/usr/lib/python2.7/dist-packages/bs4/tests/test_soup.py is in python-bs4 4.6.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | # -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
from pdb import set_trace
import logging
import unittest
import sys
import tempfile
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
)
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
SoupStrainer,
NamespacedAttribute,
)
import bs4.dammit
from bs4.dammit import (
EntitySubstitution,
UnicodeDammit,
EncodingDetector,
)
from bs4.testing import (
SoupTest,
skipIf,
)
import warnings
try:
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
LXML_PRESENT = True
except ImportError, e:
LXML_PRESENT = False
PYTHON_3_PRE_3_2 = (sys.version_info[0] == 3 and sys.version_info < (3,2))
class TestConstructor(SoupTest):
def test_short_unicode_input(self):
data = u"<h1>éé</h1>"
soup = self.soup(data)
self.assertEqual(u"éé", soup.h1.string)
def test_embedded_null(self):
data = u"<h1>foo\0bar</h1>"
soup = self.soup(data)
self.assertEqual(u"foo\0bar", soup.h1.string)
def test_exclude_encodings(self):
utf8_data = u"Räksmörgås".encode("utf-8")
soup = self.soup(utf8_data, exclude_encodings=["utf-8"])
self.assertEqual("windows-1252", soup.original_encoding)
class TestWarnings(SoupTest):
def _no_parser_specified(self, s, is_there=True):
v = s.startswith(BeautifulSoup.NO_PARSER_SPECIFIED_WARNING[:80])
self.assertTrue(v)
def test_warning_if_no_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>")
msg = str(w[0].message)
self._assert_no_parser_specified(msg)
def test_warning_if_parser_specified_too_vague(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", "html")
msg = str(w[0].message)
self._assert_no_parser_specified(msg)
def test_no_warning_if_explicit_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", "html.parser")
self.assertEqual([], w)
def test_parseOnlyThese_renamed_to_parse_only(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
msg = str(w[0].message)
self.assertTrue("parseOnlyThese" in msg)
self.assertTrue("parse_only" in msg)
self.assertEqual(b"<b></b>", soup.encode())
def test_fromEncoding_renamed_to_from_encoding(self):
with warnings.catch_warnings(record=True) as w:
utf8 = b"\xc3\xa9"
soup = self.soup(utf8, fromEncoding="utf8")
msg = str(w[0].message)
self.assertTrue("fromEncoding" in msg)
self.assertTrue("from_encoding" in msg)
self.assertEqual("utf8", soup.original_encoding)
def test_unrecognized_keyword_argument(self):
self.assertRaises(
TypeError, self.soup, "<a>", no_such_argument=True)
class TestWarnings(SoupTest):
def test_disk_file_warning(self):
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
try:
with warnings.catch_warnings(record=True) as w:
soup = self.soup(filename)
msg = str(w[0].message)
self.assertTrue("looks like a filename" in msg)
finally:
filehandle.close()
# The file no longer exists, so Beautiful Soup will no longer issue the warning.
with warnings.catch_warnings(record=True) as w:
soup = self.soup(filename)
self.assertEqual(0, len(w))
def test_url_warning_with_bytes_url(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/")
# Be aware this isn't the only warning that can be raised during
# execution..
self.assertTrue(any("looks like a URL" in str(w.message)
for w in warning_list))
def test_url_warning_with_unicode_url(self):
with warnings.catch_warnings(record=True) as warning_list:
# note - this url must differ from the bytes one otherwise
# python's warnings system swallows the second warning
soup = self.soup(u"http://www.crummyunicode.com/")
self.assertTrue(any("looks like a URL" in str(w.message)
for w in warning_list))
def test_url_warning_with_bytes_and_space(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/ is great")
self.assertFalse(any("looks like a URL" in str(w.message)
for w in warning_list))
def test_url_warning_with_unicode_and_space(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(u"http://www.crummyuncode.com/ is great")
self.assertFalse(any("looks like a URL" in str(w.message)
for w in warning_list))
class TestSelectiveParsing(SoupTest):
def test_parse_with_soupstrainer(self):
markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
strainer = SoupStrainer("b")
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")
class TestEntitySubstitution(unittest.TestCase):
"""Standalone tests of the EntitySubstitution class."""
