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

Fixed a regression inttroduced by patch 5798

Browse Source
This commit is contained in:
Sengian 2010-07-31 14:27:48 +02:00
parent 3405615e54
commit 5715d0fbc8
2 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/txt/input.py
View File

@ -57,7 +57,6 @@ class TXTInput(InputFormatPlugin):
txt = preserve_spaces(txt) txt = preserve_spaces(txt)
txt = _ent_pat.sub(xml_entity_to_unicode, txt) txt = _ent_pat.sub(xml_entity_to_unicode, txt)
txt = txt.encode('utf-8')
if options.markdown: if options.markdown:
log.debug('Running text though markdown conversion...') log.debug('Running text though markdown conversion...')
@ -80,7 +79,7 @@ class TXTInput(InputFormatPlugin):
base = os.path.dirname(stream.name) base = os.path.dirname(stream.name)
htmlfile = open(os.path.join(base, 'temp_calibre_txt_input_to_html.html'), htmlfile = open(os.path.join(base, 'temp_calibre_txt_input_to_html.html'),
'wb') 'wb')
htmlfile.write(html) #html.encode('utf-8') htmlfile.write(html.encode('utf-8'))
htmlfile.close() htmlfile.close()
cwd = os.getcwdu() cwd = os.getcwdu()
odi = options.debug_pipeline odi = options.debug_pipeline

12
src/calibre/ebooks/txt/processor.py
View File

@ -19,7 +19,7 @@ HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html
def convert_basic(txt, title='', epub_split_size_kb=0): def convert_basic(txt, title='', epub_split_size_kb=0):
# Strip whitespace from the beginning and end of the line. Also replace # Strip whitespace from the beginning and end of the line. Also replace
# all line breaks with \n. # all line breaks with \n.
txt = u'\n'.join([line.strip() for line in txt.splitlines()]) txt = '\n'.join([line.strip() for line in txt.splitlines()])
# Condense redundant spaces # Condense redundant spaces
txt = re.sub('[ ]{2,}', ' ', txt) txt = re.sub('[ ]{2,}', ' ', txt)
@ -30,9 +30,9 @@ def convert_basic(txt, title='', epub_split_size_kb=0):
# Remove excessive line breaks. # Remove excessive line breaks.
txt = re.sub('\n{3,}', '\n\n', txt) txt = re.sub('\n{3,}', '\n\n', txt)
#remove ASCII invalid chars : 0 to 8 and 11-14 to 24 #remove ASCII invalid chars : 0 to 8 and 11-14 to 24
#illegal_char = re.compile('\x00|\x01|\x02|\x03|\x04|\x05|\x06|\x07|\x08| \ illegal_char = re.compile('\x00|\x01|\x02|\x03|\x04|\x05|\x06|\x07|\x08| \
# \x0B|\x0E|\x0F|\x10|\x11|\x12|\x13|\x14|\x15|\x16|\x17|\x18') \x0B|\x0E|\x0F|\x10|\x11|\x12|\x13|\x14|\x15|\x16|\x17|\x18')
txt = re.sub('\u000[0-8]|\u001[14-9]|\u002[0-4]', '', txt) txt = illegal_char.sub('', txt)
#Takes care if there is no point to split #Takes care if there is no point to split
if epub_split_size_kb > 0: if epub_split_size_kb > 0:
@ -41,7 +41,7 @@ def convert_basic(txt, title='', epub_split_size_kb=0):
chunk_size = long(length_byte / (int(length_byte / (epub_split_size_kb * 1024) ) + 2 )) chunk_size = long(length_byte / (int(length_byte / (epub_split_size_kb * 1024) ) + 2 ))
#if there are chunks with a superior size then go and break #if there are chunks with a superior size then go and break
if (len(filter(lambda x: len(x) > chunk_size, txt.split('\n\n')))) : if (len(filter(lambda x: len(x) > chunk_size, txt.split('\n\n')))) :
txt = u'\n\n'.join([split_string_separator(line, chunk_size) txt = '\n\n'.join([split_string_separator(line, chunk_size)
for line in txt.split('\n\n')]) for line in txt.split('\n\n')])
lines = [] lines = []
@ -83,7 +83,7 @@ def opf_writer(path, opf_name, manifest, spine, mi):
def split_string_separator(txt, size) : def split_string_separator(txt, size) :
if len(txt) > size: if len(txt) > size:
txt = u''.join([re.sub(u'\.(?P<ends>[^.]*)$', u'.\n\n\g<ends>', txt = ''.join([re.sub(u'\.(?P<ends>[^.]*)$', '.\n\n\g<ends>',
txt[i:i+size], 1) for i in txt[i:i+size], 1) for i in
xrange(0, len(txt), size)]) xrange(0, len(txt), size)])
return txt return txt