Extensions Docs Server: Samples zip files

chrome/common/extensions/docs/server2/subversion_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.
+
+import re
+
+class SubversionDataSource(object):

[not at google - send to devlin, 2012/07/11 00:35:09]

How about just putting a list-files method on the Fetcher interface, not having
this class at all.

[cduvall, 2012/07/11 20:56:30]

Done.

+  """This class gets files and lists directories from subversion.
+  """
+  def __init__(self, cache_builder, base_path, ignore_path):
+    self._dir_cache = cache_builder.build(self._ListFilesInDirectory)
+    self._file_cache = cache_builder.build(lambda x: x)
+    self._base_path = base_path
+    self._ignore_path = ignore_path
+
+  def _GetDirFromPage(self, page):
+    page_dir = re.search('<title>.* (.*)</title>', page).group(1)

[not at google - send to devlin, 2012/07/11 00:35:09]

Could we try using an HTML parser here rather than regular expressions? Regex is
inefficient and hard to maintain, and looks kind of awkward.

[Aaron Boodman, 2012/07/11 02:54:51]

The directory listing page looks like valid xml to me. If so, you can just do
that. If not, there's BeautifulSoup.

[not at google - send to devlin, 2012/07/11 07:23:58]

I think there's actually an HTML parser in python?
http://docs.python.org/library/htmlparser.html is BeautifulSoup better or
something?

Anyway, cool if it's valid XML.

It might be worth quickly looking to see whether you can make svn just return
the file list (like svn ls does) then this wouldn't be necessary at all.

+    if self._ignore_path:
+      page_dir = page_dir.split(self._ignore_path)[-1]
+    return page_dir
+
+  def _GetFilesFromPage(self, page):
+    dir_contents = re.findall('<a.*>(.*)</a>', page)
+    if '..' in dir_contents:
+      dir_contents.remove('..')
+    return dir_contents
+
+  def _ListFilesInDirectory(self, directory, add_dir=False):
+    dir_contents = self._GetFilesFromPage(directory)
+    file_list = filter(lambda x: not x.endswith('/'), dir_contents)
+    for file_name in dir_contents:
+      if file_name.endswith('/'):
+        par_dir = self._GetDirFromPage(directory)
+        next_dir = par_dir + '/' + file_name
+        # Add the full path to each file.
+        file_list.extend(map(lambda x: file_name + x,
+                         self._dir_cache.get(self._base_path + '/' + next_dir)))
+    if add_dir:
+      par_dir = self._GetDirFromPage(directory)
+      return map(lambda x: par_dir + '/' + x, file_list)
+    return file_list