21.10.2021, 9:00 - 11:00: Due to updates GitLab may be unavailable for some minutes between 09:00 and 11:00.

test_parser.py 18.5 KB
Newer Older
1
2
#!/usr/bin/python3

3
"""test_parser.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
from DHParser.toolkit import is_logging, logging, compile_python_object, StringView
28
from DHParser.error import Error
Eckhart Arnold's avatar
Eckhart Arnold committed
29
from DHParser.parser import compile_source, Retrieve, Grammar, Forward, Token, ZeroOrMore, RE, \
30
    RegExp, Lookbehind, NegativeLookahead, OneOrMore, Series, Alternative
Eckhart Arnold's avatar
Eckhart Arnold committed
31
from DHParser.ebnf import get_ebnf_grammar, get_ebnf_transformer, get_ebnf_compiler
32
from DHParser.dsl import grammar_provider, DHPARSER_IMPORTS
33
34


35
class TestInfiLoopsAndRecursion:
36
    def test_direct_left_recursion1(self):
37
38
39
40
41
        minilang =""" 
            expr = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
42
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
43
        parser = grammar_provider(minilang)()
44
        assert parser
Eckhart Arnold's avatar
Eckhart Arnold committed
45
        syntax_tree = parser(snippet)
46
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())
47
        assert snippet == str(syntax_tree)
Eckhart Arnold's avatar
Eckhart Arnold committed
48
49
        if is_logging():
            syntax_tree.log("test_LeftRecursion_direct.cst")
50
            parser.log_parsing_history__("test_LeftRecursion_direct")
51

52
    def test_direct_left_recursion2(self):
53
54
55
56
57
58
        minilang = """
            expr = ex
            ex   = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
59
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
60
        parser = grammar_provider(minilang)()
61
62
        assert parser
        syntax_tree = parser(snippet)
63
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
64
        assert snippet == str(syntax_tree)
65

66
    def test_indirect_left_recursion1(self):
67
68
        minilang = """
            Expr    = //~ (Product | Sum | Value)
69
70
            Product = Expr { ('*' | '/') Expr }+
            Sum     = Expr { ('+' | '-') Expr }+
71
72
            Value   = /[0-9.]+/~ | '(' Expr ')'
            """
73
        parser = grammar_provider(minilang)()
74
        assert parser
75
        snippet = "8 * 4"
76
        syntax_tree = parser(snippet)
77
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
78
79
        snippet = "7 + 8 * 4"
        syntax_tree = parser(snippet)
80
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
81
82
        snippet = "9 + 8 * (4 + 3)"
        syntax_tree = parser(snippet)
83
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
84
        assert snippet == str(syntax_tree)
85

86
87
88
    def test_inifinite_loops(self):
        minilang = """not_forever = { // } \n"""
        snippet = " "
89
        parser = grammar_provider(minilang)()
Eckhart Arnold's avatar
Eckhart Arnold committed
90
        syntax_tree = parser(snippet)
91
92
        assert syntax_tree.error_flag

93

Eckhart Arnold's avatar
Eckhart Arnold committed
94
class TestFlowControl:
95
96
97
98
99
100
101
102
    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
103
104
105
    def test_lookbehind(self):
        ws = RegExp('\s*')
        end = RegExp("END")
106
        doc_end = Lookbehind(RegExp('\\s*?\\n')) + end
Eckhart Arnold's avatar
Eckhart Arnold committed
107
108
109
110
111
        word = RegExp('\w+')
        sequence = OneOrMore(NegativeLookahead(end) + word + ws)
        document = ws + sequence + doc_end + ws

        parser = Grammar(document)
112
113
114
115
116
117
118
119
120
121
        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')
122
            SUCC_LB = RegExp('\\s*?\\n')
123
124
125
126
127
128
129
130
            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
131
        assert not cst.error_flag, cst.as_sxpr()
132
        cst = parser(self.t2)
Eckhart Arnold's avatar
Eckhart Arnold committed
133
134
135
        assert cst.error_flag, cst.as_sxpr()


