dos-ified release_notes file

git-svn-id: http://comictagger.googlecode.com/svn/trunk@728 6c5673fe-1810-88d6-992b-cd32ca31540c

MANIFEST.in

@@ -1,2 +1,4 @@
-include readme.txt
+include README.txt
 include release_notes.txt
+include requirements.txt
+recursive-include scripts *.py *.txt

Makefile

@@ -1,4 +1,4 @@
-TAGGER_BASE := $(HOME)/Dropbox/tagger/comictagger
+TAGGER_BASE ?= $(HOME)/Dropbox/tagger/comictagger
 TAGGER_SRC := $(TAGGER_BASE)/comictaggerlib
 VERSION_STR := $(shell grep version $(TAGGER_SRC)/ctversion.py| cut -d= -f2 | sed 's/\"//g')
 PASSWORD    := $(shell cat $(TAGGER_BASE)/project_password.txt)  
@@ -7,51 +7,55 @@ all: clean
 
 clean:
 	rm -rf *~ *.pyc *.pyo
-	cd comictagger; rm -f *~ *.pyc *.pyo
-	sudo rm -rf dist MANIFEST
+	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
 	make -C windows clean
-
-zip:
-	cd release; \
-		rm -rf *zip comictagger-src-$(VERSION_STR) ;  \
-		svn export https://comictagger.googlecode.com/svn/trunk/ comictagger-src-$(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
+	rm -rf build
 
 pydist:
-	python setup.py sdist --formats=gztar,zip
+	mkdir -p release
+	rm -f release/*.zip
+	python setup.py sdist --formats=zip  #,gztar
+	mv dist/comictagger-$(VERSION_STR).zip release
+	@echo When satisfied with release, do this:
+	@echo make svn_tag
 
 remove_test_install:
 	sudo rm -rf /usr/local/bin/comictagger.py
 	sudo rm -rf /usr/local/lib/python2.7/dist-packages/comictagger*
 	
-deb:
-	fpm -s python -t deb \
-		-n 'comictagger' \
-		--category 'utilities' \
-		--maintainer 'comictagger@gmail.com' \
-		--after-install debian_scripts/after_install.sh \
-		--before-remove debian_scripts/before_remove.sh \
-		-d 'python >= 2.6' \
-		-d 'python < 2.8' \
-		-d 'python-imaging >= 1.1.7' \
-		-d 'python-bs4 >= 4.1' \
-		setup.py 
-
-		# For now, don't require PyQt, since command-line is available without it
-		#-d 'python-qt4 >= 4.8' 
-
+#deb:
+#	fpm -s python -t deb \
+#		-n 'comictagger' \
+#		--category 'utilities' \
+#		--maintainer 'comictagger@gmail.com' \
+#		--after-install debian_scripts/after_install.sh \
+#		--before-remove debian_scripts/before_remove.sh \
+#		-d 'python >= 2.6' \
+#		-d 'python < 2.8' \
+#		-d 'python-imaging' \
+#		-d 'python-bs4' \
+#		--deb-suggests 'rar' \
+#		--deb-suggests 'unrar-free' \
+#		--python-install-bin /usr/share/comictagger \
+#		--python-install-lib /usr/share/comictagger \
+#		setup.py 
+#
+#		# For now, don't require PyQt, since command-line is available without it
+#		#-d 'python-qt4 >= 4.8' 
+		
+upload:
+	#$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR) Source" -l Featured,Type-Source -u beville -w $(PASSWORD) "release/comictagger-$(VERSION_STR).zip"
+	#$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR)  Mac OS X" -l Featured,Type-Archive -u beville -w $(PASSWORD) "release/ComicTagger-$(VERSION_STR).dmg"
+	#$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR)  Windows" -l Featured,Type-Installer -u beville -w $(PASSWORD) "release/ComicTagger v$(VERSION_STR).exe"
+	python setup.py register
+	python setup.py sdist --formats=zip upload
+ 
 svn_tag:
 	svn copy https://comictagger.googlecode.com/svn/trunk \
-      https://comictagger.googlecode.com/svn/tags/$(VERSION_STR) -m "Release $(VERSION_STR)"
+		https://comictagger.googlecode.com/svn/tags/$(VERSION_STR) -m "Release $(VERSION_STR)"
 
-upload:
-	$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR) Source" -l Featured,Type-Source -u beville -w $(PASSWORD) "release/comictagger-src-$(VERSION_STR).zip"
-	$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR)  Mac OS X" -l Featured,Type-Archive -u beville -w $(PASSWORD) "release/ComicTagger-$(VERSION_STR).dmg"
-	$(UPLOAD_TOOL) -p comictagger -s "ComicTagger $(VERSION_STR)  Windows" -l Featured,Type-Installer -u beville -w $(PASSWORD) "release/ComicTagger v$(VERSION_STR).exe"

README.txt

@@ -1,4 +1,4 @@
-ComicTagger is a multi-platform app for writing metadata to comic archives, written in Python and PyQt.
+ComicTagger is a multi-platform app for writing metadata to digital comics, written in Python and PyQt.
 
 Features:
 
@@ -7,16 +7,17 @@ Features:
 * Uses image processing to automatically match a given archive with the correct issue data
 * Batch processing in the GUI for tagging hundreds or more comics at a time
 * Reads and writes multiple tagging schemes ( ComicBookLover and ComicRack, with more planned).
-* Reads and writes RAR, Zip, and folder archives (external tools needed for writing RAR)
-* Command line interface (CLI) on all platforms (including Windows), which supports batch operations, and which can be used in native scripts for complex operations. For example, to scrape and tag a folder, just one line
-	ComicTagger -s -o -f -t cr -v -i --nooverwrite *.cb?
+* Reads and writes RAR and Zip archives (external tools needed for writing RAR)
+* Command line interface (CLI) on all platforms (including Windows), which supports batch operations, and which can be used in native scripts for complex operations. For example, to recusrively scrape and tag all archives in a folder
+	comictagger.py -R -s -o -f -t cr -v -i --nooverwrite /path/to/comics/
 
 For details, screenshots, release notes, and more, visit http://code.google.com/p/comictagger/
 
 Requires:
 
 * python 2.6 or 2.7
-* python imaging (PIL) >= 1.1.7
+* configparser
+* python imaging (PIL) >= 1.1.6
 * beautifulsoup > 4.1
     
 Optional requirement (for GUI):
@@ -27,4 +28,4 @@ Install and run:
 
 * ComicTagger can be run directly from this directory, using the launcher script "comictagger.py"
 
-* To install on your system use:  "python setup.py install".  Make note in the output where comictagger.py goes!
+* To install on your system use:  "python setup.py install".  Take note in the output where comictagger.py goes!

comictagger.py

@@ -1,4 +1,5 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 from comictaggerlib.main import ctmain
 
-ctmain()			
+if __name__ == '__main__':
+	ctmain()

comictaggerlib/UnRAR2/__init__.py

@@ -33,7 +33,7 @@ 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'
+__version__ = '0.99.3'
 
 try:
     WindowsError

comictaggerlib/UnRAR2/test_UnRAR2.py

@@ -12,13 +12,11 @@ def cleanup(dir='test'):
             os.removedirs(os.path.join(path, dir))
 
 
-
-
-
-# reuse RarArchive object, en
+# basic test
 cleanup()
 rarc = UnRAR2.RarFile('test.rar')
 rarc.infolist()
+assert rarc.comment == "This is a test."
 for info in rarc.infoiter():
     saveinfo = info
     assert (str(info)=="""<RarInfo "test" in "test.rar">""")
@@ -98,7 +96,8 @@ 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()
+rarc = UnRAR2.RarFile('test_protected_files.rar', password="protected")
+rarc.extract()
 assert os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
 cleanup()
 errored = False

comictaggerlib/UnRAR2/unix.py

@@ -33,6 +33,7 @@ from rar_exceptions import *
 class UnpackerNotInstalled(Exception): pass
 
 rar_executable_cached = None
+rar_executable_version = None
 
 def call_unrar(params):
     "Calls rar/unrar command line executable, returns stdout pipe"
@@ -59,10 +60,10 @@ def call_unrar(params):
 class RarFileImplementation(object):
 
     def init(self, password=None):
+        global rar_executable_version
         self.password = password
         
         
-
         stdoutdata, stderrdata = self.call('v', []).communicate()
         
         for line in stderrdata.splitlines():
@@ -73,18 +74,42 @@ class RarFileImplementation(object):
         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
+        while not (line.startswith('UNRAR')):
             line = source.next()
-        while not line.startswith('Pathname/Comment'):
-            accum.append(line.rstrip('\n'))
+        signature = line
+        # The code below is mighty flaky
+        # and will probably crash on localized versions of RAR
+        # but I see no safe way to rewrite it using a CLI tool
+        if signature.startswith("UNRAR 4"):
+            rar_executable_version = 4
+            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:] # strip out "Comment:" part
+                self.comment = '\n'.join(accum[:-1])
+            else:
+                self.comment = None
+        elif signature.startswith("UNRAR 5"):
+            rar_executable_version = 5
             line = source.next()
-        if len(accum):
-            accum[0] = accum[0][9:]
-            self.comment = '\n'.join(accum[:-1])
+            while not line.startswith('Archive:'):
+                if line.strip().endswith('is not RAR archive'):
+                    raise InvalidRARArchive
+                accum.append(line.rstrip('\n'))
+                line = source.next()
+            if len(accum):
+                self.comment = '\n'.join(accum[:-1]).strip()
+            else:
+                self.comment = None
         else:
-            self.comment = None
+            raise UnpackerNotInstalled("Unsupported RAR version, expected 4.x or 5.x, found: " 
+                    + signature.split(" ")[1])
+                
                 
     def escaped_password(self):
         return '-' if self.password == None else self.password
@@ -97,7 +122,8 @@ class RarFileImplementation(object):
 
     def infoiter(self):
         
-        stdoutdata, stderrdata = self.call('v', ['c-']).communicate()
+        command = "v" if rar_executable_version == 4 else "l"
+        stdoutdata, stderrdata = self.call(command, ['c-']).communicate()
         
         for line in stderrdata.splitlines():
             if line.strip().startswith("Cannot open"):
@@ -106,33 +132,48 @@ class RarFileImplementation(object):
         accum = []
         source = iter(stdoutdata.splitlines())
         line = ''
-        while not line.startswith('--------------'):
+        while not line.startswith('-----------'):
             if line.strip().endswith('is not RAR archive'):
                 raise InvalidRARArchive
-            if line.find("CRC failed")>=0:
+            if line.startswith("CRC failed") or line.startswith("Checksum error"):
                 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:
+        if rar_executable_version == 4:
+            while not line.startswith('-----------'):
+                accum.append(line)
+                if len(accum)==2:
+                    data = {}
+                    data['index'] = i
+                    # asterisks mark password-encrypted files
+                    data['filename'] = accum[0].strip().lstrip("*") # asterisks marks password-encrypted files
+                    fields = re_spaces.split(accum[1].strip())
+                    data['size'] = int(fields[0])
+                    attr = fields[5]
+                    data['isdir'] = 'd' in attr.lower()
+                    data['datetime'] = time.strptime(fields[3]+" "+fields[4], '%d-%m-%y %H:%M')
+                    data['comment'] = None
+                    yield data
+                    accum = []
+                    i += 1
+                line = source.next()
+        elif rar_executable_version == 5:
+            while not line.startswith('-----------'):
+                fields = line.strip().lstrip("*").split()
                 data = {}
                 data['index'] = i
-                #!!!ATB - changed this because it was choking when a folder or file started with a space.
-                #!!!      now, just strip off the first char in the string
-                data['filename'] = accum[0].rstrip()[1:]
-                info = re_spaces.split(accum[1].strip())
-                data['size'] = int(info[0])
-                attr = info[5]
+                data['filename'] = " ".join(fields[4:])
+                data['size'] = int(fields[1])
+                attr = fields[0]
                 data['isdir'] = 'd' in attr.lower()
-                data['datetime'] = time.strptime(info[3]+" "+info[4], '%d-%m-%y %H:%M')
+                data['datetime'] = time.strptime(fields[2]+" "+fields[3], '%d-%m-%y %H:%M')
                 data['comment'] = None
                 yield data
-                accum = []
                 i += 1
-            line = source.next()
+                line = source.next()
+            
 
     def read_files(self, checker):
         res = []
@@ -153,7 +194,7 @@ class RarFileImplementation(object):
         if overwrite:
             options.append('o+')
         else:
-			options.append('o-')
+            options.append('o-')
         if not path.endswith(os.sep):
             path += os.sep
         names = []
@@ -167,7 +208,7 @@ class RarFileImplementation(object):
         names.append(path)
         proc = self.call(command, options, names)
         stdoutdata, stderrdata = proc.communicate()
-        if stderrdata.find("CRC failed")>=0:
+        if stderrdata.find("CRC failed")>=0 or stderrdata.find("Checksum error")>=0:
             raise IncorrectRARPassword  
         return res            
             

comictaggerlib/autotagmatchwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to select from automated issue matches
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -26,7 +26,7 @@ from PyQt4.QtCore import QUrl, pyqtSignal, QByteArray
 
 from imagefetcher import  ImageFetcher
 from settings import ComicTaggerSettings
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 from coverimagewidget import CoverImageWidget
 from comicvinetalker import ComicVineTalker
 import utils
@@ -38,7 +38,7 @@ class AutoTagMatchWindow(QtGui.QDialog):
 	def __init__(self, parent, match_set_list, style, fetch_func):
 		super(AutoTagMatchWindow, self).__init__(parent)
 		
-		uic.loadUi(ComicTaggerSettings.getUIFile('autotagmatchwindow.ui' ), self)
+		uic.loadUi(ComicTaggerSettings.getUIFile('matchselectionwindow.ui' ), self)
 
 		self.altCoverWidget = CoverImageWidget( self.altCoverContainer, CoverImageWidget.AltCoverMode )
 		gridlayout = QtGui.QGridLayout( self.altCoverContainer )
@@ -51,6 +51,7 @@ class AutoTagMatchWindow(QtGui.QDialog):
 		gridlayout.setContentsMargins(0,0,0,0)
 
 		utils.reduceWidgetFontSize( self.twList )		
+		utils.reduceWidgetFontSize( self.teDescription, 1 )
 
 		self.setWindowFlags(self.windowFlags() |
 									  QtCore.Qt.WindowSystemMenuHint |
@@ -132,7 +133,9 @@ class AutoTagMatchWindow(QtGui.QDialog):
 			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
 			self.twList.setItem(row, 2, item)
 
-			item_text = match['issue_title']  
+			item_text = match['issue_title']
+			if item_text is None:
+				item_text = ""
 			item = QtGui.QTableWidgetItem(item_text)			
 			item.setData( QtCore.Qt.ToolTipRole, item_text )
 			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
@@ -159,6 +162,10 @@ class AutoTagMatchWindow(QtGui.QDialog):
 				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

comictaggerlib/autotagprogresswindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to show ID log and progress
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -22,6 +22,7 @@ import sys
 from PyQt4 import QtCore, QtGui, uic
 import os
 from settings import ComicTaggerSettings
+from coverimagewidget import CoverImageWidget
 import utils
 
 class AutoTagProgressWindow(QtGui.QDialog):
@@ -31,8 +32,17 @@ class AutoTagProgressWindow(QtGui.QDialog):
 		super(AutoTagProgressWindow, self).__init__(parent)
 		
 		uic.loadUi(ComicTaggerSettings.getUIFile('autotagprogresswindow.ui' ), self)
-		self.lblTest.setPixmap(QtGui.QPixmap(ComicTaggerSettings.getGraphic('nocover.png')))
-		self.lblArchive.setPixmap(QtGui.QPixmap(ComicTaggerSettings.getGraphic('nocover.png')))
+		
+		self.archiveCoverWidget = CoverImageWidget( self.archiveCoverContainer, CoverImageWidget.DataMode, False )
+		gridlayout = QtGui.QGridLayout( self.archiveCoverContainer )
+		gridlayout.addWidget( self.archiveCoverWidget )
+		gridlayout.setContentsMargins(0,0,0,0)
+
+		self.testCoverWidget = CoverImageWidget( self.testCoverContainer, CoverImageWidget.DataMode, False )
+		gridlayout = QtGui.QGridLayout( self.testCoverContainer )
+		gridlayout.addWidget( self.testCoverWidget )
+		gridlayout.setContentsMargins(0,0,0,0)
+				
 		self.isdone = False
 
 		self.setWindowFlags(self.windowFlags() |
@@ -42,23 +52,16 @@ class AutoTagProgressWindow(QtGui.QDialog):
 		utils.reduceWidgetFontSize( self.textEdit )	
 		
 	def setArchiveImage( self, img_data):
-		self.setCoverImage( img_data, self.lblArchive )
+		self.setCoverImage( img_data, self.archiveCoverWidget)
 
 	def setTestImage( self, img_data):
-		self.setCoverImage( img_data, self.lblTest )
+		self.setCoverImage( img_data, self.testCoverWidget)
 
-	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(ComicTaggerSettings.getGraphic('nocover.png')))
-			label.setScaledContents(True)
+	def setCoverImage( self, img_data , widget):
+		widget.setImageData( img_data )
 		QtCore.QCoreApplication.processEvents()
 		QtCore.QCoreApplication.processEvents()
-			
+	
 	def reject(self):
 		QtGui.QDialog.reject(self)		
 		self.isdone = True

comictaggerlib/autotagstartwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to confirm and set options for auto-tag
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -48,6 +48,17 @@ class AutoTagStartWindow(QtGui.QDialog):
 		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)		
 
 		nlmtTip = (
 			""" <html>The <b>Name Length Match Tolerance</b> is for eliminating automatic
@@ -97,6 +108,13 @@ class AutoTagStartWindow(QtGui.QDialog):
 		self.removeAfterSuccess = self.cbxRemoveAfterSuccess.isChecked()
 		self.nameLengthMatchTolerance = int(self.leNameLengthMatchTolerance.text())
 		
+		#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
+		
 		if self.cbxSpecifySearchString.isChecked():
 			self.searchString = unicode(self.leSearchString.text())
 			if len(self.searchString) == 0:

comictaggerlib/cbltransformer.py

@@ -3,7 +3,7 @@ Class to manage modifying metadata specifically for CBL/CBI
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -74,6 +74,9 @@ class CBLTransformer:
 			
 		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:

comictaggerlib/cli.py

@@ -33,8 +33,8 @@ import locale
 filename_encoding = sys.getfilesystemencoding()
 
 from settings import ComicTaggerSettings
-from options import Options, MetaDataStyle
-from comicarchive import ComicArchive
+from options import Options
+from comicarchive import ComicArchive, MetaDataStyle
 from issueidentifier import IssueIdentifier
 from genericmetadata import GenericMetadata
 from comicvinetalker import ComicVineTalker, ComicVineTalkerException
@@ -92,7 +92,7 @@ def actual_metadata_save( ca, opts, md ):
 	return True
 
 def display_match_set_for_choice( label, match_set, opts, settings ):
-	print "{0} -- {1}:".format(match_set.filename, label )
+	print u"{0} -- {1}:".format(match_set.filename, label )
 
 	# sort match list by year
 	match_set.matches.sort(key=lambda k: k['year'])			
@@ -115,9 +115,7 @@ def display_match_set_for_choice( label, match_set, opts, settings ):
 			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 )
-			if settings.rar_exe_path != "":
-				ca.setExternalRarProgram( settings.rar_exe_path )	
+			ca = ComicArchive( match_set.filename, settings.rar_exe_path )
 			md = create_local_metadata( opts, ca, ca.hasMetadata(opts.data_style) )
 			cv_md = actual_issue_data_fetch(match_set.matches[int(i)], settings)
 			md.overlay( cv_md )
@@ -181,7 +179,8 @@ def cli_mode( opts, settings ):
 	match_results = OnlineMatchResults()
 	
 	for f in opts.file_list:
-		f = f.decode(filename_encoding, 'replace')
+		if type(f) ==  str:
+			f = f.decode(filename_encoding, 'replace')
 		process_file_cli( f, opts, settings, match_results )
 		sys.stdout.flush()
 		
@@ -210,9 +209,7 @@ 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 )	
+	ca = ComicArchive(filename, settings.rar_exe_path)
 	
 	if not os.path.lexists( filename ):
 		print >> sys.stderr,"Cannot find "+ filename
@@ -241,7 +238,7 @@ def process_file_cli( filename, opts, settings, match_results ):
 			brief = ""
 
 			if batch_mode:
-				brief = "{0}: ".format(filename)
+				brief = u"{0}: ".format(filename)
 
 			if ca.isZip():      brief += "ZIP archive    "
 			elif ca.isRar():    brief += "RAR archive    "
@@ -295,21 +292,21 @@ def process_file_cli( filename, opts, settings, match_results ):
 		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 )
+					print u"{0}: Tag removal seemed to fail!".format( filename )
 				else:
-					print "{0}: Removed {1} tags.".format( filename, style_name )
+					print u"{0}: Removed {1} tags.".format( filename, style_name )
 			else:
-				print "{0}: dry-run.  {1} tags not removed".format( filename, style_name )		
+				print u"{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 )
+			print u"{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)
+			print u"{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)
+			print u"{0}: Destination and source are same: {1}.  Nothing to do.".format(filename, dst_style_name)
 			return
 			
 		src_style_name = MetaDataStyle.name[ opts.copy_source ]
@@ -340,7 +337,10 @@ def process_file_cli( filename, opts, settings, match_results ):
 			print u"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:

comictaggerlib/comet.py

@@ -3,7 +3,7 @@ A python class to encapsulate CoMet data
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/comicarchive.py

@@ -3,7 +3,7 @@ A python class to represent a single comic, be it file or folder of images
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -25,6 +25,8 @@ import sys
 import tempfile
 import subprocess
 import platform
+import locale
+
 if platform.system() == "Windows":
 	import _subprocess
 import time
@@ -40,13 +42,18 @@ sys.path.insert(0, os.path.abspath(".") )
 import UnRAR2
 from UnRAR2.rar_exceptions import *
 
