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: convet_basic changed at some point to require single line paragraphs. Add function to turn block formatted paragraphs to single so they are processed correctly.

Browse Source
This commit is contained in:
John Schember 2011-02-06 08:45:50 -05:00
parent 92ee46cdb9
commit 2d4fc57ddc
2 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -12,7 +12,7 @@ from calibre.ebooks.chardet import detect
from calibre.ebooks.txt.processor import convert_basic, convert_markdown, \ from calibre.ebooks.txt.processor import convert_basic, convert_markdown, \
separate_paragraphs_single_line, separate_paragraphs_print_formatted, \ separate_paragraphs_single_line, separate_paragraphs_print_formatted, \
preserve_spaces, detect_paragraph_type, detect_formatting_type, \ preserve_spaces, detect_paragraph_type, detect_formatting_type, \
normalize_line_endings, convert_textile, remove_indents normalize_line_endings, convert_textile, remove_indents, block_to_single_line
from calibre import _ent_pat, xml_entity_to_unicode from calibre import _ent_pat, xml_entity_to_unicode
class TXTInput(InputFormatPlugin): class TXTInput(InputFormatPlugin):
@ -106,6 +106,7 @@ class TXTInput(InputFormatPlugin):
txt = separate_paragraphs_single_line(txt) txt = separate_paragraphs_single_line(txt)
elif options.paragraph_type == 'print': elif options.paragraph_type == 'print':
txt = separate_paragraphs_print_formatted(txt) txt = separate_paragraphs_print_formatted(txt)
txt = block_to_single_line(txt)
elif options.paragraph_type == 'unformatted': elif options.paragraph_type == 'unformatted':
from calibre.ebooks.conversion.utils import HeuristicProcessor from calibre.ebooks.conversion.utils import HeuristicProcessor
# unwrap lines based on punctuation # unwrap lines based on punctuation
@ -114,6 +115,8 @@ class TXTInput(InputFormatPlugin):
preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None)) preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None))
txt = preprocessor.punctuation_unwrap(length, txt, 'txt') txt = preprocessor.punctuation_unwrap(length, txt, 'txt')
txt = separate_paragraphs_single_line(txt) txt = separate_paragraphs_single_line(txt)
else:
txt = block_to_single_line(txt)
if getattr(options, 'enable_heuristics', False) and getattr(options, 'dehyphenate', False): if getattr(options, 'enable_heuristics', False) and getattr(options, 'dehyphenate', False):
docanalysis = DocAnalysis('txt', txt) docanalysis = DocAnalysis('txt', txt)

6
src/calibre/ebooks/txt/processor.py
View File

@ -99,7 +99,11 @@ def separate_paragraphs_single_line(txt):
return txt return txt
def separate_paragraphs_print_formatted(txt): def separate_paragraphs_print_formatted(txt):
txt = re.sub(u'(?miu)^(?P<indent>\t+|[ ]{2,})(?=.)', lambda mo: '%s\n\t' % mo.group('indent'), txt) txt = re.sub(u'(?miu)^(?P<indent>\t+|[ ]{2,})(?=.)', lambda mo: '\n%s' % mo.group('indent'), txt)
return txt
def block_to_single_line(txt):
txt = re.sub(r'(?<=.)\n(?=.)', ' ', txt)
return txt return txt
def preserve_spaces(txt): def preserve_spaces(txt):