
+                item_text = "Unknown"
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 1, item)
+
+            month_str = ""
+            year_str = "????"
+            if match['month'] is not None:
+                month_str = "-{0:02d}".format(int(match['month']))
+            if match['year'] is not None:
+                year_str = "{0}".format(match['year'])
+
+            item_text = year_str + month_str
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 2, item)
+
+            item_text = match['issue_title']
+            if item_text is None:
+                item_text = ""
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 3, item)
+
+            row += 1
+
+        self.twList.resizeColumnsToContents()
+        self.twList.setSortingEnabled(True)
+        self.twList.sortItems(2, QtCore.Qt.AscendingOrder)
+        self.twList.selectRow(0)
+        self.twList.resizeColumnsToContents()
+        self.twList.horizontalHeader().setStretchLastSection(True)
+
+    def cellDoubleClicked(self, r, c):
+        self.accept()
+
+    def currentItemChanged(self, curr, prev):
+
+        if curr is None:
+            return
+        if prev is not None and prev.row() == curr.row():
+            return
+
+        self.altCoverWidget.setIssueID(self.currentMatch()['issue_id'])
+        if self.currentMatch()['description'] is None:
+            self.teDescription.setText("")
+        else:
+            self.teDescription.setText(self.currentMatch()['description'])
+
+    def setCoverImage(self):
+        ca = self.current_match_set.ca
+        self.archiveCoverWidget.setArchive(ca)
+
+    def currentMatch(self):
+        row = self.twList.currentRow()
+        match = self.twList.item(row, 0).data(
+            QtCore.Qt.UserRole)[0]
+        return match
+
+    def accept(self):
+
+        self.saveMatch()
+        self.current_match_set_idx += 1
+
+        if self.current_match_set_idx == len(self.match_set_list):
+            # no more items
+            QtWidgets.QDialog.accept(self)
+        else:
+            self.updateData()
+
+    def skipToNext(self):
+        self.current_match_set_idx += 1
+
+        if self.current_match_set_idx == len(self.match_set_list):
+            # no more items
+            QtWidgets.QDialog.reject(self)
+        else:
+            self.updateData()
+
+    def reject(self):
+        reply = QtWidgets.QMessageBox.question(
+            self,
+            self.tr("Cancel Matching"),
+            self.tr("Are you sure you wish to cancel the matching process?"),
+            QtWidgets.QMessageBox.Yes,
+            QtWidgets.QMessageBox.No)
+
+        if reply == QtWidgets.QMessageBox.No:
+            return
+
+        QtWidgets.QDialog.reject(self)
+
+    def saveMatch(self):
+
+        match = self.currentMatch()
+        ca = self.current_match_set.ca
+
+        md = ca.readMetadata(self.style)
+        if md.isEmpty:
+            md = ca.metadataFromFilename()
+
+        # now get the particular issue data
+        cv_md = self.fetch_func(match)
+        if cv_md is None:
+            QtWidgets.QMessageBox.critical(self, self.tr("Network Issue"), self.tr(
+                "Could not connect to Comic Vine to get issue details!"))
+            return
+
+        QtWidgets.QApplication.setOverrideCursor(
+            QtGui.QCursor(QtCore.Qt.WaitCursor))
+        md.overlay(cv_md)
+        success = ca.writeMetadata(md, self.style)
+        ca.loadCache([MetaDataStyle.CBI, MetaDataStyle.CIX])
+
+        QtWidgets.QApplication.restoreOverrideCursor()
+
+        if not success:
+            QtWidgets.QMessageBox.warning(self, self.tr("Write Error"), self.tr(
+                "Saving the tags to the archive seemed to fail!"))

comictaggerlib/autotagprogresswindow.py

@@ -0,0 +1,69 @@
+"""A PyQT4 dialog to show ID log and progress"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import sys
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+from .coverimagewidget import CoverImageWidget
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize
+#import utils
+
+
+class AutoTagProgressWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent):
+        super(AutoTagProgressWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('autotagprogresswindow.ui'), self)
+
+        self.archiveCoverWidget = CoverImageWidget(
+            self.archiveCoverContainer, CoverImageWidget.DataMode, False)
+        gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
+        gridlayout.addWidget(self.archiveCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.testCoverWidget = CoverImageWidget(
+            self.testCoverContainer, CoverImageWidget.DataMode, False)
+        gridlayout = QtWidgets.QGridLayout(self.testCoverContainer)
+        gridlayout.addWidget(self.testCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.isdone = False
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        reduceWidgetFontSize(self.textEdit)
+
+    def setArchiveImage(self, img_data):
+        self.setCoverImage(img_data, self.archiveCoverWidget)
+
+    def setTestImage(self, img_data):
+        self.setCoverImage(img_data, self.testCoverWidget)
+
+    def setCoverImage(self, img_data, widget):
+        widget.setImageData(img_data)
+        QtCore.QCoreApplication.processEvents()
+        QtCore.QCoreApplication.processEvents()
+
+    def reject(self):
+        QtWidgets.QDialog.reject(self)
+        self.isdone = True

comictaggerlib/autotagstartwindow.py

@@ -0,0 +1,127 @@
+"""A PyQT4 dialog to confirm and set options for auto-tag"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+#from settingswindow import SettingsWindow
+#from filerenamer import FileRenamer
+#import utils
+
+
+class AutoTagStartWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent, settings, msg):
+        super(AutoTagStartWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('autotagstartwindow.ui'), self)
+        self.label.setText(msg)
+
+        self.setWindowFlags(self.windowFlags() &
+                            ~QtCore.Qt.WindowContextHelpButtonHint)
+
+        self.settings = settings
+
+        self.cbxSaveOnLowConfidence.setCheckState(QtCore.Qt.Unchecked)
+        self.cbxDontUseYear.setCheckState(QtCore.Qt.Unchecked)
+        self.cbxAssumeIssueOne.setCheckState(QtCore.Qt.Unchecked)
+        self.cbxIgnoreLeadingDigitsInFilename.setCheckState(
+            QtCore.Qt.Unchecked)
+        self.cbxRemoveAfterSuccess.setCheckState(QtCore.Qt.Unchecked)
+        self.cbxSpecifySearchString.setCheckState(QtCore.Qt.Unchecked)
+        self.leNameLengthMatchTolerance.setText(
+            str(self.settings.id_length_delta_thresh))
+        self.leSearchString.setEnabled(False)
+
+        if self.settings.save_on_low_confidence:
+            self.cbxSaveOnLowConfidence.setCheckState(QtCore.Qt.Checked)
+        if self.settings.dont_use_year_when_identifying:
+            self.cbxDontUseYear.setCheckState(QtCore.Qt.Checked)
+        if self.settings.assume_1_if_no_issue_num:
+            self.cbxAssumeIssueOne.setCheckState(QtCore.Qt.Checked)
+        if self.settings.ignore_leading_numbers_in_filename:
+            self.cbxIgnoreLeadingDigitsInFilename.setCheckState(
+                QtCore.Qt.Checked)
+        if self.settings.remove_archive_after_successful_match:
+            self.cbxRemoveAfterSuccess.setCheckState(QtCore.Qt.Checked)
+        if self.settings.wait_and_retry_on_rate_limit:
+            self.cbxWaitForRateLimit.setCheckState(QtCore.Qt.Checked)
+
+        nlmtTip = (
+            """ <html>The <b>Name Length Match Tolerance</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The higher
+                it is, the more likely to have a good match, but each search will take longer and
+                use more bandwidth. Too low, and only the very closest lexical matches will be
+                explored.</html>""")
+
+        self.leNameLengthMatchTolerance.setToolTip(nlmtTip)
+
+        ssTip = (
+            """<html>
+            The <b>series search string</b> specifies the search string to be used for all selected archives.
+            Use this when trying to match archives with hard-to-parse or incorrect filenames.  All archives selected
+            should be from the same series.
+            </html>"""
+        )
+        self.leSearchString.setToolTip(ssTip)
+        self.cbxSpecifySearchString.setToolTip(ssTip)
+
+        validator = QtGui.QIntValidator(0, 99, self)
+        self.leNameLengthMatchTolerance.setValidator(validator)
+
+        self.cbxSpecifySearchString.stateChanged.connect(
+            self.searchStringToggle)
+
+        self.autoSaveOnLow = False
+        self.dontUseYear = False
+        self.assumeIssueOne = False
+        self.ignoreLeadingDigitsInFilename = False
+        self.removeAfterSuccess = False
+        self.waitAndRetryOnRateLimit = False
+        self.searchString = None
+        self.nameLengthMatchTolerance = self.settings.id_length_delta_thresh
+
+    def searchStringToggle(self):
+        enable = self.cbxSpecifySearchString.isChecked()
+        self.leSearchString.setEnabled(enable)
+
+    def accept(self):
+        QtWidgets.QDialog.accept(self)
+
+        self.autoSaveOnLow = self.cbxSaveOnLowConfidence.isChecked()
+        self.dontUseYear = self.cbxDontUseYear.isChecked()
+        self.assumeIssueOne = self.cbxAssumeIssueOne.isChecked()
+        self.ignoreLeadingDigitsInFilename = self.cbxIgnoreLeadingDigitsInFilename.isChecked()
+        self.removeAfterSuccess = self.cbxRemoveAfterSuccess.isChecked()
+        self.nameLengthMatchTolerance = int(
+            self.leNameLengthMatchTolerance.text())
+        self.waitAndRetryOnRateLimit = self.cbxWaitForRateLimit.isChecked()
+
+        # persist some settings
+        self.settings.save_on_low_confidence = self.autoSaveOnLow
+        self.settings.dont_use_year_when_identifying = self.dontUseYear
+        self.settings.assume_1_if_no_issue_num = self.assumeIssueOne
+        self.settings.ignore_leading_numbers_in_filename = self.ignoreLeadingDigitsInFilename
+        self.settings.remove_archive_after_successful_match = self.removeAfterSuccess
+        self.settings.wait_and_retry_on_rate_limit = self.waitAndRetryOnRateLimit
+
+        if self.cbxSpecifySearchString.isChecked():
+            self.searchString = str(self.leSearchString.text())
+            if len(self.searchString) == 0:
+                self.searchString = None

comictaggerlib/cbltransformer.py

@@ -0,0 +1,97 @@
+"""A class to manage modifying metadata specifically for CBL/CBI"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+#import utils
+
+
+class CBLTransformer:
+
+    def __init__(self, metadata, settings):
+        self.metadata = metadata
+        self.settings = settings
+
+    def apply(self):
+        # helper funcs
+        def append_to_tags_if_unique(item):
+            if item.lower() not in (tag.lower() for tag in self.metadata.tags):
+                self.metadata.tags.append(item)
+
+        def add_string_list_to_tags(str_list):
+            if str_list is not None and str_list != "":
+                items = [s.strip() for s in str_list.split(',')]
+                for item in items:
+                    append_to_tags_if_unique(item)
+
+        if self.settings.assume_lone_credit_is_primary:
+
+            # helper
+            def setLonePrimary(role_list):
+                lone_credit = None
+                count = 0
+                for c in self.metadata.credits:
+                    if c['role'].lower() in role_list:
+                        count += 1
+                        lone_credit = c
+                    if count > 1:
+                        lone_credit = None
+                        break
+                if lone_credit is not None:
+                    lone_credit['primary'] = True
+                return lone_credit, count
+
+            # need to loop three times, once for 'writer', 'artist', and then
+            # 'penciler' if no artist
+            setLonePrimary(['writer'])
+            c, count = setLonePrimary(['artist'])
+            if c is None and count == 0:
+                c, count = setLonePrimary(['penciler', 'penciller'])
+                if c is not None:
+                    c['primary'] = False
+                    self.metadata.addCredit(c['person'], 'Artist', True)
+
+        if self.settings.copy_characters_to_tags:
+            add_string_list_to_tags(self.metadata.characters)
+
+        if self.settings.copy_teams_to_tags:
+            add_string_list_to_tags(self.metadata.teams)
+
+        if self.settings.copy_locations_to_tags:
+            add_string_list_to_tags(self.metadata.locations)
+
+        if self.settings.copy_storyarcs_to_tags:
+            add_string_list_to_tags(self.metadata.storyArc)
+
+        if self.settings.copy_notes_to_comments:
+            if self.metadata.notes is not None:
+                if self.metadata.comments is None:
+                    self.metadata.comments = ""
+                else:
+                    self.metadata.comments += "\n\n"
+                if self.metadata.notes not in self.metadata.comments:
+                    self.metadata.comments += self.metadata.notes
+
+        if self.settings.copy_weblink_to_comments:
+            if self.metadata.webLink is not None:
+                if self.metadata.comments is None:
+                    self.metadata.comments = ""
+                else:
+                    self.metadata.comments += "\n\n"
+                if self.metadata.webLink not in self.metadata.comments:
+                    self.metadata.comments += self.metadata.webLink
+
+        return self.metadata

comictaggerlib/cli.py

@@ -0,0 +1,584 @@
+#!/usr/bin/python
+
+"""ComicTagger CLI functions"""
+
+# Copyright 2013 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sys
+import os
+from pprint import pprint
+import json
+#import signal
+#import traceback
+#import time
+#import platform
+#import locale
+#import codecs
+
+filename_encoding = sys.getfilesystemencoding()
+
+from .settings import ComicTaggerSettings
+from .options import Options
+from .comicarchive import ComicArchive, MetaDataStyle
+from .issueidentifier import IssueIdentifier
+from .genericmetadata import GenericMetadata
+from .comicvinetalker import ComicVineTalker, ComicVineTalkerException
+from .filerenamer import FileRenamer
+from .cbltransformer import CBLTransformer
+from . import utils
+
+
+class MultipleMatch():
+
+    def __init__(self, filename, match_list):
+        self.filename = filename
+        self.matches = match_list
+
+
+class OnlineMatchResults():
+
+    def __init__(self):
+        self.goodMatches = []
+        self.noMatches = []
+        self.multipleMatches = []
+        self.lowConfidenceMatches = []
+        self.writeFailures = []
+        self.fetchDataFailures = []
+
+#-----------------------------
+
+
+def actual_issue_data_fetch(match, settings, opts):
+
+    # now get the particular issue data
+    try:
+        comicVine = ComicVineTalker()
+        comicVine.wait_for_rate_limit = opts.wait_and_retry_on_rate_limit
+        cv_md = comicVine.fetchIssueData(
+            match['volume_id'], match['issue_number'], settings)
+    except ComicVineTalkerException:
+        print("Network error while getting issue details.  Save aborted", file=sys.stderr)
+        return None
+
+    if settings.apply_cbl_transform_on_cv_import:
+        cv_md = CBLTransformer(cv_md, settings).apply()
+
+    return cv_md
+
+
+def actual_metadata_save(ca, opts, md):
+
+    if not opts.dryrun:
+        # write out the new data
+        if not ca.writeMetadata(md, opts.data_style):
+            print("The tag save seemed to fail!", file=sys.stderr)
+            return False
+        else:
+            print("Save complete.", file=sys.stderr)
+    else:
+        if opts.terse:
+            print("dry-run option was set, so nothing was written", file=sys.stderr)
+        else:
+            print("dry-run option was set, so nothing was written, but here is the final set of tags:", file=sys.stderr)
+            print(("{0}".format(md)))
+    return True
+
+
+def display_match_set_for_choice(label, match_set, opts, settings):
+    print(("{0} -- {1}:".format(match_set.filename, label)))
+
+    # sort match list by year
+    match_set.matches.sort(key=lambda k: k['year'])
+
+    for (counter, m) in enumerate(match_set.matches):
+        counter += 1
+        print((
+            "    {0}. {1} #{2} [{3}] ({4}/{5}) - {6}".format(
+                counter,
+                m['series'],
+                m['issue_number'],
+                m['publisher'],
+                m['month'],
+                m['year'],
+                m['issue_title'])))
+    if opts.interactive:
+        while True:
+            i = input("Choose a match #, or 's' to skip: ")
+            if (i.isdigit() and int(i) in range(
+                    1, len(match_set.matches) + 1)) or i == 's':
+                break
+        if i != 's':
+            i = int(i) - 1
+            # save the data!
+            # we know at this point, that the file is all good to go
+            ca = ComicArchive(
+                match_set.filename,
+                settings.rar_exe_path,
+                ComicTaggerSettings.getGraphic('nocover.png'))
+            md = create_local_metadata(
+                opts, ca, ca.hasMetadata(opts.data_style))
+            cv_md = actual_issue_data_fetch(
+                match_set.matches[int(i)], settings, opts)
+            md.overlay(cv_md)
+            actual_metadata_save(ca, opts, md)
+
+
+def post_process_matches(match_results, opts, settings):
+    # now go through the match results
+    if opts.show_save_summary:
+        if len(match_results.goodMatches) > 0:
+            print("\nSuccessful matches:\n------------------")
+            for f in match_results.goodMatches:
+                print(f)
+
+        if len(match_results.noMatches) > 0:
+            print("\nNo matches:\n------------------")
+            for f in match_results.noMatches:
+                print(f)
+
+        if len(match_results.writeFailures) > 0:
+            print("\nFile Write Failures:\n------------------")
+            for f in match_results.writeFailures:
+                print(f)
+
+        if len(match_results.fetchDataFailures) > 0:
+            print("\nNetwork Data Fetch Failures:\n------------------")
+            for f in match_results.fetchDataFailures:
+                print(f)
+
+    if not opts.show_save_summary and not opts.interactive:
+        # just quit if we're not interactive or showing the summary
+        return
+
+    if len(match_results.multipleMatches) > 0:
+        print(
+            "\nArchives with multiple high-confidence matches:\n------------------")
+        for match_set in match_results.multipleMatches:
+            display_match_set_for_choice(
+                "Multiple high-confidence matches", match_set, opts, settings)
+
+    if len(match_results.lowConfidenceMatches) > 0:
+        print("\nArchives with low-confidence matches:\n------------------")
+        for match_set in match_results.lowConfidenceMatches:
+            if len(match_set.matches) == 1:
+                label = "Single low-confidence match"
+            else:
+                label = "Multiple low-confidence matches"
+
+            display_match_set_for_choice(label, match_set, opts, settings)
+
+
+def cli_mode(opts, settings):
+    if len(opts.file_list) < 1:
+        print("You must specify at least one filename.  Use the -h option for more info", file=sys.stderr)
+        return
+
+    match_results = OnlineMatchResults()
+
+    for f in opts.file_list:
+        if isinstance(f, str):
+            pass
+        process_file_cli(f, opts, settings, match_results)
+        sys.stdout.flush()
+
+    post_process_matches(match_results, opts, settings)
+
+
+def create_local_metadata(opts, ca, has_desired_tags):
+
+    md = GenericMetadata()
+    md.setDefaultPageList(ca.getNumberOfPages())
+
+    if has_desired_tags:
+        md = ca.readMetadata(opts.data_style)
+
+    # now, overlay the parsed filename info
+    if opts.parse_filename:
+        md.overlay(ca.metadataFromFilename())
+
+    # finally, use explicit stuff
+    if opts.metadata is not None:
+        md.overlay(opts.metadata)
+
+    return md
+
+
+def process_file_cli(filename, opts, settings, match_results):
+
+    batch_mode = len(opts.file_list) > 1
+
+    ca = ComicArchive(
+        filename,
+        settings.rar_exe_path,
+        ComicTaggerSettings.getGraphic('nocover.png'))
+
+    if not os.path.lexists(filename):
+        print("Cannot find " + filename, file=sys.stderr)
+        return
+
+    if not ca.seemsToBeAComicArchive():
+        print("Sorry, but " + \
+            filename + "  is not a comic archive!", file=sys.stderr)
+        return
+
+    # if not ca.isWritableForStyle(opts.data_style) and (opts.delete_tags or
+    # opts.save_tags or opts.rename_file):
+    if not ca.isWritable() and (
+            opts.delete_tags or opts.copy_tags or opts.save_tags or opts.rename_file):
+        print("This archive is not writable for that tag type", file=sys.stderr)
+        return
+
+    has = [False, False, False]
+    if ca.hasCIX():
+        has[MetaDataStyle.CIX] = True
+    if ca.hasCBI():
+        has[MetaDataStyle.CBI] = True
+    if ca.hasCoMet():
+        has[MetaDataStyle.COMET] = True
+
+    if opts.print_tags:
+
+        if opts.data_style is None:
+            page_count = ca.getNumberOfPages()
+
+            brief = ""
+
+            if batch_mode:
+                brief = "{0}: ".format(filename)
+
+            if ca.isZip():
+                brief += "ZIP archive    "
+            elif ca.isRar():
+                brief += "RAR archive    "
+            elif ca.isFolder():
+                brief += "Folder archive "
+
+            brief += "({0: >3} pages)".format(page_count)
+            brief += "  tags:[ "
+
+            if not (has[MetaDataStyle.CBI] or has[
+                    MetaDataStyle.CIX] or has[MetaDataStyle.COMET]):
+                brief += "none "
+            else:
+                if has[MetaDataStyle.CBI]:
+                    brief += "CBL "
+                if has[MetaDataStyle.CIX]:
+                    brief += "CR "
+                if has[MetaDataStyle.COMET]:
+                    brief += "CoMet "
+            brief += "]"
+
+            print(brief)
+
+        if opts.terse:
+            return
+
+        print()
+
+        if opts.data_style is None or opts.data_style == MetaDataStyle.CIX:
+            if has[MetaDataStyle.CIX]:
+                print("--------- ComicRack tags ---------")
+                if opts.raw:
+                    print((
+                        "{0}".format(
+                            str(
+                                ca.readRawCIX(),
+                                errors='ignore'))))
+                else:
+                    print(("{0}".format(ca.readCIX())))
+
+        if opts.data_style is None or opts.data_style == MetaDataStyle.CBI:
+            if has[MetaDataStyle.CBI]:
+                print("------- ComicBookLover tags -------")
+                if opts.raw:
+                    pprint(json.loads(ca.readRawCBI()))
+                else:
+                    print(("{0}".format(ca.readCBI())))
+
+        if opts.data_style is None or opts.data_style == MetaDataStyle.COMET:
+            if has[MetaDataStyle.COMET]:
+                print("----------- CoMet tags -----------")
+                if opts.raw:
+                    print(("{0}".format(ca.readRawCoMet())))
+                else:
+                    print(("{0}".format(ca.readCoMet())))
+
+    elif opts.delete_tags:
+        style_name = MetaDataStyle.name[opts.data_style]
+        if has[opts.data_style]:
+            if not opts.dryrun:
+                if not ca.removeMetadata(opts.data_style):
+                    print(("{0}: Tag removal seemed to fail!".format(filename)))
+                else:
+                    print((
+                        "{0}: Removed {1} tags.".format(filename, style_name)))
+            else:
+                print((
+                    "{0}: dry-run. {1} tags not removed".format(filename, style_name)))
+        else:
+            print(("{0}: This archive doesn't have {1} tags to remove.".format(
+                filename, style_name)))
+
+    elif opts.copy_tags:
+        dst_style_name = MetaDataStyle.name[opts.data_style]
+        if opts.no_overwrite and has[opts.data_style]:
+            print(("{0}: Already has {1} tags. Not overwriting.".format(
+                filename, dst_style_name)))
+            return
+        if opts.copy_source == opts.data_style:
+            print((
+                "{0}: Destination and source are same: {1}. Nothing to do.".format(
+                    filename,
+                    dst_style_name)))
+            return
+
+        src_style_name = MetaDataStyle.name[opts.copy_source]
+        if has[opts.copy_source]:
+            if not opts.dryrun:
+                md = ca.readMetadata(opts.copy_source)
+
+                if settings.apply_cbl_transform_on_bulk_operation and opts.data_style == MetaDataStyle.CBI:
+                    md = CBLTransformer(md, settings).apply()
+
+                if not ca.writeMetadata(md, opts.data_style):
+                    print(("{0}: Tag copy seemed to fail!".format(filename)))
+                else:
+                    print(("{0}: Copied {1} tags to {2} .".format(
+                        filename, src_style_name, dst_style_name)))
+            else:
+                print((
+                    "{0}: dry-run.  {1} tags not copied".format(filename, src_style_name)))
+        else:
+            print(("{0}: This archive doesn't have {1} tags to copy.".format(
+                filename, src_style_name)))
+
+    elif opts.save_tags:
+
+        if opts.no_overwrite and has[opts.data_style]:
+            print(("{0}: Already has {1} tags. Not overwriting.".format(
+                filename, MetaDataStyle.name[opts.data_style])))
+            return
+
+        if batch_mode:
+            print(("Processing {0}...".format(filename)))
+
+        md = create_local_metadata(opts, ca, has[opts.data_style])
+        if md.issue is None or md.issue == "":
+            if opts.assume_issue_is_one_if_not_set:
+                md.issue = "1"
+
+        # now, search online
+        if opts.search_online:
+            if opts.issue_id is not None:
+                # we were given the actual ID to search with
+                try:
+                    comicVine = ComicVineTalker()
+                    comicVine.wait_for_rate_limit = opts.wait_and_retry_on_rate_limit
+                    cv_md = comicVine.fetchIssueDataByIssueID(
+                        opts.issue_id, settings)
+                except ComicVineTalkerException:
+                    print("Network error while getting issue details.  Save aborted", file=sys.stderr)
+                    match_results.fetchDataFailures.append(filename)
+                    return
+
+                if cv_md is None:
+                    print("No match for ID {0} was found.".format(
+                        opts.issue_id), file=sys.stderr)
+                    match_results.noMatches.append(filename)
+                    return
+
+                if settings.apply_cbl_transform_on_cv_import:
+                    cv_md = CBLTransformer(cv_md, settings).apply()
+            else:
+                ii = IssueIdentifier(ca, settings)
+
+                if md is None or md.isEmpty:
+                    print("No metadata given to search online with!", file=sys.stderr)
+                    match_results.noMatches.append(filename)
+                    return
+
+                def myoutput(text):
+                    if opts.verbose:
+                        IssueIdentifier.defaultWriteOutput(text)
+
+                # use our overlayed MD struct to search
+                ii.setAdditionalMetadata(md)
+                ii.onlyUseAdditionalMetaData = True
+                ii.waitAndRetryOnRateLimit = opts.wait_and_retry_on_rate_limit
+                ii.setOutputFunction(myoutput)
+                ii.cover_page_index = md.getCoverPageIndexList()[0]
+                matches = ii.search()
+
+                result = ii.search_result
+
+                found_match = False
+                choices = False
+                low_confidence = False
+
+                if result == ii.ResultNoMatches:
+                    pass
+                elif result == ii.ResultFoundMatchButBadCoverScore:
+                    low_confidence = True
+                    found_match = True
+                elif result == ii.ResultFoundMatchButNotFirstPage:
+                    found_match = True
+                elif result == ii.ResultMultipleMatchesWithBadImageScores:
+                    low_confidence = True
+                    choices = True
+                elif result == ii.ResultOneGoodMatch:
+                    found_match = True
+                elif result == ii.ResultMultipleGoodMatches:
+                    choices = True
+
+                if choices:
+                    if low_confidence:
+                        print("Online search: Multiple low confidence matches.  Save aborted", file=sys.stderr)
+                        match_results.lowConfidenceMatches.append(
+                            MultipleMatch(filename, matches))
+                        return
+                    else:
+                        print("Online search: Multiple good matches.  Save aborted", file=sys.stderr)
+                        match_results.multipleMatches.append(
+                            MultipleMatch(filename, matches))
+                        return
+                if low_confidence and opts.abortOnLowConfidence:
+                    print("Online search: Low confidence match.  Save aborted", file=sys.stderr)
+                    match_results.lowConfidenceMatches.append(
+                        MultipleMatch(filename, matches))
+                    return
+                if not found_match:
+                    print("Online search: No match found.  Save aborted", file=sys.stderr)
+                    match_results.noMatches.append(filename)
+                    return
+
+                # we got here, so we have a single match
+
+                # now get the particular issue data
+                cv_md = actual_issue_data_fetch(matches[0], settings, opts)
+                if cv_md is None:
+                    match_results.fetchDataFailures.append(filename)
+                    return
+
+            md.overlay(cv_md)
+
+        # ok, done building our metadata. time to save
+        if not actual_metadata_save(ca, opts, md):
+            match_results.writeFailures.append(filename)
+        else:
+            match_results.goodMatches.append(filename)
+
+    elif opts.rename_file:
+
+        msg_hdr = ""
+        if batch_mode:
+            msg_hdr = "{0}: ".format(filename)
+
+        if opts.data_style is not None:
+            use_tags = has[opts.data_style]
+        else:
+            use_tags = False
+
+        md = create_local_metadata(opts, ca, use_tags)
+
+        if md.series is None:
+            print(msg_hdr + "Can't rename without series name", file=sys.stderr)
+            return
+
+        new_ext = None  # default
+        if settings.rename_extension_based_on_archive:
+            if ca.isZip():
+                new_ext = ".cbz"
+            elif ca.isRar():
+                new_ext = ".cbr"
+
+        renamer = FileRenamer(md)
+        renamer.setTemplate(settings.rename_template)
+        renamer.setIssueZeroPadding(settings.rename_issue_number_padding)
+        renamer.setSmartCleanup(settings.rename_use_smart_string_cleanup)
+
+        new_name = renamer.determineName(filename, ext=new_ext)
+
+        if new_name == os.path.basename(filename):
+            print(msg_hdr + "Filename is already good!", file=sys.stderr)
+            return
+
+        folder = os.path.dirname(os.path.abspath(filename))
+        new_abs_path = utils.unique_file(os.path.join(folder, new_name))
+
+        suffix = ""
+        if not opts.dryrun:
+            # rename the file
+            os.rename(filename, new_abs_path)
+        else:
+            suffix = " (dry-run, no change)"
+
+        print((
+            "renamed '{0}' -> '{1}' {2}".format(os.path.basename(filename), new_name, suffix)))
+
+    elif opts.export_to_zip:
+        msg_hdr = ""
+        if batch_mode:
+            msg_hdr = "{0}: ".format(filename)
+
+        if not ca.isRar():
+            print(msg_hdr + "Archive is not a RAR.", file=sys.stderr)
+            return
+
+        rar_file = os.path.abspath(os.path.abspath(filename))
+        new_file = os.path.splitext(rar_file)[0] + ".cbz"
+
+        if opts.abort_export_on_conflict and os.path.lexists(new_file):
+            print(msg_hdr + "{0} already exists in the that folder.".format(os.path.split(new_file)[1]))
+            return
+
+        new_file = utils.unique_file(os.path.join(new_file))
+
+        delete_success = False
+        export_success = False
+        if not opts.dryrun:
+            if ca.exportAsZip(new_file):
+                export_success = True
+                if opts.delete_rar_after_export:
+                    try:
+                        os.unlink(rar_file)
+                    except:
+                        print(msg_hdr + \
+                            "Error deleting original RAR after export", file=sys.stderr)
+                        delete_success = False
+                    else:
+                        delete_success = True
+            else:
+                # last export failed, so remove the zip, if it exists
+                if os.path.lexists(new_file):
+                    os.remove(new_file)
+        else:
+            msg = msg_hdr + \
+                "Dry-run:  Would try to create {0}".format(
+                    os.path.split(new_file)[1])
+            if opts.delete_rar_after_export:
+                msg += " and delete orginal."
+            print(msg)
+            return
+
+        msg = msg_hdr
+        if export_success:
+            msg += "Archive exported successfully to: {0}".format(
+                os.path.split(new_file)[1])
+            if opts.delete_rar_after_export and delete_success:
+                msg += " (Original deleted) "
+        else:
+            msg += "Archive failed to export!"
+
+        print(msg)

