Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Do not choke when reading metadata from MOBI files with incorrectly encoded metadata fields

Browse Source
This commit is contained in:
Kovid Goyal 2013-01-18 21:32:56 +05:30
parent 67e691c2ff
commit 70a22e0327
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/calibre/ebooks/mobi/reader/headers.py
View File

@ -13,6 +13,7 @@ from calibre.utils.date import parse_date
from calibre.ebooks.mobi import MobiError from calibre.ebooks.mobi import MobiError
from calibre.ebooks.metadata import MetaInformation, check_isbn from calibre.ebooks.metadata import MetaInformation, check_isbn
from calibre.ebooks.mobi.langcodes import main_language, sub_language, mobi2iana from calibre.ebooks.mobi.langcodes import main_language, sub_language, mobi2iana
from calibre.utils.cleantext import clean_ascii_chars
from calibre.utils.localization import canonicalize_lang from calibre.utils.localization import canonicalize_lang
NULL_INDEX = 0xffffffff NULL_INDEX = 0xffffffff
@ -31,6 +32,8 @@ class EXTHHeader(object): # {{{
self.kf8_header = None self.kf8_header = None
self.uuid = self.cdetype = None self.uuid = self.cdetype = None
self.decode = lambda x : clean_ascii_chars(x.decode(codec, 'replace'))
while left > 0: while left > 0:
left -= 1 left -= 1
idx, size = struct.unpack('>LL', raw[pos:pos + 8]) idx, size = struct.unpack('>LL', raw[pos:pos + 8])
@ -66,7 +69,7 @@ class EXTHHeader(object): # {{{
# title contains non ASCII chars or non filename safe chars # title contains non ASCII chars or non filename safe chars
# they are messed up in the PDB header # they are messed up in the PDB header
try: try:
title = content.decode(codec) title = self.decode(content)
except: except:
pass pass
elif idx == 524: # Lang code elif idx == 524: # Lang code
@ -80,31 +83,30 @@ class EXTHHeader(object): # {{{
#else: #else:
# print 'unknown record', idx, repr(content) # print 'unknown record', idx, repr(content)
if title: if title:
self.mi.title = replace_entities(title) self.mi.title = replace_entities(clean_ascii_chars(title))
def process_metadata(self, idx, content, codec): def process_metadata(self, idx, content, codec):
if idx == 100: if idx == 100:
if self.mi.is_null('authors'): if self.mi.is_null('authors'):
self.mi.authors = [] self.mi.authors = []
au = content.decode(codec, 'ignore').strip() au = self.decode(content).strip()
self.mi.authors.append(au) self.mi.authors.append(au)
if self.mi.is_null('author_sort') and re.match(r'\S+?\s*,\s+\S+', au.strip()): if self.mi.is_null('author_sort') and re.match(r'\S+?\s*,\s+\S+', au.strip()):
self.mi.author_sort = au.strip() self.mi.author_sort = au.strip()
elif idx == 101: elif idx == 101:
self.mi.publisher = content.decode(codec, 'ignore').strip() self.mi.publisher = self.decode(content).strip()
if self.mi.publisher in {'Unknown', _('Unknown')}: if self.mi.publisher in {'Unknown', _('Unknown')}:
self.mi.publisher = None self.mi.publisher = None
elif idx == 103: elif idx == 103:
self.mi.comments = content.decode(codec, 'ignore') self.mi.comments = self.decode(content).strip()
elif idx == 104: elif idx == 104:
raw = check_isbn(content.decode(codec, 'ignore').strip().replace('-', '')) raw = check_isbn(self.decode(content).strip().replace('-', ''))
if raw: if raw:
self.mi.isbn = raw self.mi.isbn = raw
elif idx == 105: elif idx == 105:
if not self.mi.tags: if not self.mi.tags:
self.mi.tags = [] self.mi.tags = []
self.mi.tags.extend([x.strip() for x in content.decode(codec, self.mi.tags.extend([x.strip() for x in self.decode(content).split(';')])
'ignore').split(';')])
self.mi.tags = list(set(self.mi.tags)) self.mi.tags = list(set(self.mi.tags))
elif idx == 106: elif idx == 106:
try: try:
@ -112,7 +114,7 @@ class EXTHHeader(object): # {{{
except: except:
pass pass
elif idx == 108: elif idx == 108:
self.mi.book_producer = content.decode(codec, 'ignore').strip() self.mi.book_producer = self.decode(content).strip()
elif idx == 112: # dc:source set in some EBSP amazon samples elif idx == 112: # dc:source set in some EBSP amazon samples
try: try:
content = content.decode(codec).strip() content = content.decode(codec).strip()