aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/python/Pygments/py3/pygments/lexers/ml.py
blob: 60bd8b9dbc025f940e8b60f27eabf72b8e1cf4f3 (plain) (blame)
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
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
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
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
"""
    pygments.lexers.ml
    ~~~~~~~~~~~~~~~~~~

    Lexers for ML family languages.

    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pygments.lexer import RegexLexer, include, bygroups, default, words
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
    Number, Punctuation, Error

__all__ = ['SMLLexer', 'OcamlLexer', 'OpaLexer', 'ReasonLexer', 'FStarLexer']


class SMLLexer(RegexLexer):
    """
    For the Standard ML language.

    .. versionadded:: 1.5
    """

    name = 'Standard ML'
    aliases = ['sml']
    filenames = ['*.sml', '*.sig', '*.fun']
    mimetypes = ['text/x-standardml', 'application/x-standardml']

    alphanumid_reserved = {
        # Core
        'abstype', 'and', 'andalso', 'as', 'case', 'datatype', 'do', 'else',
        'end', 'exception', 'fn', 'fun', 'handle', 'if', 'in', 'infix',
        'infixr', 'let', 'local', 'nonfix', 'of', 'op', 'open', 'orelse',
        'raise', 'rec', 'then', 'type', 'val', 'with', 'withtype', 'while',
        # Modules
        'eqtype', 'functor', 'include', 'sharing', 'sig', 'signature',
        'struct', 'structure', 'where',
    }

    symbolicid_reserved = {
        # Core
        ':', r'\|', '=', '=>', '->', '#',
        # Modules
        ':>',
    }

    nonid_reserved = {'(', ')', '[', ']', '{', '}', ',', ';', '...', '_'}

    alphanumid_re = r"[a-zA-Z][\w']*"
    symbolicid_re = r"[!%&$#+\-/:<=>?@\\~`^|*]+"

    # A character constant is a sequence of the form #s, where s is a string
    # constant denoting a string of size one character. This setup just parses
    # the entire string as either a String.Double or a String.Char (depending
    # on the argument), even if the String.Char is an erronous
    # multiple-character string.
    def stringy(whatkind):
        return [
            (r'[^"\\]', whatkind),
            (r'\\[\\"abtnvfr]', String.Escape),
            # Control-character notation is used for codes < 32,
            # where \^@ == \000
            (r'\\\^[\x40-\x5e]', String.Escape),
            # Docs say 'decimal digits'
            (r'\\[0-9]{3}', String.Escape),
            (r'\\u[0-9a-fA-F]{4}', String.Escape),
            (r'\\\s+\\', String.Interpol),
            (r'"', whatkind, '#pop'),
        ]

    # Callbacks for distinguishing tokens and reserved words
    def long_id_callback(self, match):
        if match.group(1) in self.alphanumid_reserved:
            token = Error
        else:
            token = Name.Namespace
        yield match.start(1), token, match.group(1)
        yield match.start(2), Punctuation, match.group(2)

    def end_id_callback(self, match):
        if match.group(1) in self.alphanumid_reserved:
            token = Error
        elif match.group(1) in self.symbolicid_reserved:
            token = Error
        else:
            token = Name
        yield match.start(1), token, match.group(1)

    def id_callback(self, match):
        str = match.group(1)
        if str in self.alphanumid_reserved:
            token = Keyword.Reserved
        elif str in self.symbolicid_reserved:
            token = Punctuation
        else:
            token = Name
        yield match.start(1), token, str

    tokens = {
        # Whitespace and comments are (almost) everywhere
        'whitespace': [
            (r'\s+', Text),
            (r'\(\*', Comment.Multiline, 'comment'),
        ],

        'delimiters': [
            # This lexer treats these delimiters specially:
            # Delimiters define scopes, and the scope is how the meaning of
            # the `|' is resolved - is it a case/handle expression, or function
            # definition by cases? (This is not how the Definition works, but
            # it's how MLton behaves, see http://mlton.org/SMLNJDeviations)
            (r'\(|\[|\{', Punctuation, 'main'),
            (r'\)|\]|\}', Punctuation, '#pop'),
            (r'\b(let|if|local)\b(?!\')', Keyword.Reserved, ('main', 'main')),
            (r'\b(struct|sig|while)\b(?!\')', Keyword.Reserved, 'main'),
            (r'\b(do|else|end|in|then)\b(?!\')', Keyword.Reserved, '#pop'),
        ],

        'core': [
            # Punctuation that doesn't overlap symbolic identifiers
            (r'(%s)' % '|'.join(re.escape(z) for z in nonid_reserved),
             Punctuation),

