def do_set_metadata(opts, mi, stream, stream_type):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
from_opf = getattr(opts, 'from_opf', None)
if from_opf is not None:
from calibre.ebooks.metadata.opf2 import OPF
opf_mi = OPF(open(from_opf, 'rb')).to_book_metadata()
mi.smart_update(opf_mi)
for pref in config().option_set.preferences:
if pref.name in ('to_opf', 'from_opf', 'authors', 'title_sort',
'author_sort', 'get_cover', 'cover', 'tags',
'lrf_bookid', 'identifiers'):
continue
val = getattr(opts, pref.name, None)
if val is not None:
setattr(mi, pref.name, val)
if getattr(opts, 'authors', None) is not None:
mi.authors = string_to_authors(opts.authors)
mi.author_sort = authors_to_sort_string(mi.authors)
if getattr(opts, 'author_sort', None) is not None:
mi.author_sort = opts.author_sort
if getattr(opts, 'title_sort', None) is not None:
mi.title_sort = opts.title_sort
elif getattr(opts, 'title', None) is not None:
mi.title_sort = title_sort(opts.title)
if getattr(opts, 'tags', None) is not None:
mi.tags = [t.strip() for t in opts.tags.split(',')]
if getattr(opts, 'series', None) is not None:
mi.series = opts.series.strip()
if getattr(opts, 'series_index', None) is not None:
mi.series_index = float(opts.series_index.strip())
if getattr(opts, 'pubdate', None) is not None:
mi.pubdate = parse_date(opts.pubdate, assume_utc=False, as_utc=False)
if getattr(opts, 'identifiers', None):
val = {
k.strip(): v.strip()
for k, v in (x.partition(':')[0::2] for x in opts.identifiers)
}
if val:
orig = mi.get_identifiers()
orig.update(val)
val = {k: v for k, v in orig.iteritems() if k and v}
mi.set_identifiers(val)
if getattr(opts, 'cover', None) is not None:
ext = os.path.splitext(opts.cover)[1].replace('.', '').upper()
mi.cover_data = (ext, open(opts.cover, 'rb').read())
with force_identifiers:
set_metadata(stream, mi, stream_type)
def do_set_metadata(opts, mi, stream, stream_type):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
from_opf = getattr(opts, 'from_opf', None)
if from_opf is not None:
from calibre.ebooks.metadata.opf2 import OPF
opf_mi = OPF(open(from_opf, 'rb')).to_book_metadata()
mi.smart_update(opf_mi)
for pref in config().option_set.preferences:
if pref.name in ('to_opf', 'from_opf', 'authors', 'title_sort',
'author_sort', 'get_cover', 'cover', 'tags',
'lrf_bookid', 'identifiers'):
continue
val = getattr(opts, pref.name, None)
if val is not None:
setattr(mi, pref.name, val)
if getattr(opts, 'authors', None) is not None:
mi.authors = string_to_authors(opts.authors)
mi.author_sort = authors_to_sort_string(mi.authors)
if getattr(opts, 'author_sort', None) is not None:
mi.author_sort = opts.author_sort
if getattr(opts, 'title_sort', None) is not None:
mi.title_sort = opts.title_sort
elif getattr(opts, 'title', None) is not None:
mi.title_sort = title_sort(opts.title)
if getattr(opts, 'tags', None) is not None:
mi.tags = [t.strip() for t in opts.tags.split(',')]
if getattr(opts, 'series', None) is not None:
mi.series = opts.series.strip()
if getattr(opts, 'series_index', None) is not None:
mi.series_index = float(opts.series_index.strip())
if getattr(opts, 'pubdate', None) is not None:
mi.pubdate = parse_date(opts.pubdate, assume_utc=False, as_utc=False)
if getattr(opts, 'identifiers', None):
val = {k.strip():v.strip() for k, v in (x.partition(':')[0::2] for x in opts.identifiers)}
if val:
orig = mi.get_identifiers()
orig.update(val)
val = {k:v for k, v in iteritems(orig) if k and v}
mi.set_identifiers(val)
if getattr(opts, 'cover', None) is not None:
ext = os.path.splitext(opts.cover)[1].replace('.', '').upper()
mi.cover_data = (ext, open(opts.cover, 'rb').read())
with force_identifiers:
set_metadata(stream, mi, stream_type)
def get_metadata(stream, extract_cover=True):
zin = zipfile.ZipFile(stream, 'r')
odfs = odfmetaparser()
parser = xml.sax.make_parser()
parser.setFeature(xml.sax.handler.feature_namespaces, 1)