comictaggerlib/comet.py

@@ -0,0 +1 @@
+from comicapi.comet import *

comictaggerlib/comicarchive.py

@@ -0,0 +1 @@
+from comicapi.comicarchive import *

comictaggerlib/comicbookinfo.py

@@ -0,0 +1 @@
+from comicapi.comicbookinfo import *

comictaggerlib/comicinfoxml.py

@@ -0,0 +1 @@
+from comicapi.comicinfoxml import *

comictaggerlib/comicvinecacher.py

@@ -0,0 +1,469 @@
+"""A python class to manage caching of data from Comic Vine"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sqlite3 as lite
+import os
+import datetime
+#import sys
+#from pprint import pprint
+
+from . import ctversion
+from .settings import ComicTaggerSettings
+from . import utils
+
+
+class ComicVineCacher:
+
+    def __init__(self):
+        self.settings_folder = ComicTaggerSettings.getSettingsFolder()
+        self.db_file = os.path.join(self.settings_folder, "cv_cache.db")
+        self.version_file = os.path.join(
+            self.settings_folder, "cache_version.txt")
+
+        # verify that cache is from same version as this one
+        data = ""
+        try:
+            with open(self.version_file, 'rb') as f:
+                data = f.read().decode("utf-8") 
+                f.close()
+        except:
+            pass
+        if data != ctversion.version:
+            self.clearCache()
+
+        if not os.path.exists(self.db_file):
+            self.create_cache_db()
+
+    def clearCache(self):
+        try:
+            os.unlink(self.db_file)
+        except:
+            pass
+        try:
+            os.unlink(self.version_file)
+        except:
+            pass
+
+    def create_cache_db(self):
+
+        # create the version file
+        with open(self.version_file, 'w') as f:
+            f.write(ctversion.version)
+
+        # this will wipe out any existing version
+        open(self.db_file, 'w').close()
+
+        con = lite.connect(self.db_file)
+
+        # create tables
+        with con:
+
+            cur = con.cursor()
+            # name,id,start_year,publisher,image,description,count_of_issues
+            cur.execute(
+                "CREATE TABLE VolumeSearchCache(" +
+                "search_term TEXT," +
+                "id INT," +
+                "name TEXT," +
+                "start_year INT," +
+                "publisher TEXT," +
+                "count_of_issues INT," +
+                "image_url TEXT," +
+                "description TEXT," +
+                "timestamp DATE DEFAULT (datetime('now','localtime'))) ")
+
+            cur.execute(
+                "CREATE TABLE Volumes(" +
+                "id INT," +
+                "name TEXT," +
+                "publisher TEXT," +
+                "count_of_issues INT," +
+                "start_year INT," +
+                "timestamp DATE DEFAULT (datetime('now','localtime')), " +
+                "PRIMARY KEY (id))")
+
+            cur.execute(
+                "CREATE TABLE AltCovers(" +
+                "issue_id INT," +
+                "url_list TEXT," +
+                "timestamp DATE DEFAULT (datetime('now','localtime')), " +
+                "PRIMARY KEY (issue_id))")
+
+            cur.execute(
+                "CREATE TABLE Issues(" +
+                "id INT," +
+                "volume_id INT," +
+                "name TEXT," +
+                "issue_number TEXT," +
+                "super_url TEXT," +
+                "thumb_url TEXT," +
+                "cover_date TEXT," +
+                "site_detail_url TEXT," +
+                "description TEXT," +
+                "timestamp DATE DEFAULT (datetime('now','localtime')), " +
+                "PRIMARY KEY (id))")
+
+    def add_search_results(self, search_term, cv_search_results):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+            con.text_factory = str
+            cur = con.cursor()
+
+            # remove all previous entries with this search term
+            cur.execute(
+                "DELETE FROM VolumeSearchCache WHERE search_term = ?", [
+                    search_term.lower()])
+
+            # now add in new results
+            for record in cv_search_results:
+                timestamp = datetime.datetime.now()
+
+                if record['publisher'] is None:
+                    pub_name = ""
+                else:
+                    pub_name = record['publisher']['name']
+
+                if record['image'] is None:
+                    url = ""
+                else:
+                    url = record['image']['super_url']
+
+                cur.execute(
+                    "INSERT INTO VolumeSearchCache " +
+                    "(search_term, id, name, start_year, publisher, count_of_issues, image_url, description) " +
+                    "VALUES(?, ?, ?, ?, ?, ?, ?, ?)",
+                    (search_term.lower(),
+                     record['id'],
+                        record['name'],
+                        record['start_year'],
+                        pub_name,
+                        record['count_of_issues'],
+                        url,
+                        record['description']))
+
+    def get_search_results(self, search_term):
+
+        results = list()
+        con = lite.connect(self.db_file)
+        with con:
+            con.text_factory = str
+            cur = con.cursor()
+
+            # purge stale search results
+            a_day_ago = datetime.datetime.today() - datetime.timedelta(days=1)
+            cur.execute(
+                "DELETE FROM VolumeSearchCache WHERE timestamp  < ?", [
+                    str(a_day_ago)])
+
+            # fetch
+            cur.execute(
+                "SELECT * FROM VolumeSearchCache WHERE search_term=?", [search_term.lower()])
+            rows = cur.fetchall()
+            # now process the results
+            for record in rows:
+
+                result = dict()
+                result['id'] = record[1]
+                result['name'] = record[2]
+                result['start_year'] = record[3]
+                result['publisher'] = dict()
+                result['publisher']['name'] = record[4]
+                result['count_of_issues'] = record[5]
+                result['image'] = dict()
+                result['image']['super_url'] = record[6]
+                result['description'] = record[7]
+
+                results.append(result)
+
+        return results
+
+    def add_alt_covers(self, issue_id, url_list):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+            con.text_factory = str
+            cur = con.cursor()
+
+            # remove all previous entries with this search term
+            cur.execute("DELETE FROM AltCovers WHERE issue_id = ?", [issue_id])
+
+            url_list_str = utils.listToString(url_list)
+            # now add in new record
+            cur.execute("INSERT INTO AltCovers " +
+                        "(issue_id, url_list) " +
+                        "VALUES(?, ?)",
+                        (issue_id,
+                         url_list_str)
+                        )
+
+    def get_alt_covers(self, issue_id):
+
+        con = lite.connect(self.db_file)
+        with con:
+            cur = con.cursor()
+            con.text_factory = str
+
+            # purge stale issue info - probably issue data won't change
+            # much....
+            a_month_ago = datetime.datetime.today() - \
+                datetime.timedelta(days=30)
+            cur.execute(
+                "DELETE FROM AltCovers WHERE timestamp  < ?", [
+                    str(a_month_ago)])
+
+            cur.execute(
+                "SELECT url_list FROM AltCovers WHERE issue_id=?", [issue_id])
+            row = cur.fetchone()
+            if row is None:
+                return None
+            else:
+                url_list_str = row[0]
+                if len(url_list_str) == 0:
+                    return []
+                raw_list = url_list_str.split(",")
+                url_list = []
+                for item in raw_list:
+                    url_list.append(str(item).strip())
+                return url_list
+
+    def add_volume_info(self, cv_volume_record):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+
+            cur = con.cursor()
+
+            timestamp = datetime.datetime.now()
+
+            if cv_volume_record['publisher'] is None:
+                pub_name = ""
+            else:
+                pub_name = cv_volume_record['publisher']['name']
+
+            data = {
+                "name": cv_volume_record['name'],
+                "publisher": pub_name,
+                "count_of_issues": cv_volume_record['count_of_issues'],
+                "start_year": cv_volume_record['start_year'],
+                "timestamp": timestamp
+            }
+            self.upsert(cur, "volumes", "id", cv_volume_record['id'], data)
+
+    def add_volume_issues_info(self, volume_id, cv_volume_issues):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+
+            cur = con.cursor()
+
+            timestamp = datetime.datetime.now()
+
+            # add in issues
+
+            for issue in cv_volume_issues:
+
+                data = {
+                    "volume_id": volume_id,
+                    "name": issue['name'],
+                    "issue_number": issue['issue_number'],
+                    "site_detail_url": issue['site_detail_url'],
+                    "cover_date": issue['cover_date'],
+                    "super_url": issue['image']['super_url'],
+                    "thumb_url": issue['image']['thumb_url'],
+                    "description": issue['description'],
+                    "timestamp": timestamp
+                }
+                self.upsert(cur, "issues", "id", issue['id'], data)
+
+    def get_volume_info(self, volume_id):
+
+        result = None
+
+        con = lite.connect(self.db_file)
+        with con:
+            cur = con.cursor()
+            con.text_factory = str
+
+            # purge stale volume info
+            a_week_ago = datetime.datetime.today() - datetime.timedelta(days=7)
+            cur.execute(
+                "DELETE FROM Volumes WHERE timestamp  < ?", [str(a_week_ago)])
+
+            # fetch
+            cur.execute(
+                "SELECT id,name,publisher,count_of_issues,start_year FROM Volumes WHERE id = ?",
+                [volume_id])
+
+            row = cur.fetchone()
+
+            if row is None:
+                return result
+
+            result = dict()
+
+            # since ID is primary key, there is only one row
+            result['id'] = row[0]
+            result['name'] = row[1]
+            result['publisher'] = dict()
+            result['publisher']['name'] = row[2]
+            result['count_of_issues'] = row[3]
+            result['start_year'] = row[4]
+            result['issues'] = list()
+
+        return result
+
+    def get_volume_issues_info(self, volume_id):
+
+        result = None
+
+        con = lite.connect(self.db_file)
+        with con:
+            cur = con.cursor()
+            con.text_factory = str
+
+            # purge stale issue info - probably issue data won't change
+            # much....
+            a_week_ago = datetime.datetime.today() - datetime.timedelta(days=7)
+            cur.execute(
+                "DELETE FROM Issues WHERE timestamp  < ?", [str(a_week_ago)])
+
+            # fetch
+            results = list()
+
+            cur.execute(
+                "SELECT id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description FROM Issues WHERE volume_id = ?",
+                [volume_id])
+            rows = cur.fetchall()
+
+            # now process the results
+            for row in rows:
+                record = dict()
+
+                record['id'] = row[0]
+                record['name'] = row[1]
+                record['issue_number'] = row[2]
+                record['site_detail_url'] = row[3]
+                record['cover_date'] = row[4]
+                record['image'] = dict()
+                record['image']['super_url'] = row[5]
+                record['image']['thumb_url'] = row[6]
+                record['description'] = row[7]
+
+                results.append(record)
+
+        if len(results) == 0:
+            return None
+
+        return results
+
+    def add_issue_select_details(
+            self,
+            issue_id,
+            image_url,
+            thumb_image_url,
+            cover_date,
+            site_detail_url):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+            cur = con.cursor()
+            con.text_factory = str
+            timestamp = datetime.datetime.now()
+
+            data = {
+                "super_url": image_url,
+                "thumb_url": thumb_image_url,
+                "cover_date": cover_date,
+                "site_detail_url": site_detail_url,
+                "timestamp": timestamp
+            }
+            self.upsert(cur, "issues", "id", issue_id, data)
+
+    def get_issue_select_details(self, issue_id):
+
+        con = lite.connect(self.db_file)
+        with con:
+            cur = con.cursor()
+            con.text_factory = str
+
+            cur.execute(
+                "SELECT super_url,thumb_url,cover_date,site_detail_url FROM Issues WHERE id=?",
+                [issue_id])
+            row = cur.fetchone()
+
+            details = dict()
+            if row is None or row[0] is None:
+                details['image_url'] = None
+                details['thumb_image_url'] = None
+                details['cover_date'] = None
+                details['site_detail_url'] = None
+
+            else:
+                details['image_url'] = row[0]
+                details['thumb_image_url'] = row[1]
+                details['cover_date'] = row[2]
+                details['site_detail_url'] = row[3]
+
+            return details
+
+    def upsert(self, cur, tablename, pkname, pkval, data):
+        """This does an insert if the given PK doesn't exist, and an
+        update it if does
+
+        TODO: look into checking if UPDATE is needed
+        TODO: should the cursor be created here, and not up the stack?
+        """
+
+        ins_count = len(data) + 1
+
+        keys = ""
+        vals = list()
+        ins_slots = ""
+        set_slots = ""
+
+        for key in data:
+
+            if keys != "":
+                keys += ", "
+            if ins_slots != "":
+                ins_slots += ", "
+            if set_slots != "":
+                set_slots += ", "
+
+            keys += key
+            vals.append(data[key])
+            ins_slots += "?"
+            set_slots += key + " = ?"
+
+        keys += ", " + pkname
+        vals.append(pkval)
+        ins_slots += ", ?"
+        condition = pkname + " = ?"
+
+        sql_ins = ("INSERT OR IGNORE INTO " + tablename +
+                   " (" + keys + ") " +
+                   " VALUES (" + ins_slots + ")")
+        cur.execute(sql_ins, vals)
+
+        sql_upd = ("UPDATE " + tablename +
+                   " SET " + set_slots + " WHERE " + condition)
+        cur.execute(sql_upd, vals)

comictaggerlib/comicvinetalker.py

@@ -0,0 +1,848 @@
+"""A python class to manage communication with Comic Vine's REST API"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import json
+import urllib.request, urllib.error, urllib.parse
+import urllib.request, urllib.parse, urllib.error
+import re
+import time
+import datetime
+import sys
+import ssl
+#from pprint import pprint
+#import math
+
+from bs4 import BeautifulSoup
+
+try:
+    from PyQt5.QtNetwork import QNetworkAccessManager, QNetworkRequest
+    from PyQt5.QtCore import QUrl, pyqtSignal, QObject, QByteArray
+except ImportError:
+    # No Qt, so define a few dummy QObjects to help us compile
+    class QObject():
+
+        def __init__(self, *args):
+            pass
+
+    class pyqtSignal():
+
+        def __init__(self, *args):
+            pass
+
+        def emit(a, b, c):
+            pass
+
+from . import ctversion
+from . import utils
+from .comicvinecacher import ComicVineCacher
+from .genericmetadata import GenericMetadata
+from .issuestring import IssueString
+#from settings import ComicTaggerSettings
+
+
+class CVTypeID:
+    Volume = "4050"
+    Issue = "4000"
+
+
+class ComicVineTalkerException(Exception):
+    Unknown = -1
+    Network = -2
+    InvalidKey = 100
+    RateLimit = 107
+
+    def __init__(self, code=-1, desc=""):
+        self.desc = desc
+        self.code = code
+
+    def __str__(self):
+        if (self.code == ComicVineTalkerException.Unknown or
+                self.code == ComicVineTalkerException.Network):
+            return self.desc
+        else:
+            return "CV error #{0}:  [{1}]. \n".format(self.code, self.desc)
+
+
+class ComicVineTalker(QObject):
+
+    logo_url = "http://static.comicvine.com/bundles/comicvinesite/images/logo.png"
+    api_key = ""
+
+    @staticmethod
+    def getRateLimitMessage():
+        if ComicVineTalker.api_key == "":
+            return "Comic Vine rate limit exceeded.  You should configue your own Comic Vine API key."
+        else:
+            return "Comic Vine rate limit exceeded.  Please wait a bit."
+
+    def __init__(self):
+        QObject.__init__(self)
+
+        self.api_base_url = "https://comicvine.gamespot.com/api"
+        self.wait_for_rate_limit = False
+
+        # key that is registered to comictagger
+        default_api_key = '27431e6787042105bd3e47e169a624521f89f3a4'
+
+        if ComicVineTalker.api_key == "":
+            self.api_key = default_api_key
+        else:
+            self.api_key = ComicVineTalker.api_key
+
+        self.log_func = None
+
+        # always use a tls context for urlopen
+        self.ssl = ssl.SSLContext(ssl.PROTOCOL_TLS)
+
+    def setLogFunc(self, log_func):
+        self.log_func = log_func
+
+    def writeLog(self, text):
+        if self.log_func is None:
+            # sys.stdout.write(text.encode(errors='replace'))
+            # sys.stdout.flush()
+            print(text, file=sys.stderr)
+        else:
+            self.log_func(text)
+
+    def parseDateStr(self, date_str):
+        day = None
+        month = None
+        year = None
+        if date_str is not None:
+            parts = date_str.split('-')
+            year = parts[0]
+            if len(parts) > 1:
+                month = parts[1]
+                if len(parts) > 2:
+                    day = parts[2]
+        return day, month, year
+
+    def testKey(self, key):
+
+        try:
+            test_url = self.api_base_url + "/issue/1/?api_key=" + \
+                key + "&format=json&field_list=name"
+            resp = urllib.request.urlopen(test_url, context=self.ssl)
+            content = resp.read()
+    
+            cv_response = json.loads(content.decode('utf-8'))
+    
+            # Bogus request, but if the key is wrong, you get error 100: "Invalid
+            # API Key"
+            return cv_response['status_code'] != 100
+        except:
+            return False
+
+    """
+    Get the contect from the CV server.  If we're in "wait mode" and status code is a rate limit error
+    sleep for a bit and retry.
+    """
+
+    def getCVContent(self, url):
+        total_time_waited = 0
+        limit_wait_time = 1
+        counter = 0
+        wait_times = [1, 2, 3, 4]
+        while True:
+            content = self.getUrlContent(url)
+            cv_response = json.loads(content.decode('utf-8'))
+            if self.wait_for_rate_limit and cv_response[
+                    'status_code'] == ComicVineTalkerException.RateLimit:
+                self.writeLog(
+                    "Rate limit encountered.  Waiting for {0} minutes\n".format(limit_wait_time))
+                time.sleep(limit_wait_time * 60)
+                total_time_waited += limit_wait_time
+                limit_wait_time = wait_times[counter]
+                if counter < 3:
+                    counter += 1
+                # don't wait much more than 20 minutes
+                if total_time_waited < 20:
+                    continue
+            if cv_response['status_code'] != 1:
+                self.writeLog(
+                    "Comic Vine query failed with error #{0}:  [{1}]. \n".format(
+                        cv_response['status_code'],
+                        cv_response['error']))
+                raise ComicVineTalkerException(
+                    cv_response['status_code'], cv_response['error'])
+            else:
+                # it's all good
+                break
+        return cv_response
+
+    def getUrlContent(self, url):
+        # connect to server:
+        #  if there is a 500 error, try a few more times before giving up
+        #  any other error, just bail
+        #print("---", url)
+        for tries in range(3):
+            try:
+                resp = urllib.request.urlopen(url, context=self.ssl)
+                return resp.read()
+            except urllib.error.HTTPError as e:
+                if e.getcode() == 500:
+                    self.writeLog("Try #{0}: ".format(tries + 1))
+                    time.sleep(1)
+                self.writeLog(str(e) + "\n")
+
+                if e.getcode() != 500:
+                    break
+
+            except Exception as e:
+                self.writeLog(str(e) + "\n")
+                raise ComicVineTalkerException(
+                    ComicVineTalkerException.Network, "Network Error!")
+
+        raise ComicVineTalkerException(
+            ComicVineTalkerException.Unknown, "Error on Comic Vine server")
+
+    def searchForSeries(self, series_name, callback=None, refresh_cache=False):
+
+        # remove cruft from the search string
+        series_name = utils.removearticles(series_name).lower().strip()
+
+        # before we search online, look in our cache, since we might have
+        # done this same search recently
+        cvc = ComicVineCacher()
+        if not refresh_cache:
+            cached_search_results = cvc.get_search_results(series_name)
+
+            if len(cached_search_results) > 0:
+                return cached_search_results
+
+        original_series_name = series_name
+
+        # Split and rejoin to remove extra internal spaces
+        query_word_list = series_name.split()
+        query_string = " ".join( query_word_list ).strip()
+        #print ("Query string = ", query_string)
+
+        query_string = urllib.parse.quote_plus(query_string.encode("utf-8"))
+
+        search_url = self.api_base_url + "/search/?api_key=" + self.api_key + "&format=json&resources=volume&query=" + \
+            query_string + \
+            "&field_list=name,id,start_year,publisher,image,description,count_of_issues&limit=100"
+        cv_response = self.getCVContent(search_url + "&page=1")
+
+        search_results = list()
+
+        # see http://api.comicvine.com/documentation/#handling_responses
+
+        limit = cv_response['limit']
+        current_result_count = cv_response['number_of_page_results']
+        total_result_count = cv_response['number_of_total_results']
+
+        # 8 Dec 2018 - Comic Vine changed query results again. Terms are now
+        # ORed together, and we get thousands of results.  Good news is the
+        # results are sorted by relevance, so we can be smart about halting
+        # the search.  
+        # 1. Don't fetch more than some sane amount of pages.
+        max_results = 500 
+        # 2. Halt when not all of our search terms are present in a result
+        # 3. Halt when the results contain more (plus threshold) words than
+        #    our search
+        result_word_count_max = len(query_word_list) + 3
+
+        total_result_count = min(total_result_count, max_results) 
+
+        if callback is None:
+            self.writeLog(
+                "Found {0} of {1} results\n".format(
+                    cv_response['number_of_page_results'],
+                    cv_response['number_of_total_results']))
+        search_results.extend(cv_response['results'])
+        page = 1
+
+        if callback is not None:
+            callback(current_result_count, total_result_count)
+
+        # see if we need to keep asking for more pages...
+        stop_searching = False
+        while (current_result_count < total_result_count):
+
+            last_result = search_results[-1]['name']
+
+            # See if the last result's name has all the of the search terms.
+            # if not, break out of this, loop, we're done.
+            #print("Searching for {} in '{}'".format(query_word_list, last_result))
+            for term in query_word_list:
+                if term not in last_result.lower():
+                    #print("Term '{}' not in last result. Halting search result fetching".format(term))
+                    stop_searching = True
+                    break
+
+            # Also, stop searching when the word count of last results is too much longer
+            # than our search terms list 
+            if len(utils.removearticles(last_result).split()) > result_word_count_max:
+                #print("Last result '{}' is too long. Halting search result fetching".format(last_result))
+                stop_searching = True
+
+            if stop_searching:
+                break
+
+            if callback is None:
+                self.writeLog(
+                    "getting another page of results {0} of {1}...\n".format(
+                        current_result_count,
+                        total_result_count))
+            page += 1
+
+            cv_response = self.getCVContent(search_url + "&page=" + str(page))
+
+            search_results.extend(cv_response['results'])
+            current_result_count += cv_response['number_of_page_results']
+
+            if callback is not None:
+                callback(current_result_count, total_result_count)
+
+        # Remove any search results that don't contain all the search terms
+        # (iterate backwards for easy removal)
+        for i in range(len(search_results) - 1, -1, -1):
+            record = search_results[i]
+            for term in query_word_list:
+                if term not in record['name'].lower():
+                    del search_results[i]
+                    break
+
+        # for record in search_results:
+            #print(u"{0}: {1} ({2})".format(record['id'], record['name'] , record['start_year']))
+            # print(record)
+            #record['count_of_issues'] = record['count_of_isssues']
+        #print(u"{0}: {1} ({2})".format(search_results['results'][0]['id'], search_results['results'][0]['name'] , search_results['results'][0]['start_year']))
+
+        # cache these search results
+        cvc.add_search_results(original_series_name, search_results)
+
+        return search_results
+
+    def fetchVolumeData(self, series_id):
+
+        # before we search online, look in our cache, since we might already
+        # have this info
+        cvc = ComicVineCacher()
+        cached_volume_result = cvc.get_volume_info(series_id)
+
+        if cached_volume_result is not None:
+            return cached_volume_result
+
+        volume_url = self.api_base_url + "/volume/" + CVTypeID.Volume + "-" + \
+            str(series_id) + "/?api_key=" + self.api_key + \
+            "&field_list=name,id,start_year,publisher,count_of_issues&format=json"
+
+        cv_response = self.getCVContent(volume_url)
+
+        volume_results = cv_response['results']
+
+        cvc.add_volume_info(volume_results)
+
+        return volume_results
+
+    def fetchIssuesByVolume(self, series_id):
+
+        # before we search online, look in our cache, since we might already
+        # have this info
+        cvc = ComicVineCacher()
+        cached_volume_issues_result = cvc.get_volume_issues_info(series_id)
+
+        if cached_volume_issues_result is not None:
+            return cached_volume_issues_result
+
+        #---------------------------------
+        issues_url = self.api_base_url + "/issues/" + "?api_key=" + self.api_key + "&filter=volume:" + \
+            str(series_id) + \
+            "&field_list=id,volume,issue_number,name,image,cover_date,site_detail_url,description&format=json"
+        cv_response = self.getCVContent(issues_url)
+
+        #------------------------------------
+
+        limit = cv_response['limit']
+        current_result_count = cv_response['number_of_page_results']
+        total_result_count = cv_response['number_of_total_results']
+        #print("total_result_count", total_result_count)
+
+        #print("Found {0} of {1} results".format(cv_response['number_of_page_results'], cv_response['number_of_total_results']))
+        volume_issues_result = cv_response['results']
+        page = 1
+        offset = 0
+
+        # see if we need to keep asking for more pages...
+        while (current_result_count < total_result_count):
+            #print("getting another page of issue results {0} of {1}...".format(current_result_count, total_result_count))
+            page += 1
+            offset += cv_response['number_of_page_results']
+
+            # print issues_url+ "&offset="+str(offset)
+            cv_response = self.getCVContent(
+                issues_url + "&offset=" + str(offset))
+
+            volume_issues_result.extend(cv_response['results'])
+            current_result_count += cv_response['number_of_page_results']
+
+        self.repairUrls(volume_issues_result)
+
+        cvc.add_volume_issues_info(series_id, volume_issues_result)
+
+        return volume_issues_result
+
+    def fetchIssuesByVolumeIssueNumAndYear(
+            self, volume_id_list, issue_number, year):
+        volume_filter = "volume:"
+        for vid in volume_id_list:
+            volume_filter += str(vid) + "|"
+
+        year_filter = ""
+        if year is not None and str(year).isdigit():
+            year_filter = ",cover_date:{0}-1-1|{1}-1-1".format(
+                year, int(year) + 1)
+
+        issue_number = urllib.parse.quote_plus(str(issue_number).encode("utf-8"))
+
+        filter = "&filter=" + volume_filter + \
+            year_filter + ",issue_number:" + issue_number
+
+        issues_url = self.api_base_url + "/issues/" + "?api_key=" + self.api_key + filter + \
+            "&field_list=id,volume,issue_number,name,image,cover_date,site_detail_url,description&format=json"
+
+        cv_response = self.getCVContent(issues_url)
+
+        #------------------------------------
+
+        limit = cv_response['limit']
+        current_result_count = cv_response['number_of_page_results']
+        total_result_count = cv_response['number_of_total_results']
+        #print("total_result_count", total_result_count)
+
+        #print("Found {0} of {1} results\n".format(cv_response['number_of_page_results'], cv_response['number_of_total_results']))
+        filtered_issues_result = cv_response['results']
+        page = 1
+        offset = 0
+
+        # see if we need to keep asking for more pages...
+        while (current_result_count < total_result_count):
+            #print("getting another page of issue results {0} of {1}...\n".format(current_result_count, total_result_count))
+            page += 1
+            offset += cv_response['number_of_page_results']
+
+            # print issues_url+ "&offset="+str(offset)
+            cv_response = self.getCVContent(
+                issues_url + "&offset=" + str(offset))
+
+            filtered_issues_result.extend(cv_response['results'])
+            current_result_count += cv_response['number_of_page_results']
+
+        self.repairUrls(filtered_issues_result)
+
+        return filtered_issues_result
+
+    def fetchIssueData(self, series_id, issue_number, settings):
+
+        volume_results = self.fetchVolumeData(series_id)
+        issues_list_results = self.fetchIssuesByVolume(series_id)
+
+        found = False
+        for record in issues_list_results:
+            if IssueString(issue_number).asString() is None:
+                issue_number = 1
+            if IssueString(record['issue_number']).asString().lower() == IssueString(
+                    issue_number).asString().lower():
+                found = True
+                break
+
+        if (found):
+            issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + \
+                str(record['id']) + "/?api_key=" + \
+                self.api_key + "&format=json"
+
+            cv_response = self.getCVContent(issue_url)
+            issue_results = cv_response['results']
+
+        else:
+            return None
+
+        # Now, map the Comic Vine data to generic metadata
+        return self.mapCVDataToMetadata(
+            volume_results, issue_results, settings)
+
+    def fetchIssueDataByIssueID(self, issue_id, settings):
+
+        issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + \
+            str(issue_id) + "/?api_key=" + self.api_key + "&format=json"
+        cv_response = self.getCVContent(issue_url)
+
+        issue_results = cv_response['results']
+
+        volume_results = self.fetchVolumeData(issue_results['volume']['id'])
+
+        # Now, map the Comic Vine data to generic metadata
+        md = self.mapCVDataToMetadata(volume_results, issue_results, settings)
+        md.isEmpty = False
+        return md
+
+    def mapCVDataToMetadata(self, volume_results, issue_results, settings):
+
+        # Now, map the Comic Vine data to generic metadata
+        metadata = GenericMetadata()
+
+        metadata.series = issue_results['volume']['name']
+
+        num_s = IssueString(issue_results['issue_number']).asString()
+        metadata.issue = num_s
+        metadata.title = issue_results['name']
+
+        metadata.publisher = volume_results['publisher']['name']
+        metadata.day, metadata.month, metadata.year = self.parseDateStr(
+            issue_results['cover_date'])
+
+        #metadata.issueCount = volume_results['count_of_issues']
+        metadata.comments = self.cleanup_html(
+            issue_results['description'], settings.remove_html_tables)
+        if settings.use_series_start_as_volume:
+            metadata.volume = volume_results['start_year']
+
+        metadata.notes = "Tagged with ComicTagger {0} using info from Comic Vine on {1}.  [Issue ID {2}]".format(
+            ctversion.version,
+            datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+            issue_results['id'])
+        #metadata.notes  += issue_results['site_detail_url']
+
+        metadata.webLink = issue_results['site_detail_url']
+
+        person_credits = issue_results['person_credits']
+        for person in person_credits:
+            if 'role' in person:
+                roles = person['role'].split(',')
+                for role in roles:
+                    # can we determine 'primary' from CV??
+                    metadata.addCredit(
+                        person['name'], role.title().strip(), False)
+
+        character_credits = issue_results['character_credits']
+        character_list = list()
+        for character in character_credits:
+            character_list.append(character['name'])
+        metadata.characters = utils.listToString(character_list)
+
+        team_credits = issue_results['team_credits']
+        team_list = list()
+        for team in team_credits:
+            team_list.append(team['name'])
+        metadata.teams = utils.listToString(team_list)
+
+        location_credits = issue_results['location_credits']
+        location_list = list()
+        for location in location_credits:
+            location_list.append(location['name'])
+        metadata.locations = utils.listToString(location_list)
+
+        story_arc_credits = issue_results['story_arc_credits']
+        arc_list = []
+        for arc in story_arc_credits:
+            arc_list.append(arc['name'])
+        if len(arc_list) > 0:
+            metadata.storyArc = utils.listToString(arc_list)
+
+        return metadata
+
+    def cleanup_html(self, string, remove_html_tables):
+        """
+        converter = html2text.HTML2Text()
+        #converter.emphasis_mark = '*'
+        #converter.ignore_links = True
+        converter.body_width = 0
+
+        print(html2text.html2text(string))
+        return string
+        #return converter.handle(string)
+        """
+
+        if string is None:
+            return ""
+        # find any tables
+        soup = BeautifulSoup(string, "html.parser")
+        tables = soup.findAll('table')
+
+        # remove all newlines first
+        string = string.replace("\n", "")
+
+        # put in our own
+        string = string.replace("<br>", "\n")
+        string = string.replace("</p>", "\n\n")
+        string = string.replace("<h4>", "*")
+        string = string.replace("</h4>", "*\n")
+
+        # remove the tables
+        p = re.compile(r'<table[^<]*?>.*?<\/table>')
+        if remove_html_tables:
+            string = p.sub('', string)
+            string = string.replace("*List of covers and their creators:*", "")
+        else:
+            string = p.sub('{}', string)
+
+        # now strip all other tags
+        p = re.compile(r'<[^<]*?>')
+        newstring = p.sub('', string)
+
+        newstring = newstring.replace('&nbsp;', ' ')
+        newstring = newstring.replace('&amp;', '&')
+
+        newstring = newstring.strip()
+
+        if not remove_html_tables:
+            # now rebuild the tables into text from BSoup
+            try:
+                table_strings = []
+                for table in tables:
+                    rows = []
+                    hdrs = []
+                    col_widths = []
+                    for hdr in table.findAll('th'):
+                        item = hdr.string.strip()
+                        hdrs.append(item)
+                        col_widths.append(len(item))
+                    rows.append(hdrs)
+
+                    for row in table.findAll('tr'):
+                        cols = []
+                        col = row.findAll('td')
+                        i = 0
+                        for c in col:
+                            item = c.string.strip()
+                            cols.append(item)
+                            if len(item) > col_widths[i]:
+                                col_widths[i] = len(item)
+                            i += 1
+                        if len(cols) != 0:
+                            rows.append(cols)
+                    # now we have the data, make it into text
+                    fmtstr = ""
+                    for w in col_widths:
+                        fmtstr += " {{:{}}}|".format(w + 1)
+                    width = sum(col_widths) + len(col_widths) * 2
+                    print("width=", width)
+                    table_text = ""
+                    counter = 0
+                    for row in rows:
+                        table_text += fmtstr.format(*row) + "\n"
+                        if counter == 0 and len(hdrs) != 0:
+                            table_text += "-" * width + "\n"
+                        counter += 1
+
+                    table_strings.append(table_text)
+
+                newstring = newstring.format(*table_strings)
+            except:
+                # we caught an error rebuilding the table.
+                # just bail and remove the formatting
+                print("table parse error")
+                newstring.replace("{}", "")
+
+        return newstring
+
+    def fetchIssueDate(self, issue_id):
+        details = self.fetchIssueSelectDetails(issue_id)
+        day, month, year = self.parseDateStr(details['cover_date'])
+        return month, year
+
+    def fetchIssueCoverURLs(self, issue_id):
+        details = self.fetchIssueSelectDetails(issue_id)
+        return details['image_url'], details['thumb_image_url']
+
+    def fetchIssuePageURL(self, issue_id):
+        details = self.fetchIssueSelectDetails(issue_id)
+        return details['site_detail_url']
+
+    def fetchIssueSelectDetails(self, issue_id):
+
+        #cached_image_url,cached_thumb_url,cached_month,cached_year = self.fetchCachedIssueSelectDetails(issue_id)
+        cached_details = self.fetchCachedIssueSelectDetails(issue_id)
+        if cached_details['image_url'] is not None:
+            return cached_details
+
+        issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + \
+            str(issue_id) + "/?api_key=" + self.api_key + \
+            "&format=json&field_list=image,cover_date,site_detail_url"
+
+        details = dict()
+        details['image_url'] = None
+        details['thumb_image_url'] = None
+        details['cover_date'] = None
+        details['site_detail_url'] = None
+
+        cv_response = self.getCVContent(issue_url)
+
+        details['image_url'] = cv_response['results']['image']['super_url']
+        details['thumb_image_url'] = cv_response[
+            'results']['image']['thumb_url']
+        details['cover_date'] = cv_response['results']['cover_date']
+        details['site_detail_url'] = cv_response['results']['site_detail_url']
+
+        if details['image_url'] is not None:
+            self.cacheIssueSelectDetails(issue_id,
+                                         details['image_url'],
+                                         details['thumb_image_url'],
+                                         details['cover_date'],
+                                         details['site_detail_url'])
+        # print(details['site_detail_url'])
+        return details
+
+    def fetchCachedIssueSelectDetails(self, issue_id):
+
+        # before we search online, look in our cache, since we might already
+        # have this info
+        cvc = ComicVineCacher()
+        return cvc.get_issue_select_details(issue_id)
+
+    def cacheIssueSelectDetails(
+            self, issue_id, image_url, thumb_url, cover_date, page_url):
+        cvc = ComicVineCacher()
+        cvc.add_issue_select_details(
+            issue_id, image_url, thumb_url, cover_date, page_url)
+
+    def fetchAlternateCoverURLs(self, issue_id, issue_page_url):
+        url_list = self.fetchCachedAlternateCoverURLs(issue_id)
+        if url_list is not None:
+            return url_list
+
+        # scrape the CV issue page URL to get the alternate cover URLs
+        resp = urllib.request.urlopen(issue_page_url, context=self.ssl)
+        content = resp.read()
+        alt_cover_url_list = self.parseOutAltCoverUrls(content)
+
+        # cache this alt cover URL list
+        self.cacheAlternateCoverURLs(issue_id, alt_cover_url_list)
+
+        return alt_cover_url_list
+
+    def parseOutAltCoverUrls(self, page_html):
+        soup = BeautifulSoup(page_html, "html.parser")
+    
+        alt_cover_url_list = []
+    
+        # Using knowledge of the layout of the Comic Vine issue page here:
+        # look for the divs that are in the classes 'imgboxart' and
+        # 'issue-cover'
+        div_list = soup.find_all('div')
+        covers_found = 0
+        for d in div_list:
+            if 'class' in d.attrs:
+                c = d['class']
+                if ('imgboxart' in c and 
+                        'issue-cover' in c and
+                        d.img['src'].startswith("http")
+                   ):
+                    
+                    covers_found += 1
+                    if covers_found != 1:
+                            alt_cover_url_list.append(d.img['src'])
+    
+        return alt_cover_url_list
+
+    def fetchCachedAlternateCoverURLs(self, issue_id):
+
+        # before we search online, look in our cache, since we might already
+        # have this info
+        cvc = ComicVineCacher()
+        url_list = cvc.get_alt_covers(issue_id)
+        if url_list is not None:
+            return url_list
+        else:
+            return None
+
+    def cacheAlternateCoverURLs(self, issue_id, url_list):
+        cvc = ComicVineCacher()
+        cvc.add_alt_covers(issue_id, url_list)
+
+    #-------------------------------------------------------------------------
+    urlFetchComplete = pyqtSignal(str, str, int)
+
+    def asyncFetchIssueCoverURLs(self, issue_id):
+
+        self.issue_id = issue_id
+        details = self.fetchCachedIssueSelectDetails(issue_id)
+        if details['image_url'] is not None:
+            self.urlFetchComplete.emit(
+                details['image_url'],
+                details['thumb_image_url'],
+                self.issue_id)
+            return
+
+        issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + \
+            str(issue_id) + "/?api_key=" + self.api_key + \
+            "&format=json&field_list=image,cover_date,site_detail_url"
+        self.nam = QNetworkAccessManager()
+        self.nam.finished.connect(self.asyncFetchIssueCoverURLComplete)
+        self.nam.get(QNetworkRequest(QUrl(issue_url)))
+
+    def asyncFetchIssueCoverURLComplete(self, reply):
+
+        # read in the response
+        data = reply.readAll()
+
+        try:
+            cv_response = json.loads(bytes(data))
+        except Exception as e:
+            print("Comic Vine query failed to get JSON data", file=sys.stderr)
+            print(str(data), file=sys.stderr)
+            return
+
+        if cv_response['status_code'] != 1:
+            print("Comic Vine query failed with error:  [{0}]. ".format(
+                cv_response['error']), file=sys.stderr)
+            return
+
+        image_url = cv_response['results']['image']['super_url']
+        thumb_url = cv_response['results']['image']['thumb_url']
+        cover_date = cv_response['results']['cover_date']
+        page_url = cv_response['results']['site_detail_url']
+
+        self.cacheIssueSelectDetails(
+            self.issue_id, image_url, thumb_url, cover_date, page_url)
+
+        self.urlFetchComplete.emit(image_url, thumb_url, self.issue_id)
+
+    altUrlListFetchComplete = pyqtSignal(list, int)
+
+    def asyncFetchAlternateCoverURLs(self, issue_id, issue_page_url):
+        # This async version requires the issue page url to be provided!
+        self.issue_id = issue_id
+        url_list = self.fetchCachedAlternateCoverURLs(issue_id)
+        if url_list is not None:
+            self.altUrlListFetchComplete.emit(url_list, int(self.issue_id))
+            return
+
+        self.nam = QNetworkAccessManager()
+        self.nam.finished.connect(self.asyncFetchAlternateCoverURLsComplete)
+        self.nam.get(QNetworkRequest(QUrl(str(issue_page_url))))
+
+    def asyncFetchAlternateCoverURLsComplete(self, reply):
+        # read in the response
+        html = str(reply.readAll())
+        alt_cover_url_list = self.parseOutAltCoverUrls(html)
+
+        # cache this alt cover URL list
+        self.cacheAlternateCoverURLs(self.issue_id, alt_cover_url_list)
+
+        self.altUrlListFetchComplete.emit(
+            alt_cover_url_list, int(self.issue_id))
+
+    def repairUrls(self, issue_list):
+        # make sure there are URLs for the image fields
+        for issue in issue_list:
+            if issue['image'] is None:
+                issue['image'] = dict()
+                issue['image']['super_url'] = ComicVineTalker.logo_url
+                issue['image']['thumb_url'] = ComicVineTalker.logo_url

