test_parse.py 27.4 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
eckhart's avatar
eckhart committed
30
31
32
from DHParser.parse import Retrieve, Parser, Grammar, Forward, TKN, ZeroOrMore, RE, \
    RegExp, Lookbehind, NegativeLookahead, OneOrMore, Series, Alternative, AllOf, SomeOf, \
    UnknownParserError
33
from DHParser import compile_source
Eckhart Arnold's avatar
Eckhart Arnold committed
34
from DHParser.ebnf import get_ebnf_grammar, get_ebnf_transformer, get_ebnf_compiler
35
from DHParser.dsl import grammar_provider, DHPARSER_IMPORTS
36
37


eckhart's avatar
eckhart committed
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
class TestParserClass:
    def test_apply(self):
        minilang ="""
            expr = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
        gr = grammar_provider(minilang)()
        l = []
        def visitor(p: Parser):
            l.append(p.name + p.ptype)
        gr.root__.apply(visitor)
        s1 = ", ".join(l)
        l = []
        gr.root__.apply(visitor)
        s2 = ", ".join(l)
        l = []
        gr.root__.apply(visitor)
        s3 = ", ".join(l)
        # print(s1);  print(s2);  print(s3)
        assert s1 == s2 == s3


61
class TestInfiLoopsAndRecursion:
62
    def test_direct_left_recursion1(self):
eckhart's avatar
eckhart committed
63
        minilang ="""
64
65
66
67
            expr = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
68
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
69
        parser = grammar_provider(minilang)()
70
        assert parser
Eckhart Arnold's avatar
Eckhart Arnold committed
71
        syntax_tree = parser(snippet)
72
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())
73
        assert snippet == str(syntax_tree)
Eckhart Arnold's avatar
Eckhart Arnold committed
74
        if is_logging():
75
            log_ST(syntax_tree, "test_LeftRecursion_direct.cst")
76
            parser.log_parsing_history__("test_LeftRecursion_direct")
77

78
    def test_direct_left_recursion2(self):
79
80
81
82
83
84
        minilang = """
            expr = ex
            ex   = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            """
85
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
86
        parser = grammar_provider(minilang)()
87
88
        assert parser
        syntax_tree = parser(snippet)
89
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
90
        assert snippet == str(syntax_tree)
91

92
    def test_indirect_left_recursion1(self):
93
94
        minilang = """
            Expr    = //~ (Product | Sum | Value)
95
96
            Product = Expr { ('*' | '/') Expr }+
            Sum     = Expr { ('+' | '-') Expr }+
97
98
            Value   = /[0-9.]+/~ | '(' Expr ')'
            """
99
        parser = grammar_provider(minilang)()
100
        assert parser
101
        snippet = "8 * 4"
102
        syntax_tree = parser(snippet)
103
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
104
105
        snippet = "7 + 8 * 4"
        syntax_tree = parser(snippet)
106
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
107
108
        snippet = "9 + 8 * (4 + 3)"
        syntax_tree = parser(snippet)
109
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
110
        assert snippet == str(syntax_tree)
111
        if is_logging():
112
            log_ST(syntax_tree, "test_LeftRecursion_indirect.cst")
113
            parser.log_parsing_history__("test_LeftRecursion_indirect")
114

115
116
117
    def test_inifinite_loops(self):
        minilang = """not_forever = { // } \n"""
        snippet = " "
118
        parser = grammar_provider(minilang)()
Eckhart Arnold's avatar
Eckhart Arnold committed
119
        syntax_tree = parser(snippet)
120
121
        assert syntax_tree.error_flag

