-
Notifications
You must be signed in to change notification settings - Fork 131
/
Grammar.nqp
499 lines (437 loc) · 15.8 KB
/
Grammar.nqp
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
use QRegex;
use NQPHLL;
use QAST;
class QRegex::P6Regex::World is HLL::World {
method create_code($ast, $name) {
# Create a fresh stub code, and set its name.
my $dummy := nqp::freshcoderef(-> { nqp::die("Uncompiled code executed") });
nqp::setcodename($dummy, $name);
# Tag it as a static code ref and add it to the root code refs set.
nqp::markcodestatic($dummy);
self.add_root_code_ref($dummy, $ast);
# Create code object.
my $code_obj := nqp::create(NQPRegex);
nqp::bindattr($code_obj, NQPRegex, '$!do', $dummy);
my $slot := self.add_object($code_obj);
# Add fixup of the code object and the $!do attribute.
my $fixups := QAST::Stmt.new();
$fixups.push(QAST::Op.new(
:op('bindattr'),
QAST::WVal.new( :value($code_obj) ),
QAST::WVal.new( :value(NQPRegex) ),
QAST::SVal.new( :value('$!do') ),
QAST::BVal.new( :value($ast) )
));
$fixups.push(QAST::Op.new(
:op('setcodeobj'),
QAST::BVal.new( :value($ast) ),
QAST::WVal.new( :value($code_obj) )
));
self.add_fixup_task(:fixup_ast($fixups));
$code_obj
}
}
grammar QRegex::P6Regex::Grammar is HLL::Grammar {
method obs ($old, $new, $when = ' in Perl 6') {
self.panic('Unsupported use of ' ~ ~$old ~ ';'
~ ~$when ~ ' please use ' ~ ~$new);
}
# errors are reported through methods, so that subclasses like Rakudo's
# Perl6::RegexGrammar can override them, and throw language-specific
# exceptions
method throw_unrecognized_metachar ($char) {
self.panic('Unrecognized regex metacharacter ' ~ $char ~ ' (must be quoted to match literally)');
}
method throw_malformed_range() {
self.panic('Malformed range.');
}
method throw_confused() {
self.panic('Confused.');
}
method throw_unspace($char) {
self.panic: "No unspace allowed in regex; " ~
" if you meant to match the literal character," ~
" please enclose in single quotes ('"
~ $char ~ "') or use a backslashed form like \\x"
~ nqp::sprintf('%02x', [nqp::ord($char)]);
}
method throw_regex_not_terminated() {
self.panic('Regex not terminated.');
}
method throw_spaces_in_bare_range() {
self.panic('Spaces not allowed in bare range.');
}
method throw_unecessary_upto_inf() {
self.panic('Unecessary use of "** ^*" quantifier. Did you mean to use the "*" quantifier');
}
method throw_solitary_quantifier() {
self.panic('Quantifier quantifies nothing.');
}
method throw_non_quantifiable() {
self.panic('Can only quantify a construct that produces a match');
}
method throw_solitary_backtrack_control() {
self.panic("Backtrack control ':' does not seem to have a preceding atom to control");
}
method throw_null_pattern() {
self.panic('Null regex not allowed');
}
method worry(*@args) {
note(nqp::join('', @args) ~ "\n");
}
token ws { [ \s | '#' \N* ]* }
token normspace { <?[\s#]> <.ws> }
token identifier { <.ident> [ <[\-']> <.ident> ]* }
token arg {
[
| <?[']> <quote_EXPR: ':q'>
| <?["]> <quote_EXPR: ':qq'>
| $<val>=[\d+]
]
}
rule arglist { '' <arg> +% [',' ] }
my $cur_handle := 0;
token TOP {
:my %*RX;
:my $handle := '__QREGEX_P6REGEX__' ~ $cur_handle++;
:my $*W := QRegex::P6Regex::World.new(:$handle);
<nibbler>
[ $ || <.throw_confused> ]
}
token nibbler {
:my $OLDRX := nqp::getlexdyn('%*RX');
:my %*RX;
:my $*SEQ := 0;
{
for $OLDRX { %*RX{$_.key} := $_.value; }
}
<.ws>
<termseq>
[
|| <?infixstopper>
|| $$ <.throw_regex_not_terminated>
|| (\W) { self.throw_unrecognized_metachar: ~$/[0] }
|| <.throw_regex_not_terminated>
]
}
regex infixstopper {
:dba('infix stopper')
[
| <?before <.[\) \} \]]> >
| <?before '>' <.-[>]> >
| <?rxstopper>
]
}
token rxstopper { $ }
# XXX Eventually squish termseq and termish and
# get < || && | & > infixes using by EXPR in nibbler
token termseq {
<termaltseq>
}
token termaltseq {
[ <!rxstopper> '||' { $*SEQ := 1; } <.ws> ]?
