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
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
| | ;;; rx.el --- sexp notation for regular expressions -*- lexical-binding: t -*-
;; Copyright (C) 2001-2019 Free Software Foundation, Inc.
;; Author: Gerd Moellmann <gerd@gnu.org>
;; Maintainer: emacs-devel@gnu.org
;; Keywords: strings, regexps, extensions
;; This file is part of GNU Emacs.
;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
;; the Free Software Foundation, either version 3 of the License, or
;; (at your option) any later version.
;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;; GNU General Public License for more details.
;; You should have received a copy of the GNU General Public License
;; along with GNU Emacs. If not, see <https://www.gnu.org/licenses/>.
;;; Commentary:
;; This is another implementation of sexp-form regular expressions.
;; It was unfortunately written without being aware of the Sregex
;; package coming with Emacs, but as things stand, Rx completely
;; covers all regexp features, which Sregex doesn't, doesn't suffer
;; from the bugs mentioned in the commentary section of Sregex, and
;; uses a nicer syntax (IMHO, of course :-).
;; This significantly extended version of the original, is almost
;; compatible with Sregex. The only incompatibility I (fx) know of is
;; that the `repeat' form can't have multiple regexp args.
;; Now alternative forms are provided for a degree of compatibility
;; with Olin Shivers' attempted definitive SRE notation. SRE forms
;; not catered for include: dsm, uncase, w/case, w/nocase, ,@<exp>,
;; ,<exp>, (word ...), word+, posix-string, and character class forms.
;; Some forms are inconsistent with SRE, either for historical reasons
;; or because of the implementation -- simple translation into Emacs
;; regexp strings. These include: any, word. Also, case-sensitivity
;; and greediness are controlled by variables external to the regexp,
;; and you need to feed the forms to the `posix-' functions to get
;; SRE's POSIX semantics. There are probably more difficulties.
;; Rx translates a sexp notation for regular expressions into the
;; usual string notation. The translation can be done at compile-time
;; by using the `rx' macro. It can be done at run-time by calling
;; function `rx-to-string'. See the documentation of `rx' for a
;; complete description of the sexp notation.
;;
;; Some examples of string regexps and their sexp counterparts:
;;
;; "^[a-z]*"
;; (rx (and line-start (0+ (in "a-z"))))
;;
;; "\n[^ \t]"
;; (rx (and "\n" (not (any " \t"))))
;;
;; "\\*\\*\\* EOOH \\*\\*\\*\n"
;; (rx "*** EOOH ***\n")
;;
;; "\\<\\(catch\\|finally\\)\\>[^_]"
;; (rx (and word-start (submatch (or "catch" "finally")) word-end
;; (not (any ?_))))
;;
;; "[ \t\n]*:\\([^:]+\\|$\\)"
;; (rx (and (zero-or-more (in " \t\n")) ":"
;; (submatch (or line-end (one-or-more (not (any ?:)))))))
;;
;; "^content-transfer-encoding:\\(\n?[\t ]\\)*quoted-printable\\(\n?[\t ]\\)*"
;; (rx (and line-start
;; "content-transfer-encoding:"
;; (+ (? ?\n)) (any " \t")
;; "quoted-printable"
;; (+ (? ?\n)) (any " \t"))
;;
;; (concat "^\\(?:" something-else "\\)")
;; (rx (and line-start (eval something-else))), statically or
;; (rx-to-string '(and line-start ,something-else)), dynamically.
;;
;; (regexp-opt '(STRING1 STRING2 ...))
;; (rx (or STRING1 STRING2 ...)), or in other words, `or' automatically
;; calls `regexp-opt' as needed.
;;
;; "^;;\\s-*\n\\|^\n"
;; (rx (or (and line-start ";;" (0+ space) ?\n)
;; (and line-start ?\n)))
;;
;; "\\$[I]d: [^ ]+ \\([^ ]+\\) "
;; (rx (and "$Id: "
;; (1+ (not (in " ")))
;; " "
;; (submatch (1+ (not (in " "))))
;; " "))
;;
;; "\\\\\\\\\\[\\w+"
;; (rx (and ?\\ ?\\ ?\[ (1+ word)))
;;
;; etc.
;;; History:
;;
;;; Code:
(require 'cl-lib)
;; FIXME: support macros.
(defvar rx-constituents ;Not `const' because some modes extend it.
'((and . (rx-and 1 nil))
(seq . and) ; SRE
(: . and) ; SRE
(sequence . and) ; sregex
(or . (rx-or 1 nil))
(| . or) ; SRE
(not-newline . ".")
