summaryrefslogtreecommitdiffstats
path: root/Lib/lib2to3/tests/test_parser.py
blob: cec2f98e9665878fdfce5e1138ee460af10c204d (plain)
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
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
"""Test suite for 2to3's parser and grammar files.

This is the place to add tests for changes to 2to3's grammar, such as those
merging the grammars for Python 2 and 3. In addition to specific tests for
parts of the grammar we've changed, we also make sure we can parse the
test_grammar.py files from both Python 2 and Python 3.
"""

# Testing imports
from . import support
from .support import driver, driver_no_print_statement

# Python imports
import difflib
import importlib
import operator
import os
import pickle
import shutil
import subprocess
import sys
import tempfile
import unittest

# Local imports
from lib2to3.pgen2 import driver as pgen2_driver
from lib2to3.pgen2 import tokenize
from ..pgen2.parse import ParseError
from lib2to3.pygram import python_symbols as syms


class TestDriver(support.TestCase):

    def test_formfeed(self):
        s = """print 1\n\x0Cprint 2\n"""
        t = driver.parse_string(s)
        self.assertEqual(t.children[0].children[0].type, syms.print_stmt)
        self.assertEqual(t.children[1].children[0].type, syms.print_stmt)


class TestPgen2Caching(support.TestCase):
    def test_load_grammar_from_txt_file(self):
        pgen2_driver.load_grammar(support.grammar_path, save=False, force=True)

    def test_load_grammar_from_pickle(self):
        # Make a copy of the grammar file in a temp directory we are
        # guaranteed to be able to write to.
        tmpdir = tempfile.mkdtemp()
        try:
            grammar_copy = os.path.join(
                    tmpdir, os.path.basename(support.grammar_path))
            shutil.copy(support.grammar_path, grammar_copy)
            pickle_name = pgen2_driver._generate_pickle_name(grammar_copy)

            pgen2_driver.load_grammar(grammar_copy, save=True, force=True)
            self.assertTrue(os.path.exists(pickle_name))

            os.unlink(grammar_copy)  # Only the pickle remains...
            pgen2_driver.load_grammar(grammar_copy, save=False, force=False)
        finally:
            shutil.rmtree(tmpdir)

    @unittest.skipIf(sys.executable is None, 'sys.executable required')
    def test_load_grammar_from_subprocess(self):
        tmpdir = tempfile.mkdtemp()
        tmpsubdir = os.path.join(tmpdir, 'subdir')
        try:
            os.mkdir(tmpsubdir)
            grammar_base = os.path.basename(support.grammar_path)
            grammar_copy = os.path.join(tmpdir, grammar_base)
            grammar_sub_copy = os.path.join(tmpsubdir, grammar_base)
            shutil.copy(support.grammar_path, grammar_copy)
            shutil.copy(support.grammar_path, grammar_sub_copy)
            pickle_name = pgen2_driver._generate_pickle_name(grammar_copy)
            pickle_sub_name = pgen2_driver._generate_pickle_name(
                     grammar_sub_copy)
            self.assertNotEqual(pickle_name, pickle_sub_name)

            # Generate a pickle file from this process.
            pgen2_driver.load_grammar(grammar_copy, save=True, force=True)
            self.assertTrue(os.path.exists(pickle_name))

            # Generate a new pickle file in a subprocess with a most likely
            # different hash randomization seed.
            sub_env = dict(os.environ)
            sub_env['PYTHONHASHSEED'] = 'random'
            subprocess.check_call(
                    [sys.executable, '-c', """
from lib2to3.pgen2 import driver as pgen2_driver
pgen2_driver.load_grammar(%r, save=True, force=True)
                    """ % (grammar_sub_copy,)],
                    env=sub_env)
            self.assertTrue(os.path.exists(pickle_sub_name))

            with open(pickle_name, 'rb') as pickle_f_1, \
                    open(pickle_sub_name, 'rb') as pickle_f_2:
                self.assertEqual(
                    pickle_f_1.read(), pickle_f_2.read(),
                    msg='Grammar caches generated using different hash seeds'
                    ' were not identical.')
        finally:
            shutil.rmtree(tmpdir)

