def set_metadata_opf2(root, cover_prefix, mi, opf_version,
cover_data=None, apply_null=False, update_timestamp=False, force_identifiers=False, add_missing_cover=True):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
opf = OPF(None, preparsed_opf=root, read_toc=False)
if mi.languages:
mi.languages = normalize_languages(list(opf.raw_languages) or [], mi.languages)
opf.smart_update(mi, apply_null=apply_null)
if getattr(mi, 'uuid', None):
opf.application_id = mi.uuid
if apply_null or force_identifiers:
opf.set_identifiers(mi.get_identifiers())
else:
orig = opf.get_identifiers()
orig.update(mi.get_identifiers())
opf.set_identifiers({k:v for k, v in orig.iteritems() if k and v})
if update_timestamp and mi.timestamp is not None:
opf.timestamp = mi.timestamp
raster_cover = opf.raster_cover
if raster_cover is None and cover_data is not None and add_missing_cover:
guide_raster_cover = opf.guide_raster_cover
i = None
if guide_raster_cover is not None:
i = guide_raster_cover
raster_cover = i.get('href')
else:
if cover_prefix and not cover_prefix.endswith('/'):
cover_prefix += '/'
name = cover_prefix + 'cover.jpg'
i = create_manifest_item(opf.root, name, 'cover')
if i is not None:
raster_cover = name
if i is not None:
if opf_version.major < 3:
[x.getparent().remove(x) for x in opf.root.xpath('//*[local-name()="meta" and @name="cover"]')]
m = opf.create_metadata_element('meta', is_dc=False)
m.set('name', 'cover'), m.set('content', i.get('id'))
else:
for x in opf.root.xpath('//*[local-name()="item" and contains(@properties, "cover-image")]'):
x.set('properties', x.get('properties').replace('cover-image', '').strip())
i.set('properties', 'cover-image')
with pretty_print:
return opf.render(), raster_cover
def set_metadata_opf2(root, cover_prefix, mi, opf_version,
cover_data=None, apply_null=False, update_timestamp=False, force_identifiers=False, add_missing_cover=True):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
opf = OPF(None, preparsed_opf=root, read_toc=False)
if mi.languages:
mi.languages = normalize_languages(list(opf.raw_languages) or [], mi.languages)
opf.smart_update(mi, apply_null=apply_null)
if getattr(mi, 'uuid', None):
opf.application_id = mi.uuid
if apply_null or force_identifiers:
opf.set_identifiers(mi.get_identifiers())
else:
orig = opf.get_identifiers()
orig.update(mi.get_identifiers())
opf.set_identifiers({k:v for k, v in orig.items() if k and v})
if update_timestamp and mi.timestamp is not None:
opf.timestamp = mi.timestamp
raster_cover = opf.raster_cover
if raster_cover is None and cover_data is not None and add_missing_cover:
guide_raster_cover = opf.guide_raster_cover
i = None
if guide_raster_cover is not None:
i = guide_raster_cover
raster_cover = i.get('href')
else:
if cover_prefix and not cover_prefix.endswith('/'):
cover_prefix += '/'
name = cover_prefix + 'cover.jpg'
i = create_manifest_item(opf.root, name, 'cover')
if i is not None:
raster_cover = name
if i is not None:
if opf_version.major < 3:
[x.getparent().remove(x) for x in opf.root.xpath('//*[local-name()="meta" and @name="cover"]')]
m = opf.create_metadata_element('meta', is_dc=False)
m.set('name', 'cover'), m.set('content', i.get('id'))
else:
for x in opf.root.xpath('//*[local-name()="item" and contains(@properties, "cover-image")]'):
x.set('properties', x.get('properties').replace('cover-image', '').strip())
i.set('properties', 'cover-image')
with pretty_print:
return opf.render(), raster_cover
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, cover=True):
with TemporaryDirectory('_pdf_metadata_read') as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, 'src.pdf'), 'wb') as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job('calibre.ebooks.metadata.pdf', 'read_info',
(pdfpath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError('Failed to run pdfinfo')
info = res['result']
with open(res['stdout_stderr'], 'rb') as f:
raw = f.read().strip()
if raw:
prints(raw)
if info is None:
raise ValueError('Could not read info dict from PDF')
covpath = os.path.join(pdfpath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None) or _('Unknown')
au = info.get('Author', None)
if au is None:
au = [_('Unknown')]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
# if isbn is not None:
# mi.isbn = isbn
creator = info.get('Creator', None)
if creator:
mi.book_producer = creator
keywords = info.get('Keywords', None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(',')]
isbn = [check_isbn(x) for x in mi.tags if check_isbn(x)]
if isbn:
mi.isbn = isbn = isbn[0]
mi.tags = [x for x in mi.tags if check_isbn(x) != isbn]
subject = info.get('Subject', None)
if subject:
mi.tags.insert(0, subject)
if 'xmp_metadata' in info:
from calibre.ebooks.metadata.xmp import consolidate_metadata
mi = consolidate_metadata(mi, info)
# Look for recognizable identifiers in the info dict, if they were not
# found in the XMP metadata
for scheme, check_func in iteritems({
'doi': check_doi,
'isbn': check_isbn
}):
if scheme not in mi.get_identifiers():
for k, v in iteritems(info):
if k != 'xmp_metadata':
val = check_func(v)
if val:
mi.set_identifier(scheme, val)
break
if cdata:
mi.cover_data = ('jpeg', cdata)
return mi
def get_metadata(stream, cover=True):
with TemporaryDirectory('_pdf_metadata_read') as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, 'src.pdf'), 'wb') as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job('calibre.ebooks.metadata.pdf', 'read_info',
(pdfpath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError('Failed to run pdfinfo')
info = res['result']
with open(res['stdout_stderr'], 'rb') as f:
raw = f.read().strip()
if raw:
prints(raw)
if not info:
raise ValueError('Could not read info dict from PDF')
covpath = os.path.join(pdfpath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None)
au = info.get('Author', None)
if au is None:
au = [_('Unknown')]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
# if isbn is not None:
# mi.isbn = isbn
creator = info.get('Creator', None)
if creator:
mi.book_producer = creator
keywords = info.get('Keywords', None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(',')]
isbn = [check_isbn(x) for x in mi.tags if check_isbn(x)]
if isbn:
mi.isbn = isbn = isbn[0]
mi.tags = [x for x in mi.tags if check_isbn(x) != isbn]
subject = info.get('Subject', None)
if subject:
mi.tags.insert(0, subject)
if 'xmp_metadata' in info:
from calibre.ebooks.metadata.xmp import consolidate_metadata
mi = consolidate_metadata(mi, info)
# Look for recognizable identifiers in the info dict, if they were not
# found in the XMP metadata
for scheme, check_func in {'doi':check_doi, 'isbn':check_isbn}.iteritems():
if scheme not in mi.get_identifiers():
for k, v in info.iteritems():
if k != 'xmp_metadata':
val = check_func(v)
if val:
mi.set_identifier(scheme, val)
break
if cdata:
mi.cover_data = ('jpeg', cdata)
return mi
