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
"""
    pygments.lexers.csound
    ~~~~~~~~~~~~~~~~~~~~~~

    Lexers for Csound languages.

    :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pygments.lexer import RegexLexer, bygroups, default, include, using, words
from pygments.token import Comment, Error, Keyword, Name, Number, Operator, Punctuation, \
    String, Text, Whitespace
from pygments.lexers._csound_builtins import OPCODES, DEPRECATED_OPCODES, REMOVED_OPCODES
from pygments.lexers.html import HtmlLexer
from pygments.lexers.python import PythonLexer
from pygments.lexers.scripting import LuaLexer

__all__ = ['CsoundScoreLexer', 'CsoundOrchestraLexer', 'CsoundDocumentLexer']

newline = (r'((?:(?:;|//).*)*)(\n)', bygroups(Comment.Single, Text))


class CsoundLexer(RegexLexer):
    url = 'https://csound.com/'

    tokens = {
        'whitespace': [
            (r'[ \t]+', Whitespace),
            (r'/[*](?:.|\n)*?[*]/', Comment.Multiline),
            (r'(?:;|//).*$', Comment.Single),
            (r'(\\)(\n)', bygroups(Text, Whitespace))
        ],

        'preprocessor directives': [
            (r'#(?:e(?:nd(?:if)?|lse)\b|##)|@@?[ \t]*\d+', Comment.Preproc),
            (r'#includestr', Comment.Preproc, 'includestr directive'),
            (r'#include', Comment.Preproc, 'include directive'),
            (r'#[ \t]*define', Comment.Preproc, 'define directive'),
            (r'#(?:ifn?def|undef)\b', Comment.Preproc, 'macro directive')
        ],

        'include directive': [
            include('whitespace'),
            (r'([^ \t]).*?\1', String, '#pop')
        ],
        'includestr directive': [
            include('whitespace'),
            (r'"', String, ('#pop', 'quoted string'))
        ],

        'define directive': [
            (r'\n', Whitespace),
            include('whitespace'),
            (r'([A-Z_a-z]\w*)(\()', bygroups(Comment.Preproc, Punctuation),
             ('#pop', 'macro parameter name list')),
            (r'[A-Z_a-z]\w*', Comment.Preproc, ('#pop', 'before macro body'))
        ],
        'macro parameter name list': [
            include('whitespace'),
            (r'[A-Z_a-z]\w*', Comment.Preproc),
            (r"['#]", Punctuation),
            (r'\)', Punctuation, ('#pop', 'before macro body'))
        ],
        'before macro body': [
            (r'\n', Whitespace),
            include('whitespace'),
            (r'#', Punctuation, ('#pop', 'macro body'))
        ],
        'macro body': [
            (r'(?:\\(?!#)|[^#\\]|\n)+', Comment.Preproc),
            (r'\\#', Comment.Preproc),
            (r'(?<!\\)#', Punctuation, '#pop')
        ],

        'macro directive': [
            include('whitespace'),
            (r'[A-Z_a-z]\w*', Comment.Preproc, '#pop')
        ],

        'macro uses': [
            (r'(\$[A-Z_a-z]\w*\.?)(\()', bygroups(Comment.Preproc, Punctuation),
             'macro parameter value list'),
            (r'\$[A-Z_a-z]\w*(?:\.|\b)', Comment.Preproc)
        ],
        'macro parameter value list': [
            (r'(?:[^\'#"{()]|\{(?!\{))+', Comment.Preproc),
            (r"['#]", Punctuation),
            (r'"', String, 'macro parameter value quoted string'),
            (r'\{\{', String, 'macro parameter value braced string'),
            (r'\(', Comment.Preproc, 'macro parameter value parenthetical'),
            (r'\)', Punctuation, '#pop')
        ],
        'macro parameter value quoted string': [
            (r"\\[#'()]", Comment.Preproc),
            (r"[#'()]", Error),
            include('quoted string')
        ],
        'macro parameter value braced string': [
            (r"\\[#'()]", Comment.Preproc),
            (r"[#'()]", Error),
            include('braced string')
        ],
        'macro parameter value parenthetical': [
            (r'(?:[^\\()]|\\\))+', Comment.Preproc),
            (r'\(', Comment.Preproc, '#push'),
            (r'\)', Comment.Preproc, '#pop')
        ],

        'whitespace and macro uses': [
            include('whitespace'),
            include('macro uses')
        ],

        'numbers': [
            (r'\d+[Ee][+-]?\d+|(\d+\.\d*|\d*\.\d+)([Ee][+-]?\d+)?', Number.Float),
            (r'(0[Xx])([0-9A-Fa-f]+)', bygroups(Keyword.Type, Number.Hex)),
            (r'\d+', Number.Integer)
        ],

        'quoted string': [
            (r'"', String, '#pop'),
            (r'[^"$]+', String),
            include('macro uses'),
            (r'[$]', String)
        ],

        'braced string': [
            # Do nothing. This must be defined in subclasses.
        ]
    }


class CsoundScoreLexer(CsoundLexer):
    """
    For `Csound <https://csound.com>`_ scores.

