Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge changes from zeno.

Browse Source
This commit is contained in:
Marshall T. Vandegrift 2008-12-30 19:41:01 -05:00
commit 12935cec01
3 changed files with 204 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/calibre/ebooks/lit/oeb.py
View File

@ -128,6 +128,7 @@ class Metadata(object):
TERMS = set(['contributor', 'coverage', 'creator', 'date', 'description', TERMS = set(['contributor', 'coverage', 'creator', 'date', 'description',
'format', 'identifier', 'language', 'publisher', 'relation', 'format', 'identifier', 'language', 'publisher', 'relation',
'rights', 'source', 'subject', 'title', 'type']) 'rights', 'source', 'subject', 'title', 'type'])
ATTRS = set(['role', 'file-as', 'scheme'])
OPF1_NSMAP = {'dc': DC11_NS, 'oebpackage': OPF1_NS} OPF1_NSMAP = {'dc': DC11_NS, 'oebpackage': OPF1_NS}
OPF2_NSMAP = {'opf': OPF2_NS, 'dc': DC11_NS, 'dcterms': DCTERMS_NS, OPF2_NSMAP = {'opf': OPF2_NS, 'dc': DC11_NS, 'dcterms': DCTERMS_NS,
'xsi': XSI_NS} 'xsi': XSI_NS}
@ -144,7 +145,12 @@ class Metadata(object):
self.value = value self.value = value
self.attrib = attrib = {} self.attrib = attrib = {}
for fq_attr in fq_attrib: for fq_attr in fq_attrib:
attr = barename(fq_attr) if fq_attr in Metadata.ATTRS:
attr = fq_attr
fq_attr = OPF2(fq_attr)
fq_attrib[fq_attr] = fq_attrib.pop(attr)
else:
attr = barename(fq_attr)
attrib[attr] = fq_attrib[fq_attr] attrib[attr] = fq_attrib[fq_attr]
def __getattr__(self, name): def __getattr__(self, name):
@ -161,7 +167,7 @@ class Metadata(object):
% (barename(self.term), self.value, self.attrib) % (barename(self.term), self.value, self.attrib)
def __str__(self): def __str__(self):
return self.value.encode('ascii', 'xmlcharrefreplace') return unicode(self.value).encode('ascii', 'xmlcharrefreplace')
def __unicode__(self): def __unicode__(self):
return unicode(self.value) return unicode(self.value)
@ -276,6 +282,14 @@ class Manifest(object):
if result != 0: if result != 0:
return result return result
return cmp(self.id, other.id) return cmp(self.id, other.id)
def abshref(self, href):
if '/' not in self.href:
return href
dirname = os.path.dirname(self.href)
href = os.path.join(dirname, href)
href = os.path.normpath(href).replace('\\', '/')
return href
def __init__(self, oeb): def __init__(self, oeb):
self.oeb = oeb self.oeb = oeb
@ -581,6 +595,15 @@ class OEBBook(object):
else: else:
self.logger.log_warn(u'Unique-identifier %r not found.' % uid) self.logger.log_warn(u'Unique-identifier %r not found.' % uid)
self.uid = metadata.identifier[0] self.uid = metadata.identifier[0]
if not metadata.language:
self.logger.log_warn(u'Language not specified.')
metadata.add('language', 'en')
if not metadata.creator:
self.logger.log_warn(u'Creator not specified.')
metadata.add('creator', 'Unknown')
if not metadata.title:
self.logger.log_warn(u'Title not specified.')
metadata.add('title', 'Unknown')
def _manifest_from_opf(self, opf): def _manifest_from_opf(self, opf):
self.manifest = manifest = Manifest(self) self.manifest = manifest = Manifest(self)