parser.setContentHandler(odfs)
content = zin.read('meta.xml')
parser.parse(StringIO(content))
data = odfs.seenfields
mi = MetaInformation(None, [])
if 'title' in data:
mi.title = data['title']
if data.get('initial-creator', '').strip():
mi.authors = string_to_authors(data['initial-creator'])
elif 'creator' in data:
mi.authors = string_to_authors(data['creator'])
if 'description' in data:
mi.comments = data['description']
if 'language' in data:
mi.language = data['language']
if data.get('keywords', ''):
mi.tags = [x.strip() for x in data['keywords'].split(',') if x.strip()]
opfmeta = False # we need this later for the cover
opfnocover = False
if data.get('opf.metadata','') == 'true':
# custom metadata contains OPF information
opfmeta = True
if data.get('opf.titlesort', ''):
mi.title_sort = data['opf.titlesort']
if data.get('opf.authors', ''):
mi.authors = string_to_authors(data['opf.authors'])
if data.get('opf.authorsort', ''):
mi.author_sort = data['opf.authorsort']
if data.get('opf.isbn', ''):
isbn = check_isbn(data['opf.isbn'])
if isbn is not None:
mi.isbn = isbn
if data.get('opf.publisher', ''):
mi.publisher = data['opf.publisher']
if data.get('opf.pubdate', ''):
mi.pubdate = parse_date(data['opf.pubdate'], assume_utc=True)
if data.get('opf.series', ''):
mi.series = data['opf.series']
if data.get('opf.seriesindex', ''):
try:
mi.series_index = float(data['opf.seriesindex'])
except ValueError:
mi.series_index = 1.0
if data.get('opf.language', ''):
cl = canonicalize_lang(data['opf.language'])
if cl:
mi.languages = [cl]
opfnocover = data.get('opf.nocover', 'false') == 'true'
if not opfnocover:
try:
read_cover(stream, zin, mi, opfmeta, extract_cover)
except:
pass # Do not let an error reading the cover prevent reading other data
return mi
def get_metadata(stream, extract_cover=True):
zin = zipfile.ZipFile(stream, 'r')
odfs = odfmetaparser()
parser = xml.sax.make_parser()
parser.setFeature(xml.sax.handler.feature_namespaces, 1)
parser.setContentHandler(odfs)
content = zin.read('meta.xml')
parser.parse(StringIO(content))
data = odfs.seenfields
mi = MetaInformation(None, [])
if data.has_key('title'):
mi.title = data['title']
if data.get('initial-creator', '').strip():
mi.authors = string_to_authors(data['initial-creator'])
elif data.has_key('creator'):
mi.authors = string_to_authors(data['creator'])
if data.has_key('description'):
mi.comments = data['description']
if data.has_key('language'):
mi.language = data['language']
if data.get('keywords', ''):
mi.tags = [x.strip() for x in data['keywords'].split(',') if x.strip()]
opfmeta = False # we need this later for the cover
opfnocover = False
if data.get('opf.metadata','') == 'true':
# custom metadata contains OPF information
opfmeta = True
if data.get('opf.titlesort', ''):
mi.title_sort = data['opf.titlesort']
if data.get('opf.authors', ''):
mi.authors = string_to_authors(data['opf.authors'])
if data.get('opf.authorsort', ''):
mi.author_sort = data['opf.authorsort']
if data.get('opf.isbn', ''):
isbn = check_isbn(data['opf.isbn'])
if isbn is not None:
mi.isbn = isbn
if data.get('opf.publisher', ''):
mi.publisher = data['opf.publisher']
if data.get('opf.pubdate', ''):
mi.pubdate = parse_date(data['opf.pubdate'], assume_utc=True)
if data.get('opf.series', ''):
mi.series = data['opf.series']
if data.get('opf.seriesindex', ''):
try:
mi.series_index = float(data['opf.seriesindex'])
except ValueError:
mi.series_index = 1.0
if data.get('opf.language', ''):
cl = canonicalize_lang(data['opf.language'])
if cl:
mi.languages = [cl]
opfnocover = data.get('opf.nocover', 'false') == 'true'
if not opfnocover:
try:
read_cover(stream, zin, mi, opfmeta, extract_cover)
except:
pass # Do not let an error reading the cover prevent reading other data
return mi
def get_metadata(stream):
"""
Return basic meta-data about the LRF file in C{stream} as a
L{MetaInformation} object.