    .. versionadded:: 2.1
    """

    name = 'Csound Score'
    aliases = ['csound-score', 'csound-sco']
    filenames = ['*.sco']

    tokens = {
        'root': [
            (r'\n', Whitespace),
            include('whitespace and macro uses'),
            include('preprocessor directives'),

            (r'[aBbCdefiqstvxy]', Keyword),
            # There is also a w statement that is generated internally and should not be
            # used; see https://github.com/csound/csound/issues/750.

            (r'z', Keyword.Constant),
            # z is a constant equal to 800,000,000,000. 800 billion seconds is about
            # 25,367.8 years. See also
            # https://csound.com/docs/manual/ScoreTop.html and
            # https://github.com/csound/csound/search?q=stof+path%3AEngine+filename%3Asread.c.

            (r'([nNpP][pP])(\d+)', bygroups(Keyword, Number.Integer)),

            (r'[mn]', Keyword, 'mark statement'),

            include('numbers'),
            (r'[!+\-*/^%&|<>#~.]', Operator),
            (r'[()\[\]]', Punctuation),
            (r'"', String, 'quoted string'),
            (r'\{', Comment.Preproc, 'loop after left brace'),
        ],

        'mark statement': [
            include('whitespace and macro uses'),
            (r'[A-Z_a-z]\w*', Name.Label),
            (r'\n', Whitespace, '#pop')
        ],

        'loop after left brace': [
            include('whitespace and macro uses'),
            (r'\d+', Number.Integer, ('#pop', 'loop after repeat count')),
        ],
        'loop after repeat count': [
            include('whitespace and macro uses'),
            (r'[A-Z_a-z]\w*', Comment.Preproc, ('#pop', 'loop'))
        ],
        'loop': [
            (r'\}', Comment.Preproc, '#pop'),
            include('root')
        ],

        # Braced strings are not allowed in Csound scores, but this is needed because the
        # superclass includes it.
        'braced string': [
            (r'\}\}', String, '#pop'),
            (r'[^}]|\}(?!\})', String)
        ]
    }


class CsoundOrchestraLexer(CsoundLexer):
    """
    For `Csound <https://csound.com>`_ orchestras.

    .. versionadded:: 2.1
    """

    name = 'Csound Orchestra'
    aliases = ['csound', 'csound-orc']
    filenames = ['*.orc', '*.udo']

    user_defined_opcodes = set()

    def opcode_name_callback(lexer, match):
        opcode = match.group(0)
        lexer.user_defined_opcodes.add(opcode)
        yield match.start(), Name.Function, opcode

    def name_callback(lexer, match):
        type_annotation_token = Keyword.Type

        name = match.group(1)
        if name in OPCODES or name in DEPRECATED_OPCODES or name in REMOVED_OPCODES:
            yield match.start(), Name.Builtin, name
        elif name in lexer.user_defined_opcodes:
            yield match.start(), Name.Function, name
        else:
            type_annotation_token = Name
            name_match = re.search(r'^(g?[afikSw])(\w+)', name)
            if name_match:
                yield name_match.start(1), Keyword.Type, name_match.group(1)
                yield name_match.start(2), Name, name_match.group(2)
            else:
                yield match.start(), Name, name

        if match.group(2):
            yield match.start(2), Punctuation, match.group(2)
            yield match.start(3), type_annotation_token, match.group(3)

    tokens = {
        'root': [
            (r'\n', Whitespace),

            (r'^([ \t]*)(\w+)(:)([ \t]+|$)', bygroups(Whitespace, Name.Label, Punctuation, Whitespace)),

            include('whitespace and macro uses'),
            include('preprocessor directives'),

            (r'\binstr\b', Keyword.Declaration, 'instrument numbers and identifiers'),
            (r'\bopcode\b', Keyword.Declaration, 'after opcode keyword'),
            (r'\b(?:end(?:in|op))\b', Keyword.Declaration),

            include('partial statements')
        ],

        'partial statements': [
            (r'\b(?:0dbfs|A4|k(?:r|smps)|nchnls(?:_i)?|sr)\b', Name.Variable.Global),

            include('numbers'),

            (r'\+=|-=|\*=|/=|<<|>>|<=|>=|==|!=|&&|\|\||[~¬]|[=!+\-*/^%&|<>#?:]', Operator),
            (r'[(),\[\]]', Punctuation),