            # Special constants: strings, floats, numbers in decimal and hex
            (r'#"', String.Char, 'char'),
            (r'"', String.Double, 'string'),
            (r'~?0x[0-9a-fA-F]+', Number.Hex),
            (r'0wx[0-9a-fA-F]+', Number.Hex),
            (r'0w\d+', Number.Integer),
            (r'~?\d+\.\d+[eE]~?\d+', Number.Float),
            (r'~?\d+\.\d+', Number.Float),
            (r'~?\d+[eE]~?\d+', Number.Float),
            (r'~?\d+', Number.Integer),

            # Labels
            (r'#\s*[1-9][0-9]*', Name.Label),
            (r'#\s*(%s)' % alphanumid_re, Name.Label),
            (r'#\s+(%s)' % symbolicid_re, Name.Label),
            # Some reserved words trigger a special, local lexer state change
            (r'\b(datatype|abstype)\b(?!\')', Keyword.Reserved, 'dname'),
            (r'\b(exception)\b(?!\')', Keyword.Reserved, 'ename'),
            (r'\b(functor|include|open|signature|structure)\b(?!\')',
             Keyword.Reserved, 'sname'),
            (r'\b(type|eqtype)\b(?!\')', Keyword.Reserved, 'tname'),

            # Regular identifiers, long and otherwise
            (r'\'[\w\']*', Name.Decorator),
            (r'(%s)(\.)' % alphanumid_re, long_id_callback, "dotted"),
            (r'(%s)' % alphanumid_re, id_callback),
            (r'(%s)' % symbolicid_re, id_callback),
        ],
        'dotted': [
            (r'(%s)(\.)' % alphanumid_re, long_id_callback),
            (r'(%s)' % alphanumid_re, end_id_callback, "#pop"),
            (r'(%s)' % symbolicid_re, end_id_callback, "#pop"),
            (r'\s+', Error),
            (r'\S+', Error),
        ],


        # Main parser (prevents errors in files that have scoping errors)
        'root': [
            default('main')
        ],

        # In this scope, I expect '|' to not be followed by a function name,
        # and I expect 'and' to be followed by a binding site
        'main': [
            include('whitespace'),

            # Special behavior of val/and/fun
            (r'\b(val|and)\b(?!\')', Keyword.Reserved, 'vname'),
            (r'\b(fun)\b(?!\')', Keyword.Reserved,
             ('#pop', 'main-fun', 'fname')),

            include('delimiters'),
            include('core'),
            (r'\S+', Error),
        ],

        # In this scope, I expect '|' and 'and' to be followed by a function
        'main-fun': [
            include('whitespace'),

            (r'\s', Text),
            (r'\(\*', Comment.Multiline, 'comment'),

            # Special behavior of val/and/fun
            (r'\b(fun|and)\b(?!\')', Keyword.Reserved, 'fname'),
            (r'\b(val)\b(?!\')', Keyword.Reserved,
             ('#pop', 'main', 'vname')),

            # Special behavior of '|' and '|'-manipulating keywords
            (r'\|', Punctuation, 'fname'),
            (r'\b(case|handle)\b(?!\')', Keyword.Reserved,
             ('#pop', 'main')),

            include('delimiters'),
            include('core'),
            (r'\S+', Error),
        ],

        # Character and string parsers
        'char': stringy(String.Char),
        'string': stringy(String.Double),

        'breakout': [
            (r'(?=\b(%s)\b(?!\'))' % '|'.join(alphanumid_reserved), Text, '#pop'),
        ],

        # Dealing with what comes after module system keywords
        'sname': [
            include('whitespace'),
            include('breakout'),

            (r'(%s)' % alphanumid_re, Name.Namespace),
            default('#pop'),
        ],

        # Dealing with what comes after the 'fun' (or 'and' or '|') keyword
        'fname': [
            include('whitespace'),
            (r'\'[\w\']*', Name.Decorator),
            (r'\(', Punctuation, 'tyvarseq'),

            (r'(%s)' % alphanumid_re, Name.Function, '#pop'),
            (r'(%s)' % symbolicid_re, Name.Function, '#pop'),

            # Ignore interesting function declarations like "fun (x + y) = ..."
            default('#pop'),
        ],

        # Dealing with what comes after the 'val' (or 'and') keyword
        'vname': [
            include('whitespace'),
            (r'\'[\w\']*', Name.Decorator),
            (r'\(', Punctuation, 'tyvarseq'),

            (r'(%s)(\s*)(=(?!%s))' % (alphanumid_re, symbolicid_re),
             bygroups(Name.Variable, Text, Punctuation), '#pop'),
            (r'(%s)(\s*)(=(?!%s))' % (symbolicid_re, symbolicid_re),
             bygroups(Name.Variable, Text, Punctuation), '#pop'),
            (r'(%s)' % alphanumid_re, Name.Variable, '#pop'),
            (r'(%s)' % symbolicid_re, Name.Variable, '#pop'),

