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

CHM Input: If an input encoding is specified, use it rather than trying to detect the encoding of the text in the CHM file. Fixes #9173 ("Input character encoding" is useless for chm file.)

Browse Source
This commit is contained in:
Kovid Goyal 2011-03-07 22:08:48 -07:00
parent 0285c22a84
commit 24d8f758e7
2 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/chm/input.py
View File

@ -22,7 +22,7 @@ class CHMInput(InputFormatPlugin):
def _chmtohtml(self, output_dir, chm_path, no_images, log): def _chmtohtml(self, output_dir, chm_path, no_images, log):
from calibre.ebooks.chm.reader import CHMReader from calibre.ebooks.chm.reader import CHMReader
log.debug('Opening CHM file') log.debug('Opening CHM file')
rdr = CHMReader(chm_path, log) rdr = CHMReader(chm_path, log, self.opts)
log.debug('Extracting CHM to %s' % output_dir) log.debug('Extracting CHM to %s' % output_dir)
rdr.extract_content(output_dir) rdr.extract_content(output_dir)
self._chm_reader = rdr self._chm_reader = rdr
@ -32,13 +32,13 @@ class CHMInput(InputFormatPlugin):
def convert(self, stream, options, file_ext, log, accelerators): def convert(self, stream, options, file_ext, log, accelerators):
from calibre.ebooks.chm.metadata import get_metadata_from_reader from calibre.ebooks.chm.metadata import get_metadata_from_reader
from calibre.customize.ui import plugin_for_input_format from calibre.customize.ui import plugin_for_input_format
self.opts = options
log.debug('Processing CHM...') log.debug('Processing CHM...')
with TemporaryDirectory('_chm2oeb') as tdir: with TemporaryDirectory('_chm2oeb') as tdir:
html_input = plugin_for_input_format('html') html_input = plugin_for_input_format('html')
for opt in html_input.options: for opt in html_input.options:
setattr(options, opt.option.name, opt.recommended_value) setattr(options, opt.option.name, opt.recommended_value)
options.input_encoding = 'utf-8'
no_images = False #options.no_images no_images = False #options.no_images
chm_name = stream.name chm_name = stream.name
#chm_data = stream.read() #chm_data = stream.read()
@ -54,6 +54,7 @@ class CHMInput(InputFormatPlugin):
odi = options.debug_pipeline odi = options.debug_pipeline
options.debug_pipeline = None options.debug_pipeline = None
options.input_encoding = 'utf-8'
# try a custom conversion: # try a custom conversion:
#oeb = self._create_oebbook(mainpath, tdir, options, log, metadata) #oeb = self._create_oebbook(mainpath, tdir, options, log, metadata)
# try using html converter: # try using html converter:

5
src/calibre/ebooks/chm/reader.py
View File

@ -40,13 +40,14 @@ class CHMError(Exception):
pass pass
class CHMReader(CHMFile): class CHMReader(CHMFile):
def __init__(self, input, log): def __init__(self, input, log, opts):
CHMFile.__init__(self) CHMFile.__init__(self)
if isinstance(input, unicode): if isinstance(input, unicode):
input = input.encode(filesystem_encoding) input = input.encode(filesystem_encoding)
if not self.LoadCHM(input): if not self.LoadCHM(input):
raise CHMError("Unable to open CHM file '%s'"%(input,)) raise CHMError("Unable to open CHM file '%s'"%(input,))
self.log = log self.log = log
self.opts = opts
self._sourcechm = input self._sourcechm = input
self._contents = None self._contents = None
self._playorder = 0 self._playorder = 0
@ -151,6 +152,8 @@ class CHMReader(CHMFile):
break break
def _reformat(self, data, htmlpath): def _reformat(self, data, htmlpath):
if self.opts.input_encoding:
data = data.decode(self.opts.input_encoding)
try: try:
data = xml_to_unicode(data, strip_encoding_pats=True)[0] data = xml_to_unicode(data, strip_encoding_pats=True)[0]
soup = BeautifulSoup(data) soup = BeautifulSoup(data)