Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 1 | import _testcapi |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2 | import codecs |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 3 | import io |
Antoine Pitrou | cf9d3c0 | 2011-07-24 02:27:04 +0200 | [diff] [blame] | 4 | import locale |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 5 | import sys |
| 6 | import unittest |
| 7 | import warnings |
| 8 | |
| 9 | from test import support |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 10 | |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 11 | if sys.platform == 'win32': |
| 12 | VISTA_OR_LATER = (sys.getwindowsversion().major >= 6) |
| 13 | else: |
| 14 | VISTA_OR_LATER = False |
| 15 | |
Antoine Pitrou | 00b2c86 | 2011-10-05 13:01:41 +0200 | [diff] [blame] | 16 | try: |
| 17 | import ctypes |
| 18 | except ImportError: |
| 19 | ctypes = None |
| 20 | SIZEOF_WCHAR_T = -1 |
| 21 | else: |
| 22 | SIZEOF_WCHAR_T = ctypes.sizeof(ctypes.c_wchar) |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 23 | |
Serhiy Storchaka | d679377 | 2013-01-29 10:20:44 +0200 | [diff] [blame] | 24 | def coding_checker(self, coder): |
| 25 | def check(input, expect): |
| 26 | self.assertEqual(coder(input), (expect, len(input))) |
| 27 | return check |
| 28 | |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 29 | class Queue(object): |
| 30 | """ |
| 31 | queue: write bytes at one end, read bytes from the other end |
| 32 | """ |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 33 | def __init__(self, buffer): |
| 34 | self._buffer = buffer |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 35 | |
| 36 | def write(self, chars): |
| 37 | self._buffer += chars |
| 38 | |
| 39 | def read(self, size=-1): |
| 40 | if size<0: |
| 41 | s = self._buffer |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 42 | self._buffer = self._buffer[:0] # make empty |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 43 | return s |
| 44 | else: |
| 45 | s = self._buffer[:size] |
| 46 | self._buffer = self._buffer[size:] |
| 47 | return s |
| 48 | |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 49 | class MixInCheckStateHandling: |
| 50 | def check_state_handling_decode(self, encoding, u, s): |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 51 | for i in range(len(s)+1): |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 52 | d = codecs.getincrementaldecoder(encoding)() |
| 53 | part1 = d.decode(s[:i]) |
| 54 | state = d.getstate() |
Ezio Melotti | e961593 | 2010-01-24 19:26:24 +0000 | [diff] [blame] | 55 | self.assertIsInstance(state[1], int) |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 56 | # Check that the condition stated in the documentation for |
| 57 | # IncrementalDecoder.getstate() holds |
| 58 | if not state[1]: |
| 59 | # reset decoder to the default state without anything buffered |
| 60 | d.setstate((state[0][:0], 0)) |
| 61 | # Feeding the previous input may not produce any output |
Benjamin Peterson | c9c0f20 | 2009-06-30 23:06:06 +0000 | [diff] [blame] | 62 | self.assertTrue(not d.decode(state[0])) |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 63 | # The decoder must return to the same state |
| 64 | self.assertEqual(state, d.getstate()) |
| 65 | # Create a new decoder and set it to the state |
| 66 | # we extracted from the old one |
| 67 | d = codecs.getincrementaldecoder(encoding)() |
| 68 | d.setstate(state) |
| 69 | part2 = d.decode(s[i:], True) |
| 70 | self.assertEqual(u, part1+part2) |
| 71 | |
| 72 | def check_state_handling_encode(self, encoding, u, s): |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 73 | for i in range(len(u)+1): |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 74 | d = codecs.getincrementalencoder(encoding)() |
| 75 | part1 = d.encode(u[:i]) |
| 76 | state = d.getstate() |
| 77 | d = codecs.getincrementalencoder(encoding)() |
| 78 | d.setstate(state) |
| 79 | part2 = d.encode(u[i:], True) |
| 80 | self.assertEqual(s, part1+part2) |
| 81 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 82 | class ReadTest(MixInCheckStateHandling): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 83 | def check_partial(self, input, partialresults): |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 84 | # get a StreamReader for the encoding and feed the bytestring version |
Guido van Rossum | 87c0f1d | 2007-11-19 18:03:44 +0000 | [diff] [blame] | 85 | # of input to the reader byte by byte. Read everything available from |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 86 | # the StreamReader and check that the results equal the appropriate |
| 87 | # entries from partialresults. |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 88 | q = Queue(b"") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 89 | r = codecs.getreader(self.encoding)(q) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 90 | result = "" |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 91 | for (c, partialresult) in zip(input.encode(self.encoding), partialresults): |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 92 | q.write(bytes([c])) |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 93 | result += r.read() |
| 94 | self.assertEqual(result, partialresult) |
| 95 | # check that there's nothing left in the buffers |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 96 | self.assertEqual(r.read(), "") |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 97 | self.assertEqual(r.bytebuffer, b"") |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 98 | |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 99 | # do the check again, this time using a incremental decoder |
| 100 | d = codecs.getincrementaldecoder(self.encoding)() |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 101 | result = "" |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 102 | for (c, partialresult) in zip(input.encode(self.encoding), partialresults): |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 103 | result += d.decode(bytes([c])) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 104 | self.assertEqual(result, partialresult) |
| 105 | # check that there's nothing left in the buffers |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 106 | self.assertEqual(d.decode(b"", True), "") |
| 107 | self.assertEqual(d.buffer, b"") |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 108 | |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 109 | # Check whether the reset method works properly |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 110 | d.reset() |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 111 | result = "" |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 112 | for (c, partialresult) in zip(input.encode(self.encoding), partialresults): |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 113 | result += d.decode(bytes([c])) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 114 | self.assertEqual(result, partialresult) |
| 115 | # check that there's nothing left in the buffers |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 116 | self.assertEqual(d.decode(b"", True), "") |
| 117 | self.assertEqual(d.buffer, b"") |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 118 | |
| 119 | # check iterdecode() |
| 120 | encoded = input.encode(self.encoding) |
| 121 | self.assertEqual( |
| 122 | input, |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 123 | "".join(codecs.iterdecode([bytes([c]) for c in encoded], self.encoding)) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 124 | ) |
| 125 | |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 126 | def test_readline(self): |
| 127 | def getreader(input): |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 128 | stream = io.BytesIO(input.encode(self.encoding)) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 129 | return codecs.getreader(self.encoding)(stream) |
| 130 | |
Walter Dörwald | ca19943 | 2006-03-06 22:39:12 +0000 | [diff] [blame] | 131 | def readalllines(input, keepends=True, size=None): |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 132 | reader = getreader(input) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 133 | lines = [] |
| 134 | while True: |
Walter Dörwald | ca19943 | 2006-03-06 22:39:12 +0000 | [diff] [blame] | 135 | line = reader.readline(size=size, keepends=keepends) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 136 | if not line: |
| 137 | break |
| 138 | lines.append(line) |
Walter Dörwald | ca19943 | 2006-03-06 22:39:12 +0000 | [diff] [blame] | 139 | return "|".join(lines) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 140 | |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 141 | s = "foo\nbar\r\nbaz\rspam\u2028eggs" |
| 142 | sexpected = "foo\n|bar\r\n|baz\r|spam\u2028|eggs" |
| 143 | sexpectednoends = "foo|bar|baz|spam|eggs" |
Walter Dörwald | ca19943 | 2006-03-06 22:39:12 +0000 | [diff] [blame] | 144 | self.assertEqual(readalllines(s, True), sexpected) |
| 145 | self.assertEqual(readalllines(s, False), sexpectednoends) |
| 146 | self.assertEqual(readalllines(s, True, 10), sexpected) |
| 147 | self.assertEqual(readalllines(s, False, 10), sexpectednoends) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 148 | |
| 149 | # Test long lines (multiple calls to read() in readline()) |
| 150 | vw = [] |
| 151 | vwo = [] |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 152 | for (i, lineend) in enumerate("\n \r\n \r \u2028".split()): |
| 153 | vw.append((i*200)*"\3042" + lineend) |
| 154 | vwo.append((i*200)*"\3042") |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 155 | self.assertEqual(readalllines("".join(vw), True), "".join(vw)) |
| 156 | self.assertEqual(readalllines("".join(vw), False),"".join(vwo)) |
| 157 | |
| 158 | # Test lines where the first read might end with \r, so the |
| 159 | # reader has to look ahead whether this is a lone \r or a \r\n |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 160 | for size in range(80): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 161 | for lineend in "\n \r\n \r \u2028".split(): |
| 162 | s = 10*(size*"a" + lineend + "xxx\n") |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 163 | reader = getreader(s) |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 164 | for i in range(10): |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 165 | self.assertEqual( |
| 166 | reader.readline(keepends=True), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 167 | size*"a" + lineend, |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 168 | ) |
| 169 | reader = getreader(s) |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 170 | for i in range(10): |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 171 | self.assertEqual( |
| 172 | reader.readline(keepends=False), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 173 | size*"a", |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 174 | ) |
| 175 | |
| 176 | def test_bug1175396(self): |
| 177 | s = [ |
| 178 | '<%!--===================================================\r\n', |
| 179 | ' BLOG index page: show recent articles,\r\n', |
| 180 | ' today\'s articles, or articles of a specific date.\r\n', |
| 181 | '========================================================--%>\r\n', |
| 182 | '<%@inputencoding="ISO-8859-1"%>\r\n', |
| 183 | '<%@pagetemplate=TEMPLATE.y%>\r\n', |
| 184 | '<%@import=import frog.util, frog%>\r\n', |
| 185 | '<%@import=import frog.objects%>\r\n', |
| 186 | '<%@import=from frog.storageerrors import StorageError%>\r\n', |
| 187 | '<%\r\n', |
| 188 | '\r\n', |
| 189 | 'import logging\r\n', |
| 190 | 'log=logging.getLogger("Snakelets.logger")\r\n', |
| 191 | '\r\n', |
| 192 | '\r\n', |
| 193 | 'user=self.SessionCtx.user\r\n', |
| 194 | 'storageEngine=self.SessionCtx.storageEngine\r\n', |
| 195 | '\r\n', |
| 196 | '\r\n', |
| 197 | 'def readArticlesFromDate(date, count=None):\r\n', |
| 198 | ' entryids=storageEngine.listBlogEntries(date)\r\n', |
| 199 | ' entryids.reverse() # descending\r\n', |
| 200 | ' if count:\r\n', |
| 201 | ' entryids=entryids[:count]\r\n', |
| 202 | ' try:\r\n', |
| 203 | ' return [ frog.objects.BlogEntry.load(storageEngine, date, Id) for Id in entryids ]\r\n', |
| 204 | ' except StorageError,x:\r\n', |
| 205 | ' log.error("Error loading articles: "+str(x))\r\n', |
| 206 | ' self.abort("cannot load articles")\r\n', |
| 207 | '\r\n', |
| 208 | 'showdate=None\r\n', |
| 209 | '\r\n', |
| 210 | 'arg=self.Request.getArg()\r\n', |
| 211 | 'if arg=="today":\r\n', |
| 212 | ' #-------------------- TODAY\'S ARTICLES\r\n', |
| 213 | ' self.write("<h2>Today\'s articles</h2>")\r\n', |
| 214 | ' showdate = frog.util.isodatestr() \r\n', |
| 215 | ' entries = readArticlesFromDate(showdate)\r\n', |
| 216 | 'elif arg=="active":\r\n', |
| 217 | ' #-------------------- ACTIVE ARTICLES redirect\r\n', |
| 218 | ' self.Yredirect("active.y")\r\n', |
| 219 | 'elif arg=="login":\r\n', |
| 220 | ' #-------------------- LOGIN PAGE redirect\r\n', |
| 221 | ' self.Yredirect("login.y")\r\n', |
| 222 | 'elif arg=="date":\r\n', |
| 223 | ' #-------------------- ARTICLES OF A SPECIFIC DATE\r\n', |
| 224 | ' showdate = self.Request.getParameter("date")\r\n', |
| 225 | ' self.write("<h2>Articles written on %s</h2>"% frog.util.mediumdatestr(showdate))\r\n', |
| 226 | ' entries = readArticlesFromDate(showdate)\r\n', |
| 227 | 'else:\r\n', |
| 228 | ' #-------------------- RECENT ARTICLES\r\n', |
| 229 | ' self.write("<h2>Recent articles</h2>")\r\n', |
| 230 | ' dates=storageEngine.listBlogEntryDates()\r\n', |
| 231 | ' if dates:\r\n', |
| 232 | ' entries=[]\r\n', |
| 233 | ' SHOWAMOUNT=10\r\n', |
| 234 | ' for showdate in dates:\r\n', |
| 235 | ' entries.extend( readArticlesFromDate(showdate, SHOWAMOUNT-len(entries)) )\r\n', |
| 236 | ' if len(entries)>=SHOWAMOUNT:\r\n', |
| 237 | ' break\r\n', |
| 238 | ' \r\n', |
| 239 | ] |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 240 | stream = io.BytesIO("".join(s).encode(self.encoding)) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 241 | reader = codecs.getreader(self.encoding)(stream) |
Walter Dörwald | 7a6dc13 | 2005-04-04 21:38:47 +0000 | [diff] [blame] | 242 | for (i, line) in enumerate(reader): |
| 243 | self.assertEqual(line, s[i]) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 244 | |
| 245 | def test_readlinequeue(self): |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 246 | q = Queue(b"") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 247 | writer = codecs.getwriter(self.encoding)(q) |
| 248 | reader = codecs.getreader(self.encoding)(q) |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 249 | |
| 250 | # No lineends |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 251 | writer.write("foo\r") |
| 252 | self.assertEqual(reader.readline(keepends=False), "foo") |
| 253 | writer.write("\nbar\r") |
| 254 | self.assertEqual(reader.readline(keepends=False), "") |
| 255 | self.assertEqual(reader.readline(keepends=False), "bar") |
| 256 | writer.write("baz") |
| 257 | self.assertEqual(reader.readline(keepends=False), "baz") |
| 258 | self.assertEqual(reader.readline(keepends=False), "") |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 259 | |
| 260 | # Lineends |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 261 | writer.write("foo\r") |
| 262 | self.assertEqual(reader.readline(keepends=True), "foo\r") |
| 263 | writer.write("\nbar\r") |
| 264 | self.assertEqual(reader.readline(keepends=True), "\n") |
| 265 | self.assertEqual(reader.readline(keepends=True), "bar\r") |
| 266 | writer.write("baz") |
| 267 | self.assertEqual(reader.readline(keepends=True), "baz") |
| 268 | self.assertEqual(reader.readline(keepends=True), "") |
| 269 | writer.write("foo\r\n") |
| 270 | self.assertEqual(reader.readline(keepends=True), "foo\r\n") |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 271 | |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 272 | def test_bug1098990_a(self): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 273 | s1 = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy\r\n" |
| 274 | s2 = "offending line: ladfj askldfj klasdj fskla dfzaskdj fasklfj laskd fjasklfzzzzaa%whereisthis!!!\r\n" |
| 275 | s3 = "next line.\r\n" |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 276 | |
| 277 | s = (s1+s2+s3).encode(self.encoding) |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 278 | stream = io.BytesIO(s) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 279 | reader = codecs.getreader(self.encoding)(stream) |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 280 | self.assertEqual(reader.readline(), s1) |
| 281 | self.assertEqual(reader.readline(), s2) |
| 282 | self.assertEqual(reader.readline(), s3) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 283 | self.assertEqual(reader.readline(), "") |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 284 | |