(nonl . not-newline) ; SRE
(anything . (rx-anything 0 nil))
(any . (rx-any 1 nil rx-check-any)) ; inconsistent with SRE
(any . ".") ; sregex
(in . any)
(char . any) ; sregex
(not-char . (rx-not-char 1 nil rx-check-any)) ; sregex
(not . (rx-not 1 1 rx-check-not))
(repeat . (rx-repeat 2 nil))
(= . (rx-= 2 nil)) ; SRE
(>= . (rx->= 2 nil)) ; SRE
(** . (rx-** 2 nil)) ; SRE
(submatch . (rx-submatch 1 nil)) ; SRE
(group . submatch) ; sregex
(submatch-n . (rx-submatch-n 2 nil))
(group-n . submatch-n)
(zero-or-more . (rx-kleene 1 nil))
(one-or-more . (rx-kleene 1 nil))
(zero-or-one . (rx-kleene 1 nil))
(\? . zero-or-one) ; SRE
(\?? . zero-or-one)
(* . zero-or-more) ; SRE
(*? . zero-or-more)
(0+ . zero-or-more)
(+ . one-or-more) ; SRE
(+? . one-or-more)
(1+ . one-or-more)
(optional . zero-or-one)
(opt . zero-or-one) ; sregex
(minimal-match . (rx-greedy 1 1))
(maximal-match . (rx-greedy 1 1))
(backref . (rx-backref 1 1 rx-check-backref))
(line-start . "^")
(bol . line-start) ; SRE
(line-end . "$")
(eol . line-end) ; SRE
(string-start . "\\`")
(bos . string-start) ; SRE
(bot . string-start) ; sregex
(string-end . "\\'")
(eos . string-end) ; SRE
(eot . string-end) ; sregex
(buffer-start . "\\`")
(buffer-end . "\\'")
(point . "\\=")
(word-start . "\\<")
(bow . word-start) ; SRE
(word-end . "\\>")
(eow . word-end) ; SRE
(word-boundary . "\\b")
(not-word-boundary . "\\B") ; sregex
(symbol-start . "\\_<")
(symbol-end . "\\_>")
(syntax . (rx-syntax 1 1))
(not-syntax . (rx-not-syntax 1 1)) ; sregex
(category . (rx-category 1 1 rx-check-category))
(eval . (rx-eval 1 1))
(regexp . (rx-regexp 1 1 stringp))
(regex . regexp) ; sregex
(digit . "[[:digit:]]")
(numeric . digit) ; SRE
(num . digit) ; SRE
(control . "[[:cntrl:]]") ; SRE
(cntrl . control) ; SRE
(hex-digit . "[[:xdigit:]]") ; SRE
(hex . hex-digit) ; SRE
(xdigit . hex-digit) ; SRE
(blank . "[[:blank:]]") ; SRE
(graphic . "[[:graph:]]") ; SRE
(graph . graphic) ; SRE
(printing . "[[:print:]]") ; SRE
(print . printing) ; SRE
(alphanumeric . "[[:alnum:]]") ; SRE
(alnum . alphanumeric) ; SRE
(letter . "[[:alpha:]]")
(alphabetic . letter) ; SRE
(alpha . letter) ; SRE
(ascii . "[[:ascii:]]") ; SRE
(nonascii . "[[:nonascii:]]")
(lower . "[[:lower:]]") ; SRE
(lower-case . lower) ; SRE
(punctuation . "[[:punct:]]") ; SRE
(punct . punctuation) ; SRE
(space . "[[:space:]]") ; SRE
(whitespace . space) ; SRE
(white . space) ; SRE
(upper . "[[:upper:]]") ; SRE
(upper-case . upper) ; SRE
(word . "[[:word:]]") ; inconsistent with SRE
(wordchar . word) ; sregex
(not-wordchar . "\\W"))
"Alist of sexp form regexp constituents.
Each element of the alist has the form (SYMBOL . DEFN).
SYMBOL is a valid constituent of sexp regular expressions.
If DEFN is a string, SYMBOL is translated into DEFN.
If DEFN is a symbol, use the definition of DEFN, recursively.
Otherwise, DEFN must be a list (FUNCTION MIN-ARGS MAX-ARGS PREDICATE).
FUNCTION is used to produce code for SYMBOL. MIN-ARGS and MAX-ARGS
are the minimum and maximum number of arguments the function-form
sexp constituent SYMBOL may have in sexp regular expressions.
MAX-ARGS nil means no limit. PREDICATE, if specified, means that
all arguments must satisfy PREDICATE.")
(defconst rx-syntax
'((whitespace . ?-)
(punctuation . ?.)
(word . ?w)
(symbol . ?_)
(open-parenthesis . ?\()
(close-parenthesis . ?\))
(expression-prefix . ?\')
(string-quote . ?\")
(paired-delimiter . ?$)
(escape . ?\\)
(character-quote . ?/)
(comment-start . ?<)
(comment-end . ?>)
(string-delimiter . ?|)
(comment-delimiter . ?!))
"Alist mapping Rx syntax symbols to syntax characters.
Each entry has the form (SYMBOL . CHAR), where SYMBOL is a valid
symbol in `(syntax SYMBOL)', and CHAR is the syntax character
corresponding to SYMBOL, as it would be used with \\s or \\S in
regular expressions.")
(defconst rx-categories
'((space-for-indent . ?\s)
(base . ?.)
(consonant . ?0)
(base-vowel . ?1)
(upper-diacritical-mark . ?2)
(lower-diacritical-mark . ?3)
(tone-mark . ?4)
(symbol . ?5)
(digit . ?6)
(vowel-modifying-diacritical-mark . ?7)
(vowel-sign . ?8)
(semivowel-lower . ?9)
(not-at-end-of-line . ?<)
(not-at-beginning-of-line . ?>)
(alpha-numeric-two-byte . ?A)
(chinese-two-byte . ?C)
(chinse-two-byte . ?C) ;; A typo in Emacs 21.1-24.3.
