Merge branch 'fcanc-master'
This commit is contained in:
davide-romanini
commit
d84110ccb2
@ -1,30 +1,28 @@
|
||||
"""
|
||||
A python class to encapsulate CoMet data
|
||||
"""
|
||||
"""A class to encapsulate CoMet data"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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
|
||||
# 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.
|
||||
"""
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from datetime import datetime
|
||||
import zipfile
|
||||
from pprint import pprint
|
||||
import xml.etree.ElementTree as ET
|
||||
#from datetime import datetime
|
||||
#from pprint import pprint
|
||||
#import zipfile
|
||||
|
||||
from genericmetadata import GenericMetadata
|
||||
import utils
|
||||
|
||||
|
||||
class CoMet:
|
||||
|
||||
writer_synonyms = ['writer', 'plotter', 'scripter']
|
||||
@ -72,7 +70,8 @@ class CoMet:
|
||||
root = ET.Element("comet")
|
||||
root.attrib['xmlns:comet'] = "http://www.denvog.com/comet/"
|
||||
root.attrib['xmlns:xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
|
||||
root.attrib['xsi:schemaLocation'] = "http://www.denvog.com http://www.denvog.com/comet/comet.xsd"
|
||||
root.attrib[
|
||||
'xsi:schemaLocation'] = "http://www.denvog.com http://www.denvog.com/comet/comet.xsd"
|
||||
|
||||
# helper func
|
||||
def assign(comet_entry, md_entry):
|
||||
@ -116,7 +115,8 @@ class CoMet:
|
||||
|
||||
assign('coverImage', md.coverImage)
|
||||
|
||||
# need to specially process the credits, since they are structured differently than CIX
|
||||
# need to specially process the credits, since they are structured
|
||||
# differently than CIX
|
||||
credit_writer_list = list()
|
||||
credit_penciller_list = list()
|
||||
credit_inker_list = list()
|
||||
@ -129,26 +129,46 @@ class CoMet:
|
||||
for credit in metadata.credits:
|
||||
|
||||
if credit['role'].lower() in set(self.writer_synonyms):
|
||||
ET.SubElement(root, 'writer').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'writer').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.penciller_synonyms):
|
||||
ET.SubElement(root, 'penciller').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'penciller').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.inker_synonyms):
|
||||
ET.SubElement(root, 'inker').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'inker').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.colorist_synonyms):
|
||||
ET.SubElement(root, 'colorist').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'colorist').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.letterer_synonyms):
|
||||
ET.SubElement(root, 'letterer').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'letterer').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.cover_synonyms):
|
||||
ET.SubElement(root, 'coverDesigner').text = u"{0}".format(credit['person'])
|
||||
ET.SubElement(
|
||||
root,
|
||||
'coverDesigner').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
if credit['role'].lower() in set(self.editor_synonyms):
|
||||
ET.SubElement(root, 'editor').text = u"{0}".format(credit['person'])
|
||||
|
||||
ET.SubElement(
|
||||
root,
|
||||
'editor').text = u"{0}".format(
|
||||
credit['person'])
|
||||
|
||||
# self pretty-print
|
||||
self.indent(root)
|
||||
@ -157,7 +177,6 @@ class CoMet:
|
||||
tree = ET.ElementTree(root)
|
||||
return tree
|
||||
|
||||
|
||||
def convertXMLToMetadata(self, tree):
|
||||
|
||||
root = tree.getroot()
|
||||
@ -229,7 +248,6 @@ class CoMet:
|
||||
if n.tag == 'coverDesigner':
|
||||
metadata.addCredit(n.text.strip(), "Cover")
|
||||
|
||||
|
||||
metadata.isEmpty = False
|
||||
|
||||
return metadata
|
||||
@ -246,7 +264,6 @@ class CoMet:
|
||||
|
||||
return True
|
||||
|
||||
|
||||
def writeToExternalFile(self, filename, metadata):
|
||||
|
||||
tree = self.convertMetadataToXML(self, metadata)
|
||||
@ -257,4 +274,3 @@ class CoMet:
|
||||
|
||||
tree = ET.parse(filename)
|
||||
return self.convertXMLToMetadata(tree)
|
||||
|
||||
|
||||
@ -1,22 +1,18 @@
|
||||
"""
|
||||
A python class to represent a single comic, be it file or folder of images
|
||||
"""
|
||||
"""A class to represent a single comic, be it file or folder of images"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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
|
||||
# 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.
|
||||
"""
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import zipfile
|
||||
import os
|
||||
@ -25,27 +21,57 @@ import sys
|
||||
import tempfile
|
||||
import subprocess
|
||||
import platform
|
||||
import locale
|
||||
import shutil
|
||||
import ctypes
|
||||
import time
|
||||
import StringIO
|
||||
#import io
|
||||
#import locale
|
||||
#import shutil
|
||||
|
||||
from natsort import natsorted
|
||||
from PyPDF2 import PdfFileReader
|
||||
from unrar import rarfile
|
||||
from unrar import unrarlib
|
||||
import unrar.constants
|
||||
import ctypes
|
||||
import io
|
||||
from unrar import constants
|
||||
#import UnRAR2
|
||||
#from UnRAR2.rar_exceptions import *
|
||||
|
||||
if platform.system() == "Windows":
|
||||
import _subprocess
|
||||
|
||||
try:
|
||||
import Image
|
||||
pil_available = True
|
||||
except ImportError:
|
||||
pil_available = False
|
||||
|
||||
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
|
||||
|
||||
|
||||
sys.path.insert(0, os.path.abspath("."))
