def parseMetadataFromString(self, mdstr):
"""The metadata string is a comma separated list of name-value pairs
The names match the attributes of the internal metadata struct (for now)
The caret is the special "escape character", since it's not common in
natural language text
example = "series=Kickers^, Inc. ,issue=1, year=1986"
"""
escaped_comma = "^,"
escaped_equals = "^="
replacement_token = "<_~_>"
md = GenericMetadata()
# First, replace escaped commas with with a unique token (to be changed
# back later)
mdstr = mdstr.replace(escaped_comma, replacement_token)
tmp_list = mdstr.split(",")
md_list = []
for item in tmp_list:
item = item.replace(replacement_token, ",")
md_list.append(item)
# Now build a nice dict from the list
md_dict = dict()
for item in md_list:
# Make sure to fix any escaped equal signs
i = item.replace(escaped_equals, replacement_token)
key, value = i.split("=")
value = value.replace(replacement_token, "=").strip()
key = key.strip()
if key.lower() == "credit":
cred_attribs = value.split(":")
role = cred_attribs[0]
person = (cred_attribs[1] if len(cred_attribs) > 1 else "")
primary = (cred_attribs[2] if len(cred_attribs) > 2 else None)
md.addCredit(
person.strip(),
role.strip(),
True if primary is not None else False)
else:
md_dict[key] = value
# Map the dict to the metadata object
for key in md_dict:
if not hasattr(md, key):
print("Warning: '{0}' is not a valid tag name".format(key))
else:
md.isEmpty = False
setattr(md, key, md_dict[key])
# print(md)
return md
def parseMetadataFromString(self, mdstr):
"""The metadata string is a comma separated list of name-value pairs
The names match the attributes of the internal metadata struct (for now)
The caret is the special "escape character", since it's not common in
natural language text
example = "series=Kickers^, Inc. ,issue=1, year=1986"
"""
escaped_comma = "^,"
escaped_equals = "^="
replacement_token = "<_~_>"
md = GenericMetadata()
# First, replace escaped commas with with a unique token (to be changed
# back later)
mdstr = mdstr.replace(escaped_comma, replacement_token)
tmp_list = mdstr.split(",")
md_list = []
for item in tmp_list:
item = item.replace(replacement_token, ",")
md_list.append(item)
# Now build a nice dict from the list
md_dict = dict()
for item in md_list:
# Make sure to fix any escaped equal signs
i = item.replace(escaped_equals, replacement_token)
key, value = i.split("=")
value = value.replace(replacement_token, "=").strip()
key = key.strip()
if key.lower() == "credit":
cred_attribs = value.split(":")
role = cred_attribs[0]
person = (cred_attribs[1] if len(cred_attribs) > 1 else "")
primary = (cred_attribs[2] if len(cred_attribs) > 2 else None)
md.addCredit(person.strip(), role.strip(),
True if primary is not None else False)
else:
md_dict[key] = value
# Map the dict to the metadata object
for key in md_dict:
if not hasattr(md, key):
print("Warning: '{0}' is not a valid tag name".format(key))
else:
md.isEmpty = False
setattr(md, key, md_dict[key])
# print(md)
return md
def __init__(self, comic_archive, settings):
self.comic_archive = comic_archive
self.image_hasher = 1
self.onlyUseAdditionalMetaData = False
# a decent hamming score, good enough to call it a match
self.min_score_thresh = 16
# for alternate covers, be more stringent, since we're a bit more scattershot in comparisons
self.min_alternate_score_thresh = 12
# the min distance a hamming score must be to separate itself from closest neighbor
self.min_score_distance = 4
# a very strong hamming score, almost certainly the same image
self.strong_score_thresh = 8
# used to eliminate series names that are too long based on our search string
self.length_delta_thresh = settings.id_length_delta_thresh
# used to eliminate unlikely publishers
self.publisher_blacklist = [
s.strip().lower()
for s in settings.id_publisher_blacklist.split(',')
]
self.additional_metadata = GenericMetadata()
self.output_function = IssueIdentifier.defaultWriteOutput
self.callback = None
self.coverUrlCallback = None
self.search_result = self.ResultNoMatches
self.cover_page_index = 0
self.cancel = False
self.waitAndRetryOnRateLimit = False
def readMetadata(self, style):
if style == MetaDataStyle.CIX:
return self.readCIX()
elif style == MetaDataStyle.CBI:
return self.readCBI()
elif style == MetaDataStyle.COMET:
return self.readCoMet()
else:
return GenericMetadata()
def readCBI(self):
if self.cbi_md is None:
raw_cbi = self.readRawCBI()
if raw_cbi is None:
self.cbi_md = GenericMetadata()
else:
self.cbi_md = ComicBookInfo().metadataFromString(raw_cbi)
self.cbi_md.setDefaultPageList(self.getNumberOfPages())
return self.cbi_md
def autoSelect(self):
if self.comic_archive is None:
QtGui.QMessageBox.information(
self, "Auto-Select", "You need to load a comic first!")