-from options import Options, MetaDataStyle
+from settings import ComicTaggerSettings
 from comicinfoxml import ComicInfoXml
 from comicbookinfo import ComicBookInfo
 from comet import CoMet
 from genericmetadata import GenericMetadata, PageType
 from filenameparser import FileNameParser
-from settings import ComicTaggerSettings
+
+class MetaDataStyle:
+	CBI = 0
+	CIX = 1
+	COMET = 2
+	name = [ 'ComicBookLover', 'ComicRack', 'CoMet' ]
 
 class ZipArchiver:
 	
@@ -65,15 +72,16 @@ class ZipArchiver:
 	def readArchiveFile( self, archive_file ):
 		data = ""
 		zf = zipfile.ZipFile( self.path, 'r' )
+
 		try:
 			data = zf.read( archive_file )
 		except zipfile.BadZipfile as e:
-			print >> sys.stderr, "bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
+			print >> sys.stderr, u"bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
 			zf.close()	
 			raise IOError
 		except Exception as e:
 			zf.close()	
-			print >> sys.stderr, "bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
+			print >> sys.stderr, u"bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
 			raise IOError
 		finally:
 			zf.close()
@@ -102,12 +110,16 @@ class ZipArchiver:
 		except:
 			return False
 			
-	def getArchiveFilenameList( self ):		
-		zf = zipfile.ZipFile( self.path, 'r' )
-		namelist = zf.namelist()
-		zf.close()
-		return namelist
-	
+	def getArchiveFilenameList( self ):
+		try:
+			zf = zipfile.ZipFile( self.path, 'r' )
+			namelist = zf.namelist()
+			zf.close()
+			return namelist
+		except Exception as e:
+			print >> sys.stderr, u"Unable to get zipfile list [{0}]: {1}".format(e, self.path)
+			return []
+			
 	# zip helper func
 	def rebuildZipFile( self, exclude_list ):
 		
@@ -215,7 +227,7 @@ class ZipArchiver:
 				if not self.writeZipComment( self.path, comment ):
 					return False
 		except  Exception as e:
-			print >> sys.stderr, "Error while copying to {0}: {1}".format(self.path, e)
+			print >> sys.stderr, u"Error while copying to {0}: {1}".format(self.path, e)
 			return False
 		else:
 			return True
@@ -227,9 +239,9 @@ class ZipArchiver:
 class RarArchiver:
 	
 	devnull = None
-	def __init__( self, path ):
+	def __init__( self, path, rar_exe_path ):
 		self.path = path
-		self.rar_exe_path = None
+		self.rar_exe_path = rar_exe_path
 
 		if RarArchiver.devnull is None:
 			RarArchiver.devnull = open(os.devnull, "w")
@@ -294,22 +306,22 @@ class RarArchiver:
 				entries = rarc.read_files( archive_file )
 
 				if entries[0][0].size != len(entries[0][1]):
-					print >> sys.stderr, "readArchiveFile(): [file is not expected size: {0} vs {1}]  {2}:{3} [attempt # {4}]".format(
+					print >> sys.stderr, u"readArchiveFile(): [file is not expected size: {0} vs {1}]  {2}:{3} [attempt # {4}]".format(
 								entries[0][0].size,len(entries[0][1]), self.path, archive_file, tries)
 					continue
 				
 			except (OSError, IOError) as e:
-				print >> sys.stderr, "readArchiveFile(): [{0}]  {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
+				print >> sys.stderr, u"readArchiveFile(): [{0}]  {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
 				time.sleep(1)
 			except Exception as e:
-				print >> sys.stderr, "Unexpected exception in readArchiveFile(): [{0}] for {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
+				print >> sys.stderr, u"Unexpected exception in readArchiveFile(): [{0}] for {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
 				break
 
 			else:
 				#Success"
 				#entries is a list of of tuples:  ( rarinfo, filedata)
 				if tries > 1:
-					print >> sys.stderr, "Attempted read_files() {0} times".format(tries)
+					print >> sys.stderr, u"Attempted read_files() {0} times".format(tries)
 				if (len(entries) == 1):
 					return entries[0][1]
 				else:
@@ -385,7 +397,7 @@ class RarArchiver:
 						namelist.append( item.filename )
 			
 			except (OSError, IOError) as e:
-				print >> sys.stderr, "getArchiveFilenameList(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
+				print >> sys.stderr, u"getArchiveFilenameList(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
 				time.sleep(1)
 
 			else:
@@ -403,7 +415,7 @@ class RarArchiver:
 				rarc = UnRAR2.RarFile( self.path )
 			
 			except (OSError, IOError) as e:
-				print >> sys.stderr, "getRARObj(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
+				print >> sys.stderr, u"getRARObj(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
 				time.sleep(1)
 
 			else:
@@ -503,20 +515,22 @@ class ComicArchive:
 	class ArchiveType:
 		Zip, Rar, Folder, Unknown = range(4)
     
-	def __init__( self, path ):
+	def __init__( self, path, rar_exe_path=None ):
 		self.path = path
+		
+		self.rar_exe_path = rar_exe_path
 		self.ci_xml_filename = 'ComicInfo.xml'
 		self.comet_default_filename = 'CoMet.xml'
 		self.resetCache()
 		
-		if self.zipTest():
+		if self.rarTest(): 
+			self.archive_type =  self.ArchiveType.Rar
+			self.archiver = RarArchiver( self.path, rar_exe_path=self.rar_exe_path )
+			
+		elif 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 )			
@@ -527,7 +541,7 @@ class ComicArchive:
 		if ComicArchive.logo_data is None:
 			fname = ComicTaggerSettings.getGraphic('nocover.png')
 			with open(fname, 'rb') as fd:
-				ComicArchive.logo_data = fd.read()				
+				ComicArchive.logo_data = fd.read()
 
 	# Clears the cached data
 	def resetCache( self ):
@@ -548,10 +562,6 @@ class ComicArchive:
 	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 )
@@ -578,7 +588,7 @@ class ComicArchive:
 		if self.archive_type == self.ArchiveType.Unknown :
 			return False
 		
-		elif check_rar_status and self.isRar() and self.archiver.rar_exe_path is None:
+		elif check_rar_status and self.isRar() and self.rar_exe_path is None:
 			return False
 			
 		elif not os.access(self.path, os.W_OK):
@@ -603,9 +613,9 @@ class ComicArchive:
 		ext = os.path.splitext(self.path)[1].lower()
 
 		if ( 
-		      ( self.isZip() or  self.isRar() or self.isFolder() )
+		      ( self.isZip() or  self.isRar() ) #or self.isFolder() )
 		      and
-		      ( self.getNumberOfPages() > 2)
+		      ( self.getNumberOfPages() > 0)
 
 			):
 			return True
@@ -666,13 +676,16 @@ class ComicArchive:
 			try:
 				image_data = self.archiver.readArchiveFile( filename )
 			except IOError:
-				print >> sys.stderr, "Error reading in page.  Substituting logo page."
+				print >> sys.stderr, u"Error reading in page.  Substituting logo page."
 				image_data = ComicArchive.logo_data				
 
 		return image_data
 
 	def getPageName( self, index ):
 		
+		if index is None:
+			return None
+		
 		page_list = self.getPageNameList()
 		
 		num_pages = len( page_list )
@@ -681,6 +694,56 @@ class ComicArchive:
 	
 		return  page_list[index]
 
+	def getScannerPageIndex( self ):
+		
+		scanner_page_index = None
+		
+		#make a guess at the scanner page
+		name_list = self.getPageNameList()
+		count = self.getNumberOfPages()
+
+		#too few pages to really know	
+		if count < 5:
+			return None
+
+		# count the length of every filename, and count occurences
+		length_buckets = dict()		
+		for name in name_list:
+			fname =  os.path.split(name)[1]
+			length = len(fname)
+			if length_buckets.has_key( length ):
+				length_buckets[ length ] += 1
+			else:
+				length_buckets[ length ] = 1
+			
+		# sort by most common
+		sorted_buckets = sorted(length_buckets.iteritems(), key=lambda (k,v): (v,k), reverse=True)
+		
+		# statistical mode occurence is first
+		mode_length = sorted_buckets[0][0]
+
+		# we are only going to consider the final image file:
+		final_name = os.path.split(name_list[count-1])[1]
+
+		common_length_list = list()
+		for name in name_list:
+			if len(os.path.split(name)[1]) == mode_length:
+				common_length_list.append( os.path.split(name)[1] )
+
+		prefix = os.path.commonprefix(common_length_list)
+
+		if mode_length <= 7 and prefix == "":
+			#probably all numbers
+			if len(final_name) > mode_length:
+				scanner_page_index = count-1
+
+		# see if the last page doesn't start with the same prefix as most others
+		elif not final_name.startswith(prefix):
+			scanner_page_index = count-1
+
+		return scanner_page_index
+			
+			
 	def getPageNameList( self , sort_list=True):
 		
 		if self.page_list is None:
@@ -689,7 +752,14 @@ class ComicArchive:
 			
 			# 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())
+				def keyfunc(k):
+					#hack to account for some weird scanner ID pages
+					basename=os.path.split(k)[1]
+					if basename < '0':
+						k = os.path.join(os.path.split(k)[0], "z" + basename)
+					return k.lower()
+				
+				files.sort(key=keyfunc)
 			
 			# make a sub-list of image files
 			self.page_list = []
@@ -857,7 +927,7 @@ class ComicArchive:
 		try:
 			raw_comet = self.archiver.readArchiveFile( self.comet_filename )
 		except IOError:
-			print >> sys.stderr, "Error reading in raw CoMet!"
+			print >> sys.stderr, u"Error reading in raw CoMet!"
 			raw_comet = ""
 		return  raw_comet
 		
@@ -908,7 +978,7 @@ class ComicArchive:
 						data = self.archiver.readArchiveFile( n )
 					except:
 						data = ""
-						print >> sys.stderr, "Error reading in Comet XML for validation!"
+						print >> sys.stderr, u"Error reading in Comet XML for validation!"
 					if CoMet().validateString( data ):
 						# since we found it, save it!
 						self.comet_filename = n
@@ -946,7 +1016,7 @@ class ComicArchive:
 
 
 			
-	def metadataFromFilename( self ):
+	def metadataFromFilename( self , parse_scan_info=True):
 		 
 		metadata = GenericMetadata()
 		
@@ -963,6 +1033,9 @@ class ComicArchive:
 			metadata.year = fnp.year
 		if fnp.issue_count != "":
 			metadata.issueCount = fnp.issue_count
+		if parse_scan_info:
+			if fnp.remainder != "":
+				metadata.scanInfo = fnp.remainder
 
 		metadata.isEmpty = False
 

comictaggerlib/comicbookinfo.py

@@ -3,7 +3,7 @@ A python class to encapsulate the ComicBookInfo data
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/comicinfoxml.py

@@ -3,7 +3,7 @@ A python class to encapsulate ComicRack's ComicInfo.xml data
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -89,36 +89,21 @@ class ComicInfoXml:
 			if md_entry is not None:
 				ET.SubElement(root, cix_entry).text = u"{0}".format(md_entry)
 
+		assign( 'Title', md.title )
 		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( '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( '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"
+		assign( 'Day', md.day )
 
 		# need to specially process the credits, since they are structured differently than CIX	
 		credit_writer_list    = list()
@@ -181,7 +166,23 @@ class ComicInfoXml:
 		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')
@@ -229,6 +230,7 @@ class ComicInfoXml:
 		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' )
@@ -258,12 +260,14 @@ class ComicInfoXml:
 				n.tag == 'Letterer' or
 				n.tag == 'Editor' 
 			):
-				for name in n.text.split(','):
-					metadata.addCredit( name.strip(), n.tag )
+				if n.text is not None:
+					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" )
+				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" )

comictaggerlib/comicvinecacher.py

@@ -3,7 +3,7 @@ A python class to manage caching of data from Comic Vine
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -110,13 +110,11 @@ class ComicVineCacher:
 							"volume_id INT," +
 							"name TEXT," +
 							"issue_number TEXT," +
-							"image_url TEXT," +
-							"image_hash TEXT," +
-							"thumb_image_url TEXT," +
-							"thumb_image_hash TEXT," +
-							"publish_month TEXT," +
-							"publish_year 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 ) )" 
 						)
@@ -263,18 +261,34 @@ class ComicVineCacher:
 					}
 			self.upsert( cur, "volumes", "id", cv_volume_record['id'], data)
 
-			# now add in issues
 
-			for issue in cv_volume_record['issues']:
+	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":    cv_volume_record['id'], 
-				         "name":         issue['name'], 
-				         "issue_number": issue['issue_number'], 
-				         "timestamp":    timestamp 
+						"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 ):
 		
@@ -288,10 +302,6 @@ class ComicVineCacher:
 			# 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) ] )	
-
-			# 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 Issues WHERE timestamp  < ?", [ str(a_month_ago) ] )	
 			
 			# fetch
 			cur.execute("SELECT id,name,publisher,count_of_issues,start_year FROM Volumes WHERE id = ?", [ volume_id ] )
@@ -311,25 +321,51 @@ class ComicVineCacher:
 			result['count_of_issues'] =   row[3]
 			result['start_year'] =   row[4]
 			result['issues'] = list()
+		
+		return result
 
-			cur.execute("SELECT id,name,issue_number,image_url,image_hash FROM Issues WHERE volume_id = ?", [ volume_id ] )
+	def get_volume_issues_info( self, volume_id ):
+	
+		result = None
+
+		con = lite.connect( self.db_file )
+		with con:
+			cur = con.cursor() 
+			con.text_factory = unicode					
+			
+			# 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['image_url'] =    row[3]
-				record['image_hash'] =   row[4]
 				
-				result['issues'].append(record)
+				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)
 		
-		return result
+		if len(results) == 0:
+			return None
+			
+		return results
+	
 
-
-	def add_issue_select_details( self, issue_id, image_url, thumb_image_url, publish_month, publish_year, site_detail_url ):
+	def add_issue_select_details( self, issue_id, image_url, thumb_image_url, cover_date, site_detail_url ):
 		
 		con = lite.connect( self.db_file )
 
@@ -339,10 +375,9 @@ class ComicVineCacher:
 			timestamp = datetime.datetime.now()
 			
 			data = { 
-			          "image_url": image_url, 
-			          "thumb_image_url": thumb_image_url, 
-			          "publish_month": publish_month, 
-			          "publish_year": publish_year, 
+			          "super_url": image_url, 
+			          "thumb_url": thumb_image_url, 
+			          "cover_date": cover_date, 
 			          "site_detail_url": site_detail_url, 
 			          "timestamp": timestamp 
 			       }
@@ -357,23 +392,21 @@ class ComicVineCacher:
 			cur = con.cursor() 
 			con.text_factory = unicode					
 			
-			cur.execute("SELECT image_url,thumb_image_url,publish_month,publish_year,site_detail_url FROM Issues WHERE id=?", [ issue_id ])
+			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[0] is None :
+			if row is None or row[0] is None :
 				details['image_url'] = None
 				details['thumb_image_url'] = None
-				details['publish_month'] = None
-				details['publish_year'] = None
+				details['cover_date'] = None
 				details['site_detail_url'] = None
 
 			else:
 				details['image_url'] = row[0]
 				details['thumb_image_url'] = row[1]
-				details['publish_month'] = row[2]
-				details['publish_year'] = row[3]
-				details['site_detail_url'] = row[4]
+				details['cover_date'] = row[2]
+				details['site_detail_url'] = row[3]
 				
 			return details
 			

comictaggerlib/comicvinetalker.py

@@ -3,7 +3,7 @@ A python class to manage communication with Comic Vine's REST API
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -24,6 +24,7 @@ from pprint import pprint
 import urllib2, urllib 
 import math 
 import re
+import time
 import datetime
 import ctversion
 import sys
@@ -49,15 +50,22 @@ from comicvinecacher import ComicVineCacher
 from genericmetadata import GenericMetadata
 from issuestring import IssueString
 
-
+class CVTypeID:
+	Volume = "4050"
+	Issue  = "4000"
+	
 class ComicVineTalkerException(Exception):
 	pass
 
 class ComicVineTalker(QObject):
 
+	logo_url = "http://static.comicvine.com/bundles/comicvinesite/images/logo.png"
+
 	def __init__(self, api_key=""):
 		QObject.__init__(self)
 
+		self.api_base_url = "http://www.comicvine.com/api"
+		
 		# key that is registered to comictagger
 		self.api_key = '27431e6787042105bd3e47e169a624521f89f3a4'
 
@@ -74,9 +82,22 @@ class ComicVineTalker(QObject):
 		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 ):
 	
-		test_url = "http://api.comicvine.com/issue/1/?api_key=" + self.api_key + "&format=json&field_list=name"
+		test_url = self.api_base_url + "/issue/1/?api_key=" + self.api_key + "&format=json&field_list=name"
 		resp = urllib2.urlopen( test_url ) 
 		content = resp.read()
 	
@@ -86,12 +107,28 @@ class ComicVineTalker(QObject):
 		return cv_response[ 'status_code' ] != 100
 
 	def getUrlContent( self, url ):
-		try:
-			resp = urllib2.urlopen( url ) 
-			return resp.read()
-		except Exception as e:
-			self.writeLog( str(e) )
-			raise ComicVineTalkerException("Network Error!")
+		# connect to server:
+		#  if there is a 500 error, try a few more times before giving up
+		#  any other error, just bail
+		#print "ATB---", url
+		for tries in range(3):
+			try:
+				resp = urllib2.urlopen( url ) 
+				return resp.read()
+			except urllib2.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("Network Error!")
+				
+		raise ComicVineTalkerException("Error on Comic Vine server")
 
 	def searchForSeries( self, series_name , callback=None, refresh_cache=False ):
 		
@@ -108,12 +145,23 @@ class ComicVineTalker(QObject):
 				return cached_search_results
 		
 		original_series_name = series_name
-	
-		series_name = urllib.quote_plus(series_name.encode("utf-8"))
-		#series_name = urllib.quote_plus(unicode(series_name))
-		search_url = "http://api.comicvine.com/search/?api_key=" + self.api_key + "&format=json&resources=volume&query=" + series_name + "&field_list=name,id,start_year,publisher,image,description,count_of_issues&sort=start_year"
+		
+		# We need to make the series name into an "AND"ed query list
+		query_word_list = series_name.split()
+		and_list =  ['AND'] * (len(query_word_list)-1)
+		and_list.append('')
+		# zipper up the two lists
+		query_list = zip(query_word_list, and_list)
+		# flatten the list
+		query_list = [ item for sublist in query_list for item in sublist]
+		# convert back to a string
+		query_string = " ".join( query_list ).strip()
+		#print "Query string = ", query_string
+		
+		query_string = urllib.quote_plus(query_string.encode("utf-8"))
 
-		content = self.getUrlContent(search_url) 
+		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"
+		content = self.getUrlContent(search_url + "&page=1") 
 	
 		cv_response = json.loads(content)
 	
@@ -132,7 +180,7 @@ class ComicVineTalker(QObject):
 		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'])
-		offset = 0
+		page = 1
 		
 		if callback is not None:
 			callback( current_result_count, total_result_count )
@@ -141,8 +189,9 @@ class ComicVineTalker(QObject):
 		while ( current_result_count < total_result_count ):
 			if callback is None:
 				self.writeLog("getting another page of results {0} of {1}...\n".format( current_result_count, total_result_count))
-			offset += limit
-			content = self.getUrlContent(search_url + "&offset="+str(offset)) 
+			page += 1
+
+			content = self.getUrlContent(search_url + "&page="+str(page)) 
 		
 			cv_response = json.loads(content)
 		
@@ -157,10 +206,10 @@ class ComicVineTalker(QObject):
 
 	
 		#for record in search_results: 
-		#	print( "{0}: {1} ({2})".format(record['id'], smart_str(record['name']) , record['start_year'] ) )
-		#	print( "{0}: {1} ({2})".format(record['id'], record['name'] , record['start_year'] ) )
-		
-		#print "{0}: {1} ({2})".format(search_results['results'][0]['id'], smart_str(search_results['results'][0]['name']) , search_results['results'][0]['start_year'] ) 
+		#	#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 )
@@ -178,7 +227,7 @@ class ComicVineTalker(QObject):
 			return cached_volume_result
 