            # Ignore interesting patterns like 'val (x, y)'
            default('#pop'),
        ],

        # Dealing with what comes after the 'type' (or 'and') keyword
        'tname': [
            include('whitespace'),
            include('breakout'),

            (r'\'[\w\']*', Name.Decorator),
            (r'\(', Punctuation, 'tyvarseq'),
            (r'=(?!%s)' % symbolicid_re, Punctuation, ('#pop', 'typbind')),

            (r'(%s)' % alphanumid_re, Keyword.Type),
            (r'(%s)' % symbolicid_re, Keyword.Type),
            (r'\S+', Error, '#pop'),
        ],

        # A type binding includes most identifiers
        'typbind': [
            include('whitespace'),

            (r'\b(and)\b(?!\')', Keyword.Reserved, ('#pop', 'tname')),

            include('breakout'),
            include('core'),
            (r'\S+', Error, '#pop'),
        ],

        # Dealing with what comes after the 'datatype' (or 'and') keyword
        'dname': [
            include('whitespace'),
            include('breakout'),

            (r'\'[\w\']*', Name.Decorator),
            (r'\(', Punctuation, 'tyvarseq'),
            (r'(=)(\s*)(datatype)',
             bygroups(Punctuation, Text, Keyword.Reserved), '#pop'),
            (r'=(?!%s)' % symbolicid_re, Punctuation,
             ('#pop', 'datbind', 'datcon')),

            (r'(%s)' % alphanumid_re, Keyword.Type),
            (r'(%s)' % symbolicid_re, Keyword.Type),
            (r'\S+', Error, '#pop'),
        ],

        # common case - A | B | C of int
        'datbind': [
            include('whitespace'),

            (r'\b(and)\b(?!\')', Keyword.Reserved, ('#pop', 'dname')),
            (r'\b(withtype)\b(?!\')', Keyword.Reserved, ('#pop', 'tname')),
            (r'\b(of)\b(?!\')', Keyword.Reserved),

            (r'(\|)(\s*)(%s)' % alphanumid_re,
             bygroups(Punctuation, Text, Name.Class)),
            (r'(\|)(\s+)(%s)' % symbolicid_re,
             bygroups(Punctuation, Text, Name.Class)),

            include('breakout'),
            include('core'),
            (r'\S+', Error),
        ],

        # Dealing with what comes after an exception
        'ename': [
            include('whitespace'),

            (r'(and\b)(\s+)(%s)' % alphanumid_re,
             bygroups(Keyword.Reserved, Text, Name.Class)),
            (r'(and\b)(\s*)(%s)' % symbolicid_re,
             bygroups(Keyword.Reserved, Text, Name.Class)),
            (r'\b(of)\b(?!\')', Keyword.Reserved),
            (r'(%s)|(%s)' % (alphanumid_re, symbolicid_re), Name.Class),

            default('#pop'),
        ],

        'datcon': [
            include('whitespace'),
            (r'(%s)' % alphanumid_re, Name.Class, '#pop'),
            (r'(%s)' % symbolicid_re, Name.Class, '#pop'),
            (r'\S+', Error, '#pop'),
        ],

        # Series of type variables
        'tyvarseq': [
            (r'\s', Text),
            (r'\(\*', Comment.Multiline, 'comment'),

            (r'\'[\w\']*', Name.Decorator),
            (alphanumid_re, Name),
            (r',', Punctuation),
            (r'\)', Punctuation, '#pop'),
            (symbolicid_re, Name),
        ],

        'comment': [
            (r'[^(*)]', Comment.Multiline),
            (r'\(\*', Comment.Multiline, '#push'),
            (r'\*\)', Comment.Multiline, '#pop'),
            (r'[(*)]', Comment.Multiline),
        ],
    }


class OcamlLexer(RegexLexer):
    """
    For the OCaml language.

