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
|
if not modules then modules = { } end modules ['l-lpeg'] = {
version = 1.001,
comment = "companion to luat-lib.mkiv",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files"
}
-- lpeg 12 vs lpeg 10: slower compilation, similar parsing speed (i need to check
-- if i can use new features like capture / 2 and .B (at first sight the xml
-- parser is some 5% slower)
-- a new lpeg fails on a #(1-P(":")) test and really needs a + P(-1)
-- move utf -> l-unicode
-- move string -> l-string or keep it here
lpeg = require("lpeg")
-- The latest lpeg doesn't have print any more, and even the new ones are not
-- available by default (only when debug mode is enabled), which is a pitty as
-- as it helps nailign down bottlenecks. Performance seems comparable: some 10%
-- slower pattern compilation, same parsing speed, although,
--
-- local p = lpeg.C(lpeg.P(1)^0 * lpeg.P(-1))
-- local a = string.rep("123",100)
-- lpeg.match(p,a)
--
-- seems slower and is also still suboptimal (i.e. a match that runs from begin
-- to end, one of the cases where string matchers win).
if not lpeg.print then function lpeg.print(...) print(lpeg.pcode(...)) end end
-- tracing (only used when we encounter a problem in integration of lpeg in luatex)
-- some code will move to unicode and string
-- local lpmatch = lpeg.match
-- local lpprint = lpeg.print
-- local lpp = lpeg.P
-- local lpr = lpeg.R
-- local lps = lpeg.S
-- local lpc = lpeg.C
-- local lpb = lpeg.B
-- local lpv = lpeg.V
-- local lpcf = lpeg.Cf
-- local lpcb = lpeg.Cb
-- local lpcg = lpeg.Cg
-- local lpct = lpeg.Ct
-- local lpcs = lpeg.Cs
-- local lpcc = lpeg.Cc
-- local lpcmt = lpeg.Cmt
-- local lpcarg = lpeg.Carg
-- function lpeg.match(l,...) print("LPEG MATCH") lpprint(l) return lpmatch(l,...) end
-- function lpeg.P (l) local p = lpp (l) print("LPEG P =") lpprint(l) return p end
-- function lpeg.R (l) local p = lpr (l) print("LPEG R =") lpprint(l) return p end
-- function lpeg.S (l) local p = lps (l) print("LPEG S =") lpprint(l) return p end
-- function lpeg.C (l) local p = lpc (l) print("LPEG C =") lpprint(l) return p end
-- function lpeg.B (l) local p = lpb (l) print("LPEG B =") lpprint(l) return p end
-- function lpeg.V (l) local p = lpv (l) print("LPEG V =") lpprint(l) return p end
-- function lpeg.Cf (l) local p = lpcf (l) print("LPEG Cf =") lpprint(l) return p end
-- function lpeg.Cb (l) local p = lpcb (l) print("LPEG Cb =") lpprint(l) return p end
-- function lpeg.Cg (l) local p = lpcg (l) print("LPEG Cg =") lpprint(l) return p end
-- function lpeg.Ct (l) local p = lpct (l) print("LPEG Ct =") lpprint(l) return p end
-- function lpeg.Cs (l) local p = lpcs (l) print("LPEG Cs =") lpprint(l) return p end
-- function lpeg.Cc (l) local p = lpcc (l) print("LPEG Cc =") lpprint(l) return p end
-- function lpeg.Cmt (l) local p = lpcmt (l) print("LPEG Cmt =") lpprint(l) return p end
-- function lpeg.Carg (l) local p = lpcarg(l) print("LPEG Carg =") lpprint(l) return p end
local type, next, tostring = type, next, tostring
local byte, char, gmatch, format = string.byte, string.char, string.gmatch, string.format
----- mod, div = math.mod, math.div
local floor = math.floor
local P, R, S, V, Ct, C, Cs, Cc, Cp, Cmt = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc, lpeg.Cp, lpeg.Cmt
local lpegtype, lpegmatch, lpegprint = lpeg.type, lpeg.match, lpeg.print
-- let's start with an inspector:
if setinspector then
setinspector(function(v) if lpegtype(v) then lpegprint(v) return true end end)
end
-- Beware, we predefine a bunch of patterns here and one reason for doing so
-- is that we get consistent behaviour in some of the visualizers.
lpeg.patterns = lpeg.patterns or { } -- so that we can share
local patterns = lpeg.patterns
local anything = P(1)
local endofstring = P(-1)
local alwaysmatched = P(true)
patterns.anything = anything
patterns.endofstring = endofstring
patterns.beginofstring = alwaysmatched
patterns.alwaysmatched = alwaysmatched
local sign = S('+-')
local zero = P('0')
local digit = R('09')
local octdigit = R("07")
local lowercase = R("az")
local uppercase = R("AZ")
local underscore = P("_")
local hexdigit = digit + lowercase + uppercase
local cr, lf, crlf = P("\r"), P("\n"), P("\r\n")
----- newline = crlf + S("\r\n") -- cr + lf
local newline = P("\r") * (P("\n") + P(true)) + P("\n")
local escaped = P("\\") * anything
local squote = P("'")
local dquote = P('"')
local space = P(" ")
local period = P(".")
