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: Restructure to run dehyphenator when auto and heuristic formatting options are used. This causes textile and markdown to be dehyphenated.

Browse Source
This commit is contained in:
John Schember 2011-02-05 12:51:47 -05:00
parent 37dd8f6f3a
commit 9cdad92468
1 changed files with 23 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
src/calibre/ebooks/txt/input.py
View File

@ -77,20 +77,6 @@ class TXTInput(InputFormatPlugin):
# Normalize line endings
txt = normalize_line_endings(txt)
# Detect formatting
if options.formatting_type == 'auto':
options.formatting_type = detect_formatting_type(txt)
log.debug('Auto detected formatting as %s' % options.formatting_type)
if options.formatting_type == 'heuristic':
setattr(options, 'enable_heuristics', True)
setattr(options, 'markup_chapter_headings', True)
setattr(options, 'italicize_common_cases', True)
setattr(options, 'fix_indents', True)
setattr(options, 'delete_blank_paragraphs', True)
setattr(options, 'format_scene_breaks', True)
setattr(options, 'dehyphenate', True)
# Determine the paragraph type of the document.
if options.paragraph_type == 'auto':
options.paragraph_type = detect_paragraph_type(txt)
@ -100,15 +86,26 @@ class TXTInput(InputFormatPlugin):
else:
log.debug('Auto detected paragraph type as %s' % options.paragraph_type)
dehyphenate = False
if options.formatting_type in ('auto', 'heuristic'):
# Set this here because we want it to run over all
# formatting types if auto is used.
dehyphenate = True
# Detect formatting
if options.formatting_type == 'auto':
options.formatting_type = detect_formatting_type(txt)
log.debug('Auto detected formatting as %s' % options.formatting_type)
if options.formatting_type == 'heuristic':
setattr(options, 'enable_heuristics', True)
setattr(options, 'unwrap_lines', False)
# Preserve spaces will replace multiple spaces to a space
# followed by the   entity.
if options.preserve_spaces:
txt = preserve_spaces(txt)
# Get length for hyphen removal and punctuation unwrap
docanalysis = DocAnalysis('txt', txt)
length = docanalysis.line_length(.5)
# Reformat paragraphs to block formatting based on the detected type.
# We don't check for block because the processor assumes block.
# single and print at transformed to block for processing.
@ -119,9 +116,17 @@ class TXTInput(InputFormatPlugin):
elif options.paragraph_type == 'unformatted':
from calibre.ebooks.conversion.utils import HeuristicProcessor
# unwrap lines based on punctuation
docanalysis = DocAnalysis('txt', txt)
length = docanalysis.line_length(.5)
preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None))
txt = preprocessor.punctuation_unwrap(length, txt, 'txt')
if dehyphenate:
docanalysis = DocAnalysis('txt', txt)
length = docanalysis.line_length(.5)
dehyphenator = Dehyphenator(options.verbose, log=self.log)
txt = dehyphenator(txt,'txt', length)
# Process the text using the appropriate text processor.
html = ''
if options.formatting_type == 'markdown':
@ -134,14 +139,8 @@ class TXTInput(InputFormatPlugin):
elif options.formatting_type == 'textile':
log.debug('Running text through textile conversion...')
html = convert_textile(txt)
else:
log.debug('Running text through basic conversion...')
if options.formatting_type == 'heuristic':
# Dehyphenate
dehyphenator = Dehyphenator(options.verbose, log=self.log)
txt = dehyphenator(txt,'txt', length)
flow_size = getattr(options, 'flow_size', 0)
html = convert_basic(txt, epub_split_size_kb=flow_size)