Mercurial Mercurial > comt / changeset
summary | shortlog | changelog | graph | tags | bookmarks | branches | files | changeset | raw | zip | gz | bz2 | help
Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Fixed export with abiword by running tidy on html
authorgibus
Thu, 09 Aug 2012 11:06:46 +0200
changeset 457 f62f7f0bcaa4
parent 456 b2a7c015362b
child 458 ba7e05582435
Fixed export with abiword by running tidy on html
src/cm/converters/abi_converters.py file | annotate | diff | comparison | revisions
src/cm/views/texts.py file | annotate | diff | comparison | revisions 
--- a/src/cm/converters/abi_converters.py	Thu Aug 09 10:11:21 2012 +0200
+++ b/src/cm/converters/abi_converters.py	Thu Aug 09 11:06:46 2012 +0200
@@ -5,6 +5,7 @@
 import pexpect
 
 from abi_error import AbiConverterError, AbiCommandError
+from cm.converters.pandoc_converters import do_tidy
 
 
 TYPES_IN  = {'602': '602',       'abw': 'abw',       'aw': 'aw',     
@@ -302,8 +303,4 @@
           except KeyError:
             p['style'] = 'margin-top: 10pt; margin-bottom: 10pt;';
 
-        # for some reason having DOCTYPE declaration makes soup unhappy
-        output = re.sub(r'<!(<!DOCTYPE html[^>]*>)>', r'\1', unicode(soup))
-        # And for some reason, & is not converted to &amp; from time to time!
-        output = re.sub(r'&(?![A-Za-z]+[0-9]*;|#[0-9]+;|#x[0-9a-fA-F]+;)', r'&amp;', output)
-        return output
+        return do_tidy(unicode(soup))
--- a/src/cm/views/texts.py	Thu Aug 09 10:11:21 2012 +0200
+++ b/src/cm/views/texts.py	Thu Aug 09 11:06:46 2012 +0200
@@ -302,7 +302,7 @@
   Replaces (html) links to attachs with embeded inline images
   """
   content = re.sub("%s" %settings.SITE_URL, '', content) # changes absolute urls to relative urls
-  attach_re = r'(?:/text/(?P<key>\w*))?/attach/(?P<attach_key>\w*)/'
+  attach_re = r'"(?:/text/(?P<key>\w*))?/attach/(?P<attach_key>\w*)/'
   attach_str_textversion = r'/text/%s/attach/%s/'
   attach_str = r'/attach/%s/'
   for match in re.findall(attach_re, content):
comt