@param stream: A file like object or an instance of L{LRFMetaFile}
"""
lrf = stream if isinstance(stream, LRFMetaFile) else LRFMetaFile(stream)
authors = string_to_authors(lrf.author)
mi = MetaInformation(lrf.title.strip(), authors)
mi.author = lrf.author.strip()
mi.comments = lrf.free_text.strip()
mi.category = lrf.category.strip() + ', ' + lrf.classification.strip()
tags = [x.strip() for x in mi.category.split(',') if x.strip()]
if tags:
mi.tags = tags
if mi.category.strip() == ',':
mi.category = None
mi.publisher = lrf.publisher.strip()
mi.cover_data = lrf.get_cover()
try:
mi.title_sort = lrf.title_reading.strip()
if not mi.title_sort:
mi.title_sort = None
except:
pass
try:
mi.author_sort = lrf.author_reading.strip()
if not mi.author_sort:
mi.author_sort = None
except:
pass
if not mi.title or 'unknown' in mi.title.lower():
mi.title = None
if not mi.authors:
mi.authors = None
if not mi.author or 'unknown' in mi.author.lower():
mi.author = None
if not mi.category or 'unknown' in mi.category.lower():
mi.category = None
if not mi.publisher or 'unknown' in mi.publisher.lower() or \
'some publisher' in mi.publisher.lower():
mi.publisher = None
return mi
def get_metadata(stream):
"""
Return basic meta-data about the LRF file in C{stream} as a
L{MetaInformation} object.
@param stream: A file like object or an instance of L{LRFMetaFile}
"""
lrf = stream if isinstance(stream, LRFMetaFile) else LRFMetaFile(stream)
authors = string_to_authors(lrf.author)
mi = MetaInformation(lrf.title.strip(), authors)
mi.author = lrf.author.strip()
mi.comments = lrf.free_text.strip()
mi.category = lrf.category.strip()+', '+lrf.classification.strip()
tags = [x.strip() for x in mi.category.split(',') if x.strip()]
if tags:
mi.tags = tags
if mi.category.strip() == ',':
mi.category = None
mi.publisher = lrf.publisher.strip()
mi.cover_data = lrf.get_cover()
try:
mi.title_sort = lrf.title_reading.strip()
if not mi.title_sort:
mi.title_sort = None
except:
pass
try:
mi.author_sort = lrf.author_reading.strip()
if not mi.author_sort:
mi.author_sort = None
except:
pass
if not mi.title or 'unknown' in mi.title.lower():
mi.title = None
if not mi.authors:
mi.authors = None
if not mi.author or 'unknown' in mi.author.lower():
mi.author = None
if not mi.category or 'unknown' in mi.category.lower():
mi.category = None
if not mi.publisher or 'unknown' in mi.publisher.lower() or \
'some publisher' in mi.publisher.lower():
mi.publisher = None
return mi
def get_metadata(f):
read = lambda at, amount: _read(f, at, amount)
f.seek(0)
buf = f.read(12)
if buf[4:] == 'ftypLRX2':
offset = 0
while True:
offset += word_be(buf[:4])
try:
buf = read(offset, 8)
except:
raise ValueError('Not a valid LRX file')
if buf[4:] == 'bbeb':
break
offset += 8
buf = read(offset, 16)
if buf[:8].decode('utf-16-le') != 'LRF\x00':
raise ValueError('Not a valid LRX file')
lrf_version = word_le(buf[8:12])
offset += 0x4c
compressed_size = short_le(read(offset, 2))
offset += 2
if lrf_version >= 800:
offset += 6
compressed_size -= 4
uncompressed_size = word_le(read(offset, 4))
info = decompress(f.read(compressed_size))
if len(info) != uncompressed_size:
raise ValueError('LRX file has malformed metadata section')
root = etree.fromstring(info)
bi = root.find('BookInfo')
title = bi.find('Title')
title_sort = title.get('reading', None)
title = title.text
author = bi.find('Author')
author_sort = author.get('reading', None)
mi = MetaInformation(title, string_to_authors(author.text))
mi.title_sort, mi.author_sort = title_sort, author_sort
author = author.text
publisher = bi.find('Publisher')
mi.publisher = getattr(publisher, 'text', None)
mi.tags = [x.text for x in bi.findall('Category')]
mi.language = root.find('DocInfo').find('Language').text
return mi
elif buf[4:8] == 'LRX':
raise ValueError('Librie LRX format not supported')
else:
raise ValueError('Not a LRX file')
def get_metadata(f):
read = lambda at, amount: _read(f, at, amount)
