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
|
# -*- coding: utf-8 -*-
# pylint: disable=R1708
from __future__ import unicode_literals
import unittest
from cmakelang import configuration
from cmakelang import lex
from cmakelang import parse
from cmakelang.parse.printer import tree_string, test_string
from cmakelang.parse.common import NodeType
def overzip(iterable_a, iterable_b):
"""
Like itertools.izip but instead if the two lists have different sizes then
the resulting generator will yield a number of pairs equal to the larger of
the two inputs (rathe than the smaller). The empty list will be padded with
None elements.
"""
iter_a = iter(iterable_a)
iter_b = iter(iterable_b)
item_a = next(iter_a, None)
item_b = next(iter_b, None)
while isinstance(item_a, lex.Token):
item_a = next(iter_a, None)
while item_a is not None and item_b is not None:
yield(item_a, item_b)
item_a = next(iter_a, None)
while isinstance(item_a, lex.Token):
item_a = next(iter_a, None)
item_b = next(iter_b, None)
while item_a is not None:
yield(item_a, None)
item_a = next(iter_a, None)
while isinstance(item_a, lex.Token):
item_a = next(iter_a, None)
while item_b is not None:
yield(None, item_b)
item_b = next(iter_b, None)
def assert_tree_type(test, nodes, tups, tree=None, history=None):
"""
Check the output tree structure against that of expect_tree: a nested tuple
tree.
"""
if tree is None:
tree = nodes
if history is None:
history = []
for node, tup in overzip(nodes, tups):
if isinstance(node, lex.Token):
continue
message = ("For node {} at\n {} within \n{}. "
"If this is infact correct, copy-paste this:\n\n{}"
.format(node, tree_string([node]),
tree_string(tree, history),
test_string(tree)))
test.assertIsNotNone(node, msg="Missing node " + message)
test.assertIsNotNone(tup, msg="Extra node " + message)
expect_type, expect_children = tup
test.assertEqual(node.node_type, expect_type,
msg="Expected type={} ".format(expect_type) + message)
assert_tree_type(test, node.children, expect_children, tree,
history + [node])
class TestCanonicalParse(unittest.TestCase):
"""
Given a bunch of example inputs, ensure that they parse into the expected
tree structure.
"""
def __init__(self, *args, **kwargs):
super(TestCanonicalParse, self).__init__(*args, **kwargs)
self.config = configuration.Configuration()
parse_db = parse.funs.get_parse_db()
self.parse_ctx = parse.ParseContext(parse_db)
def setUp(self):
self.config.parse.fn_spec.add(
'foo',
flags=['BAR', 'BAZ'],
kwargs={
"HEADERS": '*',
"SOURCES": '*',
"DEPENDS": '*'
})
self.parse_ctx.parse_db.update(
parse.funs.get_funtree(self.config.parse.fn_spec))
def do_type_test(self, input_str, expect_tree):
"""
Run the parser to get the fst, then compare the result to the types in the
``expect_tree`` tuple tree.
"""
tokens = lex.tokenize(input_str)
fst_root = parse.parse(tokens, self.parse_ctx)
assert_tree_type(self, [fst_root], expect_tree)
def test_collapse_additional_newlines(self):
self.do_type_test("""\
# The following multiple newlines should be collapsed into a single newline
cmake_minimum_required(VERSION 2.8.11)
project(cmakelang_test)
""", [
(NodeType.BODY, [
(NodeType.WHITESPACE, []),
(NodeType.COMMENT, []),
(NodeType.WHITESPACE, []),
(NodeType.STATEMENT, [
(NodeType.FUNNAME, []),
(NodeType.LPAREN, []),
(NodeType.ARGGROUP, [
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
]),
]),
(NodeType.RPAREN, []),
]),
(NodeType.WHITESPACE, []),
(NodeType.STATEMENT, [
(NodeType.FUNNAME, []),
(NodeType.LPAREN, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
(NodeType.RPAREN, []),
]),
(NodeType.WHITESPACE, []),
]),
])
def test_multiline_comment(self):
self.do_type_test("""\
# This multiline-comment should be reflowed
# into a single comment
# on one line
""", [
(NodeType.BODY, [
(NodeType.WHITESPACE, []),
(NodeType.COMMENT, []),
(NodeType.WHITESPACE, []),
])
])
def test_nested_kwargs(self):
self.do_type_test("""\
add_custom_target(name ALL VERBATIM
COMMAND echo hello world
COMMENT "this is some text")
""", [
(NodeType.BODY, [
(NodeType.WHITESPACE, []),
(NodeType.STATEMENT, [
(NodeType.FUNNAME, []),
(NodeType.LPAREN, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.FLAG, []),
]),
(NodeType.PARGGROUP, [
(NodeType.FLAG, []),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.RPAREN, []),
]),
(NodeType.WHITESPACE, []),
]),
])
def test_custom_command(self):
self.do_type_test("""\
# This very long command should be broken up along keyword arguments
foo(nonkwarg_a nonkwarg_b HEADERS a.h b.h c.h d.h e.h f.h SOURCES a.cc b.cc d.cc DEPENDS foo bar baz)
""", [
(NodeType.BODY, [
(NodeType.WHITESPACE, []),
(NodeType.COMMENT, []),
(NodeType.WHITESPACE, []),
(NodeType.STATEMENT, [
(NodeType.FUNNAME, []),
(NodeType.LPAREN, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.PARGGROUP, [
(NodeType.FLAG, []),
(NodeType.FLAG, []),
]),
]),
(NodeType.RPAREN, []),
]),
(NodeType.WHITESPACE, []),
]),
])
def test_shellcommand_parse(self):
self.do_type_test("""\
add_test(NAME foo-test
COMMAND cmdname -Bm -h --hello foo bar --world baz buck
WORKING_DIRECTORY ${CMAKE_SOURCE_DIR})
""", [
(NodeType.BODY, [
(NodeType.WHITESPACE, []),
(NodeType.STATEMENT, [
(NodeType.FUNNAME, []),
(NodeType.LPAREN, []),
(NodeType.ARGGROUP, [
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
(NodeType.ARGUMENT, []),
]),
]),
]),
(NodeType.KWARGGROUP, [
(NodeType.KEYWORD, []),
(NodeType.ARGGROUP, [
(NodeType.PARGGROUP, [
(NodeType.ARGUMENT, []),
]),
]),
]),
]),
(NodeType.RPAREN, []),
]),
(NodeType.WHITESPACE, []),
]),
])
if __name__ == '__main__':
unittest.main()
|
