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
|
import re
from typing import Callable, List, Optional, Tuple, Type, TypeVar, Union
from ._vendor.funcparserlib.lexer import LexerError, Token
from ._vendor.funcparserlib.parser import (
NoParseError,
Parser,
_Tuple,
finished,
many,
pure,
skip,
some,
tok,
)
StringLike = TypeVar("StringLike", str, bytes)
class Test:
def __init__(
self, data: List[Tuple[StringLike, StringLike]], lineno: Optional[int] = None
) -> None:
self.data = data
self.lineno = lineno
def _make_tokenizer(specs: List[Tuple[str, Tuple[StringLike]]]) -> Callable:
# Forked from upstream funcparserlib.lexer to fix #46
def compile_spec(spec):
name, args = spec
return name, re.compile(*args)
compiled = [compile_spec(s) for s in specs]
def match_specs(specs, s, i, position):
if isinstance(s, str):
lf = "\n"
else:
lf = b"\n"
line, pos = position
for type, regexp in specs:
m = regexp.match(s, i)
if m is not None:
value = m.group()
nls = value.count(lf)
n_line = line + nls
if nls == 0:
n_pos = pos + len(value)
else:
n_pos = len(value) - value.rfind(lf) - 1
return Token(type, value, (line, pos + 1), (n_line, n_pos))
else:
errline = s.splitlines()[line - 1]
raise LexerError((line, pos + 1), errline)
def f(s):
length = len(s)
line, pos = 1, 0
i = 0
while i < length:
t = match_specs(compiled, s, i, (line, pos))
yield t
line, pos = t.end
i += len(t.value)
return f
_token_specs_u = [
("HEADER", (r"[ \t]*#[^\n]*",)),
("BODY", (r"[^#\n][^\n]*",)),
("EOL", (r"\n",)),
]
_token_specs_b = [
(name, (regexp.encode("ascii"),)) for (name, (regexp,)) in _token_specs_u
]
_tokenizer_u = _make_tokenizer(_token_specs_u)
_tokenizer_b = _make_tokenizer(_token_specs_b)
def _many_merge(toks: _Tuple) -> List[Test]:
x, xs = toks
return [x] + xs
def _notFollowedBy(p: Parser) -> Parser:
@Parser
def __notFollowedBy(tokens, s):
try:
p.run(tokens, s)
except NoParseError:
return skip(pure(None)).run(tokens, s)
else:
raise NoParseError("is followed by", s)
__notFollowedBy.name = "(notFollowedBy {})".format(p)
return __notFollowedBy
def _trim_prefix(s: StringLike, prefix: StringLike) -> StringLike:
if s.startswith(prefix):
return s[len(prefix) :]
else:
return s
def _make_test(result: _Tuple) -> Test:
first, rest = result
(first_header, first_lineno), first_body = first
return Test([(first_header, first_body)] + rest, lineno=first_lineno)
def _parser(
tokens: List[Token],
new_test_header: StringLike,
tok_type: Union[Type[str], Type[bytes]],
) -> List[Test]:
if tok_type is str:
header_prefix = "#"
elif tok_type is bytes:
header_prefix = b"#"
else:
assert False, "unreachable"
first_header = (
some(
lambda tok: tok.type == "HEADER"
and tok.value == header_prefix + new_test_header
)
>> (
lambda x: (
_trim_prefix(x.value, header_prefix),
x.start[0] if x.start is not None else None,
)
)
) + skip(tok("EOL"))
header = (
some(
lambda tok: tok.type == "HEADER"
and tok.value != header_prefix + new_test_header
)
>> (lambda x: _trim_prefix(x.value, header_prefix))
) + skip(tok("EOL"))
body = tok("BODY") + tok("EOL") >> (lambda x: x[0] + x[1])
empty = tok("EOL")
actual_body = many(body | (empty + skip(_notFollowedBy(first_header)))) >> (
lambda xs: tok_type().join(xs)[:-1]
)
first_segment = first_header + actual_body >> tuple
rest_segment = header + actual_body >> tuple
test = first_segment + many(rest_segment) >> _make_test
tests = (test + many(skip(empty) + test)) >> _many_merge
toplevel = tests + skip(finished)
return toplevel.parse(tokens)
def parse(s: StringLike, new_test_header: StringLike) -> List[Test]:
if type(s) != type(new_test_header):
raise TypeError("s and new_test_header must have same type")
if isinstance(s, str):
return _parser(list(_tokenizer_u(s)), new_test_header, str)
elif isinstance(s, bytes):
return _parser(list(_tokenizer_b(s)), new_test_header, bytes)
else:
raise TypeError("s must be unicode or bytes object")
|
