test_parse.py 21 KB
Newer Older
1
2
#!/usr/bin/python3

3
"""test_parse.py - tests of the parsers-module of DHParser
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

Author: Eckhart Arnold <arnold@badw.de>

Copyright 2017 Bavarian Academy of Sciences and Humanities

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""

import sys
23
from functools import partial
24

Eckhart Arnold's avatar
Eckhart Arnold committed
25
sys.path.extend(['../', './'])
26

27
28
from DHParser.toolkit import compile_python_object
from DHParser.log import logging, is_logging, log_ST
29
from DHParser.error import Error
30
31
32
from DHParser.parse import Retrieve, Grammar, Forward, Token, ZeroOrMore, RE, \
    RegExp, Lookbehind, NegativeLookahead, OneOrMore, Series, Alternative, AllOf, SomeOf, UnknownParserError
from DHParser import compile_source
Eckhart Arnold's avatar
Eckhart Arnold committed
33
from DHParser.ebnf import get_ebnf_grammar, get_ebnf_transformer, get_ebnf_compiler
34
from DHParser.dsl import grammar_provider, DHPARSER_IMPORTS
35
36


37
class TestInfiLoopsAndRecursion:
38
    def test_direct_left_recursion1(self):
39
40
41
42
43
        minilang =""" 
            expr = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
44
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
45
        parser = grammar_provider(minilang)()
46
        assert parser
Eckhart Arnold's avatar
Eckhart Arnold committed
47
        syntax_tree = parser(snippet)
48
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())
49
        assert snippet == str(syntax_tree)
Eckhart Arnold's avatar
Eckhart Arnold committed
50
        if is_logging():
51
            log_ST(syntax_tree, "test_LeftRecursion_direct.cst")
52
            parser.log_parsing_history__("test_LeftRecursion_direct")
53

54
    def test_direct_left_recursion2(self):
55
56
57
58
59
60
        minilang = """
            expr = ex
            ex   = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
61
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
62
        parser = grammar_provider(minilang)()
63
64
        assert parser
        syntax_tree = parser(snippet)
65
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
66
        assert snippet == str(syntax_tree)
67

68
    def test_indirect_left_recursion1(self):
69
70
        minilang = """
            Expr    = //~ (Product | Sum | Value)
71
72
            Product = Expr { ('*' | '/') Expr }+
            Sum     = Expr { ('+' | '-') Expr }+
73
74
            Value   = /[0-9.]+/~ | '(' Expr ')'
            """
75
        parser = grammar_provider(minilang)()
76
        assert parser
77
        snippet = "8 * 4"
78
        syntax_tree = parser(snippet)
79
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
80
81
        snippet = "7 + 8 * 4"
        syntax_tree = parser(snippet)
82
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
83
84
        snippet = "9 + 8 * (4 + 3)"
        syntax_tree = parser(snippet)
85
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
86
        assert snippet == str(syntax_tree)
87
        if is_logging():
88
            log_ST(syntax_tree, "test_LeftRecursion_indirect.cst")
89
            parser.log_parsing_history__("test_LeftRecursion_indirect")
90

91
92
93
    def test_inifinite_loops(self):
        minilang = """not_forever = { // } \n"""
        snippet = " "
94
        parser = grammar_provider(minilang)()
Eckhart Arnold's avatar
Eckhart Arnold committed
95
        syntax_tree = parser(snippet)
96
97
        assert syntax_tree.error_flag

98

Eckhart Arnold's avatar
Eckhart Arnold committed
99
class TestFlowControl:
100
101
102
103
104
105
106
107
    def setup(self):
        self.t1 = """
        All work and no play 
        makes Jack a dull boy
        END
        """
        self.t2 = "All word and not play makes Jack a dull boy END\n"

