gvsig-scripting / org.gvsig.scripting / trunk / org.gvsig.scripting / org.gvsig.scripting.app / org.gvsig.scripting.app.mainplugin / src / main / resources-plugin / scripting / lib / cssutils / tests / test_encutils / __init__.py @ 475
History | View | Annotate | Download (16.7 KB)
| 1 |
# -*- coding: utf-8 -*-
|
|---|---|
| 2 |
"""
|
| 3 |
tests for encutils.py
|
| 4 |
"""
|
| 5 |
import httplib |
| 6 |
from StringIO import StringIO |
| 7 |
import sys |
| 8 |
import unittest |
| 9 |
|
| 10 |
PY2x = sys.version_info < (3,0) |
| 11 |
|
| 12 |
try:
|
| 13 |
import cssutils.encutils as encutils |
| 14 |
except ImportError: |
| 15 |
import encutils |
| 16 |
|
| 17 |
# helper log
|
| 18 |
log = encutils.buildlog(stream=StringIO()) |
| 19 |
|
| 20 |
class AutoEncodingTestCase(unittest.TestCase): |
| 21 |
|
| 22 |
def _fakeRes(self, content): |
| 23 |
"build a fake HTTP response"
|
| 24 |
class FakeRes: |
| 25 |
def __init__(self, content): |
| 26 |
if PY2x:
|
| 27 |
fp = StringIO(content) |
| 28 |
self._info = httplib.HTTPMessage(fp)
|
| 29 |
else:
|
| 30 |
self._info = httplib.HTTPMessage()
|
| 31 |
# Adjust to testdata.
|
| 32 |
l = content.split(':')
|
| 33 |
if len(l) > 1: |
| 34 |
# Get the type by just
|
| 35 |
# using the data at the end.
|
| 36 |
t = l[-1].strip()
|
| 37 |
self._info.set_type(t)
|
| 38 |
|
| 39 |
def info(self): |
| 40 |
return self._info |
| 41 |
|
| 42 |
def read(self): |
| 43 |
return content
|
| 44 |
|
| 45 |
return FakeRes(content)
|
| 46 |
|
| 47 |
def test_getTextTypeByMediaType(self): |
| 48 |
"encutils._getTextTypeByMediaType"
|
| 49 |
tests = {
|
| 50 |
'application/xml': encutils._XML_APPLICATION_TYPE,
|
| 51 |
'application/xml-dtd': encutils._XML_APPLICATION_TYPE,
|
| 52 |
'application/xml-external-parsed-entity': encutils._XML_APPLICATION_TYPE,
|
| 53 |
'application/xhtml+xml': encutils._XML_APPLICATION_TYPE,
|
| 54 |
'text/xml': encutils._XML_TEXT_TYPE,
|
| 55 |
'text/xml-external-parsed-entity': encutils._XML_TEXT_TYPE,
|
| 56 |
'text/xhtml+xml': encutils._XML_TEXT_TYPE,
|
| 57 |
'text/html': encutils._HTML_TEXT_TYPE,
|
| 58 |
'text/css': encutils._TEXT_UTF8,
|
| 59 |
'text/plain': encutils._TEXT_TYPE,
|
| 60 |
'x/x': encutils._OTHER_TYPE,
|
| 61 |
'ANYTHING': encutils._OTHER_TYPE
|
| 62 |
} |
| 63 |
for test, exp in tests.items(): |
| 64 |
self.assertEqual(
|
| 65 |
exp, encutils._getTextTypeByMediaType(test, log=log)) |
| 66 |
|
| 67 |
def test_getTextType(self): |
| 68 |
"encutils._getTextType"
|
| 69 |
tests = {
|
| 70 |
u'\x00\x00\xFE\xFF<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 71 |
u'\xFF\xFE\x00\x00<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 72 |
u'\xFE\xFF<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 73 |
u'\xFF\xFE<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 74 |
u'\xef\xbb\xbf<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 75 |
u'<?xml version="1.0"': encutils._XML_APPLICATION_TYPE,
|
| 76 |
u'\x00\x00\xFE\xFFanything': encutils._OTHER_TYPE,
|
| 77 |
u'\xFF\xFE\x00\x00anything': encutils._OTHER_TYPE,
|
| 78 |
u'\xFE\xFFanything': encutils._OTHER_TYPE,
|
| 79 |