    .. versionadded:: 0.7
    """

    name = 'OCaml'
    aliases = ['ocaml']
    filenames = ['*.ml', '*.mli', '*.mll', '*.mly']
    mimetypes = ['text/x-ocaml']

    keywords = (
        'as', 'assert', 'begin', 'class', 'constraint', 'do', 'done',
        'downto', 'else', 'end', 'exception', 'external', 'false',
        'for', 'fun', 'function', 'functor', 'if', 'in', 'include',
        'inherit', 'initializer', 'lazy', 'let', 'match', 'method',
        'module', 'mutable', 'new', 'object', 'of', 'open', 'private',
        'raise', 'rec', 'sig', 'struct', 'then', 'to', 'true', 'try',
        'type', 'value', 'val', 'virtual', 'when', 'while', 'with',
    )
    keyopts = (
        '!=', '#', '&', '&&', r'\(', r'\)', r'\*', r'\+', ',', '-',
        r'-\.', '->', r'\.', r'\.\.', ':', '::', ':=', ':>', ';', ';;', '<',
        '<-', '=', '>', '>]', r'>\}', r'\?', r'\?\?', r'\[', r'\[<', r'\[>',
        r'\[\|', ']', '_', '`', r'\{', r'\{<', r'\|', r'\|]', r'\}', '~'
    )

    operators = r'[!$%&*+\./:<=>?@^|~-]'
    word_operators = ('and', 'asr', 'land', 'lor', 'lsl', 'lxor', 'mod', 'or')
    prefix_syms = r'[!?~]'
    infix_syms = r'[=<>@^|&+\*/$%-]'
    primitives = ('unit', 'int', 'float', 'bool', 'string', 'char', 'list', 'array')

    tokens = {
        'escape-sequence': [
            (r'\\[\\"\'ntbr]', String.Escape),
            (r'\\[0-9]{3}', String.Escape),
            (r'\\x[0-9a-fA-F]{2}', String.Escape),
        ],
        'root': [
            (r'\s+', Text),
            (r'false|true|\(\)|\[\]', Name.Builtin.Pseudo),
            (r'\b([A-Z][\w\']*)(?=\s*\.)', Name.Namespace, 'dotted'),
            (r'\b([A-Z][\w\']*)', Name.Class),
            (r'\(\*(?![)])', Comment, 'comment'),
            (r'\b(%s)\b' % '|'.join(keywords), Keyword),
            (r'(%s)' % '|'.join(keyopts[::-1]), Operator),
            (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
            (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word),
            (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),

            (r"[^\W\d][\w']*", Name),

            (r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)', Number.Float),
            (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
            (r'0[oO][0-7][0-7_]*', Number.Oct),
            (r'0[bB][01][01_]*', Number.Bin),
            (r'\d[\d_]*', Number.Integer),

            (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'",
             String.Char),
            (r"'.'", String.Char),
            (r"'", Keyword),  # a stray quote is another syntax element

            (r'"', String.Double, 'string'),

            (r'[~?][a-z][\w\']*:', Name.Variable),
        ],
        'comment': [
            (r'[^(*)]+', Comment),
            (r'\(\*', Comment, '#push'),
            (r'\*\)', Comment, '#pop'),
            (r'[(*)]', Comment),
        ],
        'string': [
            (r'[^\\"]+', String.Double),
            include('escape-sequence'),
            (r'\\\n', String.Double),
            (r'"', String.Double, '#pop'),
        ],
        'dotted': [
            (r'\s+', Text),
            (r'\.', Punctuation),
            (r'[A-Z][\w\']*(?=\s*\.)', Name.Namespace),
            (r'[A-Z][\w\']*', Name.Class, '#pop'),
            (r'[a-z_][\w\']*', Name, '#pop'),
            default('#pop'),
        ],
    }


class OpaLexer(RegexLexer):
    """
    Lexer for the Opa language (http://opalang.org).

    .. versionadded:: 1.5
    """

    name = 'Opa'
    aliases = ['opa']
    filenames = ['*.opa']
    mimetypes = ['text/x-opa']

    # most of these aren't strictly keywords
    # but if you color only real keywords, you might just
    # as well not color anything
    keywords = (
        'and', 'as', 'begin', 'case', 'client', 'css', 'database', 'db', 'do',
        'else', 'end', 'external', 'forall', 'function', 'if', 'import',
        'match', 'module', 'or', 'package', 'parser', 'rec', 'server', 'then',
        'type', 'val', 'with', 'xml_parser',
    )

    # matches both stuff and `stuff`
    ident_re = r'(([a-zA-Z_]\w*)|(`[^`]*`))'

    op_re = r'[.=\-<>,@~%/+?*&^!]'
    punc_re = r'[()\[\],;|]'  # '{' and '}' are treated elsewhere
                              # because they are also used for inserts

    tokens = {
        # copied from the caml lexer, should be adapted
        'escape-sequence': [
            (r'\\[\\"\'ntr}]', String.Escape),
            (r'\\[0-9]{3}', String.Escape),
            (r'\\x[0-9a-fA-F]{2}', String.Escape),
        ],

        # factorizing these rules, because they are inserted many times
        'comments': [
            (r'/\*', Comment, 'nested-comment'),
            (r'//.*?$', Comment),
        ],
        'comments-and-spaces': [
            include('comments'),
            (r'\s+', Text),
        ],