| 285 | def test_bug1098990_b(self): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 286 | s1 = "aaaaaaaaaaaaaaaaaaaaaaaa\r\n" |
| 287 | s2 = "bbbbbbbbbbbbbbbbbbbbbbbb\r\n" |
| 288 | s3 = "stillokay:bbbbxx\r\n" |
| 289 | s4 = "broken!!!!badbad\r\n" |
| 290 | s5 = "againokay.\r\n" |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 291 | |
| 292 | s = (s1+s2+s3+s4+s5).encode(self.encoding) |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 293 | stream = io.BytesIO(s) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 294 | reader = codecs.getreader(self.encoding)(stream) |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 295 | self.assertEqual(reader.readline(), s1) |
| 296 | self.assertEqual(reader.readline(), s2) |
| 297 | self.assertEqual(reader.readline(), s3) |
| 298 | self.assertEqual(reader.readline(), s4) |
| 299 | self.assertEqual(reader.readline(), s5) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 300 | self.assertEqual(reader.readline(), "") |
Walter Dörwald | 9fa0946 | 2005-01-10 12:01:39 +0000 | [diff] [blame] | 301 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 302 | class UTF32Test(ReadTest, unittest.TestCase): |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 303 | encoding = "utf-32" |
| 304 | |
| 305 | spamle = (b'\xff\xfe\x00\x00' |
| 306 | b's\x00\x00\x00p\x00\x00\x00a\x00\x00\x00m\x00\x00\x00' |
| 307 | b's\x00\x00\x00p\x00\x00\x00a\x00\x00\x00m\x00\x00\x00') |
| 308 | spambe = (b'\x00\x00\xfe\xff' |
| 309 | b'\x00\x00\x00s\x00\x00\x00p\x00\x00\x00a\x00\x00\x00m' |
| 310 | b'\x00\x00\x00s\x00\x00\x00p\x00\x00\x00a\x00\x00\x00m') |
| 311 | |
| 312 | def test_only_one_bom(self): |
| 313 | _,_,reader,writer = codecs.lookup(self.encoding) |
| 314 | # encode some stream |
| 315 | s = io.BytesIO() |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 316 | f = writer(s) |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 317 | f.write("spam") |
| 318 | f.write("spam") |
| 319 | d = s.getvalue() |
| 320 | # check whether there is exactly one BOM in it |
Benjamin Peterson | c9c0f20 | 2009-06-30 23:06:06 +0000 | [diff] [blame] | 321 | self.assertTrue(d == self.spamle or d == self.spambe) |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 322 | # try to read it back |
| 323 | s = io.BytesIO(d) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 324 | f = reader(s) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 325 | self.assertEqual(f.read(), "spamspam") |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 326 | |
| 327 | def test_badbom(self): |
| 328 | s = io.BytesIO(4*b"\xff") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 329 | f = codecs.getreader(self.encoding)(s) |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 330 | self.assertRaises(UnicodeError, f.read) |
| 331 | |
| 332 | s = io.BytesIO(8*b"\xff") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 333 | f = codecs.getreader(self.encoding)(s) |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 334 | self.assertRaises(UnicodeError, f.read) |
| 335 | |
| 336 | def test_partial(self): |
| 337 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 338 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 339 | [ |
| 340 | "", # first byte of BOM read |
| 341 | "", # second byte of BOM read |
| 342 | "", # third byte of BOM read |
| 343 | "", # fourth byte of BOM read => byteorder known |
| 344 | "", |
| 345 | "", |
| 346 | "", |
| 347 | "\x00", |
| 348 | "\x00", |
| 349 | "\x00", |
| 350 | "\x00", |
| 351 | "\x00\xff", |
| 352 | "\x00\xff", |
| 353 | "\x00\xff", |
| 354 | "\x00\xff", |
| 355 | "\x00\xff\u0100", |
| 356 | "\x00\xff\u0100", |
| 357 | "\x00\xff\u0100", |
| 358 | "\x00\xff\u0100", |
| 359 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 360 | "\x00\xff\u0100\uffff", |
| 361 | "\x00\xff\u0100\uffff", |
| 362 | "\x00\xff\u0100\uffff", |
| 363 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 364 | ] |
| 365 | ) |
| 366 | |
Georg Brandl | 791f4e1 | 2009-09-17 11:41:24 +0000 | [diff] [blame] | 367 | def test_handlers(self): |
| 368 | self.assertEqual(('\ufffd', 1), |
| 369 | codecs.utf_32_decode(b'\x01', 'replace', True)) |
| 370 | self.assertEqual(('', 1), |
| 371 | codecs.utf_32_decode(b'\x01', 'ignore', True)) |
| 372 | |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 373 | def test_errors(self): |
| 374 | self.assertRaises(UnicodeDecodeError, codecs.utf_32_decode, |
| 375 | b"\xff", "strict", True) |
| 376 | |
| 377 | def test_decoder_state(self): |
| 378 | self.check_state_handling_decode(self.encoding, |
| 379 | "spamspam", self.spamle) |
| 380 | self.check_state_handling_decode(self.encoding, |
| 381 | "spamspam", self.spambe) |
| 382 | |
Antoine Pitrou | cc0cfd3 | 2010-06-11 21:46:32 +0000 | [diff] [blame] | 383 | def test_issue8941(self): |
| 384 | # Issue #8941: insufficient result allocation when decoding into |
| 385 | # surrogate pairs on UCS-2 builds. |
| 386 | encoded_le = b'\xff\xfe\x00\x00' + b'\x00\x00\x01\x00' * 1024 |
| 387 | self.assertEqual('\U00010000' * 1024, |
| 388 | codecs.utf_32_decode(encoded_le)[0]) |
| 389 | encoded_be = b'\x00\x00\xfe\xff' + b'\x00\x01\x00\x00' * 1024 |
| 390 | self.assertEqual('\U00010000' * 1024, |
| 391 | codecs.utf_32_decode(encoded_be)[0]) |
| 392 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 393 | class UTF32LETest(ReadTest, unittest.TestCase): |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 394 | encoding = "utf-32-le" |
| 395 | |
| 396 | def test_partial(self): |
| 397 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 398 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 399 | [ |
| 400 | "", |
| 401 | "", |
| 402 | "", |
| 403 | "\x00", |
| 404 | "\x00", |
| 405 | "\x00", |
| 406 | "\x00", |
| 407 | "\x00\xff", |
| 408 | "\x00\xff", |
| 409 | "\x00\xff", |
| 410 | "\x00\xff", |
| 411 | "\x00\xff\u0100", |
| 412 | "\x00\xff\u0100", |
| 413 | "\x00\xff\u0100", |
| 414 | "\x00\xff\u0100", |
| 415 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 416 | "\x00\xff\u0100\uffff", |
| 417 | "\x00\xff\u0100\uffff", |
| 418 | "\x00\xff\u0100\uffff", |
| 419 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 420 | ] |
| 421 | ) |
| 422 | |
| 423 | def test_simple(self): |
| 424 | self.assertEqual("\U00010203".encode(self.encoding), b"\x03\x02\x01\x00") |
| 425 | |
| 426 | def test_errors(self): |
| 427 | self.assertRaises(UnicodeDecodeError, codecs.utf_32_le_decode, |
| 428 | b"\xff", "strict", True) |
| 429 | |
Antoine Pitrou | cc0cfd3 | 2010-06-11 21:46:32 +0000 | [diff] [blame] | 430 | def test_issue8941(self): |
| 431 | # Issue #8941: insufficient result allocation when decoding into |
| 432 | # surrogate pairs on UCS-2 builds. |
| 433 | encoded = b'\x00\x00\x01\x00' * 1024 |
| 434 | self.assertEqual('\U00010000' * 1024, |
| 435 | codecs.utf_32_le_decode(encoded)[0]) |
| 436 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 437 | class UTF32BETest(ReadTest, unittest.TestCase): |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 438 | encoding = "utf-32-be" |
| 439 | |
| 440 | def test_partial(self): |
| 441 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 442 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 443 | [ |
| 444 | "", |
| 445 | "", |
| 446 | "", |
| 447 | "\x00", |
| 448 | "\x00", |
| 449 | "\x00", |
| 450 | "\x00", |
| 451 | "\x00\xff", |
| 452 | "\x00\xff", |
| 453 | "\x00\xff", |
| 454 | "\x00\xff", |
| 455 | "\x00\xff\u0100", |
| 456 | "\x00\xff\u0100", |
| 457 | "\x00\xff\u0100", |
| 458 | "\x00\xff\u0100", |
| 459 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 460 | "\x00\xff\u0100\uffff", |
| 461 | "\x00\xff\u0100\uffff", |
| 462 | "\x00\xff\u0100\uffff", |
| 463 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 41980ca | 2007-08-16 21:55:45 +0000 | [diff] [blame] | 464 | ] |
| 465 | ) |
| 466 | |
| 467 | def test_simple(self): |
| 468 | self.assertEqual("\U00010203".encode(self.encoding), b"\x00\x01\x02\x03") |
| 469 | |
| 470 | def test_errors(self): |
| 471 | self.assertRaises(UnicodeDecodeError, codecs.utf_32_be_decode, |
| 472 | b"\xff", "strict", True) |
| 473 | |
Antoine Pitrou | cc0cfd3 | 2010-06-11 21:46:32 +0000 | [diff] [blame] | 474 | def test_issue8941(self): |
| 475 | # Issue #8941: insufficient result allocation when decoding into |
| 476 | # surrogate pairs on UCS-2 builds. |
| 477 | encoded = b'\x00\x01\x00\x00' * 1024 |
| 478 | self.assertEqual('\U00010000' * 1024, |
| 479 | codecs.utf_32_be_decode(encoded)[0]) |
| 480 | |
| 481 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 482 | class UTF16Test(ReadTest, unittest.TestCase): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 483 | encoding = "utf-16" |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 484 | |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 485 | spamle = b'\xff\xfes\x00p\x00a\x00m\x00s\x00p\x00a\x00m\x00' |
| 486 | spambe = b'\xfe\xff\x00s\x00p\x00a\x00m\x00s\x00p\x00a\x00m' |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 487 | |
| 488 | def test_only_one_bom(self): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 489 | _,_,reader,writer = codecs.lookup(self.encoding) |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 490 | # encode some stream |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 491 | s = io.BytesIO() |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 492 | f = writer(s) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 493 | f.write("spam") |
| 494 | f.write("spam") |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 495 | d = s.getvalue() |
| 496 | # check whether there is exactly one BOM in it |
Benjamin Peterson | c9c0f20 | 2009-06-30 23:06:06 +0000 | [diff] [blame] | 497 | self.assertTrue(d == self.spamle or d == self.spambe) |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 498 | # try to read it back |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 499 | s = io.BytesIO(d) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 500 | f = reader(s) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 501 | self.assertEqual(f.read(), "spamspam") |
Marc-André Lemburg | a37171d | 2001-06-19 20:09:28 +0000 | [diff] [blame] | 502 | |
Walter Dörwald | 1f1d252 | 2005-02-04 14:15:34 +0000 | [diff] [blame] | 503 | def test_badbom(self): |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 504 | s = io.BytesIO(b"\xff\xff") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 505 | f = codecs.getreader(self.encoding)(s) |
Walter Dörwald | 1f1d252 | 2005-02-04 14:15:34 +0000 | [diff] [blame] | 506 | self.assertRaises(UnicodeError, f.read) |
| 507 | |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 508 | s = io.BytesIO(b"\xff\xff\xff\xff") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 509 | f = codecs.getreader(self.encoding)(s) |
Walter Dörwald | 1f1d252 | 2005-02-04 14:15:34 +0000 | [diff] [blame] | 510 | self.assertRaises(UnicodeError, f.read) |
| 511 | |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 512 | def test_partial(self): |
| 513 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 514 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 515 | [ |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 516 | "", # first byte of BOM read |
| 517 | "", # second byte of BOM read => byteorder known |
| 518 | "", |
| 519 | "\x00", |
| 520 | "\x00", |
| 521 | "\x00\xff", |
| 522 | "\x00\xff", |
| 523 | "\x00\xff\u0100", |
| 524 | "\x00\xff\u0100", |
| 525 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 526 | "\x00\xff\u0100\uffff", |
| 527 | "\x00\xff\u0100\uffff", |
| 528 | "\x00\xff\u0100\uffff", |
| 529 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 530 | ] |
| 531 | ) |
| 532 | |
Georg Brandl | 791f4e1 | 2009-09-17 11:41:24 +0000 | [diff] [blame] | 533 | def test_handlers(self): |
| 534 | self.assertEqual(('\ufffd', 1), |
| 535 | codecs.utf_16_decode(b'\x01', 'replace', True)) |
| 536 | self.assertEqual(('', 1), |
| 537 | codecs.utf_16_decode(b'\x01', 'ignore', True)) |
| 538 | |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 539 | def test_errors(self): |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 540 | self.assertRaises(UnicodeDecodeError, codecs.utf_16_decode, |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 541 | b"\xff", "strict", True) |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 542 | |
| 543 | def test_decoder_state(self): |
| 544 | self.check_state_handling_decode(self.encoding, |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 545 | "spamspam", self.spamle) |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 546 | self.check_state_handling_decode(self.encoding, |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 547 | "spamspam", self.spambe) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 548 | |
Florent Xicluna | c1c415f | 2010-02-26 11:12:33 +0000 | [diff] [blame] | 549 | def test_bug691291(self): |
| 550 | # Files are always opened in binary mode, even if no binary mode was |
| 551 | # specified. This means that no automatic conversion of '\n' is done |
| 552 | # on reading and writing. |
| 553 | s1 = 'Hello\r\nworld\r\n' |
| 554 | |
| 555 | s = s1.encode(self.encoding) |
Victor Stinner | 2cca057 | 2011-05-23 14:51:42 +0200 | [diff] [blame] | 556 | self.addCleanup(support.unlink, support.TESTFN) |
| 557 | with open(support.TESTFN, 'wb') as fp: |
| 558 | fp.write(s) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 559 | with codecs.open(support.TESTFN, 'U', encoding=self.encoding) as reader: |
Victor Stinner | 2cca057 | 2011-05-23 14:51:42 +0200 | [diff] [blame] | 560 | self.assertEqual(reader.read(), s1) |
Florent Xicluna | c1c415f | 2010-02-26 11:12:33 +0000 | [diff] [blame] | 561 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 562 | class UTF16LETest(ReadTest, unittest.TestCase): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 563 | encoding = "utf-16-le" |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 564 | |
| 565 | def test_partial(self): |
| 566 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 567 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 568 | [ |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 569 | "", |
| 570 | "\x00", |
| 571 | "\x00", |
| 572 | "\x00\xff", |
| 573 | "\x00\xff", |
| 574 | "\x00\xff\u0100", |
| 575 | "\x00\xff\u0100", |
| 576 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 577 | "\x00\xff\u0100\uffff", |
| 578 | "\x00\xff\u0100\uffff", |
| 579 | "\x00\xff\u0100\uffff", |
| 580 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 581 | ] |
| 582 | ) |
| 583 | |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 584 | def test_errors(self): |
Antoine Pitrou | b4bbee2 | 2012-07-21 00:45:14 +0200 | [diff] [blame] | 585 | tests = [ |
| 586 | (b'\xff', '\ufffd'), |
| 587 | (b'A\x00Z', 'A\ufffd'), |
| 588 | (b'A\x00B\x00C\x00D\x00Z', 'ABCD\ufffd'), |
| 589 | (b'\x00\xd8', '\ufffd'), |
| 590 | (b'\x00\xd8A', '\ufffd'), |
| 591 | (b'\x00\xd8A\x00', '\ufffdA'), |
| 592 | (b'\x00\xdcA\x00', '\ufffdA'), |
| 593 | ] |
| 594 | for raw, expected in tests: |
| 595 | self.assertRaises(UnicodeDecodeError, codecs.utf_16_le_decode, |
| 596 | raw, 'strict', True) |
| 597 | self.assertEqual(raw.decode('utf-16le', 'replace'), expected) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 598 | |
Victor Stinner | 53a9dd7 | 2010-12-08 22:25:45 +0000 | [diff] [blame] | 599 | def test_nonbmp(self): |
| 600 | self.assertEqual("\U00010203".encode(self.encoding), |
| 601 | b'\x00\xd8\x03\xde') |
| 602 | self.assertEqual(b'\x00\xd8\x03\xde'.decode(self.encoding), |
| 603 | "\U00010203") |
| 604 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 605 | class UTF16BETest(ReadTest, unittest.TestCase): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 606 | encoding = "utf-16-be" |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 607 | |
| 608 | def test_partial(self): |
| 609 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 610 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 611 | [ |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 612 | "", |
| 613 | "\x00", |
| 614 | "\x00", |
| 615 | "\x00\xff", |
| 616 | "\x00\xff", |
| 617 | "\x00\xff\u0100", |
| 618 | "\x00\xff\u0100", |
| 619 | "\x00\xff\u0100\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 620 | "\x00\xff\u0100\uffff", |
| 621 | "\x00\xff\u0100\uffff", |
| 622 | "\x00\xff\u0100\uffff", |
| 623 | "\x00\xff\u0100\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 624 | ] |
| 625 | ) |
| 626 | |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 627 | def test_errors(self): |
Antoine Pitrou | b4bbee2 | 2012-07-21 00:45:14 +0200 | [diff] [blame] | 628 | tests = [ |
| 629 | (b'\xff', '\ufffd'), |
| 630 | (b'\x00A\xff', 'A\ufffd'), |
| 631 | (b'\x00A\x00B\x00C\x00DZ', 'ABCD\ufffd'), |
| 632 | (b'\xd8\x00', '\ufffd'), |
| 633 | (b'\xd8\x00\xdc', '\ufffd'), |
| 634 | (b'\xd8\x00\x00A', '\ufffdA'), |
