| 1 | n/a | #!/usr/bin/env python3 |
|---|
| 2 | n/a | # |
|---|
| 3 | n/a | # test_multibytecodec_support.py |
|---|
| 4 | n/a | # Common Unittest Routines for CJK codecs |
|---|
| 5 | n/a | # |
|---|
| 6 | n/a | |
|---|
| 7 | n/a | import codecs |
|---|
| 8 | n/a | import os |
|---|
| 9 | n/a | import re |
|---|
| 10 | n/a | import sys |
|---|
| 11 | n/a | import unittest |
|---|
| 12 | n/a | from http.client import HTTPException |
|---|
| 13 | n/a | from test import support |
|---|
| 14 | n/a | from io import BytesIO |
|---|
| 15 | n/a | |
|---|
| 16 | n/a | class TestBase: |
|---|
| 17 | n/a | encoding = '' # codec name |
|---|
| 18 | n/a | codec = None # codec tuple (with 4 elements) |
|---|
| 19 | n/a | tstring = None # must set. 2 strings to test StreamReader |
|---|
| 20 | n/a | |
|---|
| 21 | n/a | codectests = None # must set. codec test tuple |
|---|
| 22 | n/a | roundtriptest = 1 # set if roundtrip is possible with unicode |
|---|
| 23 | n/a | has_iso10646 = 0 # set if this encoding contains whole iso10646 map |
|---|
| 24 | n/a | xmlcharnametest = None # string to test xmlcharrefreplace |
|---|
| 25 | n/a | unmappedunicode = '\udeee' # a unicode codepoint that is not mapped. |
|---|
| 26 | n/a | |
|---|
| 27 | n/a | def setUp(self): |
|---|
| 28 | n/a | if self.codec is None: |
|---|
| 29 | n/a | self.codec = codecs.lookup(self.encoding) |
|---|
| 30 | n/a | self.encode = self.codec.encode |
|---|
| 31 | n/a | self.decode = self.codec.decode |
|---|
| 32 | n/a | self.reader = self.codec.streamreader |
|---|
| 33 | n/a | self.writer = self.codec.streamwriter |
|---|
| 34 | n/a | self.incrementalencoder = self.codec.incrementalencoder |
|---|
| 35 | n/a | self.incrementaldecoder = self.codec.incrementaldecoder |
|---|
| 36 | n/a | |
|---|
| 37 | n/a | def test_chunkcoding(self): |
|---|
| 38 | n/a | tstring_lines = [] |
|---|
| 39 | n/a | for b in self.tstring: |
|---|
| 40 | n/a | lines = b.split(b"\n") |
|---|
| 41 | n/a | last = lines.pop() |
|---|
| 42 | n/a | assert last == b"" |
|---|
| 43 | n/a | lines = [line + b"\n" for line in lines] |
|---|
| 44 | n/a | tstring_lines.append(lines) |
|---|
| 45 | n/a | for native, utf8 in zip(*tstring_lines): |
|---|
| 46 | n/a | u = self.decode(native)[0] |
|---|
| 47 | n/a | self.assertEqual(u, utf8.decode('utf-8')) |
|---|
| 48 | n/a | if self.roundtriptest: |
|---|
| 49 | n/a | self.assertEqual(native, self.encode(u)[0]) |
|---|
| 50 | n/a | |
|---|
| 51 | n/a | def test_errorhandle(self): |
|---|
| 52 | n/a | for source, scheme, expected in self.codectests: |
|---|
| 53 | n/a | if isinstance(source, bytes): |
|---|
| 54 | n/a | func = self.decode |
|---|
| 55 | n/a | else: |
|---|
| 56 | n/a | func = self.encode |
|---|
| 57 | n/a | if expected: |
|---|
| 58 | n/a | result = func(source, scheme)[0] |
|---|
| 59 | n/a | if func is self.decode: |
|---|
| 60 | n/a | self.assertTrue(type(result) is str, type(result)) |
|---|
| 61 | n/a | self.assertEqual(result, expected, |
|---|