comictaggerlib/coverimagewidget.py

@@ -0,0 +1,326 @@
+"""A PyQt5 widget to display cover images
+
+Display cover images from either a local archive, or from Comic Vine.
+TODO: This should be re-factored using subclasses!
+"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+from PyQt5.QtCore import *
+from PyQt5.QtWidgets import *
+from PyQt5.QtGui import *
+from PyQt5 import uic
+
+from .settings import ComicTaggerSettings
+from .comicvinetalker import ComicVineTalker, ComicVineTalkerException
+from .imagefetcher import ImageFetcher
+from .pageloader import PageLoader
+from .imagepopup import ImagePopup
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize, getQImageFromData
+#from genericmetadata import GenericMetadata, PageType
+#from comicarchive import MetaDataStyle
+#import utils
+
+
+def clickable(widget):
+    """# Allow a label to be clickable"""
+
+    class Filter(QObject):
+
+        dblclicked = pyqtSignal()
+
+        def eventFilter(self, obj, event):
+
+            if obj == widget:
+                if event.type() == QEvent.MouseButtonDblClick:
+                    self.dblclicked.emit()
+                    return True
+
+            return False
+
+    filter = Filter(widget)
+    widget.installEventFilter(filter)
+    return filter.dblclicked
+
+
+class CoverImageWidget(QWidget):
+
+    ArchiveMode = 0
+    AltCoverMode = 1
+    URLMode = 1
+    DataMode = 3
+
+    def __init__(self, parent, mode, expand_on_click=True):
+        super(CoverImageWidget, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('coverimagewidget.ui'), self)
+
+        reduceWidgetFontSize(self.label)
+
+        self.mode = mode
+        self.comicVine = ComicVineTalker()
+        self.page_loader = None
+        self.showControls = True
+
+        self.btnLeft.setIcon(QIcon(ComicTaggerSettings.getGraphic('left.png')))
+        self.btnRight.setIcon(
+            QIcon(ComicTaggerSettings.getGraphic('right.png')))
+
+        self.btnLeft.clicked.connect(self.decrementImage)
+        self.btnRight.clicked.connect(self.incrementImage)
+        self.resetWidget()
+        if expand_on_click:
+            clickable(self.lblImage).connect(self.showPopup)
+        else:
+            self.lblImage.setToolTip("")
+
+        self.updateContent()
+
+    def resetWidget(self):
+        self.comic_archive = None
+        self.issue_id = None
+        self.comicVine = None
+        self.cover_fetcher = None
+        self.url_list = []
+        if self.page_loader is not None:
+            self.page_loader.abandoned = True
+        self.page_loader = None
+        self.imageIndex = -1
+        self.imageCount = 1
+        self.imageData = None
+
+    def clear(self):
+        self.resetWidget()
+        self.updateContent()
+
+    def incrementImage(self):
+        self.imageIndex += 1
+        if self.imageIndex == self.imageCount:
+            self.imageIndex = 0
+        self.updateContent()
+
+    def decrementImage(self):
+        self.imageIndex -= 1
+        if self.imageIndex == -1:
+            self.imageIndex = self.imageCount - 1
+        self.updateContent()
+
+    def setArchive(self, ca, page=0):
+        if self.mode == CoverImageWidget.ArchiveMode:
+            self.resetWidget()
+            self.comic_archive = ca
+            self.imageIndex = page
+            self.imageCount = ca.getNumberOfPages()
+            self.updateContent()
+
+    def setURL(self, url):
+        if self.mode == CoverImageWidget.URLMode:
+            self.resetWidget()
+            self.updateContent()
+
+            self.url_list = [url]
+            self.imageIndex = 0
+            self.imageCount = 1
+            self.updateContent()
+
+    def setIssueID(self, issue_id):
+        if self.mode == CoverImageWidget.AltCoverMode:
+            self.resetWidget()
+            self.updateContent()
+
+            self.issue_id = issue_id
+
+            self.comicVine = ComicVineTalker()
+            self.comicVine.urlFetchComplete.connect(
+                self.primaryUrlFetchComplete)
+            self.comicVine.asyncFetchIssueCoverURLs(int(self.issue_id))
+
+    def setImageData(self, image_data):
+        if self.mode == CoverImageWidget.DataMode:
+            self.resetWidget()
+
+            if image_data is None:
+                self.imageIndex = -1
+            else:
+                self.imageIndex = 0
+                self.imageData = image_data
+
+            self.updateContent()
+
+    def primaryUrlFetchComplete(self, primary_url, thumb_url, issue_id):
+        self.url_list.append(str(primary_url))
+        self.imageIndex = 0
+        self.imageCount = len(self.url_list)
+        self.updateContent()
+
+        # defer the alt cover search
+        QTimer.singleShot(1, self.startAltCoverSearch)
+
+    def startAltCoverSearch(self):
+
+        # now we need to get the list of alt cover URLs
+        self.label.setText("Searching for alt. covers...")
+
+        # page URL should already be cached, so no need to defer
+        self.comicVine = ComicVineTalker()
+        issue_page_url = self.comicVine.fetchIssuePageURL(self.issue_id)
+        self.comicVine.altUrlListFetchComplete.connect(
+            self.altCoverUrlListFetchComplete)
+        self.comicVine.asyncFetchAlternateCoverURLs(
+            int(self.issue_id), issue_page_url)
+
+    def altCoverUrlListFetchComplete(self, url_list, issue_id):
+        if len(url_list) > 0:
+            self.url_list.extend(url_list)
+            self.imageCount = len(self.url_list)
+        self.updateControls()
+
+    def setPage(self, pagenum):
+        if self.mode == CoverImageWidget.ArchiveMode:
+            self.imageIndex = pagenum
+            self.updateContent()
+
+    def updateContent(self):
+        self.updateImage()
+        self.updateControls()
+
+    def updateImage(self):
+        if self.imageIndex == -1:
+            self.loadDefault()
+        elif self.mode in [CoverImageWidget.AltCoverMode, CoverImageWidget.URLMode]:
+            self.loadURL()
+        elif self.mode == CoverImageWidget.DataMode:
+            self.coverRemoteFetchComplete(self.imageData, 0)
+        else:
+            self.loadPage()
+
+    def updateControls(self):
+        if not self.showControls or self.mode == CoverImageWidget.DataMode:
+            self.btnLeft.hide()
+            self.btnRight.hide()
+            self.label.hide()
+            return
+
+        if self.imageIndex == -1 or self.imageCount == 1:
+            self.btnLeft.setEnabled(False)
+            self.btnRight.setEnabled(False)
+            self.btnLeft.hide()
+            self.btnRight.hide()
+        else:
+            self.btnLeft.setEnabled(True)
+            self.btnRight.setEnabled(True)
+            self.btnLeft.show()
+            self.btnRight.show()
+
+        if self.imageIndex == -1 or self.imageCount == 1:
+            self.label.setText("")
+        elif self.mode == CoverImageWidget.AltCoverMode:
+            self.label.setText(
+                "Cover {0} (of {1})".format(
+                    self.imageIndex + 1,
+                    self.imageCount))
+        else:
+            self.label.setText(
+                "Page {0} (of {1})".format(
+                    self.imageIndex + 1,
+                    self.imageCount))
+
+    def loadURL(self):
+        self.loadDefault()
+        self.cover_fetcher = ImageFetcher()
+        self.cover_fetcher.fetchComplete.connect(self.coverRemoteFetchComplete)
+        self.cover_fetcher.fetch(self.url_list[self.imageIndex])
+        #print("ATB cover fetch started...")
+
+    # called when the image is done loading from internet
+    def coverRemoteFetchComplete(self, image_data, issue_id):
+        img = getQImageFromData(image_data)
+        self.current_pixmap = QPixmap(img)
+        self.setDisplayPixmap(0, 0)
+        #print("ATB cover fetch complete!")
+
+    def loadPage(self):
+        if self.comic_archive is not None:
+            if self.page_loader is not None:
+                self.page_loader.abandoned = True
+            self.page_loader = PageLoader(self.comic_archive, self.imageIndex)
+            self.page_loader.loadComplete.connect(self.pageLoadComplete)
+            self.page_loader.start()
+
+    def pageLoadComplete(self, img):
+        self.current_pixmap = QPixmap(img)
+        self.setDisplayPixmap(0, 0)
+        self.page_loader = None
+
+    def loadDefault(self):
+        self.current_pixmap = QPixmap(
+            ComicTaggerSettings.getGraphic('nocover.png'))
+        #print("loadDefault called")
+        self.setDisplayPixmap(0, 0)
+
+    def resizeEvent(self, resize_event):
+        if self.current_pixmap is not None:
+            delta_w = resize_event.size().width() - \
+                resize_event.oldSize().width()
+            delta_h = resize_event.size().height() - \
+                resize_event.oldSize().height()
+            # print "ATB resizeEvent deltas", resize_event.size().width(),
+            # resize_event.size().height()
+            self.setDisplayPixmap(delta_w, delta_h)
+
+    def setDisplayPixmap(self, delta_w, delta_h):
+        """The deltas let us know what the new width and height of the label will be"""
+
+        #new_h = self.frame.height() + delta_h
+        #new_w = self.frame.width() + delta_w
+        # print "ATB setDisplayPixmap deltas", delta_w , delta_h
+        # print "ATB self.frame", self.frame.width(), self.frame.height()
+        # print "ATB self.", self.width(), self.height()
+
+        #frame_w = new_w
+        #frame_h = new_h
+
+        new_h = self.frame.height()
+        new_w = self.frame.width()
+        frame_w = self.frame.width()
+        frame_h = self.frame.height()
+
+        new_h -= 4
+        new_w -= 4
+
+        if new_h < 0:
+            new_h = 0
+        if new_w < 0:
+            new_w = 0
+
+        # print "ATB setDisplayPixmap deltas", delta_w , delta_h
+        # print "ATB self.frame", frame_w, frame_h
+        # print "ATB new size", new_w, new_h
+
+        # scale the pixmap to fit in the frame
+        scaled_pixmap = self.current_pixmap.scaled(
+            new_w, new_h, Qt.KeepAspectRatio)
+        self.lblImage.setPixmap(scaled_pixmap)
+
+        # move and resize the label to be centered in the fame
+        img_w = scaled_pixmap.width()
+        img_h = scaled_pixmap.height()
+        self.lblImage.resize(img_w, img_h)
+        self.lblImage.move((frame_w - img_w) / 2, (frame_h - img_h) / 2)
+
+    def showPopup(self):
+        self.popup = ImagePopup(self, self.current_pixmap)

comictaggerlib/crediteditorwindow.py

@@ -0,0 +1,96 @@
+"""A PyQT4 dialog to edit credits"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+
+
+class CreditEditorWindow(QtWidgets.QDialog):
+
+    ModeEdit = 0
+    ModeNew = 1
+
+    def __init__(self, parent, mode, role, name, primary):
+        super(CreditEditorWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('crediteditorwindow.ui'), self)
+
+        self.mode = mode
+
+        if self.mode == self.ModeEdit:
+            self.setWindowTitle("Edit Credit")
+        else:
+            self.setWindowTitle("New Credit")
+
+        # Add the entries to the role combobox
+        self.cbRole.addItem("")
+        self.cbRole.addItem("Writer")
+        self.cbRole.addItem("Artist")
+        self.cbRole.addItem("Penciller")
+        self.cbRole.addItem("Inker")
+        self.cbRole.addItem("Colorist")
+        self.cbRole.addItem("Letterer")
+        self.cbRole.addItem("Cover Artist")
+        self.cbRole.addItem("Editor")
+        self.cbRole.addItem("Other")
+        self.cbRole.addItem("Plotter")
+        self.cbRole.addItem("Scripter")
+
+        self.leName.setText(name)
+
+        if role is not None and role != "":
+            i = self.cbRole.findText(role)
+            if i == -1:
+                self.cbRole.setEditText(role)
+            else:
+                self.cbRole.setCurrentIndex(i)
+
+        if primary:
+            self.cbPrimary.setCheckState(QtCore.Qt.Checked)
+
+        self.cbRole.currentIndexChanged.connect(self.roleChanged)
+        self.cbRole.editTextChanged.connect(self.roleChanged)
+
+        self.updatePrimaryButton()
+
+    def updatePrimaryButton(self):
+        enabled = self.currentRoleCanBePrimary()
+        self.cbPrimary.setEnabled(enabled)
+
+    def currentRoleCanBePrimary(self):
+        role = self.cbRole.currentText()
+        if str(role).lower() == "writer" or str(role).lower() == "artist":
+            return True
+        else:
+            return False
+
+    def roleChanged(self, s):
+        self.updatePrimaryButton()
+
+    def getCredits(self):
+        primary = self.currentRoleCanBePrimary() and self.cbPrimary.isChecked()
+        return self.cbRole.currentText(), self.leName.text(), primary
+
+    def accept(self):
+        if self.cbRole.currentText() == "" or self.leName.text() == "":
+            QtWidgets.QMessageBox.warning(self, self.tr("Whoops"), self.tr(
+                "You need to enter both role and name for a credit."))
+        else:
+            QtWidgets.QDialog.accept(self)

comictaggerlib/exportwindow.py

@@ -0,0 +1,64 @@
+"""A PyQT4 dialog to confirm and set options for export to zip"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+#from settingswindow import SettingsWindow
+#from filerenamer import FileRenamer
+#import utils
+
+
+class ExportConflictOpts:
+    dontCreate = 1
+    overwrite = 2
+    createUnique = 3
+
+
+class ExportWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent, settings, msg):
+        super(ExportWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('exportwindow.ui'), self)
+        self.label.setText(msg)
+
+        self.setWindowFlags(self.windowFlags() &
+                            ~QtCore.Qt.WindowContextHelpButtonHint)
+
+        self.settings = settings
+
+        self.cbxDeleteOriginal.setCheckState(QtCore.Qt.Unchecked)
+        self.cbxAddToList.setCheckState(QtCore.Qt.Checked)
+        self.radioDontCreate.setChecked(True)
+
+        self.deleteOriginal = False
+        self.addToList = True
+        self.fileConflictBehavior = ExportConflictOpts.dontCreate
+
+    def accept(self):
+        QtWidgets.QDialog.accept(self)
+
+        self.deleteOriginal = self.cbxDeleteOriginal.isChecked()
+        self.addToList = self.cbxAddToList.isChecked()
+        if self.radioDontCreate.isChecked():
+            self.fileConflictBehavior = ExportConflictOpts.dontCreate
+        elif self.radioCreateNew.isChecked():
+            self.fileConflictBehavior = ExportConflictOpts.createUnique
+        # else:
+        #    self.fileConflictBehavior = ExportConflictOpts.overwrite