    def test_load_packaged_grammar(self):
        modname = __name__ + '.load_test'
        class MyLoader:
            def get_data(self, where):
                return pickle.dumps({'elephant': 19})
        class MyModule:
            __file__ = 'parsertestmodule'
            __spec__ = importlib.util.spec_from_loader(modname, MyLoader())
        sys.modules[modname] = MyModule()
        self.addCleanup(operator.delitem, sys.modules, modname)
        g = pgen2_driver.load_packaged_grammar(modname, 'Grammar.txt')
        self.assertEqual(g.elephant, 19)


class GrammarTest(support.TestCase):
    def validate(self, code):
        support.parse_string(code)

    def invalid_syntax(self, code):
        try:
            self.validate(code)
        except ParseError:
            pass
        else:
            raise AssertionError("Syntax shouldn't have been valid")


class TestMatrixMultiplication(GrammarTest):
    def test_matrix_multiplication_operator(self):
        self.validate("a @ b")
        self.validate("a @= b")


class TestYieldFrom(GrammarTest):
    def test_yield_from(self):
        self.validate("yield from x")
        self.validate("(yield from x) + y")
        self.invalid_syntax("yield from")


class TestAsyncAwait(GrammarTest):
    def test_await_expr(self):
        self.validate("""async def foo():
                             await x
                      """)

        self.validate("""async def foo():
                             [i async for i in b]
                      """)

        self.validate("""async def foo():
                             {i for i in b
                                async for i in a if await i
                                  for b in i}
                      """)

        self.validate("""async def foo():
                             [await i for i in b if await c]
                      """)

        self.validate("""async def foo():
                             [ i for i in b if c]
                      """)

        self.validate("""async def foo():

            def foo(): pass

            def foo(): pass

            await x
        """)

        self.validate("""async def foo(): return await a""")

        self.validate("""def foo():
            def foo(): pass
            async def foo(): await x
        """)

        self.validate("await x")
        self.validate("""def foo():
                        await x""")

        self.validate("""def foo():
            def foo(): pass
            async def foo(): pass
            await x
        """)

    def test_async_var(self):
        self.invalid_syntax("""async = 1""")
        self.invalid_syntax("""await = 1""")
        self.invalid_syntax("""def async(): pass""")

    def test_async_with(self):
        self.validate("""async def foo():
                             async for a in b: pass""")

        self.validate("""def foo():
                             async for a in b: pass""")

    def test_async_for(self):
        self.validate("""async def foo():
                             async with a: pass""")

        self.validate("""def foo():
                             async with a: pass""")


class TestRaiseChanges(GrammarTest):
    def test_2x_style_1(self):
        self.validate("raise")

    def test_2x_style_2(self):
        self.validate("raise E, V")

    def test_2x_style_3(self):
        self.validate("raise E, V, T")

    def test_2x_style_invalid_1(self):
        self.invalid_syntax("raise E, V, T, Z")

    def test_3x_style(self):
        self.validate("raise E1 from E2")

    def test_3x_style_invalid_1(self):
        self.invalid_syntax("raise E, V from E1")

    def test_3x_style_invalid_2(self):
        self.invalid_syntax("raise E from E1, E2")

    def test_3x_style_invalid_3(self):
        self.invalid_syntax("raise from E1, E2")

    def test_3x_style_invalid_4(self):
        self.invalid_syntax("raise E from")