Eckhart Arnold's avatar
Eckhart Arnold committed
108
109
110
    def test_lookbehind(self):
        ws = RegExp('\s*')
        end = RegExp("END")
111
        doc_end = Lookbehind(RegExp('\\s*?\\n')) + end
Eckhart Arnold's avatar
Eckhart Arnold committed
112
113
114
115
116
        word = RegExp('\w+')
        sequence = OneOrMore(NegativeLookahead(end) + word + ws)
        document = ws + sequence + doc_end + ws

        parser = Grammar(document)
117
118
119
120
121
122
123
124
125
126
        cst = parser(self.t1)
        assert not cst.error_flag, cst.as_sxpr()
        cst = parser(self.t2)
        assert cst.error_flag, cst.as_sxpr()

    def test_lookbehind_indirect(self):
        class LookbehindTestGrammar(Grammar):
            parser_initialization__ = "upon instantiation"
            ws = RegExp('\\s*')
            end = RegExp('END')
127
            SUCC_LB = RegExp('\\s*?\\n')
128
129
130
131
132
133
134
135
            doc_end = Series(Lookbehind(SUCC_LB), end)
            word = RegExp('\w+')
            sequence = OneOrMore(Series(NegativeLookahead(end), word, ws))
            document = Series(ws, sequence, doc_end, ws)
            root__ = document

        parser = LookbehindTestGrammar()
        cst = parser(self.t1)
Eckhart Arnold's avatar
Eckhart Arnold committed
136
        assert not cst.error_flag, cst.as_sxpr()
137
        cst = parser(self.t2)
Eckhart Arnold's avatar
Eckhart Arnold committed
138
139
140
        assert cst.error_flag, cst.as_sxpr()


141
142
143
144
145
146
147
class TestRegex:
    def test_multilineRegex(self):
        mlregex = r"""
        regex =  /\w+    # one or more alphabetical characters including the underscore
                  [+]    # followed by a plus sign
                  \w*    # possibly followed by more alpha chracters/
        """
Eckhart Arnold's avatar
Eckhart Arnold committed
148
149
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
150
        assert result
151
        assert not messages, str(messages)
152
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
eckhart's avatar
eckhart committed
153
154
        node = parser('abc+def', parser.regex)
        assert not node.error_flag
155
156
157
        assert node.parser.name == "regex"
        assert str(node) == 'abc+def'

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
    def text_ignore_case(self):
        mlregex = r"""
        @ ignorecase = True
        regex = /alpha/
        """
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
        assert result
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
        node, rest = parser.regex('Alpha')
        assert node
        assert not node.error_flag
        assert rest == ''
        assert node.parser.name == "regex"
        assert str(node) == 'Alpha'

        mlregex = r"""
        @ ignorecase = False
        regex = /alpha/
        """
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
        assert result
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
        node, rest = parser.regex('Alpha')
        assert node.error_flag


188
189
190
191
192
193
194
195
196
197
198
199
    def test_token(self):
        tokenlang = r"""
            @whitespace = linefeed
            lang        = "" begin_token {/\w+/ ""} end_token
            begin_token = "\begin{document}"
            end_token   = "\end{document}"
            """
        testdoc = r"""
            \begin{document}
            test
            \end{document}
            """
Eckhart Arnold's avatar
Eckhart Arnold committed
200
201
        result, messages, syntax_tree = compile_source(tokenlang, None, get_ebnf_grammar(),
                                    get_ebnf_transformer(), get_ebnf_compiler("TokenTest"))
202
203
204
        assert result
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
Eckhart Arnold's avatar
Eckhart Arnold committed
205
        result = parser(testdoc)
206
        # parser.log_parsing_history("test.log")
207
208
        assert not result.error_flag

209

210
class TestGrammar:
211
    def setup(self):
212
213
214
215
216
217
        grammar = r"""@whitespace = horizontal
        haupt        = textzeile LEERZEILE
        textzeile    = { WORT }+
        WORT         = /[^ \t]+/~
        LEERZEILE    = /\n[ \t]*(?=\n)/~
        """
218
219
220
        self.pyparser, messages, syntax_tree = compile_source(grammar, None, get_ebnf_grammar(),
                                                              get_ebnf_transformer(), get_ebnf_compiler("PosTest"))
        assert self.pyparser
221
        assert not messages
222
223
224
225

    def test_pos_values_initialized(self):
        # checks whether pos values in the parsing result and in the
        # history record have been initialized
226
        with logging("LOGS"):
227
228
229
            grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
            grammar("no_file_name*")
        for record in grammar.history__:
230
231
            assert not record.node or record.node.pos >= 0