|
||||
|
||||
|
||||
class OpenableRarFile(rarfile.RarFile):
|
||||
|
||||
def open(self, member):
|
||||
|
||||
# print "opening %s..." % member
|
||||
|
||||
# based on https://github.com/matiasb/python-unrar/pull/4/files
|
||||
res = []
|
||||
if isinstance(member, rarfile.RarInfo):
|
||||
member = member.filename
|
||||
archive = unrarlib.RAROpenArchiveDataEx(self.filename, mode=constants.RAR_OM_EXTRACT)
|
||||
archive = unrarlib.RAROpenArchiveDataEx(
|
||||
self.filename,
|
||||
mode=constants.RAR_OM_EXTRACT)
|
||||
handle = self._open(archive)
|
||||
found, buf = False, []
|
||||
|
||||
def _callback(msg, UserData, P1, P2):
|
||||
if msg == constants.UCM_PROCESSDATA:
|
||||
data = (ctypes.c_char * P2).from_address(P1).raw
|
||||
@ -56,7 +82,8 @@ class OpenableRarFile(rarfile.RarFile):
|
||||
try:
|
||||
rarinfo = self._read_header(handle)
|
||||
while rarinfo is not None:
|
||||
#print "checking rar archive %s against %s" % (rarinfo.filename, member)
|
||||
# print "checking rar archive %s against %s" % (
|
||||
# rarinfo.filename, member)
|
||||
if rarinfo.filename == member:
|
||||
self._process_current(handle, constants.RAR_TEST)
|
||||
found = True
|
||||
@ -72,37 +99,17 @@ class OpenableRarFile(rarfile.RarFile):
|
||||
return ''.join(buf)
|
||||
|
||||
|
||||
if platform.system() == "Windows":
|
||||
import _subprocess
|
||||
import time
|
||||
|
||||
import StringIO
|
||||
try:
|
||||
import Image
|
||||
pil_available = True
|
||||
except ImportError:
|
||||
pil_available = False
|
||||
|
||||
sys.path.insert(0, os.path.abspath(".") )
|
||||
#import UnRAR2
|
||||
#from UnRAR2.rar_exceptions import *
|
||||
|
||||
#from 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 PyPDF2 import PdfFileReader
|
||||
|
||||
class MetaDataStyle:
|
||||
CBI = 0
|
||||
CIX = 1
|
||||
COMET = 2
|
||||
name = ['ComicBookLover', 'ComicRack', 'CoMet']
|
||||
|
||||
|
||||
class ZipArchiver:
|
||||
|
||||
"""ZIP implementation"""
|
||||
|
||||
def __init__(self, path):
|
||||
self.path = path
|
||||
|
||||
@ -122,12 +129,14 @@ class ZipArchiver:
|
||||
try:
|
||||
data = zf.read(archive_file)
|
||||
except zipfile.BadZipfile as e:
|
||||
print >> sys.stderr, u"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, u"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()
|
||||
@ -149,7 +158,10 @@ class ZipArchiver:
|
||||
self.rebuildZipFile([archive_file])
|
||||
|
||||
# now just add the archive file as a new one
|
||||
zf = zipfile.ZipFile(self.path, mode='a', compression=zipfile.ZIP_DEFLATED )
|
||||
zf = zipfile.ZipFile(
|
||||
self.path,
|
||||
mode='a',
|
||||
compression=zipfile.ZIP_DEFLATED)
|
||||
zf.writestr(archive_file, data)
|
||||
zf.close()
|
||||
return True
|
||||
@ -163,14 +175,18 @@ class ZipArchiver:
|
||||
zf.close()
|
||||
return namelist
|
||||
except Exception as e:
|
||||
print >> sys.stderr, u"Unable to get zipfile list [{0}]: {1}".format(e, self.path)
|
||||
print >> sys.stderr, u"Unable to get zipfile list [{0}]: {1}".format(
|
||||
e, self.path)
|
||||
return []
|
||||
|
||||
# zip helper func
|
||||
def rebuildZipFile(self, exclude_list):
|
||||
"""Zip helper func
|
||||
|
||||
# this recompresses the zip archive, without the files in the exclude_list
|
||||
#print ">> sys.stderr, Rebuilding zip {0} without {1}".format( self.path, exclude_list )
|
||||
This recompresses the zip archive, without the files in the exclude_list
|
||||
"""
|
||||
|
||||
# print ">> sys.stderr, Rebuilding zip {0} without {1}".format(
|
||||
# self.path, exclude_list )
|
||||
|
||||
# generate temp file
|
||||
tmp_fd, tmp_name = tempfile.mkstemp(dir=os.path.dirname(self.path))
|
||||
@ -193,7 +209,6 @@ class ZipArchiver:
|
||||
os.remove(self.path)
|
||||
os.rename(tmp_name, self.path)
|
||||
|
||||
|
||||
def writeZipComment(self, filename, comment):
|
||||
"""
|
||||
This is a custom function for writing a comment to a zip file,
|
||||
@ -240,7 +255,9 @@ class ZipArchiver:
|
||||
|
||||
# Pack the length of the comment string
|
||||
format = "H" # one 2-byte integer
|
||||
comment_length = struct.pack(format, len(comment)) # pack integer in a binary string
|
||||
comment_length = struct.pack(
|
||||
format,
|
||||
len(comment)) # pack integer in a binary string
|
||||
|
||||
# write out the length
|
||||
fo.write(comment_length)
|
||||
@ -258,7 +275,8 @@ class ZipArchiver:
|
||||
return True
|
||||
|
||||
def copyFromArchive(self, otherArchive):
|
||||
# Replace the current zip with one copied from another archive
|
||||
"""Replace the current zip with one copied from another archive"""
|
||||
|
||||
try:
|
||||
zout = zipfile.ZipFile(self.path, 'w')
|
||||
for fname in otherArchive.getArchiveFilenameList():
|
||||
@ -273,18 +291,21 @@ class ZipArchiver:
|
||||
if not self.writeZipComment(self.path, comment):
|
||||
return False
|
||||
except Exception as e:
|
||||
print >> sys.stderr, u"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
|
||||
|
||||
|
||||
#------------------------------------------
|
||||
# RAR implementation
|
