summaryrefslogtreecommitdiffstats
path: root/src/LexPerl.cpp
blob: 4a42bc29f57f46e663a6c68b7fcbffe3d537ae2b (plain)
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
// Scintilla source code edit control
/** @file LexPerl.cxx
 ** Lexer for subset of Perl.
 **/
// Copyright 1998-2005 by Neil Hodgson <neilh@scintilla.org>
// Lexical analysis fixes by Kein-Hong Man <mkh@pl.jaring.my>
// The License.txt file describes the conditions under which this software may be distributed.

#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <stdio.h>
#include <stdarg.h>

#include "Platform.h"

#include "PropSet.h"
#include "Accessor.h"
#include "KeyWords.h"
#include "Scintilla.h"
#include "SciLexer.h"

#define PERLNUM_BINARY 1    // order is significant: 1-4 cannot have a dot
#define PERLNUM_HEX 2
#define PERLNUM_OCTAL 3
#define PERLNUM_FLOAT 4     // actually exponent part
#define PERLNUM_DECIMAL 5   // 1-5 are numbers; 6-7 are strings
#define PERLNUM_VECTOR 6
#define PERLNUM_V_VECTOR 7
#define PERLNUM_BAD 8

#define BACK_NONE 0         // lookback state for bareword disambiguation:
#define BACK_OPERATOR 1     // whitespace/comments are insignificant
#define BACK_KEYWORD 2      // operators/keywords are needed for disambiguation

#define HERE_DELIM_MAX 256

static inline bool isEOLChar(char ch) {
	return (ch == '\r') || (ch == '\n');
}

static bool isSingleCharOp(char ch) {
	char strCharSet[2];
	strCharSet[0] = ch;
	strCharSet[1] = '\0';
	return (NULL != strstr("rwxoRWXOezsfdlpSbctugkTBMAC", strCharSet));
}

static inline bool isPerlOperator(char ch) {
	if (ch == '^' || ch == '&' || ch == '\\' ||
	        ch == '(' || ch == ')' || ch == '-' || ch == '+' ||
	        ch == '=' || ch == '|' || ch == '{' || ch == '}' ||
	        ch == '[' || ch == ']' || ch == ':' || ch == ';' ||
	        ch == '>' || ch == ',' ||
	        ch == '?' || ch == '!' || ch == '.' || ch == '~')
		return true;
	// these chars are already tested before this call
	// ch == '%' || ch == '*' || ch == '<' || ch == '/' ||
	return false;
}

static bool isPerlKeyword(unsigned int start, unsigned int end, WordList &keywords, Accessor &styler) {
	char s[100];
    unsigned int i, len = end - start;
    if (len > 30) { len = 30; }
	for (i = 0; i < len; i++, start++) s[i] = styler[start];
    s[i] = '\0';
	return keywords.InList(s);
}

// Note: as lexer uses chars, UTF-8 bytes are considered as <0 values
// Note: iswordchar() was used in only one place in LexPerl, it is
// unnecessary as '.' is processed as the concatenation operator, so
// only isWordStart() is used in LexPerl

static inline bool isWordStart(char ch) {
	return !isascii(ch) || isalnum(ch) || ch == '_';
}

static inline bool isEndVar(char ch) {
	return isascii(ch) && !isalnum(ch) && ch != '#' && ch != '$' &&
	       ch != '_' && ch != '\'';
}

static inline bool isNonQuote(char ch) {
	return !isascii(ch) || isalnum(ch) || ch == '_';
}

static inline char actualNumStyle(int numberStyle) {
    if (numberStyle == PERLNUM_VECTOR || numberStyle == PERLNUM_V_VECTOR) {
        return SCE_PL_STRING;
    } else if (numberStyle == PERLNUM_BAD) {
        return SCE_PL_ERROR;
    }
    return SCE_PL_NUMBER;
}

static bool isMatch(Accessor &styler, int lengthDoc, int pos, const char *val) {
	if ((pos + static_cast<int>(strlen(val))) >= lengthDoc) {
		return false;
	}
	while (*val) {
		if (*val != styler[pos++]) {
			return false;
		}
		val++;
	}
	return true;
}

static char opposite(char ch) {
	if (ch == '(')
		return ')';
	if (ch == '[')
		return ']';
	if (ch == '{')
		return '}';
	if (ch == '<')
		return '>';
	return ch;
}

static void ColourisePerlDoc(unsigned int startPos, int length, int initStyle,
                             WordList *keywordlists[], Accessor &styler) {