return
if self.issue_number is None or self.issue_number == "":
QtGui.QMessageBox.information(
self,
"Auto-Select",
"Can't auto-select without an issue number (yet!)")
return
self.iddialog = IDProgressWindow(self)
self.iddialog.setModal(True)
self.iddialog.rejected.connect(self.identifyCancel)
self.iddialog.show()
self.ii = IssueIdentifier(self.comic_archive, self.settings)
md = GenericMetadata()
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
self.ii.cover_page_index = int(self.cover_index_list[0])
self.id_thread = IdentifyThread(self.ii)
self.id_thread.identifyComplete.connect(self.identifyComplete)
self.id_thread.identifyLogMsg.connect(self.logIDOutput)
self.id_thread.identifyProgress.connect(self.identifyProgress)
self.id_thread.start()
self.iddialog.exec_()
def create_local_metadata(opts, ca, has_desired_tags):
md = GenericMetadata()
md.setDefaultPageList(ca.getNumberOfPages())
if has_desired_tags:
md = ca.readMetadata(opts.data_style)
# now, overlay the parsed filename info
if opts.parse_filename:
md.overlay(ca.metadataFromFilename())
# finally, use explicit stuff
if opts.metadata is not None:
md.overlay(opts.metadata)
return md
def create_local_metadata( opts, ca, has_desired_tags ): md = GenericMetadata() md.setDefaultPageList( ca.getNumberOfPages() ) if has_desired_tags: md = ca.readMetadata( opts.data_style ) # now, overlay the parsed filename info if opts.parse_filename: md.overlay( ca.metadataFromFilename() ) # finally, use explicit stuff if opts.metadata is not None: md.overlay( opts.metadata ) return md
def metadataFromFilename(self, parse_scan_info=True):
metadata = GenericMetadata()
fnp = FileNameParser()
fnp.parseFilename(self.path)
if fnp.issue != "":
metadata.issue = fnp.issue
if fnp.series != "":
metadata.series = fnp.series
if fnp.volume != "":
metadata.volume = fnp.volume
if fnp.year != "":
metadata.year = fnp.year
if fnp.issue_count != "":
metadata.issueCount = fnp.issue_count
if parse_scan_info:
if fnp.remainder != "":
metadata.scanInfo = fnp.remainder
metadata.isEmpty = False
return metadata
def readCIX(self):
if self.cix_md is None:
raw_cix = self.readRawCIX()
if raw_cix is None or raw_cix == "":
self.cix_md = GenericMetadata()
else:
self.cix_md = ComicInfoXml().metadataFromString(raw_cix)
#validate the existing page list (make sure count is correct)
if len(self.cix_md.pages) != 0:
if len(self.cix_md.pages) != self.getNumberOfPages():
# pages array doesn't match the actual number of images we're seeing
# in the archive, so discard the data
self.cix_md.pages = []
if len(self.cix_md.pages) == 0:
self.cix_md.setDefaultPageList(self.getNumberOfPages())
return self.cix_md
def metadataFromFilename( self ): metadata = GenericMetadata() fnp = FileNameParser() fnp.parseFilename( self.path ) if fnp.issue != "": metadata.issue = fnp.issue if fnp.series != "": metadata.series = fnp.series if fnp.volume != "": metadata.volume = fnp.volume if fnp.year != "": metadata.year = fnp.year if fnp.issue_count != "": metadata.issueCount = fnp.issue_count if self.settings.parse_scan_info: if fnp.remainder != "": metadata.scanInfo = fnp.remainder metadata.isEmpty = False return metadata
def readCoMet( self ): if self.comet_md is None: raw_comet = self.readRawCoMet() if raw_comet is None or raw_comet == "": self.comet_md = GenericMetadata() else: self.comet_md = CoMet().metadataFromString( raw_comet ) self.comet_md.setDefaultPageList( self.getNumberOfPages() ) #use the coverImage value from the comet_data to mark the cover in this struct # walk through list of images in file, and find the matching one for md.coverImage # need to remove the existing one in the default if self.comet_md.coverImage is not None: cover_idx = 0 for idx,f in enumerate(self.getPageNameList()): if self.comet_md.coverImage == f: cover_idx = idx break if cover_idx != 0: del (self.comet_md.pages[0]['Type'] ) self.comet_md.pages[ cover_idx ]['Type'] = PageType.FrontCover return self.comet_md
def autoSelect(self):
if self.comic_archive is None:
QtGui.QMessageBox.information(self, "Auto-Select",
"You need to load a comic first!")