||||
|
||||
class RarArchiver:
|
||||
|
||||
"""RAR implementation"""
|
||||
|
||||
devnull = None
|
||||
|
||||
def __init__(self, path, rar_exe_path):
|
||||
self.path = path
|
||||
self.rar_exe_path = rar_exe_path
|
||||
@ -321,7 +342,12 @@ class RarArchiver:
|
||||
working_dir = os.path.dirname(os.path.abspath(self.path))
|
||||
|
||||
# use external program to write comment to Rar archive
|
||||
subprocess.call([self.rar_exe_path, 'c', '-w' + working_dir , '-c-', '-z' + tmp_name, self.path],
|
||||
subprocess.call([self.rar_exe_path,
|
||||
'c',
|
||||
'-w' + working_dir,
|
||||
'-c-',
|
||||
'-z' + tmp_name,
|
||||
self.path],
|
||||
startupinfo=self.startupinfo,
|
||||
stdout=RarArchiver.devnull)
|
||||
|
||||
@ -356,28 +382,31 @@ class RarArchiver:
|
||||
#data = open(tmp_file).read()
|
||||
entries = [(rarc.getinfo(archive_file), data)]
|
||||
|
||||
|
||||
#shutil.rmtree(tmp_folder, ignore_errors=True)
|
||||
|
||||
#entries = rarc.read_files( archive_file )
|
||||
|
||||
if entries[0][0].file_size != len(entries[0][1]):
|
||||
print >> sys.stderr, u"readArchiveFile(): [file is not expected size: {0} vs {1}] {2}:{3} [attempt # {4}]".format(
|
||||
entries[0][0].file_size,len(entries[0][1]), self.path, archive_file, tries)
|
||||
entries[0][0].file_size, len(
|
||||
entries[0][1]), self.path, archive_file, tries)
|
||||
continue
|
||||
|
||||
except (OSError, IOError) as e:
|
||||
print >> sys.stderr, u"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, u"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, u"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:
|
||||
@ -385,8 +414,6 @@ class RarArchiver:
|
||||
|
||||
raise IOError
|
||||
|
||||
|
||||
|
||||
def writeArchiveFile(self, archive_file, data):
|
||||
|
||||
if self.rar_exe_path is not None:
|
||||
@ -404,7 +431,13 @@ class RarArchiver:
|
||||
f.close()
|
||||
|
||||
# use external program to write file to Rar archive
|
||||
subprocess.call([self.rar_exe_path, 'a', '-w' + working_dir ,'-c-', '-ep', self.path, tmp_file],
|
||||
subprocess.call([self.rar_exe_path,
|
||||
'a',
|
||||
'-w' + working_dir,
|
||||
'-c-',
|
||||
'-ep',
|
||||
self.path,
|
||||
tmp_file],
|
||||
startupinfo=self.startupinfo,
|
||||
stdout=RarArchiver.devnull)
|
||||
|
||||
@ -423,7 +456,11 @@ class RarArchiver:
|
||||
if self.rar_exe_path is not None:
|
||||
try:
|
||||
# use external program to remove file from Rar archive
|
||||
subprocess.call([self.rar_exe_path, 'd','-c-', self.path, archive_file],
|
||||
subprocess.call([self.rar_exe_path,
|
||||
'd',
|
||||
'-c-',
|
||||
self.path,
|
||||
archive_file],
|
||||
startupinfo=self.startupinfo,
|
||||
stdout=RarArchiver.devnull)
|
||||
|
||||
@ -453,7 +490,8 @@ class RarArchiver:
|
||||
namelist.append(item.filename)
|
||||
|
||||
except (OSError, IOError) as e:
|
||||
print >> sys.stderr, u"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:
|
||||
@ -462,7 +500,6 @@ class RarArchiver:
|
||||
|
||||
raise e
|
||||
|
||||
|
||||
def getRARObj(self):
|
||||
tries = 0
|
||||
while tries < 7:
|
||||
@ -472,7 +509,8 @@ class RarArchiver:
|
||||
rarc = OpenableRarFile(self.path)
|
||||
|
||||
except (OSError, IOError) as e:
|
||||
print >> sys.stderr, u"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:
|
||||
@ -481,10 +519,11 @@ class RarArchiver:
|
||||
|
||||
raise e
|
||||
|
||||
#------------------------------------------
|
||||
# Folder implementation
|
||||
|
||||
class FolderArchiver:
|
||||
|
||||
"""Folder implementation"""
|
||||
|
||||
def __init__(self, path):
|
||||
self.path = path
|
||||
self.comment_file_name = "ComicTaggerFolderComment.txt"
|
||||
@ -544,40 +583,54 @@ class FolderArchiver:
|
||||
|
||||
return itemlist
|
||||
|
||||
#------------------------------------------
|
||||
# Unknown implementation
|
||||
|
||||
class UnknownArchiver:
|
||||
|
||||
"""Unknown implementation"""
|
||||
|
||||
def __init__(self, path):
|
||||
self.path = path
|
||||
|
||||
def getArchiveComment(self):
|
||||
return ""
|
||||
|
||||
def setArchiveComment(self, comment):
|
||||
return False
|
||||
|
||||
def readArchiveFile(self):
|
||||
return ""
|
||||
|
||||
def writeArchiveFile(self, archive_file, data):
|
||||
return False
|
||||
|
||||
def removeArchiveFile(self, archive_file):
|
||||
return False
|
||||
|
||||
def getArchiveFilenameList(self):
|
||||
return []
|
||||
|
||||
|
||||
class PdfArchiver:
|
||||
|
||||
def __init__(self, path):
|
||||
self.path = path
|
||||
|
||||
def getArchiveComment(self):
|
||||
return ""
|
||||
|
||||
def setArchiveComment(self, comment):
|
||||
return False
|
||||
|
||||
def readArchiveFile(self, page_num):
|
||||
return subprocess.check_output(['mudraw', '-o','-', self.path, str(int(os.path.basename(page_num)[:-4]))])
|
||||
return subprocess.check_output(
|
||||
['mudraw', '-o', '-', self.path, str(int(os.path.basename(page_num)[:-4]))])
|
||||
|
||||
def writeArchiveFile(self, archive_file, data):
|
||||
return False
|
||||
|
||||
def removeArchiveFile(self, archive_file):
|
