Support Google Chrome Bookmark files.

doc/changelog.txt

@@ -14,6 +14,7 @@ Changes:
 Features:
 - gui: Preselect filename on save dialog when editing file:// URLs.
   Closes: SF bug #3176022
+- checking: Added support for Google Chrome bookmark files.
 
 
 6.3 "Due Date" (released 6.2.2011)

linkcheck/bookmarks/chromium.py

@@ -0,0 +1,53 @@
+# -*- coding: iso-8859-1 -*-
+# Copyright (C) 2011 Bastian Kleineidam
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program 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
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+import json
+
+
+def parse_bookmarks_data (data):
+    """Parse data string.
+    Return iterator for bookmarks of the form (url, name).
+    Bookmarks are not sorted.
+    """
+    for url, name in parse_bookmarks_json(json.loads(data)):
+        yield url, name
+
+
+def parse_bookmarks_file (file):
+    """Parse file object.
+    Return iterator for bookmarks of the form (url, name).
+    Bookmarks are not sorted.
+    """
+    for url, name in parse_bookmarks_json(json.load(file)):
+        yield url, name
+
+
+def parse_bookmarks_json (data):
+    """Parse complete JSON data for Chromium Bookmarks."""
+    for entry in data["roots"].values():
+        for entry in parse_bookmarks_node(entry):
+            yield entry
+
+
+def parse_bookmarks_node (node):
+    """Parse one JSON node of Chromium Bookmarks."""
+    if node["type"] == "url":
+        yield node["url"], node["name"]
+    elif node["type"] == "folder":
+        for child in node["children"]:
+            for entry in parse_bookmarks_node(child):
+                yield entry

linkcheck/checker/urlbase.py

@@ -86,6 +86,7 @@ class UrlBase (object):
         "application/msword": "word",
         "text/plain+linkchecker": "text",
         "text/plain+opera": "opera",
+        "text/plain+chromium": "chromium",
     }
 
     def __init__ (self, base_url, recursion_level, aggregate,
@@ -930,6 +931,15 @@ class UrlBase (object):
                self.aggregate, parent_url=self.url, line=lineno, name=name)
             self.aggregate.urlqueue.put(url_data)
 
+    def parse_chromium (self):
+        """Parse a Google Chrome bookmark file."""
+        log.debug(LOG_CHECK, "Parsing Chromium bookmarks %s", self)
+        from ..bookmarks.chromium import parse_bookmarks_data
+        for url, name in parse_bookmarks_data(self.get_content()):
+            url_data = get_url_from(url, self.recursion_level+1,
+               self.aggregate, parent_url=self.url, name=name)
+            self.aggregate.urlqueue.put(url_data)
+
     def parse_text (self):
         """
         Parse a text file with on url per line; comment and blank

linkcheck/fileutil.py

@@ -184,6 +184,7 @@ mimedb = mimetypes.MimeTypes(strict=False)
 PARSE_CONTENTS = {
     "text/html": re.compile(r'^(?i)<(!DOCTYPE html|html|head|title)'),
     "text/plain+opera": re.compile(r'^Opera Hotlist'),
+    "text/plain+chromium": re.compile(r'^{\s*"checksum":'),
     "text/plain+linkchecker": re.compile(r'(?i)^# LinkChecker URL list'),
 }
 

tests/checker/data/Bookmarks

@@ -0,0 +1,28 @@
+{
+   "checksum": "b1135bffd7fb303459b60851e3f800eb",
+   "roots": {
+      "bookmark_bar": {
+         "children": [ {
+            "date_added": "12942261620096544",
+            "id": "3",
+            "name": "Testlink",
+            "type": "url",
+            "url": "http://example.com/"
+         } ],
+         "date_added": "0",
+         "date_modified": "12942261620096544",
+         "id": "1",
+         "name": "Bookmarks Bar",
+         "type": "folder"
+      },
+      "other": {
+         "children": [  ],
+         "date_added": "0",
+         "date_modified": "0",
+         "id": "2",
+         "name": "Other Bookmarks",
+         "type": "folder"
+      }
+   },
+   "version": 1
+}

tests/checker/data/Bookmarks.result

@@ -0,0 +1,12 @@
+url file://%(curdir)s/%(datadir)s/Bookmarks
+cache key file://%(curdir)s/%(datadir)s/Bookmarks
+real url file://%(curdir)s/%(datadir)s/Bookmarks
+name %(datadir)s/Bookmarks
+valid
+
+url http://example.com/
+cache key http://example.com/
+real url http://www.iana.org/domains/example/
+name Testlink
+info Redirected to `http://www.iana.org/domains/example/'.
+valid

tests/checker/test_file.py

@@ -69,6 +69,10 @@ class TestFile (LinkCheckTest):
         # Opera bookmark file parsing
         self.file_test("opera6.adr")
 
+    def test_chromium_bookmarks (self):
+        # Google Chrome bookmark file parsing
+        self.file_test("Bookmarks")
+
     def test_directory_listing (self):
         # unpack non-unicode filename which cannot be stored
         # in the SF subversion repository