u'\xFF\xFEanything': encutils._OTHER_TYPE,
|
| 80 |
u'\xef\xbb\xbfanything': encutils._OTHER_TYPE,
|
| 81 |
u'x/x': encutils._OTHER_TYPE,
|
| 82 |
u'ANYTHING': encutils._OTHER_TYPE
|
| 83 |
} |
| 84 |
for test, exp in tests.items(): |
| 85 |
self.assertEqual(
|
| 86 |
exp, encutils._getTextType(test, log=log)) |
| 87 |
|
| 88 |
def test_encodingByMediaType(self): |
| 89 |
"encutils.encodingByMediaType"
|
| 90 |
tests = {
|
| 91 |
'application/xml': 'utf-8', |
| 92 |
'application/xml-dtd': 'utf-8', |
| 93 |
'application/xml-external-parsed-entity': 'utf-8', |
| 94 |
'application/ANYTHING+xml': 'utf-8', |
| 95 |
' application/xml ': 'utf-8', |
| 96 |
'text/xml': 'ascii', |
| 97 |
'text/xml-external-parsed-entity': 'ascii', |
| 98 |
'text/ANYTHING+xml': 'ascii', |
| 99 |
'text/html': 'iso-8859-1', |
| 100 |
'text/css': 'utf-8', |
| 101 |
'text/plain': 'iso-8859-1', |
| 102 |
'ANYTHING': None |
| 103 |
} |
| 104 |
for test, exp in tests.items(): |
| 105 |
self.assertEqual(exp,
|
| 106 |
encutils.encodingByMediaType(test, log=log)) |
| 107 |
|
| 108 |
def test_getMetaInfo(self): |
| 109 |
"encutils.getMetaInfo"
|
| 110 |
tests = {
|
| 111 |
"""<meta tp-equiv='Content-Type' content='text/html; charset=ascii'>""":
|
| 112 |
(None, None), |
| 113 |
"""<meta http-equiv='ontent-Type' content='text/html; charset=ascii'>""":
|
| 114 |
(None, None), |
| 115 |
|
| 116 |
"""<meta http-equiv='Content-Type' content='text/html'>""":
|
| 117 |
('text/html', None), |
| 118 |
|
| 119 |
"""<meta content='text/html' http-equiv='Content-Type'>""":
|
| 120 |
('text/html', None), |
| 121 |
"""<meta content='text/html;charset=ascii' http-equiv='Content-Type'>""":
|
| 122 |
('text/html', 'ascii'), |
| 123 |
|
| 124 |
"""<meta http-equiv='Content-Type' content='text/html ;charset=ascii'>""":
|
| 125 |
('text/html', 'ascii'), |
| 126 |
"""<meta content='text/html;charset=iso-8859-1' http-equiv='Content-Type'>""":
|
| 127 |
('text/html', 'iso-8859-1'), |
| 128 |
"""<meta http-equiv="Content-Type" content="text/html;charset = ascii">""":
|
| 129 |
('text/html', 'ascii'), |
| 130 |
|
| 131 |
"""<meta http-equiv="Content-Type" content="text/html;charset=ascii;x=2">""":
|
| 132 |
('text/html', 'ascii'), |
| 133 |
"""<meta http-equiv="Content-Type" content="text/html;x=2;charset=ascii">""":
|
| 134 |
('text/html', 'ascii'), |
| 135 |
"""<meta http-equiv="Content-Type" content="text/html;x=2;charset=ascii;y=2">""":
|
| 136 |
('text/html', 'ascii'), |
| 137 |
|
| 138 |
"""<meta http-equiv='Content-Type' content="text/html;charset=ascii">""":
|
| 139 |
('text/html', 'ascii'), |
| 140 |
"""<meta http-equiv='Content-Type' content='text/html;charset=ascii' />""":
|
| 141 |
('text/html', 'ascii'), |
| 142 |
"""<meta http-equiv = " Content-Type" content = " text/html;charset=ascii " >""":
|
| 143 |
('text/html', 'ascii'), |
| 144 |
"""<meta http-equiv = " \n Content-Type " content = " \t text/html ; charset=ascii " >""":
|
| 145 |
('text/html', 'ascii'), |
| 146 |
|
| 147 |
"""<meta content="text/html;charset=ascii" http-equiv="Content-Type">""":
|
| 148 |
('text/html', 'ascii'), |
| 149 |