<termconjseq>
[ <!infixstopper> '||' <.ws> { $*SEQ := 1; } <termconjseq> ]*
}
token termconjseq {
[ <!rxstopper> '&&' { $*SEQ := 0; } <.ws> ]?
<termalt>
[ <!infixstopper> '&&' <.ws> { $*SEQ := 0; } <termalt> ]*
}
token termalt {
[ <!rxstopper> '|' <.ws> ]?
<termconj>
[ <!infixstopper> '|' <![|]> <.ws> { $*SEQ := 0; } <termconj> ]*
}
token termconj {
[ <!rxstopper> '&' <.ws> ]?
<termish>
[ <!infixstopper> '&' <![&]> <.ws> { $*SEQ := 0; } <termish> ]*
}
token termish {
:my $*SIGOK := 0;
:my $*VARDEF := 0;
[
|| <noun=.quantified_atom>+
|| <?before <.rxstopper> | <.[&|~]> > <.throw_null_pattern>
|| <?before <.infixstopper> > <.throw_null_pattern> # XXX Check if unmatched bracket
|| $$ <.throw_regex_not_terminated>
|| (\W) { self.throw_unrecognized_metachar: ~$/[0] }
|| <.throw_regex_not_terminated>
]
}
method SIGOK() { $*SIGOK := %*RX<s>; self }
token quantified_atom {
<!rxstopper>
<atom>
[
|| <sigmaybe>?
[
| <!rxstopper> <quantifier>
| <?[:]> <backmod> <!alnum>
]
[ <!{$*VARDEF}> <.SIGOK> <sigfinal=.sigmaybe> ]?
[ <.ws> <separator> ]?
|| [ <!{$*VARDEF}> <sigfinal=.sigmaybe> ]?
]
{ $*SIGOK := 0 }
}
rule separator {
$<septype>=['%''%'?]
:my $*VARDEF := 0;
:my $*SIGOK := 0;
<quantified_atom>
}
token atom {
# :dba('regex atom')
[
| \w
[ <?before ' ' \w <!before <.quantifier>> > <!{ %*RX<s> || $*HAS_GOAL }> <.worry("Space is not significant here; please use quotes or :s (:sigspace) modifier (or, to suppress this warning, omit the space, or otherwise change the spacing)")> ]?
<.SIGOK>
| <metachar>
]
}
proto token sigmaybe { <...> }
token sigmaybe:sym<normspace> {
<!{$*SIGOK}> <normspace>
}
token sigmaybe:sym<sigwhite> {
<?{$*SIGOK}> <normspace>
}
proto token quantifier { <...> }
token quantifier:sym<%> {
('%''%'?) {
$/.panic("Missing quantifier on the left argument of " ~ $/[0]);
}
}
token quantifier:sym<*> { <sym> <backmod> }
token quantifier:sym<+> { <sym> <backmod> }
token quantifier:sym<?> { <sym> <backmod> }
token quantifier:sym<{N,M}> { {} '{' (\d+) (','?) (\d*) '}'
<.obs: '{N,M} as general quantifier', '** N..M (or ** N..*)'>
}
token quantifier:sym<**> {
# 10 | 1..10 | 1^..10 | 1^..^10 | 1..^10 | ^10 | 1..* | 1^..*
<sym> <.normspace>? <backmod> <.normspace>?
[
| <min=.integer> \s+ '..' <.throw_spaces_in_bare_range>
| '^' '*' <.throw_unecessary_upto_inf>
| $<upto>='^' <max=.integer>
| [
| <min=.integer>
[
[
| $<from>='^' [ '..' | <.throw_malformed_range> ]
| '..'
]
[
| $<upto>='^'? <max=.integer> {
$/.panic("Negative numbers are not allowed as quantifiers") if nqp::radix(10, $<max>, 0, 0)[0] < 0;
}
| $<max>=['*']
| <.throw_malformed_range>
]
]?