122

Eckhart Arnold's avatar
Eckhart Arnold committed
123
class TestFlowControl:
124
125
    def setup(self):
        self.t1 = """
eckhart's avatar
eckhart committed
126
        All work and no play
127
128
129
130
131
        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
132
133
134
    def test_lookbehind(self):
        ws = RegExp('\s*')
        end = RegExp("END")
135
        doc_end = Lookbehind(RegExp('\\s*?\\n')) + end
Eckhart Arnold's avatar
Eckhart Arnold committed
136
137
138
139
140
        word = RegExp('\w+')
        sequence = OneOrMore(NegativeLookahead(end) + word + ws)
        document = ws + sequence + doc_end + ws

        parser = Grammar(document)
141
142
143
144
145
146
147
148
149
150
        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')
151
            SUCC_LB = RegExp('\\s*?\\n')
152
153
154
155
156
157
158
159
            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
160
        assert not cst.error_flag, cst.as_sxpr()
161
        cst = parser(self.t2)
Eckhart Arnold's avatar
Eckhart Arnold committed
162
163
164
        assert cst.error_flag, cst.as_sxpr()


165
166
167
168
169
170
171
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
172
173
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
174
        assert result
175
        assert not messages, str(messages)
176
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
eckhart's avatar
eckhart committed
177
178
        node = parser('abc+def', parser.regex)
        assert not node.error_flag
179
180
181
        assert node.parser.name == "regex"
        assert str(node) == 'abc+def'

182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
    def test_multilineRegex_wo_Comments(self):
        mlregex = r"""
        regex =  /\w+ 
                  [+]  
                  \w* /
        """
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
        assert result
        assert not messages, str(messages)
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
        node = parser('abc+def', parser.regex)
        assert not node.error_flag
        assert node.parser.name == "regex"
        assert str(node) == 'abc+def'

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
    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


228
229
230
231
232
233
234
235
236
237
238
239
    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
240
241
        result, messages, syntax_tree = compile_source(tokenlang, None, get_ebnf_grammar(),
                                    get_ebnf_transformer(), get_ebnf_compiler("TokenTest"))
242
        assert result
eckhart's avatar
eckhart committed
243
        assert not messages, str(messages)
244
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
Eckhart Arnold's avatar
Eckhart Arnold committed
245
        result = parser(testdoc)
246
        # parser.log_parsing_history("test.log")
247
248
        assert not result.error_flag

249

250
class TestGrammar:
251
    def setup(self):
252
253
254
255
256
257
        grammar = r"""@whitespace = horizontal
        haupt        = textzeile LEERZEILE
        textzeile    = { WORT }+
        WORT         = /[^ \t]+/~
        LEERZEILE    = /\n[ \t]*(?=\n)/~
        """
258
259
260
        self.pyparser, messages, syntax_tree = compile_source(grammar, None, get_ebnf_grammar(),
                                                              get_ebnf_transformer(), get_ebnf_compiler("PosTest"))
        assert self.pyparser
261
        assert not messages
262
263
264
265

    def test_pos_values_initialized(self):
        # checks whether pos values in the parsing result and in the
        # history record have been initialized
266
        with logging("LOGS"):
267
268
269
            grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
            grammar("no_file_name*")
        for record in grammar.history__:
270
271
            assert not record.node or record.node.pos >= 0

272
    def test_select_parsing(self):
273
274
275
276
277
        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")
278

di68kap's avatar
di68kap committed
279
280
281
282
283
284
285
286
287
    def test_grammar_subclassing(self):
        class Arithmetic(Grammar):
            '''
            expression =  term  { ("+" | "-") term }
            term       =  factor  { ("*" | "/") factor }
            factor     =  INTEGER | "("  expression  ")"
            INTEGER    =  /\d+/~
            '''
            expression = Forward()
288
289
290
291
            INTEGER = RE('\\d+')
            factor = INTEGER | TKN("(") + expression + TKN(")")
            term = factor + ZeroOrMore((TKN("*") | TKN("/")) + factor)
            expression.set(term + ZeroOrMore((TKN("+") | TKN("-")) + term))
di68kap's avatar
di68kap committed
292
293
294
295
296
297
            root__ = expression

