FB2,PML,RB,TXT Output: Fix removing of extra spaces too aggresive

This commit is contained in:
Kovid Goyal 2009-10-26 11:41:33 -06:00
parent 47eb8c1f3e
commit b9ae515df6
4 changed files with 11 additions and 11 deletions

View File

@ -241,7 +241,7 @@ class FB2MLizer(object):
if not fb2_text or fb2_text[-1] != ' ':
fb2_text.append(' ')
if hasattr(elem, 'text') and elem.text != None:
if hasattr(elem, 'text') and elem.text:
if 'p' not in tag_stack:
fb2_text.append('<p>%s</p>' % prepare_string_for_xml(elem.text))
else:
@ -255,7 +255,7 @@ class FB2MLizer(object):
close_tag_list.insert(0, tag_stack.pop())
fb2_text += self.close_tags(close_tag_list)
if hasattr(elem, 'tail') and elem.tail != None:
if hasattr(elem, 'tail') and elem.tail:
if 'p' not in tag_stack:
fb2_text.append('<p>%s</p>' % prepare_string_for_xml(elem.tail))
else:

View File

@ -257,7 +257,7 @@ class PMLMLizer(object):
# margin
# Proccess tags that contain text.
if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
if hasattr(elem, 'text') and elem.text:
text.append(self.remove_newlines(elem.text))
for item in elem:
@ -276,7 +276,7 @@ class PMLMLizer(object):
#if style['page-break-after'] == 'always':
# text.append('\\p')
if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '':
if hasattr(elem, 'tail') and elem.tail:
text.append(self.remove_newlines(elem.tail))
return text

View File

@ -191,7 +191,7 @@ class RBMLizer(object):
tag_stack.append(style_tag)
# Proccess tags that contain text.
if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
if hasattr(elem, 'text') and elem.text:
text.append(prepare_string_for_xml(elem.text))
for item in elem:
@ -203,7 +203,7 @@ class RBMLizer(object):
text += self.close_tags(close_tag_list)
if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '':
if hasattr(elem, 'tail') and elem.tail:
text.append(prepare_string_for_xml(elem.tail))
return text

View File

@ -94,7 +94,7 @@ class TXTMLizer(object):
text = re.sub('(?<=.)%s(?=.)' % os.linesep, ' ', text)
# Remove multiple spaces.
text = re.sub('[ ]+', ' ', text)
text = re.sub('[ ]{2,}', ' ', text)
# Remove excessive newlines.
text = re.sub('\n[ ]+\n', '\n\n', text)
@ -172,15 +172,15 @@ class TXTMLizer(object):
# Are we in a paragraph block?
if tag in BLOCK_TAGS or style['display'] in BLOCK_STYLES:
in_block = True
if not end.endswith(u'\n\n') and hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
if not end.endswith(u'\n\n') and hasattr(elem, 'text') and elem.text:
text.append(u'\n\n')
if tag in SPACE_TAGS:
if not end.endswith('u ') and hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
if not end.endswith('u ') and hasattr(elem, 'text') and elem.text:
text.append(u' ')
# Process tags that contain text.
if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
if hasattr(elem, 'text') and elem.text:
text.append(elem.text)
for item in elem:
@ -192,7 +192,7 @@ class TXTMLizer(object):
if in_block:
text.append(u'\n\n')
if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '':
if hasattr(elem, 'tail') and elem.tail:
text.append(elem.tail)
return text