return
if self.issue_number is None or self.issue_number == "":
QtGui.QMessageBox.information(
self, "Auto-Select",
"Can't auto-select without an issue number (yet!)")
return
self.iddialog = IDProgressWindow(self)
self.iddialog.setModal(True)
self.iddialog.rejected.connect(self.identifyCancel)
self.iddialog.show()
self.ii = IssueIdentifier(self.comic_archive, self.settings)
md = GenericMetadata()
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
self.ii.cover_page_index = int(self.cover_index_list[0])
self.id_thread = IdentifyThread(self.ii)
self.id_thread.identifyComplete.connect(self.identifyComplete)
self.id_thread.identifyLogMsg.connect(self.logIDOutput)
self.id_thread.identifyProgress.connect(self.identifyProgress)
self.id_thread.start()
self.iddialog.exec_()
def convertXMLToMetadata(self, tree):
root = tree.getroot()
if root.tag != "comet":
raise 1
return None
metadata = GenericMetadata()
md = metadata
# Helper function
def xlate(tag):
node = root.find(tag)
if node is not None:
return node.text
else:
return None
md.series = xlate("series")
md.title = xlate("title")
md.issue = xlate("issue")
md.volume = xlate("volume")
md.comments = xlate("description")
md.publisher = xlate("publisher")
md.language = xlate("language")
md.format = xlate("format")
md.pageCount = xlate("pages")
md.maturityRating = xlate("rating")
md.price = xlate("price")
md.isVersionOf = xlate("isVersionOf")
md.rights = xlate("rights")
md.identifier = xlate("identifier")
md.lastMark = xlate("lastMark")
md.genre = xlate("genre") # TODO - repeatable field
date = xlate("date")
if date is not None:
parts = date.split("-")
if len(parts) > 0:
md.year = parts[0]
if len(parts) > 1:
md.month = parts[1]
md.coverImage = xlate("coverImage")
readingDirection = xlate("readingDirection")
if readingDirection is not None and readingDirection == "rtl":
md.manga = "YesAndRightToLeft"
# loop for character tags
char_list = []
for n in root:
if n.tag == "character":
char_list.append(n.text.strip())
md.characters = utils.listToString(char_list)
# Now extract the credit info
for n in root:
if (
n.tag == "writer"
or n.tag == "penciller"
or n.tag == "inker"
or n.tag == "colorist"
or n.tag == "letterer"
or n.tag == "editor"
):
metadata.addCredit(n.text.strip(), n.tag.title())
if n.tag == "coverDesigner":
metadata.addCredit(n.text.strip(), "Cover")
metadata.isEmpty = False
return metadata
def convertXMLToMetadata(self, tree):
root = tree.getroot()
if root.tag != 'comet':
raise 1
return None
metadata = GenericMetadata()
md = metadata
# Helper function
def xlate(tag):
node = root.find(tag)
if node is not None:
return node.text
else:
return None
md.series = xlate('series')
md.title = xlate('title')
md.issue = xlate('issue')
md.volume = xlate('volume')
md.comments = xlate('description')
md.publisher = xlate('publisher')
md.language = xlate('language')
md.format = xlate('format')
md.pageCount = xlate('pages')
md.maturityRating = xlate('rating')
md.price = xlate('price')
md.isVersionOf = xlate('isVersionOf')
md.rights = xlate('rights')
md.identifier = xlate('identifier')
md.lastMark = xlate('lastMark')
md.genre = xlate('genre') # TODO - repeatable field
date = xlate('date')
if date is not None:
parts = date.split('-')
if len(parts) > 0:
md.year = parts[0]
if len(parts) > 1:
md.month = parts[1]
md.coverImage = xlate('coverImage')
readingDirection = xlate('readingDirection')
if readingDirection is not None and readingDirection == "rtl":
md.manga = "YesAndRightToLeft"
# loop for character tags
char_list = []
for n in root:
if n.tag == 'character':
char_list.append(n.text.strip())
md.characters = utils.listToString(char_list)