        'root': [
            include('comments-and-spaces'),
            # keywords
            (words(keywords, prefix=r'\b', suffix=r'\b'), Keyword),
            # directives
            # we could parse the actual set of directives instead of anything
            # starting with @, but this is troublesome
            # because it needs to be adjusted all the time
            # and assuming we parse only sources that compile, it is useless
            (r'@' + ident_re + r'\b', Name.Builtin.Pseudo),

            # number literals
            (r'-?.[\d]+([eE][+\-]?\d+)', Number.Float),
            (r'-?\d+.\d*([eE][+\-]?\d+)', Number.Float),
            (r'-?\d+[eE][+\-]?\d+', Number.Float),
            (r'0[xX][\da-fA-F]+', Number.Hex),
            (r'0[oO][0-7]+', Number.Oct),
            (r'0[bB][01]+', Number.Bin),
            (r'\d+', Number.Integer),
            # color literals
            (r'#[\da-fA-F]{3,6}', Number.Integer),

            # string literals
            (r'"', String.Double, 'string'),
            # char literal, should be checked because this is the regexp from
            # the caml lexer
            (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2})|.)'",
             String.Char),

            # this is meant to deal with embedded exprs in strings
            # every time we find a '}' we pop a state so that if we were
            # inside a string, we are back in the string state
            # as a consequence, we must also push a state every time we find a
            # '{' or else we will have errors when parsing {} for instance
            (r'\{', Operator, '#push'),
            (r'\}', Operator, '#pop'),

            # html literals
            # this is a much more strict that the actual parser,
            # since a<b would not be parsed as html
            # but then again, the parser is way too lax, and we can't hope
            # to have something as tolerant
            (r'<(?=[a-zA-Z>])', String.Single, 'html-open-tag'),

            # db path
            # matching the '[_]' in '/a[_]' because it is a part
            # of the syntax of the db path definition
            # unfortunately, i don't know how to match the ']' in
            # /a[1], so this is somewhat inconsistent
            (r'[@?!]?(/\w+)+(\[_\])?', Name.Variable),
            # putting the same color on <- as on db path, since
            # it can be used only to mean Db.write
            (r'<-(?!'+op_re+r')', Name.Variable),

            # 'modules'
            # although modules are not distinguished by their names as in caml
            # the standard library seems to follow the convention that modules
            # only area capitalized
            (r'\b([A-Z]\w*)(?=\.)', Name.Namespace),

            # operators
            # = has a special role because this is the only
            # way to syntactic distinguish binding constructions
            # unfortunately, this colors the equal in {x=2} too
            (r'=(?!'+op_re+r')', Keyword),
            (r'(%s)+' % op_re, Operator),
            (r'(%s)+' % punc_re, Operator),

            # coercions
            (r':', Operator, 'type'),
            # type variables
            # we need this rule because we don't parse specially type
            # definitions so in "type t('a) = ...", "'a" is parsed by 'root'
            ("'"+ident_re, Keyword.Type),

            # id literal, #something, or #{expr}
            (r'#'+ident_re, String.Single),
            (r'#(?=\{)', String.Single),

            # identifiers
            # this avoids to color '2' in 'a2' as an integer
            (ident_re, Text),

            # default, not sure if that is needed or not
            # (r'.', Text),
        ],

        # it is quite painful to have to parse types to know where they end
        # this is the general rule for a type
        # a type is either:
        # * -> ty
        # * type-with-slash
        # * type-with-slash -> ty
        # * type-with-slash (, type-with-slash)+ -> ty
        #
        # the code is pretty funky in here, but this code would roughly
        # translate in caml to:
        # let rec type stream =
        # match stream with
        # | [< "->";  stream >] -> type stream
        # | [< "";  stream >] ->
        #   type_with_slash stream
        #   type_lhs_1 stream;
        # and type_1 stream = ...
        'type': [
            include('comments-and-spaces'),
            (r'->', Keyword.Type),
            default(('#pop', 'type-lhs-1', 'type-with-slash')),
        ],

        # parses all the atomic or closed constructions in the syntax of type
        # expressions: record types, tuple types, type constructors, basic type
        # and type variables
        'type-1': [
            include('comments-and-spaces'),
            (r'\(', Keyword.Type, ('#pop', 'type-tuple')),
            (r'~?\{', Keyword.Type, ('#pop', 'type-record')),
            (ident_re+r'\(', Keyword.Type, ('#pop', 'type-tuple')),
            (ident_re, Keyword.Type, '#pop'),
            ("'"+ident_re, Keyword.Type),
            # this case is not in the syntax but sometimes
            # we think we are parsing types when in fact we are parsing
            # some css, so we just pop the states until we get back into
            # the root state
            default('#pop'),
        ],