169
src/calibre/ebooks/mobi/langcodes.py
View File

@ -3,6 +3,8 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
from struct import pack
main_language = { main_language = {
0 : "NEUTRAL", 0 : "NEUTRAL",
54 : "AFRIKAANS", 54 : "AFRIKAANS",
@ -155,5 +157,168 @@ sub_language = {
2 : "SWEDISH_FINLAND", 2 : "SWEDISH_FINLAND",
1 : "UZBEK_LATIN", 1 : "UZBEK_LATIN",
2 : "UZBEK_CYRILLIC", 2 : "UZBEK_CYRILLIC",
}
}
IANA_MOBI = \
{None: {None: (0, 0)},
'af': {None: (54, 0)},
'ar': {None: (1, 0),
'AE': (1, 56),
'BH': (1, 60),
'DZ': (1, 20),
'EG': (1, 12),
'JO': (1, 44),
'KW': (1, 52),
'LB': (1, 48),
'MA': (1, 24),
'OM': (1, 32),
'QA': (1, 64),
'SA': (1, 4),
'SY': (1, 40),
'TN': (1, 28),
'YE': (1, 36)},
'as': {None: (77, 0)},
'az': {None: (44, 0)},
'be': {None: (35, 0)},
'bg': {None: (2, 0)},
'bn': {None: (69, 0)},
'ca': {None: (3, 0)},
'cs': {None: (5, 0)},
'da': {None: (6, 0)},
'de': {None: (7, 0),
'AT': (7, 12),
'CH': (7, 8),
'LI': (7, 20),
'LU': (7, 16)},
'el': {None: (8, 0)},
'en': {None: (9, 0),
'AU': (9, 12),
'BZ': (9, 40),
'CA': (9, 16),
'GB': (9, 8),
'IE': (9, 24),
'JM': (9, 32),
'NZ': (9, 20),
'PH': (9, 52),
'TT': (9, 44),
'US': (9, 4),
'ZA': (9, 28),
'ZW': (9, 48)},
'es': {None: (10, 0),
'AR': (10, 44),
'BO': (10, 64),
'CL': (10, 52),
'CO': (10, 36),
'CR': (10, 20),
'DO': (10, 28),
'EC': (10, 48),
'ES': (10, 4),
'GT': (10, 16),
'HN': (10, 72),
'MX': (10, 8),
'NI': (10, 76),
'PA': (10, 24),
'PE': (10, 40),
'PR': (10, 80),
'PY': (10, 60),
'SV': (10, 68),
'UY': (10, 56),
'VE': (10, 32)},
'et': {None: (37, 0)},
'eu': {None: (45, 0)},
'fa': {None: (41, 0)},
'fi': {None: (11, 0)},
'fo': {None: (56, 0)},
'fr': {None: (12, 0),
'BE': (12, 8),
'CA': (12, 12),
'CH': (12, 16),
'FR': (12, 4),
'LU': (12, 20),
'MC': (12, 24)},
'gu': {None: (71, 0)},
'he': {None: (13, 0)},
'hi': {None: (57, 0)},
'hr': {None: (26, 0)},
'hu': {None: (14, 0)},
'hy': {None: (43, 0)},
'id': {None: (33, 0)},
'is': {None: (15, 0)},
'it': {None: (16, 0),
'CH': (16, 8),
'IT': (16, 4)},
'ja': {None: (17, 0)},
'ka': {None: (55, 0)},
'kk': {None: (63, 0)},
'kn': {None: (75, 0)},
'ko': {None: (18, 0)},
'kok': {None: (87, 0)},
'lt': {None: (39, 0)},
'lv': {None: (38, 0)},
'mk': {None: (47, 0)},
'ml': {None: (76, 0)},
'mr': {None: (78, 0)},
'ms': {None: (62, 0)},
'mt': {None: (58, 0)},
'ne': {None: (97, 0)},
'nl': {None: (19, 0),
'BE': (19, 8)},
'no': {None: (20, 0)},
'or': {None: (72, 0)},
'pa': {None: (70, 0)},
'pl': {None: (21, 0)},
'pt': {None: (22, 0),
'BR': (22, 4),
'PT': (22, 8)},
'rm': {None: (23, 0)},
'ro': {None: (24, 0)},
'ru': {None: (25, 0)},
'sa': {None: (79, 0)},
'se': {None: (59, 0)},
'sk': {None: (27, 0)},
'sl': {None: (36, 0)},
'sq': {None: (28, 0)},
'sr': {None: (26, 12),
'RS': (26, 12)},
'st': {None: (48, 0)},
'sv': {None: (29, 0),
'FI': (29, 8)},
'sw': {None: (65, 0)},
'ta': {None: (73, 0)},
'te': {None: (74, 0)},
'th': {None: (30, 0)},
'tn': {None: (50, 0)},
'tr': {None: (31, 0)},
'ts': {None: (49, 0)},
'tt': {None: (68, 0)},
'uk': {None: (34, 0)},
'ur': {None: (32, 0)},
'uz': {None: (67, 0),
'UZ': (67, 8)},
'vi': {None: (42, 0)},
'wen': {None: (46, 0)},
'xh': {None: (52, 0)},
'zh': {None: (4, 0),
'CN': (4, 8),
'HK': (4, 12),
'SG': (4, 16),
'TW': (4, 4)},
'zu': {None: (53, 0)}}
def iana2mobi(self, icode):
subtags = list(code.split('-'))
langdict = IANA_MOBI[None]
while len(subtags) > 0:
lang = subtags.pop(0).lower()
if lang in IANA_MOBI:
langdict = IANA_MOBI[lang]
break
mcode = langdict[None]
while len(subtags) > 0:
subtag = subtags.pop(0)
if subtag not in langdict:
subtag = subtag.upper()
if subtag in langdict:
mcode = langdict[subtag]
break
return pack('>HBB', 0, mcode[1], mcode[0])

