[Android WebView] Prepare the copyrights scanner to run from presubmit scripts

android_webview/tools/copyright_scanner_unittest.py

Index: android_webview/tools/copyright_scanner_unittest.py
diff --git a/android_webview/tools/copyright_scanner_unittest.py b/android_webview/tools/copyright_scanner_unittest.py
new file mode 100755
index 0000000000000000000000000000000000000000..aec0e39c3b23967e2c49bfcd84c5afc8816716a9
--- /dev/null
+++ b/android_webview/tools/copyright_scanner_unittest.py
@@ -0,0 +1,115 @@
+#!/usr/bin/env python
+# Copyright 2014 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.
+
+"""Unit tests for Copyright Scanner utilities."""
+
+import os
+import re
+import sys
+import unittest
+
+test_dir = os.path.dirname(os.path.abspath(__file__))
+sys.path.extend([
+    os.path.normpath(os.path.join(test_dir, '..', '..', 'tools')),
+    os.path.join(test_dir),
+])
+
+import find_depot_tools
+from testing_support.super_mox import SuperMoxTestBase
+
+import copyright_scanner
+
+class FindCopyrightsTest(SuperMoxTestBase):
+  def setUp(self):
+    SuperMoxTestBase.setUp(self)
+    self.input_api = self.mox.CreateMockAnything()
+    self.input_api.re = re
+    self.input_api.os_path = os.path
+    self.input_api.os_walk = os.walk
+
+  def ShouldMatchReferenceOutput(self, test_data):
+    test_data_pos = 0
+    def ReadTestData(ignore1, ignore2):
+      return test_data[test_data_pos]
+    self.input_api.ReadFile = ReadTestData
+    for test_data_pos in range(0, len(test_data), 2):
+      actual = copyright_scanner.FindCopyrights(self.input_api, '', [''])
+      self.assertEqual(
+        test_data[test_data_pos + 1],
+        actual,
+        'Input """\n%s""", expected output: "%s", actual: "%s"' % \
+            (test_data[test_data_pos], test_data[test_data_pos + 1], actual));
+
+  def testCopyrightedFiles(self):
+    test_data = [
+      '// (c) 2014 Google Inc.\n//\n//  (a) One\n//\n//  (b) Two\n//\n',

[mkosiba (inactive), 2014/10/21 15:41:22]

maybe use something like
 Expectation = collections.namedtuple('Expectation', ['input', 'expected'])
to express this data
  test_data = [
    Expectation(
      '// (c) 2014 Google Inc.\n//\n//  (a) One\n//\n//  (b) Two\n//\n',
      '2014 Google Inc.'),
    ...

or just a tuple:
  test_data = [
      ('// (c) 2014 Google Inc.\n//\n//  (a) One\n//\n//  (b) Two\n//\n',
      '2014 Google Inc.'),
    ...

[mnaganov (inactive), 2014/10/22 09:27:29]

I decided it's even simpler just to pass a single expected output to
ShouldMatchReferenceOutput. It's easy to add another test function in case when
some input has a different expected output.

+      [['2014 Google Inc.']],
+      'Copyright 2014 Google Inc.\n',
+      [['2014 Google Inc.']],
+      'Copr. 2014 Google Inc.',
+      [['2014 Google Inc.']],
+      '\xc2\xa9 2014 Google Inc.',
+      [['2014 Google Inc.']],
+      'Copyright 2014    Google  Inc.',
+      [['2014 Google Inc.']]
+    ]
+    self.ShouldMatchReferenceOutput(test_data)
+
+  def testGeneratedFiles(self):
+    test_data = [
+      'ALL CHANGES MADE IN THIS FILE WILL BE LOST\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],

[mkosiba (inactive), 2014/10/21 15:41:22]

if you had these as tuples you could use an array comprehension to remove the
duplication

test_data = ['ALL...\n', 'GEN..\n', ..]
test_data = [(data, 'GENERATED FILE') for data in test_data]
or
test_data = [Expectation(input, 'GENERATED FILE') for input in test_data]

[mnaganov (inactive), 2014/10/22 09:27:29]

See the previous comment.

+      'GENERATED FILE. DO NOT EDIT\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'GENERATED. DO NOT DELETE THIS FILE.\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'DO NOT EDIT\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'DO NOT DELETE THIS FILE\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'All changes made in this file will be lost\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'Automatically generated file\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'Synthetically generated dummy file\nCopyright 2014 Google\n',
+      [['GENERATED FILE']],
+      'Generated data (by gnugnu)\nCopyright 2014 Google\n',
+      [['GENERATED FILE']]
+    ]
+    self.ShouldMatchReferenceOutput(test_data)
+
+  def testNonCopyrightedFiles(self):
+    test_data = [
+      'std::cout << "Copyright 2014 Google"\n',
+      [['*No copyright*']],
+      '// Several points can be made:\n//\n//  (a) One\n//\n//  (b) Two\n'
+      '//\n//  (c) Three\n//\n',
+      [['*No copyright*']],
+      'See \'foo\' for copyright information.\n',
+      [['*No copyright*']],
+      'See \'foo\' for the copyright notice.\n',
+      [['*No copyright*']],
+      'See \'foo\' for the copyright and other things.\n',
+      [['*No copyright*']]
+    ]
+    self.ShouldMatchReferenceOutput(test_data)
+
+  def testNonGeneratedFiles(self):
+    test_data = [
+      'This file was prohibited from being generated.\n',
+      [['*No copyright*']],
+      'Please do not delete our files! They are valuable to us.\n',
+      [['*No copyright*']],
+      'Manually generated from dice rolls.\n',
+      [['*No copyright*']],
+      '"""This Python script produces generated data\n"""\n',
+      [['*No copyright*']],
+      '\'\'\'This Python script produces generated data\n\'\'\'\n',
+      [['*No copyright*']]
+    ]
+    self.ShouldMatchReferenceOutput(test_data)
+
+if __name__ == '__main__':
+  unittest.main()