comictaggerlib/filenameparser.py

@@ -0,0 +1 @@
+from comicapi.filenameparser import *

comictaggerlib/filerenamer.py

@@ -0,0 +1,156 @@
+"""Functions for renaming files based on metadata"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+import re
+import datetime
+
+from . import utils
+from .issuestring import IssueString
+
+
+class FileRenamer:
+
+    def __init__(self, metadata):
+        self.setMetadata(metadata)
+        self.setTemplate(
+            "%series% v%volume% #%issue% (of %issuecount%) (%year%)")
+        self.smart_cleanup = True
+        self.issue_zero_padding = 3
+
+    def setMetadata(self, metadata):
+        self.metdata = metadata
+
+    def setIssueZeroPadding(self, count):
+        self.issue_zero_padding = count
+
+    def setSmartCleanup(self, on):
+        self.smart_cleanup = on
+
+    def setTemplate(self, template):
+        self.template = template
+
+    def replaceToken(self, text, value, token):
+        # helper func
+        def isToken(word):
+            return (word[0] == "%" and word[-1:] == "%")
+
+        if value is not None:
+            return text.replace(token, str(value))
+        else:
+            if self.smart_cleanup:
+                # smart cleanup means we want to remove anything appended to token if it's empty
+                # (e.g "#%issue%"  or "v%volume%")
+                # (TODO: This could fail if there is more than one token appended together, I guess)
+                text_list = text.split()
+
+                # special case for issuecount, remove preceding non-token word,
+                # as in "...(of %issuecount%)..."
+                if token == '%issuecount%':
+                    for idx, word in enumerate(text_list):
+                        if token in word and not isToken(text_list[idx - 1]):
+                            text_list[idx - 1] = ""
+
+                text_list = [x for x in text_list if token not in x]
+                return " ".join(text_list)
+            else:
+                return text.replace(token, "")
+
+    def determineName(self, filename, ext=None):
+
+        md = self.metdata
+        new_name = self.template
+        preferred_encoding = utils.get_actual_preferred_encoding()
+
+        # print(u"{0}".format(md))
+
+        new_name = self.replaceToken(new_name, md.series, '%series%')
+        new_name = self.replaceToken(new_name, md.volume, '%volume%')
+
+        if md.issue is not None:
+            issue_str = "{0}".format(
+                IssueString(md.issue).asString(pad=self.issue_zero_padding))
+        else:
+            issue_str = None
+        new_name = self.replaceToken(new_name, issue_str, '%issue%')
+
+        new_name = self.replaceToken(new_name, md.issueCount, '%issuecount%')
+        new_name = self.replaceToken(new_name, md.year, '%year%')
+        new_name = self.replaceToken(new_name, md.publisher, '%publisher%')
+        new_name = self.replaceToken(new_name, md.title, '%title%')
+        new_name = self.replaceToken(new_name, md.month, '%month%')
+        month_name = None
+        if md.month is not None:
+            if (isinstance(md.month, str) and md.month.isdigit()) or isinstance(
+                    md.month, int):
+                if int(md.month) in range(1, 13):
+                    dt = datetime.datetime(1970, int(md.month), 1, 0, 0)
+                    #month_name = dt.strftime("%B".encode(preferred_encoding)).decode(preferred_encoding)
+                    month_name = dt.strftime("%B")
+        new_name = self.replaceToken(new_name, month_name, '%month_name%')
+
+        new_name = self.replaceToken(new_name, md.genre, '%genre%')
+        new_name = self.replaceToken(new_name, md.language, '%language_code%')
+        new_name = self.replaceToken(
+            new_name, md.criticalRating, '%criticalrating%')
+        new_name = self.replaceToken(
+            new_name, md.alternateSeries, '%alternateseries%')
+        new_name = self.replaceToken(
+            new_name, md.alternateNumber, '%alternatenumber%')
+        new_name = self.replaceToken(
+            new_name, md.alternateCount, '%alternatecount%')
+        new_name = self.replaceToken(new_name, md.imprint, '%imprint%')
+        new_name = self.replaceToken(new_name, md.format, '%format%')
+        new_name = self.replaceToken(
+            new_name, md.maturityRating, '%maturityrating%')
+        new_name = self.replaceToken(new_name, md.storyArc, '%storyarc%')
+        new_name = self.replaceToken(new_name, md.seriesGroup, '%seriesgroup%')
+        new_name = self.replaceToken(new_name, md.scanInfo, '%scaninfo%')
+
+        if self.smart_cleanup:
+
+            # remove empty braces,brackets, parentheses
+            new_name = re.sub("\(\s*[-:]*\s*\)", "", new_name)
+            new_name = re.sub("\[\s*[-:]*\s*\]", "", new_name)
+            new_name = re.sub("\{\s*[-:]*\s*\}", "", new_name)
+
+            # remove duplicate spaces
+            new_name = " ".join(new_name.split())
+
+            # remove remove duplicate -, _,
+            new_name = re.sub("[-_]{2,}\s+", "-- ", new_name)
+            new_name = re.sub("(\s--)+", " --", new_name)
+            new_name = re.sub("(\s-)+", " -", new_name)
+
+            # remove dash or double dash at end of line
+            new_name = re.sub("[-]{1,2}\s*$", "", new_name)
+
+            # remove duplicate spaces (again!)
+            new_name = " ".join(new_name.split())
+
+        if ext is None:
+            ext = os.path.splitext(filename)[1]
+
+        new_name += ext
+
+        # some tweaks to keep various filesystems happy
+        new_name = new_name.replace("/", "-")
+        new_name = new_name.replace(" :", " -")
+        new_name = new_name.replace(": ", " - ")
+        new_name = new_name.replace(":", "-")
+        new_name = new_name.replace("?", "")
+
+        return new_name

comictaggerlib/fileselectionlist.py

@@ -0,0 +1,447 @@
+# coding=utf-8
+"""A PyQt5 widget for managing list of comic archive files"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import platform
+import os
+#import os
+import sys
+
+from PyQt5.QtCore import *
+from PyQt5.QtGui import *
+from PyQt5.QtWidgets import *
+from PyQt5 import uic
+from PyQt5.QtCore import pyqtSignal
+
+from .settings import ComicTaggerSettings
+from .comicarchive import ComicArchive
+from .optionalmsgdialog import OptionalMessageDialog
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize, centerWindowOnParent
+from . import utils
+#from comicarchive import MetaDataStyle
+#from genericmetadata import GenericMetadata, PageType
+
+
+class FileTableWidgetItem(QTableWidgetItem):
+
+    def __lt__(self, other):
+        #return (self.data(Qt.UserRole).toBool() <
+        #        other.data(Qt.UserRole).toBool())
+        return (self.data(Qt.UserRole) <
+                other.data(Qt.UserRole))
+
+
+class FileInfo():
+
+    def __init__(self, ca):
+        self.ca = ca
+
+
+class FileSelectionList(QWidget):
+
+    selectionChanged = pyqtSignal(QVariant)
+    listCleared = pyqtSignal()
+
+    fileColNum = 0
+    CRFlagColNum = 1
+    CBLFlagColNum = 2
+    typeColNum = 3
+    readonlyColNum = 4
+    folderColNum = 5
+    dataColNum = fileColNum
+
+    def __init__(self, parent, settings):
+        super(FileSelectionList, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('fileselectionlist.ui'), self)
+
+        self.settings = settings
+
+        reduceWidgetFontSize(self.twList)
+
+        self.twList.setColumnCount(6)
+        #self.twlist.setHorizontalHeaderLabels (["File", "Folder", "CR", "CBL", ""])
+        # self.twList.horizontalHeader().setStretchLastSection(True)
+        self.twList.currentItemChanged.connect(self.currentItemChangedCB)
+
+        self.currentItem = None
+        self.setContextMenuPolicy(Qt.ActionsContextMenu)
+        self.modifiedFlag = False
+
+        selectAllAction = QAction("Select All", self)
+        removeAction = QAction("Remove Selected Items", self)
+        self.separator = QAction("", self)
+        self.separator.setSeparator(True)
+
+        selectAllAction.setShortcut('Ctrl+A')
+        removeAction.setShortcut('Ctrl+X')
+
+        selectAllAction.triggered.connect(self.selectAll)
+        removeAction.triggered.connect(self.removeSelection)
+
+        self.addAction(selectAllAction)
+        self.addAction(removeAction)
+        self.addAction(self.separator)
+
+    def getSorting(self):
+        col = self.twList.horizontalHeader().sortIndicatorSection()
+        order = self.twList.horizontalHeader().sortIndicatorOrder()
+        return col, order
+
+    def setSorting(self, col, order):
+        col = self.twList.horizontalHeader().setSortIndicator(col, order)
+
+    def addAppAction(self, action):
+        self.insertAction(None, action)
+
+    def setModifiedFlag(self, modified):
+        self.modifiedFlag = modified
+
+    def selectAll(self):
+        self.twList.setRangeSelected(
+            QTableWidgetSelectionRange(
+                0,
+                0,
+                self.twList.rowCount() -
+                1,
+                5),
+            True)
+
+    def deselectAll(self):
+        self.twList.setRangeSelected(
+            QTableWidgetSelectionRange(
+                0,
+                0,
+                self.twList.rowCount() -
+                1,
+                5),
+            False)
+
+    def removeArchiveList(self, ca_list):
+        self.twList.setSortingEnabled(False)
+        for ca in ca_list:
+            for row in range(self.twList.rowCount()):
+                row_ca = self.getArchiveByRow(row)
+                if row_ca == ca:
+                    self.twList.removeRow(row)
+                    break
+        self.twList.setSortingEnabled(True)
+
+    def getArchiveByRow(self, row):
+        fi = self.twList.item(row, FileSelectionList.dataColNum).data(
+            Qt.UserRole)
+        return fi.ca
+
+    def getCurrentArchive(self):
+        return self.getArchiveByRow(self.twList.currentRow())
+
+    def removeSelection(self):
+        row_list = []
+        for item in self.twList.selectedItems():
+            if item.column() == 0:
+                row_list.append(item.row())
+
+        if len(row_list) == 0:
+            return
+
+        if self.twList.currentRow() in row_list:
+            if not self.modifiedFlagVerification(
+                    "Remove Archive",
+                    "If you close this archive, data in the form will be lost.  Are you sure?"):
+                return
+
+        row_list.sort()
+        row_list.reverse()
+
+        self.twList.currentItemChanged.disconnect(self.currentItemChangedCB)
+        self.twList.setSortingEnabled(False)
+
+        for i in row_list:
+            self.twList.removeRow(i)
+
+        self.twList.setSortingEnabled(True)
+        self.twList.currentItemChanged.connect(self.currentItemChangedCB)
+
+        if self.twList.rowCount() > 0:
+            # since on a removal, we select row 0, make sure callback occurs if
+            # we're already there
+            if self.twList.currentRow() == 0:
+                self.currentItemChangedCB(self.twList.currentItem(), None)
+            self.twList.selectRow(0)
+        else:
+            self.listCleared.emit()
+
+    def addPathList(self, pathlist):
+
+        filelist = utils.get_recursive_filelist(pathlist)
+        # we now have a list of files to add
+
+        # Prog dialog on Linux flakes out for small range, so scale up
+        progdialog = QProgressDialog("", "Cancel", 0, len(filelist), parent=self)
+        progdialog.setWindowTitle("Adding Files")
+        progdialog.setWindowModality(Qt.ApplicationModal)
+        progdialog.setMinimumDuration(300)
+        centerWindowOnParent(progdialog)
+        #QCoreApplication.processEvents()
+        #progdialog.show()
+        
+        QCoreApplication.processEvents()
+        firstAdded = None
+        self.twList.setSortingEnabled(False)
+        for idx, f in enumerate(filelist):
+            QCoreApplication.processEvents()
+            if progdialog.wasCanceled():
+                break
+            progdialog.setValue(idx+1)
+            progdialog.setLabelText(f)
+            centerWindowOnParent(progdialog)
+            QCoreApplication.processEvents()
+            row = self.addPathItem(f)
+            if firstAdded is None and row is not None:
+                firstAdded = row
+ 
+        progdialog.hide()
+        QCoreApplication.processEvents()
+
+        if firstAdded is not None:
+            self.twList.selectRow(firstAdded)
+        else:
+            if len(pathlist) == 1 and os.path.isfile(pathlist[0]):
+                QMessageBox.information(self, self.tr("File Open"), self.tr(
+                    "Selected file doesn't seem to be a comic archive."))
+            else:
+                QMessageBox.information(
+                    self,
+                    self.tr("File/Folder Open"),
+                    self.tr("No readable comic archives were found."))
+
+        self.twList.setSortingEnabled(True)
+
+        # Adjust column size
+        self.twList.resizeColumnsToContents()
+        self.twList.setColumnWidth(FileSelectionList.CRFlagColNum, 35)
+        self.twList.setColumnWidth(FileSelectionList.CBLFlagColNum, 35)
+        self.twList.setColumnWidth(FileSelectionList.readonlyColNum, 35)
+        self.twList.setColumnWidth(FileSelectionList.typeColNum, 45)
+        if self.twList.columnWidth(FileSelectionList.fileColNum) > 250:
+            self.twList.setColumnWidth(FileSelectionList.fileColNum, 250)
+        if self.twList.columnWidth(FileSelectionList.folderColNum) > 200:
+            self.twList.setColumnWidth(FileSelectionList.folderColNum, 200)
+
+    def isListDupe(self, path):
+        r = 0
+        while r < self.twList.rowCount():
+            ca = self.getArchiveByRow(r)
+            if ca.path == path:
+                return True
+            r = r + 1
+
+        return False
+
+    def getCurrentListRow(self, path):
+        r = 0
+        while r < self.twList.rowCount():
+            ca = self.getArchiveByRow(r)
+            if ca.path == path:
+                return r
+            r = r + 1
+
+        return -1
+
+    def addPathItem(self, path):
+        path = str(path)
+        path = os.path.abspath(path)
+        # print "processing", path
+
+        if self.isListDupe(path):
+            return self.getCurrentListRow(path)
+
+        ca = ComicArchive(
+            path,
+            self.settings.rar_exe_path,
+            ComicTaggerSettings.getGraphic('nocover.png'))
+
+        if ca.seemsToBeAComicArchive():
+            row = self.twList.rowCount()
+            self.twList.insertRow(row)
+
+            fi = FileInfo(ca)
+
+            filename_item = QTableWidgetItem()
+            folder_item = QTableWidgetItem()
+            cix_item = FileTableWidgetItem()
+            cbi_item = FileTableWidgetItem()
+            readonly_item = FileTableWidgetItem()
+            type_item = QTableWidgetItem()
+
+            filename_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            filename_item.setData(Qt.UserRole, fi)
+            self.twList.setItem(
+                row, FileSelectionList.fileColNum, filename_item)
+
+            folder_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            self.twList.setItem(
+                row, FileSelectionList.folderColNum, folder_item)
+
+            type_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            self.twList.setItem(row, FileSelectionList.typeColNum, type_item)
+
+            cix_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            cix_item.setTextAlignment(Qt.AlignHCenter)
+            self.twList.setItem(row, FileSelectionList.CRFlagColNum, cix_item)
+
+            cbi_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            cbi_item.setTextAlignment(Qt.AlignHCenter)
+            self.twList.setItem(row, FileSelectionList.CBLFlagColNum, cbi_item)
+
+            readonly_item.setFlags(Qt.ItemIsSelectable | Qt.ItemIsEnabled)
+            readonly_item.setTextAlignment(Qt.AlignHCenter)
+            self.twList.setItem(
+                row, FileSelectionList.readonlyColNum, readonly_item)
+
+            self.updateRow(row)
+
+            return row
+
+    def updateRow(self, row):
+        fi = self.twList.item(row, FileSelectionList.dataColNum).data(
+            Qt.UserRole) #.toPyObject()
+
+        filename_item = self.twList.item(row, FileSelectionList.fileColNum)
+        folder_item = self.twList.item(row, FileSelectionList.folderColNum)
+        cix_item = self.twList.item(row, FileSelectionList.CRFlagColNum)
+        cbi_item = self.twList.item(row, FileSelectionList.CBLFlagColNum)
+        type_item = self.twList.item(row, FileSelectionList.typeColNum)
+        readonly_item = self.twList.item(row, FileSelectionList.readonlyColNum)
+
+        item_text = os.path.split(fi.ca.path)[0]
+        folder_item.setText(item_text)
+        folder_item.setData(Qt.ToolTipRole, item_text)
+
+        item_text = os.path.split(fi.ca.path)[1]
+        filename_item.setText(item_text)
+        filename_item.setData(Qt.ToolTipRole, item_text)
+
+        if fi.ca.isZip():
+            item_text = "ZIP"
+        elif fi.ca.isRar():
+            item_text = "RAR"
+        else:
+            item_text = ""
+        type_item.setText(item_text)
+        type_item.setData(Qt.ToolTipRole, item_text)
+
+        if fi.ca.hasCIX():
+            cix_item.setCheckState(Qt.Checked)
+            cix_item.setData(Qt.UserRole, True)
+        else:
+            cix_item.setData(Qt.UserRole, False)
+            cix_item.setCheckState(Qt.Unchecked)
+
+        if fi.ca.hasCBI():
+            cbi_item.setCheckState(Qt.Checked)
+            cbi_item.setData(Qt.UserRole, True)
+        else:
+            cbi_item.setData(Qt.UserRole, False)
+            cbi_item.setCheckState(Qt.Unchecked)
+
+        if not fi.ca.isWritable():
+            readonly_item.setCheckState(Qt.Checked)
+            readonly_item.setData(Qt.UserRole, True)
+        else:
+            readonly_item.setData(Qt.UserRole, False)
+            readonly_item.setCheckState(Qt.Unchecked)
+
+        # Reading these will force them into the ComicArchive's cache
+        fi.ca.readCIX()
+        fi.ca.hasCBI()
+
+    def getSelectedArchiveList(self):
+        ca_list = []
+        for r in range(self.twList.rowCount()):
+            item = self.twList.item(r, FileSelectionList.dataColNum)
+            if item.isSelected():
+                fi = item.data(Qt.UserRole)
+                ca_list.append(fi.ca)
+
+        return ca_list
+
+    def updateCurrentRow(self):
+        self.updateRow(self.twList.currentRow())
+
+    def updateSelectedRows(self):
+        self.twList.setSortingEnabled(False)
+        for r in range(self.twList.rowCount()):
+            item = self.twList.item(r, FileSelectionList.dataColNum)
+            if item.isSelected():
+                self.updateRow(r)
+        self.twList.setSortingEnabled(True)
+
+    def currentItemChangedCB(self, curr, prev):
+
+        new_idx = curr.row()
+        old_idx = -1
+        if prev is not None:
+            old_idx = prev.row()
+        #print("old {0} new {1}".format(old_idx, new_idx))
+
+        if old_idx == new_idx:
+            return
+
+        # don't allow change if modified
+        if prev is not None and new_idx != old_idx:
+            if not self.modifiedFlagVerification(
+                    "Change Archive",
+                    "If you change archives now, data in the form will be lost.  Are you sure?"):
+                self.twList.currentItemChanged.disconnect(
+                    self.currentItemChangedCB)
+                self.twList.setCurrentItem(prev)
+                self.twList.currentItemChanged.connect(
+                    self.currentItemChangedCB)
+                # Need to defer this revert selection, for some reason
+                QTimer.singleShot(1, self.revertSelection)
+                return
+
+        fi = self.twList.item(new_idx, FileSelectionList.dataColNum).data(
+            Qt.UserRole) #.toPyObject()
+        self.selectionChanged.emit(QVariant(fi))
+
+    def revertSelection(self):
+        self.twList.selectRow(self.twList.currentRow())
+
+    def modifiedFlagVerification(self, title, desc):
+        if self.modifiedFlag:
+            reply = QMessageBox.question(self,
+                                         self.tr(title),
+                                         self.tr(desc),
+                                         QMessageBox.Yes, QMessageBox.No)
+
+            if reply != QMessageBox.Yes:
+                return False
+        return True
+
+
+# Attempt to use a special checkbox widget in the cell.
+# Couldn't figure out how to disable it with "enabled" colors
+#w = QWidget()
+#cb = QCheckBox(w)
+# cb.setCheckState(Qt.Checked)
+#layout = QHBoxLayout()
+# layout.addWidget(cb)
+# layout.setAlignment(Qt.AlignHCenter)
+# layout.setMargin(2)
+# w.setLayout(layout)
+#self.twList.setCellWidget(row, 2, w)

comictaggerlib/genericmetadata.py

@@ -0,0 +1 @@
+from comicapi.genericmetadata import *

comictaggerlib/imagefetcher.py

@@ -0,0 +1,194 @@
+"""A class to manage fetching and caching of images by URL"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sqlite3 as lite
+import os
+import datetime
+import shutil
+import tempfile
+import urllib.request, urllib.parse, urllib.error
+import ssl
+#import urllib2
+
+try:
+    from PyQt5.QtNetwork import QNetworkAccessManager, QNetworkRequest
+    from PyQt5.QtCore import QUrl, pyqtSignal, QObject, QByteArray
+    from PyQt5 import QtGui
+except ImportError:
+    # No Qt, so define a few dummy QObjects to help us compile
+    class QObject():
+
+        def __init__(self, *args):
+            pass
+
+    class QByteArray():
+        pass
+
+    class pyqtSignal():
+
+        def __init__(self, *args):
+            pass
+
+        def emit(a, b, c):
+            pass
+
+from .settings import ComicTaggerSettings
+
+
+class ImageFetcherException(Exception):
+    pass
+
+
+class ImageFetcher(QObject):
+
+    fetchComplete = pyqtSignal(QByteArray, int)
+
+    def __init__(self):
+        QObject.__init__(self)
+
+        self.settings_folder = ComicTaggerSettings.getSettingsFolder()
+        self.db_file = os.path.join(self.settings_folder, "image_url_cache.db")
+        self.cache_folder = os.path.join(self.settings_folder, "image_cache")
+
+        if not os.path.exists(self.db_file):
+            self.create_image_db()
+
+        # always use a tls context for urlopen
+        self.ssl = ssl.SSLContext(ssl.PROTOCOL_TLS)
+
+    def clearCache(self):
+        os.unlink(self.db_file)
+        if os.path.isdir(self.cache_folder):
+            shutil.rmtree(self.cache_folder)
+
+    def fetch(self, url, user_data=None, blocking=False):
+        """
+        If called with blocking=True, this will block until the image is
+        fetched.
+        If called with blocking=False, this will run the fetch in the
+        background, and emit a signal when done
+        """
+
+        self.user_data = user_data
+        self.fetched_url = url
+
+        # first look in the DB
+        image_data = self.get_image_from_cache(url)
+        if blocking:
+            if image_data is None:
+                try:
+                    image_data = urllib.request.urlopen(url, context=self.ssl).read()
+                except Exception as e:
+                    print(e)
+                    raise ImageFetcherException("Network Error!")
+
+            # save the image to the cache
+            self.add_image_to_cache(self.fetched_url, image_data)
+            return image_data
+
+        else:
+
+            # if we found it, just emit the signal asap
+            if image_data is not None:
+                self.fetchComplete.emit(QByteArray(image_data), self.user_data)
+                return
+
+            # didn't find it.  look online
+            self.nam = QNetworkAccessManager()
+            self.nam.finished.connect(self.finishRequest)
+            self.nam.get(QNetworkRequest(QUrl(url)))
+
+            # we'll get called back when done...
+
+    def finishRequest(self, reply):
+
+        # read in the image data
+        image_data = reply.readAll()
+
+        # save the image to the cache
+        self.add_image_to_cache(self.fetched_url, image_data)
+
+        self.fetchComplete.emit(QByteArray(image_data), self.user_data)
+
+    def create_image_db(self):
+
+        # this will wipe out any existing version
+        open(self.db_file, 'w').close()
+
+        # wipe any existing image cache folder too
+        if os.path.isdir(self.cache_folder):
+            shutil.rmtree(self.cache_folder)
+        os.makedirs(self.cache_folder)
+
+        con = lite.connect(self.db_file)
+
+        # create tables
+        with con:
+
+            cur = con.cursor()
+
+            cur.execute("CREATE TABLE Images(" +
+                        "url TEXT," +
+                        "filename TEXT," +
+                        "timestamp TEXT," +
+                        "PRIMARY KEY (url))"
+                        )
+
+    def add_image_to_cache(self, url, image_data):
+
+        con = lite.connect(self.db_file)
+
+        with con:
+
+            cur = con.cursor()
+
+            timestamp = datetime.datetime.now()
+
+            tmp_fd, filename = tempfile.mkstemp(
+                dir=self.cache_folder, prefix="img")
+            f = os.fdopen(tmp_fd, 'w+b')
+            f.write(image_data)
+            f.close()
+
+            cur.execute("INSERT or REPLACE INTO Images VALUES(?, ?, ?)",
+                        (url,
+                         filename,
+                         timestamp)
+                        )
+
+    def get_image_from_cache(self, url):
+
+        con = lite.connect(self.db_file)
+        with con:
+            cur = con.cursor()
+
+            cur.execute("SELECT filename FROM Images WHERE url=?", [url])
+            row = cur.fetchone()
+
+            if row is None:
+                return None
+            else:
+                filename = row[0]
+                image_data = None
+
+                try:
+                    with open(filename, 'rb') as f:
+                        image_data = f.read()
+                        f.close()
+                except IOError as e:
+                    pass
+
+                return image_data

comictaggerlib/imagehasher.py

@@ -0,0 +1,193 @@
+"""A class to manage creating image content hashes, and calculate hamming distances"""
+
+# Copyright 2013 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import io
+import sys
+from functools import reduce
+
+try:
+    from PIL import Image
+    from PIL import WebPImagePlugin
+    pil_available = True
+except ImportError:
+    pil_available = False
+
+
+class ImageHasher(object):
+
+    def __init__(self, path=None, data=None, width=8, height=8):
+        #self.hash_size = size
+        self.width = width
+        self.height = height
+
+        if path is None and data is None:
+            raise IOError
+        else:
+            try:
+                if path is not None:
+                    self.image = Image.open(path)
+                else:
+                    self.image = Image.open(io.BytesIO(data))
+            except Exception as e:
+                print("Image data seems corrupted! [{}]".format(e))
+                # just generate a bogus image
+                self.image = Image.new("L", (1, 1))
+
+    def average_hash(self):
+        try:
+            image = self.image.resize(
+                (self.width, self.height), Image.ANTIALIAS).convert("L")
+        except Exception as e:
+            sys.exc_clear()
+            print("average_hash error:", e)
+            return int(0)
+
+        pixels = list(image.getdata())
+        avg = sum(pixels) / len(pixels)
+
+        def compare_value_to_avg(i):
+            return (1 if i > avg else 0)
+
+        bitlist = list(map(compare_value_to_avg, pixels))
+
+        # build up an int value from the bit list, one bit at a time
+        def set_bit(x, idx_val):
+            (idx, val) = idx_val
+            return (x | (val << idx))
+
+        result = reduce(set_bit, enumerate(bitlist), 0)
+
+        # print("{0:016x}".format(result))
+        return result
+
+    def average_hash2(self):
+        pass
+        """
+        # Got this one from somewhere on the net.  Not a clue how the 'convolve2d'
+        # works!
+
+        from numpy import array
+        from scipy.signal import convolve2d
+
+        im = self.image.resize((self.width, self.height), Image.ANTIALIAS).convert('L')
+
+        in_data = array((im.getdata())).reshape(self.width, self.height)
+        filt = array([[0,1,0],[1,-4,1],[0,1,0]])
+        filt_data = convolve2d(in_data,filt,mode='same',boundary='symm').flatten()
+
+        result = reduce(lambda x, (y, z): x | (z << y),
+                         enumerate(map(lambda i: 0 if i < 0 else 1, filt_data)),
+                         0)
+        #print("{0:016x}".format(result))
+        return result
+        """
+
+    def dct_average_hash(self):
+        pass
+        """
+        # Algorithm source: http://syntaxcandy.blogspot.com/2012/08/perceptual-hash.html
+
+        1. Reduce size. Like Average Hash, pHash starts with a small image.
+        However, the image is larger than 8x8; 32x32 is a     good size. This
+        is really done to simplify the DCT computation and not because it
+        is needed to reduce the high frequencies.
+
+        2. Reduce color. The image is reduced to a grayscale just to further
+        simplify the number of computations.
+
+        3. Compute the DCT. The DCT separates the image into a collection of
+        frequencies and scalars. While JPEG uses     an 8x8 DCT, this algorithm
+        uses a 32x32 DCT.
+
+        4. Reduce the DCT. This is the magic step. While the DCT is 32x32,
+        just keep the top-left 8x8. Those represent the lowest frequencies in
+        the picture.
+
+        5. Compute the average value. Like the Average Hash, compute the mean DCT
+        value (using only the 8x8 DCT low-frequency values and excluding the first
+        term since the DC coefficient can be significantly different     from the other
+        values and will throw off the average). Thanks to David Starkweather for the
+        added information about pHash. He wrote: "the dct hash is based on the low 2D
+        DCT coefficients starting at the second from lowest, leaving out the first DC
+        term. This excludes completely flat image information (i.e. solid colors) from
+        being included in the hash description."
+
+        6. Further reduce the DCT. This is the magic step. Set the 64 hash bits to 0 or
+        1 depending on whether     each of the 64 DCT values is above or below the average
+        value. The result doesn't tell us the actual low frequencies; it just tells us
+        the very-rough relative scale of the frequencies to the mean. The result will not
+        vary as long as the overall structure of the image remains the same; this can
+        survive gamma and color histogram adjustments without a problem.
+
+        7. Construct the hash. Set the 64 bits into a 64-bit integer. The order does not
+        matter, just as long as you are consistent.
+        """
+        """
+        import numpy
+        import scipy.fftpack
+        numpy.set_printoptions(threshold=10000, linewidth=200, precision=2, suppress=True)
+
+        # Step 1,2
+        im = self.image.resize((32, 32), Image.ANTIALIAS).convert("L")
+        in_data = numpy.asarray(im)
+
+        # Step 3
+        dct = scipy.fftpack.dct(in_data.astype(float))
+
+        # Step 4
+        # Just skip the top and left rows when slicing, as suggested somewhere else...
+        lofreq_dct = dct[1:9, 1:9].flatten()
+
+        # Step 5
+        avg = (lofreq_dct.sum()) / (lofreq_dct.size)
+        median = numpy.median(lofreq_dct)
+
+        thresh = avg
+
+        # Step 6
+        def compare_value_to_thresh(i):
+            return (1 if i > thresh else 0)
+
+        bitlist = map(compare_value_to_thresh, lofreq_dct)
+
+        #Step 7
+        def set_bit(x, (idx, val)):
+            return (x | (val << idx))
+
+        result = reduce(set_bit, enumerate(bitlist), long(0))
+
+
+        #print("{0:016x}".format(result))
+        return result
+        """
+
+    # accepts 2 hashes (longs or hex strings) and returns the hamming distance
+
+    @staticmethod
+    def hamming_distance(h1, h2):
+        if isinstance(h1, int) or isinstance(h1, int):
+            n1 = h1
+            n2 = h2
+        else:
+            # convert hex strings to ints
+            n1 = int(h1, 16)
+            n2 = int(h2, 16)
+
+        # xor the two numbers
+        n = n1 ^ n2
+
+        # count up the 1's in the binary string
+        return sum(b == '1' for b in bin(n)[2:])