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

298

299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
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)()
322
323
324
        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
325
        # print(st.collect_errors())
326
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
327
        # transitivity of mandatory-operator
328
        st = parser("ABC_");  assert st.error_flag
329
330
331
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

    def test_series_composition(self):
332
        TA, TB, TC, TD, TE = (TKN(b) for b in "ABCDE")
333
334
335
336
337
        s1 = Series(TA, TB, TC, mandatory=2)
        s2 = Series(TD, TE)

        combined = Alternative(s1 + s2, RegExp('.*'))
        parser = Grammar(combined)
338
339
340
        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
341
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION
342
        st = parser("ABC_E");  assert st.error_flag
343
344
345
346
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

        combined = Alternative(s2 + s1, RegExp('.*'))
        parser = Grammar(combined)
347
348
349
350
351
352
        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
353
354
        assert st.collect_errors()[0].code == Error.MANDATORY_CONTINUATION

eckhart's avatar
eckhart committed
355
356
357
358
359
360
361
362
363
364
    # def test_boundary_cases(self):
    #     lang = """
    #     document = series | §!single | /.*/
    #     series = "A" "B" §"C" "D"
    #     single = "E"
    #     """
    #     parser_class = grammar_provider(lang)
    #     parser = parser_class()
    #     print(parser.python_src__)
    #     print(parser_class.python_src__)
eckhart's avatar
eckhart committed
365

366

367
368
369
class TestAllOfSomeOf:
    def test_allOf_order(self):
        """Test that parsers of an AllOf-List can match in arbitrary order."""
370
        prefixes = AllOf(TKN("A"), TKN("B"))
371
372
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B A').content == 'B A'
373
        # aternative Form
374
        prefixes = AllOf(Series(TKN("B"), TKN("A")))
375
        assert Grammar(prefixes)('A B').content == 'A B'
376
377
378
379

    def test_allOf_completeness(self):
        """Test that an error is raised if not  all parsers of an AllOf-List
        match."""
380
        prefixes = AllOf(TKN("A"), TKN("B"))
381
382
383
384
385
        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."""
386
        prefixes = AllOf(TKN("A"), TKN("B"), TKN("A"))
387
388
389
        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'
390
391
392
393
        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."""
394
        prefixes = SomeOf(TKN("A"), TKN("B"))
395
396
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B A').content == 'B A'
397
        # aternative Form
398
        prefixes = SomeOf(Alternative(TKN("B"), TKN("A")))
399
400
        assert Grammar(prefixes)('A B').content == 'A B'
        assert Grammar(prefixes)('B').content == 'B'
401
402
403
404

    def test_someOf_redundance(self):
        """Test that one and the same parser may be listed several times
        and must be matched several times accordingly."""
405
        prefixes = SomeOf(TKN("A"), TKN("B"), TKN("A"))
406
407
408
        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'
409
410
411
        assert Grammar(prefixes)('A B B').error_flag


412
413
414
415
class TestPopRetrieve:
    mini_language = """
        document       = { text | codeblock }
        codeblock      = delimiter { text | (!:delimiter delimiter_sign) } ::delimiter
416
        delimiter      = delimiter_sign  # never use delimiter between capture and pop except for retrival!
417
        delimiter_sign = /`+/
eckhart's avatar
eckhart committed
418
        text           = /[^`]+/
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
        """
    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 ">"
eckhart's avatar
eckhart committed
434
        closetag       = close_slash | close_star
435
436
437
438
439
440
441
442
        close_slash    = "<" ::name "/>"
        close_star     = "<" ::name "*>"
        closespecial   = "<" /ABC/~ ">"
        name           = /\w+/~
        text           = /[^<>]+/
        """

    def setup(self):
443
444
445
        self.minilang_parser = grammar_provider(self.mini_language)()
        self.minilang_parser2 = grammar_provider(self.mini_lang2)()
        self.minilang_parser3 = grammar_provider(self.mini_lang3)()
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