local comma = P(",")
local utfbom_32_be = P('\000\000\254\255') -- 00 00 FE FF
local utfbom_32_le = P('\255\254\000\000') -- FF FE 00 00
local utfbom_16_be = P('\254\255') -- FE FF
local utfbom_16_le = P('\255\254') -- FF FE
local utfbom_8 = P('\239\187\191') -- EF BB BF
local utfbom = utfbom_32_be + utfbom_32_le
+ utfbom_16_be + utfbom_16_le
+ utfbom_8
local utftype = utfbom_32_be * Cc("utf-32-be") + utfbom_32_le * Cc("utf-32-le")
+ utfbom_16_be * Cc("utf-16-be") + utfbom_16_le * Cc("utf-16-le")
+ utfbom_8 * Cc("utf-8") + alwaysmatched * Cc("utf-8") -- assume utf8
local utfstricttype = utfbom_32_be * Cc("utf-32-be") + utfbom_32_le * Cc("utf-32-le")
+ utfbom_16_be * Cc("utf-16-be") + utfbom_16_le * Cc("utf-16-le")
+ utfbom_8 * Cc("utf-8")
local utfoffset = utfbom_32_be * Cc(4) + utfbom_32_le * Cc(4)
+ utfbom_16_be * Cc(2) + utfbom_16_le * Cc(2)
+ utfbom_8 * Cc(3) + Cc(0)
local utf8next = R("\128\191")
patterns.utfbom_32_be = utfbom_32_be
patterns.utfbom_32_le = utfbom_32_le
patterns.utfbom_16_be = utfbom_16_be
patterns.utfbom_16_le = utfbom_16_le
patterns.utfbom_8 = utfbom_8
patterns.utf_16_be_nl = P("\000\r\000\n") + P("\000\r") + P("\000\n") -- P("\000\r") * (P("\000\n") + P(true)) + P("\000\n")
patterns.utf_16_le_nl = P("\r\000\n\000") + P("\r\000") + P("\n\000") -- P("\r\000") * (P("\n\000") + P(true)) + P("\n\000")
patterns.utf_32_be_nl = P("\000\000\000\r\000\000\000\n") + P("\000\000\000\r") + P("\000\000\000\n")
patterns.utf_32_le_nl = P("\r\000\000\000\n\000\000\000") + P("\r\000\000\000") + P("\n\000\000\000")
patterns.utf8one = R("\000\127")
patterns.utf8two = R("\194\223") * utf8next
patterns.utf8three = R("\224\239") * utf8next * utf8next
patterns.utf8four = R("\240\244") * utf8next * utf8next * utf8next
patterns.utfbom = utfbom
patterns.utftype = utftype
patterns.utfstricttype = utfstricttype
patterns.utfoffset = utfoffset
local utf8char = patterns.utf8one + patterns.utf8two + patterns.utf8three + patterns.utf8four
local validutf8char = utf8char^0 * endofstring * Cc(true) + Cc(false)
local utf8character = P(1) * R("\128\191")^0 -- unchecked but fast
patterns.utf8 = utf8char
patterns.utf8char = utf8char
patterns.utf8character = utf8character -- this one can be used in most cases so we might use that one
patterns.validutf8 = validutf8char
patterns.validutf8char = validutf8char
local eol = S("\n\r")
local spacer = S(" \t\f\v") -- + char(0xc2, 0xa0) if we want utf (cf mail roberto)
local whitespace = eol + spacer
local nonspacer = 1 - spacer
local nonwhitespace = 1 - whitespace
patterns.eol = eol
patterns.spacer = spacer
patterns.whitespace = whitespace
patterns.nonspacer = nonspacer
patterns.nonwhitespace = nonwhitespace
local stripper = spacer ^0 * C((spacer ^0 * nonspacer ^1)^0) -- from example by roberto
local fullstripper = whitespace^0 * C((whitespace^0 * nonwhitespace^1)^0)
----- collapser = Cs(spacer^0/"" * ((spacer^1 * endofstring / "") + (spacer^1/" ") + P(1))^0)
local collapser = Cs(spacer^0/"" * nonspacer^0 * ((spacer^0/" " * nonspacer^1)^0))
local b_collapser = Cs( whitespace^0 /"" * (nonwhitespace^1 + whitespace^1/" ")^0)
local e_collapser = Cs((whitespace^1 * P(-1)/"" + nonwhitespace^1 + whitespace^1/" ")^0)
local m_collapser = Cs( (nonwhitespace^1 + whitespace^1/" ")^0)
local b_stripper = Cs( spacer^0 /"" * (nonspacer^1 + spacer^1/" ")^0)
local e_stripper = Cs((spacer^1 * P(-1)/"" + nonspacer^1 + spacer^1/" ")^0)
local m_stripper = Cs( (nonspacer^1 + spacer^1/" ")^0)
patterns.stripper = stripper
patterns.fullstripper = fullstripper
patterns.collapser = collapser
patterns.b_collapser = b_collapser
patterns.m_collapser = m_collapser
patterns.e_collapser = e_collapser
