Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix handling of encoding

Browse Source
This commit is contained in:
Kovid Goyal 2007-07-26 17:19:38 +00:00
parent 5b7416ff84
commit a69e3991b3
1 changed files with 18 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
src/libprs500/ebooks/lrf/txt/convert_from.py
View File

@ -27,11 +27,10 @@ from libprs500.ebooks.markdown import markdown
def option_parser(): def option_parser():
parser = lrf_option_parser('''Usage: %prog [options] mybook.txt\n\n''' parser = lrf_option_parser('''Usage: %prog [options] mybook.txt\n\n'''
'''%prog converts mybook.txt to mybook.lrf''') '''%prog converts mybook.txt to mybook.lrf''')
defenc = 'cp1252' if iswindows else 'utf8'
enchelp = 'Set the encoding used to decode ' + \ enchelp = 'Set the encoding used to decode ' + \
'the text in mybook.txt. Default encoding is %default' 'the text in mybook.txt. Default is to try to autodetect.'
parser.add_option('-e', '--encoding', action='store', type='string', \ parser.add_option('-e', '--encoding', action='store', type='string', \
dest='encoding', help=enchelp, default=defenc) dest='encoding', help=enchelp, default=None)
return parser return parser
@ -40,27 +39,27 @@ def generate_html(txtfile, encoding):
Convert txtfile to html and return a PersistentTemporaryFile object pointing Convert txtfile to html and return a PersistentTemporaryFile object pointing
to the file with the HTML. to the file with the HTML.
''' '''
encodings = ['iso-8859-1', 'koi8_r', 'koi8_u', 'utf8'] enc = encoding
if iswindows: if not encoding:
encodings = ['cp1252'] + encodings encodings = ['cp1252', 'latin-1', 'iso-8859-1', 'koi8_r', 'koi8_u', 'utf8']
if encoding not in ['cp1252', 'utf8']: txt, enc = None, None
encodings = [encoding] + encodings for encoding in encodings:
txt, enc = None, None try:
for encoding in encodings: txt = codecs.open(txtfile, 'rb', encoding).read()
try: except UnicodeDecodeError:
txt = codecs.open(txtfile, 'rb', encoding).read() continue
except UnicodeDecodeError: enc = encoding
continue break
enc = encoding if txt == None:
break raise ConversionError, 'Could not detect encoding of %s'%(txtfile,)
if txt == None: else:
raise ConversionError, 'Could not detect encoding of %s'%(txtfile,) txt = codecs.open(txtfile, 'rb', enc).read()
md = markdown.Markdown(txt, md = markdown.Markdown(txt,
extensions=['footnotes', 'tables', 'toc'], extensions=['footnotes', 'tables', 'toc'],
encoding=enc, encoding=enc,
safe_mode=False, safe_mode=False,
) )
html = md.toString().decode(enc) html = md.toString()
p = PersistentTemporaryFile('.html', dir=os.path.dirname(txtfile)) p = PersistentTemporaryFile('.html', dir=os.path.dirname(txtfile))
p.close() p.close()
codecs.open(p.name, 'wb', enc).write(html) codecs.open(p.name, 'wb', enc).write(html)