Extensions Docs Server: Large performance increase

chrome/common/extensions/docs/server2/intro_data_source.py

 # Copyright (c) 2012 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 from HTMLParser import HTMLParser
-import logging
 import re
 
 from docs_server_utils import FormatKey
 from file_system import FileNotFoundError
+import file_system_cache as fs_cache
 from third_party.handlebar import Handlebar
 
+_intro_regex = re.compile('<h1[^>.]*?>.*?</h1>', flags=re.DOTALL)

[not at google - send to devlin, 2012/08/21 00:30:11]

should be _INTRO_REGEX

or _H1_REGEX

[cduvall, 2012/08/21 01:33:33]

Done.

+
 class _IntroParser(HTMLParser):
   """ An HTML parser which will parse table of contents and page title info out
   of an intro.
   """
   def __init__(self):
     HTMLParser.__init__(self)
     self.toc = []
     self.page_title = None
     self._recent_tag = None
     self._current_heading = {}
@@ skipping 23 matching lines @@
       return
     if self._recent_tag == 'h1':
       if self.page_title is None:
         self.page_title = data
       else:
         self.page_title += data
     elif self._recent_tag in ['h2', 'h3']:
       self._current_heading['title'] += data
 
 class IntroDataSource(object):
+
+  class Factory(object):
+    def __init__(self, cache_builder, base_paths):
+      self._cache = cache_builder.build(self._MakeIntroDict,
+                                        fs_cache.INTRO)
+      self._base_paths = base_paths
+
+    def _MakeIntroDict(self, intro):
+      parser = _IntroParser()
+      parser.feed(intro)
+      intro = re.sub(_intro_regex, '', intro, count=1)
+      return {
+        'intro': Handlebar(intro),
+        'toc': parser.toc,
+        'title': parser.page_title
+      }
+
+    def Create(self):
+      return IntroDataSource(self._cache, self._base_paths)
+
   """This class fetches the intros for a given API. From this intro, a table
   of contents dictionary is created, which contains the headings in the intro.
   """
-  def __init__(self, cache_builder, base_paths):
-    self._cache = cache_builder.build(self._MakeIntroDict)
+  def __init__(self, cache, base_paths):
+    self._cache = cache
     self._base_paths = base_paths
-    self._intro_regex = re.compile('<h1[^>.]*?>.*?</h1>', flags=re.DOTALL)
-
-  def _MakeIntroDict(self, intro):
-    parser = _IntroParser()
-    parser.feed(intro)
-    intro = re.sub(self._intro_regex, '', intro, count=1)
-    return {
-      'intro': Handlebar(intro),
-      'toc': parser.toc,
-      'title': parser.page_title
-    }
 
   def __getitem__(self, key):
     return self.get(key)
 
   def get(self, key):
     real_path = FormatKey(key)
     error = None
     for base_path in self._base_paths:
       try:
         return self._cache.GetFromFile(base_path + '/' + real_path)
       except FileNotFoundError as error:
         pass
     raise ValueError(str(error) + ': No intro found for "%s".' % key)