| 62 | n/a | '%a.decode(%r, %r)=%a != %a' |
|---|
| 63 | n/a | % (source, self.encoding, scheme, result, |
|---|
| 64 | n/a | expected)) |
|---|
| 65 | n/a | else: |
|---|
| 66 | n/a | self.assertTrue(type(result) is bytes, type(result)) |
|---|
| 67 | n/a | self.assertEqual(result, expected, |
|---|
| 68 | n/a | '%a.encode(%r, %r)=%a != %a' |
|---|
| 69 | n/a | % (source, self.encoding, scheme, result, |
|---|
| 70 | n/a | expected)) |
|---|
| 71 | n/a | else: |
|---|
| 72 | n/a | self.assertRaises(UnicodeError, func, source, scheme) |
|---|
| 73 | n/a | |
|---|
| 74 | n/a | def test_xmlcharrefreplace(self): |
|---|
| 75 | n/a | if self.has_iso10646: |
|---|
| 76 | n/a | return |
|---|
| 77 | n/a | |
|---|
| 78 | n/a | s = "\u0b13\u0b23\u0b60 nd eggs" |
|---|
| 79 | n/a | self.assertEqual( |
|---|
| 80 | n/a | self.encode(s, "xmlcharrefreplace")[0], |
|---|
| 81 | n/a | b"ଓଣୠ nd eggs" |
|---|
| 82 | n/a | ) |
|---|
| 83 | n/a | |
|---|
| 84 | n/a | def test_customreplace_encode(self): |
|---|
| 85 | n/a | if self.has_iso10646: |
|---|
| 86 | n/a | return |
|---|
| 87 | n/a | |
|---|
| 88 | n/a | from html.entities import codepoint2name |
|---|
| 89 | n/a | |
|---|
| 90 | n/a | def xmlcharnamereplace(exc): |
|---|
| 91 | n/a | if not isinstance(exc, UnicodeEncodeError): |
|---|
| 92 | n/a | raise TypeError("don't know how to handle %r" % exc) |
|---|
| 93 | n/a | l = [] |
|---|
| 94 | n/a | for c in exc.object[exc.start:exc.end]: |
|---|
| 95 | n/a | if ord(c) in codepoint2name: |
|---|
| 96 | n/a | l.append("&%s;" % codepoint2name[ord(c)]) |
|---|
| 97 | n/a | else: |
|---|
| 98 | n/a | l.append("&#%d;" % ord(c)) |
|---|
| 99 | n/a | return ("".join(l), exc.end) |
|---|
| 100 | n/a | |
|---|
| 101 | n/a | codecs.register_error("test.xmlcharnamereplace", xmlcharnamereplace) |
|---|
| 102 | n/a | |
|---|
| 103 | n/a | if self.xmlcharnametest: |
|---|
| 104 | n/a | sin, sout = self.xmlcharnametest |
|---|
| 105 | n/a | else: |
|---|
| 106 | n/a | sin = "\xab\u211c\xbb = \u2329\u1234\u232a" |
|---|
| 107 | n/a | sout = b"«ℜ» = ⟨ሴ⟩" |
|---|
| 108 | n/a | self.assertEqual(self.encode(sin, |
|---|
| 109 | n/a | "test.xmlcharnamereplace")[0], sout) |
|---|
| 110 | n/a | |
|---|
| 111 | n/a | def test_callback_wrong_objects(self): |
|---|
| 112 | n/a | def myreplace(exc): |
|---|
| 113 | n/a | return (ret, exc.end) |
|---|
| 114 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 115 | n/a | |
|---|
| 116 | n/a | for ret in ([1, 2, 3], [], None, object(), b'string', b''): |
|---|
| 117 | n/a | self.assertRaises(TypeError, self.encode, self.unmappedunicode, |
|---|
| 118 | n/a | 'test.cjktest') |
|---|
| 119 | n/a | |
|---|
| 120 | n/a | def test_callback_long_index(self): |
|---|
| 121 | n/a | def myreplace(exc): |
|---|
| 122 | n/a | return ('x', int(exc.end)) |
|---|
| 123 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 124 | n/a | self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh', |
|---|
| 125 | n/a | 'test.cjktest'), (b'abcdxefgh', 9)) |
