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

TXT Input: Don't preserve spaces in heuristic processing. Detect and retain soft scene breaks.

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-27 09:10:44 -07:00
commit da2c132d58
2 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/txt/input.py
View File

@ -83,7 +83,6 @@ class TXTInput(InputFormatPlugin):
setattr(options, 'markup_chapter_headings', True) setattr(options, 'markup_chapter_headings', True)
setattr(options, 'italicize_common_cases', True) setattr(options, 'italicize_common_cases', True)
setattr(options, 'fix_indents', True) setattr(options, 'fix_indents', True)
setattr(options, 'preserve_spaces', True)
setattr(options, 'delete_blank_paragraphs', True) setattr(options, 'delete_blank_paragraphs', True)
setattr(options, 'format_scene_breaks', True) setattr(options, 'format_scene_breaks', True)
setattr(options, 'dehyphenate', True) setattr(options, 'dehyphenate', True)

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

@ -31,7 +31,7 @@ def clean_txt(txt):
txt = re.sub('^\s+(?=.)', '', txt) txt = re.sub('^\s+(?=.)', '', txt)
txt = re.sub('(?<=.)\s+$', '', txt) txt = re.sub('(?<=.)\s+$', '', txt)
# Remove excessive line breaks. # Remove excessive line breaks.
txt = re.sub('\n{3,}', '\n\n', txt) txt = re.sub('\n{5,}', '\n\n\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
txt = clean_ascii_chars(txt) txt = clean_ascii_chars(txt)
@ -59,10 +59,16 @@ def convert_basic(txt, title='', epub_split_size_kb=0):
txt = split_txt(txt, epub_split_size_kb) txt = split_txt(txt, epub_split_size_kb)
lines = [] lines = []
blank_count = 0
# Split into paragraphs based on having a blank line between text. # Split into paragraphs based on having a blank line between text.
for line in txt.split('\n\n'): for line in txt.split('\n'):
if line.strip(): if line.strip():
blank_count = 0
lines.append(u'<p>%s</p>' % prepare_string_for_xml(line.replace('\n', ' '))) lines.append(u'<p>%s</p>' % prepare_string_for_xml(line.replace('\n', ' ')))
else:
blank_count += 1
if blank_count == 2:
lines.append(u'<p>&nbsp;</p>')
return HTML_TEMPLATE % (title, u'\n'.join(lines)) return HTML_TEMPLATE % (title, u'\n'.join(lines))
@ -85,7 +91,7 @@ def normalize_line_endings(txt):
return txt return txt
def separate_paragraphs_single_line(txt): def separate_paragraphs_single_line(txt):
txt = re.sub(u'(?<=.)\n(?=.)', '\n\n', txt) txt = txt.replace('\n', '\n\n')
return txt return txt
def separate_paragraphs_print_formatted(txt): def separate_paragraphs_print_formatted(txt):