(greek-two-byte . ?G)
(japanese-hiragana-two-byte . ?H)
(indian-two-byte . ?I)
(japanese-katakana-two-byte . ?K)
(strong-left-to-right . ?L)
(korean-hangul-two-byte . ?N)
(strong-right-to-left . ?R)
(cyrillic-two-byte . ?Y)
(combining-diacritic . ?^)
(ascii . ?a)
(arabic . ?b)
(chinese . ?c)
(ethiopic . ?e)
(greek . ?g)
(korean . ?h)
(indian . ?i)
(japanese . ?j)
(japanese-katakana . ?k)
(latin . ?l)
(lao . ?o)
(tibetan . ?q)
(japanese-roman . ?r)
(thai . ?t)
(vietnamese . ?v)
(hebrew . ?w)
(cyrillic . ?y)
(can-break . ?|))
"Alist mapping symbols to category characters.
Each entry has the form (SYMBOL . CHAR), where SYMBOL is a valid
symbol in `(category SYMBOL)', and CHAR is the category character
corresponding to SYMBOL, as it would be used with `\\c' or `\\C' in
regular expression strings.")
(defvar rx-greedy-flag t
"Non-nil means produce greedy regular expressions for `zero-or-one',
`zero-or-more', and `one-or-more'. Dynamically bound.")
(defun rx-info (op head)
"Return parsing/code generation info for OP.
If OP is the space character ASCII 32, return info for the symbol `?'.
If OP is the character `?', return info for the symbol `??'.
See also `rx-constituents'.
If HEAD is non-nil, then OP is the head of a sexp, otherwise it's
a standalone symbol."
(cond ((eq op ? ) (setq op '\?))
((eq op ??) (setq op '\??)))
(let (old-op)
(while (and (not (null op)) (symbolp op))
(setq old-op op)
(setq op (cdr (assq op rx-constituents)))
(when (if head (stringp op) (consp op))
;; We found something but of the wrong kind. Let's look for an
;; alternate definition for the other case.
(let ((new-op
(cdr (assq old-op (cdr (memq (assq old-op rx-constituents)
rx-constituents))))))
(if (and new-op (not (if head (stringp new-op) (consp new-op))))
(setq op new-op))))))
op)
(defun rx-check (form)
"Check FORM according to its car's parsing info."
(unless (listp form)
(error "rx `%s' needs argument(s)" form))
(let* ((rx (rx-info (car form) 'head))
(nargs (1- (length form)))
(min-args (nth 1 rx))
(max-args (nth 2 rx))
(type-pred (nth 3 rx)))
(when (and (not (null min-args))
(< nargs min-args))
(error "rx form `%s' requires at least %d args"
(car form) min-args))
(when (and (not (null max-args))
(> nargs max-args))
(error "rx form `%s' accepts at most %d args"
(car form) max-args))
(when (not (null type-pred))
(dolist (sub-form (cdr form))
(unless (funcall type-pred sub-form)
(error "rx form `%s' requires args satisfying `%s'"
(car form) type-pred))))))
(defun rx-group-if (regexp group)
"Put shy groups around REGEXP if seemingly necessary when GROUP
is non-nil."
(cond
;; for some repetition
((eq group '*) (if (rx-atomic-p regexp) (setq group nil)))
;; for concatenation
((eq group ':)
(if (rx-atomic-p
(if (string-match
"\\(?:[?*+]\\??\\|\\\\{[0-9]*,?[0-9]*\\\\}\\)\\'" regexp)
(substring regexp 0 (match-beginning 0))
regexp))
(setq group nil)))
;; for OR
((eq group '|) (setq group nil))
;; do anyway
((eq group t))
((rx-atomic-p regexp t) (setq group nil)))
(if group
(concat "\\(?:" regexp "\\)")
regexp))
(defvar rx-parent)
;; dynamically bound in some functions.
(defun rx-and (form)
"Parse and produce code from FORM.
FORM is of the form `(and FORM1 ...)'."
(rx-check form)
(rx-group-if
(mapconcat (lambda (x) (rx-form x ':)) (cdr form) nil)
(and (memq rx-parent '(* t)) rx-parent)))
(defun rx-or (form)
"Parse and produce code from FORM, which is `(or FORM1 ...)'."
(rx-check form)
(rx-group-if
(if (memq nil (mapcar 'stringp (cdr form)))
(mapconcat (lambda (x) (rx-form x '|)) (cdr form) "\\|")
(regexp-opt (cdr form)))
(and (memq rx-parent '(: * t)) rx-parent)))
(defun rx-anything (form)
"Match any character."
(if (consp form)
(error "rx `anything' syntax error: %s" form))
(rx-or (list 'or 'not-newline ?\n)))
(defun rx-any-delete-from-range (char ranges)
"Delete by side effect character CHAR from RANGES.
Only both edges of each range is checked."
(let (m)
(cond
((memq char ranges) (setq ranges (delq char ranges)))
((setq m (assq char ranges))
(if (eq (1+ char) (cdr m))
(setcar (memq m ranges) (1+ char))
(setcar m (1+ char))))
((setq m (rassq char ranges))
(if (eq (1- char) (car m))
(setcar (memq m ranges) (1- char))
(setcdr m (1- char)))))
ranges))
(defun rx-any-condense-range (args)
"Condense by side effect ARGS as range for Rx `any'."
(let (str
l)
;; set STR list of all strings
;; set L list of all ranges
(mapc (lambda (e) (cond ((stringp e) (push e str))
((numberp e) (push (cons e e) l))
(t (push e l))))
args)
;; condense overlapped ranges in L
(let ((tail (setq l (sort l #'car-less-than-car)))
d)
(while (setq d (cdr tail))
(if (>= (cdar tail) (1- (caar d)))
(progn
(setcdr (car tail) (max (cdar tail) (cdar d)))
(setcdr tail (cdr d)))
(setq tail d))))
;; Separate small ranges to single number, and delete dups.