"""<meta content="text/html;charset=ascii" http-equiv="cONTENT-type">""":
|
| 150 |
('text/html', 'ascii'), |
| 151 |
"""raises exception: </ >""":
|
| 152 |
(None, None), |
| 153 |
"""<meta content="text/html;charset=ascii" http-equiv="cONTENT-type">
|
| 154 |
</ >""":
|
| 155 |
('text/html', 'ascii'), |
| 156 |
"""</ >
|
| 157 |
<meta content="text/html;charset=ascii" http-equiv="cONTENT-type">""":
|
| 158 |
('text/html', 'ascii'), |
| 159 |
# py 2.7.3 fixed HTMLParser so: (None, None)
|
| 160 |
"""<meta content="text/html" http-equiv="cONTENT-type">
|
| 161 |
</ >
|
| 162 |
<meta content="text/html;charset=ascii" http-equiv="cONTENT-type">""":
|
| 163 |
('text/html', None) |
| 164 |
} |
| 165 |
for test, exp in tests.items(): |
| 166 |
self.assertEqual(exp, encutils.getMetaInfo(test, log=log))
|
| 167 |
|
| 168 |
def test_detectXMLEncoding(self): |
| 169 |
"encutils.detectXMLEncoding"
|
| 170 |
tests = {
|
| 171 |
# BOM
|
| 172 |
('utf_32_be'): u'\x00\x00\xFE\xFFanything', |
| 173 |
('utf_32_le'): u'\xFF\xFE\x00\x00anything', |
| 174 |
('utf_16_be'): u'\xFE\xFFanything', |
| 175 |
('utf_16_le'): u'\xFF\xFEanything', |
| 176 |
('utf-8'): u'\xef\xbb\xbfanything', |
| 177 |
# encoding=
|
| 178 |
('ascii'): '<?xml version="1.0" encoding="ascii" ?>', |
| 179 |
('ascii'): "<?xml version='1.0' encoding='ascii' ?>", |
| 180 |
('iso-8859-1'): "<?xml version='1.0' encoding='iso-8859-1' ?>", |
| 181 |
# default
|
| 182 |
('utf-8'): '<?xml version="1.0" ?>', |
| 183 |
('utf-8'): '<?xml version="1.0"?><x encoding="ascii"/>' |
| 184 |
} |
| 185 |
for exp, test in tests.items(): |
| 186 |
self.assertEqual(exp, encutils.detectXMLEncoding(test, log=log))
|
| 187 |
|
| 188 |
def test_tryEncodings(self): |
| 189 |
"encutils.tryEncodings"
|
| 190 |
try:
|
| 191 |
import chardet |
| 192 |
tests = [ |
| 193 |
('ascii', u'abc'.encode('ascii')), |
| 194 |
('windows-1252', u'€'.encode('windows-1252')), |
| 195 |
('ascii', u'1'.encode('utf-8')) |
| 196 |
] |
| 197 |
except ImportError: |
| 198 |
tests = [ |
| 199 |
('ascii', u'abc'.encode('ascii')), |
| 200 |
('windows-1252', u'€'.encode('windows-1252')), |
| 201 |
('iso-8859-1', u'äöüß'.encode('iso-8859-1')), |
| 202 |
('iso-8859-1', u'äöüß'.encode('windows-1252')), |
| 203 |
#('utf-8', u'\u1111'.encode('utf-8'))
|
| 204 |
] |
| 205 |
for exp, test in tests: |
| 206 |
self.assertEqual(exp, encutils.tryEncodings(test))
|
| 207 |
|
| 208 |
|
| 209 |
def test_getEncodingInfo(self): |
| 210 |
"encutils.getEncodingInfo"
|
| 211 |
# (expectedencoding, expectedmismatch): (httpheader, filecontent)
|
| 212 |
tests = [ |
| 213 |
|
| 214 |
# --- application/xhtml+xml ---
|
| 215 |
|
| 216 |
# header default and XML default
|
| 217 |
(('utf-8', False), ( |
| 218 |
'''Content-Type: application/xhtml+xml''',
|
| 219 |
'''<?xml version="1.0" ?>
|
| 220 |
<example>
|
| 221 |
<meta http-equiv="Content-Type"
|
| 222 |
content="application/xhtml+xml"/>
|
| 223 |
</example>''')),
|
| 224 |
# XML default
|
| 225 |
(('utf-8', False), ( |
| 226 |
None,
|
| 227 |
'''<?xml version="1.0" ?>
|
| 228 |
<example>
|
| 229 |
<meta http-equiv="Content-Type"
