This repository was archived by the owner on May 5, 2023. It is now read-only.
forked from html5lib/html5lib-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtokenizer.py
More file actions
257 lines (206 loc) · 9.12 KB
/
Copy pathtokenizer.py
File metadata and controls
257 lines (206 loc) · 9.12 KB
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
# SPDX-FileCopyrightText: 2006-2021 html5lib contributors. See AUTHORS.rst
#
# SPDX-License-Identifier: MIT
from __future__ import absolute_import, division, unicode_literals
import codecs
import json
import warnings
import re
import pytest
from six import unichr
from html5lib._tokenizer import HTMLTokenizer
from html5lib import constants, _utils
class TokenizerTestParser(object):
def __init__(self, initialState, lastStartTag=None):
self.tokenizer = HTMLTokenizer
self._state = initialState
self._lastStartTag = lastStartTag
def parse(self, stream, encoding=None, innerHTML=False):
# pylint:disable=unused-argument
tokenizer = self.tokenizer(stream, encoding)
self.outputTokens = []
tokenizer.state = getattr(tokenizer, self._state)
if self._lastStartTag is not None:
tokenizer.currentToken = {"type": "startTag",
"name": self._lastStartTag}
types = {v: k for k, v in constants.tokenTypes.items()}
for token in tokenizer:
getattr(self, 'process%s' % types[token["type"]])(token)
return self.outputTokens
def processDoctype(self, token):
self.outputTokens.append(["DOCTYPE", token["name"], token["publicId"],
token["systemId"], token["correct"]])
def processStartTag(self, token):
self.outputTokens.append(["StartTag", token["name"],
token["data"], token["selfClosing"]])
def processEmptyTag(self, token):
if token["name"] not in constants.voidElements:
self.outputTokens.append("ParseError")
self.outputTokens.append(["StartTag", token["name"], dict(token["data"][::-1])])
def processEndTag(self, token):
self.outputTokens.append(["EndTag", token["name"],
token["selfClosing"]])
def processComment(self, token):
self.outputTokens.append(["Comment", token["data"]])
def processSpaceCharacters(self, token):
self.outputTokens.append(["Character", token["data"]])
self.processSpaceCharacters = self.processCharacters
def processCharacters(self, token):
self.outputTokens.append(["Character", token["data"]])
def processEOF(self, token):
pass
def processParseError(self, token):
self.outputTokens.append(["ParseError", token["data"]])
def concatenateCharacterTokens(tokens):
outputTokens = []
for token in tokens:
if "ParseError" not in token and token[0] == "Character":
if (outputTokens and "ParseError" not in outputTokens[-1] and
outputTokens[-1][0] == "Character"):
outputTokens[-1][1] += token[1]
else:
outputTokens.append(token)
else:
outputTokens.append(token)
return outputTokens
def normalizeTokens(tokens):
# TODO: convert tests to reflect arrays
for i, token in enumerate(tokens):
if token[0] == 'ParseError':
tokens[i] = token[0]
return tokens
def tokensMatch(expectedTokens, receivedTokens, ignoreErrorOrder,
ignoreErrors=False):
"""Test whether the test has passed or failed
If the ignoreErrorOrder flag is set to true we don't test the relative
positions of parse errors and non parse errors
"""
checkSelfClosing = False
for token in expectedTokens:
if (token[0] == "StartTag" and len(token) == 4 or
token[0] == "EndTag" and len(token) == 3):
checkSelfClosing = True
break
if not checkSelfClosing:
for token in receivedTokens:
if token[0] == "StartTag" or token[0] == "EndTag":
token.pop()
if not ignoreErrorOrder and not ignoreErrors:
expectedTokens = concatenateCharacterTokens(expectedTokens)
return expectedTokens == receivedTokens
else:
# Sort the tokens into two groups; non-parse errors and parse errors
tokens = {"expected": [[], []], "received": [[], []]}
for tokenType, tokenList in zip(list(tokens.keys()),
(expectedTokens, receivedTokens)):
for token in tokenList:
if token != "ParseError":
tokens[tokenType][0].append(token)
else:
if not ignoreErrors:
tokens[tokenType][1].append(token)
tokens[tokenType][0] = concatenateCharacterTokens(tokens[tokenType][0])
return tokens["expected"] == tokens["received"]
_surrogateRe = re.compile(r"\\u([0-9A-Fa-f]{4})(?:\\u([0-9A-Fa-f]{4}))?")
def unescape(test):
def decode(inp):
"""Decode \\uXXXX escapes
This decodes \\uXXXX escapes, possibly into non-BMP characters when
two surrogate character escapes are adjacent to each other.