def setUp(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = u"foo\u2200\N{SNOWMAN}\u00f5bar"
self.assertEqual(self.sub.substitute_html(s),
u"foo∀\N{SNOWMAN}õbar")
def test_smart_quote_substitution(self):
# MS smart quotes are a common source of frustration, so we
# give them a special test.
quotes = b"\x91\x92foo\x93\x94"
dammit = UnicodeDammit(quotes)
self.assertEqual(self.sub.substitute_html(dammit.markup),
"‘’foo“”")
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
self.assertEqual(self.sub.substitute_xml(s, False), s)
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
self.assertEqual(self.sub.substitute_xml("Welcome", True),
'"Welcome"')
self.assertEqual(self.sub.substitute_xml("Bob's Bar", True),
'"Bob\'s Bar"')
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
s = 'Welcome to "my bar"'
self.assertEqual(self.sub.substitute_xml(s, True),
"'Welcome to \"my bar\"'")
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
s = 'Welcome to "Bob\'s Bar"'
self.assertEqual(
self.sub.substitute_xml(s, True),
'"Welcome to "Bob\'s Bar""')
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
self.assertEqual(self.sub.substitute_xml(quoted), quoted)
def test_xml_quoting_handles_angle_brackets(self):
self.assertEqual(
self.sub.substitute_xml("foo<bar>"),
"foo<bar>")
def test_xml_quoting_handles_ampersands(self):
self.assertEqual(self.sub.substitute_xml("AT&T"), "AT&T")
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
self.assertEqual(
self.sub.substitute_xml("ÁT&T"),
"&Aacute;T&T")
def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
self.assertEqual(
self.sub.substitute_xml_containing_entities("ÁT&T"),
"ÁT&T")
def test_quotes_not_html_substituted(self):
"""There's no need to do this except inside attribute values."""
text = 'Bob\'s "bar"'
self.assertEqual(self.sub.substitute_html(text), text)
class TestEncodingConversion(SoupTest):
# Test Beautiful Soup's ability to decode and encode from various
# encodings.
def setUp(self):
super(TestEncodingConversion, self).setUp()
self.unicode_data = u'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
self.utf8_data = self.unicode_data.encode("utf-8")
# Just so you know what it looks like.
self.assertEqual(
self.utf8_data,
b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>')
def test_ascii_in_unicode_out(self):
# ASCII input is converted to Unicode. The original_encoding
# attribute is set to 'utf-8', a superset of ASCII.
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
# Disable chardet, which will realize that the ASCII is ASCII.
bs4.dammit.chardet_dammit = noop
ascii = b"<foo>a</foo>"
soup_from_ascii = self.soup(ascii)
unicode_output = soup_from_ascii.decode()
self.assertTrue(isinstance(unicode_output, unicode))
self.assertEqual(unicode_output, self.document_for(ascii.decode()))
self.assertEqual(soup_from_ascii.original_encoding.lower(), "utf-8")
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_unicode_in_unicode_out(self):
# Unicode input is left alone. The original_encoding attribute
# is not set.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEqual(soup_from_unicode.decode(), self.unicode_data)
self.assertEqual(soup_from_unicode.foo.string, u'Sacr\xe9 bleu!')
self.assertEqual(soup_from_unicode.original_encoding, None)
def test_utf8_in_unicode_out(self):
# UTF-8 input is converted to Unicode. The original_encoding
# attribute is set.
soup_from_utf8 = self.soup(self.utf8_data)
self.assertEqual(soup_from_utf8.decode(), self.unicode_data)
self.assertEqual(soup_from_utf8.foo.string, u'Sacr\xe9 bleu!')
def test_utf8_out(self):
# The internal data structures can be encoded as UTF-8.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEqual(soup_from_unicode.encode('utf-8'), self.utf8_data)
@skipIf(
PYTHON_3_PRE_3_2,
"Bad HTMLParser detected; skipping test of non-ASCII characters in attribute name.")
def test_attribute_name_containing_unicode_characters(self):
markup = u'<div><a \N{SNOWMAN}="snowman"></a></div>'
self.assertEqual(self.soup(markup).div.encode("utf8"), markup.encode("utf8"))
class TestUnicodeDammit(unittest.TestCase):
"""Standalone tests of UnicodeDammit."""
def test_unicode_input(self):
markup = u"I'm already Unicode! \N{SNOWMAN}"
dammit = UnicodeDammit(markup)
self.assertEqual(dammit.unicode_markup, markup)
def test_smart_quotes_to_unicode(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
self.assertEqual(
dammit.unicode_markup, u"<foo>\u2018\u2019\u201c\u201d</foo>")
def test_smart_quotes_to_xml_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
self.assertEqual(
dammit.unicode_markup, "<foo>‘’“”</foo>")
def test_smart_quotes_to_html_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="html")
self.assertEqual(
dammit.unicode_markup, "<foo>‘’“”</foo>")
def test_smart_quotes_to_ascii(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
self.assertEqual(
dammit.unicode_markup, """<foo>''""</foo>""")
def test_detect_utf8(self):
utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
dammit = UnicodeDammit(utf8)
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
self.assertEqual(dammit.unicode_markup, u'Sacr\xe9 bleu! \N{SNOWMAN}')
def test_convert_hebrew(self):
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
self.assertEqual(dammit.original_encoding.lower(), 'iso-8859-8')
self.assertEqual(dammit.unicode_markup, u'\u05dd\u05d5\u05dc\u05e9')
def test_dont_see_smart_quotes_where_there_are_none(self):
utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
dammit = UnicodeDammit(utf_8)
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
self.assertEqual(dammit.unicode_markup.encode("utf-8"), utf_8)
def test_ignore_inappropriate_codecs(self):
utf8_data = u"Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
def test_ignore_invalid_codecs(self):
utf8_data = u"Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
def test_exclude_encodings(self):
