Fixes 5343 - add global function: get_canonical_url

cms/converters.py

 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2017 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,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
@@ skipping 379 matching lines @@
             'translate': self.translate,
             'linkify': self.linkify,
             'toclist': self.toclist,
         }
 
         globals = {
             'get_string': self.get_string,
             'has_string': self.has_string,
             'get_page_content': self.get_page_content,
             'get_pages_metadata': self.get_pages_metadata,
-            'get_page_url': self.get_page_url,
+            'get_canonical_url': self.get_canonical_url,
         }
 
         for dirname, dictionary in [('filters', filters),
                                     ('globals', globals)]:
             for filename in self._params['source'].list_files(dirname):
                 root, ext = os.path.splitext(filename)
                 if ext.lower() != '.py':
                     continue
 
                 path = os.path.join(dirname, filename)
@@ skipping 101 matching lines @@
             if isinstance(metadata[filter_name], list):
                 if isinstance(filter_value, basestring):
                     filter_value = [filter_value]
                 for option in filter_value:
                     if str(option) not in metadata[filter_name]:
                         return False
             elif filter_value != metadata[filter_name]:
                     return False
         return True
 
-    def get_page_url(self, page, locale='default'):
-        """Return URL of `page` in given `locale`
-
-        By default current locale will be used. When `locale` is set to `None`,
-        the canonical URL for the page (with no locale component) will be
-        returned.
-        """
+    def get_canonical_url(self, page):
+        """Return canonical URL for the page (without locale code)"""
         try:
             base_url = self._params['site_url']
         except KeyError:
-            raise Exception('You must configure siteurl to use `get_page_url`')
-
-        if locale == 'default':
-            locale = self._params['locale']
-        if locale is not None:
-            base_url = urlparse.urljoin(base_url, locale + '/')
-
-        return urlparse.urljoin(base_url, page)
+            raise Exception('You must configure `siteurl` to use'
+                            '`get_canonical_url()`')
+
+        locale, page_url = self._params['source'].resolve_link(
+            page, self._params['locale']
+        )
+        # Remove the locale component that `resolve_link` adds at the
+        # beginning.
+        page_url = page_url[len(locale) + 1:]
+        return urlparse.urljoin(base_url, page_url)
 
     def toclist(self, content):
         toc_re = r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h\1>'
         flat = []
         for match in re.finditer(toc_re, content, re.S):
             flat.append({
                 'level': int(match.group(1)),
                 'anchor': jinja2.Markup(match.group(2)).unescape(),
                 'title': jinja2.Markup(match.group(3)).unescape(),
                 'subitems': [],
             })
 
         structured = []
         stack = [{'level': 0, 'subitems': structured}]
         for item in flat:
             while stack[-1]['level'] >= item['level']:
                 stack.pop()
             stack[-1]['subitems'].append(item)
             stack.append(item)
         return structured
 
 converters = {
     'html': RawConverter,
     'md': MarkdownConverter,
     'tmpl': TemplateConverter,
 }