||||
return False
|
||||
|
||||
def getArchiveFilenameList(self):
|
||||
out = []
|
||||
pdf = PdfFileReader(open(self.path, 'rb'))
|
||||
@ -586,6 +639,8 @@ class PdfArchiver:
|
||||
return out
|
||||
|
||||
#------------------------------------------------------------------
|
||||
|
||||
|
||||
class ComicArchive:
|
||||
|
||||
logo_data = None
|
||||
@ -611,7 +666,9 @@ class ComicArchive:
|
||||
if ext == ".cbr" or ext == ".rar":
|
||||
if self.rarTest():
|
||||
self.archive_type = self.ArchiveType.Rar
|
||||
self.archiver = RarArchiver( self.path, rar_exe_path=self.rar_exe_path )
|
||||
self.archiver = RarArchiver(
|
||||
self.path,
|
||||
rar_exe_path=self.rar_exe_path)
|
||||
|
||||
elif self.zipTest():
|
||||
self.archive_type = self.ArchiveType.Zip
|
||||
@ -623,7 +680,9 @@ class ComicArchive:
|
||||
|
||||
elif self.rarTest():
|
||||
self.archive_type = self.ArchiveType.Rar
|
||||
self.archiver = RarArchiver( self.path, rar_exe_path=self.rar_exe_path )
|
||||
self.archiver = RarArchiver(
|
||||
self.path,
|
||||
rar_exe_path=self.rar_exe_path)
|
||||
elif os.path.basename(self.path)[-3:] == 'pdf':
|
||||
self.archive_type = self.ArchiveType.Pdf
|
||||
self.archiver = PdfArchiver(self.path)
|
||||
@ -634,8 +693,9 @@ class ComicArchive:
|
||||
with open(fname, 'rb') as fd:
|
||||
ComicArchive.logo_data = fd.read()
|
||||
|
||||
# Clears the cached data
|
||||
def resetCache(self):
|
||||
"""Clears the cached data"""
|
||||
|
||||
self.has_cix = None
|
||||
self.has_cbi = None
|
||||
self.has_comet = None
|
||||
@ -665,14 +725,15 @@ class ComicArchive:
|
||||
else:
|
||||
return True
|
||||
|
||||
|
||||
def isZip(self):
|
||||
return self.archive_type == self.ArchiveType.Zip
|
||||
|
||||
def isRar(self):
|
||||
return self.archive_type == self.ArchiveType.Rar
|
||||
|
||||
def isPdf(self):
|
||||
return self.archive_type == self.ArchiveType.Pdf
|
||||
|
||||
def isFolder(self):
|
||||
return self.archive_type == self.ArchiveType.Folder
|
||||
|
||||
@ -705,7 +766,8 @@ class ComicArchive:
|
||||
ext = os.path.splitext(self.path)[1].lower()
|
||||
|
||||
if (
|
||||
( self.isZip() or self.isRar() or self.isPdf()) #or self.isFolder() )
|
||||
# or self.isFolder() )
|
||||
(self.isZip() or self.isRar() or self.isPdf())
|
||||
and
|
||||
(self.getNumberOfPages() > 0)
|
||||
|
||||
@ -736,7 +798,6 @@ class ComicArchive:
|
||||
retcode = self.writeCoMet(metadata)
|
||||
return retcode
|
||||
|
||||
|
||||
def hasMetadata(self, style):
|
||||
|
||||
if style == MetaDataStyle.CIX:
|
||||
@ -803,13 +864,18 @@ class ComicArchive:
|
||||
for name in name_list:
|
||||
fname = os.path.split(name)[1]
|
||||
length = len(fname)
|
||||
if length_buckets.has_key( length ):
|
||||
if length in length_buckets:
|
||||
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)
|
||||
sorted_buckets = sorted(
|
||||
length_buckets.iteritems(),
|
||||
key=lambda k_v: (
|
||||
k_v[1],
|
||||
k_v[0]),
|
||||
reverse=True)
|
||||
|
||||
# statistical mode occurence is first
|
||||
mode_length = sorted_buckets[0][0]
|
||||
@ -829,20 +895,21 @@ class ComicArchive:
|
||||
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
|
||||
# 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:
|
||||
# get the list file names in the archive, and sort
|
||||
files = self.archiver.getArchiveFilenameList()
|
||||
|
||||
# seems like some archive creators are on Windows, and don't know about case-sensitivity!
|
||||
# seems like some archive creators are on Windows, and don't know
|
||||
# about case-sensitivity!
|
||||
if sort_list:
|
||||
def keyfunc(k):
|
||||
# hack to account for some weird scanner ID pages
|
||||
@ -856,7 +923,11 @@ class ComicArchive:
|
||||
# make a sub-list of image files
|
||||
self.page_list = []
|
||||
for name in files:
|
||||
if ( name[-4:].lower() in [ ".jpg", "jpeg", ".png", ".gif", "webp" ] and os.path.basename(name)[0] != "." ):
|
||||
if (name[-4:].lower() in [".jpg",
|
||||
"jpeg",
|
||||
".png",
|
||||
".gif",
|
||||
"webp"] and os.path.basename(name)[0] != "."):
|
||||
self.page_list.append(name)
|
||||
|
||||
return self.page_list
|
||||
@ -888,7 +959,8 @@ class ComicArchive:
|
||||
def hasCBI(self):
|
||||
if self.has_cbi is None:
|
||||
|
||||
#if ( not ( self.isZip() or self.isRar()) or not self.seemsToBeAComicArchive() ):
|
||||
# if ( not ( self.isZip() or self.isRar()) or not
|
||||
# self.seemsToBeAComicArchive() ):
|
||||
if not self.seemsToBeAComicArchive():
|
||||
self.has_cbi = False
|
||||
else:
|
||||
@ -955,7 +1027,9 @@ class ComicArchive:
|
||||
if metadata is not None:
|
||||
self.applyArchiveInfoToMetadata(metadata, calc_page_sizes=True)
|
||||
cix_string = ComicInfoXml().stringFromMetadata(metadata)
|
||||
write_success = self.archiver.writeArchiveFile( self.ci_xml_filename, cix_string )
|
||||
write_success = self.archiver.writeArchiveFile(
|
||||
self.ci_xml_filename,
|
||||
cix_string)
|
||||
if write_success:
|
||||
self.has_cix = True
|
||||
self.cix_md = metadata
|
||||
@ -966,7 +1040,8 @@ class ComicArchive:
|