 	
-		volume_url = "http://api.comicvine.com/volume/" + str(series_id) + "/?api_key=" + self.api_key + "&format=json"
+		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"
 
 		content = self.getUrlContent(volume_url) 	
 		cv_response = json.loads(content)
@@ -192,22 +241,130 @@ class ComicVineTalker(QObject):
 		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"
+		content = self.getUrlContent(issues_url) 	
+		cv_response = json.loads(content)
+		
+		if cv_response[ 'status_code' ] != 1:
+			print >> sys.stderr, "Comic Vine query failed with error:  [{0}]. ".format( cv_response[ 'error' ] )
+			return None
+		#------------------------------------
+		
+		limit = cv_response['limit']
+		current_result_count = cv_response['number_of_page_results']
+		total_result_count = cv_response['number_of_total_results']
+		#print "ATB total_result_count", total_result_count
+		
+		#print "ATB 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 "ATB 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)
+			content = self.getUrlContent(issues_url + "&offset="+str(offset)) 
+			cv_response = json.loads(content)
+		
+			if cv_response[ 'status_code' ] != 1:
+				self.writeLog( "Comic Vine query failed with error:  [{0}]. \n".format( cv_response[ 'error' ] ))
+				return None
+			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.quote_plus(unicode(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"
+
+		content = self.getUrlContent(issues_url) 	
+		cv_response = json.loads(content)
+		
+		if cv_response[ 'status_code' ] != 1:
+			print >> sys.stderr, "Comic Vine query failed with error:  [{0}]. ".format( cv_response[ 'error' ] )
+			return None
+		#------------------------------------
+		
+		limit = cv_response['limit']
+		current_result_count = cv_response['number_of_page_results']
+		total_result_count = cv_response['number_of_total_results']
+		#print "ATB total_result_count", total_result_count
+		
+		#print "ATB 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 "ATB 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)
+			content = self.getUrlContent(issues_url + "&offset="+str(offset)) 
+			cv_response = json.loads(content)
+		
+			if cv_response[ 'status_code' ] != 1:
+				self.writeLog( "Comic Vine query failed with error:  [{0}]. \n".format( cv_response[ 'error' ] ))
+				return None
+			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 volume_results['issues']:
-			if IssueString(issue_number).asFloat() is None:
+		for record in issues_list_results:
+			if IssueString(issue_number).asString() is None:
 				issue_number = 1
-			if float(record['issue_number']) == IssueString(issue_number).asFloat():
+			if IssueString(record['issue_number']).asString().lower() == IssueString(issue_number).asString().lower():
 				found = True
 				break
 			
 		if (found):
-			issue_url = "http://api.comicvine.com/issue/" + str(record['id']) + "/?api_key=" + self.api_key + "&format=json"
+			issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + str(record['id']) + "/?api_key=" + self.api_key + "&format=json"
 
 			content = self.getUrlContent(issue_url) 
 			cv_response = json.loads(content)
@@ -224,7 +381,7 @@ class ComicVineTalker(QObject):
 
 	def fetchIssueDataByIssueID( self, issue_id, settings ):
 
-		issue_url = "http://api.comicvine.com/issue/" + str(issue_id) + "/?api_key=" + self.api_key + "&format=json"
+		issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + str(issue_id) + "/?api_key=" + self.api_key + "&format=json"
 		content = self.getUrlContent(issue_url)
 		cv_response = json.loads(content)
 		if cv_response[ 'status_code' ] != 1:
@@ -248,14 +405,14 @@ class ComicVineTalker(QObject):
 		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.month = issue_results['publish_month']
-		metadata.year = issue_results['publish_year']
+		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'])
+		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']
 		
@@ -268,11 +425,12 @@ class ComicVineTalker(QObject):
 		metadata.webLink = issue_results['site_detail_url']
 		
 		person_credits = issue_results['person_credits']
-		for person in person_credits: 
-			for role in person['roles']:
-				# can we determine 'primary' from CV??
-				role_name = role['role'].title()
-				metadata.addCredit( person['name'], role['role'].title(), False )			
+		for person in person_credits:
+			if person.has_key('role'):
+				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()
@@ -300,9 +458,25 @@ class ComicVineTalker(QObject):
 			metadata.storyArc =  utils.listToString(arc_list)
 
 		return metadata
-	
-	def cleanup_html( self, string):
+	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)
+		tables = soup.findAll('table')
+
 		# remove all newlines first
 		string = string.replace("\n", "")
 		
@@ -311,6 +485,14 @@ class ComicVineTalker(QObject):
 		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'<[^<]*?>')
@@ -321,13 +503,63 @@ class ComicVineTalker(QObject):
 	
 		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 )
-		return details['publish_month'], details['publish_year']
-
+		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']
@@ -343,15 +575,14 @@ class ComicVineTalker(QObject):
 		if cached_details['image_url'] is not None:
 			return cached_details
 
-		issue_url = "http://api.comicvine.com/issue/" + str(issue_id) + "/?api_key=" + self.api_key + "&format=json&field_list=image,publish_month,publish_year,site_detail_url"
+		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"
 
 		content = self.getUrlContent(issue_url) 
 		
 		details = dict()
 		details['image_url'] = None
 		details['thumb_image_url'] = None
-		details['publish_month'] = None
-		details['publish_year'] = None
+		details['cover_date'] = None
 		details['site_detail_url'] = None
 		
 		cv_response = json.loads(content)
@@ -361,16 +592,14 @@ class ComicVineTalker(QObject):
 		
 		details['image_url'] =       cv_response['results']['image']['super_url']
 		details['thumb_image_url'] = cv_response['results']['image']['thumb_url']
-		details['publish_year'] =    cv_response['results']['publish_year']
-		details['publish_month'] =   cv_response['results']['publish_month']
+		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['publish_month'],
-										details['publish_year'],
+										details['cover_date'],
 										details['site_detail_url'] )
 		#print details['site_detail_url']
 		return details
@@ -382,18 +611,16 @@ class ComicVineTalker(QObject):
 		cvc = ComicVineCacher( )
 		return  cvc.get_issue_select_details( issue_id )
 
-	def cacheIssueSelectDetails( self, issue_id, image_url, thumb_url, month, year, page_url ):
+	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, month, year, page_url )
+		cvc.add_issue_select_details( issue_id, image_url, thumb_url, cover_date, page_url )
 
 
-	def fetchAlternateCoverURLs(self, issue_id):
+	def fetchAlternateCoverURLs(self, issue_id, issue_page_url):
 		url_list = self.fetchCachedAlternateCoverURLs( issue_id )
 		if url_list is not None:
 			return url_list
 		
-		issue_page_url = self.fetchIssuePageURL( issue_id )
-		
 		# scrape the CV issue page URL to get the alternate cover URLs 
 		resp = urllib2.urlopen( issue_page_url ) 
 		content = resp.read()
@@ -412,11 +639,14 @@ class ComicVineTalker(QObject):
 		# Using knowledge of the layout of the ComicVine issue page here:
 		#  look for the divs that are in the classes 'content-pod' and 'alt-cover'
 		div_list = soup.find_all( 'div')
+		covers_found = 0
 		for d in div_list:
 			if d.has_key('class'):
 				c = d['class']
-				if 'content-pod' in c and 'alt-cover' in c:
-					alt_cover_url_list.append( d.img['src'] )
+				if 'imgboxart' in c and 'issue-cover' in c:
+					covers_found += 1
+					if covers_found != 1:
+						alt_cover_url_list.append( d.img['src'] )
 					
 		return alt_cover_url_list
 
@@ -446,7 +676,7 @@ class ComicVineTalker(QObject):
 			self.urlFetchComplete.emit( details['image_url'],details['thumb_image_url'], self.issue_id )
 			return
 
-		issue_url = "http://api.comicvine.com/issue/" + str(issue_id) + "/?api_key=" + self.api_key + "&format=json&field_list=image,publish_month,publish_year,site_detail_url"
+		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)))
@@ -455,18 +685,24 @@ class ComicVineTalker(QObject):
 
 		# read in the response
 		data = reply.readAll()
-		cv_response = json.loads(str(data))
+			
+		try:
+			cv_response = json.loads(str(data))
+		except:
+			print >> sys.stderr,  "Comic Vine query failed to get JSON data"
+			print >> sys.stderr, str(data)
+			return 
+		
 		if cv_response[ 'status_code' ] != 1:
 			print >> sys.stderr,  "Comic Vine query failed with error:  [{0}]. ".format( cv_response[ 'error' ] )
 			return 
 		
 		image_url = cv_response['results']['image']['super_url']
 		thumb_url = cv_response['results']['image']['thumb_url']
-		year = cv_response['results']['publish_year']
-		month = cv_response['results']['publish_month']
+		cover_date = cv_response['results']['cover_date']
 		page_url = cv_response['results']['site_detail_url']
 
-		self.cacheIssueSelectDetails(  self.issue_id, image_url, thumb_url, month, year, page_url )
+		self.cacheIssueSelectDetails(  self.issue_id, image_url, thumb_url, cover_date, page_url )
 
 		self.urlFetchComplete.emit( image_url, thumb_url, self.issue_id ) 
 
@@ -495,3 +731,11 @@ class ComicVineTalker(QObject):
 
 		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

@@ -1,9 +1,11 @@
 """
 A PyQt4 widget display cover images from either local archive, or from ComicVine
+
+(TODO: This should be re-factored using subclasses!)
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -26,7 +28,7 @@ from PyQt4 import uic
 
 from settings import ComicTaggerSettings
 from genericmetadata import GenericMetadata, PageType
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 from comicvinetalker import ComicVineTalker, ComicVineTalkerException
 from imagefetcher import  ImageFetcher
 from pageloader import PageLoader
@@ -59,8 +61,9 @@ class CoverImageWidget(QWidget):
 	ArchiveMode = 0
 	AltCoverMode = 1
 	URLMode = 1
+	DataMode = 3
 	
-	def __init__(self, parent, mode ):
+	def __init__(self, parent, mode, expand_on_click = True ):
 		super(CoverImageWidget, self).__init__(parent)
 		
 		uic.loadUi(ComicTaggerSettings.getUIFile('coverimagewidget.ui' ), self)
@@ -78,7 +81,10 @@ class CoverImageWidget(QWidget):
 		self.btnLeft.clicked.connect( self.decrementImage )
 		self.btnRight.clicked.connect( self.incrementImage )
 		self.resetWidget()
-		clickable(self.lblImage).connect(self.showPopup)
+		if expand_on_click:
+			clickable(self.lblImage).connect(self.showPopup)
+		else:
+			self.lblImage.setToolTip( "" )
 
 		self.updateContent()
 
@@ -93,11 +99,12 @@ class CoverImageWidget(QWidget):
 		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:
@@ -138,7 +145,19 @@ class CoverImageWidget(QWidget):
 			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
@@ -179,11 +198,13 @@ class CoverImageWidget(QWidget):
 			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:
+		if not self.showControls or self.mode == CoverImageWidget.DataMode:
 			self.btnLeft.hide()
 			self.btnRight.hide()
 			self.label.hide()
@@ -288,3 +309,4 @@ class CoverImageWidget(QWidget):
 			
 	def showPopup( self ):
 		self.popup = ImagePopup(self, self.current_pixmap)
+

comictaggerlib/crediteditorwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to edit credits
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/ctversion.py

@@ -1,3 +1,3 @@
 # This file should contan only these comments, and the line below.  
 # Used by packaging makefiles and app
-version="1.1.1-beta"
+version="1.1.14-beta"

comictaggerlib/exportwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to confirm and set options for export to zip
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/filenameparser.py

@@ -6,7 +6,7 @@ This should probably be re-written, but, well, it mostly works!
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -30,28 +30,25 @@ import os
 from urllib import unquote
 
 class FileNameParser:
-	def fixSpaces( self, string ):
-		placeholders = ['[-_]','  +']
+
+	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, ' ', string )
-		return string.strip()
-
-	# check for silly .1 or .5 style issue strings
-	# allow up to 5 chars total
-	def isPointIssue( self, word ):
-		ret = False
-		try:
-			float(word)
-			if (len(word) < 5 and not word.isdigit()):
-				ret = True
-		except ValueError:
-			pass
-		return ret
+			string = re.sub(ph, self.repl, string )
+		return string #.strip()
 
 
-	def getIssueCount( self,filename ):
+	def getIssueCount( self,filename, issue_end ):
 
 		count = ""
+		filename = filename[issue_end:]
+		
 		# replace any name seperators with spaces
 		tmpstr = self.fixSpaces(filename)
 		found = False
@@ -71,115 +68,150 @@ class FileNameParser:
 		count = count.lstrip("0")
 
 		return count
-		
-		
+	
 	def getIssueNumber( self, filename ):
 
+		# Returns a tuple of issue number string, and start and end indexs 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 mean's it's formatted differently from most:
+		# 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 = filename.split("--")[0]
-		elif "___" in filename:
+			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 = filename.split("__")[0]
+			filename = re.sub("__.*", self.repl, filename)	
 
 		filename = filename.replace("+", " ")
 			
-		# remove parenthetical phrases
-		filename = re.sub( "\(.*\)", "", filename)
-		filename = re.sub( "\[.*\]", "", filename)
-		
-		# guess based on position
+		# replace parenthetical phrases with spaces
+		filename = re.sub( "\(.*?\)", self.repl, filename)
+		filename = re.sub( "\[.*?\]", self.repl, filename)
 
 		# replace any name seperators with spaces
-		tmpstr = self.fixSpaces(filename)
-		word_list = tmpstr.split(' ')
+		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)
 		
-		#before we search, remove any kind of likely "of X" phrase
-		for i in range(0, len(word_list)-2):
-			if ( word_list[i].isdigit() and
-				word_list[i+1] == "of"  and
-				word_list[i+2].isdigit() ):
-				word_list[i+1] ="XXX"
-				word_list[i+2] ="XXX"
-				
-				
-		# first look for the last "#" followed by a digit in the filename. this is almost certainly the issue number
-		#issnum = re.search('#\d+', filename)
-		matchlist = re.findall("#\d+", filename)
-		if len(matchlist) > 0:
-			#get the last item
-			issue = matchlist[ len(matchlist) - 1]
-			issue = issue[1:]
-			found = True
-
-		
-		# assume the last number in the filename that is under 4 digits is the issue number
-		if not found:
-			for word in reversed(word_list):
-				if len(word) > 0 and word[0] == "#":
-					word = word[1:]
-				if ( 
-					 (word.isdigit() and len(word) < 4) or
-					 (self.isPointIssue(word))
-					):
-					issue = word
-					found = True
-					#print 'Assuming issue number is ' + str(issue) + ' based on the position.'
-					break
-
-		if not found:
-			# try a regex
-			issnum = re.search('(?<=[_#\s-])(\d+[a-zA-Z]|\d+\.\d|\d+)', filename)
-			if issnum:
-				issue = issnum.group()
-				found = True
-				#print 'Got the issue using regex. Issue is ' + issue 
-		
-		return issue.strip()
-
-	def getSeriesName(self, filename, issue ):
-
-		# use the issue number string to split the filename string
-		# assume first element of list is the series name, plus cruft
-		#!!! this could fail in the case of small numerics in the series name!!!
-
-		# TODO:  we really should pass in the *INDEX* of the issue, that makes 
-		# finding it easier
-		
-		filename = filename.replace("+", " ")
-		tmpstr = self.fixSpaces(filename)
-		
-		#remove pound signs.  this might mess up the series name if there is a# in it.
-		tmpstr = tmpstr.replace("#", " ")
-
-		if issue != "":	
-			# assume that issue substr has at least one space before it
-			issue_str = " " + str(issue)
-			series = tmpstr.split(issue_str)[0]
-		else:
-			# no issue to work off of
-			#!!! TODO we should look for the year, and split from that
-			# and if that doesn't exist, remove parenthetical phrases
-			series = tmpstr
-			series = re.sub( "\(.*\)", "", tmpstr)
+		# we should now have a cleaned up filename version with all the words in
+		# the same positions as original filename
 			
-		volume = ""
+		# 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
 		
-		series = series.rstrip("#")
+		# first look for a word with "#" followed by digits with optional sufix 
+		# 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)
-		
-		return series.strip(), volume.strip()
+			
+		# 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)
 
-	def getYear( self,filename):
+		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
@@ -190,6 +222,28 @@ class FileNameParser:
 			year = re.sub("[^0-9]", "", year)
 		return year
 
+	def getRemainder( self, filename, year, count, 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 year != "":
+			remainder = remainder.replace(year,"",1)
+		if count != "":
+			remainder = remainder.replace("of "+count,"",1)
+			
+		remainder = remainder.replace("()","")
+		
+		return remainder.strip()
+		
 	def parseFilename( self, filename ):
 
 		# remove the path
@@ -207,20 +261,12 @@ class FileNameParser:
 		if filename.count("_28") > 1 and filename.count("_29") > 1:
 			filename = filename.replace("_28", "(")
 			filename = filename.replace("_29", ")")
-		
-		# ----HACK  
-		# remove the first word that word is a 3 digit number.
-		# some story arcs collection packs do this, but it's ugly
-		# this will probably break something, i.e. "100 bullets"
-		#word = filename.split(' ')[0]
-		#if len(word) == 3 and word[0] =='0' and word.isdigit():
-		#	filename = filename[4:]
-		# ----HACK  -
 					
-		self.issue = self.getIssueNumber(filename)
-		self.series, self.volume = self.getSeriesName(filename, self.issue)
-		self.year = self.getYear(filename)
-		self.issue_count = self.getIssueCount(filename)
+		self.issue, issue_start, issue_end = self.getIssueNumber(filename)
+		self.series, self.volume = self.getSeriesName(filename, issue_start)
+		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, issue_end )
 	
 		if self.issue != "":
 			# strip off leading zeros
@@ -229,4 +275,3 @@ class FileNameParser:
 				self.issue = "0"
 			if self.issue[0] == ".":
 				self.issue = "0" + self.issue
-

comictaggerlib/filerenamer.py

@@ -3,7 +3,7 @@ Functions for renaming files based on metadata
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -21,6 +21,7 @@ limitations under the License.
 import os
 import re
 import datetime
+import utils
 from issuestring import IssueString
 
 class FileRenamer:
@@ -71,6 +72,7 @@ class FileRenamer:
 
 		md = self.metdata
 		new_name = self.template
+		preferred_encoding = utils.get_actual_preferred_encoding()
 
 		#print u"{0}".format(md)
 		
@@ -93,7 +95,7 @@ class FileRenamer:
 			if (type(md.month) == str and md.month.isdigit()) or type(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")
+					month_name = dt.strftime(u"%B".encode(preferred_encoding)).decode(preferred_encoding)
 		new_name = self.replaceToken( new_name, month_name, '%month_name%')
 
 		new_name = self.replaceToken( new_name, md.genre, '%genre%')
@@ -116,12 +118,20 @@ class FileRenamer:
 			new_name = re.sub("\[\s*[-:]*\s*\]", "", new_name )
 			new_name = re.sub("\{\s*[-:]*\s*\}", "", new_name )
 
-			# remove remove duplicate -, _,
-			new_name = re.sub("[-_]+\s+", "- ", new_name )
-			new_name = re.sub("(\s-)+", " -", new_name )
-
 			# remove duplicate spaces
 			new_name = u" ".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 = u" ".join(new_name.split())
+
 		
 		if ext is None:
 			ext = os.path.splitext( filename )[1]
@@ -130,7 +140,9 @@ class FileRenamer:
 		
 		# 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(":",  "-")
 		new_name = new_name.replace("?", "")
 		
 		return new_name

comictaggerlib/fileselectionlist.py

@@ -4,7 +4,7 @@ A PyQt4 widget for managing list of comic archive files
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -29,9 +29,12 @@ from PyQt4.QtCore import pyqtSignal
 
 from settings import ComicTaggerSettings
 from comicarchive import ComicArchive
+from comicarchive import MetaDataStyle
 from genericmetadata import GenericMetadata, PageType
-from options import MetaDataStyle
+from optionalmsgdialog import OptionalMessageDialog
 import utils
+import platform
+import os
 
 class FileTableWidget( QTableWidget ):
 
@@ -98,6 +101,14 @@ class FileSelectionList(QWidget):
 		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 )
 	
@@ -154,26 +165,16 @@ class FileSelectionList(QWidget):
 		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 = []
-		for p in pathlist:
-			# if path is a folder, walk it recursivly, and all files underneath
-			if type(p) == str:
-				#make sure string is unicode
-				filename_encoding = sys.getfilesystemencoding()
-				p = p.decode(filename_encoding, 'replace')
-			
-			if os.path.isdir( unicode(p)):
-				for root,dirs,files in os.walk( unicode(p) ):
-					for f in files:
-						filelist.append(os.path.join(root,unicode(f)))
-			else:
-				filelist.append(unicode(p))
-			
+		
+		filelist = utils.get_recursive_filelist( pathlist )
 		# we now have a list of files to add
 
 		progdialog = QProgressDialog("", "Cancel", 0, len(filelist), self)
@@ -197,9 +198,33 @@ class FileSelectionList(QWidget):
 				firstAdded = row
 			
 		progdialog.close()
+		if ( self.settings.show_no_unrar_warning and
+			 self.settings.unrar_exe_path == "" and
+			 self.settings.rar_exe_path == "" and
+			 platform.system() != "Windows"):
+			for f in filelist:
+				ext = os.path.splitext(f)[1].lower()
+				if ext == ".rar" or ext ==".cbr":
+					checked = OptionalMessageDialog.msg(  self, "No unrar tool",
+							"""
+							It looks like you've tried to open at least one CBR or RAR file.<br><br>
+							In order for ComicTagger to read this kind of file, you will have to configure
+							the location of the unrar tool in the settings.  Until then, ComicTagger
+							will not be able recognize these kind of files.
+							"""
+							)
+					self.settings.show_no_unrar_warning = not checked
+					break
+			
 		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 comic archives were found."))
 			