(nconc
(apply #'nconc
(mapcar (lambda (e)
(cond
((= (car e) (cdr e)) (list (car e)))
((= (1+ (car e)) (cdr e)) (list (car e) (cdr e)))
((list e))))
l))
(delete-dups str))))
(defun rx-check-any-string (str)
"Turn the `any' argument string STR into a list of characters.
The original order is not preserved. Ranges, \"A-Z\", become pairs, (?A . ?Z)."
(let ((decode-char
;; Make sure raw bytes are decoded as such, to avoid confusion with
;; U+0080..U+00FF.
(if (multibyte-string-p str)
#'identity
(lambda (c) (if (<= #x80 c #xff)
(+ c #x3fff00)
c))))
(len (length str))
(i 0)
(ret nil))
(if (= 0 len)
(error "String arg for Rx `any' must not be empty"))
(while (< i len)
(cond ((and (< i (- len 2))
(= (aref str (+ i 1)) ?-))
;; Range.
(let ((start (funcall decode-char (aref str i)))
(end (funcall decode-char (aref str (+ i 2)))))
(cond ((< start end) (push (cons start end) ret))
((= start end) (push start ret)))
(setq i (+ i 3))))
(t
;; Single character.
(push (funcall decode-char (aref str i)) ret)
(setq i (+ i 1)))))
ret))
(defun rx-check-any (arg)
"Check arg ARG for Rx `any'."
(cond
((integerp arg) (list arg))
((symbolp arg)
(let ((translation (condition-case nil
(rx-form arg)
(error nil))))
(if (or (null translation)
(null (string-match "\\`\\[\\[:[-a-z]+:\\]\\]\\'" translation)))
(error "Invalid char class `%s' in Rx `any'" arg))
(list (substring translation 1 -1)))) ; strip outer brackets
((and (integerp (car-safe arg)) (integerp (cdr-safe arg)))
(list arg))
((stringp arg) (rx-check-any-string arg))
((error
"rx `any' requires string, character, char pair or char class args"))))
(defun rx-any (form)
"Parse and produce code from FORM, which is `(any ARG ...)'.
ARG is optional."
(rx-check form)
(let* ((args (rx-any-condense-range
(apply
#'nconc
(mapcar #'rx-check-any (cdr form)))))
m
s)
(cond
;; single close bracket
;; => "[]...-]" or "[]...--.]"
((memq ?\] args)
;; set ] at the beginning
(setq args (cons ?\] (delq ?\] args)))
;; set - at the end
(if (or (memq ?- args) (assq ?- args))
(setq args (nconc (rx-any-delete-from-range ?- args)
(list ?-)))))
;; close bracket starts a range
;; => "[]-....-]" or "[]-.--....]"
((setq m (assq ?\] args))
;; bring it to the beginning
(setq args (cons m (delq m args)))
(cond ((memq ?- args)
;; to the end
(setq args (nconc (delq ?- args) (list ?-))))
((setq m (assq ?- args))
;; next to the bracket's range, make the second range
(setcdr args (cons m (delq m (cdr args)))))))
;; bracket in the end range
;; => "[]...-]"
((setq m (rassq ?\] args))
;; set ] at the beginning
(setq args (cons ?\] (rx-any-delete-from-range ?\] args)))
;; set - at the end
(if (or (memq ?- args) (assq ?- args))
(setq args (nconc (rx-any-delete-from-range ?- args)
(list ?-)))))
;; {no close bracket appears}
;;
;; bring single bar to the beginning
((memq ?- args)
(setq args (cons ?- (delq ?- args))))
;; bar start a range, bring it to the beginning
((setq m (assq ?- args))
(setq args (cons m (delq m args))))
;;
;; hat at the beginning?
((or (eq (car args) ?^) (eq (car-safe (car args)) ?^))
(setq args (if (cdr args)
`(,(cadr args) ,(car args) ,@(cddr args))
(nconc (rx-any-delete-from-range ?^ args)
(list ?^))))))
;; some 1-char?
(if (and (null (cdr args)) (numberp (car args))
(or (= 1 (length
(setq s (regexp-quote (string (car args))))))
(and (equal (car args) ?^) ;; unnecessary predicate?
(null (eq rx-parent '!)))))
s
(concat "["
(mapconcat
(lambda (e) (cond
((numberp e) (string e))
((consp e)
(if (and (= (1+ (car e)) (cdr e))
;; rx-any-condense-range should
;; prevent this case from happening.
(null (memq (car e) '(?\] ?-)))
(null (memq (cdr e) '(?\] ?-))))
(string (car e) (cdr e))
(string (car e) ?- (cdr e))))
(e)))
args
nil)
"]"))))
(defun rx-check-not (arg)
"Check arg ARG for Rx `not'."
(unless (or (and (symbolp arg)
(string-match "\\`\\[\\[:[-a-z]+:\\]\\]\\'"
(condition-case nil
(rx-form arg)
(error ""))))
(eq arg 'word-boundary)
(and (consp arg)
(memq (car arg) '(not any in syntax category))))
(error "rx `not' syntax error: %s" arg))
t)
(defun rx-not (form)
"Parse and produce code from FORM. FORM is `(not ...)'."
(rx-check form)
(let ((result (rx-form (cadr form) '!))
case-fold-search)
(cond ((string-match "\\`\\[^" result)
(cond
((equal result "[^]") "[^^]")
((and (= (length result) 4) (null (eq rx-parent '!)))