||||
|
||||
def removeCIX(self):
|
||||
if self.hasCIX():
|
||||
write_success = self.archiver.removeArchiveFile( self.ci_xml_filename )
|
||||
write_success = self.archiver.removeArchiveFile(
|
||||
self.ci_xml_filename)
|
||||
if write_success:
|
||||
self.has_cix = False
|
||||
self.cix_md = None
|
||||
@ -974,7 +1049,6 @@ class ComicArchive:
|
||||
return write_success
|
||||
return True
|
||||
|
||||
|
||||
def hasCIX(self):
|
||||
if self.has_cix is None:
|
||||
|
||||
@ -986,7 +1060,6 @@ class ComicArchive:
|
||||
self.has_cix = False
|
||||
return self.has_cix
|
||||
|
||||
|
||||
def readCoMet(self):
|
||||
if self.comet_md is None:
|
||||
raw_comet = self.readRawCoMet()
|
||||
@ -1007,7 +1080,8 @@ class ComicArchive:
|
||||
break
|
||||
if cover_idx != 0:
|
||||
del (self.comet_md.pages[0]['Type'])
|
||||
self.comet_md.pages[ cover_idx ]['Type'] = PageType.FrontCover
|
||||
self.comet_md.pages[cover_idx][
|
||||
'Type'] = PageType.FrontCover
|
||||
|
||||
return self.comet_md
|
||||
|
||||
@ -1036,7 +1110,9 @@ class ComicArchive:
|
||||
metadata.coverImage = self.getPageName(cover_idx)
|
||||
|
||||
comet_string = CoMet().stringFromMetadata(metadata)
|
||||
write_success = self.archiver.writeArchiveFile( self.comet_filename, comet_string )
|
||||
write_success = self.archiver.writeArchiveFile(
|
||||
self.comet_filename,
|
||||
comet_string)
|
||||
if write_success:
|
||||
self.has_comet = True
|
||||
self.comet_md = metadata
|
||||
@ -1047,7 +1123,8 @@ class ComicArchive:
|
||||
|
||||
def removeCoMet(self):
|
||||
if self.hasCoMet():
|
||||
write_success = self.archiver.removeArchiveFile( self.comet_filename )
|
||||
write_success = self.archiver.removeArchiveFile(
|
||||
self.comet_filename)
|
||||
if write_success:
|
||||
self.has_comet = False
|
||||
self.comet_md = None
|
||||
@ -1061,7 +1138,8 @@ class ComicArchive:
|
||||
if not self.seemsToBeAComicArchive():
|
||||
return self.has_comet
|
||||
|
||||
#look at all xml files in root, and search for CoMet data, get first
|
||||
# look at all xml files in root, and search for CoMet data, get
|
||||
# first
|
||||
for n in self.archiver.getArchiveFilenameList():
|
||||
if (os.path.dirname(n) == "" and
|
||||
os.path.splitext(n)[1].lower() == '.xml'):
|
||||
@ -1079,8 +1157,6 @@ class ComicArchive:
|
||||
|
||||
return self.has_comet
|
||||
|
||||
|
||||
|
||||
def applyArchiveInfoToMetadata(self, md, calc_page_sizes=False):
|
||||
md.pageCount = self.getNumberOfPages()
|
||||
|
||||
@ -1106,8 +1182,6 @@ class ComicArchive:
|
||||
data = self.getPage(idx)
|
||||
p['ImageSize'] = str(len(data))
|
||||
|
||||
|
||||
|
||||
def metadataFromFilename(self, parse_scan_info=True):
|
||||
|
||||
metadata = GenericMetadata()
|
||||
@ -1140,4 +1214,3 @@ class ComicArchive:
|
||||
|
||||
zip_archiver = ZipArchiver(zipfilename)
|
||||
return zip_archiver.copyFromArchive(self.archiver)
|
||||
|
||||
|
||||
@ -1,34 +1,29 @@
|
||||
"""
|
||||
A python class to encapsulate the ComicBookInfo data
|
||||
"""
|
||||
"""A class to encapsulate the ComicBookInfo data"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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.
|
||||
"""
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
import zipfile
|
||||
#import zipfile
|
||||
|
||||
from genericmetadata import GenericMetadata
|
||||
import utils
|
||||
#import ctversion
|
||||
|
||||
class ComicBookInfo:
|
||||
|
||||
class ComicBookInfo:
|
||||
|
||||
def metadataFromString(self, string):
|
||||
|
||||
@ -88,8 +83,8 @@ class ComicBookInfo:
|
||||
cbi_container = self.createJSONDictionary(metadata)
|
||||
return json.dumps(cbi_container)
|
||||
|
||||
#verify that the string actually contains CBI data in JSON format
|
||||
def validateString(self, string):
|
||||
"""Verify that the string actually contains CBI data in JSON format"""
|
||||
|
||||
try:
|
||||
cbi_container = json.loads(string)
|
||||
@ -98,10 +93,9 @@ class ComicBookInfo:
|
||||
|
||||
return ('ComicBookInfo/1.0' in cbi_container)
|
||||
|
||||
|
||||
def createJSONDictionary(self, metadata):
|
||||
"""Create the dictionary that we will convert to JSON text"""
|
||||
|
||||
# Create the dictionary that we will convert to JSON text
|
||||
cbi = dict()
|
||||
cbi_container = {'appID': 'ComicTagger/' + '1.0.0', # ctversion.version,
|
||||
'lastModified': str(datetime.now()),
|
||||
@ -141,7 +135,6 @@ class ComicBookInfo:
|
||||
|
||||
return cbi_container
|
||||
|
||||
|
||||
def writeToExternalFile(self, filename, metadata):
|
||||
|
||||
cbi_container = self.createJSONDictionary(metadata)
|
||||
@ -149,4 +142,3 @@ class ComicBookInfo:
|
||||
f = open(filename, 'w')
|
||||
f.write(json.dumps(cbi_container, indent=4))
|
||||
f.close
|
||||
|
||||
|
||||
@ -1,30 +1,28 @@
|
||||
"""
|
||||
A python class to encapsulate ComicRack's ComicInfo.xml data
|
||||
"""
|
||||
"""A class to encapsulate ComicRack's ComicInfo.xml data"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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