patterns.b_stripper = b_stripper
patterns.m_stripper = m_stripper
patterns.e_stripper = e_stripper
patterns.lowercase = lowercase
patterns.uppercase = uppercase
patterns.letter = patterns.lowercase + patterns.uppercase
patterns.space = space
patterns.tab = P("\t")
patterns.spaceortab = patterns.space + patterns.tab
patterns.newline = newline
patterns.emptyline = newline^1
patterns.equal = P("=")
patterns.comma = comma
patterns.commaspacer = comma * spacer^0
patterns.period = period
patterns.colon = P(":")
patterns.semicolon = P(";")
patterns.underscore = underscore
patterns.escaped = escaped
patterns.squote = squote
patterns.dquote = dquote
patterns.nosquote = (escaped + (1-squote))^0
patterns.nodquote = (escaped + (1-dquote))^0
patterns.unsingle = (squote/"") * patterns.nosquote * (squote/"") -- will change to C in the middle
patterns.undouble = (dquote/"") * patterns.nodquote * (dquote/"") -- will change to C in the middle
patterns.unquoted = patterns.undouble + patterns.unsingle -- more often undouble
patterns.unspacer = ((patterns.spacer^1)/"")^0
patterns.singlequoted = squote * patterns.nosquote * squote
patterns.doublequoted = dquote * patterns.nodquote * dquote
patterns.quoted = patterns.doublequoted + patterns.singlequoted
patterns.digit = digit
patterns.octdigit = octdigit
patterns.hexdigit = hexdigit
patterns.sign = sign
patterns.cardinal = digit^1
patterns.integer = sign^-1 * digit^1
patterns.unsigned = digit^0 * period * digit^1
patterns.float = sign^-1 * patterns.unsigned
patterns.cunsigned = digit^0 * comma * digit^1
patterns.cpunsigned = digit^0 * (period + comma) * digit^1
patterns.cfloat = sign^-1 * patterns.cunsigned
patterns.cpfloat = sign^-1 * patterns.cpunsigned
patterns.number = patterns.float + patterns.integer
patterns.cnumber = patterns.cfloat + patterns.integer
patterns.cpnumber = patterns.cpfloat + patterns.integer
patterns.oct = zero * octdigit^1
patterns.octal = patterns.oct
patterns.HEX = zero * P("X") * (digit+uppercase)^1
patterns.hex = zero * P("x") * (digit+lowercase)^1
patterns.hexadecimal = zero * S("xX") * hexdigit^1
patterns.hexafloat = sign^-1
* zero * S("xX")
* (hexdigit^0 * period * hexdigit^1 + hexdigit^1 * period * hexdigit^0 + hexdigit^1)
* (S("pP") * sign^-1 * hexdigit^1)^-1
patterns.decafloat = sign^-1
* (digit^0 * period * digit^1 + digit^1 * period * digit^0 + digit^1)
* S("eE") * sign^-1 * digit^1
patterns.propername = (uppercase + lowercase + underscore) * (uppercase + lowercase + underscore + digit)^0 * endofstring
patterns.somecontent = (anything - newline - space)^1 -- (utf8char - newline - space)^1
patterns.beginline = #(1-newline)
patterns.longtostring = Cs(whitespace^0/"" * ((patterns.quoted + nonwhitespace^1 + whitespace^1/"" * (P(-1) + Cc(" ")))^0))
local function anywhere(pattern) --slightly adapted from website
return P { P(pattern) + 1 * V(1) }
end
lpeg.anywhere = anywhere
function lpeg.instringchecker(p)
p = anywhere(p)
return function(str)
return lpegmatch(p,str) and true or false
end
end
function lpeg.splitter(pattern, action)
return (((1-P(pattern))^1)/action+1)^0
end
function lpeg.tsplitter(pattern, action)
return Ct((((1-P(pattern))^1)/action+1)^0)
end
-- probleem: separator can be lpeg and that does not hash too well, but
-- it's quite okay as the key is then not garbage collected
local splitters_s, splitters_m, splitters_t = { }, { }, { }
local function splitat(separator,single)
local splitter = (single and splitters_s[separator]) or splitters_m[separator]
if not splitter then
separator = P(separator)
local other = C((1 - separator)^0)
if single then
local any = anything
splitter = other * (separator * C(any^0) + "") -- ?