232
    def test_select_parsing(self):
233
234
235
236
237
        grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
        grammar("wort", "WORT")
        grammar("eine Zeile", "textzeile")
        grammar("kein Haupt", "haupt")
        grammar("so ist es richtig", "haupt")
238

di68kap's avatar
di68kap committed
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
    def test_grammar_subclassing(self):
        class Arithmetic(Grammar):
            '''
            expression =  term  { ("+" | "-") term }
            term       =  factor  { ("*" | "/") factor }
            factor     =  INTEGER | "("  expression  ")"
            INTEGER    =  /\d+/~
            '''
            expression = Forward()
            INTEGER = RE('\\d+')
            factor = INTEGER | Token("(") + expression + Token(")")
            term = factor + ZeroOrMore((Token("*") | Token("/")) + factor)
            expression.set(term + ZeroOrMore((Token("+") | Token("-")) + term))
            root__ = expression

        grammar = Arithmetic()
        CST = grammar('3+4')
        assert not CST.error_flag, CST.as_sxpr()

258

259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
class TestSeries:
    def test_non_mandatory(self):
        lang = """
        document = series | /.*/
        series = "A" "B" "C" "D"
        """
        parser = grammar_provider(lang)()
        st = parser("ABCD");
        assert not st.error_flag
        st = parser("A_CD");
        assert not st.error_flag
        st = parser("AB_D");
        assert not st.error_flag

    def test_mandatory(self):
        """Test for the §-operator. The Series-parser should raise an
        error for any non-match that occurs after the mandatory-operator.
        """
        lang = """
        document = series | /.*/
        series = "A" "B" §"C" "D"
        """
        parser = grammar_provider(lang)()
282
283
284
        st = parser("ABCD");  assert not st.error_flag
        st = parser("A_CD");  assert not st.error_flag
        st = parser("AB_D");  assert st.error_flag
285
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
286
        # transitivity of mandatory-operator
287
        st = parser("ABC_");  assert st.error_flag
288
289
290
291
292
293
294
295
296
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

    def test_series_composition(self):
        TA, TB, TC, TD, TE = (Token(b) for b in "ABCDE")
        s1 = Series(TA, TB, TC, mandatory=2)
        s2 = Series(TD, TE)

        combined = Alternative(s1 + s2, RegExp('.*'))
        parser = Grammar(combined)
297
298
299
        st = parser("ABCDE");  assert not st.error_flag
        st = parser("A_CDE");  assert not st.error_flag
        st = parser("AB_DE");  assert st.error_flag
300
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
301
        st = parser("ABC_E");  assert st.error_flag
302
303
304
305
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

        combined = Alternative(s2 + s1, RegExp('.*'))
        parser = Grammar(combined)
306
307
308
309
310
311
        st = parser("DEABC");  assert not st.error_flag
        st = parser("_EABC");  assert not st.error_flag
        st = parser("D_ABC");  assert not st.error_flag
        st = parser("DE_BC");  assert not st.error_flag
        st = parser("DEA_C");  assert not st.error_flag
        st = parser("DEAB_");  assert st.error_flag
312
313
314
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION


315
316
317
318
class TestAllOfSomeOf:
    def test_allOf_order(self):
        """Test that parsers of an AllOf-List can match in arbitrary order."""
        prefixes = AllOf(Token("A"), Token("B"))
319
320
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B A').content == 'B A'
321
322
        # aternative Form
        prefixes = AllOf(Series(Token("B"), Token("A")))
323
        assert Grammar(prefixes)('A B').content == 'A B'
324
325
326
327
328
329
330
331
332
333
334

    def test_allOf_completeness(self):
        """Test that an error is raised if not  all parsers of an AllOf-List
        match."""
        prefixes = AllOf(Token("A"), Token("B"))
        assert Grammar(prefixes)('B').error_flag