| 635 | (b'\xdc\x00\x00A', '\ufffdA'), |
| 636 | ] |
| 637 | for raw, expected in tests: |
| 638 | self.assertRaises(UnicodeDecodeError, codecs.utf_16_be_decode, |
| 639 | raw, 'strict', True) |
| 640 | self.assertEqual(raw.decode('utf-16be', 'replace'), expected) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 641 | |
Victor Stinner | 53a9dd7 | 2010-12-08 22:25:45 +0000 | [diff] [blame] | 642 | def test_nonbmp(self): |
| 643 | self.assertEqual("\U00010203".encode(self.encoding), |
| 644 | b'\xd8\x00\xde\x03') |
| 645 | self.assertEqual(b'\xd8\x00\xde\x03'.decode(self.encoding), |
| 646 | "\U00010203") |
| 647 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 648 | class UTF8Test(ReadTest, unittest.TestCase): |
Walter Dörwald | e57d7b1 | 2004-12-21 22:24:00 +0000 | [diff] [blame] | 649 | encoding = "utf-8" |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 650 | |
| 651 | def test_partial(self): |
| 652 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 653 | "\x00\xff\u07ff\u0800\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 654 | [ |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 655 | "\x00", |
| 656 | "\x00", |
| 657 | "\x00\xff", |
| 658 | "\x00\xff", |
| 659 | "\x00\xff\u07ff", |
| 660 | "\x00\xff\u07ff", |
| 661 | "\x00\xff\u07ff", |
| 662 | "\x00\xff\u07ff\u0800", |
| 663 | "\x00\xff\u07ff\u0800", |
| 664 | "\x00\xff\u07ff\u0800", |
| 665 | "\x00\xff\u07ff\u0800\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 666 | "\x00\xff\u07ff\u0800\uffff", |
| 667 | "\x00\xff\u07ff\u0800\uffff", |
| 668 | "\x00\xff\u07ff\u0800\uffff", |
| 669 | "\x00\xff\u07ff\u0800\uffff\U00010000", |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 670 | ] |
| 671 | ) |
| 672 | |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 673 | def test_decoder_state(self): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 674 | u = "\x00\x7f\x80\xff\u0100\u07ff\u0800\uffff\U0010ffff" |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 675 | self.check_state_handling_decode(self.encoding, |
| 676 | u, u.encode(self.encoding)) |
| 677 | |
Martin v. Löwis | db12d45 | 2009-05-02 18:52:14 +0000 | [diff] [blame] | 678 | def test_lone_surrogates(self): |
| 679 | self.assertRaises(UnicodeEncodeError, "\ud800".encode, "utf-8") |
| 680 | self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "utf-8") |
Victor Stinner | 31be90b | 2010-04-22 19:38:16 +0000 | [diff] [blame] | 681 | self.assertEqual("[\uDC80]".encode("utf-8", "backslashreplace"), |
| 682 | b'[\\udc80]') |
| 683 | self.assertEqual("[\uDC80]".encode("utf-8", "xmlcharrefreplace"), |
| 684 | b'[�]') |
| 685 | self.assertEqual("[\uDC80]".encode("utf-8", "surrogateescape"), |
| 686 | b'[\x80]') |
| 687 | self.assertEqual("[\uDC80]".encode("utf-8", "ignore"), |
| 688 | b'[]') |
| 689 | self.assertEqual("[\uDC80]".encode("utf-8", "replace"), |
| 690 | b'[?]') |
Martin v. Löwis | db12d45 | 2009-05-02 18:52:14 +0000 | [diff] [blame] | 691 | |
Martin v. Löwis | e0a2b72 | 2009-05-10 08:08:56 +0000 | [diff] [blame] | 692 | def test_surrogatepass_handler(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 693 | self.assertEqual("abc\ud800def".encode("utf-8", "surrogatepass"), |
| 694 | b"abc\xed\xa0\x80def") |
| 695 | self.assertEqual(b"abc\xed\xa0\x80def".decode("utf-8", "surrogatepass"), |
| 696 | "abc\ud800def") |
Martin v. Löwis | d63a3b8 | 2011-09-28 07:41:54 +0200 | [diff] [blame] | 697 | self.assertEqual("\U00010fff\uD800".encode("utf-8", "surrogatepass"), |
| 698 | b"\xf0\x90\xbf\xbf\xed\xa0\x80") |
| 699 | self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("utf-8", "surrogatepass"), |
| 700 | "\U00010fff\uD800") |
Martin v. Löwis | e0a2b72 | 2009-05-10 08:08:56 +0000 | [diff] [blame] | 701 | self.assertTrue(codecs.lookup_error("surrogatepass")) |
Philip Jenvey | 45c4149 | 2012-10-26 17:01:53 -0700 | [diff] [blame] | 702 | with self.assertRaises(UnicodeDecodeError): |
| 703 | b"abc\xed\xa0".decode("utf-8", "surrogatepass") |
Ezio Melotti | 540da76 | 2012-11-03 23:03:39 +0200 | [diff] [blame] | 704 | with self.assertRaises(UnicodeDecodeError): |
| 705 | b"abc\xed\xa0z".decode("utf-8", "surrogatepass") |
Martin v. Löwis | db12d45 | 2009-05-02 18:52:14 +0000 | [diff] [blame] | 706 | |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 707 | @unittest.skipUnless(sys.platform == 'win32', |
| 708 | 'cp65001 is a Windows-only codec') |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 709 | class CP65001Test(ReadTest, unittest.TestCase): |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 710 | encoding = "cp65001" |
| 711 | |
| 712 | def test_encode(self): |
| 713 | tests = [ |
| 714 | ('abc', 'strict', b'abc'), |
| 715 | ('\xe9\u20ac', 'strict', b'\xc3\xa9\xe2\x82\xac'), |
| 716 | ('\U0010ffff', 'strict', b'\xf4\x8f\xbf\xbf'), |
| 717 | ] |
| 718 | if VISTA_OR_LATER: |
| 719 | tests.extend(( |
| 720 | ('\udc80', 'strict', None), |
| 721 | ('\udc80', 'ignore', b''), |
| 722 | ('\udc80', 'replace', b'?'), |
| 723 | ('\udc80', 'backslashreplace', b'\\udc80'), |
| 724 | ('\udc80', 'surrogatepass', b'\xed\xb2\x80'), |
| 725 | )) |
| 726 | else: |
| 727 | tests.append(('\udc80', 'strict', b'\xed\xb2\x80')) |
| 728 | for text, errors, expected in tests: |
| 729 | if expected is not None: |
| 730 | try: |
| 731 | encoded = text.encode('cp65001', errors) |
| 732 | except UnicodeEncodeError as err: |
| 733 | self.fail('Unable to encode %a to cp65001 with ' |
| 734 | 'errors=%r: %s' % (text, errors, err)) |
| 735 | self.assertEqual(encoded, expected, |
| 736 | '%a.encode("cp65001", %r)=%a != %a' |
| 737 | % (text, errors, encoded, expected)) |
| 738 | else: |
| 739 | self.assertRaises(UnicodeEncodeError, |
| 740 | text.encode, "cp65001", errors) |
| 741 | |
| 742 | def test_decode(self): |
| 743 | tests = [ |
| 744 | (b'abc', 'strict', 'abc'), |
| 745 | (b'\xc3\xa9\xe2\x82\xac', 'strict', '\xe9\u20ac'), |
| 746 | (b'\xf4\x8f\xbf\xbf', 'strict', '\U0010ffff'), |
| 747 | (b'\xef\xbf\xbd', 'strict', '\ufffd'), |
| 748 | (b'[\xc3\xa9]', 'strict', '[\xe9]'), |
| 749 | # invalid bytes |
| 750 | (b'[\xff]', 'strict', None), |
| 751 | (b'[\xff]', 'ignore', '[]'), |
| 752 | (b'[\xff]', 'replace', '[\ufffd]'), |
| 753 | (b'[\xff]', 'surrogateescape', '[\udcff]'), |
| 754 | ] |
| 755 | if VISTA_OR_LATER: |
| 756 | tests.extend(( |
| 757 | (b'[\xed\xb2\x80]', 'strict', None), |
| 758 | (b'[\xed\xb2\x80]', 'ignore', '[]'), |
| 759 | (b'[\xed\xb2\x80]', 'replace', '[\ufffd\ufffd\ufffd]'), |
| 760 | )) |
| 761 | else: |
| 762 | tests.extend(( |
| 763 | (b'[\xed\xb2\x80]', 'strict', '[\udc80]'), |
| 764 | )) |
| 765 | for raw, errors, expected in tests: |
| 766 | if expected is not None: |
| 767 | try: |
| 768 | decoded = raw.decode('cp65001', errors) |
| 769 | except UnicodeDecodeError as err: |
| 770 | self.fail('Unable to decode %a from cp65001 with ' |
| 771 | 'errors=%r: %s' % (raw, errors, err)) |
| 772 | self.assertEqual(decoded, expected, |
| 773 | '%a.decode("cp65001", %r)=%a != %a' |
| 774 | % (raw, errors, decoded, expected)) |
| 775 | else: |
| 776 | self.assertRaises(UnicodeDecodeError, |
| 777 | raw.decode, 'cp65001', errors) |
| 778 | |
| 779 | @unittest.skipUnless(VISTA_OR_LATER, 'require Windows Vista or later') |
| 780 | def test_lone_surrogates(self): |
| 781 | self.assertRaises(UnicodeEncodeError, "\ud800".encode, "cp65001") |
| 782 | self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "cp65001") |
| 783 | self.assertEqual("[\uDC80]".encode("cp65001", "backslashreplace"), |
| 784 | b'[\\udc80]') |
| 785 | self.assertEqual("[\uDC80]".encode("cp65001", "xmlcharrefreplace"), |
| 786 | b'[�]') |
| 787 | self.assertEqual("[\uDC80]".encode("cp65001", "surrogateescape"), |
| 788 | b'[\x80]') |
| 789 | self.assertEqual("[\uDC80]".encode("cp65001", "ignore"), |
| 790 | b'[]') |
| 791 | self.assertEqual("[\uDC80]".encode("cp65001", "replace"), |
| 792 | b'[?]') |
| 793 | |
| 794 | @unittest.skipUnless(VISTA_OR_LATER, 'require Windows Vista or later') |
| 795 | def test_surrogatepass_handler(self): |
| 796 | self.assertEqual("abc\ud800def".encode("cp65001", "surrogatepass"), |
| 797 | b"abc\xed\xa0\x80def") |
| 798 | self.assertEqual(b"abc\xed\xa0\x80def".decode("cp65001", "surrogatepass"), |
| 799 | "abc\ud800def") |
| 800 | self.assertEqual("\U00010fff\uD800".encode("cp65001", "surrogatepass"), |
| 801 | b"\xf0\x90\xbf\xbf\xed\xa0\x80") |
| 802 | self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("cp65001", "surrogatepass"), |
| 803 | "\U00010fff\uD800") |
| 804 | self.assertTrue(codecs.lookup_error("surrogatepass")) |
| 805 | |
| 806 | |
| 807 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 808 | class UTF7Test(ReadTest, unittest.TestCase): |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 809 | encoding = "utf-7" |
| 810 | |
Christian Heimes | 5d14c2b | 2007-11-20 23:38:09 +0000 | [diff] [blame] | 811 | def test_partial(self): |
| 812 | self.check_partial( |
| 813 | "a+-b", |
| 814 | [ |
| 815 | "a", |
| 816 | "a", |
| 817 | "a+", |
| 818 | "a+-", |
| 819 | "a+-b", |
| 820 | ] |
| 821 | ) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 822 | |
| 823 | class UTF16ExTest(unittest.TestCase): |
| 824 | |
| 825 | def test_errors(self): |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 826 | self.assertRaises(UnicodeDecodeError, codecs.utf_16_ex_decode, b"\xff", "strict", 0, True) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 827 | |
| 828 | def test_bad_args(self): |
| 829 | self.assertRaises(TypeError, codecs.utf_16_ex_decode) |
| 830 | |
| 831 | class ReadBufferTest(unittest.TestCase): |
| 832 | |
| 833 | def test_array(self): |
| 834 | import array |
| 835 | self.assertEqual( |
Guido van Rossum | 09549f4 | 2007-08-27 20:40:10 +0000 | [diff] [blame] | 836 | codecs.readbuffer_encode(array.array("b", b"spam")), |
Walter Dörwald | 2233d27 | 2007-06-22 12:17:08 +0000 | [diff] [blame] | 837 | (b"spam", 4) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 838 | ) |
| 839 | |
| 840 | def test_empty(self): |
Walter Dörwald | 2233d27 | 2007-06-22 12:17:08 +0000 | [diff] [blame] | 841 | self.assertEqual(codecs.readbuffer_encode(""), (b"", 0)) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 842 | |
| 843 | def test_bad_args(self): |
| 844 | self.assertRaises(TypeError, codecs.readbuffer_encode) |
| 845 | self.assertRaises(TypeError, codecs.readbuffer_encode, 42) |
| 846 | |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 847 | class UTF8SigTest(ReadTest, unittest.TestCase): |
Martin v. Löwis | 412ed3b | 2006-01-08 10:45:39 +0000 | [diff] [blame] | 848 | encoding = "utf-8-sig" |
| 849 | |
| 850 | def test_partial(self): |
| 851 | self.check_partial( |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 852 | "\ufeff\x00\xff\u07ff\u0800\uffff\U00010000", |
Martin v. Löwis | 412ed3b | 2006-01-08 10:45:39 +0000 | [diff] [blame] | 853 | [ |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 854 | "", |
| 855 | "", |
| 856 | "", # First BOM has been read and skipped |
| 857 | "", |
| 858 | "", |
| 859 | "\ufeff", # Second BOM has been read and emitted |
| 860 | "\ufeff\x00", # "\x00" read and emitted |
Walter Dörwald | 32a4c71 | 2007-06-20 09:25:34 +0000 | [diff] [blame] | 861 | "\ufeff\x00", # First byte of encoded "\xff" read |
| 862 | "\ufeff\x00\xff", # Second byte of encoded "\xff" read |
| 863 | "\ufeff\x00\xff", # First byte of encoded "\u07ff" read |
| 864 | "\ufeff\x00\xff\u07ff", # Second byte of encoded "\u07ff" read |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 865 | "\ufeff\x00\xff\u07ff", |
| 866 | "\ufeff\x00\xff\u07ff", |
| 867 | "\ufeff\x00\xff\u07ff\u0800", |
| 868 | "\ufeff\x00\xff\u07ff\u0800", |
| 869 | "\ufeff\x00\xff\u07ff\u0800", |
| 870 | "\ufeff\x00\xff\u07ff\u0800\uffff", |
Serhiy Storchaka | 48e188e | 2013-01-08 23:14:24 +0200 | [diff] [blame] | 871 | "\ufeff\x00\xff\u07ff\u0800\uffff", |
| 872 | "\ufeff\x00\xff\u07ff\u0800\uffff", |
| 873 | "\ufeff\x00\xff\u07ff\u0800\uffff", |
| 874 | "\ufeff\x00\xff\u07ff\u0800\uffff\U00010000", |
Martin v. Löwis | 412ed3b | 2006-01-08 10:45:39 +0000 | [diff] [blame] | 875 | ] |
| 876 | ) |
| 877 | |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 878 | def test_bug1601501(self): |
| 879 | # SF bug #1601501: check that the codec works with a buffer |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 880 | self.assertEqual(str(b"\xef\xbb\xbf", "utf-8-sig"), "") |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 881 | |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 882 | def test_bom(self): |
| 883 | d = codecs.getincrementaldecoder("utf-8-sig")() |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 884 | s = "spam" |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 885 | self.assertEqual(d.decode(s.encode("utf-8-sig")), s) |
| 886 | |
Guido van Rossum | 87c0f1d | 2007-11-19 18:03:44 +0000 | [diff] [blame] | 887 | def test_stream_bom(self): |
| 888 | unistring = "ABC\u00A1\u2200XYZ" |
| 889 | bytestring = codecs.BOM_UTF8 + b"ABC\xC2\xA1\xE2\x88\x80XYZ" |
| 890 | |
| 891 | reader = codecs.getreader("utf-8-sig") |
| 892 | for sizehint in [None] + list(range(1, 11)) + \ |
| 893 | [64, 128, 256, 512, 1024]: |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 894 | istream = reader(io.BytesIO(bytestring)) |
Guido van Rossum | 87c0f1d | 2007-11-19 18:03:44 +0000 | [diff] [blame] | 895 | ostream = io.StringIO() |
| 896 | while 1: |
| 897 | if sizehint is not None: |
| 898 | data = istream.read(sizehint) |
| 899 | else: |
| 900 | data = istream.read() |
| 901 | |
| 902 | if not data: |
| 903 | break |
| 904 | ostream.write(data) |
| 905 | |
| 906 | got = ostream.getvalue() |
| 907 | self.assertEqual(got, unistring) |
| 908 | |
| 909 | def test_stream_bare(self): |
| 910 | unistring = "ABC\u00A1\u2200XYZ" |
| 911 | bytestring = b"ABC\xC2\xA1\xE2\x88\x80XYZ" |
| 912 | |
| 913 | reader = codecs.getreader("utf-8-sig") |
| 914 | for sizehint in [None] + list(range(1, 11)) + \ |
| 915 | [64, 128, 256, 512, 1024]: |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 916 | istream = reader(io.BytesIO(bytestring)) |
Guido van Rossum | 87c0f1d | 2007-11-19 18:03:44 +0000 | [diff] [blame] | 917 | ostream = io.StringIO() |
| 918 | while 1: |
| 919 | if sizehint is not None: |
| 920 | data = istream.read(sizehint) |
| 921 | else: |
| 922 | data = istream.read() |
| 923 | |
| 924 | if not data: |
| 925 | break |
| 926 | ostream.write(data) |
| 927 | |
| 928 | got = ostream.getvalue() |
| 929 | self.assertEqual(got, unistring) |
| 930 | |
| 931 | class EscapeDecodeTest(unittest.TestCase): |
| 932 | def test_empty(self): |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 933 | self.assertEqual(codecs.escape_decode(b""), (b"", 0)) |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 934 | |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 935 | def test_raw(self): |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 936 | decode = codecs.escape_decode |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 937 | for b in range(256): |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 938 | b = bytes([b]) |
| 939 | if b != b'\\': |
| 940 | self.assertEqual(decode(b + b'0'), (b + b'0', 2)) |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 941 | |
| 942 | def test_escape(self): |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 943 | decode = codecs.escape_decode |
| 944 | check = coding_checker(self, decode) |
| 945 | check(b"[\\\n]", b"[]") |
| 946 | check(br'[\"]', b'["]') |
| 947 | check(br"[\']", b"[']") |
| 948 | check(br"[\\]", br"[\]") |
| 949 | check(br"[\a]", b"[\x07]") |
| 950 | check(br"[\b]", b"[\x08]") |
| 951 | check(br"[\t]", b"[\x09]") |
| 952 | check(br"[\n]", b"[\x0a]") |
| 953 | check(br"[\v]", b"[\x0b]") |
| 954 | check(br"[\f]", b"[\x0c]") |
| 955 | check(br"[\r]", b"[\x0d]") |
| 956 | check(br"[\7]", b"[\x07]") |
| 957 | check(br"[\8]", br"[\8]") |
| 958 | check(br"[\78]", b"[\x078]") |
| 959 | check(br"[\41]", b"[!]") |
| 960 | check(br"[\418]", b"[!8]") |
| 961 | check(br"[\101]", b"[A]") |
| 962 | check(br"[\1010]", b"[A0]") |
| 963 | check(br"[\501]", b"[A]") |
| 964 | check(br"[\x41]", b"[A]") |
| 965 | check(br"[\X41]", br"[\X41]") |
| 966 | check(br"[\x410]", b"[A0]") |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 967 | for b in range(256): |
| 968 | if b not in b'\n"\'\\abtnvfr01234567x': |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 969 | b = bytes([b]) |
| 970 | check(b'\\' + b, b'\\' + b) |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 971 | |
| 972 | def test_errors(self): |
Serhiy Storchaka | 077cb34 | 2013-01-29 11:06:53 +0200 | [diff] [blame] | 973 | decode = codecs.escape_decode |
| 974 | self.assertRaises(ValueError, decode, br"\x") |
| 975 | self.assertRaises(ValueError, decode, br"[\x]") |
| 976 | self.assertEqual(decode(br"[\x]\x", "ignore"), (b"[]", 6)) |
| 977 | self.assertEqual(decode(br"[\x]\x", "replace"), (b"[?]?", 6)) |