        # type-with-slash is either:
        # * type-1
        # * type-1 (/ type-1)+
        'type-with-slash': [
            include('comments-and-spaces'),
            default(('#pop', 'slash-type-1', 'type-1')),
        ],
        'slash-type-1': [
            include('comments-and-spaces'),
            ('/', Keyword.Type, ('#pop', 'type-1')),
            # same remark as above
            default('#pop'),
        ],

        # we go in this state after having parsed a type-with-slash
        # while trying to parse a type
        # and at this point we must determine if we are parsing an arrow
        # type (in which case we must continue parsing) or not (in which
        # case we stop)
        'type-lhs-1': [
            include('comments-and-spaces'),
            (r'->', Keyword.Type, ('#pop', 'type')),
            (r'(?=,)', Keyword.Type, ('#pop', 'type-arrow')),
            default('#pop'),
        ],
        'type-arrow': [
            include('comments-and-spaces'),
            # the look ahead here allows to parse f(x : int, y : float -> truc)
            # correctly
            (r',(?=[^:]*?->)', Keyword.Type, 'type-with-slash'),
            (r'->', Keyword.Type, ('#pop', 'type')),
            # same remark as above
            default('#pop'),
        ],

        # no need to do precise parsing for tuples and records
        # because they are closed constructions, so we can simply
        # find the closing delimiter
        # note that this function would be not work if the source
        # contained identifiers like `{)` (although it could be patched
        # to support it)
        'type-tuple': [
            include('comments-and-spaces'),
            (r'[^()/*]+', Keyword.Type),
            (r'[/*]', Keyword.Type),
            (r'\(', Keyword.Type, '#push'),
            (r'\)', Keyword.Type, '#pop'),
        ],
        'type-record': [
            include('comments-and-spaces'),
            (r'[^{}/*]+', Keyword.Type),
            (r'[/*]', Keyword.Type),
            (r'\{', Keyword.Type, '#push'),
            (r'\}', Keyword.Type, '#pop'),
        ],

        # 'type-tuple': [
        #     include('comments-and-spaces'),
        #     (r'\)', Keyword.Type, '#pop'),
        #     default(('#pop', 'type-tuple-1', 'type-1')),
        # ],
        # 'type-tuple-1': [
        #     include('comments-and-spaces'),
        #     (r',?\s*\)', Keyword.Type, '#pop'), # ,) is a valid end of tuple, in (1,)
        #     (r',', Keyword.Type, 'type-1'),
        # ],
        # 'type-record':[
        #     include('comments-and-spaces'),
        #     (r'\}', Keyword.Type, '#pop'),
        #     (r'~?(?:\w+|`[^`]*`)', Keyword.Type, 'type-record-field-expr'),
        # ],
        # 'type-record-field-expr': [
        #
        # ],

        'nested-comment': [
            (r'[^/*]+', Comment),
            (r'/\*', Comment, '#push'),
            (r'\*/', Comment, '#pop'),
            (r'[/*]', Comment),
        ],

        # the copy pasting between string and single-string
        # is kinda sad. Is there a way to avoid that??
        'string': [
            (r'[^\\"{]+', String.Double),
            (r'"', String.Double, '#pop'),
            (r'\{', Operator, 'root'),
            include('escape-sequence'),
        ],
        'single-string': [
            (r'[^\\\'{]+', String.Double),
            (r'\'', String.Double, '#pop'),
            (r'\{', Operator, 'root'),
            include('escape-sequence'),
        ],

        # all the html stuff
        # can't really reuse some existing html parser
        # because we must be able to parse embedded expressions

        # we are in this state after someone parsed the '<' that
        # started the html literal
        'html-open-tag': [
            (r'[\w\-:]+', String.Single, ('#pop', 'html-attr')),
            (r'>', String.Single, ('#pop', 'html-content')),
        ],

        # we are in this state after someone parsed the '</' that
        # started the end of the closing tag
        'html-end-tag': [
            # this is a star, because </> is allowed
            (r'[\w\-:]*>', String.Single, '#pop'),
        ],

        # we are in this state after having parsed '<ident(:ident)?'
        # we thus parse a possibly empty list of attributes
        'html-attr': [
            (r'\s+', Text),
            (r'[\w\-:]+=', String.Single, 'html-attr-value'),
            (r'/>', String.Single, '#pop'),
            (r'>', String.Single, ('#pop', 'html-content')),
        ],