            (r'"', String, 'quoted string'),
            (r'\{\{', String, 'braced string'),

            (words((
                'do', 'else', 'elseif', 'endif', 'enduntil', 'fi', 'if', 'ithen', 'kthen',
                'od', 'then', 'until', 'while',
                ), prefix=r'\b', suffix=r'\b'), Keyword),
            (words(('return', 'rireturn'), prefix=r'\b', suffix=r'\b'), Keyword.Pseudo),

            (r'\b[ik]?goto\b', Keyword, 'goto label'),
            (r'\b(r(?:einit|igoto)|tigoto)(\(|\b)', bygroups(Keyword.Pseudo, Punctuation),
             'goto label'),
            (r'\b(c(?:g|in?|k|nk?)goto)(\(|\b)', bygroups(Keyword.Pseudo, Punctuation),
             ('goto label', 'goto argument')),
            (r'\b(timout)(\(|\b)', bygroups(Keyword.Pseudo, Punctuation),
             ('goto label', 'goto argument', 'goto argument')),
            (r'\b(loop_[gl][et])(\(|\b)', bygroups(Keyword.Pseudo, Punctuation),
             ('goto label', 'goto argument', 'goto argument', 'goto argument')),

            (r'\bprintk?s\b', Name.Builtin, 'prints opcode'),
            (r'\b(?:readscore|scoreline(?:_i)?)\b', Name.Builtin, 'Csound score opcode'),
            (r'\bpyl?run[it]?\b', Name.Builtin, 'Python opcode'),
            (r'\blua_(?:exec|opdef)\b', Name.Builtin, 'Lua opcode'),
            (r'\bp\d+\b', Name.Variable.Instance),
            (r'\b([A-Z_a-z]\w*)(?:(:)([A-Za-z]))?\b', name_callback)
        ],

        'instrument numbers and identifiers': [
            include('whitespace and macro uses'),
            (r'\d+|[A-Z_a-z]\w*', Name.Function),
            (r'[+,]', Punctuation),
            (r'\n', Whitespace, '#pop')
        ],

        'after opcode keyword': [
            include('whitespace and macro uses'),
            (r'[A-Z_a-z]\w*', opcode_name_callback, ('#pop', 'opcode type signatures')),
            (r'\n', Whitespace, '#pop')
        ],
        'opcode type signatures': [
            include('whitespace and macro uses'),

            # https://github.com/csound/csound/search?q=XIDENT+path%3AEngine+filename%3Acsound_orc.lex
            (r'0|[afijkKoOpPStV\[\]]+', Keyword.Type),

            (r',', Punctuation),
            (r'\n', Whitespace, '#pop')
        ],

        'quoted string': [
            (r'"', String, '#pop'),
            (r'[^\\"$%)]+', String),
            include('macro uses'),
            include('escape sequences'),
            include('format specifiers'),
            (r'[\\$%)]', String)
        ],
        'braced string': [
            (r'\}\}', String, '#pop'),
            (r'(?:[^\\%)}]|\}(?!\}))+', String),
            include('escape sequences'),
            include('format specifiers'),
            (r'[\\%)]', String)
        ],
        'escape sequences': [
            # https://github.com/csound/csound/search?q=unquote_string+path%3AEngine+filename%3Acsound_orc_compile.c
            (r'\\(?:[\\abnrt"]|[0-7]{1,3})', String.Escape)
        ],
        # Format specifiers are highlighted in all strings, even though only
        #   fprintks        https://csound.com/docs/manual/fprintks.html
        #   fprints         https://csound.com/docs/manual/fprints.html
        #   printf/printf_i https://csound.com/docs/manual/printf.html
        #   printks         https://csound.com/docs/manual/printks.html
        #   prints          https://csound.com/docs/manual/prints.html
        #   sprintf         https://csound.com/docs/manual/sprintf.html
        #   sprintfk        https://csound.com/docs/manual/sprintfk.html
        # work with strings that contain format specifiers. In addition, these opcodes’
        # handling of format specifiers is inconsistent:
        #   - fprintks and fprints accept %a and %A specifiers, and accept %s specifiers
        #     starting in Csound 6.15.0.
        #   - printks and prints accept %a and %A specifiers, but don’t accept %s
        #     specifiers.
        #   - printf, printf_i, sprintf, and sprintfk don’t accept %a and %A specifiers,
        #     but accept %s specifiers.
        # See https://github.com/csound/csound/issues/747 for more information.
        'format specifiers': [
            (r'%[#0\- +]*\d*(?:\.\d+)?[AE-GXac-giosux]', String.Interpol),
            (r'%%', String.Escape)
        ],