| 978 | self.assertRaises(ValueError, decode, br"\x0") |
| 979 | self.assertRaises(ValueError, decode, br"[\x0]") |
| 980 | self.assertEqual(decode(br"[\x0]\x0", "ignore"), (b"[]", 8)) |
| 981 | self.assertEqual(decode(br"[\x0]\x0", "replace"), (b"[?]?", 8)) |
Serhiy Storchaka | ace3ad3 | 2013-01-25 23:31:43 +0200 | [diff] [blame] | 982 | |
Marc-André Lemburg | 29273c8 | 2003-02-04 19:35:03 +0000 | [diff] [blame] | 983 | class RecodingTest(unittest.TestCase): |
| 984 | def test_recoding(self): |
Guido van Rossum | f4cfc8f | 2007-05-17 21:52:23 +0000 | [diff] [blame] | 985 | f = io.BytesIO() |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 986 | f2 = codecs.EncodedFile(f, "unicode_internal", "utf-8") |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 987 | f2.write("a") |
Marc-André Lemburg | 29273c8 | 2003-02-04 19:35:03 +0000 | [diff] [blame] | 988 | f2.close() |
| 989 | # Python used to crash on this at exit because of a refcount |
| 990 | # bug in _codecsmodule.c |
Fred Drake | 2e2be37 | 2001-09-20 21:33:42 +0000 | [diff] [blame] | 991 | |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 992 | # From RFC 3492 |
| 993 | punycode_testcases = [ |
| 994 | # A Arabic (Egyptian): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 995 | ("\u0644\u064A\u0647\u0645\u0627\u0628\u062A\u0643\u0644" |
| 996 | "\u0645\u0648\u0634\u0639\u0631\u0628\u064A\u061F", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 997 | b"egbpdaj6bu4bxfgehfvwxn"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 998 | # B Chinese (simplified): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 999 | ("\u4ED6\u4EEC\u4E3A\u4EC0\u4E48\u4E0D\u8BF4\u4E2D\u6587", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1000 | b"ihqwcrb4cv8a8dqg056pqjye"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1001 | # C Chinese (traditional): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1002 | ("\u4ED6\u5011\u7232\u4EC0\u9EBD\u4E0D\u8AAA\u4E2D\u6587", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1003 | b"ihqwctvzc91f659drss3x8bo0yb"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1004 | # D Czech: Pro<ccaron>prost<ecaron>nemluv<iacute><ccaron>esky |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1005 | ("\u0050\u0072\u006F\u010D\u0070\u0072\u006F\u0073\u0074" |
| 1006 | "\u011B\u006E\u0065\u006D\u006C\u0075\u0076\u00ED\u010D" |
| 1007 | "\u0065\u0073\u006B\u0079", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1008 | b"Proprostnemluvesky-uyb24dma41a"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1009 | # E Hebrew: |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1010 | ("\u05DC\u05DE\u05D4\u05D4\u05DD\u05E4\u05E9\u05D5\u05D8" |
| 1011 | "\u05DC\u05D0\u05DE\u05D3\u05D1\u05E8\u05D9\u05DD\u05E2" |
| 1012 | "\u05D1\u05E8\u05D9\u05EA", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1013 | b"4dbcagdahymbxekheh6e0a7fei0b"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1014 | # F Hindi (Devanagari): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1015 | ("\u092F\u0939\u0932\u094B\u0917\u0939\u093F\u0928\u094D" |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1016 | "\u0926\u0940\u0915\u094D\u092F\u094B\u0902\u0928\u0939" |
| 1017 | "\u0940\u0902\u092C\u094B\u0932\u0938\u0915\u0924\u0947" |
| 1018 | "\u0939\u0948\u0902", |
| 1019 | b"i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1020 | |
| 1021 | #(G) Japanese (kanji and hiragana): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1022 | ("\u306A\u305C\u307F\u3093\u306A\u65E5\u672C\u8A9E\u3092" |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1023 | "\u8A71\u3057\u3066\u304F\u308C\u306A\u3044\u306E\u304B", |
| 1024 | b"n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1025 | |
| 1026 | # (H) Korean (Hangul syllables): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1027 | ("\uC138\uACC4\uC758\uBAA8\uB4E0\uC0AC\uB78C\uB4E4\uC774" |
| 1028 | "\uD55C\uAD6D\uC5B4\uB97C\uC774\uD574\uD55C\uB2E4\uBA74" |
| 1029 | "\uC5BC\uB9C8\uB098\uC88B\uC744\uAE4C", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1030 | b"989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5j" |
| 1031 | b"psd879ccm6fea98c"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1032 | |
| 1033 | # (I) Russian (Cyrillic): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1034 | ("\u043F\u043E\u0447\u0435\u043C\u0443\u0436\u0435\u043E" |
| 1035 | "\u043D\u0438\u043D\u0435\u0433\u043E\u0432\u043E\u0440" |
| 1036 | "\u044F\u0442\u043F\u043E\u0440\u0443\u0441\u0441\u043A" |
| 1037 | "\u0438", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1038 | b"b1abfaaepdrnnbgefbaDotcwatmq2g4l"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1039 | |
| 1040 | # (J) Spanish: Porqu<eacute>nopuedensimplementehablarenEspa<ntilde>ol |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1041 | ("\u0050\u006F\u0072\u0071\u0075\u00E9\u006E\u006F\u0070" |
| 1042 | "\u0075\u0065\u0064\u0065\u006E\u0073\u0069\u006D\u0070" |
| 1043 | "\u006C\u0065\u006D\u0065\u006E\u0074\u0065\u0068\u0061" |
| 1044 | "\u0062\u006C\u0061\u0072\u0065\u006E\u0045\u0073\u0070" |
| 1045 | "\u0061\u00F1\u006F\u006C", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1046 | b"PorqunopuedensimplementehablarenEspaol-fmd56a"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1047 | |
| 1048 | # (K) Vietnamese: |
| 1049 | # T<adotbelow>isaoh<odotbelow>kh<ocirc>ngth<ecirchookabove>ch\ |
| 1050 | # <ihookabove>n<oacute>iti<ecircacute>ngVi<ecircdotbelow>t |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1051 | ("\u0054\u1EA1\u0069\u0073\u0061\u006F\u0068\u1ECD\u006B" |
| 1052 | "\u0068\u00F4\u006E\u0067\u0074\u0068\u1EC3\u0063\u0068" |
| 1053 | "\u1EC9\u006E\u00F3\u0069\u0074\u0069\u1EBF\u006E\u0067" |
| 1054 | "\u0056\u0069\u1EC7\u0074", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1055 | b"TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1056 | |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1057 | #(L) 3<nen>B<gumi><kinpachi><sensei> |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1058 | ("\u0033\u5E74\u0042\u7D44\u91D1\u516B\u5148\u751F", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1059 | b"3B-ww4c5e180e575a65lsy2b"), |
Tim Peters | 0eadaac | 2003-04-24 16:02:54 +0000 | [diff] [blame] | 1060 | |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1061 | # (M) <amuro><namie>-with-SUPER-MONKEYS |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1062 | ("\u5B89\u5BA4\u5948\u7F8E\u6075\u002D\u0077\u0069\u0074" |
| 1063 | "\u0068\u002D\u0053\u0055\u0050\u0045\u0052\u002D\u004D" |
| 1064 | "\u004F\u004E\u004B\u0045\u0059\u0053", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1065 | b"-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1066 | |
| 1067 | # (N) Hello-Another-Way-<sorezore><no><basho> |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1068 | ("\u0048\u0065\u006C\u006C\u006F\u002D\u0041\u006E\u006F" |
| 1069 | "\u0074\u0068\u0065\u0072\u002D\u0057\u0061\u0079\u002D" |
| 1070 | "\u305D\u308C\u305E\u308C\u306E\u5834\u6240", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1071 | b"Hello-Another-Way--fc4qua05auwb3674vfr0b"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1072 | |
| 1073 | # (O) <hitotsu><yane><no><shita>2 |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1074 | ("\u3072\u3068\u3064\u5C4B\u6839\u306E\u4E0B\u0032", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1075 | b"2-u9tlzr9756bt3uc0v"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1076 | |
| 1077 | # (P) Maji<de>Koi<suru>5<byou><mae> |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1078 | ("\u004D\u0061\u006A\u0069\u3067\u004B\u006F\u0069\u3059" |
| 1079 | "\u308B\u0035\u79D2\u524D", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1080 | b"MajiKoi5-783gue6qz075azm5e"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1081 | |
| 1082 | # (Q) <pafii>de<runba> |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1083 | ("\u30D1\u30D5\u30A3\u30FC\u0064\u0065\u30EB\u30F3\u30D0", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1084 | b"de-jg4avhby1noc0d"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1085 | |
| 1086 | # (R) <sono><supiido><de> |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1087 | ("\u305D\u306E\u30B9\u30D4\u30FC\u30C9\u3067", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1088 | b"d9juau41awczczp"), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1089 | |
| 1090 | # (S) -> $1.00 <- |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1091 | ("\u002D\u003E\u0020\u0024\u0031\u002E\u0030\u0030\u0020" |
| 1092 | "\u003C\u002D", |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1093 | b"-> $1.00 <--") |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1094 | ] |
| 1095 | |
| 1096 | for i in punycode_testcases: |
| 1097 | if len(i)!=2: |
Guido van Rossum | be19ed7 | 2007-02-09 05:37:30 +0000 | [diff] [blame] | 1098 | print(repr(i)) |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1099 | |
| 1100 | class PunycodeTest(unittest.TestCase): |
| 1101 | def test_encode(self): |
| 1102 | for uni, puny in punycode_testcases: |
| 1103 | # Need to convert both strings to lower case, since |
| 1104 | # some of the extended encodings use upper case, but our |
| 1105 | # code produces only lower case. Converting just puny to |
| 1106 | # lower is also insufficient, since some of the input characters |
| 1107 | # are upper case. |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1108 | self.assertEqual( |
Walter Dörwald | a4c6128 | 2007-05-10 12:36:25 +0000 | [diff] [blame] | 1109 | str(uni.encode("punycode"), "ascii").lower(), |
| 1110 | str(puny, "ascii").lower() |
| 1111 | ) |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1112 | |
| 1113 | def test_decode(self): |
| 1114 | for uni, puny in punycode_testcases: |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1115 | self.assertEqual(uni, puny.decode("punycode")) |
Guido van Rossum | 04c70ad | 2007-08-29 14:04:40 +0000 | [diff] [blame] | 1116 | puny = puny.decode("ascii").encode("ascii") |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1117 | self.assertEqual(uni, puny.decode("punycode")) |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1118 | |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1119 | class UnicodeInternalTest(unittest.TestCase): |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1120 | @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t') |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1121 | def test_bug1251300(self): |
| 1122 | # Decoding with unicode_internal used to not correctly handle "code |
| 1123 | # points" above 0x10ffff on UCS-4 builds. |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1124 | ok = [ |
| 1125 | (b"\x00\x10\xff\xff", "\U0010ffff"), |
| 1126 | (b"\x00\x00\x01\x01", "\U00000101"), |
| 1127 | (b"", ""), |
| 1128 | ] |
| 1129 | not_ok = [ |
| 1130 | b"\x7f\xff\xff\xff", |
| 1131 | b"\x80\x00\x00\x00", |
| 1132 | b"\x81\x00\x00\x00", |
| 1133 | b"\x00", |
| 1134 | b"\x00\x00\x00\x00\x00", |
| 1135 | ] |
| 1136 | for internal, uni in ok: |
| 1137 | if sys.byteorder == "little": |
| 1138 | internal = bytes(reversed(internal)) |
Ezio Melotti | 11060a4 | 2011-11-16 09:39:10 +0200 | [diff] [blame] | 1139 | with support.check_warnings(): |
| 1140 | self.assertEqual(uni, internal.decode("unicode_internal")) |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1141 | for internal in not_ok: |
| 1142 | if sys.byteorder == "little": |
| 1143 | internal = bytes(reversed(internal)) |
Ezio Melotti | 345379a | 2011-11-16 09:54:19 +0200 | [diff] [blame] | 1144 | with support.check_warnings(('unicode_internal codec has been ' |
Ezio Melotti | 11060a4 | 2011-11-16 09:39:10 +0200 | [diff] [blame] | 1145 | 'deprecated', DeprecationWarning)): |
| 1146 | self.assertRaises(UnicodeDecodeError, internal.decode, |
| 1147 | "unicode_internal") |
Victor Stinner | e3b4715 | 2011-12-09 20:49:49 +0100 | [diff] [blame] | 1148 | if sys.byteorder == "little": |
| 1149 | invalid = b"\x00\x00\x11\x00" |
| 1150 | else: |
| 1151 | invalid = b"\x00\x11\x00\x00" |
| 1152 | with support.check_warnings(): |
| 1153 | self.assertRaises(UnicodeDecodeError, |
| 1154 | invalid.decode, "unicode_internal") |
| 1155 | with support.check_warnings(): |
| 1156 | self.assertEqual(invalid.decode("unicode_internal", "replace"), |
| 1157 | '\ufffd') |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1158 | |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1159 | @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t') |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1160 | def test_decode_error_attributes(self): |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1161 | try: |
Ezio Melotti | 345379a | 2011-11-16 09:54:19 +0200 | [diff] [blame] | 1162 | with support.check_warnings(('unicode_internal codec has been ' |
Ezio Melotti | 11060a4 | 2011-11-16 09:39:10 +0200 | [diff] [blame] | 1163 | 'deprecated', DeprecationWarning)): |
| 1164 | b"\x00\x00\x00\x00\x00\x11\x11\x00".decode("unicode_internal") |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1165 | except UnicodeDecodeError as ex: |
| 1166 | self.assertEqual("unicode_internal", ex.encoding) |
| 1167 | self.assertEqual(b"\x00\x00\x00\x00\x00\x11\x11\x00", ex.object) |
| 1168 | self.assertEqual(4, ex.start) |
| 1169 | self.assertEqual(8, ex.end) |
| 1170 | else: |
| 1171 | self.fail() |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1172 | |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1173 | @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t') |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1174 | def test_decode_callback(self): |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1175 | codecs.register_error("UnicodeInternalTest", codecs.ignore_errors) |
| 1176 | decoder = codecs.getdecoder("unicode_internal") |
Ezio Melotti | 345379a | 2011-11-16 09:54:19 +0200 | [diff] [blame] | 1177 | with support.check_warnings(('unicode_internal codec has been ' |
Ezio Melotti | 11060a4 | 2011-11-16 09:39:10 +0200 | [diff] [blame] | 1178 | 'deprecated', DeprecationWarning)): |
| 1179 | ab = "ab".encode("unicode_internal").decode() |
| 1180 | ignored = decoder(bytes("%s\x22\x22\x22\x22%s" % (ab[:4], ab[4:]), |
| 1181 | "ascii"), |
| 1182 | "UnicodeInternalTest") |
Victor Stinner | 182d90d | 2011-09-29 19:53:55 +0200 | [diff] [blame] | 1183 | self.assertEqual(("ab", 12), ignored) |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 1184 | |
Walter Dörwald | 8dc33d5 | 2009-05-06 14:41:26 +0000 | [diff] [blame] | 1185 | def test_encode_length(self): |
Ezio Melotti | adc417c | 2011-11-17 12:23:34 +0200 | [diff] [blame] | 1186 | with support.check_warnings(('unicode_internal codec has been ' |
| 1187 | 'deprecated', DeprecationWarning)): |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 1188 | # Issue 3739 |
| 1189 | encoder = codecs.getencoder("unicode_internal") |
| 1190 | self.assertEqual(encoder("a")[1], 1) |
| 1191 | self.assertEqual(encoder("\xe9\u0142")[1], 2) |
| 1192 | |
| 1193 | self.assertEqual(codecs.escape_encode(br'\x00')[1], 4) |
Philip Jenvey | 66a1bd5 | 2010-04-05 03:05:24 +0000 | [diff] [blame] | 1194 | |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1195 | # From http://www.gnu.org/software/libidn/draft-josefsson-idn-test-vectors.html |
| 1196 | nameprep_tests = [ |
| 1197 | # 3.1 Map to nothing. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1198 | (b'foo\xc2\xad\xcd\x8f\xe1\xa0\x86\xe1\xa0\x8bbar' |
| 1199 | b'\xe2\x80\x8b\xe2\x81\xa0baz\xef\xb8\x80\xef\xb8\x88\xef' |
| 1200 | b'\xb8\x8f\xef\xbb\xbf', |
| 1201 | b'foobarbaz'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1202 | # 3.2 Case folding ASCII U+0043 U+0041 U+0046 U+0045. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1203 | (b'CAFE', |
| 1204 | b'cafe'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1205 | # 3.3 Case folding 8bit U+00DF (german sharp s). |
| 1206 | # The original test case is bogus; it says \xc3\xdf |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1207 | (b'\xc3\x9f', |
| 1208 | b'ss'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1209 | # 3.4 Case folding U+0130 (turkish capital I with dot). |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1210 | (b'\xc4\xb0', |
| 1211 | b'i\xcc\x87'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1212 | # 3.5 Case folding multibyte U+0143 U+037A. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1213 | (b'\xc5\x83\xcd\xba', |
| 1214 | b'\xc5\x84 \xce\xb9'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1215 | # 3.6 Case folding U+2121 U+33C6 U+1D7BB. |
| 1216 | # XXX: skip this as it fails in UCS-2 mode |
| 1217 | #('\xe2\x84\xa1\xe3\x8f\x86\xf0\x9d\x9e\xbb', |
| 1218 | # 'telc\xe2\x88\x95kg\xcf\x83'), |
| 1219 | (None, None), |
| 1220 | # 3.7 Normalization of U+006a U+030c U+00A0 U+00AA. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1221 | (b'j\xcc\x8c\xc2\xa0\xc2\xaa', |