        'html-attr-value': [
            (r"'", String.Single, ('#pop', 'single-string')),
            (r'"', String.Single, ('#pop', 'string')),
            (r'#'+ident_re, String.Single, '#pop'),
            (r'#(?=\{)', String.Single, ('#pop', 'root')),
            (r'[^"\'{`=<>]+', String.Single, '#pop'),
            (r'\{', Operator, ('#pop', 'root')),  # this is a tail call!
        ],

        # we should probably deal with '\' escapes here
        'html-content': [
            (r'<!--', Comment, 'html-comment'),
            (r'</', String.Single, ('#pop', 'html-end-tag')),
            (r'<', String.Single, 'html-open-tag'),
            (r'\{', Operator, 'root'),
            (r'[^<{]+', String.Single),
        ],

        'html-comment': [
            (r'-->', Comment, '#pop'),
            (r'[^\-]+|-', Comment),
        ],
    }


class ReasonLexer(RegexLexer):
    """
    For the ReasonML language (https://reasonml.github.io/).

    .. versionadded:: 2.6
    """

    name = 'ReasonML'
    aliases = ['reasonml', 'reason']
    filenames = ['*.re', '*.rei']
    mimetypes = ['text/x-reasonml']

    keywords = (
        'as', 'assert', 'begin', 'class', 'constraint', 'do', 'done', 'downto',
        'else', 'end', 'exception', 'external', 'false', 'for', 'fun', 'esfun',
        'function', 'functor', 'if', 'in', 'include', 'inherit', 'initializer', 'lazy',
        'let', 'switch', 'module', 'pub', 'mutable', 'new', 'nonrec', 'object', 'of',
        'open', 'pri', 'rec', 'sig', 'struct', 'then', 'to', 'true', 'try',
        'type', 'val', 'virtual', 'when', 'while', 'with',
    )
    keyopts = (
        '!=', '#', '&', '&&', r'\(', r'\)', r'\*', r'\+', ',', '-',
        r'-\.', '=>', r'\.', r'\.\.', r'\.\.\.', ':', '::', ':=', ':>', ';', ';;', '<',
        '<-', '=', '>', '>]', r'>\}', r'\?', r'\?\?', r'\[', r'\[<', r'\[>',
        r'\[\|', ']', '_', '`', r'\{', r'\{<', r'\|', r'\|\|', r'\|]', r'\}', '~'
    )

    operators = r'[!$%&*+\./:<=>?@^|~-]'
    word_operators = ('and', 'asr', 'land', 'lor', 'lsl', 'lsr', 'lxor', 'mod', 'or')
    prefix_syms = r'[!?~]'
    infix_syms = r'[=<>@^|&+\*/$%-]'
    primitives = ('unit', 'int', 'float', 'bool', 'string', 'char', 'list', 'array')

    tokens = {
        'escape-sequence': [
            (r'\\[\\"\'ntbr]', String.Escape),
            (r'\\[0-9]{3}', String.Escape),
            (r'\\x[0-9a-fA-F]{2}', String.Escape),
        ],
        'root': [
            (r'\s+', Text),
            (r'false|true|\(\)|\[\]', Name.Builtin.Pseudo),
            (r'\b([A-Z][\w\']*)(?=\s*\.)', Name.Namespace, 'dotted'),
            (r'\b([A-Z][\w\']*)', Name.Class),
            (r'//.*?\n', Comment.Single),
            (r'\/\*(?!/)', Comment.Multiline, 'comment'),
            (r'\b(%s)\b' % '|'.join(keywords), Keyword),
            (r'(%s)' % '|'.join(keyopts[::-1]), Operator.Word),
            (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
            (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word),
            (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),

            (r"[^\W\d][\w']*", Name),

            (r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)', Number.Float),
            (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
            (r'0[oO][0-7][0-7_]*', Number.Oct),
            (r'0[bB][01][01_]*', Number.Bin),
            (r'\d[\d_]*', Number.Integer),

            (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'",
             String.Char),
            (r"'.'", String.Char),
            (r"'", Keyword),

            (r'"', String.Double, 'string'),

            (r'[~?][a-z][\w\']*:', Name.Variable),
        ],
        'comment': [
            (r'[^/*]+', Comment.Multiline),
            (r'\/\*', Comment.Multiline, '#push'),
            (r'\*\/', Comment.Multiline, '#pop'),
            (r'\*', Comment.Multiline),
        ],
        'string': [
            (r'[^\\"]+', String.Double),
            include('escape-sequence'),
            (r'\\\n', String.Double),
            (r'"', String.Double, '#pop'),
        ],
        'dotted': [
            (r'\s+', Text),
            (r'\.', Punctuation),
            (r'[A-Z][\w\']*(?=\s*\.)', Name.Namespace),
            (r'[A-Z][\w\']*', Name.Class, '#pop'),
            (r'[a-z_][\w\']*', Name, '#pop'),
            default('#pop'),
        ],
    }