|
| 230 |
content="application/xhtml+xml"/>
|
| 231 |
</example>''')),
|
| 232 |
# meta is ignored!
|
| 233 |
(('utf-8', False), ( |
| 234 |
'''Content-Type: application/xhtml+xml''',
|
| 235 |
'''<?xml version="1.0" ?>
|
| 236 |
<example>
|
| 237 |
<meta http-equiv="Content-Type"
|
| 238 |
content="application/xhtml+xml;charset=iso_M"/>
|
| 239 |
</example>''')),
|
| 240 |
|
| 241 |
# header enc and XML default
|
| 242 |
(('iso-h', True), ( |
| 243 |
'''Content-Type: application/xhtml+xml;charset=iso-H''',
|
| 244 |
'''<?xml version="1.0" ?>
|
| 245 |
<example>
|
| 246 |
<meta http-equiv="Content-Type"
|
| 247 |
content="application/xhtml+xml"/>
|
| 248 |
</example>''')),
|
| 249 |
|
| 250 |
# mismatch header and XML explicit, header wins
|
| 251 |
(('iso-h', True), ( |
| 252 |
'''Content-Type: application/xhtml+xml;charset=iso-H''',
|
| 253 |
'''<?xml version="1.0" encoding="iso-X" ?>
|
| 254 |
<example/>''')),
|
| 255 |
|
| 256 |
# header == XML, meta ignored!
|
| 257 |
(('iso-h', False), ( |
| 258 |
'''Content-Type: application/xhtml+xml;charset=iso-H''',
|
| 259 |
'''<?xml version="1.0" encoding="iso-h" ?>
|
| 260 |
<example>
|
| 261 |
<meta http-equiv="Content-Type"
|
| 262 |
content="application/xhtml+xml;charset=iso_M"/>
|
| 263 |
</example>''')),
|
| 264 |
|
| 265 |
# XML only, meta ignored!
|
| 266 |
(('iso-x', False), ( |
| 267 |
'''Content-Type: application/xhtml+xml''',
|
| 268 |
'''<?xml version="1.0" encoding="iso-X" ?>
|
| 269 |
<example>
|
| 270 |
<meta http-equiv="Content-Type"
|
| 271 |
content="application/xhtml+xml;charset=iso_M"/>
|
| 272 |
</example>''')),
|
| 273 |
|
| 274 |
|
| 275 |
# no text or not enough text:
|
| 276 |
(('iso-h', False), ('Content-Type: application/xml;charset=iso-h', |
| 277 |
'1')),
|
| 278 |
(('utf-8', False), ('Content-Type: application/xml', |
| 279 |
None)),
|
| 280 |
((None, False), ('Content-Type: application/xml', |
| 281 |
'1')),
|
| 282 |
|
| 283 |
|
| 284 |
# --- text/xml ---
|
| 285 |
|
| 286 |
# default enc
|
| 287 |
(('ascii', False), ( |
| 288 |
'''Content-Type: text/xml''',
|
| 289 |
'''<?xml version="1.0" ?>
|
| 290 |
<example>
|
| 291 |
<meta http-equiv="Content-Type"
|
| 292 |
content="text/xml"/>
|
| 293 |
</example>''')),
|
| 294 |
# default as XML ignored and meta completely ignored
|
| 295 |
(('ascii', False), ( |
| 296 |
'''Content-Type: text/xml''',
|
| 297 |
'''<?xml version="1.0" encoding="iso-X" ?>
|
| 298 |
<example>
|
| 299 |
<meta http-equiv="Content-Type"
|
| 300 |
content="text/xml;charset=iso_M"/>
|
| 301 |
</example>''')),
|
| 302 |
(('ascii', False), ('Content-Type: text/xml', |
| 303 |
'1')),
|
| 304 |
(('ascii', False), ('Content-Type: text/xml', |
| 305 |
None)),
|
| 306 |
|
| 307 |
# header enc
|
| 308 |
(('iso-h', False), ( |
| 309 |
'''Content-Type: text/xml;charset=iso-H''',
|
| 310 |
'''<?xml version="1.0" ?>
|
| 311 |
<example>
|
| 312 |
<meta http-equiv="Content-Type"