| 1222 | b'\xc7\xb0 a'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1223 | # 3.8 Case folding U+1FB7 and normalization. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1224 | (b'\xe1\xbe\xb7', |
| 1225 | b'\xe1\xbe\xb6\xce\xb9'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1226 | # 3.9 Self-reverting case folding U+01F0 and normalization. |
| 1227 | # The original test case is bogus, it says `\xc7\xf0' |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1228 | (b'\xc7\xb0', |
| 1229 | b'\xc7\xb0'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1230 | # 3.10 Self-reverting case folding U+0390 and normalization. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1231 | (b'\xce\x90', |
| 1232 | b'\xce\x90'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1233 | # 3.11 Self-reverting case folding U+03B0 and normalization. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1234 | (b'\xce\xb0', |
| 1235 | b'\xce\xb0'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1236 | # 3.12 Self-reverting case folding U+1E96 and normalization. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1237 | (b'\xe1\xba\x96', |
| 1238 | b'\xe1\xba\x96'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1239 | # 3.13 Self-reverting case folding U+1F56 and normalization. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1240 | (b'\xe1\xbd\x96', |
| 1241 | b'\xe1\xbd\x96'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1242 | # 3.14 ASCII space character U+0020. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1243 | (b' ', |
| 1244 | b' '), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1245 | # 3.15 Non-ASCII 8bit space character U+00A0. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1246 | (b'\xc2\xa0', |
| 1247 | b' '), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1248 | # 3.16 Non-ASCII multibyte space character U+1680. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1249 | (b'\xe1\x9a\x80', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1250 | None), |
| 1251 | # 3.17 Non-ASCII multibyte space character U+2000. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1252 | (b'\xe2\x80\x80', |
| 1253 | b' '), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1254 | # 3.18 Zero Width Space U+200b. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1255 | (b'\xe2\x80\x8b', |
| 1256 | b''), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1257 | # 3.19 Non-ASCII multibyte space character U+3000. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1258 | (b'\xe3\x80\x80', |
| 1259 | b' '), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1260 | # 3.20 ASCII control characters U+0010 U+007F. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1261 | (b'\x10\x7f', |
| 1262 | b'\x10\x7f'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1263 | # 3.21 Non-ASCII 8bit control character U+0085. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1264 | (b'\xc2\x85', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1265 | None), |
| 1266 | # 3.22 Non-ASCII multibyte control character U+180E. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1267 | (b'\xe1\xa0\x8e', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1268 | None), |
| 1269 | # 3.23 Zero Width No-Break Space U+FEFF. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1270 | (b'\xef\xbb\xbf', |
| 1271 | b''), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1272 | # 3.24 Non-ASCII control character U+1D175. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1273 | (b'\xf0\x9d\x85\xb5', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1274 | None), |
| 1275 | # 3.25 Plane 0 private use character U+F123. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1276 | (b'\xef\x84\xa3', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1277 | None), |
| 1278 | # 3.26 Plane 15 private use character U+F1234. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1279 | (b'\xf3\xb1\x88\xb4', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1280 | None), |
| 1281 | # 3.27 Plane 16 private use character U+10F234. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1282 | (b'\xf4\x8f\x88\xb4', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1283 | None), |
| 1284 | # 3.28 Non-character code point U+8FFFE. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1285 | (b'\xf2\x8f\xbf\xbe', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1286 | None), |
| 1287 | # 3.29 Non-character code point U+10FFFF. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1288 | (b'\xf4\x8f\xbf\xbf', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1289 | None), |
| 1290 | # 3.30 Surrogate code U+DF42. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1291 | (b'\xed\xbd\x82', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1292 | None), |
| 1293 | # 3.31 Non-plain text character U+FFFD. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1294 | (b'\xef\xbf\xbd', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1295 | None), |
| 1296 | # 3.32 Ideographic description character U+2FF5. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1297 | (b'\xe2\xbf\xb5', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1298 | None), |
| 1299 | # 3.33 Display property character U+0341. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1300 | (b'\xcd\x81', |
| 1301 | b'\xcc\x81'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1302 | # 3.34 Left-to-right mark U+200E. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1303 | (b'\xe2\x80\x8e', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1304 | None), |
| 1305 | # 3.35 Deprecated U+202A. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1306 | (b'\xe2\x80\xaa', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1307 | None), |
| 1308 | # 3.36 Language tagging character U+E0001. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1309 | (b'\xf3\xa0\x80\x81', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1310 | None), |
| 1311 | # 3.37 Language tagging character U+E0042. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1312 | (b'\xf3\xa0\x81\x82', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1313 | None), |
| 1314 | # 3.38 Bidi: RandALCat character U+05BE and LCat characters. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1315 | (b'foo\xd6\xbebar', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1316 | None), |
| 1317 | # 3.39 Bidi: RandALCat character U+FD50 and LCat characters. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1318 | (b'foo\xef\xb5\x90bar', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1319 | None), |
| 1320 | # 3.40 Bidi: RandALCat character U+FB38 and LCat characters. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1321 | (b'foo\xef\xb9\xb6bar', |
| 1322 | b'foo \xd9\x8ebar'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1323 | # 3.41 Bidi: RandALCat without trailing RandALCat U+0627 U+0031. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1324 | (b'\xd8\xa71', |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1325 | None), |
| 1326 | # 3.42 Bidi: RandALCat character U+0627 U+0031 U+0628. |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1327 | (b'\xd8\xa71\xd8\xa8', |
| 1328 | b'\xd8\xa71\xd8\xa8'), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1329 | # 3.43 Unassigned code point U+E0002. |
Martin v. Löwis | b5c4b7b | 2003-04-18 20:21:00 +0000 | [diff] [blame] | 1330 | # Skip this test as we allow unassigned |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1331 | #(b'\xf3\xa0\x80\x82', |
Martin v. Löwis | b5c4b7b | 2003-04-18 20:21:00 +0000 | [diff] [blame] | 1332 | # None), |
| 1333 | (None, None), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1334 | # 3.44 Larger test (shrinking). |
| 1335 | # Original test case reads \xc3\xdf |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1336 | (b'X\xc2\xad\xc3\x9f\xc4\xb0\xe2\x84\xa1j\xcc\x8c\xc2\xa0\xc2' |
| 1337 | b'\xaa\xce\xb0\xe2\x80\x80', |
| 1338 | b'xssi\xcc\x87tel\xc7\xb0 a\xce\xb0 '), |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1339 | # 3.45 Larger test (expanding). |
| 1340 | # Original test case reads \xc3\x9f |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1341 | (b'X\xc3\x9f\xe3\x8c\x96\xc4\xb0\xe2\x84\xa1\xe2\x92\x9f\xe3\x8c' |
| 1342 | b'\x80', |
| 1343 | b'xss\xe3\x82\xad\xe3\x83\xad\xe3\x83\xa1\xe3\x83\xbc\xe3' |
| 1344 | b'\x83\x88\xe3\x83\xabi\xcc\x87tel\x28d\x29\xe3\x82' |
| 1345 | b'\xa2\xe3\x83\x91\xe3\x83\xbc\xe3\x83\x88') |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1346 | ] |
| 1347 | |
| 1348 | |
| 1349 | class NameprepTest(unittest.TestCase): |
| 1350 | def test_nameprep(self): |
| 1351 | from encodings.idna import nameprep |
| 1352 | for pos, (orig, prepped) in enumerate(nameprep_tests): |
| 1353 | if orig is None: |
| 1354 | # Skipped |
| 1355 | continue |
| 1356 | # The Unicode strings are given in UTF-8 |
Martin v. Löwis | e0a2b72 | 2009-05-10 08:08:56 +0000 | [diff] [blame] | 1357 | orig = str(orig, "utf-8", "surrogatepass") |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1358 | if prepped is None: |
| 1359 | # Input contains prohibited characters |
| 1360 | self.assertRaises(UnicodeError, nameprep, orig) |
| 1361 | else: |
Martin v. Löwis | e0a2b72 | 2009-05-10 08:08:56 +0000 | [diff] [blame] | 1362 | prepped = str(prepped, "utf-8", "surrogatepass") |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1363 | try: |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1364 | self.assertEqual(nameprep(orig), prepped) |
Guido van Rossum | b940e11 | 2007-01-10 16:19:56 +0000 | [diff] [blame] | 1365 | except Exception as e: |
Benjamin Peterson | ee8712c | 2008-05-20 21:35:26 +0000 | [diff] [blame] | 1366 | raise support.TestFailed("Test 3.%d: %s" % (pos+1, str(e))) |
Martin v. Löwis | 2548c73 | 2003-04-18 10:39:54 +0000 | [diff] [blame] | 1367 | |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1368 | class IDNACodecTest(unittest.TestCase): |
| 1369 | def test_builtin_decode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1370 | self.assertEqual(str(b"python.org", "idna"), "python.org") |
| 1371 | self.assertEqual(str(b"python.org.", "idna"), "python.org.") |
| 1372 | self.assertEqual(str(b"xn--pythn-mua.org", "idna"), "pyth\xf6n.org") |
| 1373 | self.assertEqual(str(b"xn--pythn-mua.org.", "idna"), "pyth\xf6n.org.") |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1374 | |
| 1375 | def test_builtin_encode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1376 | self.assertEqual("python.org".encode("idna"), b"python.org") |
| 1377 | self.assertEqual("python.org.".encode("idna"), b"python.org.") |
| 1378 | self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org") |
| 1379 | self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.") |
Martin v. Löwis | a1dde13 | 2004-03-24 16:48:24 +0000 | [diff] [blame] | 1380 | |
Martin v. Löwis | 8b59514 | 2005-08-25 11:03:38 +0000 | [diff] [blame] | 1381 | def test_stream(self): |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1382 | r = codecs.getreader("idna")(io.BytesIO(b"abc")) |
Martin v. Löwis | 8b59514 | 2005-08-25 11:03:38 +0000 | [diff] [blame] | 1383 | r.read(3) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1384 | self.assertEqual(r.read(), "") |
Martin v. Löwis | 8b59514 | 2005-08-25 11:03:38 +0000 | [diff] [blame] | 1385 | |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1386 | def test_incremental_decode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1387 | self.assertEqual( |
Guido van Rossum | 09549f4 | 2007-08-27 20:40:10 +0000 | [diff] [blame] | 1388 | "".join(codecs.iterdecode((bytes([c]) for c in b"python.org"), "idna")), |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1389 | "python.org" |
| 1390 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1391 | self.assertEqual( |
Guido van Rossum | 09549f4 | 2007-08-27 20:40:10 +0000 | [diff] [blame] | 1392 | "".join(codecs.iterdecode((bytes([c]) for c in b"python.org."), "idna")), |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1393 | "python.org." |
| 1394 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1395 | self.assertEqual( |
Guido van Rossum | 09549f4 | 2007-08-27 20:40:10 +0000 | [diff] [blame] | 1396 | "".join(codecs.iterdecode((bytes([c]) for c in b"xn--pythn-mua.org."), "idna")), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1397 | "pyth\xf6n.org." |
| 1398 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1399 | self.assertEqual( |
Guido van Rossum | 09549f4 | 2007-08-27 20:40:10 +0000 | [diff] [blame] | 1400 | "".join(codecs.iterdecode((bytes([c]) for c in b"xn--pythn-mua.org."), "idna")), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1401 | "pyth\xf6n.org." |
| 1402 | ) |
| 1403 | |
| 1404 | decoder = codecs.getincrementaldecoder("idna")() |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1405 | self.assertEqual(decoder.decode(b"xn--xam", ), "") |
| 1406 | self.assertEqual(decoder.decode(b"ple-9ta.o", ), "\xe4xample.") |
| 1407 | self.assertEqual(decoder.decode(b"rg"), "") |
| 1408 | self.assertEqual(decoder.decode(b"", True), "org") |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1409 | |
| 1410 | decoder.reset() |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1411 | self.assertEqual(decoder.decode(b"xn--xam", ), "") |
| 1412 | self.assertEqual(decoder.decode(b"ple-9ta.o", ), "\xe4xample.") |
| 1413 | self.assertEqual(decoder.decode(b"rg."), "org.") |
| 1414 | self.assertEqual(decoder.decode(b"", True), "") |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1415 | |
| 1416 | def test_incremental_encode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1417 | self.assertEqual( |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1418 | b"".join(codecs.iterencode("python.org", "idna")), |
| 1419 | b"python.org" |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1420 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1421 | self.assertEqual( |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1422 | b"".join(codecs.iterencode("python.org.", "idna")), |
| 1423 | b"python.org." |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1424 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1425 | self.assertEqual( |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1426 | b"".join(codecs.iterencode("pyth\xf6n.org.", "idna")), |
| 1427 | b"xn--pythn-mua.org." |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1428 | ) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1429 | self.assertEqual( |
Walter Dörwald | 0ac30f8 | 2007-05-11 10:32:57 +0000 | [diff] [blame] | 1430 | b"".join(codecs.iterencode("pyth\xf6n.org.", "idna")), |
| 1431 | b"xn--pythn-mua.org." |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1432 | ) |
| 1433 | |
| 1434 | encoder = codecs.getincrementalencoder("idna")() |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1435 | self.assertEqual(encoder.encode("\xe4x"), b"") |
| 1436 | self.assertEqual(encoder.encode("ample.org"), b"xn--xample-9ta.") |
| 1437 | self.assertEqual(encoder.encode("", True), b"org") |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1438 | |
| 1439 | encoder.reset() |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1440 | self.assertEqual(encoder.encode("\xe4x"), b"") |
| 1441 | self.assertEqual(encoder.encode("ample.org."), b"xn--xample-9ta.org.") |
| 1442 | self.assertEqual(encoder.encode("", True), b"") |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1443 | |
Marc-André Lemburg | 3f41974 | 2004-07-10 12:06:10 +0000 | [diff] [blame] | 1444 | class CodecsModuleTest(unittest.TestCase): |
| 1445 | |
| 1446 | def test_decode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1447 | self.assertEqual(codecs.decode(b'\xe4\xf6\xfc', 'latin-1'), |
| 1448 | '\xe4\xf6\xfc') |
Walter Dörwald | 063e1e8 | 2004-10-28 13:04:26 +0000 | [diff] [blame] | 1449 | self.assertRaises(TypeError, codecs.decode) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1450 | self.assertEqual(codecs.decode(b'abc'), 'abc') |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1451 | self.assertRaises(UnicodeDecodeError, codecs.decode, b'\xff', 'ascii') |
Walter Dörwald | 063e1e8 | 2004-10-28 13:04:26 +0000 | [diff] [blame] | 1452 | |
Marc-André Lemburg | 3f41974 | 2004-07-10 12:06:10 +0000 | [diff] [blame] | 1453 | def test_encode(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1454 | self.assertEqual(codecs.encode('\xe4\xf6\xfc', 'latin-1'), |
| 1455 | b'\xe4\xf6\xfc') |
Walter Dörwald | 063e1e8 | 2004-10-28 13:04:26 +0000 | [diff] [blame] | 1456 | self.assertRaises(TypeError, codecs.encode) |
Walter Dörwald | 690402f | 2005-11-17 18:51:34 +0000 | [diff] [blame] | 1457 | self.assertRaises(LookupError, codecs.encode, "foo", "__spam__") |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1458 | self.assertEqual(codecs.encode('abc'), b'abc') |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1459 | self.assertRaises(UnicodeEncodeError, codecs.encode, '\xffff', 'ascii') |