|
||||
# 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.
|
||||
"""
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from datetime import datetime
|
||||
import zipfile
|
||||
from pprint import pprint
|
||||
import xml.etree.ElementTree as ET
|
||||
#from datetime import datetime
|
||||
#from pprint import pprint
|
||||
#import zipfile
|
||||
|
||||
from genericmetadata import GenericMetadata
|
||||
import utils
|
||||
|
||||
|
||||
class ComicInfoXml:
|
||||
|
||||
writer_synonyms = ['writer', 'plotter', 'scripter']
|
||||
@ -35,7 +33,6 @@ class ComicInfoXml:
|
||||
cover_synonyms = ['cover', 'covers', 'coverartist', 'cover artist']
|
||||
editor_synonyms = ['editor']
|
||||
|
||||
|
||||
def getParseableCredits(self):
|
||||
parsable_credits = []
|
||||
parsable_credits.extend(self.writer_synonyms)
|
||||
@ -85,6 +82,7 @@ class ComicInfoXml:
|
||||
root.attrib['xmlns:xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
|
||||
root.attrib['xmlns:xsd'] = "http://www.w3.org/2001/XMLSchema"
|
||||
# helper func
|
||||
|
||||
def assign(cix_entry, md_entry):
|
||||
if md_entry is not None:
|
||||
ET.SubElement(root, cix_entry).text = u"{0}".format(md_entry)
|
||||
@ -105,7 +103,8 @@ class ComicInfoXml:
|
||||
assign('Month', md.month)
|
||||
assign('Day', md.day)
|
||||
|
||||
# need to specially process the credits, since they are structured differently than CIX
|
||||
# need to specially process the credits, since they are structured
|
||||
# differently than CIX
|
||||
credit_writer_list = list()
|
||||
credit_penciller_list = list()
|
||||
credit_inker_list = list()
|
||||
@ -114,7 +113,8 @@ class ComicInfoXml:
|
||||
credit_cover_list = list()
|
||||
credit_editor_list = list()
|
||||
|
||||
# first, loop thru credits, and build a list for each role that CIX supports
|
||||
# first, loop thru credits, and build a list for each role that CIX
|
||||
# supports
|
||||
for credit in metadata.credits:
|
||||
|
||||
if credit['role'].lower() in set(self.writer_synonyms):
|
||||
@ -197,7 +197,6 @@ class ComicInfoXml:
|
||||
tree = ET.ElementTree(root)
|
||||
return tree
|
||||
|
||||
|
||||
def convertXMLToMetadata(self, tree):
|
||||
|
||||
root = tree.getroot()
|
||||
@ -209,7 +208,6 @@ class ComicInfoXml:
|
||||
metadata = GenericMetadata()
|
||||
md = metadata
|
||||
|
||||
|
||||
# Helper function
|
||||
def xlate(tag):
|
||||
node = root.find(tag)
|
||||
@ -290,4 +288,3 @@ class ComicInfoXml:
|
||||
|
||||
tree = ET.parse(filename)
|
||||
return self.convertXMLToMetadata(tree)
|
||||
|
||||
|
||||
@ -1,26 +1,21 @@
|
||||
"""
|
||||
Functions for parsing comic info from filename
|
||||
"""Functions for parsing comic info from filename
|
||||
|
||||
This should probably be re-written, but, well, it mostly works!
|
||||
|
||||
"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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.
|
||||
"""
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
# Some portions of this code were modified from pyComicMetaThis project
|
||||
# http://code.google.com/p/pycomicmetathis/
|
||||
@ -29,6 +24,7 @@ import re
|
||||
import os
|
||||
from urllib import unquote
|
||||
|
||||
|
||||
class FileNameParser:
|
||||
|
||||
def repl(self, m):
|
||||
@ -43,13 +39,12 @@ class FileNameParser:
|
||||
string = re.sub(ph, self.repl, string)
|
||||
return string # .strip()
|
||||
|
||||
|
||||
def getIssueCount(self, filename, issue_end):
|
||||
|
||||
count = ""
|
||||
filename = filename[issue_end:]
|
||||
|
||||
# replace any name seperators with spaces
|
||||
# replace any name separators with spaces
|
||||
tmpstr = self.fixSpaces(filename)
|
||||
found = False
|
||||
|
||||
@ -64,28 +59,30 @@ class FileNameParser:
|
||||
count = match.group()
|
||||
found = True
|
||||
|
||||
|
||||
count = count.lstrip("0")
|
||||
|
||||
return count
|
||||
|
||||
def getIssueNumber(self, filename):
|
||||
|
||||
# Returns a tuple of issue number string, and start and end indexs in the filename
|
||||
# (The indexes will be used to split the string up for further parsing)
|
||||
"""Returns a tuple of issue number string, and start and end indexes in the filename
|
||||
(The indexes will be used to split the string up for further parsing)
|
||||
"""
|
||||
|
||||
found = False
|
||||
issue = ''
|
||||
start = 0
|
||||
end = 0
|
||||
|
||||
# first, look for multiple "--", this means it's formatted differently from most:
|
||||
# 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
|
||||
# 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
|
||||
# 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("+", " ")
|
||||
@ -94,10 +91,11 @@ class FileNameParser:
|
||||
filename = re.sub("\(.*?\)", self.repl, filename)
|
||||
filename = re.sub("\[.*?\]", self.repl, filename)
|
||||
|
||||
# replace any name seperators with spaces
|
||||
# replace any name separators with spaces
|
||||
filename = self.fixSpaces(filename)
|
||||
|
||||
# remove any "of NN" phrase with spaces (problem: this could break on some titles)
|
||||
# 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)
|
||||
@ -119,14 +117,15 @@ class FileNameParser:
|
||||
|
||||
# Now try to search for the likely issue number word in the list
|
||||
|
||||
# first look for a word with "#" followed by digits with optional sufix
|
||||
# first look for a word with "#" followed by digits with optional suffix
|
||||
# this is almost certainly the issue number
|
||||
for w in reversed(word_list):
|
||||
if re.match("#[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
|
||||
found = True
|
||||
break
|
||||
|
||||
# same as above but w/o a '#', and only look at the last word in the list
|
||||
# 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]):
|
||||
@ -149,19 +148,20 @@ class FileNameParser:
|
||||
return issue, start, end
|
||||
|
||||
def getSeriesName(self, filename, issue_start):
|
||||
|
||||
# use the issue number string index to split the filename string
|
||||