    def test_allOf_redundance(self):
        """Test that one and the same parser may be listed several times
        and must be matched several times accordingly."""
        prefixes = AllOf(Token("A"), Token("B"), Token("A"))
335
336
337
        assert Grammar(prefixes)('A A B').content == 'A A B'
        assert Grammar(prefixes)('A B A').content == 'A B A'
        assert Grammar(prefixes)('B A A').content == 'B A A'
338
339
340
341
342
        assert Grammar(prefixes)('A B B').error_flag

    def test_someOf_order(self):
        """Test that parsers of an AllOf-List can match in arbitrary order."""
        prefixes = SomeOf(Token("A"), Token("B"))
343
344
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B A').content == 'B A'
345
346
        # aternative Form
        prefixes = SomeOf(Alternative(Token("B"), Token("A")))
347
348
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B').content == 'B'
349
350
351
352
353

    def test_someOf_redundance(self):
        """Test that one and the same parser may be listed several times
        and must be matched several times accordingly."""
        prefixes = SomeOf(Token("A"), Token("B"), Token("A"))
354
355
356
        assert Grammar(prefixes)('A A B').content == 'A A B'
        assert Grammar(prefixes)('A B A').content == 'A B A'
        assert Grammar(prefixes)('B A A').content == 'B A A'
357
358
359
        assert Grammar(prefixes)('A B B').error_flag


360
361
362
363
class TestPopRetrieve:
    mini_language = """
        document       = { text | codeblock }
        codeblock      = delimiter { text | (!:delimiter delimiter_sign) } ::delimiter
364
        delimiter      = delimiter_sign  # never use delimiter between capture and pop except for retrival!
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
        delimiter_sign = /`+/
        text           = /[^`]+/ 
        """
    mini_lang2 = """
        @braces_filter=counterpart
        document       = { text | codeblock }
        codeblock      = braces { text | opening_braces | (!:braces closing_braces) } ::braces
        braces         = opening_braces
        opening_braces = /\{+/
        closing_braces = /\}+/
        text           = /[^{}]+/
        """
    mini_lang3 = """
        document       = { text | env }
        env            = (specialtag | opentag) text [closespecial | closetag]
        opentag        = "<" name ">"
        specialtag     = "<" /ABC/ !name ">"
        closetag       = close_slash | close_star 
        close_slash    = "<" ::name "/>"
        close_star     = "<" ::name "*>"
        closespecial   = "<" /ABC/~ ">"
        name           = /\w+/~
        text           = /[^<>]+/
        """

    def setup(self):
391
392
393
        self.minilang_parser = grammar_provider(self.mini_language)()
        self.minilang_parser2 = grammar_provider(self.mini_lang2)()
        self.minilang_parser3 = grammar_provider(self.mini_lang3)()
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

    @staticmethod
    def opening_delimiter(node, name):
        return node.tag_name == name and not isinstance(node.parser, Retrieve)

    @staticmethod
    def closing_delimiter(node):
        return isinstance(node.parser, Retrieve)

    def test_compile_mini_language(self):
        assert self.minilang_parser
        assert self.minilang_parser2
        assert self.minilang_parser3

    def test_stackhandling(self):
        ambigous_opening = "<ABCnormal> normal tag <ABCnormal*>"
        syntax_tree = self.minilang_parser3(ambigous_opening)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        ambigous_opening = "<ABCnormal> normal tag <ABCnormal/>"
        syntax_tree = self.minilang_parser3(ambigous_opening)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        forgot_closing_tag = "<em> where is the closing tag?"
        syntax_tree = self.minilang_parser3(forgot_closing_tag)
        assert syntax_tree.error_flag, str(syntax_tree.collect_errors())

        proper = "<em> has closing tag <em/>"
        syntax_tree = self.minilang_parser3(proper)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        proper = "<em> has closing tag <em*>"
        syntax_tree = self.minilang_parser3(proper)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

