File: test_parser.py

package info (click to toggle)
python-openstep-plist 0.5.0-1
  • links: PTS, VCS
  • area: main
  • in suites: sid, trixie
  • size: 200 kB
  • sloc: python: 768; sh: 14; makefile: 4
file content (329 lines) | stat: -rw-r--r-- 10,576 bytes parent folder | download | duplicates (2)
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
# -*- coding: utf-8 -*-
from __future__ import absolute_import, unicode_literals
import sys
from io import StringIO, BytesIO
from collections import OrderedDict
from openstep_plist._test import (
    line_number_strings,
    is_valid_unquoted_string_char,
    advance_to_non_space,
    get_slashed_char,
    parse_unquoted_plist_string,
    parse_plist_string,
)
import openstep_plist
from openstep_plist.parser import string_to_number

import pytest


def test_line_number_strings():
    assert line_number_strings("", 0) == 1
    assert line_number_strings("a\na", 1) == 1
    assert line_number_strings("a\na", 2) == 2
    assert line_number_strings("a\naa\n", 4) == 2
    assert line_number_strings("a\naa\na", 5) == 3
    assert line_number_strings("a\raa\ra", 5) == 3
    assert line_number_strings("a\r\naa\ra", 6) == 3
    assert line_number_strings("a\n\naa\n\na", 7) == 5


def test_is_valid_unquoted_string_char():
    assert is_valid_unquoted_string_char(ord("a"))
    assert is_valid_unquoted_string_char(ord("b"))
    assert is_valid_unquoted_string_char(ord("z"))
    assert is_valid_unquoted_string_char(ord("A"))
    assert is_valid_unquoted_string_char(ord("B"))
    assert is_valid_unquoted_string_char(ord("Z"))
    assert is_valid_unquoted_string_char(ord("_"))
    assert is_valid_unquoted_string_char(ord("$"))
    assert is_valid_unquoted_string_char(ord("/"))
    assert is_valid_unquoted_string_char(ord(":"))
    assert is_valid_unquoted_string_char(ord("."))
    assert is_valid_unquoted_string_char(ord("-"))
    assert not is_valid_unquoted_string_char(ord('"'))
    assert not is_valid_unquoted_string_char(ord(","))
    assert not is_valid_unquoted_string_char(ord("{"))
    assert not is_valid_unquoted_string_char(ord(")"))
    assert not is_valid_unquoted_string_char(ord(";"))
    assert not is_valid_unquoted_string_char(0x00)  # NULL
    assert not is_valid_unquoted_string_char(0x0A)  # \n
    assert not is_valid_unquoted_string_char(0x0D)  # \r


@pytest.mark.parametrize(
    "string, offset, expected",
    [
        ("", 0, None),
        (" a", 0, "a"),
        (" a", 1, "a"),
        (" a", 2, None),
        ("\t\ta", 1, "a"),
        ("\t\ta", 2, "a"),
        ("\t\ta", 3, None),
        ("abc//this is an inline comment", 3, None),
        ("abc //also this\n", 3, None),
        ("abc //this as well\n\nz", 3, "z"),
        ("abc/this is not a comment", 3, "/"),
        ("abc/", 3, "/"),  # not a comment either
        ("abcd /* C-style comments! */z", 4, "z"),
    ],
)
def test_advance_to_non_space(string, offset, expected):
    assert advance_to_non_space(string, offset) == expected


@pytest.mark.parametrize(
    "string, expected",
    [
        ("000", "\x00"),
        ("001", "\x01"),
        ("002", "\x02"),
        ("003", "\x03"),
        ("004", "\x04"),
        ("005", "\x05"),
        ("006", "\x06"),
        ("007", "\x07"),
        ("012", "\n"),
        ("111", "I"),
        ("111", "I"),
        ("200", "\xa0"),
        ("201", "\xc0"),
        ("375", "\xff"),
        ("376", "\ufffd"),
        ("376", "\ufffd"),
        ("U0000", "\u0000"),
        ("U0001", "\u0001"),
        ("U0411", "\u0411"),
        ("U00FA", "\u00fa"),
        ("a", "\a"),
        ("b", "\b"),
        ("f", "\f"),
        ("n", "\n"),
        ("r", "\r"),
        ("t", "\t"),
        ("v", "\v"),
        ('"', '"'),
        ("\n", "\n"),
        ("\\", "\\"),
        ("z", "z"),
    ],
)
def test_get_slashed_char(string, expected):
    assert get_slashed_char(string) == expected