class FStarLexer(RegexLexer):
    """
    For the F* language (https://www.fstar-lang.org/).
    .. versionadded:: 2.7
    """

    name = 'FStar'
    aliases = ['fstar']
    filenames = ['*.fst', '*.fsti']
    mimetypes = ['text/x-fstar']

    keywords = (
        'abstract', 'attributes', 'noeq', 'unopteq', 'and'
        'begin', 'by', 'default', 'effect', 'else', 'end', 'ensures',
        'exception', 'exists', 'false', 'forall', 'fun', 'function', 'if',
        'in', 'include', 'inline', 'inline_for_extraction', 'irreducible',
        'logic', 'match', 'module', 'mutable', 'new', 'new_effect', 'noextract',
        'of', 'open', 'opaque', 'private', 'range_of', 'reifiable',
        'reify', 'reflectable', 'requires', 'set_range_of', 'sub_effect',
        'synth', 'then', 'total', 'true', 'try', 'type', 'unfold', 'unfoldable',
        'val', 'when', 'with', 'not'
    )
    decl_keywords = ('let', 'rec')
    assume_keywords = ('assume', 'admit', 'assert', 'calc')
    keyopts = (
        r'~', r'-', r'/\\', r'\\/', r'<:', r'<@', r'\(\|', r'\|\)', r'#', r'u#',
        r'&', r'\(', r'\)', r'\(\)', r',', r'~>', r'->', r'<-', r'<--', r'<==>',
        r'==>', r'\.', r'\?', r'\?\.', r'\.\[', r'\.\(', r'\.\(\|', r'\.\[\|',
        r'\{:pattern', r':', r'::', r':=', r';', r';;', r'=', r'%\[', r'!\{',
        r'\[', r'\[@', r'\[\|', r'\|>', r'\]', r'\|\]', r'\{', r'\|', r'\}', r'\$'
    )

    operators = r'[!$%&*+\./:<=>?@^|~-]'
    prefix_syms = r'[!?~]'
    infix_syms = r'[=<>@^|&+\*/$%-]'
    primitives = ('unit', 'int', 'float', 'bool', 'string', 'char', 'list', 'array')

    tokens = {
        'escape-sequence': [
            (r'\\[\\"\'ntbr]', String.Escape),
            (r'\\[0-9]{3}', String.Escape),
            (r'\\x[0-9a-fA-F]{2}', String.Escape),
        ],
        'root': [
            (r'\s+', Text),
            (r'false|true|False|True|\(\)|\[\]', Name.Builtin.Pseudo),
            (r'\b([A-Z][\w\']*)(?=\s*\.)', Name.Namespace, 'dotted'),
            (r'\b([A-Z][\w\']*)', Name.Class),
            (r'\(\*(?![)])', Comment, 'comment'),
            (r'^\/\/.+$', Comment),
            (r'\b(%s)\b' % '|'.join(keywords), Keyword),
            (r'\b(%s)\b' % '|'.join(assume_keywords), Name.Exception),
            (r'\b(%s)\b' % '|'.join(decl_keywords), Keyword.Declaration),
            (r'(%s)' % '|'.join(keyopts[::-1]), Operator),
            (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
            (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),

            (r"[^\W\d][\w']*", Name),

            (r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)', Number.Float),
            (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
            (r'0[oO][0-7][0-7_]*', Number.Oct),
            (r'0[bB][01][01_]*', Number.Bin),
            (r'\d[\d_]*', Number.Integer),

            (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'",
             String.Char),
            (r"'.'", String.Char),
            (r"'", Keyword),  # a stray quote is another syntax element
            (r"\`([\w\'.]+)\`", Operator.Word),  # for infix applications
            (r"\`", Keyword),  # for quoting
            (r'"', String.Double, 'string'),

            (r'[~?][a-z][\w\']*:', Name.Variable),
        ],
        'comment': [
            (r'[^(*)]+', Comment),
            (r'\(\*', Comment, '#push'),
            (r'\*\)', Comment, '#pop'),
            (r'[(*)]', Comment),
        ],
        'string': [
            (r'[^\\"]+', String.Double),
            include('escape-sequence'),
            (r'\\\n', String.Double),
            (r'"', String.Double, '#pop'),
        ],
        'dotted': [
            (r'\s+', Text),
            (r'\.', Punctuation),
            (r'[A-Z][\w\']*(?=\s*\.)', Name.Namespace),
            (r'[A-Z][\w\']*', Name.Class, '#pop'),
            (r'[a-z_][\w\']*', Name, '#pop'),
            default('#pop'),
        ],
    }