22
src/calibre/ebooks/mobi/writer.py
View File

@ -20,6 +20,7 @@ from urlparse import urldefrag
from lxml import etree from lxml import etree
from PIL import Image from PIL import Image
from calibre.ebooks.mobi.palmdoc import compress_doc from calibre.ebooks.mobi.palmdoc import compress_doc
from calibre.ebooks.mobi.langcodes import iana2mobi
from calibre.ebooks.lit.oeb import XML_NS, XHTML, XHTML_NS, OEB_DOCS from calibre.ebooks.lit.oeb import XML_NS, XHTML, XHTML_NS, OEB_DOCS
from calibre.ebooks.lit.oeb import xpath, barename, namespace, prefixname from calibre.ebooks.lit.oeb import xpath, barename, namespace, prefixname
from calibre.ebooks.lit.oeb import FauxLogger, OEBBook from calibre.ebooks.lit.oeb import FauxLogger, OEBBook
@ -87,19 +88,20 @@ class Serializer(object):
buffer.write('/>') buffer.write('/>')
buffer.write('</guide>') buffer.write('</guide>')
def serialize_href(self, href, baseid=None): def serialize_href(self, href, base=None):
hrefs = self.oeb.manifest.hrefs hrefs = self.oeb.manifest.hrefs
path, frag = urldefrag(href) path, frag = urldefrag(href)
# TODO: Absolute path translation if path and base:
path = base.abshref(path)
if path and path not in hrefs: if path and path not in hrefs:
return False return False
buffer = self.buffer buffer = self.buffer
item = hrefs[path] if path else None item = hrefs[path] if path else None
if item and item.spine_position is None: if item and item.spine_position is None:
return False return False
id = item.id if item else baseid id = item.id if item else base.id
frag = frag if frag else 'calibre_top' frag = frag if frag else 'calibre_top'
href = '_'.join((id, frag)) href = '#'.join((id, frag))
buffer.write('filepos=') buffer.write('filepos=')
self.href_offsets[href].append(buffer.tell()) self.href_offsets[href].append(buffer.tell())
buffer.write('0000000000') buffer.write('0000000000')
@ -117,7 +119,7 @@ class Serializer(object):
buffer.write('<mbp:pagebreak/>') buffer.write('<mbp:pagebreak/>')
# TODO: Figure out how to make the 'crossable' stuff work for # TODO: Figure out how to make the 'crossable' stuff work for
# non-"linear" spine items. # non-"linear" spine items.
self.id_offsets[item.id + '_calibre_top'] = buffer.tell() self.id_offsets[item.id + '#calibre_top'] = buffer.tell()
for elem in item.data.find(XHTML('body')): for elem in item.data.find(XHTML('body')):
self.serialize_elem(elem, item) self.serialize_elem(elem, item)
@ -129,7 +131,7 @@ class Serializer(object):
tag = prefixname(elem.tag, nsrmap) tag = prefixname(elem.tag, nsrmap)
for attr in ('name', 'id'): for attr in ('name', 'id'):
if attr in elem.attrib: if attr in elem.attrib:
id = '_'.join((item.id, elem.attrib[attr])) id = '#'.join((item.id, elem.attrib[attr]))
self.id_offsets[id] = buffer.tell() self.id_offsets[id] = buffer.tell()
del elem.attrib[attr] del elem.attrib[attr]
buffer.write('<') buffer.write('<')
@ -141,7 +143,7 @@ class Serializer(object):
attr = prefixname(attr, nsrmap) attr = prefixname(attr, nsrmap)
buffer.write(' ') buffer.write(' ')
if attr == 'href': if attr == 'href':
if self.serialize_href(val, item.id): if self.serialize_href(val, item):
continue continue
elif attr == 'src' and val in hrefs: elif attr == 'src' and val in hrefs:
index = self.images[val] index = self.images[val]
@ -256,19 +258,19 @@ class MobiWriter(object):
self._records.append(data) self._records.append(data)
def _generate_record0(self): def _generate_record0(self):
metadata = self._oeb.metadata
exth = self._build_exth() exth = self._build_exth()
record0 = StringIO() record0 = StringIO()
record0.write(pack('>HHIHHHH', self._compress, 0, self._text_length, record0.write(pack('>HHIHHHH', self._compress, 0, self._text_length,
self._text_nrecords, 0x1000, 0, 0)) self._text_nrecords, 0x1000, 0, 0))
uid = random.randint(0, 0xffffffff) uid = random.randint(0, 0xffffffff)
title = str(self._oeb.metadata.title[0]) title = str(metadata.title[0])
record0.write('MOBI') record0.write('MOBI')
record0.write(pack('>IIIII', 0xe8, 2, 65001, uid, 5)) record0.write(pack('>IIIII', 0xe8, 2, 65001, uid, 5))
record0.write('\xff' * 40) record0.write('\xff' * 40)
record0.write(pack('>I', self._text_nrecords + 1)) record0.write(pack('>I', self._text_nrecords + 1))
record0.write(pack('>II', 0xe8 + 16 + len(exth), len(title))) record0.write(pack('>II', 0xe8 + 16 + len(exth), len(title)))
# TODO: Translate <dc:language/> to language code record0.write(iana2mobi(str(metadata.language[0])))
record0.write(pack('>I', 9))
record0.write('\0' * 8) record0.write('\0' * 8)
record0.write(pack('>II', 5, self._text_nrecords + 1)) record0.write(pack('>II', 5, self._text_nrecords + 1))
record0.write('\0' * 16) record0.write('\0' * 16)