    @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())

481
    def test_cache_neutrality(self):
482
483
        """Test that packrat-caching does not interfere with the variable-
        changing parsers: Capture and Retrieve."""
484
485
486
487
488
489
490
491
492
493
        lang = """
            text = opening closing
            opening = (unmarked_package | marked_package)
            closing = ::variable
            unmarked_package = package "."
            marked_package = package "*" "."
            package = "(" variable ")"
            variable = /\w+/~
            """
        case = "(secret)*. secret"
494
        gr = grammar_provider(lang)()
495
496
        st = gr(case)
        assert not st.error_flag, str(st.collect_errors())
497
498
499
500
501

    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()
502
503
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
504
505
        assert delim == pop
        if is_logging():
506
            log_ST(syntax_tree, "test_PopRetrieve_single_line.cst")
507
508
509
510
511
512
513
514
515
516
517
518

    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()
519
520
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
521
522
        assert delim == pop
        if is_logging():
523
            log_ST(syntax_tree, "test_PopRetrieve_multi_line.cst")
524
525
526
527
528

    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()
529
530
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
531
532
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
533
            log_ST(syntax_tree, "test_PopRetrieve_single_line.cst")
534
535
536
537
538
539
540
541
542
543
544
545

    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()
546
547
        delim = str(next(syntax_tree.select(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.select(self.closing_delimiter)))
548
549
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
550
            log_ST(syntax_tree, "test_PopRetrieve_multi_line.cst")
551
552


553
class TestWhitespaceHandling:
Eckhart Arnold's avatar
Eckhart Arnold committed
554
    minilang = """
555
556
557
558
559
560
561
562
563
        doc = A B
        A = "A"
        B = "B"
        Rdoc = ar br
        ar = /A/
        br = /B/
        """

    def setup(self):
564
        self.gr = grammar_provider(self.minilang)()
565
566
567
568
569
570
571
572
573
574
575
576

    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
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601


class TestErrorReporting:
    grammar = """
        root      = series alpha | anything
        series    = subseries &alpha 
        subseries = alpha §beta
        alpha     = /[a-z]+/
        beta      = /[A-Z]+/
        anything  = /.*/
        """

    def setup(self):
        self.parser = grammar_provider(self.grammar)()

    def test_error_propagation(self):
        testcode1 = "halloB"
        testcode2 = "XYZ"
        testcode3 = "hallo "
        cst = self.parser(testcode1)
        assert not cst.error_flag, str(cst.collect_errors())
        cst = self.parser(testcode2)
        assert not cst.error_flag
        cst = self.parser(testcode3)
        assert cst.error_flag
602
603


di68kap's avatar
di68kap committed
604
605
606
607
608
609
610
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')
611
        assert cst.error_flag and cst.collect_errors()[0].code == Error.PARSER_DID_NOT_MATCH
di68kap's avatar
di68kap committed
612
        cst = gr('', 'parser')
613
        assert cst.error_flag and cst.collect_errors()[0].code == Error.PARSER_DID_NOT_MATCH
di68kap's avatar
di68kap committed
614
615
616
617
618
619
620

    def test_matching(self):
        minilang = """parser = /.?/"""
        gr = grammar_provider(minilang)()
        cst = gr(' ', 'parser')
        assert not cst.error_flag
        cst = gr('  ', 'parser')
621
        assert cst.error_flag and cst.collect_errors()[0].code == Error.PARSER_STOPPED_BEFORE_END
di68kap's avatar
di68kap committed
622
623
624
625
        cst = gr('', 'parser')
        assert not cst.error_flag