|---|
| 126 | n/a | |
|---|
| 127 | n/a | def myreplace(exc): |
|---|
| 128 | n/a | return ('x', sys.maxsize + 1) |
|---|
| 129 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 130 | n/a | self.assertRaises(IndexError, self.encode, self.unmappedunicode, |
|---|
| 131 | n/a | 'test.cjktest') |
|---|
| 132 | n/a | |
|---|
| 133 | n/a | def test_callback_None_index(self): |
|---|
| 134 | n/a | def myreplace(exc): |
|---|
| 135 | n/a | return ('x', None) |
|---|
| 136 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 137 | n/a | self.assertRaises(TypeError, self.encode, self.unmappedunicode, |
|---|
| 138 | n/a | 'test.cjktest') |
|---|
| 139 | n/a | |
|---|
| 140 | n/a | def test_callback_backward_index(self): |
|---|
| 141 | n/a | def myreplace(exc): |
|---|
| 142 | n/a | if myreplace.limit > 0: |
|---|
| 143 | n/a | myreplace.limit -= 1 |
|---|
| 144 | n/a | return ('REPLACED', 0) |
|---|
| 145 | n/a | else: |
|---|
| 146 | n/a | return ('TERMINAL', exc.end) |
|---|
| 147 | n/a | myreplace.limit = 3 |
|---|
| 148 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 149 | n/a | self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh', |
|---|
| 150 | n/a | 'test.cjktest'), |
|---|
| 151 | n/a | (b'abcdREPLACEDabcdREPLACEDabcdREPLACEDabcdTERMINALefgh', 9)) |
|---|
| 152 | n/a | |
|---|
| 153 | n/a | def test_callback_forward_index(self): |
|---|
| 154 | n/a | def myreplace(exc): |
|---|
| 155 | n/a | return ('REPLACED', exc.end + 2) |
|---|
| 156 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 157 | n/a | self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh', |
|---|
| 158 | n/a | 'test.cjktest'), (b'abcdREPLACEDgh', 9)) |
|---|
| 159 | n/a | |
|---|
| 160 | n/a | def test_callback_index_outofbound(self): |
|---|
| 161 | n/a | def myreplace(exc): |
|---|
| 162 | n/a | return ('TERM', 100) |
|---|
| 163 | n/a | codecs.register_error("test.cjktest", myreplace) |
|---|
| 164 | n/a | self.assertRaises(IndexError, self.encode, self.unmappedunicode, |
|---|
| 165 | n/a | 'test.cjktest') |
|---|
| 166 | n/a | |
|---|
| 167 | n/a | def test_incrementalencoder(self): |
|---|
| 168 | n/a | UTF8Reader = codecs.getreader('utf-8') |
|---|
| 169 | n/a | for sizehint in [None] + list(range(1, 33)) + \ |
|---|
| 170 | n/a | [64, 128, 256, 512, 1024]: |
|---|
| 171 | n/a | istream = UTF8Reader(BytesIO(self.tstring[1])) |
|---|
| 172 | n/a | ostream = BytesIO() |
|---|
| 173 | n/a | encoder = self.incrementalencoder() |
|---|
| 174 | n/a | while 1: |
|---|
| 175 | n/a | if sizehint is not None: |
|---|
| 176 | n/a | data = istream.read(sizehint) |
|---|
| 177 | n/a | else: |
|---|
| 178 | n/a | data = istream.read() |
|---|
| 179 | n/a | |
|---|
| 180 | n/a | if not data: |
|---|
| 181 | n/a | break |
|---|
| 182 | n/a | e = encoder.encode(data) |
|---|
| 183 | n/a | ostream.write(e) |
|---|
| 184 | n/a | |
|---|
| 185 | n/a | self.assertEqual(ostream.getvalue(), self.tstring[0]) |
|---|
| 186 | n/a | |