(regexp-quote (substring result 2 3)))
((concat "[" (substring result 2)))))
((eq ?\[ (aref result 0))
(concat "[^" (substring result 1)))
((string-match "\\`\\\\[scbw]" result)
(concat (upcase (substring result 0 2))
(substring result 2)))
((string-match "\\`\\\\[SCBW]" result)
(concat (downcase (substring result 0 2))
(substring result 2)))
(t
(concat "[^" result "]")))))
(defun rx-not-char (form)
"Parse and produce code from FORM. FORM is `(not-char ...)'."
(rx-check form)
(rx-not `(not (in ,@(cdr form)))))
(defun rx-not-syntax (form)
"Parse and produce code from FORM. FORM is `(not-syntax SYNTAX)'."
(rx-check form)
(rx-not `(not (syntax ,@(cdr form)))))
(defun rx-trans-forms (form &optional skip)
"If FORM's length is greater than two, transform it to length two.
A form (HEAD REST ...) becomes (HEAD (and REST ...)).
If SKIP is non-nil, allow that number of items after the head, i.e.
`(= N REST ...)' becomes `(= N (and REST ...))' if SKIP is 1."
(unless skip (setq skip 0))
(let ((tail (nthcdr (1+ skip) form)))
(if (= (length tail) 1)
form
(let ((form (copy-sequence form)))
(setcdr (nthcdr skip form) (list (cons 'and tail)))
form))))
(defun rx-= (form)
"Parse and produce code from FORM `(= N ...)'."
(rx-check form)
(setq form (rx-trans-forms form 1))
(unless (and (integerp (nth 1 form))
(> (nth 1 form) 0))
(error "rx `=' requires positive integer first arg"))
(format "%s\\{%d\\}" (rx-form (nth 2 form) '*) (nth 1 form)))
(defun rx->= (form)
"Parse and produce code from FORM `(>= N ...)'."
(rx-check form)
(setq form (rx-trans-forms form 1))
(unless (and (integerp (nth 1 form))
(> (nth 1 form) 0))
(error "rx `>=' requires positive integer first arg"))
(format "%s\\{%d,\\}" (rx-form (nth 2 form) '*) (nth 1 form)))
(defun rx-** (form)
"Parse and produce code from FORM `(** N M ...)'."
(rx-check form)
(rx-form (cons 'repeat (cdr (rx-trans-forms form 2))) '*))
(defun rx-repeat (form)
"Parse and produce code from FORM.
FORM is either `(repeat N FORM1)' or `(repeat N M FORMS...)'."
(rx-check form)
(if (> (length form) 4)
(setq form (rx-trans-forms form 2)))
(if (null (nth 2 form))
(setq form (cons (nth 0 form) (cons (nth 1 form) (nthcdr 3 form)))))
(cond ((= (length form) 3)
(unless (and (integerp (nth 1 form))
(> (nth 1 form) 0))
(error "rx `repeat' requires positive integer first arg"))
(format "%s\\{%d\\}" (rx-form (nth 2 form) '*) (nth 1 form)))
((or (not (integerp (nth 2 form)))
(< (nth 2 form) 0)
(not (integerp (nth 1 form)))
(< (nth 1 form) 0)
(< (nth 2 form) (nth 1 form)))
(error "rx `repeat' range error"))
(t
(format "%s\\{%d,%d\\}" (rx-form (nth 3 form) '*)
(nth 1 form) (nth 2 form)))))
(defun rx-submatch (form)
"Parse and produce code from FORM, which is `(submatch ...)'."
(concat "\\("
(if (= 2 (length form))
;; Only one sub-form.
(rx-form (cadr form))
;; Several sub-forms implicitly concatenated.
(mapconcat (lambda (re) (rx-form re ':)) (cdr form) nil))
"\\)"))
(defun rx-submatch-n (form)
"Parse and produce code from FORM, which is `(submatch-n N ...)'."
(let ((n (nth 1 form)))
(concat "\\(?" (number-to-string n) ":"
(if (= 3 (length form))
;; Only one sub-form.
(rx-form (nth 2 form))
;; Several sub-forms implicitly concatenated.
(mapconcat (lambda (re) (rx-form re ':)) (cddr form) nil))
"\\)")))
(defun rx-backref (form)
"Parse and produce code from FORM, which is `(backref N)'."
(rx-check form)
(format "\\%d" (nth 1 form)))
(defun rx-check-backref (arg)
"Check arg ARG for Rx `backref'."
(or (and (integerp arg) (>= arg 1) (<= arg 9))
(error "rx `backref' requires numeric 1<=arg<=9: %s" arg)))
(defun rx-kleene (form)
"Parse and produce code from FORM.
FORM is `(OP FORM1)', where OP is one of the `zero-or-one',
`zero-or-more' etc. operators.
If OP is one of `*', `+', `?', produce a greedy regexp.
If OP is one of `*?', `+?', `??', produce a non-greedy regexp.
If OP is anything else, produce a greedy regexp if `rx-greedy-flag'
is non-nil."
(rx-check form)
(setq form (rx-trans-forms form))
(let ((suffix (cond ((memq (car form) '(* + \? ?\s)) "")
((memq (car form) '(*? +? \?? ??)) "?")
(rx-greedy-flag "")
(t "?")))
(op (cond ((memq (car form) '(* *? 0+ zero-or-more)) "*")
((memq (car form) '(+ +? 1+ one-or-more)) "+")
(t "?"))))