splitters_s[separator] = splitter
else
splitter = other * (separator * other)^0
splitters_m[separator] = splitter
end
end
return splitter
end
local function tsplitat(separator)
local splitter = splitters_t[separator]
if not splitter then
splitter = Ct(splitat(separator))
splitters_t[separator] = splitter
end
return splitter
end
lpeg.splitat = splitat
lpeg.tsplitat = tsplitat
function string.splitup(str,separator)
if not separator then
separator = ","
end
return lpegmatch(splitters_m[separator] or splitat(separator),str)
end
-- local p = splitat("->",false) print(lpegmatch(p,"oeps->what->more")) -- oeps what more
-- local p = splitat("->",true) print(lpegmatch(p,"oeps->what->more")) -- oeps what->more
-- local p = splitat("->",false) print(lpegmatch(p,"oeps")) -- oeps
-- local p = splitat("->",true) print(lpegmatch(p,"oeps")) -- oeps
local cache = { }
function lpeg.split(separator,str)
local c = cache[separator]
if not c then
c = tsplitat(separator)
cache[separator] = c
end
return lpegmatch(c,str)
end
function string.split(str,separator)
if separator then
local c = cache[separator]
if not c then
c = tsplitat(separator)
cache[separator] = c
end
return lpegmatch(c,str)
else
return { str }
end
end
local spacing = patterns.spacer^0 * newline -- sort of strip
local empty = spacing * Cc("")
local nonempty = Cs((1-spacing)^1) * spacing^-1
local content = (empty + nonempty)^1
patterns.textline = content
local linesplitter = tsplitat(newline)
patterns.linesplitter = linesplitter
function string.splitlines(str)
return lpegmatch(linesplitter,str)
end
-- lpeg.splitters = cache -- no longer public
local cache = { }
function lpeg.checkedsplit(separator,str)
local c = cache[separator]
if not c then
separator = P(separator)
local other = C((1 - separator)^1)
c = Ct(separator^0 * other * (separator^1 * other)^0)
cache[separator] = c
end
return lpegmatch(c,str)
end
function string.checkedsplit(str,separator)
local c = cache[separator]
if not c then
separator = P(separator)
local other = C((1 - separator)^1)
c = Ct(separator^0 * other * (separator^1 * other)^0)
cache[separator] = c
end
return lpegmatch(c,str)
end
-- from roberto's site:
local function f2(s) local c1, c2 = byte(s,1,2) return c1 * 64 + c2 - 12416 end
local function f3(s) local c1, c2, c3 = byte(s,1,3) return (c1 * 64 + c2) * 64 + c3 - 925824 end
local function f4(s) local c1, c2, c3, c4 = byte(s,1,4) return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168 end
local utf8byte = patterns.utf8one/byte + patterns.utf8two/f2 + patterns.utf8three/f3 + patterns.utf8four/f4
patterns.utf8byte = utf8byte
--~ local str = " a b c d "
--~ local s = lpeg.stripper(lpeg.R("az")) print("["..lpegmatch(s,str).."]")
--~ local s = lpeg.keeper(lpeg.R("az")) print("["..lpegmatch(s,str).."]")
--~ local s = lpeg.stripper("ab") print("["..lpegmatch(s,str).."]")
--~ local s = lpeg.keeper("ab") print("["..lpegmatch(s,str).."]")
local cache = { }
function lpeg.stripper(str)
if type(str) == "string" then
local s = cache[str]
if not s then
s = Cs(((S(str)^1)/"" + 1)^0)
cache[str] = s
end
return s
else
return Cs(((str^1)/"" + 1)^0)
end
end
local cache = { }
function lpeg.keeper(str)
if type(str) == "string" then
local s = cache[str]
if not s then
s = Cs((((1-S(str))^1)/"" + 1)^0)
cache[str] = s
end
return s
else
return Cs((((1-str)^1)/"" + 1)^0)
end
end
function lpeg.frontstripper(str) -- or pattern (yet undocumented)
return (P(str) + P(true)) * Cs(anything^0)
end
function lpeg.endstripper(str) -- or pattern (yet undocumented)
return Cs((1 - P(str) * endofstring)^0)
end
-- Just for fun I looked at the used bytecode and
-- p = (p and p + pp) or pp gets one more (testset).