Walter Dörwald | 063e1e8 | 2004-10-28 13:04:26 +0000 | [diff] [blame] | 1460 | |
| 1461 | def test_register(self): |
| 1462 | self.assertRaises(TypeError, codecs.register) |
Walter Dörwald | 690402f | 2005-11-17 18:51:34 +0000 | [diff] [blame] | 1463 | self.assertRaises(TypeError, codecs.register, 42) |
Walter Dörwald | 063e1e8 | 2004-10-28 13:04:26 +0000 | [diff] [blame] | 1464 | |
| 1465 | def test_lookup(self): |
| 1466 | self.assertRaises(TypeError, codecs.lookup) |
| 1467 | self.assertRaises(LookupError, codecs.lookup, "__spam__") |
Walter Dörwald | 690402f | 2005-11-17 18:51:34 +0000 | [diff] [blame] | 1468 | self.assertRaises(LookupError, codecs.lookup, " ") |
| 1469 | |
| 1470 | def test_getencoder(self): |
| 1471 | self.assertRaises(TypeError, codecs.getencoder) |
| 1472 | self.assertRaises(LookupError, codecs.getencoder, "__spam__") |
| 1473 | |
| 1474 | def test_getdecoder(self): |
| 1475 | self.assertRaises(TypeError, codecs.getdecoder) |
| 1476 | self.assertRaises(LookupError, codecs.getdecoder, "__spam__") |
| 1477 | |
| 1478 | def test_getreader(self): |
| 1479 | self.assertRaises(TypeError, codecs.getreader) |
| 1480 | self.assertRaises(LookupError, codecs.getreader, "__spam__") |
| 1481 | |
| 1482 | def test_getwriter(self): |
| 1483 | self.assertRaises(TypeError, codecs.getwriter) |
| 1484 | self.assertRaises(LookupError, codecs.getwriter, "__spam__") |
Marc-André Lemburg | 3f41974 | 2004-07-10 12:06:10 +0000 | [diff] [blame] | 1485 | |
Antoine Pitrou | cf9d3c0 | 2011-07-24 02:27:04 +0200 | [diff] [blame] | 1486 | def test_lookup_issue1813(self): |
| 1487 | # Issue #1813: under Turkish locales, lookup of some codecs failed |
| 1488 | # because 'I' is lowercased as "ı" (dotless i) |
Antoine Pitrou | d05066d | 2011-07-26 23:55:33 +0200 | [diff] [blame] | 1489 | oldlocale = locale.setlocale(locale.LC_CTYPE) |
Antoine Pitrou | cf9d3c0 | 2011-07-24 02:27:04 +0200 | [diff] [blame] | 1490 | self.addCleanup(locale.setlocale, locale.LC_CTYPE, oldlocale) |
| 1491 | try: |
| 1492 | locale.setlocale(locale.LC_CTYPE, 'tr_TR') |
| 1493 | except locale.Error: |
| 1494 | # Unsupported locale on this system |
| 1495 | self.skipTest('test needs Turkish locale') |
| 1496 | c = codecs.lookup('ASCII') |
| 1497 | self.assertEqual(c.name, 'ascii') |
| 1498 | |
Hye-Shik Chang | af5c7cf | 2004-10-17 23:51:21 +0000 | [diff] [blame] | 1499 | class StreamReaderTest(unittest.TestCase): |
| 1500 | |
| 1501 | def setUp(self): |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1502 | self.reader = codecs.getreader('utf-8') |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 1503 | self.stream = io.BytesIO(b'\xed\x95\x9c\n\xea\xb8\x80') |
Hye-Shik Chang | af5c7cf | 2004-10-17 23:51:21 +0000 | [diff] [blame] | 1504 | |
| 1505 | def test_readlines(self): |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1506 | f = self.reader(self.stream) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1507 | self.assertEqual(f.readlines(), ['\ud55c\n', '\uae00']) |
Hye-Shik Chang | af5c7cf | 2004-10-17 23:51:21 +0000 | [diff] [blame] | 1508 | |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1509 | class EncodedFileTest(unittest.TestCase): |
| 1510 | |
| 1511 | def test_basic(self): |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 1512 | f = io.BytesIO(b'\xed\x95\x9c\n\xea\xb8\x80') |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1513 | ef = codecs.EncodedFile(f, 'utf-16-le', 'utf-8') |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1514 | self.assertEqual(ef.read(), b'\\\xd5\n\x00\x00\xae') |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1515 | |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 1516 | f = io.BytesIO() |
Marc-André Lemburg | 8f36af7 | 2011-02-25 15:42:01 +0000 | [diff] [blame] | 1517 | ef = codecs.EncodedFile(f, 'utf-8', 'latin-1') |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1518 | ef.write(b'\xc3\xbc') |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1519 | self.assertEqual(f.getvalue(), b'\xfc') |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1520 | |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1521 | all_unicode_encodings = [ |
| 1522 | "ascii", |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1523 | "big5", |
| 1524 | "big5hkscs", |
| 1525 | "charmap", |
| 1526 | "cp037", |
| 1527 | "cp1006", |
| 1528 | "cp1026", |
| 1529 | "cp1140", |
| 1530 | "cp1250", |
| 1531 | "cp1251", |
| 1532 | "cp1252", |
| 1533 | "cp1253", |
| 1534 | "cp1254", |
| 1535 | "cp1255", |
| 1536 | "cp1256", |
| 1537 | "cp1257", |
| 1538 | "cp1258", |
| 1539 | "cp424", |
| 1540 | "cp437", |
| 1541 | "cp500", |
Benjamin Peterson | 5a6214a | 2010-06-27 22:41:29 +0000 | [diff] [blame] | 1542 | "cp720", |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1543 | "cp737", |
| 1544 | "cp775", |
| 1545 | "cp850", |
| 1546 | "cp852", |
| 1547 | "cp855", |
| 1548 | "cp856", |
| 1549 | "cp857", |
Benjamin Peterson | 5a6214a | 2010-06-27 22:41:29 +0000 | [diff] [blame] | 1550 | "cp858", |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1551 | "cp860", |
| 1552 | "cp861", |
| 1553 | "cp862", |
| 1554 | "cp863", |
| 1555 | "cp864", |
| 1556 | "cp865", |
| 1557 | "cp866", |
| 1558 | "cp869", |
| 1559 | "cp874", |
| 1560 | "cp875", |
| 1561 | "cp932", |
| 1562 | "cp949", |
| 1563 | "cp950", |
| 1564 | "euc_jis_2004", |
| 1565 | "euc_jisx0213", |
| 1566 | "euc_jp", |
| 1567 | "euc_kr", |
| 1568 | "gb18030", |
| 1569 | "gb2312", |
| 1570 | "gbk", |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1571 | "hp_roman8", |
| 1572 | "hz", |
| 1573 | "idna", |
| 1574 | "iso2022_jp", |
| 1575 | "iso2022_jp_1", |
| 1576 | "iso2022_jp_2", |
| 1577 | "iso2022_jp_2004", |
| 1578 | "iso2022_jp_3", |
| 1579 | "iso2022_jp_ext", |
| 1580 | "iso2022_kr", |
| 1581 | "iso8859_1", |
| 1582 | "iso8859_10", |
| 1583 | "iso8859_11", |
| 1584 | "iso8859_13", |
| 1585 | "iso8859_14", |
| 1586 | "iso8859_15", |
| 1587 | "iso8859_16", |
| 1588 | "iso8859_2", |
| 1589 | "iso8859_3", |
| 1590 | "iso8859_4", |
| 1591 | "iso8859_5", |
| 1592 | "iso8859_6", |
| 1593 | "iso8859_7", |
| 1594 | "iso8859_8", |
| 1595 | "iso8859_9", |
| 1596 | "johab", |
| 1597 | "koi8_r", |
| 1598 | "koi8_u", |
| 1599 | "latin_1", |
| 1600 | "mac_cyrillic", |
| 1601 | "mac_greek", |
| 1602 | "mac_iceland", |
| 1603 | "mac_latin2", |
| 1604 | "mac_roman", |
| 1605 | "mac_turkish", |
| 1606 | "palmos", |
| 1607 | "ptcp154", |
| 1608 | "punycode", |
| 1609 | "raw_unicode_escape", |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1610 | "shift_jis", |
| 1611 | "shift_jis_2004", |
| 1612 | "shift_jisx0213", |
| 1613 | "tis_620", |
| 1614 | "unicode_escape", |
| 1615 | "unicode_internal", |
| 1616 | "utf_16", |
| 1617 | "utf_16_be", |
| 1618 | "utf_16_le", |
| 1619 | "utf_7", |
| 1620 | "utf_8", |
| 1621 | ] |
| 1622 | |
| 1623 | if hasattr(codecs, "mbcs_encode"): |
| 1624 | all_unicode_encodings.append("mbcs") |
| 1625 | |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1626 | # The following encoding is not tested, because it's not supposed |
| 1627 | # to work: |
| 1628 | # "undefined" |
| 1629 | |
| 1630 | # The following encodings don't work in stateful mode |
| 1631 | broken_unicode_with_streams = [ |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1632 | "punycode", |
| 1633 | "unicode_internal" |
| 1634 | ] |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 1635 | broken_incremental_coders = broken_unicode_with_streams + [ |
| 1636 | "idna", |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 1637 | ] |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1638 | |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 1639 | class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1640 | def test_basics(self): |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1641 | s = "abc123" # all codecs should be able to encode these |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1642 | for encoding in all_unicode_encodings: |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1643 | name = codecs.lookup(encoding).name |
| 1644 | if encoding.endswith("_codec"): |
| 1645 | name += "_codec" |
| 1646 | elif encoding == "latin_1": |
| 1647 | name = "latin_1" |
| 1648 | self.assertEqual(encoding.replace("_", "-"), name.replace("_", "-")) |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 1649 | |
Ezio Melotti | adc417c | 2011-11-17 12:23:34 +0200 | [diff] [blame] | 1650 | with support.check_warnings(): |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 1651 | # unicode-internal has been deprecated |
Victor Stinner | 040e16e | 2011-11-15 22:44:05 +0100 | [diff] [blame] | 1652 | (b, size) = codecs.getencoder(encoding)(s) |
| 1653 | self.assertEqual(size, len(s), "%r != %r (encoding=%r)" % (size, len(s), encoding)) |
| 1654 | (chars, size) = codecs.getdecoder(encoding)(b) |
| 1655 | self.assertEqual(chars, s, "%r != %r (encoding=%r)" % (chars, s, encoding)) |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1656 | |
| 1657 | if encoding not in broken_unicode_with_streams: |
| 1658 | # check stream reader/writer |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1659 | q = Queue(b"") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1660 | writer = codecs.getwriter(encoding)(q) |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1661 | encodedresult = b"" |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1662 | for c in s: |
| 1663 | writer.write(c) |
Guido van Rossum | 98297ee | 2007-11-06 21:34:58 +0000 | [diff] [blame] | 1664 | chunk = q.read() |
Benjamin Peterson | c9c0f20 | 2009-06-30 23:06:06 +0000 | [diff] [blame] | 1665 | self.assertTrue(type(chunk) is bytes, type(chunk)) |
Guido van Rossum | 98297ee | 2007-11-06 21:34:58 +0000 | [diff] [blame] | 1666 | encodedresult += chunk |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1667 | q = Queue(b"") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1668 | reader = codecs.getreader(encoding)(q) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1669 | decodedresult = "" |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1670 | for c in encodedresult: |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1671 | q.write(bytes([c])) |
Walter Dörwald | ee1d247 | 2004-12-29 16:04:38 +0000 | [diff] [blame] | 1672 | decodedresult += reader.read() |
| 1673 | self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) |
| 1674 | |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1675 | if encoding not in broken_incremental_coders: |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1676 | # check incremental decoder/encoder (fetched via the Python |
| 1677 | # and C API) and iterencode()/iterdecode() |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1678 | try: |
| 1679 | encoder = codecs.getincrementalencoder(encoding)() |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1680 | cencoder = _testcapi.codec_incrementalencoder(encoding) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1681 | except LookupError: # no IncrementalEncoder |
| 1682 | pass |
| 1683 | else: |
| 1684 | # check incremental decoder/encoder |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1685 | encodedresult = b"" |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1686 | for c in s: |
| 1687 | encodedresult += encoder.encode(c) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1688 | encodedresult += encoder.encode("", True) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1689 | decoder = codecs.getincrementaldecoder(encoding)() |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1690 | decodedresult = "" |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1691 | for c in encodedresult: |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1692 | decodedresult += decoder.decode(bytes([c])) |
Guido van Rossum | f4cfc8f | 2007-05-17 21:52:23 +0000 | [diff] [blame] | 1693 | decodedresult += decoder.decode(b"", True) |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1694 | self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) |
| 1695 | |
| 1696 | # check C API |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1697 | encodedresult = b"" |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1698 | for c in s: |
| 1699 | encodedresult += cencoder.encode(c) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1700 | encodedresult += cencoder.encode("", True) |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1701 | cdecoder = _testcapi.codec_incrementaldecoder(encoding) |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1702 | decodedresult = "" |
Thomas Wouters | 49fd7fa | 2006-04-21 10:40:58 +0000 | [diff] [blame] | 1703 | for c in encodedresult: |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1704 | decodedresult += cdecoder.decode(bytes([c])) |
Guido van Rossum | f4cfc8f | 2007-05-17 21:52:23 +0000 | [diff] [blame] | 1705 | decodedresult += cdecoder.decode(b"", True) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1706 | self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) |
| 1707 | |
| 1708 | # check iterencode()/iterdecode() |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1709 | result = "".join(codecs.iterdecode(codecs.iterencode(s, encoding), encoding)) |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1710 | self.assertEqual(result, s, "%r != %r (encoding=%r)" % (result, s, encoding)) |
| 1711 | |
| 1712 | # check iterencode()/iterdecode() with empty string |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1713 | result = "".join(codecs.iterdecode(codecs.iterencode("", encoding), encoding)) |
| 1714 | self.assertEqual(result, "") |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1715 | |
Victor Stinner | 554f3f0 | 2010-06-16 23:33:54 +0000 | [diff] [blame] | 1716 | if encoding not in ("idna", "mbcs"): |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1717 | # check incremental decoder/encoder with errors argument |
| 1718 | try: |
| 1719 | encoder = codecs.getincrementalencoder(encoding)("ignore") |
| 1720 | cencoder = _testcapi.codec_incrementalencoder(encoding, "ignore") |
| 1721 | except LookupError: # no IncrementalEncoder |
| 1722 | pass |
| 1723 | else: |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1724 | encodedresult = b"".join(encoder.encode(c) for c in s) |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1725 | decoder = codecs.getincrementaldecoder(encoding)("ignore") |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1726 | decodedresult = "".join(decoder.decode(bytes([c])) for c in encodedresult) |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1727 | self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) |
| 1728 | |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1729 | encodedresult = b"".join(cencoder.encode(c) for c in s) |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1730 | cdecoder = _testcapi.codec_incrementaldecoder(encoding, "ignore") |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1731 | decodedresult = "".join(cdecoder.decode(bytes([c])) for c in encodedresult) |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1732 | self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) |
| 1733 | |
Walter Dörwald | 729c31f | 2005-03-14 19:06:30 +0000 | [diff] [blame] | 1734 | def test_seek(self): |
| 1735 | # all codecs should be able to encode these |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1736 | s = "%s\n%s\n" % (100*"abc123", 100*"def456") |
Walter Dörwald | 729c31f | 2005-03-14 19:06:30 +0000 | [diff] [blame] | 1737 | for encoding in all_unicode_encodings: |
| 1738 | if encoding == "idna": # FIXME: See SF bug #1163178 |
| 1739 | continue |
| 1740 | if encoding in broken_unicode_with_streams: |
| 1741 | continue |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1742 | reader = codecs.getreader(encoding)(io.BytesIO(s.encode(encoding))) |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 1743 | for t in range(5): |
Walter Dörwald | 729c31f | 2005-03-14 19:06:30 +0000 | [diff] [blame] | 1744 | # Test that calling seek resets the internal codec state and buffers |
| 1745 | reader.seek(0, 0) |
Guido van Rossum | f4cfc8f | 2007-05-17 21:52:23 +0000 | [diff] [blame] | 1746 | data = reader.read() |
| 1747 | self.assertEqual(s, data) |
Walter Dörwald | 729c31f | 2005-03-14 19:06:30 +0000 | [diff] [blame] | 1748 | |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 1749 | def test_bad_decode_args(self): |
| 1750 | for encoding in all_unicode_encodings: |
| 1751 | decoder = codecs.getdecoder(encoding) |
| 1752 | self.assertRaises(TypeError, decoder) |
| 1753 | if encoding not in ("idna", "punycode"): |
| 1754 | self.assertRaises(TypeError, decoder, 42) |
| 1755 | |
| 1756 | def test_bad_encode_args(self): |
| 1757 | for encoding in all_unicode_encodings: |