comictaggerlib/imagepopup.py

@@ -0,0 +1,93 @@
+"""A PyQT4 widget to display a popup image"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import sys
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+
+
+class ImagePopup(QtWidgets.QDialog):
+
+    def __init__(self, parent, image_pixmap):
+        super(ImagePopup, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('imagepopup.ui'), self)
+
+        QtWidgets.QApplication.setOverrideCursor(
+            QtGui.QCursor(QtCore.Qt.WaitCursor))
+
+        # self.setWindowModality(QtCore.Qt.WindowModal)
+        self.setWindowFlags(QtCore.Qt.Popup)
+        self.setWindowState(QtCore.Qt.WindowFullScreen)
+
+        self.imagePixmap = image_pixmap
+
+        screen_size = QtWidgets.QDesktopWidget().screenGeometry()
+        self.resize(screen_size.width(), screen_size.height())
+        self.move(0, 0)
+
+        # This is a total hack.  Uses a snapshot of the desktop, and overlays a
+        # translucent screen over it.  Probably can do it better by setting opacity of a
+        # widget
+        screen = QtWidgets.QApplication.primaryScreen()
+        self.desktopBg = screen.grabWindow(
+            QtWidgets.QApplication.desktop().winId(),
+            0,
+            0,
+            screen_size.width(),
+            screen_size.height())
+        bg = QtGui.QPixmap(ComicTaggerSettings.getGraphic('popup_bg.png'))
+        self.clientBgPixmap = bg.scaled(
+            screen_size.width(), screen_size.height())
+        self.setMask(self.clientBgPixmap.mask())
+
+        self.applyImagePixmap()
+        self.showFullScreen()
+        self.raise_()
+        QtWidgets.QApplication.restoreOverrideCursor()
+
+    def paintEvent(self, event):
+        self.painter = QtGui.QPainter(self)
+        self.painter.setRenderHint(QtGui.QPainter.Antialiasing)
+        self.painter.drawPixmap(0, 0, self.desktopBg)
+        self.painter.drawPixmap(0, 0, self.clientBgPixmap)
+        self.painter.end()
+
+    def applyImagePixmap(self):
+        win_h = self.height()
+        win_w = self.width()
+
+        if self.imagePixmap.width(
+        ) > win_w or self.imagePixmap.height() > win_h:
+            # scale the pixmap to fit in the frame
+            display_pixmap = self.imagePixmap.scaled(
+                win_w, win_h, QtCore.Qt.KeepAspectRatio)
+            self.lblImage.setPixmap(display_pixmap)
+        else:
+            display_pixmap = self.imagePixmap
+        self.lblImage.setPixmap(display_pixmap)
+
+        # move and resize the label to be centered in the fame
+        img_w = display_pixmap.width()
+        img_h = display_pixmap.height()
+        self.lblImage.resize(img_w, img_h)
+        self.lblImage.move((win_w - img_w) / 2, (win_h - img_h) / 2)
+
+    def mousePressEvent(self, event):
+        self.close()

comictaggerlib/issueidentifier.py

@@ -0,0 +1,722 @@
+"""A class to automatically identify a comic archive"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sys
+import io
+#import math
+#import urllib2
+#import urllib
+
+try:
+    from PIL import Image
+    from PIL import WebPImagePlugin
+    pil_available = True
+except ImportError:
+    pil_available = False
+
+from .genericmetadata import GenericMetadata
+from .comicvinetalker import ComicVineTalker, ComicVineTalkerException
+from .imagehasher import ImageHasher
+from .imagefetcher import ImageFetcher, ImageFetcherException
+from .issuestring import IssueString
+from . import utils
+#from settings import ComicTaggerSettings
+#from comicvinecacher import ComicVineCacher
+
+
+class IssueIdentifierNetworkError(Exception):
+    pass
+
+
+class IssueIdentifierCancelled(Exception):
+    pass
+
+
+class IssueIdentifier:
+
+    ResultNoMatches = 0
+    ResultFoundMatchButBadCoverScore = 1
+    ResultFoundMatchButNotFirstPage = 2
+    ResultMultipleMatchesWithBadImageScores = 3
+    ResultOneGoodMatch = 4
+    ResultMultipleGoodMatches = 5
+
+    def __init__(self, comic_archive, settings):
+        self.comic_archive = comic_archive
+        self.image_hasher = 1
+
+        self.onlyUseAdditionalMetaData = False
+
+        # a decent hamming score, good enough to call it a match
+        self.min_score_thresh = 16
+
+        # for alternate covers, be more stringent, since we're a bit more
+        # scattershot in comparisons
+        self.min_alternate_score_thresh = 12
+
+        # the min distance a hamming score must be to separate itself from
+        # closest neighbor
+        self.min_score_distance = 4
+
+        # a very strong hamming score, almost certainly the same image
+        self.strong_score_thresh = 8
+
+        # used to eliminate series names that are too long based on our search
+        # string
+        self.length_delta_thresh = settings.id_length_delta_thresh
+
+        # used to eliminate unlikely publishers
+        self.publisher_blacklist = [
+            s.strip().lower() for s in settings.id_publisher_blacklist.split(',')]
+
+        self.additional_metadata = GenericMetadata()
+        self.output_function = IssueIdentifier.defaultWriteOutput
+        self.callback = None
+        self.coverUrlCallback = None
+        self.search_result = self.ResultNoMatches
+        self.cover_page_index = 0
+        self.cancel = False
+        self.waitAndRetryOnRateLimit = False
+
+    def setScoreMinThreshold(self, thresh):
+        self.min_score_thresh = thresh
+
+    def setScoreMinDistance(self, distance):
+        self.min_score_distance = distance
+
+    def setAdditionalMetadata(self, md):
+        self.additional_metadata = md
+
+    def setNameLengthDeltaThreshold(self, delta):
+        self.length_delta_thresh = delta
+
+    def setPublisherBlackList(self, blacklist):
+        self.publisher_blacklist = blacklist
+
+    def setHasherAlgorithm(self, algo):
+        self.image_hasher = algo
+        pass
+
+    def setOutputFunction(self, func):
+        self.output_function = func
+        pass
+
+    def calculateHash(self, image_data):
+        if self.image_hasher == '3':
+            return ImageHasher(data=image_data).dct_average_hash()
+        elif self.image_hasher == '2':
+            return ImageHasher(data=image_data).average_hash2()
+        else:
+            return ImageHasher(data=image_data).average_hash()
+
+    def getAspectRatio(self, image_data):
+        try:
+            im = Image.open(io.StringIO(image_data))
+            w, h = im.size
+            return float(h) / float(w)
+        except:
+            return 1.5
+
+    def cropCover(self, image_data):
+
+        im = Image.open(io.StringIO(image_data))
+        w, h = im.size
+
+        try:
+            cropped_im = im.crop((int(w / 2), 0, w, h))
+        except Exception as e:
+            sys.exc_clear()
+            print("cropCover() error:", e)
+            return None
+
+        output = io.StringIO()
+        cropped_im.save(output, format="PNG")
+        cropped_image_data = output.getvalue()
+        output.close()
+
+        return cropped_image_data
+
+    def setProgressCallback(self, cb_func):
+        self.callback = cb_func
+
+    def setCoverURLCallback(self, cb_func):
+        self.coverUrlCallback = cb_func
+
+    def getSearchKeys(self):
+
+        ca = self.comic_archive
+        search_keys = dict()
+        search_keys['series'] = None
+        search_keys['issue_number'] = None
+        search_keys['month'] = None
+        search_keys['year'] = None
+        search_keys['issue_count'] = None
+
+        if ca is None:
+            return
+
+        if self.onlyUseAdditionalMetaData:
+            search_keys['series'] = self.additional_metadata.series
+            search_keys['issue_number'] = self.additional_metadata.issue
+            search_keys['year'] = self.additional_metadata.year
+            search_keys['month'] = self.additional_metadata.month
+            search_keys['issue_count'] = self.additional_metadata.issueCount
+            return search_keys
+
+        # see if the archive has any useful meta data for searching with
+        if ca.hasCIX():
+            internal_metadata = ca.readCIX()
+        elif ca.hasCBI():
+            internal_metadata = ca.readCBI()
+        else:
+            internal_metadata = ca.readCBI()
+
+        # try to get some metadata from filename
+        md_from_filename = ca.metadataFromFilename()
+
+        # preference order:
+        # 1. Additional metadata
+        # 1. Internal metadata
+        # 1. Filename metadata
+
+        if self.additional_metadata.series is not None:
+            search_keys['series'] = self.additional_metadata.series
+        elif internal_metadata.series is not None:
+            search_keys['series'] = internal_metadata.series
+        else:
+            search_keys['series'] = md_from_filename.series
+
+        if self.additional_metadata.issue is not None:
+            search_keys['issue_number'] = self.additional_metadata.issue
+        elif internal_metadata.issue is not None:
+            search_keys['issue_number'] = internal_metadata.issue
+        else:
+            search_keys['issue_number'] = md_from_filename.issue
+
+        if self.additional_metadata.year is not None:
+            search_keys['year'] = self.additional_metadata.year
+        elif internal_metadata.year is not None:
+            search_keys['year'] = internal_metadata.year
+        else:
+            search_keys['year'] = md_from_filename.year
+
+        if self.additional_metadata.month is not None:
+            search_keys['month'] = self.additional_metadata.month
+        elif internal_metadata.month is not None:
+            search_keys['month'] = internal_metadata.month
+        else:
+            search_keys['month'] = md_from_filename.month
+
+        if self.additional_metadata.issueCount is not None:
+            search_keys['issue_count'] = self.additional_metadata.issueCount
+        elif internal_metadata.issueCount is not None:
+            search_keys['issue_count'] = internal_metadata.issueCount
+        else:
+            search_keys['issue_count'] = md_from_filename.issueCount
+
+        return search_keys
+
+    @staticmethod
+    def defaultWriteOutput(text):
+        sys.stdout.write(text)
+        sys.stdout.flush()
+
+    def log_msg(self, msg, newline=True):
+        self.output_function(msg)
+        if newline:
+            self.output_function("\n")
+
+    def getIssueCoverMatchScore(
+            self,
+            comicVine,
+            issue_id,
+            primary_img_url,
+            primary_thumb_url,
+            page_url,
+            localCoverHashList,
+            useRemoteAlternates=False,
+            useLog=True):
+        # localHashes is a list of pre-calculated hashs.
+        # useRemoteAlternates - indicates to use alternate covers from CV
+
+        try:
+            url_image_data = ImageFetcher().fetch(
+                primary_thumb_url, blocking=True)
+        except ImageFetcherException:
+            self.log_msg(
+                "Network issue while fetching cover image from Comic Vine. Aborting...")
+            raise IssueIdentifierNetworkError
+
+        if self.cancel:
+            raise IssueIdentifierCancelled
+
+        # alert the GUI, if needed
+        if self.coverUrlCallback is not None:
+            self.coverUrlCallback(url_image_data)
+
+        remote_cover_list = []
+        item = dict()
+        item['url'] = primary_img_url
+
+        item['hash'] = self.calculateHash(url_image_data)
+        remote_cover_list.append(item)
+
+        if self.cancel:
+            raise IssueIdentifierCancelled
+
+        if useRemoteAlternates:
+            alt_img_url_list = comicVine.fetchAlternateCoverURLs(
+                issue_id, page_url)
+            for alt_url in alt_img_url_list:
+                try:
+                    alt_url_image_data = ImageFetcher().fetch(
+                        alt_url, blocking=True)
+                except ImageFetcherException:
+                    self.log_msg(
+                        "Network issue while fetching alt. cover image from Comic Vine. Aborting...")
+                    raise IssueIdentifierNetworkError
+
+                if self.cancel:
+                    raise IssueIdentifierCancelled
+
+                # alert the GUI, if needed
+                if self.coverUrlCallback is not None:
+                    self.coverUrlCallback(alt_url_image_data)
+
+                item = dict()
+                item['url'] = alt_url
+                item['hash'] = self.calculateHash(alt_url_image_data)
+                remote_cover_list.append(item)
+
+                if self.cancel:
+                    raise IssueIdentifierCancelled
+
+        if useLog and useRemoteAlternates:
+            self.log_msg(
+                "[{0} alt. covers]".format(len(remote_cover_list) - 1), False)
+        if useLog:
+            self.log_msg("[ ", False)
+
+        score_list = []
+        done = False
+        for local_cover_hash in localCoverHashList:
+            for remote_cover_item in remote_cover_list:
+                score = ImageHasher.hamming_distance(
+                    local_cover_hash, remote_cover_item['hash'])
+                score_item = dict()
+                score_item['score'] = score
+                score_item['url'] = remote_cover_item['url']
+                score_item['hash'] = remote_cover_item['hash']
+                score_list.append(score_item)
+                if useLog:
+                    self.log_msg("{0}".format(score), False)
+
+                if score <= self.strong_score_thresh:
+                    # such a good score, we can quit now, since for sure we
+                    # have a winner
+                    done = True
+                    break
+            if done:
+                break
+
+        if useLog:
+            self.log_msg(" ]", False)
+
+        best_score_item = min(score_list, key=lambda x: x['score'])
+
+        return best_score_item
+
+    # def validate(self, issue_id):
+        # create hash list
+    #    score = self.getIssueMatchScore(issue_id, hash_list, useRemoteAlternates = True)
+    #    if score < 20:
+    #        return True
+    #    else:
+    #        return False
+
+    def search(self):
+
+        ca = self.comic_archive
+        self.match_list = []
+        self.cancel = False
+        self.search_result = self.ResultNoMatches
+
+        if not pil_available:
+            self.log_msg(
+                "Python Imaging Library (PIL) is not available and is needed for issue identification.")
+            return self.match_list
+
+        if not ca.seemsToBeAComicArchive():
+            self.log_msg(
+                "Sorry, but " + opts.filename + " is not a comic archive!")
+            return self.match_list
+
+        cover_image_data = ca.getPage(self.cover_page_index)
+        cover_hash = self.calculateHash(cover_image_data)
+
+        # check the aspect ratio
+        # if it's wider than it is high, it's probably a two page spread
+        # if so, crop it and calculate a second hash
+        narrow_cover_hash = None
+        aspect_ratio = self.getAspectRatio(cover_image_data)
+        if aspect_ratio < 1.0:
+            right_side_image_data = self.cropCover(cover_image_data)
+            if right_side_image_data is not None:
+                narrow_cover_hash = self.calculateHash(right_side_image_data)
+
+        #self.log_msg("Cover hash = {0:016x}".format(cover_hash))
+
+        keys = self.getSearchKeys()
+        # normalize the issue number
+        keys['issue_number'] = IssueString(keys['issue_number']).asString()
+
+        # we need, at minimum, a series and issue number
+        if keys['series'] is None or keys['issue_number'] is None:
+            self.log_msg("Not enough info for a search!")
+            return []
+
+        self.log_msg("Going to search for:")
+        self.log_msg("\tSeries: " + keys['series'])
+        self.log_msg("\tIssue:  " + keys['issue_number'])
+        if keys['issue_count'] is not None:
+            self.log_msg("\tCount:  " + str(keys['issue_count']))
+        if keys['year'] is not None:
+            self.log_msg("\tYear:   " + str(keys['year']))
+        if keys['month'] is not None:
+            self.log_msg("\tMonth:  " + str(keys['month']))
+
+        #self.log_msg("Publisher Blacklist: " + str(self.publisher_blacklist))
+        comicVine = ComicVineTalker()
+        comicVine.wait_for_rate_limit = self.waitAndRetryOnRateLimit
+
+        comicVine.setLogFunc(self.output_function)
+
+        # self.log_msg(("Searching for " + keys['series'] + "...")
+        self.log_msg("Searching for  {0} #{1} ...".format(
+            keys['series'], keys['issue_number']))
+        try:
+            cv_search_results = comicVine.searchForSeries(keys['series'])
+        except ComicVineTalkerException:
+            self.log_msg(
+                "Network issue while searching for series. Aborting...")
+            return []
+
+        #self.log_msg("Found " + str(len(cv_search_results)) + " initial results")
+        if self.cancel:
+            return []
+
+        if cv_search_results is None:
+            return []
+
+        series_second_round_list = []
+
+        #self.log_msg("Removing results with too long names, banned publishers, or future start dates")
+        for item in cv_search_results:
+            length_approved = False
+            publisher_approved = True
+            date_approved = True
+
+            # remove any series that starts after the issue year
+            if keys['year'] is not None and str(
+                    keys['year']).isdigit() and item['start_year'] is not None and str(
+                    item['start_year']).isdigit():
+                if int(keys['year']) < int(item['start_year']):
+                    date_approved = False
+
+            # assume that our search name is close to the actual name, say
+            # within ,e.g. 5 chars
+            shortened_key = utils.removearticles(keys['series'])
+            shortened_item_name = utils.removearticles(item['name'])
+            if len(shortened_item_name) < (
+                    len(shortened_key) + self.length_delta_thresh):
+                length_approved = True
+
+            # remove any series from publishers on the blacklist
+            if item['publisher'] is not None:
+                publisher = item['publisher']['name']
+                if publisher is not None and publisher.lower(
+                ) in self.publisher_blacklist:
+                    publisher_approved = False
+
+            if length_approved and publisher_approved and date_approved:
+                series_second_round_list.append(item)
+
+        self.log_msg(
+            "Searching in " + str(len(series_second_round_list)) + " series")
+
+        if self.callback is not None:
+            self.callback(0, len(series_second_round_list))
+
+        # now sort the list by name length
+        series_second_round_list.sort(
+            key=lambda x: len(x['name']), reverse=False)
+
+        # build a list of volume IDs
+        volume_id_list = list()
+        for series in series_second_round_list:
+            volume_id_list.append(series['id'])
+
+        try:
+            issue_list = comicVine.fetchIssuesByVolumeIssueNumAndYear(
+                volume_id_list,
+                keys['issue_number'],
+                keys['year'])
+
+        except ComicVineTalkerException:
+            self.log_msg(
+                "Network issue while searching for series details. Aborting...")
+            return []
+
+        if issue_list is None:
+            return []
+
+        shortlist = list()
+        # now re-associate the issues and volumes
+        for issue in issue_list:
+            for series in series_second_round_list:
+                if series['id'] == issue['volume']['id']:
+                    shortlist.append((series, issue))
+                    break
+
+        if keys['year'] is None:
+            self.log_msg("Found {0} series that have an issue #{1}".format(
+                len(shortlist), keys['issue_number']))
+        else:
+            self.log_msg(
+                "Found {0} series that have an issue #{1} from {2}".format(
+                    len(shortlist),
+                    keys['issue_number'],
+                    keys['year']))
+
+        # now we have a shortlist of volumes with the desired issue number
+        # Do first round of cover matching
+        counter = len(shortlist)
+        for series, issue in shortlist:
+            if self.callback is not None:
+                self.callback(counter, len(shortlist) * 3)
+                counter += 1
+
+            self.log_msg("Examining covers for  ID: {0} {1} ({2}) ...".format(
+                series['id'],
+                series['name'],
+                series['start_year']), newline=False)
+
+            # parse out the cover date
+            day, month, year = comicVine.parseDateStr(issue['cover_date'])
+
+            # Now check the cover match against the primary image
+            hash_list = [cover_hash]
+            if narrow_cover_hash is not None:
+                hash_list.append(narrow_cover_hash)
+
+            try:
+                image_url = issue['image']['super_url']
+                thumb_url = issue['image']['thumb_url']
+                page_url = issue['site_detail_url']
+
+                score_item = self.getIssueCoverMatchScore(
+                    comicVine,
+                    issue['id'],
+                    image_url,
+                    thumb_url,
+                    page_url,
+                    hash_list,
+                    useRemoteAlternates=False)
+            except:
+                self.match_list = []
+                return self.match_list
+
+            match = dict()
+            match['series'] = "{0} ({1})".format(
+                series['name'], series['start_year'])
+            match['distance'] = score_item['score']
+            match['issue_number'] = keys['issue_number']
+            match['cv_issue_count'] = series['count_of_issues']
+            match['url_image_hash'] = score_item['hash']
+            match['issue_title'] = issue['name']
+            match['issue_id'] = issue['id']
+            match['volume_id'] = series['id']
+            match['month'] = month
+            match['year'] = year
+            match['publisher'] = None
+            if series['publisher'] is not None:
+                match['publisher'] = series['publisher']['name']
+            match['image_url'] = image_url
+            match['thumb_url'] = thumb_url
+            match['page_url'] = page_url
+            match['description'] = issue['description']
+
+            self.match_list.append(match)
+
+            self.log_msg(" --> {0}".format(match['distance']), newline=False)
+
+            self.log_msg("")
+
+        if len(self.match_list) == 0:
+            self.log_msg(":-(no matches!")
+            self.search_result = self.ResultNoMatches
+            return self.match_list
+
+        # sort list by image match scores
+        self.match_list.sort(key=lambda k: k['distance'])
+
+        l = []
+        for i in self.match_list:
+            l.append(i['distance'])
+
+        self.log_msg("Compared to covers in {0} issue(s):".format(
+            len(self.match_list)), newline=False)
+        self.log_msg(str(l))
+
+        def print_match(item):
+            self.log_msg("-----> {0} #{1} {2} ({3}/{4}) -- score: {5}".format(
+                item['series'],
+                item['issue_number'],
+                item['issue_title'],
+                item['month'],
+                item['year'],
+                item['distance']))
+
+        best_score = self.match_list[0]['distance']
+
+        if best_score >= self.min_score_thresh:
+            # we have 1 or more low-confidence matches (all bad cover scores)
+            # look at a few more pages in the archive, and also alternate
+            # covers online
+            self.log_msg(
+                "Very weak scores for the cover. Analyzing alternate pages and covers...")
+            hash_list = [cover_hash]
+            if narrow_cover_hash is not None:
+                hash_list.append(narrow_cover_hash)
+            for i in range(1, min(3, ca.getNumberOfPages())):
+                image_data = ca.getPage(i)
+                page_hash = self.calculateHash(image_data)
+                hash_list.append(page_hash)
+
+            second_match_list = []
+            counter = 2 * len(self.match_list)
+            for m in self.match_list:
+                if self.callback is not None:
+                    self.callback(counter, len(self.match_list) * 3)
+                    counter += 1
+                self.log_msg(
+                    "Examining alternate covers for ID: {0} {1} ...".format(
+                        m['volume_id'],
+                        m['series']),
+                    newline=False)
+                try:
+                    score_item = self.getIssueCoverMatchScore(
+                        comicVine,
+                        m['issue_id'],
+                        m['image_url'],
+                        m['thumb_url'],
+                        m['page_url'],
+                        hash_list,
+                        useRemoteAlternates=True)
+                except:
+                    self.match_list = []
+                    return self.match_list
+                self.log_msg("--->{0}".format(score_item['score']))
+                self.log_msg("")
+
+                if score_item['score'] < self.min_alternate_score_thresh:
+                    second_match_list.append(m)
+                    m['distance'] = score_item['score']
+
+            if len(second_match_list) == 0:
+                if len(self.match_list) == 1:
+                    self.log_msg("No matching pages in the issue.")
+                    self.log_msg(
+                        "--------------------------------------------------------------------------")
+                    print_match(self.match_list[0])
+                    self.log_msg(
+                        "--------------------------------------------------------------------------")
+                    self.search_result = self.ResultFoundMatchButBadCoverScore
+                else:
+                    self.log_msg(
+                        "--------------------------------------------------------------------------")
+                    self.log_msg(
+                        "Multiple bad cover matches!  Need to use other info...")
+                    self.log_msg(
+                        "--------------------------------------------------------------------------")
+                    self.search_result = self.ResultMultipleMatchesWithBadImageScores
+                return self.match_list
+            else:
+                # We did good, found something!
+                self.log_msg("Success in secondary/alternate cover matching!")
+
+                self.match_list = second_match_list
+                # sort new list by image match scores
+                self.match_list.sort(key=lambda k: k['distance'])
+                best_score = self.match_list[0]['distance']
+                self.log_msg(
+                    "[Second round cover matching: best score = {0}]".format(best_score))
+                # now drop down into the rest of the processing
+
+        if self.callback is not None:
+            self.callback(99, 100)
+
+        # now pare down list, remove any item more than specified distant from
+        # the top scores
+        for item in reversed(self.match_list):
+            if item['distance'] > best_score + self.min_score_distance:
+                self.match_list.remove(item)
+
+        # One more test for the case choosing limited series first issue vs a trade with the same cover:
+        # if we have a given issue count > 1 and the volume from CV has
+        # count==1, remove it from match list
+        if len(self.match_list) >= 2 and keys[
+                'issue_count'] is not None and keys['issue_count'] != 1:
+            new_list = list()
+            for match in self.match_list:
+                if match['cv_issue_count'] != 1:
+                    new_list.append(match)
+                else:
+                    self.log_msg(
+                        "Removing volume {0} [{1}] from consideration (only 1 issue)".format(
+                            match['series'],
+                            match['volume_id']))
+
+            if len(new_list) > 0:
+                self.match_list = new_list
+
+        if len(self.match_list) == 1:
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+            print_match(self.match_list[0])
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+            self.search_result = self.ResultOneGoodMatch
+
+        elif len(self.match_list) == 0:
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+            self.log_msg("No matches found :(")
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+            self.search_result = self.ResultNoMatches
+        else:
+            # we've got multiple good matches:
+            self.log_msg("More than one likely candidate.")
+            self.search_result = self.ResultMultipleGoodMatches
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+            for item in self.match_list:
+                print_match(item)
+            self.log_msg(
+                "--------------------------------------------------------------------------")
+
+        return self.match_list

comictaggerlib/issueselectionwindow.py

@@ -0,0 +1,188 @@
+"""A PyQT4 dialog to select specific issue from list"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import sys
+#import os
+#import re
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+#from PyQt5.QtCore import QUrl, pyqtSignal, QByteArray
+#from PyQt5.QtNetwork import QNetworkAccessManager, QNetworkRequest
+
+from .comicvinetalker import ComicVineTalker, ComicVineTalkerException
+from .settings import ComicTaggerSettings
+from .issuestring import IssueString
+from .coverimagewidget import CoverImageWidget
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize
+#from imagefetcher import ImageFetcher
+#import utils
+
+
+class IssueNumberTableWidgetItem(QtWidgets.QTableWidgetItem):
+
+    def __lt__(self, other):
+        selfStr = self.data(QtCore.Qt.DisplayRole)
+        otherStr = other.data(QtCore.Qt.DisplayRole)
+        return (IssueString(selfStr).asFloat() <
+                IssueString(otherStr).asFloat())
+
+
+class IssueSelectionWindow(QtWidgets.QDialog):
+
+    volume_id = 0
+
+    def __init__(self, parent, settings, series_id, issue_number):
+        super(IssueSelectionWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('issueselectionwindow.ui'), self)
+
+        self.coverWidget = CoverImageWidget(
+            self.coverImageContainer, CoverImageWidget.AltCoverMode)
+        gridlayout = QtWidgets.QGridLayout(self.coverImageContainer)
+        gridlayout.addWidget(self.coverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        reduceWidgetFontSize(self.twList)
+        reduceWidgetFontSize(self.teDescription, 1)
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        self.series_id = series_id
+        self.settings = settings
+        self.url_fetch_thread = None
+
+        if issue_number is None or issue_number == "":
+            self.issue_number = 1
+        else:
+            self.issue_number = issue_number
+
+        self.initial_id = None
+        self.performQuery()
+
+        self.twList.resizeColumnsToContents()
+        self.twList.currentItemChanged.connect(self.currentItemChanged)
+        self.twList.cellDoubleClicked.connect(self.cellDoubleClicked)
+
+        # now that the list has been sorted, find the initial record, and
+        # select it
+        if self.initial_id is None:
+            self.twList.selectRow(0)
+        else:
+            for r in range(0, self.twList.rowCount()):
+                issue_id = self.twList.item(r, 0).data(QtCore.Qt.UserRole)
+                if (issue_id == self.initial_id):
+                    self.twList.selectRow(r)
+                    break
+
+    def performQuery(self):
+
+        QtWidgets.QApplication.setOverrideCursor(
+            QtGui.QCursor(QtCore.Qt.WaitCursor))
+
+        try:
+            comicVine = ComicVineTalker()
+            volume_data = comicVine.fetchVolumeData(self.series_id)
+            self.issue_list = comicVine.fetchIssuesByVolume(self.series_id)
+        except ComicVineTalkerException as e:
+            QtWidgets.QApplication.restoreOverrideCursor()
+            if e.code == ComicVineTalkerException.RateLimit:
+                QtWidgets.QMessageBox.critical(
+                    self,
+                    self.tr("Comic Vine Error"),
+                    ComicVineTalker.getRateLimitMessage())
+            else:
+                QtWidgets.QMessageBox.critical(
+                    self,
+                    self.tr("Network Issue"),
+                    self.tr("Could not connect to Comic Vine to list issues!"))
+            return
+
+        while self.twList.rowCount() > 0:
+            self.twList.removeRow(0)
+
+        self.twList.setSortingEnabled(False)
+
+        row = 0
+        for record in self.issue_list:
+            self.twList.insertRow(row)
+
+            item_text = record['issue_number']
+            item = IssueNumberTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setData(QtCore.Qt.UserRole, record['id'])
+            item.setData(QtCore.Qt.DisplayRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 0, item)
+
+            item_text = record['cover_date']
+            if item_text is None:
+                item_text = ""
+            # remove the day of "YYYY-MM-DD"
+            parts = item_text.split("-")
+            if len(parts) > 1:
+                item_text = parts[0] + "-" + parts[1]
+
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 1, item)
+
+            item_text = record['name']
+            if item_text is None:
+                item_text = ""
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 2, item)
+
+            if IssueString(
+                    record['issue_number']).asString().lower() == IssueString(
+                    self.issue_number).asString().lower():
+                self.initial_id = record['id']
+
+            row += 1
+
+        self.twList.setSortingEnabled(True)
+        self.twList.sortItems(0, QtCore.Qt.AscendingOrder)
+
+        QtWidgets.QApplication.restoreOverrideCursor()
+
+    def cellDoubleClicked(self, r, c):
+        self.accept()
+
+    def currentItemChanged(self, curr, prev):
+
+        if curr is None:
+            return
+        if prev is not None and prev.row() == curr.row():
+            return
+
+        self.issue_id = self.twList.item(curr.row(), 0).data(QtCore.Qt.UserRole)
+
+        # list selection was changed, update the the issue cover
+        for record in self.issue_list:
+            if record['id'] == self.issue_id:
+                self.issue_number = record['issue_number']
+                self.coverWidget.setIssueID(int(self.issue_id))
+                if record['description'] is None:
+                    self.teDescription.setText("")
+                else:
+                    self.teDescription.setText(record['description'])
+
+                break