Eckhart Arnold's avatar
Eckhart Arnold committed
626
class TestReentryAfterError:
627
    def setup(self):
Eckhart Arnold's avatar
Eckhart Arnold committed
628
629
630
631
632
        lang = """
        document = alpha [beta] gamma "."
          alpha = "ALPHA" abc
            abc = §"a" "b" "c"
          beta = "BETA" (bac | bca)
633
634
            bac = "b" "a" §"c"
            bca = "b" "c" §"a"
Eckhart Arnold's avatar
Eckhart Arnold committed
635
636
637
638
          gamma = "GAMMA" §(cab | cba)
            cab = "c" "a" §"b"
            cba = "c" "b" §"a"
        """
639
        self.gr = grammar_provider(lang)()
640

641
    def test_no_resume_rules(self):
642
        # 1. no resume rules
643
        gr = self.gr;  gr.resume_rules = dict()
644
645
        content = 'ALPHA acb BETA bac GAMMA cab .'
        cst = gr(content)
646
647
648
649
650
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')

eckhart's avatar
eckhart committed
651
652
653
654
655
656
657
658
659
    def test_no_resume_rules_partial_parsing(self):
        gr = self.gr;  gr.resume_rules = dict()
        content = 'ALPHA acb'
        cst = gr(content, 'alpha')
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')

660
661
    def test_simple_resume_rule(self):
        gr = self.gr;  gr.resume_rules = dict()
662
        gr.resume_rules__['alpha'] = ['BETA']
663
        content = 'ALPHA acb BETA bac GAMMA cab .'
664
665
666
667
668
669
670
671
        cst = gr(content)
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message
        assert len(cst.collect_errors()) == 1

672
673
    def test_failing_resume_rule(self):
        gr = self.gr;  gr.resume_rules = dict()
674
        gr.resume_rules__['alpha'] = ['XXX']
675
        content = 'ALPHA acb BETA bac GAMMA cab .'
676
677
678
679
680
681
682
        cst = gr(content)
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        # assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message

683
684
    def test_severl_reentry_points(self):
        gr = self.gr;  gr.resume_rules = dict()
685
        gr.resume_rules__['alpha'] = ['BETA', 'GAMMA']
686
        content = 'ALPHA acb BETA bac GAMMA cab .'
687
688
689
690
691
692
693
694
        cst = gr(content)
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message
        assert len(cst.collect_errors()) == 1

695
696
    def test_several_reentry_points_second_point_matching(self):
        gr = self.gr;  gr.resume_rules = dict()
697
698
699
        gr.resume_rules__['alpha'] = ['BETA', 'GAMMA']
        content = 'ALPHA acb GAMMA cab .'
        cst = gr(content)
700
        # print(cst.as_sxpr())
Eckhart Arnold's avatar
Eckhart Arnold committed
701
        assert cst.error_flag
702
        assert cst.content == content
703
704
705
        assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message
        assert len(cst.collect_errors()) == 1
706

707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
    def test_several_resume_rules_innermost_rule_matching(self):
        gr = self.gr;  gr.resume_rules = dict()
        gr.resume_rules__['alpha'] = ['BETA', 'GAMMA']
        gr.resume_rules__['beta'] = ['GAMMA']
        gr.resume_rules__['bac'] = ['GAMMA']
        content = 'ALPHA abc BETA bad GAMMA cab .'
        cst = gr(content)
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message
        assert len(cst.collect_errors()) == 1
        # multiple failures
        content = 'ALPHA acb BETA bad GAMMA cab .'
        cst = gr(content)
        # print(cst.as_sxpr())
        assert cst.error_flag
        assert cst.content == content
        assert cst.pick('alpha').content.startswith('ALPHA')
        # because of resuming, there should be only on error message
        assert len(cst.collect_errors()) == 2

730

731
732
733
734
735
736
737
738
739
740
class TestUnknownParserError:
    def test_unknown_parser_error(self):
        gr = Grammar()
        try:
            gr("", "NonExistantParser")
            assert False, "UnknownParserError expected!"
        except UnknownParserError:
            pass


741
if __name__ == "__main__":
742
    from DHParser.testing import runner
743
744
    with logging(False):
        runner("", globals())