| 1758 | encoder = codecs.getencoder(encoding) |
Ezio Melotti | adc417c | 2011-11-17 12:23:34 +0200 | [diff] [blame] | 1759 | with support.check_warnings(): |
| 1760 | # unicode-internal has been deprecated |
| 1761 | self.assertRaises(TypeError, encoder) |
Walter Dörwald | e22d339 | 2005-11-17 08:52:34 +0000 | [diff] [blame] | 1762 | |
Thomas Wouters | 0e3f591 | 2006-08-11 14:57:12 +0000 | [diff] [blame] | 1763 | def test_encoding_map_type_initialized(self): |
| 1764 | from encodings import cp1140 |
| 1765 | # This used to crash, we are only verifying there's no crash. |
| 1766 | table_type = type(cp1140.encoding_table) |
| 1767 | self.assertEqual(table_type, table_type) |
| 1768 | |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 1769 | def test_decoder_state(self): |
| 1770 | # Check that getstate() and setstate() handle the state properly |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1771 | u = "abc123" |
Walter Dörwald | 3abcb01 | 2007-04-16 22:10:50 +0000 | [diff] [blame] | 1772 | for encoding in all_unicode_encodings: |
| 1773 | if encoding not in broken_incremental_coders: |
| 1774 | self.check_state_handling_decode(encoding, u, u.encode(encoding)) |
| 1775 | self.check_state_handling_encode(encoding, u, u.encode(encoding)) |
| 1776 | |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1777 | class CharmapTest(unittest.TestCase): |
| 1778 | def test_decode_with_string_map(self): |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1779 | self.assertEqual( |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1780 | codecs.charmap_decode(b"\x00\x01\x02", "strict", "abc"), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1781 | ("abc", 3) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1782 | ) |
| 1783 | |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1784 | self.assertEqual( |
Antoine Pitrou | a1f7655 | 2012-09-23 20:00:04 +0200 | [diff] [blame] | 1785 | codecs.charmap_decode(b"\x00\x01\x02", "strict", "\U0010FFFFbc"), |
| 1786 | ("\U0010FFFFbc", 3) |
| 1787 | ) |
| 1788 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1789 | self.assertRaises(UnicodeDecodeError, |
| 1790 | codecs.charmap_decode, b"\x00\x01\x02", "strict", "ab" |
| 1791 | ) |
| 1792 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1793 | self.assertRaises(UnicodeDecodeError, |
| 1794 | codecs.charmap_decode, b"\x00\x01\x02", "strict", "ab\ufffe" |
| 1795 | ) |
| 1796 | |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1797 | self.assertEqual( |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1798 | codecs.charmap_decode(b"\x00\x01\x02", "replace", "ab"), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1799 | ("ab\ufffd", 3) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1800 | ) |
| 1801 | |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1802 | self.assertEqual( |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1803 | codecs.charmap_decode(b"\x00\x01\x02", "replace", "ab\ufffe"), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1804 | ("ab\ufffd", 3) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1805 | ) |
| 1806 | |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1807 | self.assertEqual( |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1808 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", "ab"), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1809 | ("ab", 3) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1810 | ) |
| 1811 | |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1812 | self.assertEqual( |
Walter Dörwald | ca8a8d0 | 2007-05-04 13:05:09 +0000 | [diff] [blame] | 1813 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", "ab\ufffe"), |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1814 | ("ab", 3) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1815 | ) |
| 1816 | |
Guido van Rossum | 805365e | 2007-05-07 22:24:25 +0000 | [diff] [blame] | 1817 | allbytes = bytes(range(256)) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 1818 | self.assertEqual( |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 1819 | codecs.charmap_decode(allbytes, "ignore", ""), |
| 1820 | ("", len(allbytes)) |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 1821 | ) |
| 1822 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1823 | def test_decode_with_int2str_map(self): |
| 1824 | self.assertEqual( |
| 1825 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1826 | {0: 'a', 1: 'b', 2: 'c'}), |
| 1827 | ("abc", 3) |
| 1828 | ) |
| 1829 | |
| 1830 | self.assertEqual( |
| 1831 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1832 | {0: 'Aa', 1: 'Bb', 2: 'Cc'}), |
| 1833 | ("AaBbCc", 3) |
| 1834 | ) |
| 1835 | |
| 1836 | self.assertEqual( |
| 1837 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1838 | {0: '\U0010FFFF', 1: 'b', 2: 'c'}), |
| 1839 | ("\U0010FFFFbc", 3) |
| 1840 | ) |
| 1841 | |
| 1842 | self.assertEqual( |
| 1843 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1844 | {0: 'a', 1: 'b', 2: ''}), |
| 1845 | ("ab", 3) |
| 1846 | ) |
| 1847 | |
| 1848 | self.assertRaises(UnicodeDecodeError, |
| 1849 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
| 1850 | {0: 'a', 1: 'b'} |
| 1851 | ) |
| 1852 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1853 | self.assertRaises(UnicodeDecodeError, |
| 1854 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
| 1855 | {0: 'a', 1: 'b', 2: None} |
| 1856 | ) |
| 1857 | |
| 1858 | # Issue #14850 |
| 1859 | self.assertRaises(UnicodeDecodeError, |
| 1860 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
| 1861 | {0: 'a', 1: 'b', 2: '\ufffe'} |
| 1862 | ) |
| 1863 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1864 | self.assertEqual( |
| 1865 | codecs.charmap_decode(b"\x00\x01\x02", "replace", |
| 1866 | {0: 'a', 1: 'b'}), |
| 1867 | ("ab\ufffd", 3) |
| 1868 | ) |
| 1869 | |
| 1870 | self.assertEqual( |
| 1871 | codecs.charmap_decode(b"\x00\x01\x02", "replace", |
| 1872 | {0: 'a', 1: 'b', 2: None}), |
| 1873 | ("ab\ufffd", 3) |
| 1874 | ) |
| 1875 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1876 | # Issue #14850 |
| 1877 | self.assertEqual( |
| 1878 | codecs.charmap_decode(b"\x00\x01\x02", "replace", |
| 1879 | {0: 'a', 1: 'b', 2: '\ufffe'}), |
| 1880 | ("ab\ufffd", 3) |
| 1881 | ) |
| 1882 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1883 | self.assertEqual( |
| 1884 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", |
| 1885 | {0: 'a', 1: 'b'}), |
| 1886 | ("ab", 3) |
| 1887 | ) |
| 1888 | |
| 1889 | self.assertEqual( |
| 1890 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", |
| 1891 | {0: 'a', 1: 'b', 2: None}), |
| 1892 | ("ab", 3) |
| 1893 | ) |
| 1894 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1895 | # Issue #14850 |
| 1896 | self.assertEqual( |
| 1897 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", |
| 1898 | {0: 'a', 1: 'b', 2: '\ufffe'}), |
| 1899 | ("ab", 3) |
| 1900 | ) |
| 1901 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1902 | allbytes = bytes(range(256)) |
| 1903 | self.assertEqual( |
| 1904 | codecs.charmap_decode(allbytes, "ignore", {}), |
| 1905 | ("", len(allbytes)) |
| 1906 | ) |
| 1907 | |
| 1908 | def test_decode_with_int2int_map(self): |
| 1909 | a = ord('a') |
| 1910 | b = ord('b') |
| 1911 | c = ord('c') |
| 1912 | |
| 1913 | self.assertEqual( |
| 1914 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1915 | {0: a, 1: b, 2: c}), |
| 1916 | ("abc", 3) |
| 1917 | ) |
| 1918 | |
| 1919 | # Issue #15379 |
| 1920 | self.assertEqual( |
| 1921 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1922 | {0: 0x10FFFF, 1: b, 2: c}), |
| 1923 | ("\U0010FFFFbc", 3) |
| 1924 | ) |
| 1925 | |
Antoine Pitrou | a1f7655 | 2012-09-23 20:00:04 +0200 | [diff] [blame] | 1926 | self.assertEqual( |
| 1927 | codecs.charmap_decode(b"\x00\x01\x02", "strict", |
| 1928 | {0: sys.maxunicode, 1: b, 2: c}), |
| 1929 | (chr(sys.maxunicode) + "bc", 3) |
| 1930 | ) |
| 1931 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1932 | self.assertRaises(TypeError, |
| 1933 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
Antoine Pitrou | a1f7655 | 2012-09-23 20:00:04 +0200 | [diff] [blame] | 1934 | {0: sys.maxunicode + 1, 1: b, 2: c} |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1935 | ) |
| 1936 | |
| 1937 | self.assertRaises(UnicodeDecodeError, |
| 1938 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
| 1939 | {0: a, 1: b}, |
| 1940 | ) |
| 1941 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1942 | self.assertRaises(UnicodeDecodeError, |
| 1943 | codecs.charmap_decode, b"\x00\x01\x02", "strict", |
| 1944 | {0: a, 1: b, 2: 0xFFFE}, |
| 1945 | ) |
| 1946 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1947 | self.assertEqual( |
| 1948 | codecs.charmap_decode(b"\x00\x01\x02", "replace", |
| 1949 | {0: a, 1: b}), |
| 1950 | ("ab\ufffd", 3) |
| 1951 | ) |
| 1952 | |
| 1953 | self.assertEqual( |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1954 | codecs.charmap_decode(b"\x00\x01\x02", "replace", |
| 1955 | {0: a, 1: b, 2: 0xFFFE}), |
| 1956 | ("ab\ufffd", 3) |
| 1957 | ) |
| 1958 | |
| 1959 | self.assertEqual( |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1960 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", |
| 1961 | {0: a, 1: b}), |
| 1962 | ("ab", 3) |
| 1963 | ) |
| 1964 | |
Serhiy Storchaka | 4fb8cae | 2013-01-15 14:43:21 +0200 | [diff] [blame] | 1965 | self.assertEqual( |
| 1966 | codecs.charmap_decode(b"\x00\x01\x02", "ignore", |
| 1967 | {0: a, 1: b, 2: 0xFFFE}), |
| 1968 | ("ab", 3) |
| 1969 | ) |
| 1970 | |
Antoine Pitrou | 6f80f5d | 2012-09-23 19:55:21 +0200 | [diff] [blame] | 1971 | |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1972 | class WithStmtTest(unittest.TestCase): |
| 1973 | def test_encodedfile(self): |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 1974 | f = io.BytesIO(b"\xc3\xbc") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1975 | with codecs.EncodedFile(f, "latin-1", "utf-8") as ef: |
| 1976 | self.assertEqual(ef.read(), b"\xfc") |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1977 | |
| 1978 | def test_streamreaderwriter(self): |
Walter Dörwald | c3ab0a7 | 2007-05-10 15:02:49 +0000 | [diff] [blame] | 1979 | f = io.BytesIO(b"\xc3\xbc") |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1980 | info = codecs.lookup("utf-8") |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 1981 | with codecs.StreamReaderWriter(f, info.streamreader, |
| 1982 | info.streamwriter, 'strict') as srw: |
| 1983 | self.assertEqual(srw.read(), "\xfc") |
Thomas Wouters | 89f507f | 2006-12-13 04:49:30 +0000 | [diff] [blame] | 1984 | |
Antoine Pitrou | 81fabdb | 2009-01-22 10:11:36 +0000 | [diff] [blame] | 1985 | class TypesTest(unittest.TestCase): |
| 1986 | def test_decode_unicode(self): |
| 1987 | # Most decoders don't accept unicode input |
| 1988 | decoders = [ |
| 1989 | codecs.utf_7_decode, |
| 1990 | codecs.utf_8_decode, |
| 1991 | codecs.utf_16_le_decode, |
| 1992 | codecs.utf_16_be_decode, |
| 1993 | codecs.utf_16_ex_decode, |
| 1994 | codecs.utf_32_decode, |
| 1995 | codecs.utf_32_le_decode, |
| 1996 | codecs.utf_32_be_decode, |
| 1997 | codecs.utf_32_ex_decode, |
| 1998 | codecs.latin_1_decode, |
| 1999 | codecs.ascii_decode, |
| 2000 | codecs.charmap_decode, |
| 2001 | ] |
| 2002 | if hasattr(codecs, "mbcs_decode"): |
| 2003 | decoders.append(codecs.mbcs_decode) |
| 2004 | for decoder in decoders: |
| 2005 | self.assertRaises(TypeError, decoder, "xxx") |
| 2006 | |
| 2007 | def test_unicode_escape(self): |
| 2008 | # Escape-decoding an unicode string is supported ang gives the same |
| 2009 | # result as decoding the equivalent ASCII bytes string. |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2010 | self.assertEqual(codecs.unicode_escape_decode(r"\u1234"), ("\u1234", 6)) |
| 2011 | self.assertEqual(codecs.unicode_escape_decode(br"\u1234"), ("\u1234", 6)) |
| 2012 | self.assertEqual(codecs.raw_unicode_escape_decode(r"\u1234"), ("\u1234", 6)) |
| 2013 | self.assertEqual(codecs.raw_unicode_escape_decode(br"\u1234"), ("\u1234", 6)) |
Antoine Pitrou | 81fabdb | 2009-01-22 10:11:36 +0000 | [diff] [blame] | 2014 | |
Victor Stinner | e3b4715 | 2011-12-09 20:49:49 +0100 | [diff] [blame] | 2015 | self.assertRaises(UnicodeDecodeError, codecs.unicode_escape_decode, br"\U00110000") |
| 2016 | self.assertEqual(codecs.unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10)) |
| 2017 | |
| 2018 | self.assertRaises(UnicodeDecodeError, codecs.raw_unicode_escape_decode, br"\U00110000") |
| 2019 | self.assertEqual(codecs.raw_unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10)) |
| 2020 | |
Serhiy Storchaka | d679377 | 2013-01-29 10:20:44 +0200 | [diff] [blame] | 2021 | |
| 2022 | class UnicodeEscapeTest(unittest.TestCase): |
| 2023 | def test_empty(self): |
| 2024 | self.assertEqual(codecs.unicode_escape_encode(""), (b"", 0)) |
| 2025 | self.assertEqual(codecs.unicode_escape_decode(b""), ("", 0)) |
| 2026 | |
| 2027 | def test_raw_encode(self): |
| 2028 | encode = codecs.unicode_escape_encode |
| 2029 | for b in range(32, 127): |
| 2030 | if b != b'\\'[0]: |
| 2031 | self.assertEqual(encode(chr(b)), (bytes([b]), 1)) |
| 2032 | |
| 2033 | def test_raw_decode(self): |
| 2034 | decode = codecs.unicode_escape_decode |
| 2035 | for b in range(256): |
| 2036 | if b != b'\\'[0]: |
| 2037 | self.assertEqual(decode(bytes([b]) + b'0'), (chr(b) + '0', 2)) |
| 2038 | |
| 2039 | def test_escape_encode(self): |
| 2040 | encode = codecs.unicode_escape_encode |
| 2041 | check = coding_checker(self, encode) |
| 2042 | check('\t', br'\t') |
| 2043 | check('\n', br'\n') |
| 2044 | check('\r', br'\r') |
| 2045 | check('\\', br'\\') |
| 2046 | for b in range(32): |
| 2047 | if chr(b) not in '\t\n\r': |
| 2048 | check(chr(b), ('\\x%02x' % b).encode()) |
| 2049 | for b in range(127, 256): |
| 2050 | check(chr(b), ('\\x%02x' % b).encode()) |
| 2051 | check('\u20ac', br'\u20ac') |
| 2052 | check('\U0001d120', br'\U0001d120') |
| 2053 | |
| 2054 | def test_escape_decode(self): |
| 2055 | decode = codecs.unicode_escape_decode |
| 2056 | check = coding_checker(self, decode) |
| 2057 | check(b"[\\\n]", "[]") |
| 2058 | check(br'[\"]', '["]') |
| 2059 | check(br"[\']", "[']") |
| 2060 | check(br"[\\]", r"[\]") |
| 2061 | check(br"[\a]", "[\x07]") |
| 2062 | check(br"[\b]", "[\x08]") |
| 2063 | check(br"[\t]", "[\x09]") |
| 2064 | check(br"[\n]", "[\x0a]") |
| 2065 | check(br"[\v]", "[\x0b]") |
| 2066 | check(br"[\f]", "[\x0c]") |
| 2067 | check(br"[\r]", "[\x0d]") |
| 2068 | check(br"[\7]", "[\x07]") |
| 2069 | check(br"[\8]", r"[\8]") |
| 2070 | check(br"[\78]", "[\x078]") |
| 2071 | check(br"[\41]", "[!]") |
| 2072 | check(br"[\418]", "[!8]") |
| 2073 | check(br"[\101]", "[A]") |
| 2074 | check(br"[\1010]", "[A0]") |
| 2075 | check(br"[\x41]", "[A]") |
| 2076 | check(br"[\x410]", "[A0]") |
| 2077 | check(br"\u20ac", "\u20ac") |
| 2078 | check(br"\U0001d120", "\U0001d120") |
| 2079 | for b in range(256): |
| 2080 | if b not in b'\n"\'\\abtnvfr01234567xuUN': |
| 2081 | check(b'\\' + bytes([b]), '\\' + chr(b)) |
| 2082 | |
| 2083 | def test_decode_errors(self): |
| 2084 | decode = codecs.unicode_escape_decode |
| 2085 | for c, d in (b'x', 2), (b'u', 4), (b'U', 4): |
| 2086 | for i in range(d): |
| 2087 | self.assertRaises(UnicodeDecodeError, decode, |
| 2088 | b"\\" + c + b"0"*i) |
| 2089 | self.assertRaises(UnicodeDecodeError, decode, |
| 2090 | b"[\\" + c + b"0"*i + b"]") |
| 2091 | data = b"[\\" + c + b"0"*i + b"]\\" + c + b"0"*i |
| 2092 | self.assertEqual(decode(data, "ignore"), ("[]", len(data))) |
| 2093 | self.assertEqual(decode(data, "replace"), |
| 2094 | ("[\ufffd]\ufffd", len(data))) |
| 2095 | self.assertRaises(UnicodeDecodeError, decode, br"\U00110000") |
| 2096 | self.assertEqual(decode(br"\U00110000", "ignore"), ("", 10)) |
| 2097 | self.assertEqual(decode(br"\U00110000", "replace"), ("\ufffd", 10)) |
| 2098 | |
| 2099 | |
Serhiy Storchaka | c9c4338 | 2013-01-29 11:40:00 +0200 | [diff] [blame] | 2100 | class RawUnicodeEscapeTest(unittest.TestCase): |
| 2101 | def test_empty(self): |
| 2102 | self.assertEqual(codecs.raw_unicode_escape_encode(""), (b"", 0)) |
| 2103 | self.assertEqual(codecs.raw_unicode_escape_decode(b""), ("", 0)) |
| 2104 | |
| 2105 | def test_raw_encode(self): |
| 2106 | encode = codecs.raw_unicode_escape_encode |
| 2107 | for b in range(256): |
| 2108 | self.assertEqual(encode(chr(b)), (bytes([b]), 1)) |
| 2109 | |
| 2110 | def test_raw_decode(self): |
| 2111 | decode = codecs.raw_unicode_escape_decode |
| 2112 | for b in range(256): |
| 2113 | self.assertEqual(decode(bytes([b]) + b'0'), (chr(b) + '0', 2)) |
| 2114 | |
| 2115 | def test_escape_encode(self): |
| 2116 | encode = codecs.raw_unicode_escape_encode |
| 2117 | check = coding_checker(self, encode) |
| 2118 | for b in range(256): |
| 2119 | if b not in b'uU': |
| 2120 | check('\\' + chr(b), b'\\' + bytes([b])) |