|---|
| 187 | n/a | def test_incrementaldecoder(self): |
|---|
| 188 | n/a | UTF8Writer = codecs.getwriter('utf-8') |
|---|
| 189 | n/a | for sizehint in [None, -1] + list(range(1, 33)) + \ |
|---|
| 190 | n/a | [64, 128, 256, 512, 1024]: |
|---|
| 191 | n/a | istream = BytesIO(self.tstring[0]) |
|---|
| 192 | n/a | ostream = UTF8Writer(BytesIO()) |
|---|
| 193 | n/a | decoder = self.incrementaldecoder() |
|---|
| 194 | n/a | while 1: |
|---|
| 195 | n/a | data = istream.read(sizehint) |
|---|
| 196 | n/a | if not data: |
|---|
| 197 | n/a | break |
|---|
| 198 | n/a | else: |
|---|
| 199 | n/a | u = decoder.decode(data) |
|---|
| 200 | n/a | ostream.write(u) |
|---|
| 201 | n/a | |
|---|
| 202 | n/a | self.assertEqual(ostream.getvalue(), self.tstring[1]) |
|---|
| 203 | n/a | |
|---|
| 204 | n/a | def test_incrementalencoder_error_callback(self): |
|---|
| 205 | n/a | inv = self.unmappedunicode |
|---|
| 206 | n/a | |
|---|
| 207 | n/a | e = self.incrementalencoder() |
|---|
| 208 | n/a | self.assertRaises(UnicodeEncodeError, e.encode, inv, True) |
|---|
| 209 | n/a | |
|---|
| 210 | n/a | e.errors = 'ignore' |
|---|
| 211 | n/a | self.assertEqual(e.encode(inv, True), b'') |
|---|
| 212 | n/a | |
|---|
| 213 | n/a | e.reset() |
|---|
| 214 | n/a | def tempreplace(exc): |
|---|
| 215 | n/a | return ('called', exc.end) |
|---|
| 216 | n/a | codecs.register_error('test.incremental_error_callback', tempreplace) |
|---|
| 217 | n/a | e.errors = 'test.incremental_error_callback' |
|---|
| 218 | n/a | self.assertEqual(e.encode(inv, True), b'called') |
|---|
| 219 | n/a | |
|---|
| 220 | n/a | # again |
|---|
| 221 | n/a | e.errors = 'ignore' |
|---|
| 222 | n/a | self.assertEqual(e.encode(inv, True), b'') |
|---|
| 223 | n/a | |
|---|
| 224 | n/a | def test_streamreader(self): |
|---|
| 225 | n/a | UTF8Writer = codecs.getwriter('utf-8') |
|---|
| 226 | n/a | for name in ["read", "readline", "readlines"]: |
|---|
| 227 | n/a | for sizehint in [None, -1] + list(range(1, 33)) + \ |
|---|
| 228 | n/a | [64, 128, 256, 512, 1024]: |
|---|
| 229 | n/a | istream = self.reader(BytesIO(self.tstring[0])) |
|---|
| 230 | n/a | ostream = UTF8Writer(BytesIO()) |
|---|
| 231 | n/a | func = getattr(istream, name) |
|---|
| 232 | n/a | while 1: |
|---|
| 233 | n/a | data = func(sizehint) |
|---|
| 234 | n/a | if not data: |
|---|
| 235 | n/a | break |
|---|
| 236 | n/a | if name == "readlines": |
|---|
| 237 | n/a | ostream.writelines(data) |
|---|
| 238 | n/a | else: |
|---|
| 239 | n/a | ostream.write(data) |
|---|
| 240 | n/a | |
|---|
| 241 | n/a | self.assertEqual(ostream.getvalue(), self.tstring[1]) |
|---|
| 242 | n/a | |
|---|
| 243 | n/a | def test_streamwriter(self): |
|---|
| 244 | n/a | readfuncs = ('read', 'readline', 'readlines') |
|---|
| 245 | n/a | UTF8Reader = codecs.getreader('utf-8') |
|---|
| 246 | n/a | for name in readfuncs: |
|---|
| 247 | n/a | for sizehint in [None] + list(range(1, 33)) + \ |
|---|
| 248 | n/a | [64, 128, 256, 512, 1024]: |