	// Lexer for perl often has to backtrack to start of current style to determine
	// which characters are being used as quotes, how deeply nested is the
	// start position and what the termination string is for here documents

	WordList &keywords = *keywordlists[0];

	class HereDocCls {
	public:
		int State;		// 0: '<<' encountered
		// 1: collect the delimiter
		// 2: here doc text (lines after the delimiter)
		char Quote;		// the char after '<<'
		bool Quoted;		// true if Quote in ('\'','"','`')
		int DelimiterLength;	// strlen(Delimiter)
		char *Delimiter;	// the Delimiter, 256: sizeof PL_tokenbuf
		HereDocCls() {
			State = 0;
            Quote = 0;
            Quoted = false;
			DelimiterLength = 0;
			Delimiter = new char[HERE_DELIM_MAX];
			Delimiter[0] = '\0';
		}
		~HereDocCls() {
			delete []Delimiter;
		}
	};
	HereDocCls HereDoc;	// TODO: FIFO for stacked here-docs

	class QuoteCls {
		public:
		int  Rep;
		int  Count;
		char Up;
		char Down;
		QuoteCls() {
			this->New(1);
		}
		void New(int r) {
			Rep   = r;
			Count = 0;
			Up    = '\0';
			Down  = '\0';
		}
		void Open(char u) {
			Count++;
			Up    = u;
			Down  = opposite(Up);
		}
	};
	QuoteCls Quote;

	int state = initStyle;
	char numState = PERLNUM_DECIMAL;
	int dotCount = 0;
	unsigned int lengthDoc = startPos + length;
	//int sookedpos = 0; // these have no apparent use, see POD state
	//char sooked[100];
	//sooked[sookedpos] = '\0';

	// If in a long distance lexical state, seek to the beginning to find quote characters
	// Perl strings can be multi-line with embedded newlines, so backtrack.
	// Perl numbers have additional state during lexing, so backtrack too.
	if (state == SCE_PL_HERE_Q || state == SCE_PL_HERE_QQ || state == SCE_PL_HERE_QX) {
		while ((startPos > 1) && (styler.StyleAt(startPos) != SCE_PL_HERE_DELIM)) {
			startPos--;
		}
		startPos = styler.LineStart(styler.GetLine(startPos));
		state = styler.StyleAt(startPos - 1);
	}
	if ( state == SCE_PL_STRING_Q
	|| state == SCE_PL_STRING_QQ
	|| state == SCE_PL_STRING_QX
	|| state == SCE_PL_STRING_QR
	|| state == SCE_PL_STRING_QW
	|| state == SCE_PL_REGEX
	|| state == SCE_PL_REGSUBST
	|| state == SCE_PL_STRING
	|| state == SCE_PL_BACKTICKS
	|| state == SCE_PL_CHARACTER
	|| state == SCE_PL_NUMBER
	|| state == SCE_PL_IDENTIFIER
    || state == SCE_PL_ERROR
	) {
		while ((startPos > 1) && (styler.StyleAt(startPos - 1) == state)) {
			startPos--;
		}
		state = SCE_PL_DEFAULT;
	}

    // lookback at start of lexing to set proper state for backflag
    // after this, they are updated when elements are lexed
    int backflag = BACK_NONE;
    unsigned int backPos = startPos;
    if (backPos > 0) {
        backPos--;
        int sty = SCE_PL_DEFAULT;
        while ((backPos > 0) && (sty = styler.StyleAt(backPos),
               sty == SCE_PL_DEFAULT || sty == SCE_PL_COMMENTLINE))
            backPos--;
        if (sty == SCE_PL_OPERATOR)
            backflag = BACK_OPERATOR;
        else if (sty == SCE_PL_WORD)
            backflag = BACK_KEYWORD;
    }

	styler.StartAt(startPos);
	char chPrev = styler.SafeGetCharAt(startPos - 1);
	if (startPos == 0)
		chPrev = '\n';
	char chNext = styler[startPos];
	styler.StartSegment(startPos);

	for (unsigned int i = startPos; i < lengthDoc; i++) {
		char ch = chNext;
		// if the current character is not consumed due to the completion of an
		// earlier style, lexing can be restarted via a simple goto
	restartLexer:
		chNext = styler.SafeGetCharAt(i + 1);
		char chNext2 = styler.SafeGetCharAt(i + 2);