| 2121 | check('\u20ac', br'\u20ac') |
| 2122 | check('\U0001d120', br'\U0001d120') |
| 2123 | |
| 2124 | def test_escape_decode(self): |
| 2125 | decode = codecs.raw_unicode_escape_decode |
| 2126 | check = coding_checker(self, decode) |
| 2127 | for b in range(256): |
| 2128 | if b not in b'uU': |
| 2129 | check(b'\\' + bytes([b]), '\\' + chr(b)) |
| 2130 | check(br"\u20ac", "\u20ac") |
| 2131 | check(br"\U0001d120", "\U0001d120") |
| 2132 | |
| 2133 | def test_decode_errors(self): |
| 2134 | decode = codecs.raw_unicode_escape_decode |
| 2135 | for c, d in (b'u', 4), (b'U', 4): |
| 2136 | for i in range(d): |
| 2137 | self.assertRaises(UnicodeDecodeError, decode, |
| 2138 | b"\\" + c + b"0"*i) |
| 2139 | self.assertRaises(UnicodeDecodeError, decode, |
| 2140 | b"[\\" + c + b"0"*i + b"]") |
| 2141 | data = b"[\\" + c + b"0"*i + b"]\\" + c + b"0"*i |
| 2142 | self.assertEqual(decode(data, "ignore"), ("[]", len(data))) |
| 2143 | self.assertEqual(decode(data, "replace"), |
| 2144 | ("[\ufffd]\ufffd", len(data))) |
| 2145 | self.assertRaises(UnicodeDecodeError, decode, br"\U00110000") |
| 2146 | self.assertEqual(decode(br"\U00110000", "ignore"), ("", 10)) |
| 2147 | self.assertEqual(decode(br"\U00110000", "replace"), ("\ufffd", 10)) |
| 2148 | |
| 2149 | |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2150 | class SurrogateEscapeTest(unittest.TestCase): |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2151 | |
| 2152 | def test_utf8(self): |
| 2153 | # Bad byte |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2154 | self.assertEqual(b"foo\x80bar".decode("utf-8", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2155 | "foo\udc80bar") |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2156 | self.assertEqual("foo\udc80bar".encode("utf-8", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2157 | b"foo\x80bar") |
| 2158 | # bad-utf-8 encoded surrogate |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2159 | self.assertEqual(b"\xed\xb0\x80".decode("utf-8", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2160 | "\udced\udcb0\udc80") |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2161 | self.assertEqual("\udced\udcb0\udc80".encode("utf-8", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2162 | b"\xed\xb0\x80") |
| 2163 | |
| 2164 | def test_ascii(self): |
| 2165 | # bad byte |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2166 | self.assertEqual(b"foo\x80bar".decode("ascii", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2167 | "foo\udc80bar") |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2168 | self.assertEqual("foo\udc80bar".encode("ascii", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2169 | b"foo\x80bar") |
| 2170 | |
| 2171 | def test_charmap(self): |
| 2172 | # bad byte: \xa5 is unmapped in iso-8859-3 |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2173 | self.assertEqual(b"foo\xa5bar".decode("iso-8859-3", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2174 | "foo\udca5bar") |
Martin v. Löwis | 43c5778 | 2009-05-10 08:15:24 +0000 | [diff] [blame] | 2175 | self.assertEqual("foo\udca5bar".encode("iso-8859-3", "surrogateescape"), |
Martin v. Löwis | 011e842 | 2009-05-05 04:43:17 +0000 | [diff] [blame] | 2176 | b"foo\xa5bar") |
| 2177 | |
Amaury Forgeot d'Arc | 84ec8d9 | 2009-06-29 22:36:49 +0000 | [diff] [blame] | 2178 | def test_latin1(self): |
| 2179 | # Issue6373 |
Marc-André Lemburg | 8f36af7 | 2011-02-25 15:42:01 +0000 | [diff] [blame] | 2180 | self.assertEqual("\udce4\udceb\udcef\udcf6\udcfc".encode("latin-1", "surrogateescape"), |
Amaury Forgeot d'Arc | 84ec8d9 | 2009-06-29 22:36:49 +0000 | [diff] [blame] | 2181 | b"\xe4\xeb\xef\xf6\xfc") |
| 2182 | |
Walter Dörwald | d1c1e10 | 2005-10-06 20:29:57 +0000 | [diff] [blame] | 2183 | |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2184 | class BomTest(unittest.TestCase): |
| 2185 | def test_seek0(self): |
| 2186 | data = "1234567890" |
| 2187 | tests = ("utf-16", |
| 2188 | "utf-16-le", |
| 2189 | "utf-16-be", |
| 2190 | "utf-32", |
| 2191 | "utf-32-le", |
| 2192 | "utf-32-be") |
Victor Stinner | 2cca057 | 2011-05-23 14:51:42 +0200 | [diff] [blame] | 2193 | self.addCleanup(support.unlink, support.TESTFN) |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2194 | for encoding in tests: |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2195 | # Check if the BOM is written only once |
| 2196 | with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2197 | f.write(data) |
| 2198 | f.write(data) |
| 2199 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2200 | self.assertEqual(f.read(), data * 2) |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2201 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2202 | self.assertEqual(f.read(), data * 2) |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2203 | |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2204 | # Check that the BOM is written after a seek(0) |
| 2205 | with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: |
| 2206 | f.write(data[0]) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2207 | self.assertNotEqual(f.tell(), 0) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2208 | f.seek(0) |
| 2209 | f.write(data) |
| 2210 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2211 | self.assertEqual(f.read(), data) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2212 | |
| 2213 | # (StreamWriter) Check that the BOM is written after a seek(0) |
| 2214 | with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2215 | f.writer.write(data[0]) |
| 2216 | self.assertNotEqual(f.writer.tell(), 0) |
| 2217 | f.writer.seek(0) |
| 2218 | f.writer.write(data) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2219 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2220 | self.assertEqual(f.read(), data) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2221 | |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2222 | # Check that the BOM is not written after a seek() at a position |
| 2223 | # different than the start |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2224 | with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: |
| 2225 | f.write(data) |
| 2226 | f.seek(f.tell()) |
| 2227 | f.write(data) |
| 2228 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2229 | self.assertEqual(f.read(), data * 2) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2230 | |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2231 | # (StreamWriter) Check that the BOM is not written after a seek() |
| 2232 | # at a position different than the start |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2233 | with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2234 | f.writer.write(data) |
| 2235 | f.writer.seek(f.writer.tell()) |
| 2236 | f.writer.write(data) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2237 | f.seek(0) |
Ezio Melotti | b3aedd4 | 2010-11-20 19:04:17 +0000 | [diff] [blame] | 2238 | self.assertEqual(f.read(), data * 2) |
Victor Stinner | a92ad7e | 2010-05-22 16:59:09 +0000 | [diff] [blame] | 2239 | |
Victor Stinner | 3fed087 | 2010-05-22 02:16:27 +0000 | [diff] [blame] | 2240 | |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2241 | bytes_transform_encodings = [ |
| 2242 | "base64_codec", |
| 2243 | "uu_codec", |
| 2244 | "quopri_codec", |
| 2245 | "hex_codec", |
| 2246 | ] |
| 2247 | try: |
| 2248 | import zlib |
| 2249 | except ImportError: |
| 2250 | pass |
| 2251 | else: |
| 2252 | bytes_transform_encodings.append("zlib_codec") |
| 2253 | try: |
| 2254 | import bz2 |
| 2255 | except ImportError: |
| 2256 | pass |
| 2257 | else: |
| 2258 | bytes_transform_encodings.append("bz2_codec") |
| 2259 | |
| 2260 | class TransformCodecTest(unittest.TestCase): |
Benjamin Peterson | 28a4dce | 2010-12-12 01:33:04 +0000 | [diff] [blame] | 2261 | |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2262 | def test_basics(self): |
| 2263 | binput = bytes(range(256)) |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2264 | for encoding in bytes_transform_encodings: |
| 2265 | # generic codecs interface |
| 2266 | (o, size) = codecs.getencoder(encoding)(binput) |
| 2267 | self.assertEqual(size, len(binput)) |
| 2268 | (i, size) = codecs.getdecoder(encoding)(o) |
| 2269 | self.assertEqual(size, len(o)) |
| 2270 | self.assertEqual(i, binput) |
| 2271 | |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2272 | def test_read(self): |
| 2273 | for encoding in bytes_transform_encodings: |
Benjamin Peterson | 28a4dce | 2010-12-12 01:33:04 +0000 | [diff] [blame] | 2274 | sin = codecs.encode(b"\x80", encoding) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2275 | reader = codecs.getreader(encoding)(io.BytesIO(sin)) |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2276 | sout = reader.read() |
| 2277 | self.assertEqual(sout, b"\x80") |
| 2278 | |
| 2279 | def test_readline(self): |
| 2280 | for encoding in bytes_transform_encodings: |
| 2281 | if encoding in ['uu_codec', 'zlib_codec']: |
| 2282 | continue |
Benjamin Peterson | 28a4dce | 2010-12-12 01:33:04 +0000 | [diff] [blame] | 2283 | sin = codecs.encode(b"\x80", encoding) |
Victor Stinner | 0501070 | 2011-05-27 16:50:40 +0200 | [diff] [blame] | 2284 | reader = codecs.getreader(encoding)(io.BytesIO(sin)) |
Georg Brandl | 0252462 | 2010-12-02 18:06:51 +0000 | [diff] [blame] | 2285 | sout = reader.readline() |
| 2286 | self.assertEqual(sout, b"\x80") |
| 2287 | |
| 2288 | |
Victor Stinner | 62be4fb | 2011-10-18 21:46:37 +0200 | [diff] [blame] | 2289 | @unittest.skipUnless(sys.platform == 'win32', |
| 2290 | 'code pages are specific to Windows') |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2291 | class CodePageTest(unittest.TestCase): |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 2292 | # CP_UTF8 is already tested by CP65001Test |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2293 | CP_UTF8 = 65001 |
Victor Stinner | 62be4fb | 2011-10-18 21:46:37 +0200 | [diff] [blame] | 2294 | |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2295 | def test_invalid_code_page(self): |
| 2296 | self.assertRaises(ValueError, codecs.code_page_encode, -1, 'a') |
| 2297 | self.assertRaises(ValueError, codecs.code_page_decode, -1, b'a') |
| 2298 | self.assertRaises(WindowsError, codecs.code_page_encode, 123, 'a') |
| 2299 | self.assertRaises(WindowsError, codecs.code_page_decode, 123, b'a') |
| 2300 | |
| 2301 | def test_code_page_name(self): |
| 2302 | self.assertRaisesRegex(UnicodeEncodeError, 'cp932', |
| 2303 | codecs.code_page_encode, 932, '\xff') |
| 2304 | self.assertRaisesRegex(UnicodeDecodeError, 'cp932', |
| 2305 | codecs.code_page_decode, 932, b'\x81\x00') |
| 2306 | self.assertRaisesRegex(UnicodeDecodeError, 'CP_UTF8', |
| 2307 | codecs.code_page_decode, self.CP_UTF8, b'\xff') |
| 2308 | |
| 2309 | def check_decode(self, cp, tests): |
| 2310 | for raw, errors, expected in tests: |
| 2311 | if expected is not None: |
| 2312 | try: |
| 2313 | decoded = codecs.code_page_decode(cp, raw, errors) |
| 2314 | except UnicodeDecodeError as err: |
| 2315 | self.fail('Unable to decode %a from "cp%s" with ' |
| 2316 | 'errors=%r: %s' % (raw, cp, errors, err)) |
| 2317 | self.assertEqual(decoded[0], expected, |
| 2318 | '%a.decode("cp%s", %r)=%a != %a' |
| 2319 | % (raw, cp, errors, decoded[0], expected)) |
| 2320 | # assert 0 <= decoded[1] <= len(raw) |
| 2321 | self.assertGreaterEqual(decoded[1], 0) |
| 2322 | self.assertLessEqual(decoded[1], len(raw)) |
| 2323 | else: |
| 2324 | self.assertRaises(UnicodeDecodeError, |
| 2325 | codecs.code_page_decode, cp, raw, errors) |
| 2326 | |
| 2327 | def check_encode(self, cp, tests): |
| 2328 | for text, errors, expected in tests: |
| 2329 | if expected is not None: |
| 2330 | try: |
| 2331 | encoded = codecs.code_page_encode(cp, text, errors) |
| 2332 | except UnicodeEncodeError as err: |
| 2333 | self.fail('Unable to encode %a to "cp%s" with ' |
| 2334 | 'errors=%r: %s' % (text, cp, errors, err)) |
| 2335 | self.assertEqual(encoded[0], expected, |
| 2336 | '%a.encode("cp%s", %r)=%a != %a' |
| 2337 | % (text, cp, errors, encoded[0], expected)) |
| 2338 | self.assertEqual(encoded[1], len(text)) |
| 2339 | else: |
| 2340 | self.assertRaises(UnicodeEncodeError, |
| 2341 | codecs.code_page_encode, cp, text, errors) |
| 2342 | |
| 2343 | def test_cp932(self): |
| 2344 | self.check_encode(932, ( |
| 2345 | ('abc', 'strict', b'abc'), |
| 2346 | ('\uff44\u9a3e', 'strict', b'\x82\x84\xe9\x80'), |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 2347 | # test error handlers |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2348 | ('\xff', 'strict', None), |
| 2349 | ('[\xff]', 'ignore', b'[]'), |
| 2350 | ('[\xff]', 'replace', b'[y]'), |
| 2351 | ('[\u20ac]', 'replace', b'[?]'), |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 2352 | ('[\xff]', 'backslashreplace', b'[\\xff]'), |
| 2353 | ('[\xff]', 'xmlcharrefreplace', b'[ÿ]'), |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2354 | )) |
Victor Stinner | 9e92188 | 2011-10-18 21:55:25 +0200 | [diff] [blame] | 2355 | self.check_decode(932, ( |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2356 | (b'abc', 'strict', 'abc'), |
| 2357 | (b'\x82\x84\xe9\x80', 'strict', '\uff44\u9a3e'), |
| 2358 | # invalid bytes |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 2359 | (b'[\xff]', 'strict', None), |
| 2360 | (b'[\xff]', 'ignore', '[]'), |
| 2361 | (b'[\xff]', 'replace', '[\ufffd]'), |
| 2362 | (b'[\xff]', 'surrogateescape', '[\udcff]'), |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2363 | (b'\x81\x00abc', 'strict', None), |
| 2364 | (b'\x81\x00abc', 'ignore', '\x00abc'), |
Victor Stinner | 9e92188 | 2011-10-18 21:55:25 +0200 | [diff] [blame] | 2365 | (b'\x81\x00abc', 'replace', '\ufffd\x00abc'), |
| 2366 | )) |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2367 | |
| 2368 | def test_cp1252(self): |
| 2369 | self.check_encode(1252, ( |
| 2370 | ('abc', 'strict', b'abc'), |
| 2371 | ('\xe9\u20ac', 'strict', b'\xe9\x80'), |
| 2372 | ('\xff', 'strict', b'\xff'), |
| 2373 | ('\u0141', 'strict', None), |
| 2374 | ('\u0141', 'ignore', b''), |
| 2375 | ('\u0141', 'replace', b'L'), |
| 2376 | )) |
| 2377 | self.check_decode(1252, ( |
| 2378 | (b'abc', 'strict', 'abc'), |
| 2379 | (b'\xe9\x80', 'strict', '\xe9\u20ac'), |
| 2380 | (b'\xff', 'strict', '\xff'), |
| 2381 | )) |
| 2382 | |
| 2383 | def test_cp_utf7(self): |
| 2384 | cp = 65000 |
| 2385 | self.check_encode(cp, ( |
| 2386 | ('abc', 'strict', b'abc'), |
| 2387 | ('\xe9\u20ac', 'strict', b'+AOkgrA-'), |
| 2388 | ('\U0010ffff', 'strict', b'+2//f/w-'), |
| 2389 | ('\udc80', 'strict', b'+3IA-'), |
| 2390 | ('\ufffd', 'strict', b'+//0-'), |
| 2391 | )) |
| 2392 | self.check_decode(cp, ( |
| 2393 | (b'abc', 'strict', 'abc'), |
| 2394 | (b'+AOkgrA-', 'strict', '\xe9\u20ac'), |
| 2395 | (b'+2//f/w-', 'strict', '\U0010ffff'), |
| 2396 | (b'+3IA-', 'strict', '\udc80'), |
| 2397 | (b'+//0-', 'strict', '\ufffd'), |
| 2398 | # invalid bytes |
| 2399 | (b'[+/]', 'strict', '[]'), |
| 2400 | (b'[\xff]', 'strict', '[\xff]'), |
| 2401 | )) |
| 2402 | |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2403 | def test_multibyte_encoding(self): |
| 2404 | self.check_decode(932, ( |
| 2405 | (b'\x84\xe9\x80', 'ignore', '\u9a3e'), |
| 2406 | (b'\x84\xe9\x80', 'replace', '\ufffd\u9a3e'), |
| 2407 | )) |
| 2408 | self.check_decode(self.CP_UTF8, ( |
| 2409 | (b'\xff\xf4\x8f\xbf\xbf', 'ignore', '\U0010ffff'), |
| 2410 | (b'\xff\xf4\x8f\xbf\xbf', 'replace', '\ufffd\U0010ffff'), |
| 2411 | )) |
Victor Stinner | 2f3ca9f | 2011-10-27 01:38:56 +0200 | [diff] [blame] | 2412 | if VISTA_OR_LATER: |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2413 | self.check_encode(self.CP_UTF8, ( |
| 2414 | ('[\U0010ffff\uDC80]', 'ignore', b'[\xf4\x8f\xbf\xbf]'), |
| 2415 | ('[\U0010ffff\uDC80]', 'replace', b'[\xf4\x8f\xbf\xbf?]'), |
| 2416 | )) |
| 2417 | |
| 2418 | def test_incremental(self): |
Victor Stinner | 76a31a6 | 2011-11-04 00:05:13 +0100 | [diff] [blame] | 2419 | decoded = codecs.code_page_decode(932, b'\x82', 'strict', False) |
| 2420 | self.assertEqual(decoded, ('', 0)) |
| 2421 | |
Victor Stinner | 3a50e70 | 2011-10-18 21:21:00 +0200 | [diff] [blame] | 2422 | decoded = codecs.code_page_decode(932, |
| 2423 | b'\xe9\x80\xe9', 'strict', |
| 2424 | False) |
| 2425 | self.assertEqual(decoded, ('\u9a3e', 2)) |
| 2426 | |
| 2427 | decoded = codecs.code_page_decode(932, |
| 2428 | b'\xe9\x80\xe9\x80', 'strict', |
| 2429 | False) |
| 2430 | self.assertEqual(decoded, ('\u9a3e\u9a3e', 4)) |
| 2431 | |
| 2432 | decoded = codecs.code_page_decode(932, |
| 2433 | b'abc', 'strict', |
| 2434 | False) |
| 2435 | self.assertEqual(decoded, ('abc', 3)) |
| 2436 | |
| 2437 | |
Fred Drake | 2e2be37 | 2001-09-20 21:33:42 +0000 | [diff] [blame] | 2438 | if __name__ == "__main__": |
Ezio Melotti | 5d3dba0 | 2013-01-11 06:02:07 +0200 | [diff] [blame] | 2439 | unittest.main() |