+		
 		self.twList.setSortingEnabled(True)
 		
 		# Adjust column size
@@ -221,7 +246,17 @@ class FileSelectionList(QWidget):
 				return True
 			r = r + 1
 			
-		return False		
+		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 = unicode( path )
@@ -229,14 +264,11 @@ class FileSelectionList(QWidget):
 		#print "processing", path
 		
 		if self.isListDupe(path):
-			return None
+			return self.getCurrentListRow(path)
 		
-		ca = ComicArchive( path )
-		if self.settings.rar_exe_path != "":
-			ca.setExternalRarProgram( self.settings.rar_exe_path )
+		ca = ComicArchive( path, self.settings.rar_exe_path )
 			
 		if ca.seemsToBeAComicArchive() :
-			
 			row = self.twList.rowCount()
 			self.twList.insertRow( row )
 			

comictaggerlib/genericmetadata.py

@@ -8,7 +8,7 @@
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -31,7 +31,7 @@ class PageType:
 	InnerCover   = "InnerCover"
 	Roundup      = "Roundup"
 	Story        = "Story"
-	Advertisment = "Advertisment"
+	Advertisement = "Advertisement"
 	Editorial    = "Editorial"
 	Letters      = "Letters"
 	Preview      = "Preview"
@@ -63,6 +63,7 @@ class GenericMetadata:
 		self.publisher          = None
 		self.month              = None
 		self.year               = None
+		self.day                = None
 		self.issueCount         = None
 		self.volume             = None
 		self.genre              = None
@@ -125,6 +126,7 @@ class GenericMetadata:
 		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 )
@@ -256,8 +258,9 @@ class GenericMetadata:
 		add_attr_string( "issueCount" )
 		add_attr_string( "title" )
 		add_attr_string( "publisher" )
-		add_attr_string( "month" )
 		add_attr_string( "year" )
+		add_attr_string( "month" )
+		add_attr_string( "day" )
 		add_attr_string( "volume" )
 		add_attr_string( "volumeCount" )
 		add_attr_string( "genre" )

comictaggerlib/imagefetcher.py

@@ -3,7 +3,7 @@ A python class to manage fetching and caching of images by URL
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/imagepopup.py

@@ -3,7 +3,7 @@ A PyQT4 widget to display a popup image
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/issueselectionwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to select specific issue from list
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -20,6 +20,7 @@ limitations under the License.
 
 import sys
 import os
+import re
 from PyQt4 import QtCore, QtGui, uic
 
 from PyQt4.QtCore import QUrl, pyqtSignal, QByteArray
@@ -32,6 +33,13 @@ from issuestring import IssueString
 from coverimagewidget import CoverImageWidget
 import utils
 
+class IssueNumberTableWidgetItem(QtGui.QTableWidgetItem):
+	def __lt__(self, other):
+		selfStr = self.data(QtCore.Qt.DisplayRole).toString()
+		otherStr = other.data(QtCore.Qt.DisplayRole).toString()
+		return (IssueString(selfStr).asFloat() <
+		        IssueString(otherStr).asFloat())
+
 class IssueSelectionWindow(QtGui.QDialog):
 	
 	volume_id = 0
@@ -47,6 +55,7 @@ class IssueSelectionWindow(QtGui.QDialog):
 		gridlayout.setContentsMargins(0,0,0,0)
 
 		utils.reduceWidgetFontSize( self.twList )		
+		utils.reduceWidgetFontSize( self.teDescription, 1 )
 
 		self.setWindowFlags(self.windowFlags() |
 									  QtCore.Qt.WindowSystemMenuHint |
@@ -85,6 +94,7 @@ class IssueSelectionWindow(QtGui.QDialog):
 		try:
 			comicVine = ComicVineTalker( )
 			volume_data = comicVine.fetchVolumeData( self.series_id )
+			self.issue_list = comicVine.fetchIssuesByVolume( self.series_id )
 		except ComicVineTalkerException:
 			QtGui.QApplication.restoreOverrideCursor()		
 			QtGui.QMessageBox.critical(self, self.tr("Network Issue"), self.tr("Could not connect to ComicVine to list issues!"))
@@ -92,8 +102,6 @@ class IssueSelectionWindow(QtGui.QDialog):
 
 		while self.twList.rowCount() > 0:
 			self.twList.removeRow(0)
-				
-		self.issue_list = volume_data['issues']
 
 		self.twList.setSortingEnabled(False)
 
@@ -102,20 +110,35 @@ class IssueSelectionWindow(QtGui.QDialog):
 			self.twList.insertRow(row)
 			
 			item_text = record['issue_number']  
-			item = QtGui.QTableWidgetItem(item_text)			
+			item = IssueNumberTableWidgetItem(item_text)			
 			item.setData( QtCore.Qt.ToolTipRole, item_text )
 			item.setData( QtCore.Qt.UserRole ,record['id'])
-			item.setData(QtCore.Qt.DisplayRole, float(item_text))
+			item.setData(QtCore.Qt.DisplayRole, item_text)
 			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
 			self.twList.setItem(row, 0, item)
 			
-			item_text = record['name']
+			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 = QtGui.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 = QtGui.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() == IssueString(self.issue_number).asString():
+			if IssueString(record['issue_number']).asString().lower() == IssueString(self.issue_number).asString().lower():
 				self.initial_id = record['id']
 			
 			row += 1
@@ -142,5 +165,10 @@ class IssueSelectionWindow(QtGui.QDialog):
 			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

@@ -8,11 +8,12 @@ e.g.:
 "0"
 "-1"
 "5AU"
+"100-2"
 
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -34,31 +35,63 @@ import re
 class IssueString:
 	def __init__(self, text):
 	
-		if text is None:
-			self.num = None
-			self.suffix = ""
-			return
-			
-		self.text = str(text)
-		#strip out non float-y stuff
-		tmp_num_str = re.sub('[^0-9.-]',"", 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 tmp_num_str == "":
-			self.num = None
-			self.suffix = self.text
-			
+		if text is None:
+			return
+
+		if type(text) == int:
+			text = str(text)
+
+		if len(text) == 0:
+			return	
+		
+		text = unicode(text)
+		
+		#skip the minus sign if it's first
+		if text[0] == '-':
+			start = 1
 		else:
-			if tmp_num_str.count(".") > 1:
-				#make sure it's a valid float or int.
-				parts = tmp_num_str.split('.')
-				self.num = float( parts[0] + '.' + parts[1] )
-			else:	
-				self.num = float( tmp_num_str )
-				
-			self.suffix = ""		
-			parts = self.text.split(tmp_num_str)
-			if len( parts ) > 1 :
-				self.suffix = parts[1]
+			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

comictaggerlib/logwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to a text file or log
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/main.py

@@ -3,7 +3,7 @@ A python app to (automatically) tag comic archives
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -23,8 +23,6 @@ import signal
 import os
 import traceback
 import platform
-import locale
-import codecs
 
 import utils
 import cli
@@ -40,21 +38,12 @@ except ImportError as e:
 #---------------------------------------
 
 def ctmain():
-	# try to make stdout encodings happy for unicode
-	if platform.system() == "Darwin":
-		preferred_encoding = "utf-8"
-	else:
-		preferred_encoding = locale.getpreferredencoding()
-	sys.stdout = codecs.getwriter(preferred_encoding)(sys.stdout)
-	sys.stderr = codecs.getwriter(preferred_encoding)(sys.stderr)
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
 
 	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:
@@ -75,7 +64,7 @@ def ctmain():
 			app.processEvents()
 	
 		try:			
-			tagger_window = TaggerWindow( opts.file_list, settings )
+			tagger_window = TaggerWindow( opts.file_list, settings, opts=opts )
 			tagger_window.show()
 
 			if platform.system() != "Linux":

comictaggerlib/matchselectionwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to select from automated issue matches
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -26,7 +26,7 @@ from PyQt4.QtCore import QUrl, pyqtSignal, QByteArray
 
 from imagefetcher import  ImageFetcher
 from settings import ComicTaggerSettings
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 from coverimagewidget import CoverImageWidget
 from comicvinetalker import ComicVineTalker
 import utils
@@ -51,6 +51,7 @@ class MatchSelectionWindow(QtGui.QDialog):
 		gridlayout.setContentsMargins(0,0,0,0)
 
 		utils.reduceWidgetFontSize( self.twList )		
+		utils.reduceWidgetFontSize( self.teDescription, 1 )
 
 		self.setWindowFlags(self.windowFlags() |
 									  QtCore.Qt.WindowSystemMenuHint |
@@ -116,6 +117,8 @@ class MatchSelectionWindow(QtGui.QDialog):
 			self.twList.setItem(row, 2, item)
 
 			item_text = match['issue_title']  
+			if item_text is None:
+				item_text = ""
 			item = QtGui.QTableWidgetItem(item_text)			
 			item.setData( QtCore.Qt.ToolTipRole, item_text )
 			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
@@ -142,7 +145,11 @@ class MatchSelectionWindow(QtGui.QDialog):
 				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)
 

comictaggerlib/optionalmsgdialog.py

@@ -3,7 +3,7 @@ A PyQt4 dialog to show a message and let the user check a box
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -60,7 +60,7 @@ class OptionalMessageDialog(QDialog):
 			if style == StyleQuestion:
 				check_text = "Remember this answer"
 			else:
-				check_text = "Don't show this dialog again"
+				check_text = "Don't show this message again"
 				
 		self.theCheckBox = QCheckBox(check_text)
 		

comictaggerlib/options.py

@@ -3,7 +3,7 @@ CLI options class for comictagger app
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -22,22 +22,17 @@ import sys
 import getopt
 import platform
 import os
-
+import traceback
 import ctversion
+import utils
+try:
+	import argparse
+except:
+	pass
+
 from genericmetadata import GenericMetadata
-
-class Enum(set):
-    def __getattr__(self, name):
-        if name in self:
-            return name
-        raise AttributeError
-
-class MetaDataStyle:
-	CBI = 0
-	CIX = 1
-	COMET = 2
-	name = [ 'ComicBookLover', 'ComicRack', 'CoMet' ]
-
+from comicarchive import MetaDataStyle
+from versionchecker import VersionChecker
 
 class Options:
 	help_text = """	
@@ -57,6 +52,7 @@ If no options are given, {0} will run in windowed mode
   -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 ( relevent for -s or -c )  
+  -1, --assume-issue-one     Assume issue number is 1 if not found ( relevent for -s )  
   -n, --dryrun               Don't actually modify file (only relevent for -d, -s, or -r)
   -t, --type=TYPE            Specify TYPE as either "CR", "CBL", or "COMET" (as either 
                              ComicRack, ComicBookLover, or CoMet style tags, respectivly)
@@ -82,7 +78,10 @@ If no options are given, {0} will run in windowed mode
   -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)	  
+                             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                            
   -v, --verbose              Be noisy when doing what it does                            
       --terse                Don't say much (for print mode)                            
       --version              Display version                            
@@ -116,6 +115,10 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 		self.no_overwrite = False
 		self.interactive = False
 		self.issue_id = None
+		self.recursive = False
+		self.run_script = False
+		self.script = None
+		self.assume_issue_is_one_if_not_set = False
 		self.file_list = []
 		
 	def display_msg_and_quit( self, msg, code, show_help=False ):
@@ -177,6 +180,41 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 		#print md
 		return md
 		
+	def launch_script(self, scriptfile):
+		# we were given a script.  special case for the args:
+		#  1. ignore everthing 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:
@@ -185,14 +223,23 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 		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:vonsrc:ie", 
+			           "hpdt:fm:vonsrc:ieRS:1", 
 			           [ "help", "print", "delete", "type=", "copy=", "parsefilename", "metadata=", "verbose",
 			            "online", "dryrun", "save", "rename" , "raw", "noabort", "terse", "nooverwrite",
-			            "interactive", "nosummary", "version", "id=" 
-			            "export-to-zip", "delete-rar", "abort-on-conflict" ] )
+			            "interactive", "nosummary", "version", "id=" , "recursive", "script=",
+			            "export-to-zip", "delete-rar", "abort-on-conflict", "assume-issue-one" ] )
 
 		except getopt.GetoptError as err:
 			self.display_msg_and_quit( str(err), 2 )
@@ -203,6 +250,11 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 				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"):
@@ -247,11 +299,18 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 				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  == "--version":
-				print "ComicTagger {0}:  Copyright (c) 2012-2013 Anthony Beville".format(ctversion.version)
-				print "Distributed under Apache License 2.0 (http://www.apache.org/licenses/LICENSE-2.0)"	
+				print "ComicTagger {0}:  Copyright (c) 2012-2014 Anthony Beville".format(ctversion.version)
+				print "Distributed under Apache License 2.0 (http://www.apache.org/licenses/LICENSE-2.0)"
+				new_version = VersionChecker().getLatestVersion("", False)
+				if new_version is not None and new_version != ctversion.version:
+					print "----------------------------------------"
+					print "New version available online: {0}".format(new_version)
+					print "----------------------------------------"
 				sys.exit(0)
 			if o in ("-t", "--type"):
 				if a.lower() == "cr":
@@ -262,11 +321,12 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 					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:
 			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
@@ -275,8 +335,11 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 		if self.export_to_zip: count +=1
 		
 		if count > 1:
-			self.display_msg_and_quit( "Must choose only one action of print, delete, save, copy, rename, or export", 1 )
-		
+			self.display_msg_and_quit( "Must choose only one action of print, delete, save, copy, rename, export, 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
@@ -284,7 +347,8 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 				self.file_list = []
 				for item in args:
 					self.file_list.extend(glob.glob(item))
-				self.filename = self.file_list[0]
+				if len(self.file_list) > 0:
+					self.filename = self.file_list[0]
 			else:
 				self.filename = args[0]
 				self.file_list = args
@@ -304,3 +368,5 @@ For more help visit the wiki at: http://code.google.com/p/comictagger/
 		#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

@@ -3,7 +3,7 @@ A PyQT4 dialog to show pages of a comic archive
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/pagelisteditor.py

@@ -3,7 +3,7 @@ A PyQt4 widget for editing the page list info
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -26,7 +26,7 @@ from PyQt4 import uic
 
 from settings import ComicTaggerSettings
 from genericmetadata import GenericMetadata, PageType
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 from pageloader import PageLoader
 from coverimagewidget import CoverImageWidget
 
@@ -64,7 +64,7 @@ class PageListEditor(QWidget):
 	pageTypeNames = {
 		PageType.FrontCover: "Front Cover",
 		PageType.InnerCover: "Inner Cover",
-		PageType.Advertisment: "Advertisment",
+		PageType.Advertisement: "Advertisement",
 		PageType.Roundup: "Roundup",
 		PageType.Story: "Story",
 		PageType.Editorial: "Editorial",
@@ -92,7 +92,7 @@ class PageListEditor(QWidget):
 		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.Advertisment], PageType.Advertisment )
+		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 )

comictaggerlib/pageloader.py

@@ -3,7 +3,7 @@ A PyQT4 class to load a page image from a ComicArchive in a background thread
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/progresswindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to show ID log and progress
 """
 
 """
-Copyright 2012  Anthony Beville
+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.

comictaggerlib/renamewindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to confirm rename
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -23,7 +23,7 @@ from PyQt4 import QtCore, QtGui, uic
 from settings import ComicTaggerSettings
 from settingswindow import SettingsWindow
 from filerenamer import FileRenamer
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 
 import os
 import utils
@@ -72,7 +72,7 @@ class RenameWindow(QtGui.QDialog):
 
 			md = ca.readMetadata(self.data_style)
 			if md.isEmpty:
-				md = ca.metadataFromFilename()
+				md = ca.metadataFromFilename(self.settings.parse_scan_info)
 			self.renamer.setMetadata( md )
 			new_name = self.renamer.determineName( ca.path, ext=new_ext )		
 

comictaggerlib/settings.py

@@ -3,7 +3,7 @@ Settings class for comictagger app
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -21,8 +21,10 @@ limitations under the License.
 #import sys
 import os
 import sys
-import ConfigParser
+import configparser
 import platform
+import codecs
+import uuid
 
 import utils
 
@@ -30,18 +32,27 @@ class ComicTaggerSettings:
 
 	@staticmethod
 	def getSettingsFolder():
+		filename_encoding = sys.getfilesystemencoding()
 		if platform.system() == "Windows":
-			return os.path.join( os.environ['APPDATA'], 'ComicTagger' )
+			folder = os.path.join( os.environ['APPDATA'], 'ComicTagger' )
 		else:
-			return os.path.join( os.path.expanduser('~') , '.ComicTagger')
-
+			folder = os.path.join( os.path.expanduser('~') , '.ComicTagger')
+		if folder is not None:
+			folder = folder.decode(filename_encoding)
+		return folder
+		
+	frozen_win_exe_path = None
+	
 	@staticmethod
 	def baseDir():
 		if getattr(sys, 'frozen', None):
 			if platform.system() == "Darwin":
 				return sys._MEIPASS
 			else: # Windows
-				return os.path.dirname( os.path.abspath( sys.argv[0] ) )
+				#Preserve this value, in case sys.argv gets changed importing a plugin script
+				if ComicTaggerSettings.frozen_win_exe_path is None:
+					ComicTaggerSettings.frozen_win_exe_path = os.path.dirname( os.path.abspath( sys.argv[0] ) )
+				return ComicTaggerSettings.frozen_win_exe_path
 		else:
 			return os.path.dirname( os.path.abspath( __file__) )
 
@@ -61,8 +72,11 @@ class ComicTaggerSettings:
 		self.rar_exe_path = ""
 		self.unrar_exe_path = ""
 		self.allow_cbi_in_rar = True
+		self.check_for_new_version = True
+		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 = ""
@@ -72,6 +86,8 @@ class ComicTaggerSettings:
 		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
@@ -80,9 +96,17 @@ class ComicTaggerSettings:
 		# 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
+		self.show_no_unrar_warning = 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
 		
 		# CBL Tranform settings
 		
@@ -90,6 +114,7 @@ class ComicTaggerSettings:
 		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
@@ -100,6 +125,13 @@ class ComicTaggerSettings:
 		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
 
 	def __init__(self):
 		
@@ -107,7 +139,7 @@ class ComicTaggerSettings:
 		self.folder = ""
 		self.setDefaultValues()
 
-		self.config = ConfigParser.RawConfigParser()
+		self.config = configparser.RawConfigParser()
 		self.folder = ComicTaggerSettings.getSettingsFolder()
 		
 		if not os.path.exists( self.folder ):
@@ -143,18 +175,35 @@ class ComicTaggerSettings:
 					self.unrar_exe_path = utils.which("unrar")
 			if self.unrar_exe_path != "":
 				self.save()
+				
+		# make sure unrar/rar program is now in the path for the UnRAR class to use
+		utils.addtopath(os.path.dirname(self.unrar_exe_path))
+		utils.addtopath(os.path.dirname(self.rar_exe_path))
 
 	def reset( self ):
 		os.unlink( self.settings_file )
 		self.__init__()
 		
 	def load(self):
-		
-		self.config.read( self.settings_file )
+
+		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' )
 		self.unrar_exe_path =  self.config.get( 'settings', 'unrar_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'):
@@ -173,19 +222,37 @@ class ComicTaggerSettings:
 			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('dialogflags', 'show_no_unrar_warning'):
+			self.show_no_unrar_warning =        self.config.getboolean( 'dialogflags', 'show_no_unrar_warning' )		
+						
 		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('cbl_transform', 'assume_lone_credit_is_primary'):
 			self.assume_lone_credit_is_primary =         self.config.getboolean( 'cbl_transform', 'assume_lone_credit_is_primary' )		
@@ -196,7 +263,9 @@ class ComicTaggerSettings:
 		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' )		
+			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'):
@@ -212,18 +281,32 @@ class ComicTaggerSettings:
 			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' )		
+		
 	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', 'unrar_exe_path', self.unrar_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 )
@@ -233,6 +316,8 @@ class ComicTaggerSettings:
 		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' )
@@ -245,11 +330,21 @@ class ComicTaggerSettings:
 
 		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 )
+		self.config.set( 'dialogflags', 'show_no_unrar_warning', self.show_no_unrar_warning )
 
+		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 )
 
 		if not self.config.has_section( 'cbl_transform' ):
 			self.config.add_section( 'cbl_transform' )
@@ -258,6 +353,7 @@ class ComicTaggerSettings:
 		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 )
@@ -270,7 +366,17 @@ class ComicTaggerSettings:
 		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 )
 		
-		with open( self.settings_file, 'wb') as configfile:
+		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

@@ -3,7 +3,7 @@ A PyQT4 dialog to enter app settings
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -119,8 +119,18 @@ class SettingsWindow(QtGui.QDialog):
 		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)
 	
 		if self.settings.assume_lone_credit_is_primary:
 			self.cbxAssumeLoneCreditIsPrimary.setCheckState( QtCore.Qt.Checked)
@@ -130,6 +140,8 @@ class SettingsWindow(QtGui.QDialog):
 			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:
@@ -153,24 +165,32 @@ class SettingsWindow(QtGui.QDialog):
 		self.settings.rar_exe_path = str(self.leRarExePath.text())
 		self.settings.unrar_exe_path = str(self.leUnrarExePath.text())
 		
-		# make sure unrar program is now in the path for the UnRAR class
+		# make sure unrar/rar program is now in the path for the UnRAR class
 		utils.addtopath(os.path.dirname(self.settings.unrar_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.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()
@@ -184,7 +204,6 @@ class SettingsWindow(QtGui.QDialog):
 		self.settings.save()
 		QtGui.QDialog.accept(self)
 	
-	
 	def selectRar( self ):
 		self.selectFile(  self.leRarExePath, "RAR" )
 	
@@ -225,5 +244,5 @@ class SettingsWindow(QtGui.QDialog):
 			control.setText( str(fileList[0]) )
 
 	def showRenameTab( self ):
-		self.tabWidget.setCurrentIndex(4)	
+		self.tabWidget.setCurrentIndex(5)	
 		

comictaggerlib/taggerwindow.py

@@ -4,7 +4,7 @@ The main window of the ComicTagger app
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -21,7 +21,9 @@ limitations under the License.
 
 from PyQt4 import QtCore, QtGui, uic
 from PyQt4.QtCore import QUrl,pyqtSignal
+from PyQt4 import QtNetwork       
 
+import sys
 import signal
 import locale
 import platform
@@ -30,9 +32,10 @@ import pprint
 import json
 import webbrowser
 import re
+import pickle
 
 from volumeselectionwindow import VolumeSelectionWindow
-from options import MetaDataStyle
+from comicarchive import MetaDataStyle
 from comicinfoxml import ComicInfoXml
 from genericmetadata import GenericMetadata
 from comicvinetalker import ComicVineTalker, ComicVineTalkerException
@@ -55,6 +58,7 @@ from autotagstartwindow import AutoTagStartWindow
 from autotagprogresswindow import AutoTagProgressWindow
 from autotagmatchwindow import AutoTagMatchWindow
 from coverimagewidget import CoverImageWidget
+from versionchecker import VersionChecker
 
 import utils
 import ctversion
@@ -72,21 +76,49 @@ class MultipleMatch():
 	def __init__( self, ca, match_list):
 		self.ca = ca  
 		self.matches = match_list  		
-		
-# this reads the environment and inits the right locale
-locale.setlocale(locale.LC_ALL, "")
 
 class TaggerWindow( QtGui.QMainWindow):
 	
 	appName = "ComicTagger"
 	version = ctversion.version
 	
-	def __init__(self, file_list, settings, parent = None):
+	def __init__(self, file_list, settings, parent = None, opts=None):
 		super(TaggerWindow, self).__init__(parent)
 
 		uic.loadUi(ComicTaggerSettings.getUIFile('taggerwindow.ui' ), self)
 		self.settings = settings
 