@pytest.mark.parametrize(
    "string, expected",
    [
        ("a", "a"),
        ("abc;", "abc"),  # trailing chars left in buffer
        ("1", "1"),
        ("123456789", "123456789"),
        ("1.23456789", "1.23456789"),
    ],
)
def test_parse_unquoted_plist_string(string, expected):
    assert parse_unquoted_plist_string(string) == expected


def test_parse_unquoted_plist_string_EOF():
    with pytest.raises(openstep_plist.ParseError, match="Unexpected EOF"):
        parse_unquoted_plist_string("") == expected


@pytest.mark.parametrize(
    "string, expected",
    [
        ("a", "a"),
        ('"a"', "a"),
        ("'a'", "a"),
        ('"a\\012b"', ("a\nb")),
        # surrogate pair gets decoded as a single scalar value
        ('"\\UD83D\\UDCA9"', "\U0001F4A9"),  # '💩'
        # surrogate that don't go in pairs are simply passed through
        ('"\\UD83D"', "\ud83d"),
        ('"\\UD83D\\012"', "\ud83d\n"),
        ('"\\UDCA9"', "\udca9"),
        ('"\\UDCA9\\012"', "\udca9\n"),
    ],
)
def test_parse_plist_string(string, expected):
    assert parse_plist_string(string) == expected


def test_parse_plist_string_EOF():
    with pytest.raises(openstep_plist.ParseError, match="Unexpected EOF"):
        parse_plist_string("")
    with pytest.raises(openstep_plist.ParseError, match="Unterminated quoted string"):
        parse_plist_string("'a")


def test_parse_plist_string_invalid_char():
    with pytest.raises(openstep_plist.ParseError, match="Invalid string character"):
        parse_plist_string("\\")
    assert parse_plist_string("\\", required=False) is None


def test_parse_plist_array():
    assert openstep_plist.loads("(1)") == ["1"]
    assert openstep_plist.loads("(1,)") == ["1"]
    assert openstep_plist.loads("(\t1  \r\n, 2.2, c,\n)") == ["1", "2.2", "c"]
    assert openstep_plist.loads("('1', '2')") == ["1", "2"]
    assert openstep_plist.loads("(\n1,\n\"'2'\"\n)") == ["1", "'2'"]


@pytest.mark.parametrize("string, lineno", [("(a ", 1), ("(a,\nb,\r\nc", 3)])
def test_parse_plist_array_missing_comma(string, lineno):
    msg = "Missing ',' for array at line %d" % lineno
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads(string)


@pytest.mark.parametrize("string, lineno", [("(a,", 1), ("(a,\nb, }", 2)])
def test_parse_plist_array_missing_paren(string, lineno):
    msg = r"Expected terminating '\)' for array at line %d" % lineno
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads(string)


def test_parse_plist_array_empty():
    assert openstep_plist.loads("()") == []


def test_parse_plist_dict_empty():
    assert openstep_plist.loads("") == {}
    assert openstep_plist.loads("{}") == {}


