Mitigate spoofing attempt using Latin letters.

components/url_formatter/top_domains/make_alexa_top_list.py

Index: components/url_formatter/top_domains/make_alexa_top_list.py
diff --git a/components/url_formatter/top_domains/make_alexa_top_list.py b/components/url_formatter/top_domains/make_alexa_top_list.py
new file mode 100755
index 0000000000000000000000000000000000000000..54b586ca421c0ab66ed97b1b89e7b44475360337
--- /dev/null
+++ b/components/url_formatter/top_domains/make_alexa_top_list.py
@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+# Copyright 2017 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.
+
+"""Generates alexa_domains.list from
+   src/tools/perf/page_sets/alexa1-10000-urls.json.  By default, all the domains
+   extracted from the input will be recorded in alexa_domains.list in the script
+   directory except for duplicates and domains in ccTLDs known to disallow
+   non-ASCII Latin letters (cn,jp,kr,tw).
+   Optional command line arguments can be used to limit the output to top N
+   domains and to specify an output file.
+"""
+
+import re
+import sys
+import os
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+alexa10k_path = os.path.join(script_dir, "..", "..", "..", "tools", "perf",
+                              "page_sets", "alexa1-10000-urls.json")
+max_num_domains = 10000 if len(sys.argv) < 2 else int(sys.argv[1])
+alexa_out = os.path.join(script_dir, "alexa_domains.list") \
+    if len(sys.argv) < 3 else os.path.join(script_dir, sys.argv[2])
+
+domain_extractor = re.compile(r'^.*"https?://(?:www.)?([^/]*)/.*$')
+excluded_tld = re.compile(r'.(cn|kr|jp|tw)$')
+domains = set()
+n_domains = 0
+
+with open(alexa_out, 'w') as outfile, open(alexa10k_path, 'r') as infile:
+  for line in infile:
+    if line.startswith('#'):
+      continue
+    match = domain_extractor.match(line)
+    if match and n_domains < max_num_domains:
+      n_domains = n_domains + 1
+      domain = match.group(1)
+      labels = domain.split('.')
+      if len(labels) > 3:
+        domain = '.'.join(labels[-3:])
+      if not excluded_tld.search(match.group(1)) and domain not in domains:
+        domains.add(domain)
+        outfile.write(domain + "\n")
+
+  # Add some popular domains if they're missing.

[Peter Kasting, 2017/05/10 22:38:47]

Nit: Maybe link to a bug on getting a process in place whereby we have an
updated list?

[jungshik at Google, 2017/05/14 09:36:23]

https://bugs.chromium.org/p/chromium/issues/detail?id=722022

+  for domain in ["gmail.com", "hotmail.com", "360.cn", "ntd.tv", "onclkds.com",
+                 "uber.com", "lyft.com"]:
+    if domain not in domains:
+      outfile.write(domain + "\n")
+
+  # Add a few made-up domains for testing.
+  outfile.write("# for testing\ndigklmo68.com\ndigklmo68.co.uk\n")
+  outfile.write("islkpx123.com\n")