comictaggerlib/issuestring.py

@@ -0,0 +1 @@
+from comicapi.issuestring import *

comictaggerlib/logwindow.py

@@ -0,0 +1,41 @@
+"""A PyQT4 dialog to a text file or log"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import sys
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+
+
+class LogWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent):
+        super(LogWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('logwindow.ui'), self)
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+    def setText(self, text):
+        try:
+            text = text.decode()
+        except:
+            pass
+        self.textEdit.setPlainText(text)

comictaggerlib/main.py

@@ -0,0 +1,106 @@
+"""A python app to (automatically) tag comic archives"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+import sys
+import signal
+import traceback
+import platform
+
+from .settings import ComicTaggerSettings
+# Need to load setting before anything else
+SETTINGS = ComicTaggerSettings()
+
+try:
+    qt_available = True
+    from PyQt5 import QtCore, QtGui, QtWidgets
+    from .taggerwindow import TaggerWindow
+except ImportError as e:
+    qt_available = False
+
+
+from . import utils
+from . import cli
+from .options import Options
+from .comicvinetalker import ComicVineTalker
+
+def ctmain():
+    opts = Options()
+    opts.parseCmdLineArgs()
+
+    # manage the CV API key
+    if opts.cv_api_key:
+        if opts.cv_api_key != SETTINGS.cv_api_key:
+            SETTINGS.cv_api_key = opts.cv_api_key
+            SETTINGS.save()
+    if opts.only_set_key:
+        print("Key set")
+        return
+
+    ComicVineTalker.api_key = SETTINGS.cv_api_key
+
+    signal.signal(signal.SIGINT, signal.SIG_DFL)
+
+    if not qt_available and not opts.no_gui:
+        opts.no_gui = True
+        print("PyQt5 is not available.  ComicTagger is limited to command-line mode.", file=sys.stderr)
+
+    if opts.no_gui:
+        cli.cli_mode(opts, SETTINGS)
+    else:
+        os.environ['QT_AUTO_SCREEN_SCALE_FACTOR'] = '1'            
+        app = QtWidgets.QApplication(sys.argv)
+        if platform.system() == "Darwin":
+            # Set the MacOS dock icon
+            app.setWindowIcon(
+            QtGui.QIcon(ComicTaggerSettings.getGraphic('app.png')))
+
+        if platform.system() == "Windows":
+            # For pure python, tell windows that we're not python,
+            # so we can have our own taskbar icon
+            import ctypes
+            myappid = u'comictagger' # arbitrary string
+            ctypes.windll.shell32.SetCurrentProcessExplicitAppUserModelID(myappid)
+            # force close of console window
+            SWP_HIDEWINDOW = 0x0080
+            consoleWnd = ctypes.windll.kernel32.GetConsoleWindow()
+            if consoleWnd != 0:          
+                ctypes.windll.user32.SetWindowPos(consoleWnd, None, 0, 0, 0, 0, SWP_HIDEWINDOW)
+
+        if platform.system() != "Linux":
+            img = QtGui.QPixmap(ComicTaggerSettings.getGraphic('tags.png'))
+
+            splash = QtWidgets.QSplashScreen(img)
+            splash.show()
+            splash.raise_()
+            app.processEvents()
+
+        try:
+            tagger_window = TaggerWindow(opts.file_list, SETTINGS, opts=opts)
+            tagger_window.setWindowIcon(
+                QtGui.QIcon(ComicTaggerSettings.getGraphic('app.png')))
+            tagger_window.show()
+
+            if platform.system() != "Linux":
+                splash.finish(tagger_window)
+
+            sys.exit(app.exec_())
+        except Exception as e:
+            QtWidgets.QMessageBox.critical(
+                QtWidgets.QMainWindow(),
+                "Error",
+                "Unhandled exception in app:\n" +
+                traceback.format_exc())

comictaggerlib/matchselectionwindow.py

@@ -0,0 +1,160 @@
+"""A PyQT4 dialog to select from automated issue matches"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+#import sys
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+#from PyQt5.QtCore import QUrl, pyqtSignal, QByteArray
+
+from .settings import ComicTaggerSettings
+from .coverimagewidget import CoverImageWidget
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize
+#from imagefetcher import ImageFetcher
+#from comicarchive import MetaDataStyle
+#from comicvinetalker import ComicVineTalker
+#import utils
+
+
+class MatchSelectionWindow(QtWidgets.QDialog):
+
+    volume_id = 0
+
+    def __init__(self, parent, matches, comic_archive):
+        super(MatchSelectionWindow, self).__init__(parent)
+
+        uic.loadUi(
+            ComicTaggerSettings.getUIFile('matchselectionwindow.ui'), self)
+
+        self.altCoverWidget = CoverImageWidget(
+            self.altCoverContainer, CoverImageWidget.AltCoverMode)
+        gridlayout = QtWidgets.QGridLayout(self.altCoverContainer)
+        gridlayout.addWidget(self.altCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.archiveCoverWidget = CoverImageWidget(
+            self.archiveCoverContainer, CoverImageWidget.ArchiveMode)
+        gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
+        gridlayout.addWidget(self.archiveCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        reduceWidgetFontSize(self.twList)
+        reduceWidgetFontSize(self.teDescription, 1)
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        self.matches = matches
+        self.comic_archive = comic_archive
+
+        self.twList.currentItemChanged.connect(self.currentItemChanged)
+        self.twList.cellDoubleClicked.connect(self.cellDoubleClicked)
+
+        self.updateData()
+
+    def updateData(self):
+
+        self.setCoverImage()
+        self.populateTable()
+        self.twList.resizeColumnsToContents()
+        self.twList.selectRow(0)
+
+        path = self.comic_archive.path
+        self.setWindowTitle("Select correct match: {0}".format(
+            os.path.split(path)[1]))
+
+    def populateTable(self):
+
+        while self.twList.rowCount() > 0:
+            self.twList.removeRow(0)
+
+        self.twList.setSortingEnabled(False)
+
+        row = 0
+        for match in self.matches:
+            self.twList.insertRow(row)
+
+            item_text = match['series']
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setData(QtCore.Qt.UserRole, (match,))
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 0, item)
+
+            if match['publisher'] is not None:
+                item_text = "{0}".format(match['publisher'])
+            else:
+                item_text = "Unknown"
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 1, item)
+
+            month_str = ""
+            year_str = "????"
+            if match['month'] is not None:
+                month_str = "-{0:02d}".format(int(match['month']))
+            if match['year'] is not None:
+                year_str = "{0}".format(match['year'])
+
+            item_text = year_str + month_str
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 2, item)
+
+            item_text = match['issue_title']
+            if item_text is None:
+                item_text = ""
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 3, item)
+
+            row += 1
+
+        self.twList.resizeColumnsToContents()
+        self.twList.setSortingEnabled(True)
+        self.twList.sortItems(2, QtCore.Qt.AscendingOrder)
+        self.twList.selectRow(0)
+        self.twList.resizeColumnsToContents()
+        self.twList.horizontalHeader().setStretchLastSection(True)
+
+    def cellDoubleClicked(self, r, c):
+        self.accept()
+
+    def currentItemChanged(self, curr, prev):
+
+        if curr is None:
+            return
+        if prev is not None and prev.row() == curr.row():
+            return
+
+        self.altCoverWidget.setIssueID(self.currentMatch()['issue_id'])
+        if self.currentMatch()['description'] is None:
+            self.teDescription.setText("")
+        else:
+            self.teDescription.setText(self.currentMatch()['description'])
+
+    def setCoverImage(self):
+        self.archiveCoverWidget.setArchive(self.comic_archive)
+
+    def currentMatch(self):
+        row = self.twList.currentRow()
+        match = self.twList.item(row, 0).data(
+            QtCore.Qt.UserRole)[0]
+        return match

comictaggerlib/optionalmsgdialog.py

@@ -0,0 +1,118 @@
+"""A PyQt5 dialog to show a message and let the user check a box
+
+Example usage:
+
+checked = OptionalMessageDialog.msg(self, "Disclaimer",
+                            "This is beta software, and you are using it at your own risk!",
+                         )
+
+said_yes, checked = OptionalMessageDialog.question(self, "Question",
+                            "Are you sure you wish to do this?",
+                         )
+"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from PyQt5.QtCore import *
+from PyQt5.QtGui import *
+from PyQt5.QtWidgets import *
+
+
+StyleMessage = 0
+StyleQuestion = 1
+
+
+class OptionalMessageDialog(QDialog):
+
+    def __init__(self, parent, style, title, msg,
+                 check_state=Qt.Unchecked, check_text=None):
+        QDialog.__init__(self, parent)
+
+        self.setWindowTitle(title)
+        self.was_accepted = False
+
+        l = QVBoxLayout(self)
+
+        self.theLabel = QLabel(msg)
+        self.theLabel.setWordWrap(True)
+        self.theLabel.setTextFormat(Qt.RichText)
+        self.theLabel.setOpenExternalLinks(True)
+        self.theLabel.setTextInteractionFlags(
+            Qt.TextSelectableByMouse | Qt.LinksAccessibleByMouse | Qt.LinksAccessibleByKeyboard)
+
+        l.addWidget(self.theLabel)
+        l.insertSpacing(-1, 10)
+
+        if check_text is None:
+            if style == StyleQuestion:
+                check_text = "Remember this answer"
+            else:
+                check_text = "Don't show this message again"
+
+        self.theCheckBox = QCheckBox(check_text)
+
+        self.theCheckBox.setCheckState(check_state)
+
+        l.addWidget(self.theCheckBox)
+
+        btnbox_style = QDialogButtonBox.Ok
+        if style == StyleQuestion:
+            btnbox_style = QDialogButtonBox.Yes | QDialogButtonBox.No
+
+        self.theButtonBox = QDialogButtonBox(
+            btnbox_style,
+            parent=self,
+            accepted=self.accept,
+            rejected=self.reject)
+
+        l.addWidget(self.theButtonBox)
+
+    def accept(self):
+        self.was_accepted = True
+        QDialog.accept(self)
+
+    def reject(self):
+        self.was_accepted = False
+        QDialog.reject(self)
+
+    @staticmethod
+    def msg(parent, title, msg, check_state=Qt.Unchecked, check_text=None):
+
+        d = OptionalMessageDialog(
+            parent,
+            StyleMessage,
+            title,
+            msg,
+            check_state=check_state,
+            check_text=check_text)
+
+        d.exec_()
+        return d.theCheckBox.isChecked()
+
+    @staticmethod
+    def question(
+            parent, title, msg, check_state=Qt.Unchecked, check_text=None):
+
+        d = OptionalMessageDialog(
+            parent,
+            StyleQuestion,
+            title,
+            msg,
+            check_state=check_state,
+            check_text=check_text)
+
+        d.exec_()
+
+        return d.was_accepted, d.theCheckBox.isChecked()

comictaggerlib/options.py

@@ -0,0 +1,425 @@
+"""CLI options class for ComicTagger app"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sys
+import getopt
+import platform
+import os
+import traceback
+
+try:
+    import argparse
+except ImportError:
+    pass
+
+from datetime import datetime
+from .genericmetadata import GenericMetadata
+from .comicarchive import MetaDataStyle
+from .versionchecker import VersionChecker
+from . import ctversion
+from . import utils
+
+
+class Options:
+    help_text = """Usage: {0} [option] ... [file [files ...]]
+
+A utility for reading and writing metadata to comic archives.
+
+If no options are given, {0} will run in windowed mode.
+
+-p, --print                 Print out tag info from file. Specify type
+                            (via -t) to get only info of that tag type.
+    --raw                   With -p, will print out the raw tag block(s)
+                            from the file.
+-d, --delete                Deletes the tag block of specified type (via
+                            -t).
+-c, --copy=SOURCE           Copy the specified source tag block to
+                            destination style specified via -t
+                            (potentially lossy operation).
+-s, --save                  Save out tags as specified type (via -t).
+                            Must specify also at least -o, -p, or -m.
+    --nooverwrite           Don't modify tag block if it already exists
+                            (relevant for -s or -c).
+-1, --assume-issue-one      Assume issue number is 1 if not found
+                            (relevant for -s).
+-n, --dryrun                Don't actually modify file (only relevant for
+                            -d, -s, or -r).
+-t, --type=TYPE             Specify TYPE as either "CR", "CBL", or
+                            "COMET" (as either ComicRack, ComicBookLover,
+                            or CoMet style tags, respectively).
+-f, --parsefilename         Parse the filename to get some info,
+                            specifically series name, issue number,
+                            volume, and publication year.
+-i, --interactive           Interactively query the user when there are
+                            multiple matches for an online search.
+    --nosummary             Suppress the default summary after a save
+                            operation.
+-o, --online                Search online and attempt to identify file
+                            using existing metadata and images in archive.
+                            May be used in conjunction with -f and -m.
+    --id=ID                 Use the issue ID when searching online.
+                            Overrides all other metadata.
+-m, --metadata=LIST         Explicitly define, as a list, some tags to be
+                            used.  e.g.:
+                            "series=Plastic Man, publisher=Quality Comics"
+                            "series=Kickers^, Inc., issue=1, year=1986"
+                            Name-Value pairs are comma separated. Use a
+                            "^" to escape an "=" or a ",", as shown in
+                            the example above.  Some names that can be
+                            used: series, issue, issueCount, year,
+                            publisher, title
+-r, --rename                Rename the file based on specified tag style.
+    --noabort               Don't abort save operation when online match
+                            is of low confidence.
+-e, --export-to-zip         Export RAR archive to Zip format.
+    --delete-rar            Delete original RAR archive after successful
+                            export to Zip.
+    --abort-on-conflict     Don't export to zip if intended new filename
+                            exists (otherwise, creates a new unique
+                            filename).
+-S, --script=FILE           Run an "add-on" python script that uses the
+                            ComicTagger library for custom processing.
+                            Script arguments can follow the script name.
+-R, --recursive             Recursively include files in sub-folders.
+    --cv-api-key=KEY        Use the given Comic Vine API Key (persisted
+                            in settings).
+    --only-set-cv-key       Only set the Comic Vine API key and quit.
+-w, --wait-on-cv-rate-limit When encountering a Comic Vine rate limit
+                            error, wait and retry query.
+-v, --verbose               Be noisy when doing what it does.
+    --terse                 Don't say much (for print mode).
+    --version               Display version.
+-h, --help                  Display this message.
+
+For more help visit the wiki at: https://github.com/comictagger/comictagger/wiki
+    """
+
+    def __init__(self):
+        self.data_style = None
+        self.no_gui = False
+        self.filename = None
+        self.verbose = False
+        self.terse = False
+        self.metadata = None
+        self.print_tags = False
+        self.copy_tags = False
+        self.delete_tags = False
+        self.export_to_zip = False
+        self.abort_export_on_conflict = False
+        self.delete_rar_after_export = False
+        self.search_online = False
+        self.dryrun = False
+        self.abortOnLowConfidence = True
+        self.save_tags = False
+        self.parse_filename = False
+        self.show_save_summary = True
+        self.raw = False
+        self.cv_api_key = None
+        self.only_set_key = False
+        self.rename_file = False
+        self.no_overwrite = False
+        self.interactive = False
+        self.issue_id = None
+        self.recursive = False
+        self.run_script = False
+        self.script = None
+        self.wait_and_retry_on_rate_limit = False
+        self.assume_issue_is_one_if_not_set = False
+        self.file_list = []
+
+    def display_msg_and_quit(self, msg, code, show_help=False):
+        appname = os.path.basename(sys.argv[0])
+        if msg is not None:
+            print(msg)
+        if show_help:
+            print((self.help_text.format(appname)))
+        else:
+            print("For more help, run with '--help'")
+        sys.exit(code)
+
+    def parseMetadataFromString(self, mdstr):
+        """The metadata string is a comma separated list of name-value pairs
+        The names match the attributes of the internal metadata struct (for now)
+        The caret is the special "escape character", since it's not common in
+        natural language text
+
+        example = "series=Kickers^, Inc. ,issue=1, year=1986"
+        """
+
+        escaped_comma = "^,"
+        escaped_equals = "^="
+        replacement_token = "<_~_>"
+
+        md = GenericMetadata()
+
+        # First, replace escaped commas with with a unique token (to be changed
+        # back later)
+        mdstr = mdstr.replace(escaped_comma, replacement_token)
+        tmp_list = mdstr.split(",")
+        md_list = []
+        for item in tmp_list:
+            item = item.replace(replacement_token, ",")
+            md_list.append(item)
+
+        # Now build a nice dict from the list
+        md_dict = dict()
+        for item in md_list:
+            # Make sure to fix any escaped equal signs
+            i = item.replace(escaped_equals, replacement_token)
+            key, value = i.split("=")
+            value = value.replace(replacement_token, "=").strip()
+            key = key.strip()
+            if key.lower() == "credit":
+                cred_attribs = value.split(":")
+                role = cred_attribs[0]
+                person = (cred_attribs[1] if len(cred_attribs) > 1 else "")
+                primary = (cred_attribs[2] if len(cred_attribs) > 2 else None)
+                md.addCredit(
+                    person.strip(),
+                    role.strip(),
+                    True if primary is not None else False)
+            else:
+                md_dict[key] = value
+
+        # Map the dict to the metadata object
+        for key in md_dict:
+            if not hasattr(md, key):
+                print(("Warning: '{0}' is not a valid tag name".format(key)))
+            else:
+                md.isEmpty = False
+                setattr(md, key, md_dict[key])
+        # print(md)
+        return md
+
+    def launch_script(self, scriptfile):
+        # we were given a script.  special case for the args:
+        # 1. ignore everything before the -S,
+        # 2. pass all the ones that follow (including script name) to the
+        # script
+        script_args = list()
+        for idx, arg in enumerate(sys.argv):
+            if arg in ['-S', '--script']:
+                # found script!
+                script_args = sys.argv[idx + 1:]
+                break
+        sys.argv = script_args
+        if not os.path.exists(scriptfile):
+            print(("Can't find {0}".format(scriptfile)))
+        else:
+            # I *think* this makes sense:
+            #  assume the base name of the file is the module name
+            #  add the folder of the given file to the python path
+            #  import module
+            dirname = os.path.dirname(scriptfile)
+            module_name = os.path.splitext(os.path.basename(scriptfile))[0]
+            sys.path = [dirname] + sys.path
+            try:
+                script = __import__(module_name)
+
+                # Determine if the entry point exists before trying to run it
+                if "main" in dir(script):
+                    script.main()
+                else:
+                    print((
+                        "Can't find entry point \"main()\" in module \"{0}\"".format(module_name)))
+            except Exception as e:
+                print("Script raised an unhandled exception: ", e)
+                print((traceback.format_exc()))
+
+        sys.exit(0)
+
+    def parseCmdLineArgs(self):
+
+        if platform.system() == "Darwin" and hasattr(
+                sys, "frozen") and sys.frozen == 1:
+            # remove the PSN ("process serial number") argument from OS/X
+            input_args = [a for a in sys.argv[1:] if "-psn_0_" not in a]
+        else:
+            input_args = sys.argv[1:]
+
+        # first check if we're launching a script:
+        for n in range(len(input_args)):
+            if (input_args[n] in ["-S", "--script"] and
+                    n + 1 < len(input_args)):
+                # insert a "--" which will cause getopt to ignore the remaining args
+                # so they will be passed to the script
+                input_args.insert(n + 2, "--")
+                break
+
+        # parse command line options
+        try:
+            opts, args = getopt.getopt(input_args,
+                                       "hpdt:fm:vownsrc:ieRS:1",
+                                       ["help", "print", "delete", "type=", "copy=", "parsefilename",
+                                        "metadata=", "verbose", "online", "dryrun", "save", "rename",
+                                        "raw", "noabort", "terse", "nooverwrite", "interactive",
+                                        "nosummary", "version", "id=", "recursive", "script=",
+                                        "export-to-zip", "delete-rar", "abort-on-conflict",
+                                        "assume-issue-one", "cv-api-key=", "only-set-cv-key",
+                                        "wait-on-cv-rate-limit"])
+
+        except getopt.GetoptError as err:
+            self.display_msg_and_quit(str(err), 2)
+
+        # process options
+        for o, a in opts:
+            if o in ("-h", "--help"):
+                self.display_msg_and_quit(None, 0, show_help=True)
+            if o in ("-v", "--verbose"):
+                self.verbose = True
+            if o in ("-S", "--script"):
+                self.run_script = True
+                self.script = a
+            if o in ("-R", "--recursive"):
+                self.recursive = True
+            if o in ("-p", "--print"):
+                self.print_tags = True
+            if o in ("-d", "--delete"):
+                self.delete_tags = True
+            if o in ("-i", "--interactive"):
+                self.interactive = True
+            if o in ("-c", "--copy"):
+                self.copy_tags = True
+                if a.lower() == "cr":
+                    self.copy_source = MetaDataStyle.CIX
+                elif a.lower() == "cbl":
+                    self.copy_source = MetaDataStyle.CBI
+                elif a.lower() == "comet":
+                    self.copy_source = MetaDataStyle.COMET
+                else:
+                    self.display_msg_and_quit(
+                        "Invalid copy tag source type", 1)
+            if o in ("-o", "--online"):
+                self.search_online = True
+            if o in ("-n", "--dryrun"):
+                self.dryrun = True
+            if o in ("-m", "--metadata"):
+                self.metadata = self.parseMetadataFromString(a)
+            if o in ("-s", "--save"):
+                self.save_tags = True
+            if o in ("-r", "--rename"):
+                self.rename_file = True
+            if o in ("-e", "--export_to_zip"):
+                self.export_to_zip = True
+            if o == "--delete-rar":
+                self.delete_rar_after_export = True
+            if o == "--abort-on-conflict":
+                self.abort_export_on_conflict = True
+            if o in ("-f", "--parsefilename"):
+                self.parse_filename = True
+            if o in ("-w", "--wait-on-cv-rate-limit"):
+                self.wait_and_retry_on_rate_limit = True
+            if o == "--id":
+                self.issue_id = a
+            if o == "--raw":
+                self.raw = True
+            if o == "--noabort":
+                self.abortOnLowConfidence = False
+            if o == "--terse":
+                self.terse = True
+            if o == "--nosummary":
+                self.show_save_summary = False
+            if o in ("-1", "--assume-issue-one"):
+                self.assume_issue_is_one_if_not_set = True
+            if o == "--nooverwrite":
+                self.no_overwrite = True
+            if o == "--cv-api-key":
+                self.cv_api_key = a
+            if o == "--only-set-cv-key":
+                self.only_set_key = True
+            if o == "--version":
+                print((
+                    "ComicTagger {}:  Copyright (c) 2012-{:%Y} ComicTagger Team".format(ctversion.version, datetime.today())))
+                print(
+                    "Distributed under Apache License 2.0 (http://www.apache.org/licenses/LICENSE-2.0)")
+                sys.exit(0)
+            if o in ("-t", "--type"):
+                if a.lower() == "cr":
+                    self.data_style = MetaDataStyle.CIX
+                elif a.lower() == "cbl":
+                    self.data_style = MetaDataStyle.CBI
+                elif a.lower() == "comet":
+                    self.data_style = MetaDataStyle.COMET
+                else:
+                    self.display_msg_and_quit("Invalid tag type", 1)
+
+        if self.print_tags or self.delete_tags or self.save_tags or self.copy_tags or self.rename_file or self.export_to_zip or self.only_set_key:
+            self.no_gui = True
+
+        count = 0
+        if self.run_script:
+            count += 1
+        if self.print_tags:
+            count += 1
+        if self.delete_tags:
+            count += 1
+        if self.save_tags:
+            count += 1
+        if self.copy_tags:
+            count += 1
+        if self.rename_file:
+            count += 1
+        if self.export_to_zip:
+            count += 1
+        if self.only_set_key:
+            count += 1
+
+        if count > 1:
+            self.display_msg_and_quit(
+                "Must choose only one action of print, delete, save, copy, rename, export, set key, or run script",
+                1)
+
+        if self.script is not None:
+            self.launch_script(self.script)
+
+        if len(args) > 0:
+            if platform.system() == "Windows":
+                # no globbing on windows shell, so do it for them
+                import glob
+                self.file_list = []
+                for item in args:
+                    self.file_list.extend(glob.glob(item))
+                if len(self.file_list) > 0:
+                    self.filename = self.file_list[0]
+            else:
+                self.filename = args[0]
+                self.file_list = args
+
+        if self.only_set_key and self.cv_api_key is None:
+            self.display_msg_and_quit("Key not given!", 1)
+
+        if (self.only_set_key == False) and self.no_gui and (
+                self.filename is None):
+            self.display_msg_and_quit(
+                "Command requires at least one filename!", 1)
+
+        if self.delete_tags and self.data_style is None:
+            self.display_msg_and_quit(
+                "Please specify the type to delete with -t", 1)
+
+        if self.save_tags and self.data_style is None:
+            self.display_msg_and_quit(
+                "Please specify the type to save with -t", 1)
+
+        if self.copy_tags and self.data_style is None:
+            self.display_msg_and_quit(
+                "Please specify the type to copy to with -t", 1)
+
+        # if self.rename_file and self.data_style is None:
+        #    self.display_msg_and_quit("Please specify the type to use for renaming with -t", 1)
+
+        if self.recursive:
+            self.file_list = utils.get_recursive_filelist(self.file_list)

comictaggerlib/pagebrowser.py

@@ -0,0 +1,114 @@
+"""A PyQT4 dialog to show pages of a comic archive"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import platform
+#import sys
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+from .coverimagewidget import CoverImageWidget
+
+
+class PageBrowserWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent, metadata):
+        super(PageBrowserWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('pagebrowser.ui'), self)
+
+        self.pageWidget = CoverImageWidget(
+            self.pageContainer, CoverImageWidget.ArchiveMode)
+        gridlayout = QtWidgets.QGridLayout(self.pageContainer)
+        gridlayout.addWidget(self.pageWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+        self.pageWidget.showControls = False
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        self.comic_archive = None
+        self.page_count = 0
+        self.current_page_num = 0
+        self.metadata = metadata
+
+        self.buttonBox.button(QtWidgets.QDialogButtonBox.Close).setDefault(True)
+        if platform.system() == "Darwin":
+            self.btnPrev.setText("<<")
+            self.btnNext.setText(">>")
+        else:
+            self.btnPrev.setIcon(
+                QtGui.QIcon(ComicTaggerSettings.getGraphic('left.png')))
+            self.btnNext.setIcon(
+                QtGui.QIcon(ComicTaggerSettings.getGraphic('right.png')))
+
+        self.btnNext.clicked.connect(self.nextPage)
+        self.btnPrev.clicked.connect(self.prevPage)
+        self.show()
+
+        self.btnNext.setEnabled(False)
+        self.btnPrev.setEnabled(False)
+
+    def reset(self):
+        self.comic_archive = None
+        self.page_count = 0
+        self.current_page_num = 0
+        self.metadata = None
+
+        self.btnNext.setEnabled(False)
+        self.btnPrev.setEnabled(False)
+        self.pageWidget.clear()
+
+    def setComicArchive(self, ca):
+
+        self.comic_archive = ca
+        self.page_count = ca.getNumberOfPages()
+        self.current_page_num = 0
+        self.pageWidget.setArchive(self.comic_archive)
+        self.setPage()
+
+        if self.page_count > 1:
+            self.btnNext.setEnabled(True)
+            self.btnPrev.setEnabled(True)
+
+    def nextPage(self):
+
+        if self.current_page_num + 1 < self.page_count:
+            self.current_page_num += 1
+        else:
+            self.current_page_num = 0
+        self.setPage()
+
+    def prevPage(self):
+
+        if self.current_page_num - 1 >= 0:
+            self.current_page_num -= 1
+        else:
+            self.current_page_num = self.page_count - 1
+        self.setPage()
+
+    def setPage(self):
+        if self.metadata is not None:
+            archive_page_index = self.metadata.getArchivePageIndex(
+                self.current_page_num)
+        else:
+            archive_page_index = self.current_page_num
+
+        self.pageWidget.setPage(archive_page_index)
+        self.setWindowTitle(
+            "Page Browser - Page {0} (of {1}) ".format(self.current_page_num + 1, self.page_count))