(rx-group-if
(concat (rx-form (cadr form) '*) op suffix)
(and (memq rx-parent '(t *)) rx-parent))))
(defun rx-atomic-p (r &optional lax)
"Return non-nil if regexp string R is atomic.
An atomic regexp R is one such that a suffix operator
appended to R will apply to all of R. For example, \"a\"
\"[abc]\" and \"\\(ab\\|ab*c\\)\" are atomic and \"ab\",
\"[ab]c\", and \"ab\\|ab*c\" are not atomic.
This function may return false negatives, but it will not
return false positives. It is nevertheless useful in
situations where an efficiency shortcut can be taken only if a
regexp is atomic. The function can be improved to detect
more cases of atomic regexps. Presently, this function
detects the following categories of atomic regexp;
a group or shy group: \\(...\\)
a character class: [...]
a single character: a
On the other hand, false negatives will be returned for
regexps that are atomic but end in operators, such as
\"a+\". I think these are rare. Probably such cases could
be detected without much effort. A guarantee of no false
negatives would require a theoretic specification of the set
of all atomic regexps."
(let ((l (length r)))
(cond
((<= l 1))
((= l 2) (= (aref r 0) ?\\))
((= l 3) (string-match "\\`\\(?:\\\\[cCsS_]\\|\\[[^^]\\]\\)" r))
((null lax)
(cond
((string-match "\\`\\[^?\]?\\(?:\\[:[a-z]+:]\\|[^]]\\)*\\]\\'" r))
((string-match "\\`\\\\(\\(?:[^\\]\\|\\\\[^)]\\)*\\\\)\\'" r)))))))
(defun rx-syntax (form)
"Parse and produce code from FORM, which is `(syntax SYMBOL)'."
(rx-check form)
(let* ((sym (cadr form))
(syntax (cdr (assq sym rx-syntax))))
(unless syntax
;; Try sregex compatibility.
(cond
((characterp sym) (setq syntax sym))
((symbolp sym)
(let ((name (symbol-name sym)))
(if (= 1 (length name))
(setq syntax (aref name 0))))))
(unless syntax
(error "Unknown rx syntax `%s'" sym)))
(format "\\s%c" syntax)))
(defun rx-check-category (form)
"Check the argument FORM of a `(category FORM)'."
(unless (or (integerp form)
(cdr (assq form rx-categories)))
(error "Unknown category `%s'" form))
t)
(defun rx-category (form)
"Parse and produce code from FORM, which is `(category SYMBOL)'."
(rx-check form)
(let ((char (if (integerp (cadr form))
(cadr form)
(cdr (assq (cadr form) rx-categories)))))
(format "\\c%c" char)))
(defun rx-eval (form)
"Parse and produce code from FORM, which is `(eval FORM)'."
(rx-check form)
(rx-form (eval (cadr form)) rx-parent))
(defun rx-greedy (form)
"Parse and produce code from FORM.
If FORM is `(minimal-match FORM1)', non-greedy versions of `*',
`+', and `?' operators will be used in FORM1. If FORM is
`(maximal-match FORM1)', greedy operators will be used."
(rx-check form)
(let ((rx-greedy-flag (eq (car form) 'maximal-match)))
(rx-form (cadr form) rx-parent)))
(defun rx-regexp (form)
"Parse and produce code from FORM, which is `(regexp STRING)'."
(rx-check form)
(rx-group-if (cadr form) rx-parent))
(defun rx-form (form &optional parent)
"Parse and produce code for regular expression FORM.
FORM is a regular expression in sexp form.
PARENT shows which type of expression calls and controls putting of
shy groups around the result and some more in other functions."
(let ((rx-parent parent))
(cond
((stringp form)
(rx-group-if (regexp-quote form)
(if (and (eq parent '*) (< 1 (length form)))
parent)))
((integerp form)
(regexp-quote (char-to-string form)))
((symbolp form)
(let ((info (rx-info form nil)))
(cond ((stringp info)
info)
((null info)
(error "Unknown rx form `%s'" form))
(t
(funcall (nth 0 info) form)))))
((consp form)
(let ((info (rx-info (car form) 'head)))
(unless (consp info)
(error "Unknown rx form `%s'" (car form)))
(funcall (nth 0 info) form)))
(t
(error "rx syntax error at `%s'" form)))))
;;;###autoload
(defun rx-to-string (form &optional no-group)
"Parse and produce code for regular expression FORM.
FORM is a regular expression in sexp form.
NO-GROUP non-nil means don't put shy groups around the result."
(rx-group-if (rx-form form) (null no-group)))
;;;###autoload
(defmacro rx (&rest regexps)
"Translate regular expressions REGEXPS in sexp form to a regexp string.
REGEXPS is a non-empty sequence of forms of the sort listed below.
Note that `rx' is a Lisp macro; when used in a Lisp program being
compiled, the translation is performed by the compiler.
See `rx-to-string' for how to do such a translation at run-time.
The following are valid subforms of regular expressions in sexp
notation.
STRING
matches string STRING literally.
CHAR
matches character CHAR literally.
`not-newline', `nonl'
matches any character except a newline.
`anything'
matches any character
`(any SET ...)'
`(in SET ...)'
`(char SET ...)'
matches any character in SET .... SET may be a character or string.
Ranges of characters can be specified as `A-Z' in strings.
Ranges may also be specified as conses like `(?A . ?Z)'.
SET may also be the name of a character class: `digit',
`control', `hex-digit', `blank', `graph', `print', `alnum',
`alpha', `ascii', `nonascii', `lower', `punct', `space', `upper',
`word', or one of their synonyms.