# Modelled after Lib/test/test_grammar.py:TokenTests.test_funcdef issue2292
# and Lib/test/text_parser.py test_list_displays, test_set_displays,
# test_dict_displays, test_argument_unpacking, ... changes.
class TestUnpackingGeneralizations(GrammarTest):
    def test_mid_positional_star(self):
        self.validate("""func(1, *(2, 3), 4)""")

    def test_double_star_dict_literal(self):
        self.validate("""func(**{'eggs':'scrambled', 'spam':'fried'})""")

    def test_double_star_dict_literal_after_keywords(self):
        self.validate("""func(spam='fried', **{'eggs':'scrambled'})""")

    def test_list_display(self):
        self.validate("""[*{2}, 3, *[4]]""")

    def test_set_display(self):
        self.validate("""{*{2}, 3, *[4]}""")

    def test_dict_display_1(self):
        self.validate("""{**{}}""")

    def test_dict_display_2(self):
        self.validate("""{**{}, 3:4, **{5:6, 7:8}}""")

    def test_argument_unpacking_1(self):
        self.validate("""f(a, *b, *c, d)""")

    def test_argument_unpacking_2(self):
        self.validate("""f(**a, **b)""")

    def test_argument_unpacking_3(self):
        self.validate("""f(2, *a, *b, **b, **c, **d)""")


# Adapted from Python 3's Lib/test/test_grammar.py:GrammarTests.testFuncdef
class TestFunctionAnnotations(GrammarTest):
    def test_1(self):
        self.validate("""def f(x) -> list: pass""")

    def test_2(self):
        self.validate("""def f(x:int): pass""")

    def test_3(self):
        self.validate("""def f(*x:str): pass""")

    def test_4(self):
        self.validate("""def f(**x:float): pass""")

    def test_5(self):
        self.validate("""def f(x, y:1+2): pass""")

    def test_6(self):
        self.validate("""def f(a, (b:1, c:2, d)): pass""")

    def test_7(self):
        self.validate("""def f(a, (b:1, c:2, d), e:3=4, f=5, *g:6): pass""")

    def test_8(self):
        s = """def f(a, (b:1, c:2, d), e:3=4, f=5,
                        *g:6, h:7, i=8, j:9=10, **k:11) -> 12: pass"""
        self.validate(s)

    def test_9(self):
        s = """def f(
          a: str,
          b: int,
          *,
          c: bool = False,
          **kwargs,
        ) -> None:
            call(c=c, **kwargs,)"""
        self.validate(s)

    def test_10(self):
        s = """def f(
          a: str,
        ) -> None:
            call(a,)"""
        self.validate(s)

    def test_11(self):
        s = """def f(
          a: str = '',
        ) -> None:
            call(a=a,)"""
        self.validate(s)

    def test_12(self):
        s = """def f(
          *args: str,
        ) -> None:
            call(*args,)"""
        self.validate(s)


# Adapted from Python 3's Lib/test/test_grammar.py:GrammarTests.test_var_annot
class TestVarAnnotations(GrammarTest):
    def test_1(self):
        self.validate("var1: int = 5")

    def test_2(self):
        self.validate("var2: [int, str]")

    def test_3(self):
        self.validate("def f():\n"
                      "    st: str = 'Hello'\n"
                      "    a.b: int = (1, 2)\n"
                      "    return st\n")

    def test_4(self):
        self.validate("def fbad():\n"
                      "    x: int\n"
                      "    print(x)\n")

    def test_5(self):
        self.validate("class C:\n"
                      "    x: int\n"
                      "    s: str = 'attr'\n"
                      "    z = 2\n"
                      "    def __init__(self, x):\n"
                      "        self.x: int = x\n")

    def test_6(self):
        self.validate("lst: List[int] = []")


class TestExcept(GrammarTest):
    def test_new(self):
        s = """
            try:
                x
            except E as N:
                y"""
        self.validate(s)

    def test_old(self):
        s = """
            try:
                x
            except E, N:
                y"""
        self.validate(s)


class TestStringLiterals(GrammarTest):
    prefixes = ("'", '"',
        "r'", 'r"', "R'", 'R"',
        "u'", 'u"', "U'", 'U"',
        "b'", 'b"', "B'", 'B"',
        "f'", 'f"', "F'", 'F"',
        "ur'", 'ur"', "Ur'", 'Ur"',
        "uR'", 'uR"', "UR'", 'UR"',
        "br'", 'br"', "Br'", 'Br"',
        "bR'", 'bR"', "BR'", 'BR"',
        "rb'", 'rb"', "Rb'", 'Rb"',
        "rB'", 'rB"', "RB'", 'RB"',)

    def test_lit(self):
        for pre in self.prefixes:
            single = "{p}spamspamspam{s}".format(p=pre, s=pre[-1])
            self.validate(single)
            triple = "{p}{s}{s}eggs{s}{s}{s}".format(p=pre, s=pre[-1])
            self.validate(triple)