f.seek(0)
buf = f.read(12)
if buf[4:] == b'ftypLRX2':
offset = 0
while True:
offset += word_be(buf[:4])
try:
buf = read(offset, 8)
except:
raise ValueError('Not a valid LRX file')
if buf[4:] == b'bbeb':
break
offset += 8
buf = read(offset, 16)
if buf[:8].decode('utf-16-le') != 'LRF\x00':
raise ValueError('Not a valid LRX file')
lrf_version = word_le(buf[8:12])
offset += 0x4c
compressed_size = short_le(read(offset, 2))
offset += 2
if lrf_version >= 800:
offset += 6
compressed_size -= 4
uncompressed_size = word_le(read(offset, 4))
info = decompress(f.read(compressed_size))
if len(info) != uncompressed_size:
raise ValueError('LRX file has malformed metadata section')
root = safe_xml_fromstring(info)
bi = root.find('BookInfo')
title = bi.find('Title')
title_sort = title.get('reading', None)
title = title.text
author = bi.find('Author')
author_sort = author.get('reading', None)
mi = MetaInformation(title, string_to_authors(author.text))
mi.title_sort, mi.author_sort = title_sort, author_sort
author = author.text
publisher = bi.find('Publisher')
mi.publisher = getattr(publisher, 'text', None)
mi.tags = [x.text for x in bi.findall('Category')]
mi.language = root.find('DocInfo').find('Language').text
return mi
elif buf[4:8] == b'LRX':
raise ValueError('Librie LRX format not supported')
else:
raise ValueError('Not a LRX file')
def get_metadata(stream, extract_cover=True):
whitespace = re.compile(r'\s+')
def normalize(s):
return whitespace.sub(' ', s).strip()
with ZipFile(stream) as zf:
meta = zf.read('meta.xml')
root = fromstring(meta)
def find(field):
ns, tag = fields[field]
ans = root.xpath('//ns0:{}'.format(tag), namespaces={'ns0': ns})
if ans:
return normalize(
tostring(ans[0],
method='text',
encoding='unicode',
with_tail=False)).strip()
mi = MetaInformation(None, [])
title = find('title')
if title:
mi.title = title
creator = find('initial-creator') or find('creator')
if creator:
mi.authors = string_to_authors(creator)
desc = find('description')
if desc:
mi.comments = desc
lang = find('language')
if lang and canonicalize_lang(lang):
mi.languages = [canonicalize_lang(lang)]
kw = find('keyword') or find('keywords')
if kw:
mi.tags = [x.strip() for x in kw.split(',') if x.strip()]
data = {}
for tag in root.xpath('//ns0:user-defined',
namespaces={'ns0': fields['user-defined'][0]}):
name = (tag.get('{%s}name' % METANS) or '').lower()
vtype = tag.get('{%s}value-type' % METANS) or 'string'
val = tag.text
if name and val:
if vtype == 'boolean':
val = val == 'true'
data[name] = val
opfmeta = False # we need this later for the cover
opfnocover = False
if data.get('opf.metadata'):
# custom metadata contains OPF information
opfmeta = True
if data.get('opf.titlesort', ''):
mi.title_sort = data['opf.titlesort']
if data.get('opf.authors', ''):
mi.authors = string_to_authors(data['opf.authors'])
if data.get('opf.authorsort', ''):
mi.author_sort = data['opf.authorsort']
if data.get('opf.isbn', ''):
isbn = check_isbn(data['opf.isbn'])
if isbn is not None:
mi.isbn = isbn
if data.get('opf.publisher', ''):
mi.publisher = data['opf.publisher']
if data.get('opf.pubdate', ''):
mi.pubdate = parse_date(data['opf.pubdate'], assume_utc=True)
if data.get('opf.identifiers'):
try:
mi.identifiers = json.loads(data['opf.identifiers'])
except Exception:
pass
if data.get('opf.rating'):
try:
mi.rating = max(0, min(float(data['opf.rating']), 10))
except Exception:
pass
if data.get('opf.series', ''):
mi.series = data['opf.series']
if data.get('opf.seriesindex', ''):
try:
mi.series_index = float(data['opf.seriesindex'])
except Exception:
mi.series_index = 1.0
if data.get('opf.language', ''):
cl = canonicalize_lang(data['opf.language'])
if cl:
mi.languages = [cl]
opfnocover = data.get('opf.nocover', False)
if not opfnocover:
try:
read_cover(stream, zf, mi, opfmeta, extract_cover)
except Exception:
pass # Do not let an error reading the cover prevent reading other data
return mi