"""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
|
||||
# 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
|
||||
# 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("+", " ")
|
||||
@ -218,13 +218,13 @@ class FileNameParser:
|
||||
match = re.search('(\(\d\d\d\d\))|(--\d\d\d\d--)', filename)
|
||||
if match:
|
||||
year = match.group()
|
||||
# remove non-numerics
|
||||
# remove non-digits
|
||||
year = re.sub("[^0-9]", "", year)
|
||||
return year
|
||||
|
||||
def getRemainder(self, filename, year, count, volume, issue_end):
|
||||
"""Make a guess at where the the non-interesting stuff begins"""
|
||||
|
||||
#make a guess at where the the non-interesting stuff begins
|
||||
remainder = ""
|
||||
|
||||
if "--" in filename:
|
||||
@ -243,7 +243,9 @@ class FileNameParser:
|
||||
remainder = remainder.replace("of " + count, "", 1)
|
||||
|
||||
remainder = remainder.replace("()", "")
|
||||
remainder = remainder.replace(" "," ") # cleans some whitespace mess
|
||||
remainder = remainder.replace(
|
||||
" ",
|
||||
" ") # cleans some whitespace mess
|
||||
|
||||
return remainder.strip()
|
||||
|
||||
@ -258,7 +260,7 @@ class FileNameParser:
|
||||
# url decode, just in case
|
||||
filename = unquote(filename)
|
||||
|
||||
# sometimes archives get messed up names from too many decodings
|
||||
# sometimes archives get messed up names from too many decodes
|
||||
# often url encodings will break and leave "_28" and "_29" in place
|
||||
# of "(" and ")" see if there are a number of these, and replace them
|
||||
if filename.count("_28") > 1 and filename.count("_29") > 1:
|
||||
@ -268,14 +270,18 @@ class FileNameParser:
|
||||
self.issue, issue_start, issue_end = self.getIssueNumber(filename)
|
||||
self.series, self.volume = self.getSeriesName(filename, issue_start)
|
||||
|
||||
|
||||
# provides proper value when the filename doesn't have a issue number
|
||||
if issue_end == 0:
|
||||
issue_end = len(self.series)
|
||||
|
||||
self.year = self.getYear(filename, issue_end)
|
||||
self.issue_count = self.getIssueCount(filename, issue_end)
|
||||
self.remainder = self.getRemainder( filename, self.year, self.issue_count, self.volume, issue_end )
|
||||
self.remainder = self.getRemainder(
|
||||
filename,
|
||||
self.year,
|
||||
self.issue_count,
|
||||
self.volume,
|
||||
issue_end)
|
||||
|
||||
if self.issue != "":
|
||||
# strip off leading zeros
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
"""
|
||||
A python class for internal metadata storage
|
||||
"""A class for internal metadata storage
|
||||
|
||||
The goal of this class is to handle ALL the data that might come from various
|
||||
tagging schemes and databases, such as ComicVine or GCD. This makes conversion
|
||||
@ -7,26 +6,30 @@
|
||||
|
||||
"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 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.
|
||||
You may obtain a copy of the License at
|
||||
# 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
|
||||
# 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.
|
||||
"""
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import utils
|
||||
|
||||
# These page info classes are exactly the same as the CIX scheme, since it's unique
|
||||
|
||||
class PageType:
|
||||
|
||||
"""
|
||||
These page info classes are exactly the same as the CIX scheme, since
|
||||
it's unique
|
||||
"""
|
||||
|
||||
FrontCover = "FrontCover"
|
||||
InnerCover = "InnerCover"
|
||||
Roundup = "Roundup"
|
||||
@ -50,6 +53,7 @@ class PageInfo:
|
||||
ImageHeight = 0
|
||||
"""
|
||||
|
||||
|
||||
class GenericMetadata:
|
||||
|
||||
def __init__(self):
|
||||
@ -107,13 +111,15 @@ class GenericMetadata:
|
||||
self.coverImage = None
|
||||
|
||||
def overlay(self, new_md):
|
||||
# Overlay a metadata object on this one
|
||||
# that is, when the new object has non-None
|
||||
# values, over-write them to this one
|
||||
"""Overlay a metadata object on this one
|
||||
|
||||
That is, when the new object has non-None values, over-write them
|
||||
to this one.
|
||||
"""
|
||||
|
||||
def assign(cur, new):
|
||||
if new is not None:
|
||||
if type(new) == str and len(new) == 0:
|
||||
if isinstance(new, str) and len(new) == 0:
|
||||
setattr(self, cur, None)
|
||||
else:
|
||||
setattr(self, cur, new)
|
||||
@ -173,10 +179,9 @@ class GenericMetadata:
|
||||
if len(new_md.pages) > 0:
|
||||
assign("pages", new_md.pages)
|
||||
|
||||
|
||||
def overlayCredits(self, new_credits):
|
||||
for c in new_credits:
|
||||
if c.has_key('primary') and c['primary']:
|
||||
if 'primary' in c and c['primary']:
|
||||
primary = True
|
||||
else:
|
||||
primary = False
|
||||
@ -200,7 +205,8 @@ class GenericMetadata:
|
||||
self.pages.append(page_dict)
|
||||
|
||||
def getArchivePageIndex(self, pagenum):
|
||||
# convert the displayed page number to the page index of the file in the archive
|
||||
# convert the displayed page number to the page index of the file in
|
||||
# the archive
|
||||
if pagenum < len(self.pages):
|
||||
return int(self.pages[pagenum]['Image'])
|
||||
else:
|
||||
@ -239,7 +245,6 @@ class GenericMetadata:
|
||||
if not found:
|
||||
self.credits.append(credit)
|
||||
|
||||
|
||||
def __str__(self):
|
||||
vals = []
|
||||
if self.isEmpty:
|
||||
@ -297,7 +302,7 @@ class GenericMetadata:
|
||||
|
||||
for c in self.credits:
|
||||
primary = ""
|
||||
if c.has_key('primary') and c['primary']:
|
||||
if 'primary' in c and c['primary']:
|
||||
primary = " [P]"
|
||||
add_string("credit", c['role'] + ": " + c['person'] + primary)
|
||||
|
||||
|
||||
@ -1,39 +1,32 @@
|
||||
# coding=utf-8
|
||||
"""
|
||||
Class for handling the odd permutations of an 'issue number' that the comics industry throws at us
|
||||
|
||||
e.g.:
|
||||
|
||||
"12"
|
||||
"12.1"
|
||||
"0"
|
||||
"-1"
|
||||
"5AU"
|
||||
"100-2"
|
||||
"""Support for mixed digit/string type Issue field
|
||||
|
||||
Class for handling the odd permutations of an 'issue number' that the
|
||||
comics industry throws at us.