]
{ $/.panic("Negative numbers are not allowed as quantifiers") if nqp::radix(10, $<min>, 0, 0)[0] < 0 }
| <?[{]> <codeblock>
]
}
token codeblock {
<block=.LANG('MAIN','pblock')>
}
token backmod { ':'? [ '?' | '!' | <!before ':'> ] }
proto token metachar { <...> }
token metachar:sym<[ ]> { '[' ~ ']' <nibbler> <.SIGOK> }
token metachar:sym<( )> { '(' ~ ')' <nibbler> <.SIGOK> }
token metachar:sym<'> { <?['‘‚]> <quote_EXPR: ':q'> <.SIGOK> }
token metachar:sym<"> { <?["“„]> <quote_EXPR: ':qq'> <.SIGOK> }
token metachar:sym<.> { <sym> <.SIGOK> }
token metachar:sym<^> { <sym> <.SIGOK> }
token metachar:sym<^^> { <sym> <.SIGOK> }
token metachar:sym<$> { <sym> <.SIGOK> }
token metachar:sym<$$> { <sym> <.SIGOK> }
token metachar:sym<:::> { <sym> <.panic: '::: not yet implemented'> }
token metachar:sym<::> { <sym> <.panic: ':: not yet implemented'> }
token metachar:sym<lwb> { $<sym>=['<<'|'«'] <.SIGOK> }
token metachar:sym<rwb> { $<sym>=['>>'|'»'] <.SIGOK> }
token metachar:sym<from> { '<(' <.SIGOK> }
token metachar:sym<to> { ')>' <.SIGOK> }
token metachar:sym<bs> { \\ <backslash> <.SIGOK> }
token metachar:sym<mod> { <mod_internal> }
token metachar:sym<quantifier> {
<!rxstopper> <quantifier> <.throw_solitary_quantifier>
}
## we cheat here, really should be regex_infix:sym<~>
token metachar:sym<~> {
:my $*HAS_GOAL := 1;
<sym>
<.ws> <GOAL=.quantified_atom>
<.ws> <EXPR=.quantified_atom>
}
token metachar:sym<{*}> {
<sym>
[ \h* '#= ' \h* $<key>=[\S+ [\h+ \S+]*] ]**0..1
}
token metachar:sym<assert> {
'<' ~ '>' <assertion> <.SIGOK>
}
token sigil { <[$@%&]> }
token metachar:sym<var> {
[
| $<wantarray>=['@'] '<' $<name>=[<-[>]>+] '>'
| '$<' $<name>=[<-[>]>+] '>'
| '$' $<pos>=[\d+]
]
[
<.ws> '=' <.ws>
{ $*VARDEF := 1 }
<quantified_atom>
{ $*VARDEF := 0 }
]**0..1
<.SIGOK>
}
token metachar:sym<:> {
<sym> <?before \s> <.throw_solitary_backtrack_control>
}
proto token backslash { <...> }
token backslash:sym<s> { $<sym>=[<[dDnNsSwW]>] }
token backslash:sym<e> { $<sym>=[<[eE]>] }
token backslash:sym<f> { $<sym>=[<[fF]>] }
token backslash:sym<h> { $<sym>=[<[hH]>] }
token backslash:sym<r> { $<sym>=[<[rR]>] }
token backslash:sym<t> { $<sym>=[<[tT]>] }
token backslash:sym<v> { $<sym>=[<[vV]>] }
token backslash:sym<o> { $<sym>=[<[oO]>] [ <octint> | '[' <octints> ']' ] }
token backslash:sym<x> { $<sym>=[<[xX]>] [ <hexint> | '[' <hexints> ']' ] }
token backslash:sym<c> { $<sym>=[<[cC]>] <charspec> }
token backslash:sym<0> { $<sym>=['0'] }
token backslash:sym<B> { 'B' <.obs:
'\\B', '<!|w> for negated word boundary. If you meant a negated'
~ ' backspace character, use it in a negated character class (<-[\b]>).'
>}
token backslash:sym<b> { 'b' <.obs:
'\\b', '<|w> for word boundary (or « and » for left/right boundaries).'
~ ' If you meant the backspace character, quote it ("\b") or use it as'
~ ' inside a character class (<[\b]>)'
>}
token backslash:sym<K> { 'K' <.obs:
'\\K', '<( for discarding text before the capture marker or )> for discarding text after.'