+		#----------------------------------
+		# prevent multiple instances
+		socket = QtNetwork.QLocalSocket(self) 
+		socket.connectToServer(settings.install_id)
+		alive = socket.waitForConnected(3000)
+		if alive:
+			print "Another application with key [{}] is already running".format( settings.install_id)
+			# send file list to other instance
+			if len(file_list) > 0:
+				socket.write(pickle.dumps(file_list))
+				if not socket.waitForBytesWritten(3000):
+					print socket.errorString().toLatin1()
+			socket.disconnectFromServer()			
+			sys.exit()
+		else:
+			# listen on a socket to prevent multiple instances
+			self.socketServer = QtNetwork.QLocalServer(self)
+			self.socketServer.newConnection.connect(self.onIncomingSocketConnection)
+			ok = self.socketServer.listen(settings.install_id)
+			if not ok:
+				if self.socketServer.serverError() == QtNetwork.QAbstractSocket.AddressInUseError:
+					#print "Resetting unresponsive socket with key [{}]".format(settings.install_id)
+					self.socketServer.removeServer(settings.install_id)
+					ok = self.socketServer.listen(settings.install_id)
+				if not ok:
+					print "Cannot start local socket with key [{}]. Reason: %s ".format(settings.install_id, self.socketServer.errorString())
+					sys.exit()
+			#print "Registering as single instance with key [{}]".format(settings.install_id)
+		#----------------------------------
+
+
 		self.archiveCoverWidget = CoverImageWidget( self.coverImageContainer, CoverImageWidget.ArchiveMode )
 		gridlayout = QtGui.QGridLayout( self.coverImageContainer )
 		gridlayout.addWidget( self.archiveCoverWidget )
@@ -103,11 +135,8 @@ class TaggerWindow( QtGui.QMainWindow):
 		
 		self.fileSelectionList.selectionChanged.connect( self.fileListSelectionChanged )
 		self.fileSelectionList.listCleared.connect( self.fileListCleared )
-			
-		# ATB: Disable the list...
-		#self.splitter.setSizes([100,0])
-		#self.splitter.setHandleWidth(0)
-		#self.splitter.handle(1).setDisabled(True)
+		self.fileSelectionList.setSorting(self.settings.last_filelist_sorted_column,
+										  self.settings.last_filelist_sorted_order)
 
 		# we can't specify relative font sizes in the UI designer, so
 		# walk through all the lablels in the main form, and make them
@@ -124,6 +153,11 @@ class TaggerWindow( QtGui.QMainWindow):
 		
 		self.setWindowIcon(QtGui.QIcon( ComicTaggerSettings.getGraphic('app.png')))
 
+		if opts is not None and opts.data_style is not None and opts.data_style != MetaDataStyle.COMET:
+			#respect the command line option tag type
+			settings.last_selected_save_data_style = opts.data_style
+			settings.last_selected_load_data_style = opts.data_style
+
 		self.save_data_style = settings.last_selected_save_data_style
 		self.load_data_style = settings.last_selected_load_data_style
 
@@ -151,7 +185,13 @@ class TaggerWindow( QtGui.QMainWindow):
 		
 		#TODO set up an RE validator for issueNum that allows
 		# for all sorts of wacky things
-		
+
+		# tweak some control fonts	
+		utils.reduceWidgetFontSize( self.lblFilename, 1 )
+		utils.reduceWidgetFontSize( self.lblArchiveType )
+		utils.reduceWidgetFontSize( self.lblTagList )
+		utils.reduceWidgetFontSize( self.lblPageCount )
+
 		#make sure some editable comboboxes don't take drop actions
 		self.cbFormat.lineEdit().setAcceptDrops(False)
 		self.cbMaturityRating.lineEdit().setAcceptDrops(False)
@@ -163,6 +203,8 @@ class TaggerWindow( QtGui.QMainWindow):
 		self.btnAddCredit.clicked.connect(self.addCredit)	
 		self.btnRemoveCredit.clicked.connect(self.removeCredit)	
 		self.twCredits.cellDoubleClicked.connect(self.editCredit)
+		self.connectDirtyFlagSignals()
+		self.pageListEditor.modified.connect(self.setDirtyFlag)		
 		self.pageListEditor.firstFrontCoverChanged.connect( self.frontCoverChanged )
 		self.pageListEditor.listOrderChanged.connect( self.pageListOrderChanged )
 		self.tabWidget.currentChanged.connect( self.tabChanged )
@@ -203,7 +245,23 @@ class TaggerWindow( QtGui.QMainWindow):
 								"""
 								)
 			self.settings.show_disclaimer = not checked
-		
+
+		if self.settings.ask_about_usage_stats:
+			reply = QtGui.QMessageBox.question(self, 
+				 self.tr("Anonymous Stats"), 
+				 self.tr(
+						"Is it okay if ComicTagger occasionally sends some anonymous usage statistics?  Nothing nefarious, "
+						"just trying to get a better idea of how the app is being used.\n\nThanks for your support!"
+						),
+				 QtGui.QMessageBox.Yes|QtGui.QMessageBox.Default, QtGui.QMessageBox.No )
+				 
+			if reply == QtGui.QMessageBox.Yes:		
+				self.settings.send_usage_stats = True
+			self.settings.ask_about_usage_stats = False
+				
+		if self.settings.check_for_new_version:
+			self.checkLatestVersionOnline()
+					
 	def sigint_handler(self, *args):
 		# defer the actual close in the app loop thread
 		QtCore.QTimer.singleShot(200, self.close)
@@ -312,7 +370,7 @@ class TaggerWindow( QtGui.QMainWindow):
 		self.actionApplyCBLTransform.setStatusTip( 'Modify tags specifically for CBL format' )
 		self.actionApplyCBLTransform.triggered.connect( self.applyCBLTransform )		
 
-		#self.actionClearEntryForm.setShortcut( 'Ctrl+C' )
+		self.actionClearEntryForm.setShortcut( 'Ctrl+Shift+C' )
 		self.actionClearEntryForm.setStatusTip( 'Clear all the data on the screen' )
 		self.actionClearEntryForm.triggered.connect( self.clearForm )
 
@@ -454,11 +512,11 @@ class TaggerWindow( QtGui.QMainWindow):
 		msgBox.setIconPixmap( QtGui.QPixmap(ComicTaggerSettings.getGraphic('about.png')) )
 		msgBox.setText( "<br><br><br>" 
 		               + self.appName + " v" + self.version + "<br>" 
-		               + "(c)2012 Anthony Beville<br><br>"
+		               + "(c)2014 Anthony Beville<br><br>"
 		               + "<a href='{0}'>{0}</a><br><br>".format(website)
 		               + "<a href='mailto:{0}'>{0}</a><br><br>".format(email) 
 		               + "License: <a href='{0}'>{1}</a>".format(license_link, license_name) )
-							
+
 		msgBox.setStandardButtons( QtGui.QMessageBox.Ok )
 		msgBox.exec_()
 		
@@ -484,7 +542,7 @@ class TaggerWindow( QtGui.QMainWindow):
 
 	def actualLoadCurrentArchive( self ):
 		if self.metadata.isEmpty:
-			self.metadata = self.comic_archive.metadataFromFilename( )
+			self.metadata = self.comic_archive.metadataFromFilename( self.settings.parse_scan_info)
 		if len(self.metadata.pages) == 0:
 			self.metadata.setDefaultPageList( self.comic_archive.getNumberOfPages() )
 
@@ -560,7 +618,7 @@ class TaggerWindow( QtGui.QMainWindow):
 			
 		filename = os.path.basename( ca.path )
 		filename = os.path.splitext(filename)[0]
-		filename = FileNameParser().fixSpaces(filename)
+		filename = FileNameParser().fixSpaces(filename, False)
 
 		self.lblFilename.setText( filename )
 
@@ -850,7 +908,7 @@ class TaggerWindow( QtGui.QMainWindow):
 		if self.comic_archive is not None:
 			#copy the form onto metadata object
 			self.formToMetadata()
-			new_metadata = self.comic_archive.metadataFromFilename( )
+			new_metadata = self.comic_archive.metadataFromFilename(self.settings.parse_scan_info)
 			if new_metadata is not None:
 				self.metadata.overlay( new_metadata )				
 				self.metadataToForm()
@@ -897,7 +955,7 @@ class TaggerWindow( QtGui.QMainWindow):
 		
 	def queryOnline(self, autoselect=False):
 		
-		issue_number = str(self.leIssueNum.text()).strip()
+		issue_number = unicode(self.leIssueNum.text()).strip()
 
 		if autoselect and issue_number == "":
 			QtGui.QMessageBox.information(self,"Automatic Identify Search", "Can't auto-identify without an issue number (yet!)")
@@ -908,14 +966,17 @@ class TaggerWindow( QtGui.QMainWindow):
 		else:
 			QtGui.QMessageBox.information(self, self.tr("Online Search"), self.tr("Need to enter a series name to search."))
 			return
-			
-
+		
 		year = str(self.lePubYear.text()).strip()
 		if year == "":
 			year = None
 
+		issue_count = str(self.leIssueCount.text()).strip()
+		if issue_count == "":
+			issue_count = None
+			
 		cover_index_list =  self.metadata.getCoverPageIndexList()
-		selector = VolumeSelectionWindow( self, series_name, issue_number, year, cover_index_list, self.comic_archive, self.settings, autoselect )
+		selector = VolumeSelectionWindow( self, series_name, issue_number, year, issue_count, cover_index_list, self.comic_archive, self.settings, autoselect )
 
 		title = "Search: '" + series_name + "' - "
 		selector.setWindowTitle( title + "Select Series")
@@ -942,6 +1003,9 @@ class TaggerWindow( QtGui.QMainWindow):
 				
 					if self.settings.apply_cbl_transform_on_cv_import:
 						new_metadata = CBLTransformer( new_metadata, self.settings ).apply()
+
+					if self.settings.clear_form_before_populating_from_cv:					
+						self.clearForm()
 						
 					self.metadata.overlay( new_metadata )				
 					# Now push the new combined data into the edit controls
@@ -953,25 +1017,6 @@ class TaggerWindow( QtGui.QMainWindow):
 	def commitMetadata(self):
 
 		if ( self.metadata is not None and self.comic_archive is not None):	
-		
-			if self.comic_archive.isRar() and self.save_data_style == MetaDataStyle.CBI:
-				if self.settings.ask_about_cbi_in_rar:
-					checked = OptionalMessageDialog.msg(  self, "RAR and ComicBookLover", 
-										"""
-										You are about to write a CBL tag block to a RAR archive! 
-										While technically possible, no known reader can read those tags from RAR
-										yet.<br><br>
-										If you would like this feature in the ComicBookLover apps, please go  to their
-										forums and add your voice to a feature request!
-										<a href=http://forums.comicbooklover.com/categories/ipad-features>
-										http://forums.comicbooklover.com/categories/ipad-features</a><br>
-										<a href=http://forums.comicbooklover.com/categories/mac-features>
-										http://forums.comicbooklover.com/categories/mac-features</a>
-										""",
-										)
-					self.settings.ask_about_cbi_in_rar = not checked
-		
-		
 			reply = QtGui.QMessageBox.question(self, 
 			     self.tr("Save Tags"), 
 			     self.tr("Are you sure you wish to save " +  MetaDataStyle.name[self.save_data_style] + " tags to this archive?"),
@@ -1537,7 +1582,7 @@ class TaggerWindow( QtGui.QMainWindow):
 		# read in metadata, and parse file name if not there
 		md = ca.readMetadata( self.save_data_style )
 		if md.isEmpty:
-			md = ca.metadataFromFilename()
+			md = ca.metadataFromFilename(self.settings.parse_scan_info)
 			if dlg.ignoreLeadingDigitsInFilename and md.series is not None:
 				#remove all leading numbers
 				md.series = re.sub( "([\d.]*)(.*)", "\\2", md.series)
@@ -1750,6 +1795,7 @@ class TaggerWindow( QtGui.QMainWindow):
 			self.settings.last_main_window_y = self.y()
 			self.settings.last_form_side_width = self.splitter.sizes()[0]
 			self.settings.last_list_side_width = self.splitter.sizes()[1]
+			self.settings.last_filelist_sorted_column, self.settings.last_filelist_sorted_order = self.fileSelectionList.getSorting()
 			self.settings.save()
 
 			
@@ -1854,4 +1900,70 @@ class TaggerWindow( QtGui.QMainWindow):
 	def tabChanged( self, idx ):
 		if idx == 0:
 			self.splitterMovedEvent( 0, 0)
+		
+	def checkLatestVersionOnline( self ):
+		self.versionChecker = VersionChecker()
+		self.versionChecker.versionRequestComplete.connect( self.versionCheckComplete )
+		self.versionChecker.asyncGetLatestVersion( self.settings.install_id, self.settings.send_usage_stats )
+	
+	def versionCheckComplete( self, new_version ):
+		if (  new_version != self.version and
+		      new_version != self.settings.dont_notify_about_this_version):
+			website = "http://code.google.com/p/comictagger"
+			checked = OptionalMessageDialog.msg(  self, "New version available!",
+					"New version ({0}) available!<br>(You are currently running {1})<br><br>".format( new_version, self.version) +
+					"Visit <a href='{0}'>{0}</a> for more info.<br><br>".format(website),
+					QtCore.Qt.Unchecked,
+					"Don't tell me about this version again")
+			if checked:
+				self.settings.dont_notify_about_this_version = new_version
 
+	def onIncomingSocketConnection(self):
+		# accept connection from other instance.
+		# read in the file list if they're giving it,
+		# and add to our own list
+		localSocket = self.socketServer.nextPendingConnection()
+		if localSocket.waitForReadyRead(3000):
+			byteArray = localSocket.readAll()
+			if len(byteArray) > 0:
+				obj = pickle.loads(byteArray)
+				localSocket.disconnectFromServer()
+				if type(obj) is list:
+					self.fileSelectionList.addPathList( obj )
+		else:
+			#print localSocket.errorString().toLatin1()
+			pass
+
+		self.bringToTop()
+
+	def bringToTop(self):
+		if platform.system() == "Windows":
+			self.showNormal()
+			self.raise_()
+			self.activateWindow()
+			try:
+				import win32con
+				import win32gui
+				hwnd = self.effectiveWinId()
+				rect = win32gui.GetWindowRect(hwnd)
+				x = rect[0]
+				y = rect[1]
+				w = rect[2] - x
+				h = rect[3] - y
+				# mark it "always on top", just for a moment, to force it to the top
+				win32gui.SetWindowPos(hwnd,win32con.HWND_TOPMOST,   x, y, w, h, 0)
+				win32gui.SetWindowPos(hwnd,win32con.HWND_NOTOPMOST, x, y, w, h, 0)
+			except Exception as e:
+				print "Whoops", e
+		elif platform.system() == "Darwin":
+			self.raise_()
+			self.showNormal()
+			self.activateWindow()
+		else:
+			flags = self.windowFlags() 
+			self.setWindowFlags( flags |  QtCore.Qt.WindowStaysOnTopHint | QtCore.Qt.X11BypassWindowManagerHint)
+			QtCore.QCoreApplication.processEvents()
+			#self.show()
+			self.setWindowFlags( flags )
+			self.show()
+		

comictaggerlib/ui/autotagmatchwindow.ui

@@ -6,21 +6,18 @@
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>907</width>
-    <height>507</height>
+    <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="1">
+   <item row="0" column="0">
     <layout class="QVBoxLayout" name="verticalLayout">
      <item>
       <layout class="QHBoxLayout" name="horizontalLayout">
-       <property name="spacing">
-        <number>0</number>
-       </property>
        <item>
         <widget class="QWidget" name="archiveCoverContainer" native="true">
          <property name="minimumSize">
@@ -38,45 +35,73 @@
         </widget>
        </item>
        <item>
-        <widget class="QTableWidget" name="twList">
-         <property name="selectionMode">
-          <enum>QAbstractItemView::SingleSelection</enum>
+        <widget class="QSplitter" name="splitter">
+         <property name="sizePolicy">
+          <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+           <horstretch>0</horstretch>
+           <verstretch>0</verstretch>
+          </sizepolicy>
          </property>
-         <property name="selectionBehavior">
-          <enum>QAbstractItemView::SelectRows</enum>
+         <property name="orientation">
+          <enum>Qt::Vertical</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">
+         <property name="childrenCollapsible">
           <bool>false</bool>
-         </attribute>
-         <column>
-          <property name="text">
-           <string>Series</string>
+         </property>
+         <widget class="QTableWidget" name="twList">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>7</verstretch>
+           </sizepolicy>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Publisher</string>
+          <property name="selectionMode">
+           <enum>QAbstractItemView::SingleSelection</enum>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Date</string>
+          <property name="selectionBehavior">
+           <enum>QAbstractItemView::SelectRows</enum>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Title</string>
+          <property name="rowCount">
+           <number>0</number>
           </property>
-         </column>
+          <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>

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/issueselectionwindow.ui

@@ -6,51 +6,90 @@
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>657</width>
-    <height>400</height>
+    <width>872</width>
+    <height>550</height>
    </rect>
   </property>
   <property name="windowTitle">
    <string>Select Issue</string>
   </property>
-  <layout class="QGridLayout" name="gridLayout">
+  <layout class="QGridLayout" name="gridLayout_2">
    <item row="0" column="0">
     <layout class="QVBoxLayout" name="verticalLayout">
      <item>
       <layout class="QHBoxLayout" name="horizontalLayout">
+       <property name="spacing">
+        <number>6</number>
+       </property>
        <item>
-        <widget class="QTableWidget" name="twList">
-         <property name="selectionMode">
-          <enum>QAbstractItemView::SingleSelection</enum>
+        <widget class="QSplitter" name="splitter">
+         <property name="sizePolicy">
+          <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+           <horstretch>0</horstretch>
+           <verstretch>0</verstretch>
+          </sizepolicy>
          </property>
-         <property name="selectionBehavior">
-          <enum>QAbstractItemView::SelectRows</enum>
+         <property name="orientation">
+          <enum>Qt::Vertical</enum>
          </property>
-         <property name="rowCount">
-          <number>0</number>
-         </property>
-         <property name="columnCount">
-          <number>2</number>
-         </property>
-         <attribute name="horizontalHeaderStretchLastSection">
-          <bool>true</bool>
-         </attribute>
-         <attribute name="verticalHeaderVisible">
+         <property name="childrenCollapsible">
           <bool>false</bool>
-         </attribute>
-         <column>
-          <property name="text">
-           <string>Issue</string>
+         </property>
+         <widget class="QTableWidget" name="twList">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>7</verstretch>
+           </sizepolicy>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Title</string>
+          <property name="selectionMode">
+           <enum>QAbstractItemView::SingleSelection</enum>
           </property>
-          <property name="textAlignment">
-           <set>AlignHCenter|AlignVCenter|AlignCenter</set>
+          <property name="selectionBehavior">
+           <enum>QAbstractItemView::SelectRows</enum>
           </property>
-         </column>
+          <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>Issue</string>
+           </property>
+          </column>
+          <column>
+           <property name="text">
+            <string>Date</string>
+           </property>
+          </column>
+          <column>
+           <property name="text">
+            <string>Title</string>
+           </property>
+           <property name="textAlignment">
+            <set>AlignHCenter|AlignVCenter|AlignCenter</set>
+           </property>
+          </column>
+         </widget>
+         <widget class="QTextEdit" name="teDescription">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>3</verstretch>
+           </sizepolicy>
+          </property>
+          <property name="textInteractionFlags">
+           <set>Qt::TextSelectableByKeyboard|Qt::TextSelectableByMouse</set>
+          </property>
+         </widget>
         </widget>
        </item>
        <item>

comictaggerlib/ui/matchselectionwindow.ui

@@ -6,21 +6,18 @@
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>907</width>
-    <height>507</height>
+    <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="1">
+   <item row="0" column="0">
     <layout class="QVBoxLayout" name="verticalLayout">
      <item>
       <layout class="QHBoxLayout" name="horizontalLayout">
-       <property name="spacing">
-        <number>0</number>
-       </property>
        <item>
         <widget class="QWidget" name="archiveCoverContainer" native="true">
          <property name="minimumSize">
@@ -38,45 +35,73 @@
         </widget>
        </item>
        <item>
-        <widget class="QTableWidget" name="twList">
-         <property name="selectionMode">
-          <enum>QAbstractItemView::SingleSelection</enum>
+        <widget class="QSplitter" name="splitter">
+         <property name="sizePolicy">
+          <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+           <horstretch>0</horstretch>
+           <verstretch>0</verstretch>
+          </sizepolicy>
          </property>
-         <property name="selectionBehavior">
-          <enum>QAbstractItemView::SelectRows</enum>
+         <property name="orientation">
+          <enum>Qt::Vertical</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">
+         <property name="childrenCollapsible">
           <bool>false</bool>
-         </attribute>
-         <column>
-          <property name="text">
-           <string>Series</string>
+         </property>
+         <widget class="QTableWidget" name="twList">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+            <horstretch>0</horstretch>
+            <verstretch>7</verstretch>
+           </sizepolicy>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Publisher</string>
+          <property name="selectionMode">
+           <enum>QAbstractItemView::SingleSelection</enum>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Date</string>
+          <property name="selectionBehavior">
+           <enum>QAbstractItemView::SelectRows</enum>
           </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Title</string>
+          <property name="rowCount">
+           <number>0</number>
           </property>
-         </column>
+          <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>