|
||||
e.g.: "12", "12.1", "0", "-1", "5AU", "100-2"
|
||||
"""
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 Anthony Beville
|
||||
# Copyright 2012-2014 Anthony Beville
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
# 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
|
||||
# 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.
|
||||
"""
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
#import utils
|
||||
#import math
|
||||
#import re
|
||||
|
||||
import utils
|
||||
import math
|
||||
import re
|
||||
|
||||
class IssueString:
|
||||
|
||||
def __init__(self, text):
|
||||
|
||||
# break up the issue number string into 2 parts: the numeric and suffix string.
|
||||
@ -45,7 +38,7 @@ class IssueString:
|
||||
if text is None:
|
||||
return
|
||||
|
||||
if type(text) == int:
|
||||
if isinstance(text, int):
|
||||
text = str(text)
|
||||
|
||||
if len(text) == 0:
|
||||
@ -61,7 +54,8 @@ class IssueString:
|
||||
|
||||
# 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)
|
||||
# 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.":
|
||||
@ -79,7 +73,8 @@ class IssueString:
|
||||
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 there is no numeric after the minus, make the minus part of
|
||||
# the suffix
|
||||
if idx == 1 and start == 1:
|
||||
idx = 0
|
||||
|
||||
@ -136,5 +131,3 @@ class IssueString:
|
||||
if self.num is None:
|
||||
return None
|
||||
return int(self.num)
|
||||
|
||||
|
||||
|
||||
@ -1,25 +1,20 @@
|
||||
# coding=utf-8
|
||||
"""Some generic utilities"""
|
||||
|
||||
"""
|
||||
Some generic utilities
|
||||
"""
|
||||
# Copyright 2012-2014 Anthony Beville
|
||||
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
|
||||
"""
|
||||
Copyright 2012-2014 Anthony Beville
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
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
|
||||
# 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.
|
||||
|
||||
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
|
||||
@ -31,12 +26,14 @@ import codecs
|
||||
class UtilsVars:
|
||||
already_fixed_encoding = False
|
||||
|
||||
|
||||
def get_actual_preferred_encoding():
|
||||
preferred_encoding = locale.getpreferredencoding()
|
||||
if platform.system() == "Darwin":
|
||||
preferred_encoding = "utf-8"
|
||||
return preferred_encoding
|
||||
|
||||
|
||||
def fix_output_encoding():
|
||||
if not UtilsVars.already_fixed_encoding:
|
||||
# this reads the environment and inits the right locale
|
||||
@ -48,28 +45,28 @@ def fix_output_encoding( ):
|
||||
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
|
||||
"""
|
||||
"""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:
|
||||
# if path is a folder, walk it recursively, and all files underneath
|
||||
if isinstance(p, str):
|
||||
# make sure string is unicode
|
||||
p = p.decode(filename_encoding) # , 'replace')
|
||||
elif type(p) != unicode:
|
||||
elif not isinstance(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:
|
||||
if isinstance(f, str):
|
||||
# make sure string is unicode
|
||||
f = f.decode(filename_encoding, 'replace')
|
||||
elif type(f) != unicode:
|
||||
elif not isinstance(f, unicode):
|
||||
# it's probably a QString
|
||||
f = unicode(f)
|
||||
filelist.append(os.path.join(root, f))
|
||||
@ -78,6 +75,7 @@ def get_recursive_filelist( pathlist ):
|
||||
|
||||
return filelist
|
||||
|
||||
|
||||
def listToString(l):
|
||||
string = ""
|
||||
if l is not None:
|
||||
@ -87,19 +85,23 @@ def listToString( l ):
|
||||
string += item
|
||||
return string
|
||||
|
||||
|
||||
def addtopath(dirname):
|
||||
if dirname is not None and dirname != "":
|
||||
|
||||
# verify that path doesn't already contain the given dirname
|
||||
tmpdirname = re.escape(dirname)
|
||||
pattern = r"{sep}{dir}$|^{dir}{sep}|{sep}{dir}{sep}|^{dir}$".format( dir=tmpdirname, sep=os.pathsep)
|
||||
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):
|
||||
"""Returns path of the executable, if it exists"""
|
||||
|
||||
def is_exe(fpath):
|
||||
return os.path.isfile(fpath) and os.access(fpath, os.X_OK)
|
||||
@ -116,6 +118,7 @@ def which(program):
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def removearticles(text):
|
||||
text = text.lower()
|
||||
articles = ['and', 'the', 'a', '&', 'issue']
|
||||
@ -131,8 +134,8 @@ def removearticles( text ):
|
||||
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,
|
||||
# since the CV API changed, searches for series names with periods
|
||||
# now explicitly require the period to be in the search key,
|
||||
# so the line below is removed (for now)
|
||||
#newText = newText.replace(".", "")
|
||||
|
||||
@ -141,17 +144,19 @@ def removearticles( text ):
|
||||
|
||||
def unique_file(file_name):
|
||||
counter = 1
|
||||
file_name_parts = os.path.splitext(file_name) # returns ('/path/file', '.ext')
|
||||
while 1:
|
||||
# returns ('/path/file', '.ext')
|
||||
file_name_parts = os.path.splitext(file_name)
|
||||
while True:
|
||||
if not os.path.lexists(file_name):
|
||||
return file_name
|
||||
file_name = file_name_parts[0] + ' (' + str(counter) + ')' + file_name_parts[1]
|
||||
file_name = file_name_parts[
|
||||
0] + ' (' + str(counter) + ')' + file_name_parts[1]
|
||||
counter += 1
|
||||
|
||||
|
||||
# -o- coding: utf-8 -o-
|
||||
# ISO639 python dict
|
||||
# oficial list in http://www.loc.gov/standards/iso639-2/php/code_list.php
|
||||
# official list in http://www.loc.gov/standards/iso639-2/php/code_list.php
|
||||
|
||||
lang_dict = {
|
||||
'ab': 'Abkhaz',
|
||||
@ -576,22 +581,12 @@ countries = [
|
||||
]
|
||||
|
||||
|
||||
|
||||
def getLanguageDict():
|
||||
return lang_dict
|
||||
|
||||
|
||||
def getLanguageFromISO(iso):
|
||||
if iso == None:
|
||||
if iso is None:
|
||||
return None
|
||||
else:
|
||||
return lang_dict[iso]
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user