-- todo: cache when string
function lpeg.replacer(one,two,makefunction,isutf) -- in principle we should sort the keys
local pattern
local u = isutf and utf8char or 1
if type(one) == "table" then
local no = #one
local p = P(false)
if no == 0 then
for k, v in next, one do
p = p + P(k) / v
end
pattern = Cs((p + u)^0)
elseif no == 1 then
local o = one[1]
one, two = P(o[1]), o[2]
-- pattern = Cs(((1-one)^1 + one/two)^0)
pattern = Cs((one/two + u)^0)
else
for i=1,no do
local o = one[i]
p = p + P(o[1]) / o[2]
end
pattern = Cs((p + u)^0)
end
else
pattern = Cs((P(one)/(two or "") + u)^0)
end
if makefunction then
return function(str)
return lpegmatch(pattern,str)
end
else
return pattern
end
end
-- local pattern1 = P(1-P(pattern))^0 * P(pattern) : test for not nil
-- local pattern2 = (P(pattern) * Cc(true) + P(1))^0 : test for true (could be faster, but not much)
function lpeg.finder(lst,makefunction,isutf) -- beware: slower than find with 'patternless finds'
local pattern
if type(lst) == "table" then
pattern = P(false)
if #lst == 0 then
for k, v in next, lst do
pattern = pattern + P(k) -- ignore key, so we can use a replacer table
end
else
for i=1,#lst do
pattern = pattern + P(lst[i])
end
end
else
pattern = P(lst)
end
if isutf then
pattern = ((utf8char or 1)-pattern)^0 * pattern
else
pattern = (1-pattern)^0 * pattern
end
if makefunction then
return function(str)
return lpegmatch(pattern,str)
end
else
return pattern
end
end
-- print(lpeg.match(lpeg.replacer("e","a"),"test test"))
-- print(lpeg.match(lpeg.replacer{{"e","a"}},"test test"))
-- print(lpeg.match(lpeg.replacer({ e = "a", t = "x" }),"test test"))
local splitters_f, splitters_s = { }, { }
function lpeg.firstofsplit(separator) -- always return value
local splitter = splitters_f[separator]
if not splitter then
local pattern = P(separator)
splitter = C((1 - pattern)^0)
splitters_f[separator] = splitter
end
return splitter
end
function lpeg.secondofsplit(separator) -- nil if not split
local splitter = splitters_s[separator]
if not splitter then
local pattern = P(separator)
splitter = (1 - pattern)^0 * pattern * C(anything^0)
splitters_s[separator] = splitter
end
return splitter
end
local splitters_s, splitters_p = { }, { }
function lpeg.beforesuffix(separator) -- nil if nothing but empty is ok
local splitter = splitters_s[separator]
if not splitter then
local pattern = P(separator)
splitter = C((1 - pattern)^0) * pattern * endofstring
splitters_s[separator] = splitter
end
return splitter
end
function lpeg.afterprefix(separator) -- nil if nothing but empty is ok
local splitter = splitters_p[separator]
if not splitter then
local pattern = P(separator)
splitter = pattern * C(anything^0)
splitters_p[separator] = splitter
end
return splitter
end
function lpeg.balancer(left,right)
left, right = P(left), P(right)
return P { left * ((1 - left - right) + V(1))^0 * right }
end
-- print(1,lpegmatch(lpeg.firstofsplit(":"),"bc:de"))
-- print(2,lpegmatch(lpeg.firstofsplit(":"),":de")) -- empty
-- print(3,lpegmatch(lpeg.firstofsplit(":"),"bc"))
-- print(4,lpegmatch(lpeg.secondofsplit(":"),"bc:de"))
-- print(5,lpegmatch(lpeg.secondofsplit(":"),"bc:")) -- empty
-- print(6,lpegmatch(lpeg.secondofsplit(":",""),"bc"))
-- print(7,lpegmatch(lpeg.secondofsplit(":"),"bc"))
-- print(9,lpegmatch(lpeg.secondofsplit(":","123"),"bc"))
-- -- slower:
--
-- function lpeg.counter(pattern)
-- local n, pattern = 0, (lpeg.P(pattern)/function() n = n + 1 end + lpeg.anything)^0
-- return function(str) n = 0 ; lpegmatch(pattern,str) ; return n end
-- end
local nany = utf8char/""
function lpeg.counter(pattern)
pattern = Cs((P(pattern)/" " + nany)^0)
return function(str)
return #lpegmatch(pattern,str)
end
end
-- utf extensies
utf = utf or (unicode and unicode.utf8) or { }
local utfcharacters = utf and utf.characters or string.utfcharacters
local utfgmatch = utf and utf.gmatch
local utfchar = utf and utf.char
lpeg.UP = lpeg.P
if utfcharacters then
function lpeg.US(str)
local p = P(false)
for uc in utfcharacters(str) do
p = p + P(uc)
end
return p
end
elseif utfgmatch then
function lpeg.US(str)
local p = P(false)
for uc in utfgmatch(str,".") do
p = p + P(uc)
end
return p
end
else
function lpeg.US(str)
local p = P(false)
local f = function(uc)
