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
|
# Copyright (C) 2012-2016 Ben Kurtovic <ben.kurtovic@gmail.com>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import codecs
from os import listdir, path
import warnings
import pytest
from mwparserfromhell.parser import contexts, tokens
from mwparserfromhell.parser.builder import Builder
from mwparserfromhell.parser.tokenizer import Tokenizer as PyTokenizer
try:
from mwparserfromhell.parser._tokenizer import CTokenizer
except ImportError:
CTokenizer = None
class _TestParseError(Exception):
"""Raised internally when a test could not be parsed."""
def _parse_test(test, data):
"""Parse an individual *test*, storing its info in *data*."""
for line in test.strip().splitlines():
if line.startswith("name:"):
data["name"] = line[len("name:") :].strip()
elif line.startswith("label:"):
data["label"] = line[len("label:") :].strip()
elif line.startswith("input:"):
raw = line[len("input:") :].strip()
if raw[0] == '"' and raw[-1] == '"':
raw = raw[1:-1]
raw = raw.encode("raw_unicode_escape")
data["input"] = raw.decode("unicode_escape")
elif line.startswith("output:"):
raw = line[len("output:") :].strip()
try:
data["output"] = eval(raw, vars(tokens))
except Exception as err:
raise _TestParseError(err) from err
def _load_tests(filename, name, text):
"""Load all tests in *text* from the file *filename*."""
tests = text.split("\n---\n")
for test in tests:
data = {"name": None, "label": None, "input": None, "output": None}
try:
_parse_test(test, data)
except _TestParseError as err:
if data["name"]:
error = "Could not parse test '{0}' in '{1}':\n\t{2}"
warnings.warn(error.format(data["name"], filename, err))
else:
error = "Could not parse a test in '{0}':\n\t{1}"
warnings.warn(error.format(filename, err))
continue
if not data["name"]:
error = "A test in '{0}' was ignored because it lacked a name"
warnings.warn(error.format(filename))
continue
if data["input"] is None or data["output"] is None:
error = (
"Test '{}' in '{}' was ignored because it lacked an input or an output"
)
warnings.warn(error.format(data["name"], filename))
continue
# Include test filename in name
data["name"] = "{}:{}".format(name, data["name"])
yield data
def build():
"""Load and install all tests from the 'tokenizer' directory."""
directory = path.join(path.dirname(__file__), "tokenizer")
extension = ".mwtest"
for filename in listdir(directory):
if not filename.endswith(extension):
continue
fullname = path.join(directory, filename)
with codecs.open(fullname, "r", encoding="utf8") as fp:
text = fp.read()
name = path.split(fullname)[1][: -len(extension)]
yield from _load_tests(fullname, name, text)
@pytest.mark.parametrize(
"tokenizer",
filter(None, (CTokenizer, PyTokenizer)),
ids=lambda t: "CTokenizer" if t.USES_C else "PyTokenizer",
)
@pytest.mark.parametrize("data", build(), ids=lambda data: data["name"])
def test_tokenizer(tokenizer, data):
expected = data["output"]
actual = tokenizer().tokenize(data["input"])
assert expected == actual
@pytest.mark.parametrize("data", build(), ids=lambda data: data["name"])
def test_roundtrip(data):
expected = data["input"]
actual = str(Builder().build(data["output"][:]))
assert expected == actual
@pytest.mark.skipif(CTokenizer is None, reason="CTokenizer not available")
def test_c_tokenizer_uses_c():
"""make sure the C tokenizer identifies as using a C extension"""
assert CTokenizer.USES_C is True
assert CTokenizer().USES_C is True
def test_describe_context():
assert "" == contexts.describe(0)
ctx = contexts.describe(contexts.TEMPLATE_PARAM_KEY | contexts.HAS_TEXT)
assert "TEMPLATE_PARAM_KEY|HAS_TEXT" == ctx
|