comictaggerlib/ui/settingswindow.ui

@@ -35,7 +35,7 @@
             <string/>
            </property>
            <layout class="QGridLayout" name="gridLayout_4">
-            <item row="0" column="0">
+            <item row="1" column="0">
              <widget class="QPushButton" name="btnResetSettings">
               <property name="sizePolicy">
                <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
@@ -48,7 +48,7 @@
               </property>
              </widget>
             </item>
-            <item row="0" column="1">
+            <item row="1" column="1">
              <widget class="QLabel" name="lblDefaultSettings">
               <property name="sizePolicy">
                <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
@@ -64,7 +64,7 @@
               </property>
              </widget>
             </item>
-            <item row="1" column="0">
+            <item row="2" column="0">
              <widget class="QPushButton" name="btnClearCache">
               <property name="sizePolicy">
                <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
@@ -77,7 +77,7 @@
               </property>
              </widget>
             </item>
-            <item row="1" column="1">
+            <item row="2" column="1">
              <widget class="QLabel" name="label_2">
               <property name="sizePolicy">
                <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
@@ -93,6 +93,13 @@
               </property>
              </widget>
             </item>
+            <item row="0" column="0" colspan="2">
+             <widget class="QCheckBox" name="cbxCheckForNewVersion">
+              <property name="text">
+               <string>Check for new version on startup</string>
+              </property>
+             </widget>
+            </item>
            </layout>
           </widget>
          </item>
@@ -307,6 +314,24 @@
          </item>
         </layout>
        </widget>
+       <widget class="QWidget" name="tab_6">
+        <attribute name="title">
+         <string>Filename Parser</string>
+        </attribute>
+        <widget class="QCheckBox" name="cbxParseScanInfo">
+         <property name="geometry">
+          <rect>
+           <x>30</x>
+           <y>30</y>
+           <width>421</width>
+           <height>25</height>
+          </rect>
+         </property>
+         <property name="text">
+          <string>Parse Scan Info From Filename (Experimental)</string>
+         </property>
+        </widget>
+       </widget>
        <widget class="QWidget" name="tab_3">
         <attribute name="title">
          <string>Comic Vine</string>
@@ -316,7 +341,7 @@
           <rect>
            <x>30</x>
            <y>30</y>
-           <width>240</width>
+           <width>251</width>
            <height>25</height>
           </rect>
          </property>
@@ -324,6 +349,32 @@
           <string>Use Series Start Date as Volume</string>
          </property>
         </widget>
+        <widget class="QCheckBox" name="cbxClearFormBeforePopulating">
+         <property name="geometry">
+          <rect>
+           <x>30</x>
+           <y>50</y>
+           <width>341</width>
+           <height>25</height>
+          </rect>
+         </property>
+         <property name="text">
+          <string>Clear Form Before Importing Comic Vine data</string>
+         </property>
+        </widget>
+        <widget class="QCheckBox" name="cbxRemoveHtmlTables">
+         <property name="geometry">
+          <rect>
+           <x>30</x>
+           <y>70</y>
+           <width>351</width>
+           <height>25</height>
+          </rect>
+         </property>
+         <property name="text">
+          <string>Remove HTML tables from CV summary field</string>
+         </property>
+        </widget>
        </widget>
        <widget class="QWidget" name="tab_4">
         <attribute name="title">
@@ -360,11 +411,18 @@
              <rect>
               <x>11</x>
               <y>21</y>
-              <width>246</width>
-              <height>182</height>
+              <width>251</width>
+              <height>192</height>
              </rect>
             </property>
             <layout class="QGridLayout" name="gridLayout_7">
+             <item row="3" column="0">
+              <widget class="QCheckBox" name="cbxCopyLocationsToTags">
+               <property name="text">
+                <string>Copy Locations to Generic Tags</string>
+               </property>
+              </widget>
+             </item>
              <item row="0" column="0">
               <widget class="QCheckBox" name="cbxAssumeLoneCreditIsPrimary">
                <property name="text">
@@ -386,27 +444,27 @@
                </property>
               </widget>
              </item>
-             <item row="3" column="0">
-              <widget class="QCheckBox" name="cbxCopyLocationsToTags">
-               <property name="text">
-                <string>Copy Locations to Generic Tags</string>
-               </property>
-              </widget>
-             </item>
-             <item row="4" column="0">
+             <item row="5" column="0">
               <widget class="QCheckBox" name="cbxCopyNotesToComments">
                <property name="text">
                 <string>Copy Notes to Comments</string>
                </property>
               </widget>
              </item>
-             <item row="5" column="0">
+             <item row="6" column="0">
               <widget class="QCheckBox" name="cbxCopyWebLinkToComments">
                <property name="text">
                 <string>Copy Web Link to Comments</string>
                </property>
               </widget>
              </item>
+             <item row="4" column="0">
+              <widget class="QCheckBox" name="cbxCopyStoryArcsToTags">
+               <property name="text">
+                <string>Copy Story Arcs to Generic Tags</string>
+               </property>
+              </widget>
+             </item>
             </layout>
            </widget>
           </widget>

comictaggerlib/ui/taggerwindow.ui

@@ -7,7 +7,7 @@
     <x>0</x>
     <y>0</y>
     <width>1096</width>
-    <height>575</height>
+    <height>621</height>
    </rect>
   </property>
   <property name="sizePolicy">
@@ -91,23 +91,26 @@
             </property>
             <property name="minimumSize">
              <size>
-              <width>220</width>
+              <width>230</width>
               <height>0</height>
              </size>
             </property>
             <property name="maximumSize">
              <size>
-              <width>220</width>
+              <width>230</width>
               <height>16777215</height>
              </size>
             </property>
             <property name="frameShape">
-             <enum>QFrame::StyledPanel</enum>
+             <enum>QFrame::Panel</enum>
             </property>
             <property name="frameShadow">
-             <enum>QFrame::Raised</enum>
+             <enum>QFrame::Sunken</enum>
             </property>
             <layout class="QVBoxLayout" name="verticalLayout_4">
+             <property name="margin">
+              <number>6</number>
+             </property>
              <item>
               <widget class="QLabel" name="lblFilename">
                <property name="sizePolicy">
@@ -1092,7 +1095,7 @@
      <x>0</x>
      <y>0</y>
      <width>1096</width>
-     <height>21</height>
+     <height>22</height>
     </rect>
    </property>
    <widget class="QMenu" name="menuComicTagger">

comictaggerlib/ui/volumeselectionwindow.ui

@@ -42,17 +42,20 @@
          <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="MinimumExpanding">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
             <horstretch>0</horstretch>
-            <verstretch>0</verstretch>
+            <verstretch>7</verstretch>
            </sizepolicy>
           </property>
           <property name="minimumSize">
            <size>
             <width>0</width>
-            <height>250</height>
+            <height>0</height>
            </size>
           </property>
           <property name="selectionMode">
@@ -102,15 +105,15 @@
          </widget>
          <widget class="QTextEdit" name="teDetails">
           <property name="sizePolicy">
-           <sizepolicy hsizetype="Expanding" vsizetype="Maximum">
+           <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
             <horstretch>0</horstretch>
-            <verstretch>0</verstretch>
+            <verstretch>3</verstretch>
            </sizepolicy>
           </property>
           <property name="maximumSize">
            <size>
             <width>16777215</width>
-            <height>200</height>
+            <height>16777215</height>
            </size>
           </property>
           <property name="readOnly">

comictaggerlib/utils.py

@@ -5,7 +5,7 @@ Some generic utilities
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -19,9 +19,63 @@ 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 getattr(sys, 'frozen', None) and 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 recursivly, and all files underneath
+		if type(p) == str:
+			#make sure string is unicode
+			p = p.decode(filename_encoding) #, 'replace')
+		elif type(p) != unicode:
+			#it's probably a QString
+			p = unicode(p)
+		
+		if os.path.isdir( p ):
+			for root,dirs,files in os.walk( p ):
+				for f in files:
+					if type(f) == str:
+						#make sure string is unicode
+						f = f.decode(filename_encoding, 'replace')
+					elif type(f) != unicode:
+						#it's probably a QString
+						f = unicode(f)
+					filelist.append(os.path.join(root,f))
+		else:
+			filelist.append(p)
+	
+	return filelist
+	
 def listToString( l ):
 	string = ""
 	if l is not None:
@@ -31,10 +85,16 @@ def listToString( l ):
 			string += item 
 	return string
 		
-def addtopath( dir ):
-	# TODO only add if not there already
-	if dir is not None and dir != "": 
-		os.environ['PATH'] = dir + os.pathsep + os.environ['PATH']
+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']
 
 # returns executable path, if it exists
 def which(program):
@@ -66,9 +126,13 @@ def removearticles( text ):
 	
 	# now get rid of some other junk
 	newText = newText.replace(":", "")
-	newText = newText.replace(".", "")
 	newText = newText.replace(",", "")
 	newText = newText.replace("-", " ")
+
+	# since the CV api changed, searches for series names with periods
+	# now explicity require the period to be in the search key,
+	# so the line below is removed (for now)
+	#newText = newText.replace(".", "")
 	
 	return newText
 

comictaggerlib/versionchecker.py

@@ -0,0 +1,94 @@
+"""
+Version checker
+"""
+
+"""
+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
+import platform
+import urllib,urllib2
+import ctversion
+
+try:
+	from PyQt4.QtNetwork import QNetworkAccessManager, QNetworkRequest, QNetworkReply
+	from PyQt4.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
+			
+class VersionChecker(QObject):
+
+	def getRequestUrl( self, uuid, use_stats ):
+	
+		base_url = "http://comictagger1.appspot.com/latest"
+		args = ""
+		
+		if use_stats:
+			if platform.system() == "Windows":
+				plat = "win"
+			elif platform.system() == "Linux":
+				plat = "lin"
+			elif platform.system() == "Darwin":
+				plat = "mac"
+			else:
+				plat = "other"
+			args = "?uuid={0}&platform={1}&version={2}".format(uuid, plat, ctversion.version)
+			if not getattr(sys, 'frozen', None):
+				args += "&src=T"
+
+		return base_url+args
+		
+	def getLatestVersion( self, uuid, use_stats=True):
+		
+		try:
+			resp = urllib2.urlopen( self.getRequestUrl(uuid, use_stats ))
+			new_version = resp.read()
+		except Exception as e:
+			return None
+			
+		if new_version is None or new_version == "":
+			return None
+		return new_version.strip()
+
+	versionRequestComplete = pyqtSignal( str )
+	
+	def asyncGetLatestVersion( self, uuid, use_stats ):
+
+		url = self.getRequestUrl( uuid, use_stats )
+			
+		self.nam = QNetworkAccessManager()
+		self.nam.finished.connect( self.asyncGetLatestVersionComplete )
+		self.nam.get(QNetworkRequest(QUrl(str(url))))
+		
+	def asyncGetLatestVersionComplete( self, reply ):
+		if (reply.error() != QNetworkReply.NoError):
+			return
+			
+		# read in the response
+		new_version = str(reply.readAll())
+
+		if new_version is None or new_version == "":
+			return
+
+		self.versionRequestComplete.emit( new_version.strip() )	

comictaggerlib/volumeselectionwindow.py

@@ -3,7 +3,7 @@ A PyQT4 dialog to select specific series/volume from list
 """
 
 """
-Copyright 2012  Anthony Beville
+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.
@@ -87,7 +87,7 @@ class IdentifyThread( QtCore.QThread):
 
 class VolumeSelectionWindow(QtGui.QDialog):
 
-	def __init__(self, parent, series_name, issue_number, year, cover_index_list, comic_archive, settings, autoselect=False):
+	def __init__(self, parent, series_name, issue_number, year, issue_count, cover_index_list, comic_archive, settings, autoselect=False):
 		super(VolumeSelectionWindow, self).__init__(parent)
 		
 		uic.loadUi(ComicTaggerSettings.getUIFile('volumeselectionwindow.ui' ), self)
@@ -108,6 +108,7 @@ class VolumeSelectionWindow(QtGui.QDialog):
 		self.series_name = series_name
 		self.issue_number = issue_number
 		self.year = year
+		self.issue_count = issue_count
 		self.volume_id = 0
 		self.comic_archive = comic_archive
 		self.immediate_autoselect = autoselect
@@ -161,10 +162,11 @@ class VolumeSelectionWindow(QtGui.QDialog):
 		md.series = self.series_name
 		md.issue = self.issue_number
 		md.year = self.year
+		md.issueCount = self.issue_count
 
 		self.ii.setAdditionalMetadata( md )
 		self.ii.onlyUseAdditionalMetaData = True
-		print self.cover_index_list
+
 		self.ii.cover_page_index = int(self.cover_index_list[0])
 		
 		self.id_thread = IdentifyThread( self.ii )
@@ -369,7 +371,9 @@ class VolumeSelectionWindow(QtGui.QDialog):
 		# list selection was changed, update the info on the volume
 		for record in self.cv_search_results: 
 			if record['id'] == self.volume_id:
-
-				self.teDetails.setText ( record['description'] )
+				if record['description'] is None:
+					self.teDetails.setText ( "" )
+				else:	
+					self.teDetails.setText ( record['description'] )
 				self.imageWidget.setURL( record['image']['super_url'] )
 				break

current_version.txt

@@ -0,0 +1 @@
+1.1.7-beta

debian_scripts/after_install.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-mv /usr/bin/comictagger.py /usr/bin/comictagger

debian_scripts/before_remove.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-mv /usr/bin/comictagger /usr/bin/comictagger.py

google/gadgets/social.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8" ?> 
+<Module>
+  <ModulePrefs title="mygaget" /> 
+  <Content type="html">
+     <![CDATA[ 
+<a href="https://twitter.com/ComicTagger" class="twitter-follow-button" data-show-count="false" data-size="large">Follow @ComicTagger</a>
+<script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0];if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src="//platform.twitter.com/widgets.js";fjs.parentNode.insertBefore(js,fjs);}}(document,"script","twitter-wjs");</script>
+<iframe allowtransparency="true" frameborder="0" scrolling="no" src="http://www.facebook.com/plugins/likebox.php?href=http%3A%2F%2Fwww.facebook.com%2Fpages%2FComictagger/139615369550787&amp;width=292&amp;colorscheme=light&amp;show_faces =false&amp;border_color&amp;stream=false&amp;header=false&amp;height=62" style="background-color: white; border-bottom-style: none; border-color: initial; border-left-style: none; border-right-style: none; border-top-style: none; border-width: initial; color: #333333; font-family: Verdana; font-size: 12px; height: 62px; line-height: 19px; overflow-x: hidden; overflow-y: hidden; text-align: -webkit-auto; width: 292px;"></iframe>
+     ]]>
+  </Content> 
+</Module>

google/gadgets/twitter.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8" ?> 
+<Module>
+  <ModulePrefs title="mygaget" /> 
+  <Content type="html">
+     <![CDATA[ 
+<a href="https://twitter.com/ComicTagger" class="twitter-follow-button" data-show-count="false" data-size="large">Follow @ComicTagger</a>
+<script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0];if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src="//platform.twitter.com/widgets.js";fjs.parentNode.insertBefore(js,fjs);}}(document,"script","twitter-wjs");</script>
+     ]]>
+  </Content> 
+</Module>

mac/Makefile

@@ -1,5 +1,6 @@
+#PYINSTALLER_CMD := VERSIONER_PYTHON_PREFER_32_BIT=yes arch -i386 python $(HOME)/pyinstaller-2.0/pyinstaller.py
 PYINSTALLER_CMD := python $(HOME)/pyinstaller-2.0/pyinstaller.py
-TAGGER_BASE := $(HOME)/Dropbox/tagger/comictagger
+TAGGER_BASE ?= $(HOME)/Dropbox/tagger/comictagger
 TAGGER_SRC := $(TAGGER_BASE)/comictaggerlib
 
 APP_NAME := ComicTagger
@@ -19,7 +20,17 @@ dist:
 	cp -a $(TAGGER_SRC)/ui $(APP_BUNDLE)/Contents/MacOS
 	cp -a $(TAGGER_SRC)/graphics $(APP_BUNDLE)/Contents/MacOS
 	cp $(MAC_BASE)/app.icns $(APP_BUNDLE)/Contents/Resources/icon-windowed.icns
-	
+	# fix the version string in the Info.plist
+	sed -i -e 's/0\.0\.0/$(VERSION_STR)/' $(MAC_BASE)/dist/ComicTagger.app/Contents/Info.plist
+	# strip out PPC/x64
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/accessible
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/bearer
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/codecs
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/graphicssystems
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/iconengines
+	#./make_thin.sh dist/ComicTagger.app/Contents/MacOS/qt4_plugins/imageformats
+
 clean:
 	rm -rf $(DIST_DIR) $(MAC_BASE)/build
 	rm -f $(MAC_BASE)/*.spec
@@ -59,5 +70,6 @@ diskimage:
 	rm -f raw-$(DMG_FILE)
 	
 	#move finished product to release folder
+	mkdir -p $(TAGGER_BASE)/release
 	mv $(DMG_FILE) $(TAGGER_BASE)/release
 	

mac/make_thin.sh

@@ -0,0 +1,21 @@
+rm -rf thin
+BINFOLDER=$1
+LIST=`cd $BINFOLDER; ls Qt* *.so *.dylib Python 2>/dev/null`
+for FILE in $LIST
+do
+	ISFAT=`lipo -info $BINFOLDER/$FILE|grep -v Non-fat`
+	if [ "$ISFAT" != "" ]
+	then
+		echo "Fat Binary:  $FILE"
+		mkdir -p thin
+		lipo -thin i386 -output thin/$FILE $BINFOLDER/$FILE 
+	fi
+done
+
+if [ -d thin ]
+then 
+	mv thin/* $BINFOLDER
+else
+	echo No files to lipo
+fi
+rm -rf thin