comictaggerlib/pagelisteditor.py

@@ -0,0 +1,282 @@
+"""A PyQt5 widget for editing the page list info"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import os
+
+from PyQt5.QtCore import *
+from PyQt5.QtGui import *
+from PyQt5.QtWidgets import *
+from PyQt5 import uic
+
+from .settings import ComicTaggerSettings
+from .genericmetadata import GenericMetadata, PageType
+from .comicarchive import MetaDataStyle
+from .coverimagewidget import CoverImageWidget
+#from pageloader import PageLoader
+
+
+def itemMoveEvents(widget):
+
+    class Filter(QObject):
+
+        mysignal = pyqtSignal(str)
+
+        def eventFilter(self, obj, event):
+
+            if obj == widget:
+                # print(event.type())
+                if event.type() == QEvent.ChildRemoved:
+                    # print("ChildRemoved")
+                    self.mysignal.emit("finish")
+                if event.type() == QEvent.ChildAdded:
+                    # print("ChildAdded")
+                    self.mysignal.emit("start")
+                    return True
+
+            return False
+
+    filter = Filter(widget)
+    widget.installEventFilter(filter)
+    return filter.mysignal
+
+
+class PageListEditor(QWidget):
+
+    firstFrontCoverChanged = pyqtSignal(int)
+    listOrderChanged = pyqtSignal()
+    modified = pyqtSignal()
+
+    pageTypeNames = {
+        PageType.FrontCover: "Front Cover",
+        PageType.InnerCover: "Inner Cover",
+        PageType.Advertisement: "Advertisement",
+        PageType.Roundup: "Roundup",
+        PageType.Story: "Story",
+        PageType.Editorial: "Editorial",
+        PageType.Letters: "Letters",
+        PageType.Preview: "Preview",
+        PageType.BackCover: "Back Cover",
+        PageType.Other: "Other",
+        PageType.Deleted: "Deleted",
+    }
+
+    def __init__(self, parent):
+        super(PageListEditor, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('pagelisteditor.ui'), self)
+
+        self.pageWidget = CoverImageWidget(
+            self.pageContainer, CoverImageWidget.ArchiveMode)
+        gridlayout = QGridLayout(self.pageContainer)
+        gridlayout.addWidget(self.pageWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+        self.pageWidget.showControls = False
+
+        self.resetPage()
+
+        # Add the entries to the manga combobox
+        self.comboBox.addItem("", "")
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.FrontCover], PageType.FrontCover)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.InnerCover], PageType.InnerCover)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Advertisement], PageType.Advertisement)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Roundup], PageType.Roundup)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Story], PageType.Story)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Editorial], PageType.Editorial)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Letters], PageType.Letters)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Preview], PageType.Preview)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.BackCover], PageType.BackCover)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Other], PageType.Other)
+        self.comboBox.addItem(
+            self.pageTypeNames[PageType.Deleted], PageType.Deleted)
+
+        self.listWidget.itemSelectionChanged.connect(self.changePage)
+        itemMoveEvents(self.listWidget).connect(self.itemMoveEvent)
+        self.comboBox.activated.connect(self.changePageType)
+        self.btnUp.clicked.connect(self.moveCurrentUp)
+        self.btnDown.clicked.connect(self.moveCurrentDown)
+        self.pre_move_row = -1
+        self.first_front_page = None
+
+    def resetPage(self):
+        self.pageWidget.clear()
+        self.comboBox.setDisabled(True)
+        self.comic_archive = None
+        self.pages_list = None
+
+    def moveCurrentUp(self):
+        row = self.listWidget.currentRow()
+        if row > 0:
+            item = self.listWidget.takeItem(row)
+            self.listWidget.insertItem(row - 1, item)
+            self.listWidget.setCurrentRow(row - 1)
+            self.listOrderChanged.emit()
+            self.emitFrontCoverChange()
+            self.modified.emit()
+
+    def moveCurrentDown(self):
+        row = self.listWidget.currentRow()
+        if row < self.listWidget.count() - 1:
+            item = self.listWidget.takeItem(row)
+            self.listWidget.insertItem(row + 1, item)
+            self.listWidget.setCurrentRow(row + 1)
+            self.listOrderChanged.emit()
+            self.emitFrontCoverChange()
+            self.modified.emit()
+
+    def itemMoveEvent(self, s):
+        # print "move event: ", s, self.listWidget.currentRow()
+        if s == "start":
+            self.pre_move_row = self.listWidget.currentRow()
+        if s == "finish":
+            if self.pre_move_row != self.listWidget.currentRow():
+                self.listOrderChanged.emit()
+                self.emitFrontCoverChange()
+                self.modified.emit()
+
+    def changePageType(self, i):
+        new_type = self.comboBox.itemData(i).toString()
+        if self.getCurrentPageType() != new_type:
+            self.setCurrentPageType(new_type)
+            self.emitFrontCoverChange()
+            self.modified.emit()
+
+    def changePage(self):
+        row = self.listWidget.currentRow()
+        pagetype = self.getCurrentPageType()
+
+        i = self.comboBox.findData(pagetype)
+        self.comboBox.setCurrentIndex(i)
+
+        #idx = int(str (self.listWidget.item(row).text()))
+        idx = int(self.listWidget.item(row).data(
+            Qt.UserRole)[0]['Image'])
+
+        if self.comic_archive is not None:
+            self.pageWidget.setArchive(self.comic_archive, idx)
+
+    def getFirstFrontCover(self):
+        frontCover = 0
+        for i in range(self.listWidget.count()):
+            item = self.listWidget.item(i)
+            page_dict = item.data(Qt.UserRole)[0] #.toPyObject()[0]
+            if 'Type' in page_dict and page_dict[
+                    'Type'] == PageType.FrontCover:
+                frontCover = int(page_dict['Image'])
+                break
+        return frontCover
+
+    def getCurrentPageType(self):
+        row = self.listWidget.currentRow()
+        page_dict = self.listWidget.item(row).data(Qt.UserRole)[0] #.toPyObject()[0]
+        if 'Type' in page_dict:
+            return page_dict['Type']
+        else:
+            return ""
+
+    def setCurrentPageType(self, t):
+        row = self.listWidget.currentRow()
+        page_dict = self.listWidget.item(row).data(Qt.UserRole)[0] #.toPyObject()[0]
+
+        if t == "":
+            if 'Type' in page_dict:
+                del(page_dict['Type'])
+        else:
+            page_dict['Type'] = str(t)
+
+        item = self.listWidget.item(row)
+        # wrap the dict in a tuple to keep from being converted to QStrings
+        item.setData(Qt.UserRole, (page_dict,))
+        item.setText(self.listEntryText(page_dict))
+
+    def setData(self, comic_archive, pages_list):
+        self.comic_archive = comic_archive
+        self.pages_list = pages_list
+        if pages_list is not None and len(pages_list) > 0:
+            self.comboBox.setDisabled(False)
+
+        self.listWidget.itemSelectionChanged.disconnect(self.changePage)
+
+        self.listWidget.clear()
+        for p in pages_list:
+            item = QListWidgetItem(self.listEntryText(p))
+            # wrap the dict in a tuple to keep from being converted to QStrings
+            item.setData(Qt.UserRole, (p,))
+
+            self.listWidget.addItem(item)
+        self.first_front_page = self.getFirstFrontCover()
+        self.listWidget.itemSelectionChanged.connect(self.changePage)
+        self.listWidget.setCurrentRow(0)
+
+    def listEntryText(self, page_dict):
+        text = str(int(page_dict['Image']) + 1)
+        if 'Type' in page_dict:
+            text += " (" + self.pageTypeNames[page_dict['Type']] + ")"
+        return text
+
+    def getPageList(self):
+        page_list = []
+        for i in range(self.listWidget.count()):
+            item = self.listWidget.item(i)
+            page_list.append(item.data(Qt.UserRole)[0]) #.toPyObject()[0]
+        return page_list
+
+    def emitFrontCoverChange(self):
+        if self.first_front_page != self.getFirstFrontCover():
+            self.first_front_page = self.getFirstFrontCover()
+            self.firstFrontCoverChanged.emit(self.first_front_page)
+
+    def setMetadataStyle(self, data_style):
+
+        # depending on the current data style, certain fields are disabled
+
+        inactive_color = QColor(255, 170, 150)
+        active_palette = self.comboBox.palette()
+
+        inactive_palette3 = self.comboBox.palette()
+        inactive_palette3.setColor(QPalette.Base, inactive_color)
+
+        if data_style == MetaDataStyle.CIX:
+            self.btnUp.setEnabled(True)
+            self.btnDown.setEnabled(True)
+            self.comboBox.setEnabled(True)
+            self.listWidget.setEnabled(True)
+
+            self.listWidget.setPalette(active_palette)
+
+        elif data_style == MetaDataStyle.CBI:
+            self.btnUp.setEnabled(False)
+            self.btnDown.setEnabled(False)
+            self.comboBox.setEnabled(False)
+            self.listWidget.setEnabled(False)
+
+            self.listWidget.setPalette(inactive_palette3)
+
+        elif data_style == MetaDataStyle.CoMet:
+            pass
+
+        # make sure combo is disabled when no list
+        if self.comic_archive is None:
+            self.comboBox.setEnabled(False)

comictaggerlib/pageloader.py

@@ -0,0 +1,70 @@
+"""A PyQT4 class to load a page image from a ComicArchive in a background thread"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from PyQt5 import QtCore, QtGui, uic
+from PyQt5.QtCore import pyqtSignal
+
+from comictaggerlib.ui.qtutils import getQImageFromData
+#from comicarchive import ComicArchive
+#import utils
+
+
+class PageLoader(QtCore.QThread):
+
+    """
+    This class holds onto a reference of each instance in a list since
+    problems occur if the ref count goes to zero and the GC tries to reap
+    the object while the thread is going.
+    If the client class wants to stop the thread, they should mark it as
+    "abandoned", and no signals will be issued.
+    """
+
+    loadComplete = pyqtSignal(QtGui.QImage)
+
+    instanceList = []
+    mutex = QtCore.QMutex()
+
+    # Remove all finished threads from the list
+    @staticmethod
+    def reapInstances():
+        for obj in reversed(PageLoader.instanceList):
+            if obj.isFinished():
+                PageLoader.instanceList.remove(obj)
+
+    def __init__(self, ca, page_num):
+        QtCore.QThread.__init__(self)
+        self.ca = ca
+        self.page_num = page_num
+        self.abandoned = False
+
+        # remove any old instances, and then add ourself
+        PageLoader.mutex.lock()
+        PageLoader.reapInstances()
+        PageLoader.instanceList.append(self)
+        PageLoader.mutex.unlock()
+
+    def run(self):
+        image_data = self.ca.getPage(self.page_num)
+        if self.abandoned:
+            return
+
+        if image_data is not None:
+            img = getQImageFromData(image_data)
+
+            if self.abandoned:
+                return
+
+            self.loadComplete.emit(img)

comictaggerlib/progresswindow.py

@@ -0,0 +1,38 @@
+"""A PyQT5 dialog to show ID log and progress"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#import sys
+#import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from comictaggerlib.ui.qtutils import reduceWidgetFontSize
+from .settings import ComicTaggerSettings
+#import utils
+
+
+class IDProgressWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent):
+        super(IDProgressWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('progresswindow.ui'), self)
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        reduceWidgetFontSize(self.textEdit)

comictaggerlib/renamewindow.py

@@ -0,0 +1,170 @@
+"""A PyQT4 dialog to confirm rename"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+from .settingswindow import SettingsWindow
+from .filerenamer import FileRenamer
+from .comicarchive import MetaDataStyle
+from comictaggerlib.ui.qtutils import  centerWindowOnParent
+from . import utils
+
+
+class RenameWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent, comic_archive_list, data_style, settings):
+        super(RenameWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('renamewindow.ui'), self)
+        self.label.setText(
+            "Preview (based on {0} tags):".format(
+                MetaDataStyle.name[data_style]))
+
+        self.setWindowFlags(self.windowFlags() |
+                            QtCore.Qt.WindowSystemMenuHint |
+                            QtCore.Qt.WindowMaximizeButtonHint)
+
+        self.settings = settings
+        self.comic_archive_list = comic_archive_list
+        self.data_style = data_style
+
+        self.btnSettings.clicked.connect(self.modifySettings)
+        self.configRenamer()
+        self.doPreview()
+
+    def configRenamer(self):
+        self.renamer = FileRenamer(None)
+        self.renamer.setTemplate(self.settings.rename_template)
+        self.renamer.setIssueZeroPadding(
+            self.settings.rename_issue_number_padding)
+        self.renamer.setSmartCleanup(
+            self.settings.rename_use_smart_string_cleanup)
+
+    def doPreview(self):
+        self.rename_list = []
+        while self.twList.rowCount() > 0:
+            self.twList.removeRow(0)
+
+        self.twList.setSortingEnabled(False)
+
+        for ca in self.comic_archive_list:
+
+            new_ext = None  # default
+            if self.settings.rename_extension_based_on_archive:
+                if ca.isZip():
+                    new_ext = ".cbz"
+                elif ca.isRar():
+                    new_ext = ".cbr"
+
+            md = ca.readMetadata(self.data_style)
+            if md.isEmpty:
+                md = ca.metadataFromFilename(self.settings.parse_scan_info)
+            self.renamer.setMetadata(md)
+            new_name = self.renamer.determineName(ca.path, ext=new_ext)
+
+            row = self.twList.rowCount()
+            self.twList.insertRow(row)
+            folder_item = QtWidgets.QTableWidgetItem()
+            old_name_item = QtWidgets.QTableWidgetItem()
+            new_name_item = QtWidgets.QTableWidgetItem()
+
+            item_text = os.path.split(ca.path)[0]
+            folder_item.setFlags(
+                QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 0, folder_item)
+            folder_item.setText(item_text)
+            folder_item.setData(QtCore.Qt.ToolTipRole, item_text)
+
+            item_text = os.path.split(ca.path)[1]
+            old_name_item.setFlags(
+                QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 1, old_name_item)
+            old_name_item.setText(item_text)
+            old_name_item.setData(QtCore.Qt.ToolTipRole, item_text)
+
+            new_name_item.setFlags(
+                QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            self.twList.setItem(row, 2, new_name_item)
+            new_name_item.setText(new_name)
+            new_name_item.setData(QtCore.Qt.ToolTipRole, new_name)
+
+            dict_item = dict()
+            dict_item['archive'] = ca
+            dict_item['new_name'] = new_name
+            self.rename_list.append(dict_item)
+
+        # Adjust column sizes
+        self.twList.setVisible(False)
+        self.twList.resizeColumnsToContents()
+        self.twList.setVisible(True)
+        if self.twList.columnWidth(0) > 200:
+            self.twList.setColumnWidth(0, 200)
+
+        self.twList.setSortingEnabled(True)
+
+    def modifySettings(self):
+        settingswin = SettingsWindow(self, self.settings)
+        settingswin.setModal(True)
+        settingswin.showRenameTab()
+        settingswin.exec_()
+        if settingswin.result():
+            self.configRenamer()
+            self.doPreview()
+
+    def accept(self):
+
+        progdialog = QtWidgets.QProgressDialog(
+            "", "Cancel", 0, len(self.rename_list), self)
+        progdialog.setWindowTitle("Renaming Archives")
+        progdialog.setWindowModality(QtCore.Qt.WindowModal)
+        progdialog.setMinimumDuration(100)
+        centerWindowOnParent(progdialog)
+        #progdialog.show()
+        QtCore.QCoreApplication.processEvents()
+
+        for idx, item in enumerate(self.rename_list):
+
+            QtCore.QCoreApplication.processEvents()
+            if progdialog.wasCanceled():
+                break
+            idx += 1
+            progdialog.setValue(idx)
+            progdialog.setLabelText(item['new_name'])
+            centerWindowOnParent(progdialog)
+            QtCore.QCoreApplication.processEvents()
+
+            if item['new_name'] == os.path.basename(item['archive'].path):
+                print(item['new_name'], "Filename is already good!")
+                continue
+
+            if not item['archive'].isWritable(check_rar_status=False):
+                continue
+
+            folder = os.path.dirname(os.path.abspath(item['archive'].path))
+            new_abs_path = utils.unique_file(
+                os.path.join(folder, item['new_name']))
+
+            os.rename(item['archive'].path, new_abs_path)
+
+            item['archive'].rename(new_abs_path)
+
+        progdialog.hide()
+        QtCore.QCoreApplication.processEvents()
+
+        QtWidgets.QDialog.accept(self)

comictaggerlib/settings.py

@@ -0,0 +1,492 @@
+"""Settings class for ComicTagger app"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+import sys
+import configparser
+import platform
+import codecs
+import uuid
+
+from . import utils
+
+
+class ComicTaggerSettings:
+
+    @staticmethod
+    def getSettingsFolder():
+        filename_encoding = sys.getfilesystemencoding()
+        if platform.system() == "Windows":
+            folder = os.path.join(os.environ['APPDATA'], 'ComicTagger')
+        else:
+            folder = os.path.join(os.path.expanduser('~'), '.ComicTagger')
+        if folder is not None:
+            folder = folder
+        return folder
+    
+    @staticmethod
+    def baseDir():
+        if getattr(sys, 'frozen', None):
+            return sys._MEIPASS
+        else:
+            return os.path.dirname(os.path.abspath(__file__))
+
+    @staticmethod
+    def getGraphic(filename):
+        graphic_folder = os.path.join(
+            ComicTaggerSettings.baseDir(), 'graphics')
+        return os.path.join(graphic_folder, filename)
+
+    @staticmethod
+    def getUIFile(filename):
+        ui_folder = os.path.join(ComicTaggerSettings.baseDir(), 'ui')
+        return os.path.join(ui_folder, filename)
+
+    def setDefaultValues(self):
+        # General Settings
+        self.rar_exe_path = ""
+        self.allow_cbi_in_rar = True
+        self.check_for_new_version = False
+        self.send_usage_stats = False
+
+        # automatic settings
+        self.install_id = uuid.uuid4().hex
+        self.last_selected_save_data_style = 0
+        self.last_selected_load_data_style = 0
+        self.last_opened_folder = ""
+        self.last_main_window_width = 0
+        self.last_main_window_height = 0
+        self.last_main_window_x = 0
+        self.last_main_window_y = 0
+        self.last_form_side_width = -1
+        self.last_list_side_width = -1
+        self.last_filelist_sorted_column = -1
+        self.last_filelist_sorted_order = 0
+
+        # identifier settings
+        self.id_length_delta_thresh = 5
+        self.id_publisher_blacklist = "Panini Comics, Abril, Planeta DeAgostini, Editorial Televisa, Dino Comics"
+
+        # Show/ask dialog flags
+        self.ask_about_cbi_in_rar = True
+        self.show_disclaimer = True
+        self.dont_notify_about_this_version = ""
+        self.ask_about_usage_stats = True
+
+        # filename parsing settings
+        self.parse_scan_info = True
+
+        # Comic Vine settings
+        self.use_series_start_as_volume = False
+        self.clear_form_before_populating_from_cv = False
+        self.remove_html_tables = False
+        self.cv_api_key = ""
+
+        # CBL Tranform settings
+
+        self.assume_lone_credit_is_primary = False
+        self.copy_characters_to_tags = False
+        self.copy_teams_to_tags = False
+        self.copy_locations_to_tags = False
+        self.copy_storyarcs_to_tags = False
+        self.copy_notes_to_comments = False
+        self.copy_weblink_to_comments = False
+        self.apply_cbl_transform_on_cv_import = False
+        self.apply_cbl_transform_on_bulk_operation = False
+
+        # Rename settings
+        self.rename_template = "%series% #%issue% (%year%)"
+        self.rename_issue_number_padding = 3
+        self.rename_use_smart_string_cleanup = True
+        self.rename_extension_based_on_archive = True
+
+        # Auto-tag stickies
+        self.save_on_low_confidence = False
+        self.dont_use_year_when_identifying = False
+        self.assume_1_if_no_issue_num = False
+        self.ignore_leading_numbers_in_filename = False
+        self.remove_archive_after_successful_match = False
+        self.wait_and_retry_on_rate_limit = False
+
+    def __init__(self):
+
+        self.settings_file = ""
+        self.folder = ""
+        self.setDefaultValues()
+
+        self.config = configparser.RawConfigParser()
+        self.folder = ComicTaggerSettings.getSettingsFolder()
+
+        if not os.path.exists(self.folder):
+            os.makedirs(self.folder)
+
+        self.settings_file = os.path.join(self.folder, "settings")
+
+        # if config file doesn't exist, write one out
+        if not os.path.exists(self.settings_file):
+            self.save()
+        else:
+            self.load()
+
+        # take a crack at finding rar exe, if not set already
+        if self.rar_exe_path == "":
+            if platform.system() == "Windows":
+                # look in some likely places for Windows machines
+                if os.path.exists("C:\Program Files\WinRAR\Rar.exe"):
+                    self.rar_exe_path = "C:\Program Files\WinRAR\Rar.exe"
+                elif os.path.exists("C:\Program Files (x86)\WinRAR\Rar.exe"):
+                    self.rar_exe_path = "C:\Program Files (x86)\WinRAR\Rar.exe"
+            else:
+                # see if it's in the path of unix user
+                if utils.which("rar") is not None:
+                    self.rar_exe_path = utils.which("rar")
+            if self.rar_exe_path != "":
+                self.save()
+        if self.rar_exe_path != "":
+             # make sure rar program is now in the path for the rar class    
+            utils.addtopath(os.path.dirname(self.rar_exe_path))          
+
+    def reset(self):
+        os.unlink(self.settings_file)
+        self.__init__()
+
+    def load(self):
+
+        def readline_generator(f):
+            line = f.readline()
+            while line:
+                yield line
+                line = f.readline()
+
+        #self.config.readfp(codecs.open(self.settings_file, "r", "utf8"))
+        self.config.read_file(
+            readline_generator(codecs.open(self.settings_file, "r", "utf8")))
+
+        self.rar_exe_path = self.config.get('settings', 'rar_exe_path')
+        if self.config.has_option('settings', 'check_for_new_version'):
+            self.check_for_new_version = self.config.getboolean(
+                'settings', 'check_for_new_version')
+        if self.config.has_option('settings', 'send_usage_stats'):
+            self.send_usage_stats = self.config.getboolean(
+                'settings', 'send_usage_stats')
+
+        if self.config.has_option('auto', 'install_id'):
+            self.install_id = self.config.get('auto', 'install_id')
+        if self.config.has_option('auto', 'last_selected_load_data_style'):
+            self.last_selected_load_data_style = self.config.getint(
+                'auto', 'last_selected_load_data_style')
+        if self.config.has_option('auto', 'last_selected_save_data_style'):
+            self.last_selected_save_data_style = self.config.getint(
+                'auto', 'last_selected_save_data_style')
+        if self.config.has_option('auto', 'last_opened_folder'):
+            self.last_opened_folder = self.config.get(
+                'auto', 'last_opened_folder')
+        if self.config.has_option('auto', 'last_main_window_width'):
+            self.last_main_window_width = self.config.getint(
+                'auto', 'last_main_window_width')
+        if self.config.has_option('auto', 'last_main_window_height'):
+            self.last_main_window_height = self.config.getint(
+                'auto', 'last_main_window_height')
+        if self.config.has_option('auto', 'last_main_window_x'):
+            self.last_main_window_x = self.config.getint(
+                'auto', 'last_main_window_x')
+        if self.config.has_option('auto', 'last_main_window_y'):
+            self.last_main_window_y = self.config.getint(
+                'auto', 'last_main_window_y')
+        if self.config.has_option('auto', 'last_form_side_width'):
+            self.last_form_side_width = self.config.getint(
+                'auto', 'last_form_side_width')
+        if self.config.has_option('auto', 'last_list_side_width'):
+            self.last_list_side_width = self.config.getint(
+                'auto', 'last_list_side_width')
+        if self.config.has_option('auto', 'last_filelist_sorted_column'):
+            self.last_filelist_sorted_column = self.config.getint(
+                'auto', 'last_filelist_sorted_column')
+        if self.config.has_option('auto', 'last_filelist_sorted_order'):
+            self.last_filelist_sorted_order = self.config.getint(
+                'auto', 'last_filelist_sorted_order')
+
+        if self.config.has_option('identifier', 'id_length_delta_thresh'):
+            self.id_length_delta_thresh = self.config.getint(
+                'identifier', 'id_length_delta_thresh')
+        if self.config.has_option('identifier', 'id_publisher_blacklist'):
+            self.id_publisher_blacklist = self.config.get(
+                'identifier', 'id_publisher_blacklist')
+
+        if self.config.has_option('filenameparser', 'parse_scan_info'):
+            self.parse_scan_info = self.config.getboolean(
+                'filenameparser', 'parse_scan_info')
+
+        if self.config.has_option('dialogflags', 'ask_about_cbi_in_rar'):
+            self.ask_about_cbi_in_rar = self.config.getboolean(
+                'dialogflags', 'ask_about_cbi_in_rar')
+        if self.config.has_option('dialogflags', 'show_disclaimer'):
+            self.show_disclaimer = self.config.getboolean(
+                'dialogflags', 'show_disclaimer')
+        if self.config.has_option(
+                'dialogflags', 'dont_notify_about_this_version'):
+            self.dont_notify_about_this_version = self.config.get(
+                'dialogflags', 'dont_notify_about_this_version')
+        if self.config.has_option('dialogflags', 'ask_about_usage_stats'):
+            self.ask_about_usage_stats = self.config.getboolean(
+                'dialogflags', 'ask_about_usage_stats')
+
+        if self.config.has_option('comicvine', 'use_series_start_as_volume'):
+            self.use_series_start_as_volume = self.config.getboolean(
+                'comicvine', 'use_series_start_as_volume')
+        if self.config.has_option(
+                'comicvine', 'clear_form_before_populating_from_cv'):
+            self.clear_form_before_populating_from_cv = self.config.getboolean(
+                'comicvine', 'clear_form_before_populating_from_cv')
+        if self.config.has_option('comicvine', 'remove_html_tables'):
+            self.remove_html_tables = self.config.getboolean(
+                'comicvine', 'remove_html_tables')
+        if self.config.has_option('comicvine', 'cv_api_key'):
+            self.cv_api_key = self.config.get('comicvine', 'cv_api_key')
+
+        if self.config.has_option(
+                'cbl_transform', 'assume_lone_credit_is_primary'):
+            self.assume_lone_credit_is_primary = self.config.getboolean(
+                'cbl_transform', 'assume_lone_credit_is_primary')
+        if self.config.has_option('cbl_transform', 'copy_characters_to_tags'):
+            self.copy_characters_to_tags = self.config.getboolean(
+                'cbl_transform', 'copy_characters_to_tags')
+        if self.config.has_option('cbl_transform', 'copy_teams_to_tags'):
+            self.copy_teams_to_tags = self.config.getboolean(
+                'cbl_transform', 'copy_teams_to_tags')
+        if self.config.has_option('cbl_transform', 'copy_locations_to_tags'):
+            self.copy_locations_to_tags = self.config.getboolean(
+                'cbl_transform', 'copy_locations_to_tags')
+        if self.config.has_option('cbl_transform', 'copy_notes_to_comments'):
+            self.copy_notes_to_comments = self.config.getboolean(
+                'cbl_transform', 'copy_notes_to_comments')
+        if self.config.has_option('cbl_transform', 'copy_storyarcs_to_tags'):
+            self.copy_storyarcs_to_tags = self.config.getboolean(
+                'cbl_transform', 'copy_storyarcs_to_tags')
+        if self.config.has_option('cbl_transform', 'copy_weblink_to_comments'):
+            self.copy_weblink_to_comments = self.config.getboolean(
+                'cbl_transform', 'copy_weblink_to_comments')
+        if self.config.has_option(
+                'cbl_transform', 'apply_cbl_transform_on_cv_import'):
+            self.apply_cbl_transform_on_cv_import = self.config.getboolean(
+                'cbl_transform', 'apply_cbl_transform_on_cv_import')
+        if self.config.has_option(
+                'cbl_transform', 'apply_cbl_transform_on_bulk_operation'):
+            self.apply_cbl_transform_on_bulk_operation = self.config.getboolean(
+                'cbl_transform',
+                'apply_cbl_transform_on_bulk_operation')
+
+        if self.config.has_option('rename', 'rename_template'):
+            self.rename_template = self.config.get('rename', 'rename_template')
+        if self.config.has_option('rename', 'rename_issue_number_padding'):
+            self.rename_issue_number_padding = self.config.getint(
+                'rename', 'rename_issue_number_padding')
+        if self.config.has_option('rename', 'rename_use_smart_string_cleanup'):
+            self.rename_use_smart_string_cleanup = self.config.getboolean(
+                'rename', 'rename_use_smart_string_cleanup')
+        if self.config.has_option(
+                'rename', 'rename_extension_based_on_archive'):
+            self.rename_extension_based_on_archive = self.config.getboolean(
+                'rename', 'rename_extension_based_on_archive')
+
+        if self.config.has_option('autotag', 'save_on_low_confidence'):
+            self.save_on_low_confidence = self.config.getboolean(
+                'autotag', 'save_on_low_confidence')
+        if self.config.has_option('autotag', 'dont_use_year_when_identifying'):
+            self.dont_use_year_when_identifying = self.config.getboolean(
+                'autotag', 'dont_use_year_when_identifying')
+        if self.config.has_option('autotag', 'assume_1_if_no_issue_num'):
+            self.assume_1_if_no_issue_num = self.config.getboolean(
+                'autotag', 'assume_1_if_no_issue_num')
+        if self.config.has_option(
+                'autotag', 'ignore_leading_numbers_in_filename'):
+            self.ignore_leading_numbers_in_filename = self.config.getboolean(
+                'autotag', 'ignore_leading_numbers_in_filename')
+        if self.config.has_option(
+                'autotag', 'remove_archive_after_successful_match'):
+            self.remove_archive_after_successful_match = self.config.getboolean(
+                'autotag',
+                'remove_archive_after_successful_match')
+        if self.config.has_option('autotag', 'wait_and_retry_on_rate_limit'):
+            self.wait_and_retry_on_rate_limit = self.config.getboolean(
+                'autotag', 'wait_and_retry_on_rate_limit')
+
+    def save(self):
+
+        if not self.config.has_section('settings'):
+            self.config.add_section('settings')
+
+        self.config.set(
+            'settings', 'check_for_new_version', self.check_for_new_version)
+        self.config.set('settings', 'rar_exe_path', self.rar_exe_path)
+        self.config.set('settings', 'send_usage_stats', self.send_usage_stats)
+
+        if not self.config.has_section('auto'):
+            self.config.add_section('auto')
+
+        self.config.set('auto', 'install_id', self.install_id)
+        self.config.set(
+            'auto',
+            'last_selected_load_data_style',
+            self.last_selected_load_data_style)
+        self.config.set(
+            'auto',
+            'last_selected_save_data_style',
+            self.last_selected_save_data_style)
+        self.config.set('auto', 'last_opened_folder', self.last_opened_folder)
+        self.config.set(
+            'auto', 'last_main_window_width', self.last_main_window_width)
+        self.config.set(
+            'auto', 'last_main_window_height', self.last_main_window_height)
+        self.config.set('auto', 'last_main_window_x', self.last_main_window_x)
+        self.config.set('auto', 'last_main_window_y', self.last_main_window_y)
+        self.config.set(
+            'auto', 'last_form_side_width', self.last_form_side_width)
+        self.config.set(
+            'auto', 'last_list_side_width', self.last_list_side_width)
+        self.config.set(
+            'auto',
+            'last_filelist_sorted_column',
+            self.last_filelist_sorted_column)
+        self.config.set(
+            'auto',
+            'last_filelist_sorted_order',
+            self.last_filelist_sorted_order)
+
+        if not self.config.has_section('identifier'):
+            self.config.add_section('identifier')
+
+        self.config.set(
+            'identifier',
+            'id_length_delta_thresh',
+            self.id_length_delta_thresh)
+        self.config.set(
+            'identifier',
+            'id_publisher_blacklist',
+            self.id_publisher_blacklist)
+
+        if not self.config.has_section('dialogflags'):
+            self.config.add_section('dialogflags')
+
+        self.config.set(
+            'dialogflags', 'ask_about_cbi_in_rar', self.ask_about_cbi_in_rar)
+        self.config.set('dialogflags', 'show_disclaimer', self.show_disclaimer)
+        self.config.set(
+            'dialogflags',
+            'dont_notify_about_this_version',
+            self.dont_notify_about_this_version)
+        self.config.set(
+            'dialogflags', 'ask_about_usage_stats', self.ask_about_usage_stats)
+
+        if not self.config.has_section('filenameparser'):
+            self.config.add_section('filenameparser')
+
+        self.config.set(
+            'filenameparser', 'parse_scan_info', self.parse_scan_info)
+
+        if not self.config.has_section('comicvine'):
+            self.config.add_section('comicvine')
+
+        self.config.set(
+            'comicvine',
+            'use_series_start_as_volume',
+            self.use_series_start_as_volume)
+        self.config.set('comicvine', 'clear_form_before_populating_from_cv',
+                        self.clear_form_before_populating_from_cv)
+        self.config.set(
+            'comicvine', 'remove_html_tables', self.remove_html_tables)
+        self.config.set('comicvine', 'cv_api_key', self.cv_api_key)
+
+        if not self.config.has_section('cbl_transform'):
+            self.config.add_section('cbl_transform')
+
+        self.config.set(
+            'cbl_transform',
+            'assume_lone_credit_is_primary',
+            self.assume_lone_credit_is_primary)
+        self.config.set(
+            'cbl_transform',
+            'copy_characters_to_tags',
+            self.copy_characters_to_tags)
+        self.config.set(
+            'cbl_transform', 'copy_teams_to_tags', self.copy_teams_to_tags)
+        self.config.set(
+            'cbl_transform',
+            'copy_locations_to_tags',
+            self.copy_locations_to_tags)
+        self.config.set(
+            'cbl_transform',
+            'copy_storyarcs_to_tags',
+            self.copy_storyarcs_to_tags)
+        self.config.set(
+            'cbl_transform',
+            'copy_notes_to_comments',
+            self.copy_notes_to_comments)
+        self.config.set(
+            'cbl_transform',
+            'copy_weblink_to_comments',
+            self.copy_weblink_to_comments)
+        self.config.set(
+            'cbl_transform',
+            'apply_cbl_transform_on_cv_import',
+            self.apply_cbl_transform_on_cv_import)
+        self.config.set(
+            'cbl_transform',
+            'apply_cbl_transform_on_bulk_operation',
+            self.apply_cbl_transform_on_bulk_operation)
+
+        if not self.config.has_section('rename'):
+            self.config.add_section('rename')
+
+        self.config.set('rename', 'rename_template', self.rename_template)
+        self.config.set(
+            'rename',
+            'rename_issue_number_padding',
+            self.rename_issue_number_padding)
+        self.config.set(
+            'rename',
+            'rename_use_smart_string_cleanup',
+            self.rename_use_smart_string_cleanup)
+        self.config.set('rename', 'rename_extension_based_on_archive',
+                        self.rename_extension_based_on_archive)
+
+        if not self.config.has_section('autotag'):
+            self.config.add_section('autotag')
+        self.config.set(
+            'autotag', 'save_on_low_confidence', self.save_on_low_confidence)
+        self.config.set(
+            'autotag',
+            'dont_use_year_when_identifying',
+            self.dont_use_year_when_identifying)
+        self.config.set(
+            'autotag',
+            'assume_1_if_no_issue_num',
+            self.assume_1_if_no_issue_num)
+        self.config.set('autotag', 'ignore_leading_numbers_in_filename',
+                        self.ignore_leading_numbers_in_filename)
+        self.config.set('autotag', 'remove_archive_after_successful_match',
+                        self.remove_archive_after_successful_match)
+        self.config.set(
+            'autotag',
+            'wait_and_retry_on_rate_limit',
+            self.wait_and_retry_on_rate_limit)
+
+        with codecs.open(self.settings_file, 'wb', 'utf8') as configfile:
+            self.config.write(configfile)
+
+# make sure the basedir is cached, in case we're on Windows running a
+# script from frozen binary
+ComicTaggerSettings.baseDir()