`(not (any SET ...))'
matches any character not in SET ...
`line-start', `bol'
matches the empty string, but only at the beginning of a line
in the text being matched
`line-end', `eol'
is similar to `line-start' but matches only at the end of a line
`string-start', `bos', `bot'
matches the empty string, but only at the beginning of the
string being matched against.
`string-end', `eos', `eot'
matches the empty string, but only at the end of the
string being matched against.
`buffer-start'
matches the empty string, but only at the beginning of the
buffer being matched against. Actually equivalent to `string-start'.
`buffer-end'
matches the empty string, but only at the end of the
buffer being matched against. Actually equivalent to `string-end'.
`point'
matches the empty string, but only at point.
`word-start', `bow'
matches the empty string, but only at the beginning of a word.
`word-end', `eow'
matches the empty string, but only at the end of a word.
`word-boundary'
matches the empty string, but only at the beginning or end of a
word.
`(not word-boundary)'
`not-word-boundary'
matches the empty string, but not at the beginning or end of a
word.
`symbol-start'
matches the empty string, but only at the beginning of a symbol.
`symbol-end'
matches the empty string, but only at the end of a symbol.
`digit', `numeric', `num'
matches 0 through 9.
`control', `cntrl'
matches any character whose code is in the range 0-31.
`hex-digit', `hex', `xdigit'
matches 0 through 9, a through f and A through F.
`blank'
matches horizontal whitespace, as defined by Annex C of the
Unicode Technical Standard #18. In particular, it matches
spaces, tabs, and other characters whose Unicode
`general-category' property indicates they are spacing
separators.
`graphic', `graph'
matches graphic characters--everything except whitespace, ASCII
and non-ASCII control characters, surrogates, and codepoints
unassigned by Unicode.
`printing', `print'
matches whitespace and graphic characters.
`alphanumeric', `alnum'
matches alphabetic characters and digits. For multibyte characters,
it matches characters whose Unicode `general-category' property
indicates they are alphabetic or decimal number characters.
`letter', `alphabetic', `alpha'
matches alphabetic characters. For multibyte characters,
it matches characters whose Unicode `general-category' property
indicates they are alphabetic characters.
`ascii'
matches ASCII (unibyte) characters.
`nonascii'
matches non-ASCII (multibyte) characters.
`lower', `lower-case'
matches anything lower-case, as determined by the current case
table. If `case-fold-search' is non-nil, this also matches any
upper-case letter.
`upper', `upper-case'
matches anything upper-case, as determined by the current case
table. If `case-fold-search' is non-nil, this also matches any
lower-case letter.
`punctuation', `punct'
matches punctuation. (But at present, for multibyte characters,
it matches anything that has non-word syntax.)
`space', `whitespace', `white'
matches anything that has whitespace syntax.
`word', `wordchar'
matches anything that has word syntax.
`not-wordchar'
matches anything that has non-word syntax.
`(syntax SYNTAX)'
matches a character with syntax SYNTAX. SYNTAX must be one
of the following symbols, or a symbol corresponding to the syntax
character, e.g. `\\.' for `\\s.'.
`whitespace' (\\s- in string notation)
`punctuation' (\\s.)
`word' (\\sw)
`symbol' (\\s_)
`open-parenthesis' (\\s()
`close-parenthesis' (\\s))
`expression-prefix' (\\s')
`string-quote' (\\s\")
`paired-delimiter' (\\s$)
`escape' (\\s\\)
`character-quote' (\\s/)
`comment-start' (\\s<)
`comment-end' (\\s>)
`string-delimiter' (\\s|)
`comment-delimiter' (\\s!)
`(not (syntax SYNTAX))'
matches a character that doesn't have syntax SYNTAX.
`(category CATEGORY)'
matches a character with category CATEGORY. CATEGORY must be
either a character to use for C, or one of the following symbols.
`space-for-indent' (\\c\\s in string notation)
`base' (\\c.)
`consonant' (\\c0)
`base-vowel' (\\c1)
`upper-diacritical-mark' (\\c2)
`lower-diacritical-mark' (\\c3)
`tone-mark' (\\c4)
`symbol' (\\c5)
`digit' (\\c6)
`vowel-modifying-diacritical-mark' (\\c7)
`vowel-sign' (\\c8)
`semivowel-lower' (\\c9)
`not-at-end-of-line' (\\c<)
`not-at-beginning-of-line' (\\c>)
`alpha-numeric-two-byte' (\\cA)
`chinese-two-byte' (\\cC)
`greek-two-byte' (\\cG)
`japanese-hiragana-two-byte' (\\cH)
`indian-two-byte' (\\cI)
`japanese-katakana-two-byte' (\\cK)
`strong-left-to-right' (\\cL)
`korean-hangul-two-byte' (\\cN)
`strong-right-to-left' (\\cR)
`cyrillic-two-byte' (\\cY)
`combining-diacritic' (\\c^)
`ascii' (\\ca)
`arabic' (\\cb)
`chinese' (\\cc)
`ethiopic' (\\ce)
`greek' (\\cg)
`korean' (\\ch)
`indian' (\\ci)
`japanese' (\\cj)
`japanese-katakana' (\\ck)
`latin' (\\cl)
`lao' (\\co)
`tibetan' (\\cq)
`japanese-roman' (\\cr)
`thai' (\\ct)
`vietnamese' (\\cv)
`hebrew' (\\cw)
`cyrillic' (\\cy)
`can-break' (\\c|)
`(not (category CATEGORY))'
matches a character that doesn't have category CATEGORY.