release_notes.txt

@@ -1,106 +1,209 @@
----------------------------------  
-1.1.0-beta - 06-Feb-2013
----------------------------------
-Changes:
-	* Enhanced identification process to use alternative covers from ComicVine
-	* Post auto-tag manual matching now includes single low-confidence matches (CLI & GUI)
-	* Page and cover view mini-browser available throughout app.  Most images can be
-         double-clicked for embiggened view
-	* Export-to-zip in CLI (very handy in scripts!)
-	* More rename template variables
-	* Misc GUI & CLI Tweaks 
-
----------------------------------  
-1.0.3-beta - 31-Jan-2013
----------------------------------
-Changes:
-	Misc bug fixes and enhancements
-	
----------------------------------  
-1.0.2-beta - 25-Jan-2013
----------------------------------
-Changes:
-	More verbose logging during auto-tag
-	Added %month% and %month_name% for renaming
-	Better parsing of volume numbers in file name
-Bugs:
-	Better exception handling with corrupted image data
-	Fixed issues with RAR reading on OS X
-	Other minor bug fixes
-	
----------------------------------  
-1.0.1-beta - 24-Jan-2013
----------------------------------
-Bug Fix:
-	Fixed an issue where unicode strings can't be printed to OS X Console
-
----------------------------------  
-1.0.0-beta - 23-Jan-2013
----------------------------------
-Version 1!  New multi-file processing in GUI!
-
-GUI Changes:
-  Open multiple files and/or folders via drag/drop or file dialog
-  File management list for easy viewing and selection
-  Batch tag remove
-  Batch export as zip
-  Batch rename
-  Batch tag copy
-  Batch auto-tag (automatic identification and save!)
-  
----------------------------------  
-0.9.5-beta - 16-Jan-2013
----------------------------------
-Changes:
-  Added CLI option to search by comicvine issue ID
-  Some image loading optimizations
-  Bug Fix:  Some CBL fields that should have been ints were written as strings
-
----------------------------------  
-0.9.4-beta - 7-Jan-2013
----------------------------------
-Changes:
-  Better handling of non-ascii characters in filenames and data
-  Add CBL Transform to copy Web Link and Notes to comments
-  Minor bug fixes
-
----------------------------------  
-0.9.3-beta - 19-Dec-2012
----------------------------------
-Changes:
-  File rename in GUI
-  Setting for file rename
-  Option to use series start year as volume
-  Added "CBL Transform" to handle primary credits copying data into the generic tags field
-  Bug Fix:  unicode characters in credits caused crash 
-  Bug Fix:  bad or non-image data in file caused crash 
-
-Note:
-  The user should clear the cache and delete the existing settings when first running this version.
-  
----------------------------------  
-0.9.2-beta - 13-Dec-2012
----------------------------------
-  Page List/Type editing in GUI
-  File globbing for windows CLI (i.e. use of wildcards like '*.cbz')
-  Fixed RAR writing bug on windows
-  Minor bug and crash fixes
-
----------------------------------  
-0.9.1-beta - 07-Dec-2012
----------------------------------
-  Export as ZIP Archive
-  Added help menu option for websites
-  Added Primary Credit Flag editing
-  Menu enhancements
-  CLI Enhancements:
-	Interactive selection of matches
-	Tag copy
-	Better output
-	CoMet support
-  Minor bug and crash fixes
-
----------------------------------  
-0.9.0-beta - 30-Nov-2012
----------------------------------
-Initial beta release
+---------------------------------  
+1.1.14-beta - 13-Apr-2014
+---------------------------------
+ * Make sure app gets raised when enforcing single instance
+ * Added warning dialog for when opening rar files, and no (un)rar tool 
+ * remove pil from python package requirements
+
+---------------------------------  
+1.1.13-beta - 9-Apr-2014
+---------------------------------
+ * Handle non-ascii usernames properly
+ * better parsing of html table in summary text, and optional removal
+ * Python package should auto-install requirements
+ * Specify default GUI tag style on command-line
+ * enforce single GUI instance
+ * new CBL tranform to copy story arcs to generic tags
+ * Persist some auto-tag settings
+
+---------------------------------  
+1.1.12-beta - 23-Mar-2014
+---------------------------------
+ * Fixed noisy version update error
+
+---------------------------------  
+1.1.11-beta - 23-Mar-2014
+---------------------------------
+ * Updated unrar library to hand Rar tools 5.0 and greater
+ * Other misc bug fixes
+
+---------------------------------  
+1.1.10-beta - 30-Jan-2014
+---------------------------------
+ * Updated series query to match changes on Comic Vine side
+ * Added a message when not able to open a file or folder
+ * Fixed an issue where series names with periods would fail on search 
+ * Other misc bug fixes
+
+---------------------------------  
+1.1.9-beta - 8-May-2013
+---------------------------------
+ * Filename parser and identification enhancements
+ * Misc bug fixes
+
+---------------------------------  
+1.1.8-beta - 21-Apr-2013
+---------------------------------
+ * Handle occasional error 500 from Comic Vine by retrying a few times
+ * Nicer handling of colon (":") in file rename
+ * Fixed command-line option parsing issue for add-on scripts
+ * Misc bug fixes
+
+---------------------------------  
+1.1.7-beta - 12-Apr-2013
+---------------------------------
+ * Added description and cover date to issue selection dialogs
+ * Added notification of new version
+ * Added setting to attempt to parse scan info from file name
+ * Last sorted column in the file list is now remembered
+ * Added CLI option ('-1') to assume issue #1 if not found/parsed
+ * Misc bug fixes
+
+---------------------------------  
+1.1.6-beta - 3-Apr-2013
+---------------------------------
+ * More ComicVine API-related fixes
+ * More efficient automated search using new CV API issue filters
+ * Minor bug fixes
+ 
+---------------------------------  
+1.1.5-beta - 30-Mar-2013
+---------------------------------
+ * More updates for handling changes to ComicVine API and result sets
+ * Even better handling of non-numeric issue "numbers" ("½", "X")
+
+---------------------------------  
+1.1.4-beta - 27-Mar-2013
+---------------------------------
+ * Updated to match the changes to the ComicVine API and result sets
+ * Better handling of weird issue numbers ("0.1", "6au")
+
+---------------------------------  
+1.1.3-beta - 25-Feb-2013
+---------------------------------
+Bug Fixes:
+	* Fixed a bug when renaming on non-English systems
+	* Fixed issue when saving settings on non-English systems
+	* Fixed a bug when comic contains non-RGB images
+	* Fixed a rare crash when comic image is not-RGB format
+	* Fixed sequence order of ComicInfo.xml items
+
+Note:
+  New requirement for users of the python package:  "configparser"
+
+---------------------------------  
+1.1.2-beta - 14-Feb-2013
+---------------------------------
+Changes:
+	* Source is now packaged using Python distutils
+	* Recursive mode for CLI
+	* Run custom add-on scripts from CLI
+	* Minor UI tweaks
+	* Misc bug fixes
+
+---------------------------------  
+1.1.0-beta - 06-Feb-2013
+---------------------------------
+Changes:
+	* Enhanced identification process to use alternative covers from ComicVine
+	* Post auto-tag manual matching now includes single low-confidence matches (CLI & GUI)
+	* Page and cover view mini-browser available throughout app.  Most images can be
+         double-clicked for embiggened view
+	* Export-to-zip in CLI (very handy in scripts!)
+	* More rename template variables
+	* Misc GUI & CLI Tweaks
+
+---------------------------------  
+1.0.3-beta - 31-Jan-2013
+---------------------------------
+Changes:
+	Misc bug fixes and enhancements
+	
+---------------------------------  
+1.0.2-beta - 25-Jan-2013
+---------------------------------
+Changes:
+	More verbose logging during auto-tag
+	Added %month% and %month_name% for renaming
+	Better parsing of volume numbers in file name
+Bugs:
+	Better exception handling with corrupted image data
+	Fixed issues with RAR reading on OS X
+	Other minor bug fixes
+	
+---------------------------------  
+1.0.1-beta - 24-Jan-2013
+---------------------------------
+Bug Fix:
+	Fixed an issue where unicode strings can't be printed to OS X Console
+
+---------------------------------  
+1.0.0-beta - 23-Jan-2013
+---------------------------------
+Version 1!  New multi-file processing in GUI!
+
+GUI Changes:
+  Open multiple files and/or folders via drag/drop or file dialog
+  File management list for easy viewing and selection
+  Batch tag remove
+  Batch export as zip
+  Batch rename
+  Batch tag copy
+  Batch auto-tag (automatic identification and save!)
+  
+---------------------------------  
+0.9.5-beta - 16-Jan-2013
+---------------------------------
+Changes:
+  Added CLI option to search by comicvine issue ID
+  Some image loading optimizations
+  Bug Fix:  Some CBL fields that should have been ints were written as strings
+
+---------------------------------  
+0.9.4-beta - 7-Jan-2013
+---------------------------------
+Changes:
+  Better handling of non-ascii characters in filenames and data
+  Add CBL Transform to copy Web Link and Notes to comments
+  Minor bug fixes
+
+---------------------------------  
+0.9.3-beta - 19-Dec-2012
+---------------------------------
+Changes:
+  File rename in GUI
+  Setting for file rename
+  Option to use series start year as volume
+  Added "CBL Transform" to handle primary credits copying data into the generic tags field
+  Bug Fix:  unicode characters in credits caused crash 
+  Bug Fix:  bad or non-image data in file caused crash 
+
+Note:
+  The user should clear the cache and delete the existing settings when first running this version.
+  
+---------------------------------  
+0.9.2-beta - 13-Dec-2012
+---------------------------------
+  Page List/Type editing in GUI
+  File globbing for windows CLI (i.e. use of wildcards like '*.cbz')
+  Fixed RAR writing bug on windows
+  Minor bug and crash fixes
+
+---------------------------------  
+0.9.1-beta - 07-Dec-2012
+---------------------------------
+  Export as ZIP Archive
+  Added help menu option for websites
+  Added Primary Credit Flag editing
+  Menu enhancements
+  CLI Enhancements:
+	Interactive selection of matches
+	Tag copy
+	Better output
+	CoMet support
+  Minor bug and crash fixes
+
+---------------------------------  
+0.9.0-beta - 30-Nov-2012
+---------------------------------
+Initial beta release

requirements.txt

@@ -0,0 +1,2 @@
+configparser
+beautifulsoup4 >= 4.1

scripts/README.txt

@@ -0,0 +1,30 @@
+This folder contains a set of example scripts that be used to extend the
+capabilities of the ComicTagger app.  They can be run either directly through
+the python interpreter, or via the ComicTagger app.
+
+To run via python directly, install ComicTagger source on your system using
+the setup.py file.
+
+To run via the ComicTagger app, invoke:
+
+# comictagger.py -S script.py [script args]
+
+(This will work also for binary distributions on Mac and Windows.  No need for
+an extra python install.)
+
+The script must have an entry point function called "main()" to be invoked
+via the app.
+
+-----------------------------------------------------------------------------
+
+This feature is UNSUPPORTED, and is for the convenience of development-minded
+users of ComicTagger.  The comictaggerlib module will remain largely
+undocumented, and it will up to the crafty script developer to look through
+the code to discern APIs and such.
+
+That said, if there are questions, please post in the forums, and hopefully we
+can get your add-on scripts working!
+
+http://comictagger.forumotion.com/
+
+

scripts/find_dupes.py

@@ -0,0 +1,84 @@
+#!/usr/bin/python
+"""
+find all duplicate comics
+"""
+
+import sys
+
+from comictaggerlib.comicarchive import *
+from comictaggerlib.settings import *
+from comictaggerlib.issuestring import *
+import comictaggerlib.utils
+
+
+def main():
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	style = MetaDataStyle.CIX
+
+	if len(sys.argv) < 2:
+		print >> sys.stderr, "usage:  {0} comic_folder ".format(sys.argv[0])
+		return
+		
+	filelist = utils.get_recursive_filelist( sys.argv[1:] )
+	
+	#first find all comics with metadata
+	print >> sys.stderr, "reading in all comics..."
+	comic_list = []
+	max_name_len = 2
+	for filename in filelist:
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		if ca.seemsToBeAComicArchive() and ca.hasMetadata( style ):
+			max_name_len = max ( max_name_len, len(filename))
+			fmt_str = u"{{0:{0}}}".format(max_name_len)
+			print >> sys.stderr, fmt_str.format( filename ) + "\r",
+			sys.stderr.flush()
+			comic_list.append((filename, ca.readMetadata( style )))
+
+	print >> sys.stderr, fmt_str.format( "" ) + "\r",
+	print "-----------------------------------------------"
+	print "Found {0} comics with {1} tags".format( len(comic_list), MetaDataStyle.name[style])
+	print "-----------------------------------------------"
+
+	#sort the list by series+issue+year, to put all the dupes together
+	def makeKey(x):
+		return "<" + unicode(x[1].series) + u" #" + unicode( x[1].issue ) +  u" - " + unicode( x[1].year ) + ">" 
+	comic_list.sort(key=makeKey, reverse=False)
+
+	# look for duplicate blocks
+	dupe_set_list = list()
+	dupe_set = list()
+	prev_key = ""
+	for filename, md in comic_list:
+		print >> sys.stderr, fmt_str.format( filename ) + "\r",
+		sys.stderr.flush()
+		
+		new_key = makeKey((filename, md))
+
+		#if the new key same as the last, add to to dupe set
+		if new_key == prev_key:
+			dupe_set.append(filename)
+			
+		#else we're on a new potential block
+		else:
+			# only add if the dupe list has 2 or more
+			if len (dupe_set) > 1:
+				dupe_set_list.append( dupe_set )
+			dupe_set = list()
+			dupe_set.append(filename)
+			
+		prev_key = new_key
+		
+	print >> sys.stderr, fmt_str.format( "" ) + "\r",
+	print "Found {0} duplicate sets".format( len(dupe_set_list))
+
+	for dupe_set in dupe_set_list:
+		ca = ComicArchive(dupe_set[0], settings.rar_exe_path )
+		md = ca.readMetadata( style )
+		print "{0} #{1} ({2})".format( md.series, md.issue, md.year )
+		for filename in dupe_set:
+			print "------------->{0}".format( filename )
+
+if __name__ == '__main__':
+	main() 

scripts/inventory.py

@@ -0,0 +1,84 @@
+#!/usr/bin/python
+"""
+Print out a line-by-line list of basic tag info from all comics
+"""
+
+"""
+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 comictaggerlib.comicarchive import *
+from comictaggerlib.settings import *
+from comictaggerlib.issuestring import *
+import comictaggerlib.utils
+
+def main():
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	style = MetaDataStyle.CIX
+
+	if len(sys.argv) < 2:
+		print >> sys.stderr, "usage:  {0} comic_folder ".format(sys.argv[0])
+		return
+	
+	filelist = utils.get_recursive_filelist( sys.argv[1:] )
+			
+	#first read in metadata from all files
+	metadata_list = []	
+	max_name_len = 2
+	for filename in filelist:
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		if ca.hasMetadata( style ):
+			#make a list of paired filenames and metadata objects
+			metadata_list.append((filename, ca.readMetadata( style )))
+	
+			max_name_len = max ( max_name_len, len(filename))
+			fmt_str = u"{{0:{0}}}".format(max_name_len)
+			print >> sys.stderr, fmt_str.format( filename ) + "\r",
+			sys.stderr.flush()
+
+	print >> sys.stderr, fmt_str.format( "" ) + "\r",
+	print "-----------------------------------------------"
+	print "Found {0} comics with {1} tags".format( len(metadata_list), MetaDataStyle.name[style])
+	print "-----------------------------------------------"
+
+	# now, figure out column widths	
+	w0 = 4
+	w1 = 4
+	for filename,md in metadata_list: 
+		if not md.isEmpty:
+			w0 = max( len((os.path.split(filename)[1])), w0)
+			if md.series is not None:
+				w1 = max( len(md.series), w1)
+	w0 += 2
+	
+	# build a format string
+	fmt_str = u"{0:" + str(w0) + "} {1:" + str(w1) + "} #{2:6} ({3})"
+
+	# now sort the list by issue, and then series
+	metadata_list.sort(key=lambda x: IssueString(x[1].issue).asString(3), reverse=False)
+	metadata_list.sort(key=lambda x: unicode(x[1].series).lower()+str(x[1].year), reverse=False)
+	
+	# now print
+	for filename, md in metadata_list:
+		if not md.isEmpty:
+			print fmt_str.format(os.path.split(filename)[1]+":", md.series, md.issue, md.year), md.title
+
+if __name__ == '__main__':
+	main() 

scripts/make_links.py

@@ -0,0 +1,107 @@
+#!/usr/bin/python
+"""
+make some tree structures and symbolic links to comic files based on metadata
+oragnizing by date and series, in different trees
+"""
+
+"""
+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
+import platform
+
+from comictaggerlib.comicarchive import *
+from comictaggerlib.settings import *
+from comictaggerlib.issuestring import *
+import comictaggerlib.utils
+
+def make_folder( folder ):
+	if not os.path.exists( folder ):
+		try:
+			os.makedirs(folder)
+		except Exception as e:
+			print "{0} Can't make {1} -- quitting".format(e, folder)
+			quit()
+			
+def make_link( source, link ):
+	if not os.path.exists( link ):
+		os.symlink( os.path.abspath(source) , link )
+
+def main():
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	style = MetaDataStyle.CIX
+
+	if platform.system() == "Windows":
+		print >> sys.stderr, "Sorry, this script works only on UNIX systems"
+		
+	if len(sys.argv) < 3:
+		print >> sys.stderr, "usage:  {0} comic_root link_root".format(sys.argv[0])
+		return
+	
+	comic_root = sys.argv[1]
+	link_root = sys.argv[2]
+	
+	print "root is : ", comic_root
+	filelist = utils.get_recursive_filelist( [ comic_root ] )
+	make_folder( link_root )
+		
+	#first find all comics with metadata
+	print "reading in all comics..."
+	comic_list = []
+	max_name_len = 2
+	for filename in filelist:
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		if ca.seemsToBeAComicArchive() and ca.hasMetadata( style ):
+
+			comic_list.append((filename, ca.readMetadata( style )))
+			
+			max_name_len = max ( max_name_len, len(filename))
+			fmt_str = u"{{0:{0}}}".format(max_name_len)
+			print >> sys.stderr, fmt_str.format( filename ) + "\r",
+			sys.stderr.flush()
+
+	print >> sys.stderr, fmt_str.format( "" )
+	print "Found {0} tagged comics.".format( len(comic_list))
+
+	# walk through the comic list and add subdirs and links for each one	
+	for filename, md in comic_list:
+		print >> sys.stderr, fmt_str.format( filename ) + "\r",
+		sys.stderr.flush()
+		
+		#do date organizing:
+		if md.month is not None:
+			month_str = "{0:02d}".format(int(md.month))
+		else:
+			month_str = "00"
+		date_folder = os.path.join(link_root, "date", str(md.year), month_str)
+		make_folder( date_folder )
+		make_link( filename, os.path.join(date_folder, os.path.basename(filename)) )
+		
+		#do publisher/series organizing:
+		fixed_series_name = md.series
+		if fixed_series_name is not None:
+			# some tweaks to keep various filesystems happy		
+			fixed_series_name = fixed_series_name.replace("/", "-")
+			fixed_series_name = fixed_series_name.replace("?", "")
+		series_folder = os.path.join(link_root, "series", str(md.publisher), unicode(fixed_series_name))
+		make_folder( series_folder )
+		make_link( filename, os.path.join(series_folder, os.path.basename(filename)) )
+		
+if __name__ == '__main__':
+	main() 

scripts/name_fixer.py

@@ -0,0 +1,151 @@
+#!/usr/bin/python
+"""
+fix the comic file names using a list of transforms
+"""
+
+"""
+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
+import re
+import argparse
+import json
+
+from comictaggerlib.comicarchive import *
+from comictaggerlib.settings import *
+from comictaggerlib.filerenamer import *
+import comictaggerlib.utils
+
+def parse_args():
+	
+	input_args = sys.argv[1:]
+
+	parser = argparse.ArgumentParser(description='a script to rename comic files')
+	parser.add_argument('-t', '--transforms', metavar='xformfile', help="the file with transforms")
+	parser.add_argument('-n', '--noconfirm', action='store_true', help="don't confirm before rename")
+	parser.add_argument('paths', metavar='PATH', type=str, nargs='+', help='path to look for comic files')
+	parsed_args = parser.parse_args(input_args)
+
+	return parsed_args	
+
+def caclulate_rename(ca, md, settings):
+	
+		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( "%series% V%volume% #%issue% (of %issuecount%) (%year%) %scaninfo%" )
+		renamer.setIssueZeroPadding( 0 )
+		renamer.setSmartCleanup( settings.rename_use_smart_string_cleanup )
+		
+		return renamer.determineName( ca.path, ext=new_ext )
+
+def perform_rename(filelist):
+	for old_name,new_name in filelist:
+		folder = os.path.dirname( os.path.abspath( old_name ) )
+		new_abs_path = utils.unique_file( os.path.join( folder, new_name ) )
+
+		os.rename( old_name, new_abs_path )
+		print u"renamed '{0}' -> '{1}'".format(os.path.basename(old_name), new_name)	
+		
+def main():
+
+	default_xform_list = [
+					[ "^2000AD$", "2000 AD" ],
+					[ "^G\.{0,1}I\.{0,1}Joe$", "G.I. Joe" ],
+				 ]
+	
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	style = MetaDataStyle.CIX
+	
+	parsed_args = parse_args()
+	
+	#parsed_args.noconfirm
+	if parsed_args.transforms is not None:
+		print "Reading in transforms from:", parsed_args.transforms
+		json_data=open(parsed_args.transforms).read()		
+		data = json.loads(json_data)
+		xform_list = data['xforms']
+	else:
+		xform_list = default_xform_list
+			
+	#pprint( xform_list, indent=4)
+
+	filelist = utils.get_recursive_filelist( parsed_args.paths )
+		
+	#first find all comics 
+	print "reading in all comics..."
+	comic_list = []
+	max_name_len = 2
+	fmt_str = ""
+	for filename in filelist:
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		# do we care if it already has metadata?
+		if ca.seemsToBeAComicArchive() and not ca.hasMetadata( style ):
+
+			comic_list.append(ca)
+			
+			max_name_len = max ( max_name_len, len(filename))
+			fmt_str = u"{{0:{0}}}".format(max_name_len)
+			print >> sys.stderr, fmt_str.format( filename ) + "\r",
+			sys.stderr.flush()
+
+	print >> sys.stderr, fmt_str.format( "" )
+	print "Found {0} comics.".format( len(comic_list))
+
+	modify_list = list()
+	# walk through the comic list fix the filenames
+	for ca in comic_list:
+		
+		# 1. parse the filename into a MD object
+		md = ca.metadataFromFilename()
+		# 2. walk thru list of transforms
+		if md.series is not None and md.series != "":
+			for pattern, replacement in xform_list:
+				# apply each transform
+				new_series = re.sub( pattern, replacement, md.series )
+				if new_series != md.series:
+					md.series = new_series
+					new_name = caclulate_rename(ca, md, settings)
+					
+					#found a match.  add to proposed list, and bail on this file
+					modify_list.append( (ca.path, new_name ) ) 
+					break
+				
+	print "{0} filenames to modify".format(len(modify_list))
+	if len(modify_list) > 0:		
+		if parsed_args.noconfirm:
+			print "Not confirming before rename"
+		else:
+			for old_name, new_name in  modify_list:
+				print u"'{0}' -> '{1}'".format(os.path.basename(old_name), new_name)	
+
+			i = raw_input("Do you want to proceed with rename? [y/N] ")
+			if i.lower() not in ('y', 'yes'):
+				print "exiting without rename."				
+				sys.exit(0)
+				
+		perform_rename(modify_list)
+		
+if __name__ == '__main__':
+	main() 