p = p + P(uc)
end
lpegmatch((utf8char/f)^0,str)
return p
end
end
local range = utf8byte * utf8byte + Cc(false) -- utf8byte is already a capture
function lpeg.UR(str,more)
local first, last
if type(str) == "number" then
first = str
last = more or first
else
first, last = lpegmatch(range,str)
if not last then
return P(str)
end
end
if first == last then
return P(str)
elseif utfchar and (last - first < 8) then -- a somewhat arbitrary criterium
local p = P(false)
for i=first,last do
p = p + P(utfchar(i))
end
return p -- nil when invalid range
else
local f = function(b)
return b >= first and b <= last
end
-- tricky, these nested captures
return utf8byte / f -- nil when invalid range
end
end
-- print(lpeg.match(lpeg.Cs((C(lpeg.UR("αω"))/{ ["χ"] = "OEPS" })^0),"αωχαω"))
-- lpeg.print(lpeg.R("ab","cd","gh"))
-- lpeg.print(lpeg.P("a","b","c"))
-- lpeg.print(lpeg.S("a","b","c"))
-- print(lpeg.count("äáàa",lpeg.P("á") + lpeg.P("à")))
-- print(lpeg.count("äáàa",lpeg.UP("áà")))
-- print(lpeg.count("äáàa",lpeg.US("àá")))
-- print(lpeg.count("äáàa",lpeg.UR("aá")))
-- print(lpeg.count("äáàa",lpeg.UR("àá")))
-- print(lpeg.count("äáàa",lpeg.UR(0x0000,0xFFFF)))
function lpeg.is_lpeg(p)
return p and lpegtype(p) == "pattern"
end
function lpeg.oneof(list,...) -- lpeg.oneof("elseif","else","if","then") -- assume proper order
if type(list) ~= "table" then
list = { list, ... }
end
-- table.sort(list) -- longest match first
local p = P(list[1])
for l=2,#list do
p = p + P(list[l])
end
return p
end
-- For the moment here, but it might move to utilities. Beware, we need to
-- have the longest keyword first, so 'aaa' comes beforte 'aa' which is why we
-- loop back from the end cq. prepend.
local sort = table.sort
local function copyindexed(old)
local new = { }
for i=1,#old do
new[i] = old
end
return new
end
local function sortedkeys(tab)
local keys, s = { }, 0
for key,_ in next, tab do
s = s + 1
keys[s] = key
end
sort(keys)
return keys
end
function lpeg.append(list,pp,delayed,checked)
local p = pp
if #list > 0 then
local keys = copyindexed(list)
sort(keys)
for i=#keys,1,-1 do
local k = keys[i]
if p then
p = P(k) + p
else
p = P(k)
end
end
elseif delayed then -- hm, it looks like the lpeg parser resolves anyway
local keys = sortedkeys(list)
if p then
for i=1,#keys,1 do
local k = keys[i]
local v = list[k]
p = P(k)/list + p
end
else
for i=1,#keys do
local k = keys[i]
local v = list[k]
if p then
p = P(k) + p
else
p = P(k)
end
end
if p then
p = p / list
end
end
elseif checked then
-- problem: substitution gives a capture
local keys = sortedkeys(list)
for i=1,#keys do
local k = keys[i]
local v = list[k]
if p then
if k == v then
p = P(k) + p
else
p = P(k)/v + p
end
else
if k == v then
p = P(k)
else
p = P(k)/v
end
end
end
else
local keys = sortedkeys(list)
for i=1,#keys do
local k = keys[i]
local v = list[k]
if p then
p = P(k)/v + p
else
p = P(k)/v
end
end
end
return p
end
-- inspect(lpeg.append({ a = "1", aa = "1", aaa = "1" } ,nil,true))
-- inspect(lpeg.append({ ["degree celsius"] = "1", celsius = "1", degree = "1" } ,nil,true))
-- function lpeg.exact_match(words,case_insensitive)
-- local pattern = concat(words)
-- if case_insensitive then
-- local pattern = S(upper(characters)) + S(lower(characters))
-- local list = { }
-- for i=1,#words do
-- list[lower(words[i])] = true
-- end
-- return Cmt(pattern^1, function(_,i,s)
-- return list[lower(s)] and i
-- end)
-- else
-- local pattern = S(concat(words))
-- local list = { }
-- for i=1,#words do
-- list[words[i]] = true
-- end
-- return Cmt(pattern^1, function(_,i,s)
-- return list[s] and i
-- end)
-- end
-- end
-- experiment:
-- local function make(t)
-- local p
-- local keys = sortedkeys(t)
-- for i=1,#keys do
-- local k = keys[i]
-- local v = t[k]
-- if not p then
-- if next(v) then
-- p = P(k) * make(v)
-- else
-- p = P(k)
-- end
-- else
-- if next(v) then
-- p = p + P(k) * make(v)
-- else
-- p = p + P(k)
-- end
-- end
-- end
-- return p
-- end
-- local function make(t)
-- local p = P(false)
-- local keys = sortedkeys(t)
-- for i=1,#keys do
-- local k = keys[i]
-- local v = t[k]
-- if next(v) then
-- p = p + P(k) * make(v)
-- else
-- p = p + P(k)
-- end
-- end
-- return p
-- end
-- function lpeg.utfchartabletopattern(list) -- goes to util-lpg