# This is UTF-8.
utf8_data = u"Räksmörgås".encode("utf-8")
# But if we exclude UTF-8 from consideration, the guess is
# Windows-1252.
dammit = UnicodeDammit(utf8_data, exclude_encodings=["utf-8"])
self.assertEqual(dammit.original_encoding.lower(), 'windows-1252')
# And if we exclude that, there is no valid guess at all.
dammit = UnicodeDammit(
utf8_data, exclude_encodings=["utf-8", "windows-1252"])
self.assertEqual(dammit.original_encoding, None)
def test_encoding_detector_replaces_junk_in_encoding_name_with_replacement_character(self):
detected = EncodingDetector(
b'<?xml version="1.0" encoding="UTF-\xdb" ?>')
encodings = list(detected.encodings)
assert u'utf-\N{REPLACEMENT CHARACTER}' in encodings
def test_detect_html5_style_meta_tag(self):
for data in (
b'<html><meta charset="euc-jp" /></html>',
b"<html><meta charset='euc-jp' /></html>",
b"<html><meta charset=euc-jp /></html>",
b"<html><meta charset=euc-jp/></html>"):
dammit = UnicodeDammit(data, is_html=True)
self.assertEqual(
"euc-jp", dammit.original_encoding)
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue(u"\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_byte_order_mark_removed(self):
# A document written in UTF-16LE will have its byte order marker stripped.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
self.assertEqual(u"<a>áé</a>", dammit.unicode_markup)
self.assertEqual("utf-16le", dammit.original_encoding)
def test_detwingle(self):
# Here's a UTF8 document.
utf8 = (u"\N{SNOWMAN}" * 3).encode("utf8")
# Here's a Windows-1252 document.
windows_1252 = (
u"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
u"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
# Through some unholy alchemy, they've been stuck together.
doc = utf8 + windows_1252 + utf8
# The document can't be turned into UTF-8:
self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
# Unicode, Dammit thinks the whole document is Windows-1252,
# and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
# But if we run it through fix_embedded_windows_1252, it's fixed:
fixed = UnicodeDammit.detwingle(doc)
self.assertEqual(
u"☃☃☃“Hi, I like Windows!”☃☃☃", fixed.decode("utf8"))
def test_detwingle_ignores_multibyte_characters(self):
# Each of these characters has a UTF-8 representation ending
# in \x93. \x93 is a smart quote if interpreted as
# Windows-1252. But our code knows to skip over multibyte
# UTF-8 characters, so they'll survive the process unscathed.
for tricky_unicode_char in (
u"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
u"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
u"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
):
input = tricky_unicode_char.encode("utf8")
self.assertTrue(input.endswith(b'\x93'))
output = UnicodeDammit.detwingle(input)
self.assertEqual(output, input)
class TestNamedspacedAttribute(SoupTest):
def test_name_may_be_none(self):
a = NamespacedAttribute("xmlns", None)
self.assertEqual(a, "xmlns")
def test_attribute_is_equivalent_to_colon_separated_string(self):
a = NamespacedAttribute("a", "b")
self.assertEqual("a:b", a)
def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
a = NamespacedAttribute("a", "b", "c")
b = NamespacedAttribute("a", "b", "c")
self.assertEqual(a, b)
# The actual namespace is not considered.
c = NamespacedAttribute("a", "b", None)
self.assertEqual(a, c)
# But name and prefix are important.
d = NamespacedAttribute("a", "z", "c")
self.assertNotEqual(a, d)
e = NamespacedAttribute("z", "b", "c")
self.assertNotEqual(a, e)
class TestAttributeValueWithCharsetSubstitution(unittest.TestCase):
def test_content_meta_attribute_value(self):
value = CharsetMetaAttributeValue("euc-jp")
self.assertEqual("euc-jp", value)
self.assertEqual("euc-jp", value.original_value)
self.assertEqual("utf8", value.encode("utf8"))
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
self.assertEqual("text/html; charset=euc-jp", value)
self.assertEqual("text/html; charset=euc-jp", value.original_value)
self.assertEqual("text/html; charset=utf8", value.encode("utf8"))
|