# Now extract the credit info
for n in root:
if (n.tag == 'writer' or n.tag == 'penciller' or n.tag == 'inker'
or n.tag == 'colorist' or n.tag == 'letterer'
or n.tag == 'editor'):
metadata.addCredit(n.text.strip(), n.tag.title())
if n.tag == 'coverDesigner':
metadata.addCredit(n.text.strip(), "Cover")
metadata.isEmpty = False
return metadata
def mapCVDataToMetadata(self, volume_results, issue_results, settings):
# Now, map the Comic Vine data to generic metadata
metadata = GenericMetadata()
metadata.series = issue_results['volume']['name']
num_s = IssueString(issue_results['issue_number']).asString()
metadata.issue = num_s
metadata.title = issue_results['name']
metadata.publisher = volume_results['publisher']['name']
metadata.day, metadata.month, metadata.year = self.parseDateStr(
issue_results['cover_date'])
#metadata.issueCount = volume_results['count_of_issues']
metadata.comments = self.cleanup_html(
issue_results['description'], settings.remove_html_tables)
if settings.use_series_start_as_volume:
metadata.volume = volume_results['start_year']
metadata.notes = "Tagged with the {0} fork of ComicTagger {1} using info from Comic Vine on {2}. [Issue ID {3}]".format(
ctversion.fork,
ctversion.version,
datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
issue_results['id'])
#metadata.notes += issue_results['site_detail_url']
metadata.webLink = issue_results['site_detail_url']
person_credits = issue_results['person_credits']
for person in person_credits:
if 'role' in person:
roles = person['role'].split(',')
for role in roles:
# can we determine 'primary' from CV??
metadata.addCredit(
person['name'], role.title().strip(), False)
character_credits = issue_results['character_credits']
character_list = list()
for character in character_credits:
character_list.append(character['name'])
metadata.characters = utils.listToString(character_list)
team_credits = issue_results['team_credits']
team_list = list()
for team in team_credits:
team_list.append(team['name'])
metadata.teams = utils.listToString(team_list)
location_credits = issue_results['location_credits']
location_list = list()
for location in location_credits:
location_list.append(location['name'])
metadata.locations = utils.listToString(location_list)
story_arc_credits = issue_results['story_arc_credits']
arc_list = []
for arc in story_arc_credits:
arc_list.append(arc['name'])
if len(arc_list) > 0:
metadata.storyArc = utils.listToString(arc_list)
return metadata
def metadataFromString( self, string ):
cbi_container = json.loads( unicode(string, 'utf-8') )
metadata = GenericMetadata()
cbi = cbi_container[ 'ComicBookInfo/1.0' ]
#helper func
# If item is not in CBI, return None
def xlate( cbi_entry):
if cbi_entry in cbi:
return cbi[cbi_entry]
else:
return None
metadata.series = xlate( 'series' )
metadata.title = xlate( 'title' )
metadata.issue = xlate( 'issue' )
metadata.publisher = xlate( 'publisher' )
metadata.month = xlate( 'publicationMonth' )
metadata.year = xlate( 'publicationYear' )
metadata.issueCount = xlate( 'numberOfIssues' )
metadata.comments = xlate( 'comments' )
metadata.credits = xlate( 'credits' )
metadata.genre = xlate( 'genre' )
metadata.volume = xlate( 'volume' )
metadata.volumeCount = xlate( 'numberOfVolumes' )
metadata.language = xlate( 'language' )
metadata.country = xlate( 'country' )
metadata.criticalRating = xlate( 'rating' )
metadata.tags = xlate( 'tags' )
# make sure credits and tags are at least empty lists and not None
if metadata.credits is None:
metadata.credits = []
if metadata.tags is None:
metadata.tags = []
#need to massage the language string to be ISO