|---|
| 249 | n/a | istream = UTF8Reader(BytesIO(self.tstring[1])) |
|---|
| 250 | n/a | ostream = self.writer(BytesIO()) |
|---|
| 251 | n/a | func = getattr(istream, name) |
|---|
| 252 | n/a | while 1: |
|---|
| 253 | n/a | if sizehint is not None: |
|---|
| 254 | n/a | data = func(sizehint) |
|---|
| 255 | n/a | else: |
|---|
| 256 | n/a | data = func() |
|---|
| 257 | n/a | |
|---|
| 258 | n/a | if not data: |
|---|
| 259 | n/a | break |
|---|
| 260 | n/a | if name == "readlines": |
|---|
| 261 | n/a | ostream.writelines(data) |
|---|
| 262 | n/a | else: |
|---|
| 263 | n/a | ostream.write(data) |
|---|
| 264 | n/a | |
|---|
| 265 | n/a | self.assertEqual(ostream.getvalue(), self.tstring[0]) |
|---|
| 266 | n/a | |
|---|
| 267 | n/a | |
|---|
| 268 | n/a | class TestBase_Mapping(unittest.TestCase): |
|---|
| 269 | n/a | pass_enctest = [] |
|---|
| 270 | n/a | pass_dectest = [] |
|---|
| 271 | n/a | supmaps = [] |
|---|
| 272 | n/a | codectests = [] |
|---|
| 273 | n/a | |
|---|
| 274 | n/a | def __init__(self, *args, **kw): |
|---|
| 275 | n/a | unittest.TestCase.__init__(self, *args, **kw) |
|---|
| 276 | n/a | try: |
|---|
| 277 | n/a | self.open_mapping_file().close() # test it to report the error early |
|---|
| 278 | n/a | except (IOError, HTTPException): |
|---|
| 279 | n/a | self.skipTest("Could not retrieve "+self.mapfileurl) |
|---|
| 280 | n/a | |
|---|
| 281 | n/a | def open_mapping_file(self): |
|---|
| 282 | n/a | return support.open_urlresource(self.mapfileurl) |
|---|
| 283 | n/a | |
|---|
| 284 | n/a | def test_mapping_file(self): |
|---|
| 285 | n/a | if self.mapfileurl.endswith('.xml'): |
|---|
| 286 | n/a | self._test_mapping_file_ucm() |
|---|
| 287 | n/a | else: |
|---|
| 288 | n/a | self._test_mapping_file_plain() |
|---|
| 289 | n/a | |
|---|
| 290 | n/a | def _test_mapping_file_plain(self): |
|---|
| 291 | n/a | unichrs = lambda s: ''.join(map(chr, map(eval, s.split('+')))) |
|---|
| 292 | n/a | urt_wa = {} |
|---|
| 293 | n/a | |
|---|
| 294 | n/a | with self.open_mapping_file() as f: |
|---|
| 295 | n/a | for line in f: |
|---|
| 296 | n/a | if not line: |
|---|
| 297 | n/a | break |
|---|
| 298 | n/a | data = line.split('#')[0].strip().split() |
|---|
| 299 | n/a | if len(data) != 2: |
|---|
| 300 | n/a | continue |
|---|
| 301 | n/a | |
|---|
| 302 | n/a | csetval = eval(data[0]) |
|---|
| 303 | n/a | if csetval <= 0x7F: |
|---|
| 304 | n/a | csetch = bytes([csetval & 0xff]) |
|---|
| 305 | n/a | elif csetval >= 0x1000000: |
|---|
| 306 | n/a | csetch = bytes([(csetval >> 24), ((csetval >> 16) & 0xff), |
|---|
| 307 | n/a | ((csetval >> 8) & 0xff), (csetval & 0xff)]) |
|---|
| 308 | n/a | elif csetval >= 0x10000: |
|---|
| 309 | n/a | csetch = bytes([(csetval >> 16), ((csetval >> 8) & 0xff), |
|---|
| 310 | n/a | (csetval & 0xff)]) |
|---|
| 311 | n/a | elif csetval >= 0x100: |
|---|
| 312 | n/a | csetch = bytes([(csetval >> 8), (csetval & 0xff)]) |
|---|
| 313 | n/a | else: |
|---|