"""
# This cannot be implemented using the unicode_escape codec
# because that requires its input be ISO-8859-1, and we need
# arbitrary unicode as input.
def repl(m):
if m.group(2) is not None:
high = int(m.group(1), 16)
low = int(m.group(2), 16)
if 0xD800 <= high <= 0xDBFF and 0xDC00 <= low <= 0xDFFF:
cp = ((high - 0xD800) << 10) + (low - 0xDC00) + 0x10000
return unichr(cp)
else:
return unichr(high) + unichr(low)
else:
return unichr(int(m.group(1), 16))
try:
return _surrogateRe.sub(repl, inp)
except ValueError:
# This occurs when unichr throws ValueError, which should
# only be for a lone-surrogate.
if _utils.supports_lone_surrogates:
raise
return None
test["input"] = decode(test["input"])
for token in test["output"]:
if token == "ParseError":
continue
else:
token[1] = decode(token[1])
if len(token) > 2:
for key, value in token[2]:
del token[2][key]
token[2][decode(key)] = decode(value)
return test
def _doCapitalize(match):
return match.group(1).upper()
_capitalizeRe = re.compile(r"\W+(\w)").sub
def capitalize(s):
s = s.lower()
s = _capitalizeRe(_doCapitalize, s)
return s
class TokenizerFile(pytest.File):
def collect(self):
with codecs.open(str(self.fspath), "r", encoding="utf-8") as fp:
tests = json.load(fp)
if 'tests' in tests:
for i, test in enumerate(tests['tests']):
yield TokenizerTestCollector.from_parent(self, name=str(i), testdata=test)
class TokenizerTestCollector(pytest.Collector):
def __init__(self, name, parent=None, config=None, session=None, testdata=None):
super(TokenizerTestCollector, self).__init__(name, parent, config, session)
if 'initialStates' not in testdata:
testdata["initialStates"] = ["Data state"]
if 'doubleEscaped' in testdata:
testdata = unescape(testdata)
self.testdata = testdata
def collect(self):
for initialState in self.testdata["initialStates"]:
initialState = capitalize(initialState)
item = TokenizerTest.from_parent(self,
name=initialState,
test=self.testdata,
initialState=initialState)
if self.testdata["input"] is None:
item.add_marker(pytest.mark.skipif(True, reason="Relies on lone surrogates"))
yield item
class TokenizerTest(pytest.Item):
def __init__(self, name, parent, test, initialState):
super(TokenizerTest, self).__init__(name, parent)
self.obj = lambda: 1 # this is to hack around skipif needing a function!
self.test = test
self.initialState = initialState
def runtest(self):
warnings.resetwarnings()
warnings.simplefilter("error")
expected = self.test['output']
if 'lastStartTag' not in self.test:
self.test['lastStartTag'] = None
parser = TokenizerTestParser(self.initialState,
self.test['lastStartTag'])
tokens = parser.parse(self.test['input'])
received = normalizeTokens(tokens)
errorMsg = "\n".join(["\n\nInitial state:",
self.initialState,
"\nInput:", self.test['input'],
"\nExpected:", repr(expected),
"\nreceived:", repr(tokens)])
errorMsg = errorMsg
ignoreErrorOrder = self.test.get('ignoreErrorOrder', False)
assert tokensMatch(expected, received, ignoreErrorOrder, True), errorMsg
def repr_failure(self, excinfo):
traceback = excinfo.traceback
ntraceback = traceback.cut(path=__file__)
excinfo.traceback = ntraceback.filter()
return excinfo.getrepr(funcargs=True,
showlocals=False,
style="short", tbfilter=False)