`(and SEXP1 SEXP2 ...)'
`(: SEXP1 SEXP2 ...)'
`(seq SEXP1 SEXP2 ...)'
`(sequence SEXP1 SEXP2 ...)'
matches what SEXP1 matches, followed by what SEXP2 matches, etc.
`(submatch SEXP1 SEXP2 ...)'
`(group SEXP1 SEXP2 ...)'
like `and', but makes the match accessible with `match-end',
`match-beginning', and `match-string'.
`(submatch-n N SEXP1 SEXP2 ...)'
`(group-n N SEXP1 SEXP2 ...)'
like `group', but make it an explicitly-numbered group with
group number N.
`(or SEXP1 SEXP2 ...)'
`(| SEXP1 SEXP2 ...)'
matches anything that matches SEXP1 or SEXP2, etc. If all
args are strings, use `regexp-opt' to optimize the resulting
regular expression.
`(minimal-match SEXP)'
produce a non-greedy regexp for SEXP. Normally, regexps matching
zero or more occurrences of something are \"greedy\" in that they
match as much as they can, as long as the overall regexp can
still match. A non-greedy regexp matches as little as possible.
`(maximal-match SEXP)'
produce a greedy regexp for SEXP. This is the default.
Below, `SEXP ...' represents a sequence of regexp forms, treated as if
enclosed in `(and ...)'.
`(zero-or-more SEXP ...)'
`(0+ SEXP ...)'
matches zero or more occurrences of what SEXP ... matches.
`(* SEXP ...)'
like `zero-or-more', but always produces a greedy regexp, independent
of `rx-greedy-flag'.
`(*? SEXP ...)'
like `zero-or-more', but always produces a non-greedy regexp,
independent of `rx-greedy-flag'.
`(one-or-more SEXP ...)'
`(1+ SEXP ...)'
matches one or more occurrences of SEXP ...
`(+ SEXP ...)'
like `one-or-more', but always produces a greedy regexp.
`(+? SEXP ...)'
like `one-or-more', but always produces a non-greedy regexp.
`(zero-or-one SEXP ...)'
`(optional SEXP ...)'
`(opt SEXP ...)'
matches zero or one occurrences of A.
`(? SEXP ...)'
like `zero-or-one', but always produces a greedy regexp.
`(?? SEXP ...)'
like `zero-or-one', but always produces a non-greedy regexp.
`(repeat N SEXP)'
`(= N SEXP ...)'
matches N occurrences.
`(>= N SEXP ...)'
matches N or more occurrences.
`(repeat N M SEXP)'
`(** N M SEXP ...)'
matches N to M occurrences.
`(backref N)'
matches what was matched previously by submatch N.
`(eval FORM)'
evaluate FORM and insert result. If result is a string,
`regexp-quote' it.
`(regexp REGEXP)'
include REGEXP in string notation in the result."
(cond ((null regexps)
(error "No regexp"))
((cdr regexps)
(rx-to-string `(and ,@regexps) t))
(t
(rx-to-string (car regexps) t))))
(pcase-defmacro rx (&rest regexps)
"Build a `pcase' pattern matching `rx' REGEXPS in sexp form.
The REGEXPS are interpreted as in `rx'. The pattern matches any
string that is a match for the regular expression so constructed,
as if by `string-match'.
In addition to the usual `rx' constructs, REGEXPS can contain the
following constructs:
(let REF SEXP...) creates a new explicitly named reference to
a submatch that matches regular expressions
SEXP, and binds the match to REF.
(backref REF) creates a backreference to the submatch
introduced by a previous (let REF ...)
construct. REF can be the same symbol
in the first argument of the corresponding
(let REF ...) construct, or it can be a
submatch number. It matches the referenced
submatch.
The REFs are associated with explicitly named submatches starting
from 1. Multiple occurrences of the same REF refer to the same
submatch.
If a case matches, the match data is modified as usual so you can
use it in the case body, but you still have to pass the correct
string as argument to `match-string'."
(let* ((vars ())
(rx-constituents
`((let
,(lambda (form)
(rx-check form)
(let ((var (cadr form)))
(cl-check-type var symbol)
(let ((i (or (cl-position var vars :test #'eq)
(prog1 (length vars)
(setq vars `(,@vars ,var))))))
(rx-form `(submatch-n ,(1+ i) ,@(cddr form))))))
1 nil)
(backref
,(lambda (form)
(rx-check form)
(rx-backref
`(backref ,(let ((var (cadr form)))
(if (integerp var) var
(1+ (cl-position var vars :test #'eq)))))))
1 1
,(lambda (var)
(cond ((integerp var) (rx-check-backref var))
((memq var vars) t)
(t (error "rx `backref' variable must be one of %s: %s"
vars var)))))
,@rx-constituents))
(regexp (rx-to-string `(seq ,@regexps) :no-group)))
`(and (pred (string-match ,regexp))
,@(cl-loop for i from 1
for var in vars
collect `(app (match-string ,i) ,var)))))
\f
;; ;; sregex.el replacement
;; ;;;###autoload (provide 'sregex)
;; ;;;###autoload (autoload 'sregex "rx")
;; (defalias 'sregex 'rx-to-string)
;; ;;;###autoload (autoload 'sregexq "rx" nil nil 'macro)
;; (defalias 'sregexq 'rx)
\f
(provide 'rx)
;;; rx.el ends here
|