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

...

Browse Source
This commit is contained in:
ldolse 2011-01-19 02:01:40 +08:00
parent 01584b0784
commit 3c45dba7cc
3 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/ebooks/conversion/preprocess.py
View File

@ -175,7 +175,7 @@ class Dehyphenator(object):
'''
def __init__(self, verbose=0, log=None):
self.log = default_log if log is None else log
self.log = log
self.verbose = verbose
# Add common suffixes to the regex below to increase the likelihood of a match -
# don't add suffixes which are also complete words, such as 'able' or 'sex'

6
src/calibre/ebooks/conversion/utils.py
View File

@ -92,8 +92,8 @@ class HeuristicProcessor(object):
line_end = line_end_ere.findall(raw)
tot_htm_ends = len(htm_end)
tot_ln_fds = len(line_end)
self.log.debug("There are " + unicode(tot_ln_fds) + " total Line feeds, and " +
unicode(tot_htm_ends) + " marked up endings")
#self.log.debug("There are " + unicode(tot_ln_fds) + " total Line feeds, and " +
# unicode(tot_htm_ends) + " marked up endings")
if percent > 1:
percent = 1
@ -101,7 +101,7 @@ class HeuristicProcessor(object):
percent = 0
min_lns = tot_ln_fds * percent
self.log.debug("There must be fewer than " + unicode(min_lns) + " unmarked lines to add markup")
#self.log.debug("There must be fewer than " + unicode(min_lns) + " unmarked lines to add markup")
if min_lns > tot_htm_ends:
return True

4
src/calibre/ebooks/txt/input.py
View File

@ -118,11 +118,11 @@ class TXTInput(InputFormatPlugin):
txt = separate_paragraphs_print_formatted(txt)
if options.paragraph_type == 'unformatted':
from calibre.ebooks.conversion.utils import PreProcessor
from calibre.ebooks.conversion.utils import HeuristicProcessor
# get length
# unwrap lines based on punctuation
preprocessor = PreProcessor(options, log=getattr(self, 'log', None))
preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None))
txt = preprocessor.punctuation_unwrap(length, txt, 'txt')
flow_size = getattr(options, 'flow_size', 0)