136
137
138
139
140
141
142
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
143
144
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
145
        assert result
146
        assert not messages, str(messages)
147
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
148
        node, rest = parser.regex(StringView('abc+def'))
149
150
151
152
        assert rest == ''
        assert node.parser.name == "regex"
        assert str(node) == 'abc+def'

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
    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


183
184
185
186
187
188
189
190
191
192
193
194
    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
195
196
        result, messages, syntax_tree = compile_source(tokenlang, None, get_ebnf_grammar(),
                                    get_ebnf_transformer(), get_ebnf_compiler("TokenTest"))
197
198
199
        assert result
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
Eckhart Arnold's avatar
Eckhart Arnold committed
200
        result = parser(testdoc)
201
        # parser.log_parsing_history__("test.log")
202
203
        assert not result.error_flag

204

205
class TestGrammar:
206
    def setup(self):
207
208
209
210
211
212
        grammar = r"""@whitespace = horizontal
        haupt        = textzeile LEERZEILE
        textzeile    = { WORT }+
        WORT         = /[^ \t]+/~
        LEERZEILE    = /\n[ \t]*(?=\n)/~
        """
213
214
215
        self.pyparser, messages, syntax_tree = compile_source(grammar, None, get_ebnf_grammar(),
                                                              get_ebnf_transformer(), get_ebnf_compiler("PosTest"))
        assert self.pyparser
216
        assert not messages
217
218
219
220

    def test_pos_values_initialized(self):
        # checks whether pos values in the parsing result and in the
        # history record have been initialized
221
        with logging("LOGS"):
222
223
224
            grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
            grammar("no_file_name*")
        for record in grammar.history__:
225
226
            assert not record.node or record.node.pos >= 0

227
    def test_select_parsing(self):
228
229
230
231
232
        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")
233

di68kap's avatar
di68kap committed
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
    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()

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
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)()
        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
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
        st = parser("ABC_");
        assert st.error_flag
        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)
        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
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
        st = parser("ABC_E");
        assert st.error_flag
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

        combined = Alternative(s2 + s1, RegExp('.*'))
        parser = Grammar(combined)
        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
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION


323
324
325
326
class TestPopRetrieve:
    mini_language = """
        document       = { text | codeblock }
        codeblock      = delimiter { text | (!:delimiter delimiter_sign) } ::delimiter
327
        delimiter      = delimiter_sign  # never use delimiter between capture and pop except for retrival!
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
        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):
354
355
356
        self.minilang_parser = grammar_provider(self.mini_language)()
        self.minilang_parser2 = grammar_provider(self.mini_lang2)()
        self.minilang_parser3 = grammar_provider(self.mini_lang3)()
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

    @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())

392
    def test_cache_neutrality(self):
393
394
        """Test that packrat-caching does not interfere with the variable-
        changing parsers: Capture and Retrieve."""
395
396
397
398
399
400
401
402
403
404
        lang = """
            text = opening closing
            opening = (unmarked_package | marked_package)
            closing = ::variable
            unmarked_package = package "."
            marked_package = package "*" "."
            package = "(" variable ")"
            variable = /\w+/~
            """
        case = "(secret)*. secret"
405
        gr = grammar_provider(lang)()
406
407
        st = gr(case)
        assert not st.error_flag, str(st.collect_errors())
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

    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()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert delim == pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_single_line.cst")

    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()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert delim == pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_multi_line.cst")

    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()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_single_line.cst")

    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()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_multi_line.cst")


464
class TestWhitespaceHandling:
Eckhart Arnold's avatar
Eckhart Arnold committed
465
    minilang = """
466
467
468
469
470
471
472
473
474
        doc = A B
        A = "A"
        B = "B"
        Rdoc = ar br
        ar = /A/
        br = /B/
        """

    def setup(self):
475
        self.gr = grammar_provider(self.minilang)()
476
477
478
479
480
481
482
483
484
485
486
487
488
489

    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
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
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


512
if __name__ == "__main__":
513
    from DHParser.testing import runner
514
515
    with logging(False):
        runner("", globals())