>}
token backslash:sym<A> { 'A' <.obs: '\\A as beginning-of-string matcher', '^'> }
token backslash:sym<z> { 'z' <.obs: '\\z as end-of-string matcher', '$'> }
token backslash:sym<Z> { 'Z' <.obs: '\\Z as end-of-string matcher', '\\n?$'> }
token backslash:sym<Q> { 'Q' <.obs: '\\Q as quotemeta', 'quotes or literal variable match'> }
token backslash:sym<unrec> { {} (\w) { self.throw_unrecog_backslash_seq: $/[0].Str } }
token backslash:sym<unsp> {
\s {}
<.throw_unspace(~$/)>
}
token backslash:sym<misc> { \W }
proto token cclass_backslash { <...> }
token cclass_backslash:sym<s> { $<sym>=[<[dDnNsSwW]>] }
token cclass_backslash:sym<b> { $<sym>=[<[bB]>] }
token cclass_backslash:sym<e> { $<sym>=[<[eE]>] }
token cclass_backslash:sym<f> { $<sym>=[<[fF]>] }
token cclass_backslash:sym<h> { $<sym>=[<[hH]>] }
token cclass_backslash:sym<n> { $<sym>=[<[nN]>] }
token cclass_backslash:sym<r> { $<sym>=[<[rR]>] }
token cclass_backslash:sym<t> { $<sym>=[<[tT]>] }
token cclass_backslash:sym<v> { $<sym>=[<[vV]>] }
token cclass_backslash:sym<o> { $<sym>=[<[oO]>] [ <octint> | '[' <octints> ']' ] }
token cclass_backslash:sym<x> { $<sym>=[<[xX]>] [ <hexint> | '[' <hexints> ']' ] }
token cclass_backslash:sym<c> { $<sym>=[<[cC]>] <charspec> }
token cclass_backslash:sym<0> { $<sym>=['0'] }
token cclass_backslash:sym<any> { . }
proto token assertion { <...> }
token assertion:sym<?> { '?' [ <?before '>' > | <assertion> ] }
token assertion:sym<!> { '!' [ <?before '>' > | <assertion> ] }
token assertion:sym<|> { '|' <identifier> }
token assertion:sym<method> {
'.' <assertion>
}
token assertion:sym<name> {
<longname=.identifier>
[
| <?before '>'>
| '=' <assertion>
| ':' <arglist>
| '(' <arglist> ')'
| <.normspace> <nibbler>
]?
}
token assertion:sym<[> { <?before '['|'+'|'-'|':'> <cclass_elem>+ }
token cclass_elem {
:my $*key;
$<sign>=['+'|'-'|<?>]
<.normspace>?
[
| '[' $<charspec>=(
|| [ <!after '[' > \s* '-' <!before \s* ']'> ] <.obs: '- as character range','.. for range, for explicit - in character class, escape it or place it as the first or last thing'>
|| \s* ( '\\' <cclass_backslash> || (<-[\]\\]>) )
[
\s* '..' \s*
( '\\' <cclass_backslash> || (<-[\]\\]>) )
]**0..1
)*
{
my %seen;
for $<charspec> {
%seen{$_[0][0]} := (%seen{$_[0][0]} // 0) + 1 if nqp::defined($_[0][0]);
%seen{$_[1][0]} := (%seen{$_[1][0]} // 0) + 1 if nqp::defined($_[1][0]);
}
for %seen {
next if $_.value < 2;
self.worry("Quotes are not metacharacters in character classes") if $_.key eq '"' || $_.key eq "'";
self.worry("Repeated character (" ~ $_.key ~ ") unexpectedly found in character class");
}
}
\s* ']'
| $<name>=<identifier>
| ':' $<invert>=['!'|<?>] <identifier> { $*key := $<identifier>.Str }
[
|| <coloncircumfix=.LANG('MAIN','coloncircumfix', $*key)>
|| <?>
]
]
<.normspace>?
}
token mod_internal {
':'
[
| <?before '!'> $<n>=('!')**1 <mod_ident> »
| <?before \d> $<n>=(\d+)**1 <mod_ident> »
| <mod_ident>
[
'('
[
| $<n>=[\d+]
| <?[']> <quote_EXPR: ':q'>
| <?["]> <quote_EXPR: ':qq'>
]
')'
]**0..1
]
{
if !$<quote_EXPR> {
my $n := $<n>[0] gt '' ?? ($<n>[0] eq '!' ?? 0 !! +$<n>[0]) !! 1;
%*RX{ ~$<mod_ident><sym> } := $n;
}
}
}
proto token mod_ident { <...> }
token mod_ident:sym<ignorecase> { $<sym>=[i] 'gnorecase'? » }
token mod_ident:sym<ignoremark> {
[
| $<sym>=[m]
| 'ignore' $<sym>=[m] 'ark'
] »
}
token mod_ident:sym<ratchet> { $<sym>=[r] 'atchet'? » }
token mod_ident:sym<sigspace> { $<sym>=[s] 'igspace'? » }
token mod_ident:sym<dba> { <sym> » }
token mod_ident:sym<oops> { {} (\w+) { self.throw_unrecognized_regex_modifier($/[0].Str) } }
method throw_unrecognized_regex_modifier($mod) {
self.panic('Unrecognized regex modifier :' ~ $mod);
}
}