scripts/remove_ads.py

@@ -0,0 +1,149 @@
+#!/usr/bin/python
+"""
+Create new comic archives from old one, removing  pages marked as ads
+and deleted. Walks recursivly through the given folders.  Originals
+are kept in a subfolder at the level of the original
+"""
+
+"""
+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
+import tempfile
+import zipfile
+import shutil
+
+import comictaggerlib.utils
+from comictaggerlib.settings import *
+from comictaggerlib.comicarchive import *
+
+subfolder_name = "PRE_AD_REMOVAL"
+unwanted_types = [ 'Deleted', 'Advertisment' ]
+
+def main():
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	# this can only work with files with ComicRack tags
+	style = MetaDataStyle.CIX
+	
+	if len(sys.argv) < 2:
+		print >> sys.stderr, "usage:  {0} comic_folder ".format(sys.argv[0])
+		return
+
+	filelist = utils.get_recursive_filelist( sys.argv[1:] )
+	
+	#first read in CIX metadata from all files, make a list of candidates
+	modify_list = []	
+	for filename in filelist:
+			
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		if (ca.isZip or ca.isRar()) and ca.hasMetadata( style ):
+			md = ca.readMetadata( style )
+			if len(md.pages) != 0:
+				for p in md.pages:
+					if p.has_key('Type') and p['Type'] in unwanted_types:
+						#This one has pages to remove.  add to list!
+						modify_list.append((filename, md))
+						break
+		
+	#now actually process those files
+	for filename,md in modify_list:
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		curr_folder = os.path.dirname( filename )
+		curr_subfolder = os.path.join( curr_folder, subfolder_name )
+
+		#skip any of our generated subfolders...
+		if os.path.basename(curr_folder) == subfolder_name:
+			continue
+		sys.stdout.write("Removing unwanted pages from " + filename)
+				
+		# verify that we can write to current folder		
+		if not os.access(filename, os.W_OK):
+			print "Can't move: {0}: skipped!".format(filename)
+			continue
+		if  not os.path.exists( curr_subfolder )  and not os.access(curr_folder, os.W_OK):
+			print "Can't create subfolder here: {0}: skipped!".format(filename)
+			continue
+		if  not os.path.exists( curr_subfolder ):
+			os.mkdir( curr_subfolder )
+		if  not os.access(curr_subfolder, os.W_OK):
+			print "Can't write to the subfolder here: {0}: skipped!".format(filename)
+			continue
+			
+		# generate a new file with temp name
+		tmp_fd, tmp_name = tempfile.mkstemp( dir=os.path.dirname(filename) )
+		os.close( tmp_fd )
+		
+		try:
+			zout = zipfile.ZipFile (tmp_name, 'w')
+			
+			# now read in all the pages from the old one, except the ones we want to skip
+			new_num = 0
+			new_pages = list()
+			for p in md.pages:
+				if p.has_key('Type') and p['Type'] in unwanted_types:
+					continue
+				else:
+					pageNum = int(p['Image'])
+					name = ca.getPageName( pageNum )
+					buffer = ca.getPage( pageNum )
+					sys.stdout.write('.')
+					sys.stdout.flush()
+					
+					#Generate a new name for the page file
+					ext = os.path.splitext(name)[1]
+					new_name = "page{0:04d}{1}".format(new_num,ext)
+					zout.writestr(new_name, buffer)
+					
+					# create new page entry
+					new_p = dict()
+					new_p['Image'] = str(new_num)
+					if p.has_key('Type'):
+						new_p['Type'] = p['Type']
+					new_pages.append(new_p)
+					new_num += 1
+			
+			#preserve the old comment
+			comment = ca.archiver.getArchiveComment()
+			if comment is not None:
+				zout.comment = ca.archiver.getArchiveComment()
+
+		except Exception as e:
+			print "Failure creating new archive: {0}!".format(filename)
+			print e, sys.exc_info()[0]
+			zout.close()
+			os.unlink( tmp_name )
+		else:
+			zout.close()
+			
+			# Success!  Now move the files
+			shutil.move( filename, curr_subfolder )
+			os.rename( tmp_name, filename )
+			# TODO: We might have converted a rar to a zip, and should probably change
+			#  the extension, as needed.
+
+			print "Done!".format(filename)
+			
+			# Create a new archive object for the new file, and write the old CIX data, with new page info
+			ca = ComicArchive( filename, settings.rar_exe_path )
+			md.pages = new_pages
+			ca.writeMetadata( style, md )
+
+
+if __name__ == '__main__':
+	main() 

scripts/shrink.py

@@ -0,0 +1,189 @@
+#!/usr/bin/python
+"""
+Reduce the image size of pages in the comic archive
+"""
+
+"""
+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
+import tempfile
+import zipfile
+import shutil
+import Image
+
+import comictaggerlib.utils
+from comictaggerlib.settings import *
+from comictaggerlib.comicarchive import *
+
+subfolder_name = "ORIGINALS"
+max_height = 2000
+
+def main():
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+
+	# this can only work with files with ComicRack tags
+	style = MetaDataStyle.CIX
+	
+	if len(sys.argv) < 2:
+		print >> sys.stderr, "usage:  {0} comic_folder ".format(sys.argv[0])
+		return
+
+	filelist = utils.get_recursive_filelist( sys.argv[1:] )
+	
+	#first make a list of all comic archive files
+	comics_list = []	
+	max_name_len = 2
+	fmt_str = u"{{0:{0}}}".format(max_name_len)	
+	for filename in filelist:
+			
+		ca = ComicArchive(filename, settings.rar_exe_path )
+		if (ca.seemsToBeAComicArchive()):
+			# Check the images in the file, see if we need to reduce any
+			
+			for idx in range(ca.getNumberOfPages()):
+				in_data = ca.getPage( idx )
+				if in_data is not None:
+					try:
+						im = Image.open(StringIO.StringIO(in_data))
+						w,h = im.size
+						if h > max_height:
+							comics_list.append( ca )
+							
+							max_name_len = max ( max_name_len, len(filename))
+							fmt_str = u"{{0:{0}}}".format(max_name_len)
+							print >> sys.stderr, fmt_str.format( filename ) + "\r",
+							sys.stderr.flush()
+							break
+							
+					except IOError:
+						#doesn't appear to be an image
+						pass		
+
+	print >> sys.stderr, fmt_str.format( "" ) + "\r",
+	print "-----------------------------------------------"
+	print "Found {0} comics with over-large pages".format( len(comics_list))
+	print "-----------------------------------------------"
+		
+	for item in comics_list:		
+		print item.path
+	
+	#now actually process those files with over-large pages
+	for ca in comics_list:
+		filename = ca.path
+		curr_folder = os.path.dirname( filename )
+		curr_subfolder = os.path.join( curr_folder, subfolder_name )
+
+		#skip any of our generated subfolders...
+		if os.path.basename(curr_folder) == subfolder_name:
+			continue
+			
+		sys.stdout.write("Processing: " + filename)
+
+		# verify that we can write to current folder		
+		if not os.access(filename, os.W_OK):
+			print "Can't move: {0}: skipped!".format(filename)
+			continue
+		if  not os.path.exists( curr_subfolder )  and not os.access(curr_folder, os.W_OK):
+			print "Can't create subfolder here: {0}: skipped!".format(filename)
+			continue
+		if  not os.path.exists( curr_subfolder ):
+			os.mkdir( curr_subfolder )
+		if  not os.access(curr_subfolder, os.W_OK):
+			print "Can't write to the subfolder here: {0}: skipped!".format(filename)
+			continue
+			
+		# generate a new file with temp name
+		tmp_fd, tmp_name = tempfile.mkstemp( dir=os.path.dirname(filename) )
+		os.close( tmp_fd )
+		
+		cix_md = None
+		if ca.hasCIX():
+			cix_md = ca.readCIX()
+			
+		try:
+			zout = zipfile.ZipFile (tmp_name, 'w')
+			
+			# Check the images in the file, see if we want to reduce them
+			page_count = ca.getNumberOfPages()
+			
+			for idx in range(ca.getNumberOfPages()):
+				name = ca.getPageName( idx )
+				in_data = ca.getPage( idx )
+				out_data = in_data
+				if in_data is not None:
+					try:
+						im = Image.open(StringIO.StringIO(in_data))
+						w,h = im.size
+						if h > max_height:
+							#resize the image
+							hpercent = (max_height/float(h))
+							wsize = int((float(w)*float(hpercent)))
+							size=(wsize, max_height)
+							im = im.resize(size, Image.ANTIALIAS)
+							
+							output = StringIO.StringIO()
+							im.save(output, format="JPEG", quality=85)
+							out_data = output.getvalue()
+							output.close()							
+
+					except IOError:
+						#doesn't appear to be an image
+						pass
+									
+				else:
+					#page is empty?? nothing to write
+					out_data = ""
+					
+				sys.stdout.write('.')
+				sys.stdout.flush()
+				
+				#write out the new resized image
+				zout.writestr(name, out_data)
+									
+					
+			#preserve the old comment
+			comment = ca.archiver.getArchiveComment()
+			if comment is not None:
+				zout.comment = ca.archiver.getArchiveComment()
+
+		except Exception as e:
+			print "Failure creating new archive: {0}!".format(filename)
+			print e, sys.exc_info()[0]
+			zout.close()
+			os.unlink( tmp_name )
+		else:
+			zout.close()
+			
+			# Success!  Now move the files
+			shutil.move( filename, curr_subfolder )
+			os.rename( tmp_name, filename )
+			# TODO: We might have converted a rar to a zip, and should probably change
+			#  the extension, as needed.
+
+			print "Done!".format(filename)
+			
+			# Create a new archive object for the new file, and write the old CIX data, w/o page info
+			if cix_md is not None:
+				ca = ComicArchive( filename, settings.rar_exe_path )
+				cix_md.pages = []
+				ca.writeCIX( cix_md )
+
+
+if __name__ == '__main__':
+	main() 

scripts/validate_cover.py

@@ -0,0 +1,73 @@
+#!/usr/bin/python
+"""
+test archive cover against comicvine for a given issue ID
+"""
+
+"""
+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
+
+import comictaggerlib.utils
+from comictaggerlib.settings import *
+from comictaggerlib.comicarchive import *
+from comictaggerlib.issueidentifier import *
+from comictaggerlib.comicvinetalker import *
+
+def main():
+
+	utils.fix_output_encoding()
+	settings = ComicTaggerSettings()
+	
+	if len(sys.argv) < 3:
+		print >> sys.stderr, "usage:  {0} comicfile issueid".format(sys.argv[0])
+		return
+	
+	filename = sys.argv[1]
+	issue_id = sys.argv[2]
+
+	if not os.path.exists(filename):
+		print >> sys.stderr, filename + ": not found!"
+		return
+		
+	ca = ComicArchive(filename, settings.rar_exe_path )
+	if not ca.seemsToBeAComicArchive():
+		print >> sys.stderr, "Sorry, but "+ filename + "  is not a comic archive!"
+		return
+
+	ii = IssueIdentifier( ca, settings )
+	
+	# calculate the hashes of the first two pages
+	cover_image_data = ca.getPage( 0 )
+	cover_hash0 = ii.calculateHash( cover_image_data )		
+	cover_image_data = ca.getPage( 1 )
+	cover_hash1 = ii.calculateHash( cover_image_data )
+	hash_list = [ cover_hash0, cover_hash1 ]
+	
+	comicVine = ComicVineTalker( )
+	result = ii.getIssueCoverMatchScore( comicVine, issue_id, hash_list, useRemoteAlternates=True, useLog=False)
+	
+	print "Best cover match score is :", result['score']
+	if result['score'] < ii.min_alternate_score_thresh:
+		print "Looks like a match!"
+	else:
+		print "Bad score, maybe not a match?"
+	print result['url']
+	
+	
+if __name__ == '__main__':
+	main() 

scripts/xforms

@@ -0,0 +1,8 @@
+{
+	"_comment": "This file contains JSON data.  Any backslashes should be escaped with another backslash",
+	"xforms":
+		[
+			[ "^2000AD$", "2000 AD" ],
+			[ "^G\\.{0,1}I\\.{0,1}Joe$", "G.I. Joe" ]
+		]
+}

setup.py

@@ -1,61 +1,66 @@
-#!/usr/bin/env python
-
-from distutils.core import setup
-import comictaggerlib.ctversion
-
-setup(name = "comictagger",
-    version =  comictaggerlib.ctversion.version,
-    description = "A cross-platorm GUI/CLI app for writing metadata to comic archives",
-    author = "Anthony Beville",
-    author_email = "comictagger@gmail.com",
-    url = "http://code.google.com/p/comictagger/",
-    download_url = "http://comictagger.googlecode.com/files/comictagger-{0}.zip".format(comictaggerlib.ctversion.version),
-    packages =  [ "comictaggerlib", "comictaggerlib/UnRAR2" ] ,
-    package_data = {
-      'comictaggerlib': ['ui/*.ui', 'graphics/*'] ,
-      'comictaggerlib/UnRAR2': ['UnRARDLL/*.*', 'UnRARDLL/x64/*.*'] ,
-    },
-    scripts = ["comictagger.py"],
-    classifiers = [
-         "Development Status :: 4 - Beta",
-         "Environment :: Console",
-         "Environment :: Win32 (MS Windows)",
-         "Environment :: MacOS X",
-         "Environment :: X11 Applications :: Qt",
-         "Intended Audience :: End Users/Desktop",
-         "License :: OSI Approved :: Apache Software License",
-         "Natural Language :: English",
-         "Operating System :: OS Independent",
-         "Programming Language :: Python",
-         "Programming Language :: Python :: 2.6",
-         "Programming Language :: Python :: 2.7",
-         "Topic :: Utilities",
-         "Topic :: Other/Nonlisted Topic",
-         "Topic :: Multimedia :: Graphics"
-    ],
-    license = "Apache License 2.0",
-    
-    long_description = """
-ComicTagger is a multi-platform app for writing metadata to comic archives, written in Python and PyQt.
-
-Features:
-
-* Runs on Mac OSX, Microsoft Windows, and Linux systems
-* Communicates with an online database (Comic Vine) for acquiring metadata
-* Uses image processing to automatically match a given archive with the correct issue data
-* Batch processing in the GUI for tagging hundreds or more comics at a time
-* Reads and writes multiple tagging schemes ( ComicBookLover? and ComicRack?, with more planned).
-* Reads and writes RAR, Zip, and folder archives (external tools needed for writing RAR)
-* Command line interface (CLI) on all platforms (including Windows), which supports batch operations, and which can be used in native scripts for complex operations. 
-
-Requires:
-
-* python 2.6 or 2.7
-* python imaging (PIL) >= 1.1.7
-* beautifulsoup > 4.1
-    
-Optional requirement (for GUI):
-
-* pyqt4
-"""          
-      )    
+#!/usr/bin/env python
+
+from setuptools import setup
+import comictaggerlib.ctversion
+
+with open('requirements.txt') as f:
+    required = f.read().splitlines()
+    
+setup(name = "comictagger",
+    install_requires=required,
+    version =  comictaggerlib.ctversion.version,
+    description = "A cross-platform GUI/CLI app for writing metadata to comic archives",
+    author = "Anthony Beville",
+    author_email = "comictagger@gmail.com",
+    url = "http://code.google.com/p/comictagger/",
+    download_url = "https://pypi.python.org/packages/source/c/comictagger/comictagger-{0}.zip".format(comictaggerlib.ctversion.version),
+    packages =  [ "comictaggerlib", "comictaggerlib/UnRAR2" ] ,
+    package_data = {
+      'comictaggerlib': ['ui/*.ui', 'graphics/*'] ,
+      'comictaggerlib/UnRAR2': ['UnRARDLL/*.*', 'UnRARDLL/x64/*.*'] ,
+    },
+    scripts = ["comictagger.py"],
+    classifiers = [
+         "Development Status :: 4 - Beta",
+         "Environment :: Console",
+         "Environment :: Win32 (MS Windows)",
+         "Environment :: MacOS X",
+         "Environment :: X11 Applications :: Qt",
+         "Intended Audience :: End Users/Desktop",
+         "License :: OSI Approved :: Apache Software License",
+         "Natural Language :: English",
+         "Operating System :: OS Independent",
+         "Programming Language :: Python",
+         "Programming Language :: Python :: 2.6",
+         "Programming Language :: Python :: 2.7",
+         "Topic :: Utilities",
+         "Topic :: Other/Nonlisted Topic",
+         "Topic :: Multimedia :: Graphics"
+    ],
+    license = "Apache License 2.0",
+    
+    long_description = """
+ComicTagger is a multi-platform app for writing metadata to digital comics, written in Python and PyQt.
+
+Features:
+
+* Runs on Mac OSX, Microsoft Windows, and Linux systems
+* Communicates with an online database (Comic Vine) for acquiring metadata
+* Uses image processing to automatically match a given archive with the correct issue data
+* Batch processing in the GUI for tagging hundreds or more comics at a time
+* Reads and writes multiple tagging schemes ( ComicBookLover and ComicRack, with more planned).
+* Reads and writes RAR and Zip archives (external tools needed for writing RAR)
+* Command line interface (CLI) on all platforms (including Windows), which supports batch operations, and which can be used in native scripts for complex operations. 
+
+Requires:
+
+* python 2.6 or 2.7
+* configparser 
+* python imaging (PIL) >= 1.1.6
+* beautifulsoup > 4.1
+    
+Optional requirement (for GUI):
+
+* pyqt4
+"""          
+      )    

todo.txt

@@ -1,77 +1,102 @@
------------------------------------------------------
-Features
------------------------------------------------------
-	
-Rename dialog:
-	check-box for rows?
-	manual edit the preview?
-		
-Docs:
-	Auto-Tagging Tips:
-		Multiple Passes with different options
-
------------------------------------------------------
-Bugs	
------------------------------------------------------
-
-Zip flakes out when filename differs from index (or whatever)  i.e "\" vs "/". Python issue
-
------------------------------------------------------
-Big  Future Features
------------------------------------------------------
-
-GCD scraper or DB reader
-
-Batch Edit
-	Form Mode:  Single vs Batch
-	
------------------------------------------------------
-Small(er) Future Feature
------------------------------------------------------
-Parse out the rest of the scan info from filename
-
-Style sheets for windows/mac/linux
- 
-CLI
-	explicit metadata settings option format
-		-- figure out how to add CBI "tags"
-		-- delete CBI "tags"
-		-- set primary credit flags
-		-- set frontcover and others?
-
-Archive function to  detect tag blocks out of sync
-
-Settings
-	Add setting to dis-allow writing CBI to RAR
-
-Google App engine to store hashes 
-	Content Hashes, Image hashes, who knows?
-
-Filename parsing:
-	Rework how series name is separated from issue
-	
-Support marvel's "AU" issues...
-	Mostly done, gotta wait and see what CV does
-	
-Internal GenericMetadata - Make Characters, Genre into lists?
-
------------------------------------------------------
-Config Mgmt check list
------------------------------------------------------
-
-Release Process
-    Optionally, make screen shots, upload to wiki
-    Update release notes and wiki
-	Update ctversion.py
-	Build packages
-	    Make exe on Windows
-		Make dmg on Mac
-		Make zip on Mac or Linux
-    Tag the repository
-	Upload packages
-	Announce on Forum and Main Page
-	
-----------------------------------------------
-
-	
-rename 's/([A-Za-z]+)(\d+)(.cb[rz])/$1 $2$3/' *.cb?
+TOP!:
+		Does utils.get_actual_preferred_encoding() work on Mac python source version??
+				(And does it matter?)
+
+-----------------------------------------------------
+Features
+-----------------------------------------------------
+Rename dialog:
+	check-box for rows?
+	manual edit the preview?
+
+Maybe replace configparser  -- seems to be causing all sorts of problems
+
+Feature Requests:
+	Move CBR to other folder after conversion to ZIP
+	Pre-process series name before identification
+		(using a list of regex transforms) 
+	(GC #24) Multiple options for -t i.e. "-t cr,cbl"
+	(GC #18 ) Option for handling colon in rename
+	(GC #31 ) Specify CV Series ID for auto-tag
+	Re-org - move to new folder based on template
+	
+	Denied Requests (for now):
+		Auto-rename on auto-tag
+		Re-zip (to remove compression)
+	
+	
+	Selective fields on CLI print (use -m option.  Maybe internally remove all but specified fields in MD object before print )
+		
+Docs:
+	Auto-Tagging Tips:
+		Multiple Passes with different options	
+	
+-----------------------------------------------------
+Bugs	
+-----------------------------------------------------
+
+Zip flakes out when filename differs from index (or whatever)  i.e "\" vs "/". Python issue
+
+
+
+-----------------------------------------------------
+Big  Future Features
+-----------------------------------------------------
+Support for ACBF metatdata in CBZ
+
+GCD scraper or DB reader
+
+(GC #29) Batch Edit
+	Form Mode:  Single vs Batch
+	
+-----------------------------------------------------
+Small(er) Future Feature
+-----------------------------------------------------
+Parse out the rest of the scan info from filename
+
+Style sheets for windows/mac/linux
+ 
+CLI
+	explicit metadata settings option format
+		-- figure out how to add CBI "tags"
+		-- delete CBI "tags"
+		-- set primary credit flags
+		-- set frontcover and others?
+
+Archive function to  detect tag blocks out of sync
+
+Settings
+	Add setting to dis-allow writing CBI to RAR
+
+Google App engine to store hashes 
+	Content Hashes, Image hashes, who knows?
+
+Filename parsing:
+	Rework how series name is separated from issue
+
+Internal GenericMetadata - Make Characters, Genre into lists?
+
+-----------------------------------------------------
+Config Mgmt check list
+-----------------------------------------------------
+
+Release Process
+    Optionally, make screen shots, upload to wiki
+    Update release notes and wiki
+	Update ctversion.py
+	Build packages
+	    Make exe on Windows
+		Make dmg on Mac
+		Make zip on Mac or Linux
+    Tag the repository
+	Manually upload release packages to Google Drive
+	Update the Downloads wiki page with direct links
+	"make upload" to the pypi site 
+	Announce on Forum and Main Page and Twitter and Facebook
+	MacUpdate
+	Update appspot value
+	
+----------------------------------------------
+
+	
+rename 's/([A-Za-z]+)(\d+)(.cb[rz])/$1 $2$3/' *.cb?

windows/Makefile

@@ -1,11 +1,12 @@
 # This Makefile expects that certain GNU utils are available:
 # rm, cp, grep, cut, cat
 
-TAGGER_BASE:= c:\Users\tony\Dropbox\tagger\comictagger
-TAGGER_SRC := $(TAGGER_BASE)\comictaggerlib
+HOMEPATH ?= $(HOME)
+TAGGER_BASE?= $(HOMEPATH)/Dropbox/tagger/comictagger
+TAGGER_SRC := $(TAGGER_BASE)/comictaggerlib
 DIST_DIR := $(TAGGER_BASE)\windows\dist
 NSIS_CMD :=	"C:\Program Files (x86)\NSIS\makensis.exe"
-VERSION := $(shell grep version "$(TAGGER_SRC)\ctversion.py" | cut -d= -f2)
+VERSION := $(shell grep version "$(TAGGER_SRC)/ctversion.py" | cut -d= -f2)
 
 all: clean dist package
 
@@ -28,9 +29,4 @@ package:
 
 clean:
 	-rm -rf dist
-	-rm -f "*~" *.pyc *.pyo
-	-rm -f "$(TAGGER_BASE)\windows\*.exe"
-
-test:
-	echo !define RELEASE_STR $(VERSION) > test.nsh
-	
+	-rm -rf nsis/release.nsh

windows/nsis/license.txt

@@ -1,4 +1,4 @@
-ComicTagger - Copyright 2012  Anthony Beville
+ComicTagger - Copyright 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.