if metadata.language is not None:
# reverse look-up
pattern = metadata.language
metadata.language = None
for key in utils.getLanguageDict():
if utils.getLanguageDict()[ key ] == pattern.encode('utf-8'):
metadata.language = key
break
metadata.isEmpty = False
return metadata
def convertXMLToMetadata( self, tree, check = True ):
root = tree.getroot()
if check and root.tag != 'ComicInfo':
raise 1
return None
metadata = GenericMetadata()
md = metadata
# Helper function
def xlate( tag ):
node = root.find( tag )
if node is not None:
return node.text
else:
return None
md.series = xlate( 'Series' )
md.title = xlate( 'Title' )
md.issue = xlate( 'Number' )
md.issueCount = xlate( 'Count' )
md.volume = xlate( 'Volume' )
md.alternateSeries = xlate( 'AlternateSeries' )
md.alternateNumber = xlate( 'AlternateNumber' )
md.alternateCount = xlate( 'AlternateCount' )
md.comments = xlate( 'Summary' )
md.notes = xlate( 'Notes' )
md.year = xlate( 'Year' )
md.month = xlate( 'Month' )
md.day = xlate( 'Day' )
md.publisher = xlate( 'Publisher' )
md.imprint = xlate( 'Imprint' )
md.genre = xlate( 'Genre' )
md.webLink = xlate( 'Web' )
md.language = xlate( 'LanguageISO' )
md.format = xlate( 'Format' )
md.manga = xlate( 'Manga' )
md.characters = xlate( 'Characters' )
md.teams = xlate( 'Teams' )
md.locations = xlate( 'Locations' )
md.pageCount = xlate( 'PageCount' )
md.scanInfo = xlate( 'ScanInformation' )
md.storyArc = xlate( 'StoryArc' )
md.seriesGroup = xlate( 'SeriesGroup' )
md.maturityRating = xlate( 'AgeRating' )
tmp = xlate( 'BlackAndWhite' )
md.blackAndWhite = False
if tmp is not None and tmp.lower() in [ "yes", "true", "1" ]:
md.blackAndWhite = True
# Now extract the credit info
for n in root:
if ( n.tag == 'Writer' or
n.tag == 'Penciller' or
n.tag == 'Inker' or
n.tag == 'Colorist' or
n.tag == 'Letterer' or
n.tag == 'Editor'
):
if n.text is not None:
for name in n.text.split(','):
metadata.addCredit( name.strip(), n.tag )
if n.tag == 'CoverArtist':
if n.text is not None:
for name in n.text.split(','):
metadata.addCredit( name.strip(), "Cover" )
# parse page data now
pages_node = root.find( "Pages" )
if pages_node is not None:
for page in pages_node:
metadata.pages.append( page.attrib )
#print page.attrib
metadata.isEmpty = False
return metadata
def convertXMLToMetadata(self, tree, check=True):
root = tree.getroot()
if check and root.tag != 'ComicInfo':
raise 1
return None
metadata = GenericMetadata()
md = metadata
# Helper function
def xlate(tag):
node = root.find(tag)
if node is not None:
return node.text
else:
return None
md.series = xlate('Series')
md.title = xlate('Title')
md.issue = xlate('Number')
md.issueCount = xlate('Count')
md.volume = xlate('Volume')
md.alternateSeries = xlate('AlternateSeries')
md.alternateNumber = xlate('AlternateNumber')
md.alternateCount = xlate('AlternateCount')
md.comments = xlate('Summary')
md.notes = xlate('Notes')
md.year = xlate('Year')
md.month = xlate('Month')
md.day = xlate('Day')
md.publisher = xlate('Publisher')
md.imprint = xlate('Imprint')
md.genre = xlate('Genre')
md.webLink = xlate('Web')
md.language = xlate('LanguageISO')
md.format = xlate('Format')
md.manga = xlate('Manga')
md.characters = xlate('Characters')
md.teams = xlate('Teams')
md.locations = xlate('Locations')
md.pageCount = xlate('PageCount')
md.scanInfo = xlate('ScanInformation')
md.storyArc = xlate('StoryArc')
md.seriesGroup = xlate('SeriesGroup')
md.maturityRating = xlate('AgeRating')
tmp = xlate('BlackAndWhite')
md.blackAndWhite = False
if tmp is not None and tmp.lower() in ["yes", "true", "1"]:
md.blackAndWhite = True
