OLD | NEW |
(Empty) | |
| 1 # Copyright 2016 The Chromium Authors. All rights reserved. |
| 2 # Use of this source code is govered by a BSD-style |
| 3 # license that can be found in the LICENSE file or at |
| 4 # https://developers.google.com/open-source/licenses/bsd |
| 5 |
| 6 """Tests for the filecontent module.""" |
| 7 |
| 8 import unittest |
| 9 |
| 10 from framework import filecontent |
| 11 |
| 12 |
| 13 class MimeTest(unittest.TestCase): |
| 14 """Test methods for the mime module.""" |
| 15 |
| 16 _TEST_EXTENSIONS_TO_CTYPES = { |
| 17 'html': 'text/plain', |
| 18 'htm': 'text/plain', |
| 19 'jpg': 'image/jpeg', |
| 20 'jpeg': 'image/jpeg', |
| 21 'pdf': 'application/pdf', |
| 22 } |
| 23 |
| 24 _CODE_EXTENSIONS = [ |
| 25 'py', 'java', 'mf', 'bat', 'sh', 'php', 'vb', 'pl', 'sql', |
| 26 ] |
| 27 |
| 28 def testCommonExtensions(self): |
| 29 """Tests some common extensions for their expected content types.""" |
| 30 for ext, ctype in self._TEST_EXTENSIONS_TO_CTYPES.iteritems(): |
| 31 self.assertEqual( |
| 32 filecontent.GuessContentTypeFromFilename('file.%s' % ext), |
| 33 ctype) |
| 34 |
| 35 def testCaseDoesNotMatter(self): |
| 36 """Ensure that case (upper/lower) of extension does not matter.""" |
| 37 for ext, ctype in self._TEST_EXTENSIONS_TO_CTYPES.iteritems(): |
| 38 ext = ext.upper() |
| 39 self.assertEqual( |
| 40 filecontent.GuessContentTypeFromFilename('file.%s' % ext), |
| 41 ctype) |
| 42 |
| 43 for ext in self._CODE_EXTENSIONS: |
| 44 ext = ext.upper() |
| 45 self.assertEqual( |
| 46 filecontent.GuessContentTypeFromFilename('code.%s' % ext), |
| 47 'text/plain') |
| 48 |
| 49 def testCodeIsText(self): |
| 50 """Ensure that code extensions are text/plain.""" |
| 51 for ext in self._CODE_EXTENSIONS: |
| 52 self.assertEqual( |
| 53 filecontent.GuessContentTypeFromFilename('code.%s' % ext), |
| 54 'text/plain') |
| 55 |
| 56 def testNoExtensionIsText(self): |
| 57 """Ensure that no extension indicates text/plain.""" |
| 58 self.assertEqual( |
| 59 filecontent.GuessContentTypeFromFilename('noextension'), |
| 60 'text/plain') |
| 61 |
| 62 def testUnknownExtension(self): |
| 63 """Ensure that an obviously unknown extension returns is binary.""" |
| 64 self.assertEqual( |
| 65 filecontent.GuessContentTypeFromFilename('f.madeupextension'), |
| 66 'application/octet-stream') |
| 67 |
| 68 def testNoShockwaveFlash(self): |
| 69 """Ensure that Shockwave files will NOT be served w/ that content type.""" |
| 70 self.assertEqual( |
| 71 filecontent.GuessContentTypeFromFilename('bad.swf'), |
| 72 'application/octet-stream') |
| 73 |
| 74 |
| 75 class DecodeFileContentsTest(unittest.TestCase): |
| 76 |
| 77 def IsBinary(self, contents): |
| 78 _contents, is_binary, _is_long = ( |
| 79 filecontent.DecodeFileContents(contents)) |
| 80 return is_binary |
| 81 |
| 82 def testFileIsBinaryEmpty(self): |
| 83 self.assertFalse(self.IsBinary('')) |
| 84 |
| 85 def testFileIsBinaryShortText(self): |
| 86 self.assertFalse(self.IsBinary('This is some plain text.')) |
| 87 |
| 88 def testLineLengthDetection(self): |
| 89 unicode_str = ( |
| 90 u'Some non-ascii chars - ' |
| 91 u'\xa2\xfa\xb6\xe7\xfc\xea\xd0\xf4\xe6\xf0\xce\xf6\xbe') |
| 92 short_line = unicode_str.encode('iso-8859-1') |
| 93 long_line = (unicode_str * 100)[:filecontent._MAX_SOURCE_LINE_LEN_LOWER+1] |
| 94 long_line = long_line.encode('iso-8859-1') |
| 95 |
| 96 lines = [short_line] * 100 |
| 97 lines.append(long_line) |
| 98 |
| 99 # High lower ratio - text |
| 100 self.assertFalse(self.IsBinary('\n'.join(lines))) |
| 101 |
| 102 lines.extend([long_line] * 99) |
| 103 |
| 104 # 50/50 lower/upper ratio - binary |
| 105 self.assertTrue(self.IsBinary('\n'.join(lines))) |
| 106 |
