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

More textile work.

Browse Source
This commit is contained in:
John Schember 2011-04-19 06:49:27 -04:00
parent 804b248d46
commit be3d441d3b
3 changed files with 89 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -70,7 +70,6 @@ class TXTOutput(OutputFormatPlugin):
]) ])
def convert(self, oeb_book, output_path, input_plugin, opts, log): def convert(self, oeb_book, output_path, input_plugin, opts, log):
print 'New'
if opts.txt_output_formatting.lower() == 'markdown': if opts.txt_output_formatting.lower() == 'markdown':
from calibre.ebooks.txt.markdownml import MarkdownMLizer from calibre.ebooks.txt.markdownml import MarkdownMLizer
self.writer = MarkdownMLizer(log) self.writer = MarkdownMLizer(log)

121
src/calibre/ebooks/txt/textileml.py
View File

@ -58,31 +58,39 @@ class TextileMLizer(OEB2HTML):
return ''.join(output) return ''.join(output)
def tidy_up(self, text): def tidy_up(self, text):
def check_count(text, tests): # def check_count(text, tests):
x = [] # x = []
for i, t in enumerate(reversed(tests)): # for i, t in enumerate(reversed(tests)):
x.append((text.count(t), i, t)) # x.append((text.count(t), i, t))
if x: # if x:
return sorted(x, key=itemgetter(0, 1), reverse=True)[0][2] # return sorted(x, key=itemgetter(0, 1), reverse=True)[0][2]
return '' # return ''
# NEEDS TWEAKING # Needs tweaking and finetuning - don't use yet.
# def check_escaping(text, tests): def check_escaping(text, tests):
# for t in tests: for t in tests:
# text = re.sub(r'(\S)('+t+'\w+'+t+')', r'\1[\2]', text) text = re.sub(r'(\S)'+t+t+'(\S)', r'\1\2', text)
# text = re.sub(r'(\s)('+t+'\w+'+t+')(\S)', r'\1[\2]\3', text) # text = re.sub(r'(\w)('+t+'\w+'+t+')', r'\1[\2]', text)
# return text # text = re.sub(r'('+t+'\w+'+t+')(\w)', r'[\1]\2', text)
# text = re.sub(r'(["\'])\[('+t+'\w+'+t+')\]', r'\1\2', text)
# text = re.sub(r'\[('+t+'\w+'+t+')\](["\',\.!\?])', r'\1\2', text)
return text
txt = check_count(text, ['\np<. ', '\np<>. ', '\np. ']) # txt = check_count(text, ['\np<. ', '\np<>. ', '\np. '])
text = re.sub(txt+'(\S)', r'\n\1', text) # text = re.sub(txt+'(\S)', r'\n\1', text)
# text = check_escaping(text, ['\^', '\*', '_', '\+', '~', '-']) text = check_escaping(text, ['\^', '\*', '_', '\+', '~', '-'])
text = re.sub('\npre\. bc\.', '\nbc.', text) text = re.sub(r'^\n+', r'', text)
text = re.sub('\np=. p. ', '\np. ', text) text = re.sub(r'\npre\. bc\.', r'\nbc.', text)
text = re.sub('\np=. \n', '\n', text) text = re.sub(r'\nbq\. \n\np\. ', r'\nbq. ', text)
text = re.sub('\n{3,}', '\n\n', text) text = re.sub(r'\n{4,}', r'\n\np. \n\n', text)
text = re.sub(' \|', '|', text) text = re.sub(r'\n{3}', r'\n\n', text)
text = re.sub(r'(p.*\. \n?)(p.*\. )', r'\2', text)
text = re.sub(r'p.*\. \n\n', r'', text)
# text = re.sub(u'\n \n', r'\n<br />\n', text) # blank paragraph - br tag
text = re.sub(u'p.*\. \xa0', r'p. ', text) # blank paragraph
text = re.sub(r' \|', r'|', text)
# started work on trying to fix footnotes # started work on trying to fix footnotes
# text = re.sub(r'\^"(\d+)":#.+\^', r'[\1]', text) # text = re.sub(r'\^"(\d+)":#.+\^', r'[\1]', text)
@ -95,19 +103,28 @@ class TextileMLizer(OEB2HTML):
# Condense redundant spaces created by replacing newlines with spaces. # Condense redundant spaces created by replacing newlines with spaces.
text = re.sub(r'[ ]{2,}', ' ', text) text = re.sub(r'[ ]{2,}', ' ', text)
text = re.sub(r'\t +', '', text) text = re.sub(r'\t +', '', text)
# text = re.sub(r'\n +', '', text)
return text return text
def remove_leading_ws(self, text): def remove_leading_ws(self, text):
text = text.replace('\r\n', '\n') text = text.replace('\r\n', '\n')
text = text.replace('\r', '\n') text = text.replace('\r', '\n')
text = re.sub(r'\n+', '\n', text)
text = re.sub(r'\n[\t ]+', '\n', text) text = re.sub(r'\n[\t ]+', '\n', text)
text = re.sub(r'\n{2,}', '\n', text)
return text return text
def check_align(self, style, align, tests): def check_halign(self, style):
tests = {'left':'<','justify':'<>','center':'=','right':'>'}
for i in tests: for i in tests:
if style[align] == i[0]: if style['text-align'] == i:
return i[1] return tests[i]
return ''
def check_valign(self, style):
tests = {'top':'^','bottom':'~', 'middle':'-'}
for i in tests:
if style['vertical-align'] == i:
return tests[i]
return '' return ''
def check_padding(self, style, tests): def check_padding(self, style, tests):
@ -124,15 +141,16 @@ class TextileMLizer(OEB2HTML):
def check_id_tag(self, attribs): def check_id_tag(self, attribs):
txt = '' txt = ''
if attribs.has_key('id'): if attribs.has_key('id'):
#if attribs['id'] in self.links:
txt = '(#'+attribs['id']+')' txt = '(#'+attribs['id']+')'