429
    def test_cache_neutrality(self):
430
431
        """Test that packrat-caching does not interfere with the variable-
        changing parsers: Capture and Retrieve."""
432
433
434
435
436
437
438
439
440
441
        lang = """
            text = opening closing
            opening = (unmarked_package | marked_package)
            closing = ::variable
            unmarked_package = package "."
            marked_package = package "*" "."
            package = "(" variable ")"
            variable = /\w+/~
            """
        case = "(secret)*. secret"
442
        gr = grammar_provider(lang)()
443
444
        st = gr(case)
        assert not st.error_flag, str(st.collect_errors())
445
446
447
448
449

    def test_single_line(self):
        teststr = "Anfang ```code block `` <- keine Ende-Zeichen ! ``` Ende"
        syntax_tree = self.minilang_parser(teststr)
        assert not syntax_tree.collect_errors()
450
451
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
452
453
        assert delim == pop
        if is_logging():
454
            log_ST(syntax_tree, "test_PopRetrieve_single_line.cst")
455
456
457
458
459
460
461
462
463
464
465
466

    def test_multi_line(self):
        teststr = """
            Anfang ```code block `` <- keine Ende-Zeichen ! ``` Ebde

            Absatz ohne ``` codeblock, aber
            das stellt sich erst am Ende herause...

            Mehrzeliger ```code block
            """
        syntax_tree = self.minilang_parser(teststr)
        assert not syntax_tree.collect_errors()
467
468
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
469
470
        assert delim == pop
        if is_logging():
471
            log_ST(syntax_tree, "test_PopRetrieve_multi_line.cst")
472
473
474
475
476

    def test_single_line_complement(self):
        teststr = "Anfang {{{code block }} <- keine Ende-Zeichen ! }}} Ende"
        syntax_tree = self.minilang_parser2(teststr)
        assert not syntax_tree.collect_errors()
477
478
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
479
480
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
481
            log_ST(syntax_tree, "test_PopRetrieve_single_line.cst")
482
483
484
485
486
487
488
489
490
491
492
493

    def test_multi_line_complement(self):
        teststr = """
            Anfang {{{code block {{ <- keine Ende-Zeichen ! }}} Ende

            Absatz ohne {{{ codeblock, aber
            das stellt sich erst am Ende heraus...

            Mehrzeliger }}}code block
            """
        syntax_tree = self.minilang_parser2(teststr)
        assert not syntax_tree.collect_errors()
494
495
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
496
497
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
498
            log_ST(syntax_tree, "test_PopRetrieve_multi_line.cst")
499
500


501
class TestWhitespaceHandling:
Eckhart Arnold's avatar
Eckhart Arnold committed
502
    minilang = """
503
504
505
506
507
508
509
510
511
        doc = A B
        A = "A"
        B = "B"
        Rdoc = ar br
        ar = /A/
        br = /B/
        """

    def setup(self):
512
        self.gr = grammar_provider(self.minilang)()
513
514
515
516
517
518
519
520
521
522
523
524
525
526

    def test_token_whitespace(self):
        st = self.gr("AB", 'doc')
        assert not st.error_flag
        st = self.gr("A B", 'doc')
        assert not st.error_flag

    def test_regexp_whitespace(self):
        st = self.gr("AB", 'Rdoc')
        assert not st.error_flag
        st = self.gr("A B", 'Rdoc')
        assert st.error_flag


di68kap's avatar
di68kap committed
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
class TestBorderlineCases:
    def test_not_matching(self):
        minilang = """parser = /X/"""
        gr = grammar_provider(minilang)()
        cst = gr('X', 'parser')
        assert not cst.error_flag
        cst = gr(' ', 'parser')
        assert cst.error_flag
        cst = gr('', 'parser')
        assert cst.error_flag

    def test_matching(self):
        minilang = """parser = /.?/"""
        gr = grammar_provider(minilang)()
        cst = gr(' ', 'parser')
        assert not cst.error_flag
        cst = gr('  ', 'parser')
        assert cst.error_flag
        cst = gr('', 'parser')
        assert not cst.error_flag


549
550
551
552
553
554
555
556
557
558
class TestUnknownParserError:
    def test_unknown_parser_error(self):
        gr = Grammar()
        try:
            gr("", "NonExistantParser")
            assert False, "UnknownParserError expected!"
        except UnknownParserError:
            pass


559
if __name__ == "__main__":
560
    from DHParser.testing import runner
561
562
    with logging(False):
        runner("", globals())