@pytest.mark.parametrize(
    "string, expected",
    [
        ("{a=1;}", {"a": "1"}),
        ('{"a"="1";}', {"a": "1"}),
        ("{'a'='1';}", {"a": "1"}),
        ("{\na = 1;\n}", {"a": "1"}),
        ("{\na\n=\n1;\n}", {"a": "1"}),
        ("{a=1;b;}", {"a": "1", "b": "b"}),
    ],
)
def test_parse_plist_dict(string, expected):
    assert openstep_plist.loads(string) == expected


def test_parse_plist_dict_invalid():
    msg = "Unexpected character after key at line 1: u?','"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("{a,}")

    msg = "Missing ';' on line 1"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("{b ")

    msg = "Missing ';' on line 2"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("{b = zzz;\nc = xxx}")

    msg = "Expected terminating '}' for dictionary at line 3"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("{b = zzz;\nc = xxx;\nd = jjj;")


@pytest.mark.parametrize(
    "string, expected",
    [
        ("<AA>", b"\xaa"),
        ("<B1B0AFBA>", b"\xb1\xb0\xaf\xba"),
        ("<AA BB>", b"\xaa\xbb"),
        ("<cdef>", b"\xcd\xef"),
        ("<4142\n4344>", b"ABCD"),
    ],
)
def test_parse_plist_data(string, expected):
    assert openstep_plist.loads(string) == expected


def test_parse_plist_data_invalid():
    with pytest.raises(openstep_plist.ParseError, match="Expected terminating '>'"):
        openstep_plist.loads("<FF")

    msg = "Malformed data byte group at line 1: invalid hex digit: u?'Z'"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("<Z")
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("<AZ")

    msg = "Malformed data byte group at line 1: uneven length"
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("<AAA")
    with pytest.raises(openstep_plist.ParseError, match=msg):
        openstep_plist.loads("<AAA>")


def test_parse_plist_object_invalid():
    with pytest.raises(openstep_plist.ParseError, match="Unexpected character"):
        openstep_plist.loads(";")
    with pytest.raises(
        openstep_plist.ParseError, match="Unexpected EOF while parsing plist"
    ):
        openstep_plist.loads("{a=")
    with pytest.raises(openstep_plist.ParseError, match="Junk after plist at line 3"):
        openstep_plist.loads("{a=1;\nb=2;\n}...")


def test_parse_string_resources():
    assert openstep_plist.loads("a=1;\n'b' = 2.4;\n'c' = \"hello world\";") == {
        "a": "1",
        "b": "2.4",
        "c": "hello world",
    }


def test_load():
    fp = StringIO("{a=1;}")
    assert openstep_plist.load(fp) == {"a": "1"}


def test_load_from_bytes():
    if sys.version_info.major < 3:
        assert openstep_plist.loads(b"{a=1;}") == {"a": "1"}
    else:
        with pytest.raises(TypeError, match="Could not convert to unicode"):
            openstep_plist.loads(b"{a=1;}")


@pytest.mark.parametrize(
    "string, expected",
    [
        ("{a = 2;}", {"a": 2}),
        ("{a = {b = -2;};}", {"a": {"b": -2}}),
        ("{a = (1.5, -23.9999);}", {"a": [1.5, -23.9999]}),
        ("{a = x123; b = -c; minus = -;}", {"a": "x123", "b": "-c", "minus": "-"}),
    ],
)
def test_loads_use_numbers(string, expected):
    assert openstep_plist.loads(string, use_numbers=True) == expected


def test_loads_dict_type():
    assert openstep_plist.loads(
        "{z = (a, b); y = (c, d); a = 'hello world';}", dict_type=OrderedDict
    ) == (OrderedDict([("z", ["a", "b"]), ("y", ["c", "d"]), ("a", "hello world")]))


@pytest.mark.parametrize(
    "string, expected",
    [("2", 2), ("-2", -2), ("1.5", 1.5), ("-1.5", -1.5), ("23.99999", 23.99999)],
)
def test_string_to_number(string, expected):
    assert string_to_number(string) == expected


@pytest.mark.parametrize("string", ["", "10000s", " 1.5", "-", ".5", "1e-4", "1.2.3"])
@pytest.mark.parametrize("required", [True, False])
def test_string_to_number_invalid(string, required):
    if required:
        with pytest.raises(ValueError):
            string_to_number(string)
    else:
        string_to_number(string, required=False) == string