Issue 2133 - Allow to specify default translation inline in pages rather than in a separate file

cms/converters.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2015 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus is distributed in the hope that it will be useful,
@@ skipping 24 matching lines @@
 markdown.util.isBlockLevel = isBlockLevel
 
 html_escapes = {
   "<": "&lt;",
   ">": "&gt;",
   "&": "&amp;",
   "\"": "&quot;",
   "'": "&#39;",
 }
 
 class AttributeParser(HTMLParser.HTMLParser):

[Sebastian Noack, 2015/03/12 20:33:46]

That makes actually sense, using a proper parser instead a regex. I'm just
wondring whether it explodes if we get not 100% valid HTML, or whether this is a
case we have to bother about here.

[Wladimir Palant, 2015/03/12 20:57:02]

I actually tested this - invalid HTML will be normalized, which is a nice
side-effect.

   _string = None
   _attrs = None
 
   def __init__(self, whitelist):
     self._whitelist = whitelist
 
   def parse(self, text, pagename):
     self.reset()
-    self._string = ""

[Sebastian Noack, 2015/03/12 20:33:46]

I'd rather use a list here, joining it when done. I know performance doesn't
matter here, but Python folks just consider this kind of string concatenation
ugly. ;)

[Wladimir Palant, 2015/03/12 20:57:02]

Done.

+    self._string = []
     self._attrs = {}
     self._pagename = pagename
 
     try:
       self.feed(text)
-      return self._string, self._attrs
+      return "".join(self._string), self._attrs
     finally:
       self._string = None
       self._attrs = None
       self._pagename = None
 
   def handle_starttag(self, tag, attrs):
     if tag not in self._whitelist:
       raise Exception("Unexpected HTML tag '%s' in localizable string on page %s" % (tag, self._pagename))
     self._attrs.setdefault(tag, []).append(attrs)
-    self._string += "<%s>" % tag
+    self._string.append("<%s>" % tag)
 
   def handle_endtag(self, tag):
-    self._string += "</%s>" % tag
+    self._string.append("</%s>" % tag)
 
   def handle_data(self, data):
     # Note: lack of escaping here is intentional. The result is a locale string,
     # HTML escaping is applied when this string is inserted into the document.
-    self._string += data
+    self._string.append(data)
 
   def handle_entityref(self, name):
-    self._string += self.unescape("&%s;" % name)
+    self._string.append(self.unescape("&%s;" % name))
 
   def handle_charref(self, name):
-    self._string += self.unescape("&#%s;" % name)
+    self._string.append(self.unescape("&#%s;" % name))
 
 class Converter:
   whitelist = set(["a", "em", "strong"])
 
   def __init__(self, params, key="pagedata"):
     self._params = params
     self._key = key
     self._attribute_parser = AttributeParser(self.whitelist)
 
     # Read in any parameters specified at the beginning of the file
@@ skipping 237 matching lines @@
         stack.pop()
       stack[-1]["subitems"].append(item)
       stack.append(item)
     return structured
 
 converters = {
   "raw": RawConverter,
   "md": MarkdownConverter,
   "tmpl": TemplateConverter,
 }