-- local tree = { }
-- for i=1,#list do
-- local t = tree
-- for c in gmatch(list[i],".") do
-- local tc = t[c]
-- if not tc then
-- tc = { }
-- t[c] = tc
-- end
-- t = tc
-- end
-- end
-- return make(tree)
-- end
local p_false = P(false)
local p_true = P(true)
-- local function make(t,hash)
-- local p = p_false
-- local keys = sortedkeys(t)
-- for i=1,#keys do
-- local k = keys[i]
-- local v = t[k]
-- local h = hash[v]
-- if h then
-- if next(v) then
-- p = p + P(k) * (make(v,hash) + p_true)
-- else
-- p = p + P(k) * p_true
-- end
-- else
-- if next(v) then
-- p = p + P(k) * make(v,hash)
-- else
-- p = p + P(k)
-- end
-- end
-- end
-- return p
-- end
-- local function make(t,hash)
-- local p = p_false
-- local keys = sortedkeys(t)
-- local function making(t,w)
-- local p = p_false
-- local keys = sortedkeys(t)
-- for i=1,#keys do
-- local k = keys[i]
-- local v = t[k]
-- if w then
-- if next(v) then
-- p = p + P(k) * (making(v,w) + p_true)
-- else
-- p = p + P(k) * p_true
-- end
-- else
-- if next(v) then
-- p = p + P(k) * making(v,w)
-- else
-- p = p + P(k)
-- end
-- end
-- end
-- return p
-- end
-- for i=1,#keys do
-- local k = keys[i]
-- local v = t[k]
-- local h = hash[v]
-- if h then
-- if next(v) then
-- p = p + P(k) * (making(v,true) + p_true)
-- else
-- p = p + P(k) * p_true
-- end
-- else
-- if next(v) then
-- p = p + P(k) * making(v,false)
-- else
-- p = p + P(k)
-- end
-- end
-- end
-- return p
-- end
--
-- function lpeg.utfchartabletopattern(list) -- goes to util-lpg
-- local tree = { }
-- local hash = { }
-- local n = #list
-- if n == 0 then
-- for s in next, list do
-- local t = tree
-- for c in gmatch(s,".") do
-- local tc = t[c]
-- if not tc then
-- tc = { }
-- t[c] = tc
-- end
-- t = tc
-- end
-- hash[t] = s
-- end
-- else
-- for i=1,n do
-- local t = tree
-- local s = list[i]
-- for c in gmatch(s,".") do
-- local tc = t[c]
-- if not tc then
-- tc = { }
-- t[c] = tc
-- end
-- t = tc
-- end
-- hash[t] = s
-- end
-- end
-- return make(tree,hash)
-- end
local function make(t,hash)
local p = p_false
local keys = sortedkeys(t)
local function making(t,w)
local p = p_false
local keys = sortedkeys(t)
for i=1,#keys do
local k = keys[i]
local v = t[k]
if w then
if v == true then
p = p + P(k) * p_true
else
p = p + P(k) * (making(v,w) + p_true)
end
else
if v == true then
p = p + P(k)
else
p = p + P(k) * making(v,w)
end
end
end
return p
end
for i=1,#keys do
local k = keys[i]
local v = t[k]
local h = hash[v]
if h then
if v == true then
p = p + P(k) * p_true
else
p = p + P(k) * (making(v,true) + p_true)
end
else
if v == true then
p = p + P(k)
else
p = p + P(k) * making(v,false)
end
end
end
return p
end
function lpeg.utfchartabletopattern(list) -- goes to util-lpg
local tree = { }
-- local hash = { }
local hash
local n = #list
if n == 0 then
hash = list
for s in next, list do
local t = tree
local p, pk
for c in gmatch(s,".") do
if t == true then
t = { [c] = true }
p[pk] = t
p = t
t = true
else
local tc = t[c]
if not tc then
tc = true
t[c] = tc
end
p = t
t = tc
end
pk = c
end
end
else
hash = { }
for i=1,n do
local t = tree
local s = list[i]
local p, pk
for c in gmatch(s,".") do
if t == true then
t = { [c] = true }
p[pk] = t
p = t
t = true
else
local tc = t[c]
if not tc then
tc = true
t[c] = true
end
p = t
t = tc
end
pk = c
end
hash[s] = true
end
end
return make(tree,hash)
end
-- lpeg.utfchartabletopattern {
-- utfchar(0x00A0), -- nbsp
-- utfchar(0x2000), -- enquad
-- utfchar(0x2001), -- emquad
-- utfchar(0x2002), -- enspace
-- utfchar(0x2003), -- emspace
-- utfchar(0x2004), -- threeperemspace
-- utfchar(0x2005), -- fourperemspace
-- utfchar(0x2006), -- sixperemspace
-- utfchar(0x2007), -- figurespace
-- utfchar(0x2008), -- punctuationspace
-- utfchar(0x2009), -- breakablethinspace
-- utfchar(0x200A), -- hairspace
-- utfchar(0x200B), -- zerowidthspace
-- utfchar(0x202F), -- narrownobreakspace
-- utfchar(0x205F), -- math thinspace
-- }
-- a few handy ones:
--
-- faster than find(str,"[\n\r]") when match and # > 7 and always faster when # > 3
patterns.containseol = lpeg.finder(eol) -- (1-eol)^0 * eol
-- The next pattern^n variant is based on an approach suggested
-- by Roberto: constructing a big repetition in chunks.