return txt return txt
def build_block(self, tag, style, attribs, finish): def build_block(self, tag, style, attribs, finish):
txt = tag txt = '\n' + tag
if self.opts.keep_links: if self.opts.keep_links:
txt += self.check_id_tag(attribs) txt += self.check_id_tag(attribs)
txt += self.check_padding(style, [['padding-left','('],['padding-right',')']]) txt += self.check_padding(style, [['padding-left','('],['padding-right',')']])
txt += self.check_align(style, 'text-align', [['left','<'],['justify','<>'],['center','='],['right','>']]) txt += self.check_halign(style)
txt += finish txt += finish
return txt return txt
@ -163,7 +181,17 @@ class TextileMLizer(OEB2HTML):
or style['visibility'] == 'hidden': or style['visibility'] == 'hidden':
return [''] return ['']
if tag in ('h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p'): # Soft scene breaks.
text.append(self.check_padding(style, ['margin-top',u'\n\n\xa0']))
if tag in ('h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'div'):
#For debugging
if tag == 'h1':
for i in self.links:
text.append(i)
text.append('\n')
if tag == 'div':
tag = 'p'
text.append(self.build_block(tag, style, attribs, '. ')) text.append(self.build_block(tag, style, attribs, '. '))
tags.append('\n') tags.append('\n')
@ -191,10 +219,10 @@ class TextileMLizer(OEB2HTML):
tags.append('-') tags.append('-')
self.style_strike = True self.style_strike = True
if style['font-variant'] == 'small-caps': if style['font-variant'] == 'small-caps':
if self.style_smallcap == 0: if self.style_smallcap == False:
text.append('&') text.append('&')
tags.append('&') tags.append('&')
self.style_smallcap = 1 self.style_smallcap = True
if tag == 'br': if tag == 'br':
text.append('') text.append('')
tags.append('\n') tags.append('\n')
@ -236,7 +264,10 @@ class TextileMLizer(OEB2HTML):
tags.append('(' + attribs['title'] + ')') tags.append('(' + attribs['title'] + ')')
elif tag == 'img': elif tag == 'img':
if self.opts.keep_image_references: if self.opts.keep_image_references:
text.append ('!' + attribs['src']) txt = '!' + self.check_halign(style)
txt += self.check_valign(style)
txt += attribs['src']
text.append(txt)
if attribs.has_key('alt'): if attribs.has_key('alt'):
txt = attribs['alt'] txt = attribs['alt']
if txt != '': if txt != '':
@ -247,6 +278,7 @@ class TextileMLizer(OEB2HTML):
text.append('') text.append('')
tags.append(tag) tags.append(tag)
elif tag == 'li': elif tag == 'li':
# text.append('\n')
if self.list: li = self.list[-1] if self.list: li = self.list[-1]
else: li = {'name':'ul', 'num':0} else: li = {'name':'ul', 'num':0}
if li['name'] == 'ul': text.append('*'*len(self.list)+' ') if li['name'] == 'ul': text.append('*'*len(self.list)+' ')
@ -273,8 +305,8 @@ class TextileMLizer(OEB2HTML):
elif tag == 'td': elif tag == 'td':
text.append('|') text.append('|')
txt = '' txt = ''
txt += self.check_align(style, 'text-align', [['left','<'],['justify','<>'],['center','='],['right','>']]) txt += self.check_halign(style)
txt += self.check_align(style, 'vertical-align', [['top','^'],['bottom','~']]) txt += self.check_valign(style)
if attribs.has_key ('colspan'): if attribs.has_key ('colspan'):
txt += '\\' + attribs['colspan'] txt += '\\' + attribs['colspan']
if attribs.has_key ('rowspan'): if attribs.has_key ('rowspan'):
@ -288,7 +320,10 @@ class TextileMLizer(OEB2HTML):
if self.opts.keep_links and attribs.has_key('id'): if self.opts.keep_links and attribs.has_key('id'):
if tag not in ('body', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p'): if tag not in ('body', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p'):
text.append('(#' + attribs['id'] + ')') if tag == 'span':
text.append(' %')
tags.append('% ')
text.append('(#' + attribs['id'] + u')\xa0')
# If wanted process all style tags here - before taxt in tags is written # If wanted process all style tags here - before taxt in tags is written
@ -318,11 +353,19 @@ class TextileMLizer(OEB2HTML):
if self.list: self.list.pop() if self.list: self.list.pop()
else: else:
text.append('%s' % t) text.append('%s' % t)
if t == '*': self.style_bold = False if t == '*':
if t == '_': self.style_italic = False self.style_bold = False
if t == '+': self.style_under = False if t == '_':
if t == '-': self.style_strike = False self.style_italic = False
if t == '&': self.style_smallcap = False if t == '+':
self.style_under = False
if t == '-':
self.style_strike = False
if t == '&':
self.style_smallcap = False
# Soft scene breaks.
text.append(self.check_padding(style, ['margin-bottom',u'\n\n\xa0']))
# Add the text that is outside of the tag. # Add the text that is outside of the tag.
if hasattr(elem, 'tail') and elem.tail: if hasattr(elem, 'tail') and elem.tail:

11
src/calibre/ebooks/txt/unsmarten.py
View File

@ -1,8 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
''' """unsmarten : html2textile helper function"""
'''
__version__ = '0.1' __version__ = '0.1'
__author__ = 'Leigh Parry' __author__ = 'Leigh Parry'
@ -102,8 +100,9 @@ def unsmarten(txt):
txt = re.sub(u'&#9829;|&hearts;|♥', r'{heart}', txt) # heart txt = re.sub(u'&#9829;|&hearts;|♥', r'{heart}', txt) # heart
txt = re.sub(u'&#9830;|&diams;|♦', r'{diamond}', txt) # diamond txt = re.sub(u'&#9830;|&diams;|♦', r'{diamond}', txt) # diamond
txt = re.sub(u'\xa0', r'p. ', txt) # blank paragraph # Move into main code?
txt = re.sub(u'\n\n\n\n', r'\n\np. \n\n', txt) # blank paragraph # txt = re.sub(u'\xa0', r'p. ', txt) # blank paragraph
txt = re.sub(u'\n \n', r'\n<br />\n', txt) # blank paragraph - br tag # txt = re.sub(u'\n\n\n\n', r'\n\np. \n\n', txt) # blank paragraph
# txt = re.sub(u'\n \n', r'\n<br />\n', txt) # blank paragraph - br tag
return txt return txt