|
| 313 |
content="text/xml"/>
|
| 314 |
</example>''')),
|
| 315 |
|
| 316 |
# header only, XML and meta ignored!
|
| 317 |
(('iso-h', False), ( |
| 318 |
'''Content-Type: text/xml;charset=iso-H''',
|
| 319 |
'''<?xml version="1.0" encoding="iso-X" ?>
|
| 320 |
<example/>''')),
|
| 321 |
(('iso-h', False), ( |
| 322 |
'''Content-Type: text/xml;charset=iso-H''',
|
| 323 |
'''<?xml version="1.0" encoding="iso-h" ?>
|
| 324 |
<example>
|
| 325 |
<meta http-equiv="Content-Type"
|
| 326 |
content="text/xml;charset=iso_M"/>
|
| 327 |
</example>''')),
|
| 328 |
|
| 329 |
|
| 330 |
# --- text/html ---
|
| 331 |
|
| 332 |
# default enc
|
| 333 |
(('iso-8859-1', False), ('Content-Type: text/html;', |
| 334 |
'''<meta http-equiv="Content-Type"
|
| 335 |
content="text/html">''')),
|
| 336 |
(('iso-8859-1', False), ('Content-Type: text/html;', |
| 337 |
None)),
|
| 338 |
|
| 339 |
# header enc
|
| 340 |
(('iso-h', False), ('Content-Type: text/html;charset=iso-H', |
| 341 |
'''<meta http-equiv="Content-Type"
|
| 342 |
content="text/html">''')),
|
| 343 |
# meta enc
|
| 344 |
(('iso-m', False), ('Content-Type: text/html', |
| 345 |
'''<meta http-equiv="Content-Type"
|
| 346 |
content="text/html;charset=iso-m">''')),
|
| 347 |
|
| 348 |
# mismatch header and meta, header wins
|
| 349 |
(('iso-h', True), ('Content-Type: text/html;charset=iso-H', |
| 350 |
'''<meta http-equiv="Content-Type"
|
| 351 |
content="text/html;charset=iso-m">''')),
|
| 352 |
|
| 353 |
# no header:
|
| 354 |
((None, False), (None, |
| 355 |
'''<meta http-equiv="Content-Type"
|
| 356 |
content="text/html;charset=iso-m">''')),
|
| 357 |
# no encoding at all
|
| 358 |
((None, False), (None, |
| 359 |
'''<meta http-equiv="Content-Type"
|
| 360 |
content="text/html">''')),
|
| 361 |
|
| 362 |
|
| 363 |
((None, False), (None, |
| 364 |
'''text''')),
|
| 365 |
|
| 366 |
|
| 367 |
# --- no header ---
|
| 368 |
|
| 369 |
((None, False), (None, '')), |
| 370 |
(('iso-8859-1', False), ('''NoContentType''', |
| 371 |
'''OnlyText''')),
|
| 372 |
(('iso-8859-1', False), ('Content-Type: text/html;', |
| 373 |
None)),
|
| 374 |
(('iso-8859-1', False), ('Content-Type: text/html;', |
| 375 |
'1')),
|
| 376 |
|
| 377 |
# XML
|
| 378 |
(('utf-8', False), (None, |
| 379 |
'''<?xml version=''')),
|
| 380 |
(('iso-x', False), (None, |
| 381 |
'''<?xml version="1.0" encoding="iso-X"?>''')),
|
| 382 |
# meta ignored
|
| 383 |
(('utf-8', False), (None, |
| 384 |
'''<?xml version="1.0" ?>
|
| 385 |
<html><meta http-equiv="Content-Type"
|
| 386 |
content="text/html;charset=iso-m"></html>''')),
|
| 387 |
|
| 388 |
(('utf-8', False), ('Content-Type: text/css;', |
| 389 |
'1')),
|
| 390 |
(('iso-h', False), ('Content-Type: text/css;charset=iso-h', |
| 391 |
'1')),
|
| 392 |
# only header is used by encutils
|
| 393 |
(('utf-8', False), ('Content-Type: text/css', |
| 394 |
'@charset "ascii";')),
|
| 395 |
|
| 396 |
] |
| 397 |
for exp, test in tests: |
| 398 |
header, text = test |
| 399 |
if header:
|
| 400 |
res = encutils.getEncodingInfo(self._fakeRes(header), text)
|
| 401 |
else:
|
| 402 |
res = encutils.getEncodingInfo(text=text) |
| 403 |
|
| 404 |
res = (res.encoding, res.mismatch) |
| 405 |
self.assertEqual(exp, res)
|
| 406 |
|
| 407 |
|
| 408 |
if __name__ == '__main__': |
| 409 |
unittest.main() |