--
-- Being sparse is not needed, and only complicate matters and
-- the number of redundant entries is not that large.
local function nextstep(n,step,result)
local m = n % step -- mod(n,step)
local d = floor(n/step) -- div(n,step)
if d > 0 then
local v = V(tostring(step))
local s = result.start
for i=1,d do
if s then
s = v * s
else
s = v
end
end
result.start = s
end
if step > 1 and result.start then
local v = V(tostring(step/2))
result[tostring(step)] = v * v
end
if step > 0 then
return nextstep(m,step/2,result)
else
return result
end
end
function lpeg.times(pattern,n)
return P(nextstep(n,2^16,{ "start", ["1"] = pattern }))
end
-- local p = lpeg.Cs((1 - lpeg.times(lpeg.P("AB"),25))^1)
-- local s = "12" .. string.rep("AB",20) .. "34" .. string.rep("AB",30) .. "56"
-- inspect(p)
-- print(lpeg.match(p,s))
-- moved here (before util-str)
----- digit = R("09")
----- period = P(".")
----- zero = P("0")
local trailingzeros = zero^0 * -digit -- suggested by Roberto R
local case_1 = period * trailingzeros / ""
local case_2 = period * (digit - trailingzeros)^1 * (trailingzeros / "")
local number = digit^1 * (case_1 + case_2)
local stripper = Cs((number + 1)^0)
lpeg.patterns.stripzeros = stripper
-- local sample = "bla 11.00 bla 11 bla 0.1100 bla 1.00100 bla 0.00 bla 0.001 bla 1.1100 bla 0.100100100 bla 0.00100100100"
-- collectgarbage("collect")
-- str = string.rep(sample,10000)
-- local ts = os.clock()
-- lpegmatch(stripper,str)
-- print(#str, os.clock()-ts, lpegmatch(stripper,sample))
-- for practical reasone we keep this here:
local byte_to_HEX = { }
local byte_to_hex = { }
local byte_to_dec = { } -- for md5
local hex_to_byte = { }
for i=0,255 do
local H = format("%02X",i)
local h = format("%02x",i)
local d = format("%03i",i)
local c = char(i)
byte_to_HEX[c] = H
byte_to_hex[c] = h
byte_to_dec[c] = d
hex_to_byte[h] = c
hex_to_byte[H] = c
end
local hextobyte = P(2)/hex_to_byte
local bytetoHEX = P(1)/byte_to_HEX
local bytetohex = P(1)/byte_to_hex
local bytetodec = P(1)/byte_to_dec
local hextobytes = Cs(hextobyte^0)
local bytestoHEX = Cs(bytetoHEX^0)
local bytestohex = Cs(bytetohex^0)
local bytestodec = Cs(bytetodec^0)
patterns.hextobyte = hextobyte
patterns.bytetoHEX = bytetoHEX
patterns.bytetohex = bytetohex
patterns.bytetodec = bytetodec
patterns.hextobytes = hextobytes
patterns.bytestoHEX = bytestoHEX
patterns.bytestohex = bytestohex
patterns.bytestodec = bytestodec
function string.toHEX(s)
if not s or s == "" then
return s
else
return lpegmatch(bytestoHEX,s)
end
end
function string.tohex(s)
if not s or s == "" then
return s
else
return lpegmatch(bytestohex,s)
end
end
function string.todec(s)
if not s or s == "" then
return s
else
return lpegmatch(bytestodec,s)
end
end
function string.tobytes(s)
if not s or s == "" then
return s
else
return lpegmatch(hextobytes,s)
end
end
-- local h = "ADFE0345"
-- local b = lpegmatch(patterns.hextobytes,h)
-- print(h,b,string.tohex(b),string.toHEX(b))
|