Issue 2112 - Support fixed text in strings.

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 26 matching lines @@
 html_escapes = {
   "<": "&lt;",
   ">": "&gt;",
   "&": "&amp;",
   "\"": "&quot;",
   "'": "&#39;",
 }
 
 class AttributeParser(HTMLParser.HTMLParser):
   _string = None
+  _inside_fixed = False
+  _fixed_strings = None
   _attrs = None
 
   def __init__(self, whitelist):
     self._whitelist = whitelist
 
   def parse(self, text, pagename):
     self.reset()
     self._string = []
+    self._fixed_strings = []
+    self._inside_fixed = False
     self._attrs = {}
     self._pagename = pagename
 
     try:
       self.feed(text)
-      return "".join(self._string), self._attrs
+      return "".join(self._string), self._attrs, ["".join(s) for s in self._fixed_strings]
     finally:
       self._string = None
       self._attrs = None
       self._pagename = None
+      self._inside_fixed = False
+      self._fixed_strings = None
 
   def handle_starttag(self, tag, attrs):
-    if tag not in self._whitelist:
+    if self._inside_fixed:
+      raise Exception("Unexpected HTML tag '%s' inside a fixed string on page %s" % (tag, self._pagename))
+    elif tag == "fix":
+      self._inside_fixed = True
+      self._fixed_strings.append([])
+    elif tag in self._whitelist:
+      self._attrs.setdefault(tag, []).append(attrs)
+      self._string.append("<%s>" % tag)
+    else:
       raise Exception("Unexpected HTML tag '%s' in localizable string on page %s" % (tag, self._pagename))
-    self._attrs.setdefault(tag, []).append(attrs)
-    self._string.append("<%s>" % tag)
 
   def handle_endtag(self, tag):
-    self._string.append("</%s>" % tag)
+    if tag == "fix":
+      self._string.append("{%d}" % len(self._fixed_strings))
+      self._inside_fixed = False
+    else:
+      self._string.append("</%s>" % tag)
+
+  def _append_text(self, s):
+    if self._inside_fixed:
+      self._fixed_strings[-1].append(s)
+    else:
+      self._string.append(s)
 
   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.append(data)
+    self._append_text(data)
 
   def handle_entityref(self, name):
-    self._string.append(self.unescape("&%s;" % name))
+    self._append_text(self.unescape("&%s;" % name))
 
   def handle_charref(self, name):
-    self._string.append(self.unescape("&#%s;" % name))
+    self._append_text(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
     lines = params[key].splitlines(True)
     while lines and re.search(r"^\s*[\w\-]+\s*=", lines[0]):
       name, value = lines.pop(0).split("=", 1)
       params[name.strip()] = value.strip()
     params[key] = "".join(lines)
 
   def localize_string(self, name, default, localedata, escapes):
     def escape(s):
       return re.sub(r".",
         lambda match: escapes.get(match.group(0), match.group(0)),
         s, flags=re.S)
     def re_escape(s):
       return re.escape(escape(s))
 
     # Extract tag attributes from default string
-    default, saved_attributes = self._attribute_parser.parse(default, self._params["page"])
+    default, saved_attributes, fixed_strings = self._attribute_parser.parse(default, self._params["page"])
 
     # Get translation
     if self._params["locale"] != self._params["defaultlocale"] and name in localedata:
       result = localedata[name].strip()
     else:
       result = default
 
+    # Insert fixed strings
+    for i in range(len(fixed_strings)):
+      result = re.sub(re_escape("{%d}" % (i + 1)), fixed_strings[i], result, 1)

[Wladimir Palant, 2015/03/27 07:29:48]

The string isn't escaped yes, meaning that we shouldn't escape our search string
either - re.sub(r"\{%d\}" % (i + 1), ...) will do.

[kzar, 2015/03/27 09:50:44]

Done.

+
     # Insert attributes
     result = escape(result)
     for tag in self.whitelist:
       saved = saved_attributes.get(tag, [])
       for attrs in saved:
         attrs = map(lambda (name, value): '%s="%s"' % (escape(name), escape(value)), attrs)
         result = re.sub(
           r"%s([^<>]*?)%s" % (re_escape("<%s>" % tag), re_escape("</%s>" % tag)),
           r'<%s %s>\1</%s>' % (tag, " ".join(attrs), tag),
           result, 1, flags=re.S
@@ skipping 217 matching lines @@
         stack.pop()
       stack[-1]["subitems"].append(item)
       stack.append(item)
     return structured
 
 converters = {
   "html": RawConverter,
   "md": MarkdownConverter,
   "tmpl": TemplateConverter,
 }