# Adapted from Python 3's Lib/test/test_grammar.py:GrammarTests.testAtoms
class TestSetLiteral(GrammarTest):
    def test_1(self):
        self.validate("""x = {'one'}""")

    def test_2(self):
        self.validate("""x = {'one', 1,}""")

    def test_3(self):
        self.validate("""x = {'one', 'two', 'three'}""")

    def test_4(self):
        self.validate("""x = {2, 3, 4,}""")


class TestNumericLiterals(GrammarTest):
    def test_new_octal_notation(self):
        self.validate("""0o7777777777777""")
        self.invalid_syntax("""0o7324528887""")

    def test_new_binary_notation(self):
        self.validate("""0b101010""")
        self.invalid_syntax("""0b0101021""")


class TestClassDef(GrammarTest):
    def test_new_syntax(self):
        self.validate("class B(t=7): pass")
        self.validate("class B(t, *args): pass")
        self.validate("class B(t, **kwargs): pass")
        self.validate("class B(t, *args, **kwargs): pass")
        self.validate("class B(t, y=9, *args, **kwargs,): pass")


class TestParserIdempotency(support.TestCase):

    """A cut-down version of pytree_idempotency.py."""

    def test_all_project_files(self):
        for filepath in support.all_project_files():
            with open(filepath, "rb") as fp:
                encoding = tokenize.detect_encoding(fp.readline)[0]
            self.assertIsNotNone(encoding,
                                 "can't detect encoding for %s" % filepath)
            with open(filepath, "r", encoding=encoding) as fp:
                source = fp.read()
            try:
                tree = driver.parse_string(source)
            except ParseError:
                try:
                    tree = driver_no_print_statement.parse_string(source)
                except ParseError as err:
                    self.fail('ParseError on file %s (%s)' % (filepath, err))
            new = str(tree)
            if new != source:
                print(diff_texts(source, new, filepath))
                self.fail("Idempotency failed: %s" % filepath)

    def test_extended_unpacking(self):
        driver.parse_string("a, *b, c = x\n")
        driver.parse_string("[*a, b] = x\n")
        driver.parse_string("(z, *y, w) = m\n")
        driver.parse_string("for *z, m in d: pass\n")


class TestLiterals(GrammarTest):

    def validate(self, s):
        driver.parse_string(support.dedent(s) + "\n\n")

    def test_multiline_bytes_literals(self):
        s = """
            md5test(b"\xaa" * 80,
                    (b"Test Using Larger Than Block-Size Key "
                     b"and Larger Than One Block-Size Data"),
                    "6f630fad67cda0ee1fb1f562db3aa53e")
            """
        self.validate(s)

    def test_multiline_bytes_tripquote_literals(self):
        s = '''
            b"""
            <?xml version="1.0" encoding="UTF-8"?>
            <!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN">
            """
            '''
        self.validate(s)

    def test_multiline_str_literals(self):
        s = """
            md5test("\xaa" * 80,
                    ("Test Using Larger Than Block-Size Key "
                     "and Larger Than One Block-Size Data"),
                    "6f630fad67cda0ee1fb1f562db3aa53e")
            """
        self.validate(s)


class TestGeneratorExpressions(GrammarTest):

    def test_trailing_comma_after_generator_expression_argument_works(self):
        # BPO issue 27494
        self.validate("set(x for x in [],)")


def diff_texts(a, b, filename):
    a = a.splitlines()
    b = b.splitlines()
    return difflib.unified_diff(a, b, filename, filename,
                                "(original)", "(reserialized)",
                                lineterm="")


if __name__ == '__main__':
    unittest.main()