| 314 | n/a | continue |
|---|
| 315 | n/a | |
|---|
| 316 | n/a | unich = unichrs(data[1]) |
|---|
| 317 | n/a | if ord(unich) == 0xfffd or unich in urt_wa: |
|---|
| 318 | n/a | continue |
|---|
| 319 | n/a | urt_wa[unich] = csetch |
|---|
| 320 | n/a | |
|---|
| 321 | n/a | self._testpoint(csetch, unich) |
|---|
| 322 | n/a | |
|---|
| 323 | n/a | def _test_mapping_file_ucm(self): |
|---|
| 324 | n/a | with self.open_mapping_file() as f: |
|---|
| 325 | n/a | ucmdata = f.read() |
|---|
| 326 | n/a | uc = re.findall('<a u="([A-F0-9]{4})" b="([0-9A-F ]+)"/>', ucmdata) |
|---|
| 327 | n/a | for uni, coded in uc: |
|---|
| 328 | n/a | unich = chr(int(uni, 16)) |
|---|
| 329 | n/a | codech = bytes(int(c, 16) for c in coded.split()) |
|---|
| 330 | n/a | self._testpoint(codech, unich) |
|---|
| 331 | n/a | |
|---|
| 332 | n/a | def test_mapping_supplemental(self): |
|---|
| 333 | n/a | for mapping in self.supmaps: |
|---|
| 334 | n/a | self._testpoint(*mapping) |
|---|
| 335 | n/a | |
|---|
| 336 | n/a | def _testpoint(self, csetch, unich): |
|---|
| 337 | n/a | if (csetch, unich) not in self.pass_enctest: |
|---|
| 338 | n/a | self.assertEqual(unich.encode(self.encoding), csetch) |
|---|
| 339 | n/a | if (csetch, unich) not in self.pass_dectest: |
|---|
| 340 | n/a | self.assertEqual(str(csetch, self.encoding), unich) |
|---|
| 341 | n/a | |
|---|
| 342 | n/a | def test_errorhandle(self): |
|---|
| 343 | n/a | for source, scheme, expected in self.codectests: |
|---|
| 344 | n/a | if isinstance(source, bytes): |
|---|
| 345 | n/a | func = source.decode |
|---|
| 346 | n/a | else: |
|---|
| 347 | n/a | func = source.encode |
|---|
| 348 | n/a | if expected: |
|---|
| 349 | n/a | if isinstance(source, bytes): |
|---|
| 350 | n/a | result = func(self.encoding, scheme) |
|---|
| 351 | n/a | self.assertTrue(type(result) is str, type(result)) |
|---|
| 352 | n/a | self.assertEqual(result, expected, |
|---|
| 353 | n/a | '%a.decode(%r, %r)=%a != %a' |
|---|
| 354 | n/a | % (source, self.encoding, scheme, result, |
|---|
| 355 | n/a | expected)) |
|---|
| 356 | n/a | else: |
|---|
| 357 | n/a | result = func(self.encoding, scheme) |
|---|
| 358 | n/a | self.assertTrue(type(result) is bytes, type(result)) |
|---|
| 359 | n/a | self.assertEqual(result, expected, |
|---|
| 360 | n/a | '%a.encode(%r, %r)=%a != %a' |
|---|
| 361 | n/a | % (source, self.encoding, scheme, result, |
|---|
| 362 | n/a | expected)) |
|---|
| 363 | n/a | else: |
|---|
| 364 | n/a | self.assertRaises(UnicodeError, func, self.encoding, scheme) |
|---|
| 365 | n/a | |
|---|
| 366 | n/a | def load_teststring(name): |
|---|
| 367 | n/a | dir = os.path.join(os.path.dirname(__file__), 'cjkencodings') |
|---|
| 368 | n/a | with open(os.path.join(dir, name + '.txt'), 'rb') as f: |
|---|
| 369 | n/a | encoded = f.read() |
|---|
| 370 | n/a | with open(os.path.join(dir, name + '-utf8.txt'), 'rb') as f: |
|---|
| 371 | n/a | utf8 = f.read() |
|---|
| 372 | n/a | return encoded, utf8 |
|---|