| 107 # Single line too long - binary |
| 108 lines = [short_line] * 100 |
| 109 lines.append(short_line * 100) # Very long line |
| 110 self.assertTrue(self.IsBinary('\n'.join(lines))) |
| 111 |
| 112 def testFileIsBinaryLongText(self): |
| 113 self.assertFalse(self.IsBinary('This is plain text. \n' * 100)) |
| 114 # long utf-8 lines are OK |
| 115 self.assertFalse(self.IsBinary('This one long line. ' * 100)) |
| 116 |
| 117 def testFileIsBinaryLongBinary(self): |
| 118 bin_string = ''.join([chr(c) for c in range(122, 252)]) |
| 119 self.assertTrue(self.IsBinary(bin_string * 100)) |
| 120 |
| 121 def testFileIsTextByPath(self): |
| 122 bin_string = ''.join([chr(c) for c in range(122, 252)] * 100) |
| 123 unicode_str = ( |
| 124 u'Some non-ascii chars - ' |
| 125 u'\xa2\xfa\xb6\xe7\xfc\xea\xd0\xf4\xe6\xf0\xce\xf6\xbe') |
| 126 long_line = (unicode_str * 100)[:filecontent._MAX_SOURCE_LINE_LEN_LOWER+1] |
| 127 long_line = long_line.encode('iso-8859-1') |
| 128 |
| 129 for contents in [bin_string, long_line]: |
| 130 self.assertTrue(filecontent.DecodeFileContents(contents, path=None)[1]) |
| 131 self.assertTrue(filecontent.DecodeFileContents(contents, path='')[1]) |
| 132 self.assertTrue(filecontent.DecodeFileContents(contents, path='foo')[1]) |
| 133 self.assertTrue( |
| 134 filecontent.DecodeFileContents(contents, path='foo.bin')[1]) |
| 135 self.assertTrue( |
| 136 filecontent.DecodeFileContents(contents, path='foo.zzz')[1]) |
| 137 for path in ['a/b/Makefile.in', 'README', 'a/file.js', 'b.txt']: |
| 138 self.assertFalse( |
| 139 filecontent.DecodeFileContents(contents, path=path)[1]) |
| 140 |
| 141 def testFileIsBinaryByCommonExtensions(self): |
| 142 contents = 'this is not examined' |
| 143 self.assertTrue(filecontent.DecodeFileContents( |
| 144 contents, path='junk.zip')[1]) |
| 145 self.assertTrue(filecontent.DecodeFileContents( |
| 146 contents, path='JUNK.ZIP')[1]) |
| 147 self.assertTrue(filecontent.DecodeFileContents( |
| 148 contents, path='/build/HelloWorld.o')[1]) |
| 149 self.assertTrue(filecontent.DecodeFileContents( |
| 150 contents, path='/build/Hello.class')[1]) |
| 151 self.assertTrue(filecontent.DecodeFileContents( |
| 152 contents, path='/trunk/libs.old/swing.jar')[1]) |
| 153 |
| 154 self.assertFalse(filecontent.DecodeFileContents( |
| 155 contents, path='HelloWorld.cc')[1]) |
| 156 self.assertFalse(filecontent.DecodeFileContents( |
| 157 contents, path='Hello.java')[1]) |
| 158 self.assertFalse(filecontent.DecodeFileContents( |
| 159 contents, path='README')[1]) |
| 160 self.assertFalse(filecontent.DecodeFileContents( |
| 161 contents, path='READ.ME')[1]) |
| 162 self.assertFalse(filecontent.DecodeFileContents( |
| 163 contents, path='README.txt')[1]) |
| 164 self.assertFalse(filecontent.DecodeFileContents( |
| 165 contents, path='README.TXT')[1]) |
| 166 self.assertFalse(filecontent.DecodeFileContents( |
| 167 contents, path='/trunk/src/com/monorail/Hello.java')[1]) |
| 168 self.assertFalse(filecontent.DecodeFileContents( |
| 169 contents, path='/branches/1.2/resource.el')[1]) |
| 170 self.assertFalse(filecontent.DecodeFileContents( |
| 171 contents, path='/wiki/PageName.wiki')[1]) |
| 172 |
| 173 def testUnreasonablyLongFile(self): |
| 174 contents = '\n' * (filecontent.SOURCE_FILE_MAX_LINES + 2) |
| 175 _contents, is_binary, is_long = filecontent.DecodeFileContents( |
| 176 contents) |
| 177 self.assertFalse(is_binary) |
| 178 self.assertTrue(is_long) |
| 179 |
| 180 contents = '\n' * 100 |
| 181 _contents, is_binary, is_long = filecontent.DecodeFileContents( |
| 182 contents) |
| 183 self.assertFalse(is_binary) |
| 184 self.assertFalse(is_long) |
| 185 |
| 186 |
| 187 if __name__ == '__main__': |
| 188 unittest.main() |
OLD | NEW |