comictaggerlib/settingswindow.py

@@ -0,0 +1,270 @@
+"""A PyQT4 dialog to enter app settings"""
+
+# Copyright 2012-2014 Anthony Beville
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import platform
+import os
+import sys
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from .settings import ComicTaggerSettings
+from .comicvinecacher import ComicVineCacher
+from .comicvinetalker import ComicVineTalker
+from .imagefetcher import ImageFetcher
+from . import utils
+
+
+windowsRarHelp = """
+                 <html><head/><body><p>To write to CBR/RAR archives,
+                 you will need to have the tools from
+                 <span style=" text-decoration: underline; color:#0000ff;">
+                 <a href="http://www.win-rar.com/download.html">WINRar</a></span>
+                 installed. (ComicTagger only uses the command-line rar tool,
+                 which is free to use.)</p></body></html>
+                """
+
+linuxRarHelp = """
+               <html><head/><body><p>To write to CBR/RAR archives,
+               you will need to have the shareware rar tool from RARLab installed.
+               Your package manager should have rar (e.g. "apt-get install rar"). If not, download it
+               <span style=" text-decoration: underline; color:#0000ff;">
+               <a href="https://www.rarlab.com/download.htm">here</a></span>,
+               and install in your path. </p></body></html>
+               """
+               
+macRarHelp = """
+                 <html><head/><body><p>To write to CBR/RAR archives,
+                 you will need the rar tool.  The easiest way to get this is
+                 to install <span style=" text-decoration: underline; color:#0000ff;">
+                 <a href="https://brew.sh/">homebrew</a></span>.
+                 </p>Once homebrew is installed, run: <b>brew install caskroom/cask/rar</b></body></html>  
+                """
+
+class SettingsWindow(QtWidgets.QDialog):
+
+    def __init__(self, parent, settings):
+        super(SettingsWindow, self).__init__(parent)
+
+        uic.loadUi(ComicTaggerSettings.getUIFile('settingswindow.ui'), self)
+
+        self.setWindowFlags(self.windowFlags() &
+                            ~QtCore.Qt.WindowContextHelpButtonHint)
+
+        self.settings = settings
+        self.name = "Settings"        
+            
+        if platform.system() == "Windows":
+            self.lblRarHelp.setText(windowsRarHelp)
+
+        elif platform.system() == "Linux":
+            self.lblRarHelp.setText(linuxRarHelp)
+
+        elif platform.system() == "Darwin":
+            self.leRarExePath.setReadOnly(False)
+                     
+            self.lblRarHelp.setText(macRarHelp)
+            self.name = "Preferences"
+
+        self.setWindowTitle("ComicTagger " + self.name)
+        self.lblDefaultSettings.setText(
+            "Revert to default " + self.name.lower())
+        self.btnResetSettings.setText("Default " + self.name)
+
+        nldtTip = (
+            """<html>The <b>Default Name Length Match Tolerance</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The higher
+                it is, the more likely to have a good match, but each search will take longer and
+                use more bandwidth. Too low, and only the very closest lexical matches will be
+                explored.</html>""")
+
+        self.leNameLengthDeltaThresh.setToolTip(nldtTip)
+
+        pblTip = (
+            """<html>
+            The <b>Publisher Blacklist</b> is for eliminating automatic matches to certain publishers
+            that you know are incorrect. Useful for avoiding international re-prints with same
+            covers or series names. Enter publisher names separated by commas.
+            </html>"""
+        )
+        self.tePublisherBlacklist.setToolTip(pblTip)
+
+        validator = QtGui.QIntValidator(1, 4, self)
+        self.leIssueNumPadding.setValidator(validator)
+
+        validator = QtGui.QIntValidator(0, 99, self)
+        self.leNameLengthDeltaThresh.setValidator(validator)
+
+        self.settingsToForm()
+
+        self.btnBrowseRar.clicked.connect(self.selectRar)
+        self.btnClearCache.clicked.connect(self.clearCache)
+        self.btnResetSettings.clicked.connect(self.resetSettings)
+        self.btnTestKey.clicked.connect(self.testAPIKey)
+
+    def settingsToForm(self):
+
+        # Copy values from settings to form
+        self.leRarExePath.setText(self.settings.rar_exe_path)
+        self.leNameLengthDeltaThresh.setText(
+            str(self.settings.id_length_delta_thresh))
+        self.tePublisherBlacklist.setPlainText(
+            self.settings.id_publisher_blacklist)
+
+        if self.settings.check_for_new_version:
+            self.cbxCheckForNewVersion.setCheckState(QtCore.Qt.Checked)
+
+        if self.settings.parse_scan_info:
+            self.cbxParseScanInfo.setCheckState(QtCore.Qt.Checked)
+
+        if self.settings.use_series_start_as_volume:
+            self.cbxUseSeriesStartAsVolume.setCheckState(QtCore.Qt.Checked)
+        if self.settings.clear_form_before_populating_from_cv:
+            self.cbxClearFormBeforePopulating.setCheckState(QtCore.Qt.Checked)
+        if self.settings.remove_html_tables:
+            self.cbxRemoveHtmlTables.setCheckState(QtCore.Qt.Checked)
+        self.leKey.setText(str(self.settings.cv_api_key))
+
+        if self.settings.assume_lone_credit_is_primary:
+            self.cbxAssumeLoneCreditIsPrimary.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_characters_to_tags:
+            self.cbxCopyCharactersToTags.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_teams_to_tags:
+            self.cbxCopyTeamsToTags.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_locations_to_tags:
+            self.cbxCopyLocationsToTags.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_storyarcs_to_tags:
+            self.cbxCopyStoryArcsToTags.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_notes_to_comments:
+            self.cbxCopyNotesToComments.setCheckState(QtCore.Qt.Checked)
+        if self.settings.copy_weblink_to_comments:
+            self.cbxCopyWebLinkToComments.setCheckState(QtCore.Qt.Checked)
+        if self.settings.apply_cbl_transform_on_cv_import:
+            self.cbxApplyCBLTransformOnCVIMport.setCheckState(
+                QtCore.Qt.Checked)
+        if self.settings.apply_cbl_transform_on_bulk_operation:
+            self.cbxApplyCBLTransformOnBatchOperation.setCheckState(
+                QtCore.Qt.Checked)
+
+        self.leRenameTemplate.setText(self.settings.rename_template)
+        self.leIssueNumPadding.setText(
+            str(self.settings.rename_issue_number_padding))
+        if self.settings.rename_use_smart_string_cleanup:
+            self.cbxSmartCleanup.setCheckState(QtCore.Qt.Checked)
+        if self.settings.rename_extension_based_on_archive:
+            self.cbxChangeExtension.setCheckState(QtCore.Qt.Checked)
+
+    def accept(self):
+
+        # Copy values from form to settings and save
+        self.settings.rar_exe_path = str(self.leRarExePath.text())
+        
+        # make sure rar program is now in the path for the rar class
+        if self.settings.rar_exe_path:
+            utils.addtopath(os.path.dirname(self.settings.rar_exe_path))
+            
+        if not str(self.leNameLengthDeltaThresh.text()).isdigit():
+            self.leNameLengthDeltaThresh.setText("0")
+
+        if not str(self.leIssueNumPadding.text()).isdigit():
+            self.leIssueNumPadding.setText("0")
+
+        self.settings.check_for_new_version = self.cbxCheckForNewVersion.isChecked()
+
+        self.settings.id_length_delta_thresh = int(
+            self.leNameLengthDeltaThresh.text())
+        self.settings.id_publisher_blacklist = str(
+            self.tePublisherBlacklist.toPlainText())
+
+        self.settings.parse_scan_info = self.cbxParseScanInfo.isChecked()
+
+        self.settings.use_series_start_as_volume = self.cbxUseSeriesStartAsVolume.isChecked()
+        self.settings.clear_form_before_populating_from_cv = self.cbxClearFormBeforePopulating.isChecked()
+        self.settings.remove_html_tables = self.cbxRemoveHtmlTables.isChecked()
+        self.settings.cv_api_key = str(self.leKey.text())
+        ComicVineTalker.api_key = self.settings.cv_api_key.strip()
+        self.settings.assume_lone_credit_is_primary = self.cbxAssumeLoneCreditIsPrimary.isChecked()
+        self.settings.copy_characters_to_tags = self.cbxCopyCharactersToTags.isChecked()
+        self.settings.copy_teams_to_tags = self.cbxCopyTeamsToTags.isChecked()
+        self.settings.copy_locations_to_tags = self.cbxCopyLocationsToTags.isChecked()
+        self.settings.copy_storyarcs_to_tags = self.cbxCopyStoryArcsToTags.isChecked()
+        self.settings.copy_notes_to_comments = self.cbxCopyNotesToComments.isChecked()
+        self.settings.copy_weblink_to_comments = self.cbxCopyWebLinkToComments.isChecked()
+        self.settings.apply_cbl_transform_on_cv_import = self.cbxApplyCBLTransformOnCVIMport.isChecked()
+        self.settings.apply_cbl_transform_on_bulk_operation = self.cbxApplyCBLTransformOnBatchOperation.isChecked()
+
+        self.settings.rename_template = str(self.leRenameTemplate.text())
+        self.settings.rename_issue_number_padding = int(
+            self.leIssueNumPadding.text())
+        self.settings.rename_use_smart_string_cleanup = self.cbxSmartCleanup.isChecked()
+        self.settings.rename_extension_based_on_archive = self.cbxChangeExtension.isChecked()
+
+        self.settings.save()
+        QtWidgets.QDialog.accept(self)
+            
+    def selectRar(self):
+        self.selectFile(self.leRarExePath, "RAR")
+
+    def clearCache(self):
+        ImageFetcher().clearCache()
+        ComicVineCacher().clearCache()
+        QtWidgets.QMessageBox.information(
+            self, self.name, "Cache has been cleared.")
+
+    def testAPIKey(self):
+        if ComicVineTalker().testKey(str(self.leKey.text()).strip()):
+            QtWidgets.QMessageBox.information(
+                self, "API Key Test", "Key is valid!")
+        else:
+            QtWidgets.QMessageBox.warning(
+                self, "API Key Test", "Key is NOT valid.")
+
+    def resetSettings(self):
+        self.settings.reset()
+        self.settingsToForm()
+        QtWidgets.QMessageBox.information(
+            self,
+            self.name,
+            self.name +
+            " have been returned to default values.")
+
+    def selectFile(self, control, name):
+
+        dialog = QtWidgets.QFileDialog(self)
+        dialog.setFileMode(QtWidgets.QFileDialog.ExistingFile)
+
+        if platform.system() == "Windows":
+            if name == "RAR":
+                filter = self.tr("Rar Program (Rar.exe)")
+            else:
+                filter = self.tr("Libraries (*.dll)")
+            dialog.setNameFilter(filter)
+        else:
+            # QtCore.QDir.Executable | QtCore.QDir.Files)
+            dialog.setFilter(QtCore.QDir.Files)
+            pass
+
+        dialog.setDirectory(os.path.dirname(str(control.text())))
+        if name == "RAR":
+            dialog.setWindowTitle("Find " + name + " program")
+        else:
+             dialog.setWindowTitle("Find " + name + " library")
+             
+        if (dialog.exec_()):
+            fileList = dialog.selectedFiles()
+            control.setText(str(fileList[0]))
+
+    def showRenameTab(self):
+        self.tabWidget.setCurrentIndex(5)

comictaggerlib/ui/autotagmatchwindow.ui

@@ -0,0 +1,174 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>dialogMatchSelect</class>
+ <widget class="QDialog" name="dialogMatchSelect">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>943</width>
+    <height>467</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Select Match</string>
+  </property>
+  <layout class="QGridLayout" name="gridLayout">
+   <item row="0" column="0">
+    <layout class="QVBoxLayout" name="verticalLayout">
+     <item>
+      <layout class="QHBoxLayout" name="horizontalLayout">
+       <item>
+        <widget class="QWidget" name="archiveCoverContainer" native="true">
+         <property name="minimumSize">
+          <size>
+           <width>200</width>
+           <height>350</height>
+          </size>
+         </property>
+         <property name="maximumSize">
+          <size>
+           <width>200</width>
+           <height>350</height>
+          </size>
+         </property>
+        </widget>
+       </item>
+       <item>
+        <widget class="QSplitter" name="splitter">
+         <property name="sizePolicy">
+          <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+           <horstretch>0</horstretch>
+           <verstretch>0</verstretch>
+          </sizepolicy>
+         </property>
+         <property name="orientation">
+          <enum>Qt::Vertical</enum>
+         </property>
+         <property name="childrenCollapsible">
+          <bool>false</bool>
+         </property>
+         <widget class="QTableWidget" name="twList">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>7</verstretch>
+           </sizepolicy>
+          </property>
+          <property name="selectionMode">
+           <enum>QAbstractItemView::SingleSelection</enum>
+          </property>
+          <property name="selectionBehavior">
+           <enum>QAbstractItemView::SelectRows</enum>
+          </property>
+          <property name="rowCount">
+           <number>0</number>
+          </property>
+          <property name="columnCount">
+           <number>4</number>
+          </property>
+          <attribute name="horizontalHeaderStretchLastSection">
+           <bool>true</bool>
+          </attribute>
+          <attribute name="verticalHeaderVisible">
+           <bool>false</bool>
+          </attribute>
+          <column>
+           <property name="text">
+            <string>Series</string>
+           </property>
+          </column>
+          <column>
+           <property name="text">
+            <string>Publisher</string>
+           </property>
+          </column>
+          <column>
+           <property name="text">
+            <string>Date</string>
+           </property>
+          </column>
+          <column>
+           <property name="text">
+            <string>Title</string>
+           </property>
+          </column>
+         </widget>
+         <widget class="QTextEdit" name="teDescription">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>3</verstretch>
+           </sizepolicy>
+          </property>
+         </widget>
+        </widget>
+       </item>
+       <item>
+        <widget class="QWidget" name="altCoverContainer" native="true">
+         <property name="minimumSize">
+          <size>
+           <width>200</width>
+           <height>350</height>
+          </size>
+         </property>
+         <property name="maximumSize">
+          <size>
+           <width>200</width>
+           <height>350</height>
+          </size>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </item>
+     <item>
+      <widget class="QDialogButtonBox" name="buttonBox">
+       <property name="orientation">
+        <enum>Qt::Horizontal</enum>
+       </property>
+       <property name="standardButtons">
+        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>accepted()</signal>
+   <receiver>dialogMatchSelect</receiver>
+   <slot>accept()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>248</x>
+     <y>254</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>157</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>rejected()</signal>
+   <receiver>dialogMatchSelect</receiver>
+   <slot>reject()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>316</x>
+     <y>260</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>286</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
+</ui>

comictaggerlib/ui/autotagprogresswindow.ui

@@ -21,6 +21,44 @@
   </property>
   <layout class="QGridLayout" name="gridLayout">
    <item row="0" column="1">
+    <widget class="QWidget" name="archiveCoverContainer">
+     <property name="sizePolicy">
+      <sizepolicy hsizetype="Fixed" vsizetype="Expanding">
+       <horstretch>0</horstretch>
+       <verstretch>0</verstretch>
+      </sizepolicy>
+     </property>
+     <property name="minimumSize">
+      <size>
+       <width>110</width>
+       <height>165</height>
+      </size>
+     </property>
+     <property name="maximumSize">
+      <size>
+       <width>110</width>
+       <height>165</height>
+      </size>
+     </property>
+    </widget>
+   </item>
+   <item row="0" column="4">
+    <widget class="QWidget" name="testCoverContainer">
+     <property name="minimumSize">
+      <size>
+       <width>110</width>
+       <height>165</height>
+      </size>
+     </property>
+     <property name="maximumSize">
+      <size>
+       <width>110</width>
+       <height>165</height>
+      </size>
+     </property>
+    </widget>
+   </item>
+   <item row="0" column="2">
     <layout class="QVBoxLayout" name="verticalLayout">
      <item>
       <widget class="QProgressBar" name="progressBar">
@@ -66,50 +104,6 @@
      </item>
     </layout>
    </item>
-   <item row="0" column="0">
-    <widget class="QLabel" name="lblArchive">
-     <property name="sizePolicy">
-      <sizepolicy hsizetype="Fixed" vsizetype="Expanding">
-       <horstretch>0</horstretch>
-       <verstretch>0</verstretch>
-      </sizepolicy>
-     </property>
-     <property name="minimumSize">
-      <size>
-       <width>110</width>
-       <height>165</height>
-      </size>
-     </property>
-     <property name="maximumSize">
-      <size>
-       <width>110</width>
-       <height>165</height>
-      </size>
-     </property>
-     <property name="text">
-      <string>TextLabel</string>
-     </property>
-    </widget>
-   </item>
-   <item row="0" column="2">
-    <widget class="QLabel" name="lblTest">
-     <property name="minimumSize">
-      <size>
-       <width>110</width>
-       <height>165</height>
-      </size>
-     </property>
-     <property name="maximumSize">
-      <size>
-       <width>110</width>
-       <height>165</height>
-      </size>
-     </property>
-     <property name="text">
-      <string>TextLabel</string>
-     </property>
-    </widget>
-   </item>
   </layout>
  </widget>
  <resources/>

comictaggerlib/ui/autotagstartwindow.ui

@@ -0,0 +1,239 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>dialogExport</class>
+ <widget class="QDialog" name="dialogExport">
+  <property name="windowModality">
+   <enum>Qt::NonModal</enum>
+  </property>
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>519</width>
+    <height>378</height>
+   </rect>
+  </property>
+  <property name="sizePolicy">
+   <sizepolicy hsizetype="Preferred" vsizetype="MinimumExpanding">
+    <horstretch>0</horstretch>
+    <verstretch>0</verstretch>
+   </sizepolicy>
+  </property>
+  <property name="windowTitle">
+   <string>Auto-Tag</string>
+  </property>
+  <property name="modal">
+   <bool>false</bool>
+  </property>
+  <layout class="QGridLayout" name="gridLayout_2">
+   <item row="0" column="0">
+    <widget class="QLabel" name="label">
+     <property name="sizePolicy">
+      <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
+       <horstretch>0</horstretch>
+       <verstretch>0</verstretch>
+      </sizepolicy>
+     </property>
+     <property name="text">
+      <string/>
+     </property>
+     <property name="wordWrap">
+      <bool>true</bool>
+     </property>
+    </widget>
+   </item>
+   <item row="1" column="0">
+    <layout class="QGridLayout" name="gridLayout">
+     <item row="6" column="0">
+      <widget class="QCheckBox" name="cbxSpecifySearchString">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Specify series search string for all selected archives:</string>
+       </property>
+      </widget>
+     </item>
+     <item row="0" column="0">
+      <widget class="QCheckBox" name="cbxSaveOnLowConfidence">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Save on low confidence match</string>
+       </property>
+      </widget>
+     </item>
+     <item row="4" column="0">
+      <widget class="QCheckBox" name="cbxIgnoreLeadingDigitsInFilename">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Ignore leading (sequence) numbers in filename</string>
+       </property>
+      </widget>
+     </item>
+     <item row="5" column="0">
+      <widget class="QCheckBox" name="cbxRemoveAfterSuccess">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Remove archives from list after successful tagging</string>
+       </property>
+      </widget>
+     </item>
+     <item row="3" column="0">
+      <widget class="QCheckBox" name="cbxWaitForRateLimit">
+       <property name="text">
+        <string>Wait and retry when Comic Vine rate limit is exceeded (experimental)</string>
+       </property>
+      </widget>
+     </item>
+     <item row="1" column="0">
+      <widget class="QCheckBox" name="cbxDontUseYear">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Don't use publication year in indentification process</string>
+       </property>
+      </widget>
+     </item>
+     <item row="2" column="0">
+      <widget class="QCheckBox" name="cbxAssumeIssueOne">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>If no issue number, assume &quot;1&quot;</string>
+       </property>
+      </widget>
+     </item>
+     <item row="10" column="0">
+      <widget class="QLineEdit" name="leNameLengthMatchTolerance">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="maximumSize">
+        <size>
+         <width>50</width>
+         <height>16777215</height>
+        </size>
+       </property>
+      </widget>
+     </item>
+     <item row="7" column="0">
+      <widget class="QLineEdit" name="leSearchString">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+      </widget>
+     </item>
+     <item row="8" column="0">
+      <widget class="QLabel" name="label_3">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Preferred" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Adjust Name Length Match Tolerance:</string>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+   <item row="2" column="0">
+    <widget class="QLabel" name="label_2">
+     <property name="sizePolicy">
+      <sizepolicy hsizetype="Preferred" vsizetype="Fixed">
+       <horstretch>0</horstretch>
+       <verstretch>0</verstretch>
+      </sizepolicy>
+     </property>
+     <property name="minimumSize">
+      <size>
+       <width>40</width>
+       <height>0</height>
+      </size>
+     </property>
+     <property name="text">
+      <string/>
+     </property>
+    </widget>
+   </item>
+   <item row="4" column="0">
+    <widget class="QDialogButtonBox" name="buttonBox">
+     <property name="orientation">
+      <enum>Qt::Horizontal</enum>
+     </property>
+     <property name="standardButtons">
+      <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+     </property>
+    </widget>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>accepted()</signal>
+   <receiver>dialogExport</receiver>
+   <slot>accept()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>346</x>
+     <y>187</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>277</x>
+     <y>104</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>rejected()</signal>
+   <receiver>dialogExport</receiver>
+   <slot>reject()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>346</x>
+     <y>187</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>277</x>
+     <y>104</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
+</ui>

comictaggerlib/ui/coverimagewidget.ui

@@ -0,0 +1,123 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>coverImageWidget</class>
+ <widget class="QWidget" name="coverImageWidget">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>292</width>
+    <height>353</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Form</string>
+  </property>
+  <layout class="QGridLayout" name="gridLayout">
+   <property name="horizontalSpacing">
+    <number>0</number>
+   </property>
+   <property name="verticalSpacing">
+    <number>4</number>
+   </property>
+   <property name="margin">
+    <number>0</number>
+   </property>
+   <item row="1" column="0">
+    <layout class="QHBoxLayout" name="horizontalLayout">
+     <property name="spacing">
+      <number>2</number>
+     </property>
+     <item>
+      <widget class="QPushButton" name="btnLeft">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="maximumSize">
+        <size>
+         <width>30</width>
+         <height>16777215</height>
+        </size>
+       </property>
+       <property name="text">
+        <string/>
+       </property>
+      </widget>
+     </item>
+     <item>
+      <widget class="QLabel" name="label">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="MinimumExpanding" vsizetype="Preferred">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string/>
+       </property>
+       <property name="alignment">
+        <set>Qt::AlignCenter</set>
+       </property>
+      </widget>
+     </item>
+     <item>
+      <widget class="QPushButton" name="btnRight">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="maximumSize">
+        <size>
+         <width>30</width>
+         <height>16777215</height>
+        </size>
+       </property>
+       <property name="text">
+        <string/>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+   <item row="0" column="0">
+    <widget class="QFrame" name="frame">
+     <property name="sizePolicy">
+      <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+       <horstretch>0</horstretch>
+       <verstretch>0</verstretch>
+      </sizepolicy>
+     </property>
+     <property name="frameShape">
+      <enum>QFrame::NoFrame</enum>
+     </property>
+     <property name="frameShadow">
+      <enum>QFrame::Raised</enum>
+     </property>
+     <widget class="QLabel" name="lblImage">
+      <property name="geometry">
+       <rect>
+        <x>60</x>
+        <y>50</y>
+        <width>91</width>
+        <height>61</height>
+       </rect>
+      </property>
+      <property name="toolTip">
+       <string>Double-click to expand</string>
+      </property>
+      <property name="text">
+       <string>TextLabel</string>
+      </property>
+     </widget>
+    </widget>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections/>
+</ui>