# Now extract the credit info
for n in root:
if (n.tag == 'Writer' or n.tag == 'Penciller' or n.tag == 'Inker'
or n.tag == 'Colorist' or n.tag == 'Letterer'
or n.tag == 'Editor'):
if n.text is not None:
for name in n.text.split(','):
metadata.addCredit(name.strip(), n.tag)
if n.tag == 'CoverArtist':
if n.text is not None:
for name in n.text.split(','):
metadata.addCredit(name.strip(), "Cover")
# parse page data now
pages_node = root.find("Pages")
if pages_node is not None:
for page in pages_node:
metadata.pages.append(page.attrib)
#print page.attrib
metadata.isEmpty = False
return metadata
def convertXMLToMetadata( self, tree ):
root = tree.getroot()
if root.tag != 'comet':
raise 1
return None
metadata = GenericMetadata()
md = metadata
# Helper function
def xlate( tag ):
node = root.find( tag )
if node is not None:
return node.text
else:
return None
md.series = xlate( 'series' )
md.title = xlate( 'title' )
md.issue = xlate( 'issue' )
md.volume = xlate( 'volume' )
md.comments = xlate( 'description' )
md.publisher = xlate( 'publisher' )
md.language = xlate( 'language' )
md.format = xlate( 'format' )
md.pageCount = xlate( 'pages' )
md.maturityRating = xlate( 'rating' )
md.price = xlate( 'price' )
md.isVersionOf = xlate( 'isVersionOf' )
md.rights = xlate( 'rights' )
md.identifier = xlate( 'identifier' )
md.lastMark = xlate( 'lastMark' )
md.genre = xlate( 'genre' ) # TODO - repeatable field
date = xlate( 'date' )
if date is not None:
parts = date.split('-')
if len( parts) > 0:
md.year = parts[0]
if len( parts) > 1:
md.month = parts[1]
md.coverImage = xlate( 'coverImage' )
readingDirection = xlate( 'readingDirection' )
if readingDirection is not None and readingDirection == "rtl":
md.manga = "YesAndRightToLeft"
# loop for character tags
char_list = []
for n in root:
if n.tag == 'character':
char_list.append(n.text.strip())
md.characters = utils.listToString( char_list )
# Now extract the credit info
for n in root:
if ( n.tag == 'writer' or
n.tag == 'penciller' or
n.tag == 'inker' or
n.tag == 'colorist' or
n.tag == 'letterer' or
n.tag == 'editor'
):
metadata.addCredit( n.text.strip(), n.tag.title() )
if n.tag == 'coverDesigner':
metadata.addCredit( n.text.strip(), "Cover" )
metadata.isEmpty = False
return metadata
def metadataFromString(self, string):
cbi_container = json.loads(unicode(string, 'utf-8'))
metadata = GenericMetadata()
cbi = cbi_container['ComicBookInfo/1.0']
#helper func
# If item is not in CBI, return None
def xlate(cbi_entry):
if cbi_entry in cbi:
return cbi[cbi_entry]
else:
return None
metadata.series = xlate('series')
metadata.title = xlate('title')
metadata.issue = xlate('issue')
metadata.publisher = xlate('publisher')
metadata.month = xlate('publicationMonth')
metadata.year = xlate('publicationYear')
metadata.issueCount = xlate('numberOfIssues')
metadata.comments = xlate('comments')
metadata.credits = xlate('credits')
metadata.genre = xlate('genre')
metadata.volume = xlate('volume')
metadata.volumeCount = xlate('numberOfVolumes')
metadata.language = xlate('language')
metadata.country = xlate('country')
metadata.criticalRating = xlate('rating')
metadata.tags = xlate('tags')
# make sure credits and tags are at least empty lists and not None
if metadata.credits is None:
metadata.credits = []
if metadata.tags is None:
metadata.tags = []
#need to massage the language string to be ISO
if metadata.language is not None:
# reverse look-up
pattern = metadata.language
metadata.language = None
for key in utils.getLanguageDict():
if utils.getLanguageDict()[key] == pattern.encode('utf-8'):
metadata.language = key
break
metadata.isEmpty = False
return metadata