        'goto argument': [
            include('whitespace and macro uses'),
            (r',', Punctuation, '#pop'),
            include('partial statements')
        ],
        'goto label': [
            include('whitespace and macro uses'),
            (r'\w+', Name.Label, '#pop'),
            default('#pop')
        ],

        'prints opcode': [
            include('whitespace and macro uses'),
            (r'"', String, 'prints quoted string'),
            default('#pop')
        ],
        'prints quoted string': [
            (r'\\\\[aAbBnNrRtT]', String.Escape),
            (r'%[!nNrRtT]|[~^]{1,2}', String.Escape),
            include('quoted string')
        ],

        'Csound score opcode': [
            include('whitespace and macro uses'),
            (r'"', String, 'quoted string'),
            (r'\{\{', String, 'Csound score'),
            (r'\n', Whitespace, '#pop')
        ],
        'Csound score': [
            (r'\}\}', String, '#pop'),
            (r'([^}]+)|\}(?!\})', using(CsoundScoreLexer))
        ],

        'Python opcode': [
            include('whitespace and macro uses'),
            (r'"', String, 'quoted string'),
            (r'\{\{', String, 'Python'),
            (r'\n', Whitespace, '#pop')
        ],
        'Python': [
            (r'\}\}', String, '#pop'),
            (r'([^}]+)|\}(?!\})', using(PythonLexer))
        ],

        'Lua opcode': [
            include('whitespace and macro uses'),
            (r'"', String, 'quoted string'),
            (r'\{\{', String, 'Lua'),
            (r'\n', Whitespace, '#pop')
        ],
        'Lua': [
            (r'\}\}', String, '#pop'),
            (r'([^}]+)|\}(?!\})', using(LuaLexer))
        ]
    }


class CsoundDocumentLexer(RegexLexer):
    """
    For `Csound <https://csound.com>`_ documents.

    .. versionadded:: 2.1
    """

    name = 'Csound Document'
    aliases = ['csound-document', 'csound-csd']
    filenames = ['*.csd']

    # These tokens are based on those in XmlLexer in pygments/lexers/html.py. Making
    # CsoundDocumentLexer a subclass of XmlLexer rather than RegexLexer may seem like a
    # better idea, since Csound Document files look like XML files. However, Csound
    # Documents can contain Csound comments (preceded by //, for example) before and
    # after the root element, unescaped bitwise AND & and less than < operators, etc. In
    # other words, while Csound Document files look like XML files, they may not actually
    # be XML files.
    tokens = {
        'root': [
            (r'/[*](.|\n)*?[*]/', Comment.Multiline),
            (r'(?:;|//).*$', Comment.Single),
            (r'[^/;<]+|/(?!/)', Text),

            (r'<\s*CsInstruments', Name.Tag, ('orchestra', 'tag')),
            (r'<\s*CsScore', Name.Tag, ('score', 'tag')),
            (r'<\s*[Hh][Tt][Mm][Ll]', Name.Tag, ('HTML', 'tag')),

            (r'<\s*[\w:.-]+', Name.Tag, 'tag'),
            (r'<\s*/\s*[\w:.-]+\s*>', Name.Tag)
        ],

        'orchestra': [
            (r'<\s*/\s*CsInstruments\s*>', Name.Tag, '#pop'),
            (r'(.|\n)+?(?=<\s*/\s*CsInstruments\s*>)', using(CsoundOrchestraLexer))
        ],
        'score': [
            (r'<\s*/\s*CsScore\s*>', Name.Tag, '#pop'),
            (r'(.|\n)+?(?=<\s*/\s*CsScore\s*>)', using(CsoundScoreLexer))
        ],
        'HTML': [
            (r'<\s*/\s*[Hh][Tt][Mm][Ll]\s*>', Name.Tag, '#pop'),
            (r'(.|\n)+?(?=<\s*/\s*[Hh][Tt][Mm][Ll]\s*>)', using(HtmlLexer))
        ],

        'tag': [
            (r'\s+', Whitespace),
            (r'[\w.:-]+\s*=', Name.Attribute, 'attr'),
            (r'/?\s*>', Name.Tag, '#pop')
        ],
        'attr': [
            (r'\s+', Whitespace),
            (r'".*?"', String, '#pop'),
            (r"'.*?'", String, '#pop'),
            (r'[^\s>]+', String, '#pop')
        ]
    }