		if (styler.IsLeadByte(ch)) {
			chNext = styler.SafeGetCharAt(i + 2);
			chPrev = ' ';
			i += 1;
			continue;
		}
		if ((chPrev == '\r' && ch == '\n')) {	// skip on DOS/Windows
			styler.ColourTo(i, state);
			chPrev = ch;
			continue;
		}

		if (HereDoc.State == 1 && isEOLChar(ch)) {
			// Begin of here-doc (the line after the here-doc delimiter):
			// Lexically, the here-doc starts from the next line after the >>, but the
			// first line of here-doc seem to follow the style of the last EOL sequence
			HereDoc.State = 2;
			if (HereDoc.Quoted) {
				if (state == SCE_PL_HERE_DELIM) {
					// Missing quote at end of string! We are stricter than perl.
					// Colour here-doc anyway while marking this bit as an error.
					state = SCE_PL_ERROR;
				}
				styler.ColourTo(i - 1, state);
				switch (HereDoc.Quote) {
				case '\'':
					state = SCE_PL_HERE_Q ;
					break;
				case '"':
					state = SCE_PL_HERE_QQ;
					break;
				case '`':
					state = SCE_PL_HERE_QX;
					break;
				}
			} else {
				styler.ColourTo(i - 1, state);
				switch (HereDoc.Quote) {
				case '\\':
					state = SCE_PL_HERE_Q ;
					break;
				default :
					state = SCE_PL_HERE_QQ;
				}
			}
		}

		if (state == SCE_PL_DEFAULT) {
			if ((isascii(ch) && isdigit(ch)) || (isascii(chNext) && isdigit(chNext) &&
				(ch == '.' || ch == 'v'))) {
				state = SCE_PL_NUMBER;
                backflag = BACK_NONE;
				numState = PERLNUM_DECIMAL;
				dotCount = 0;
				if (ch == '0') {	// hex,bin,octal
					if (chNext == 'x') {
						numState = PERLNUM_HEX;
					} else if (chNext == 'b') {
                        numState = PERLNUM_BINARY;
                    } else if (isascii(chNext) && isdigit(chNext)) {
                        numState = PERLNUM_OCTAL;
                    }
                    if (numState != PERLNUM_DECIMAL) {
						i++;
						ch = chNext;
						chNext = chNext2;
                    }
				} else if (ch == 'v') {	// vector
					numState = PERLNUM_V_VECTOR;
				}
			} else if (isWordStart(ch)) {
                // if immediately prefixed by '::', always a bareword
                state = SCE_PL_WORD;
                if (chPrev == ':' && styler.SafeGetCharAt(i - 2) == ':') {
                    state = SCE_PL_IDENTIFIER;
                }
                unsigned int kw = i + 1;
                // first check for possible quote-like delimiter
				if (ch == 's' && !isNonQuote(chNext)) {
					state = SCE_PL_REGSUBST;
					Quote.New(2);
				} else if (ch == 'm' && !isNonQuote(chNext)) {
					state = SCE_PL_REGEX;
					Quote.New(1);
				} else if (ch == 'q' && !isNonQuote(chNext)) {
					state = SCE_PL_STRING_Q;
					Quote.New(1);
				} else if (ch == 'y' && !isNonQuote(chNext)) {
					state = SCE_PL_REGSUBST;
					Quote.New(2);
				} else if (ch == 't' && chNext == 'r' && !isNonQuote(chNext2)) {
					state = SCE_PL_REGSUBST;
					Quote.New(2);
                    kw++;
				} else if (ch == 'q' && (chNext == 'q' || chNext == 'r' || chNext == 'w' || chNext == 'x') && !isNonQuote(chNext2)) {
					if      (chNext == 'q') state = SCE_PL_STRING_QQ;
					else if (chNext == 'x') state = SCE_PL_STRING_QX;
					else if (chNext == 'r') state = SCE_PL_STRING_QR;
					else if (chNext == 'w') state = SCE_PL_STRING_QW;
					Quote.New(1);
                    kw++;
				} else if (ch == 'x' && (chNext == '=' ||	// repetition
                           !isWordStart(chNext) ||
                           (isdigit(chPrev) && isdigit(chNext)))) {
                    state = SCE_PL_OPERATOR;
                }
                // if potentially a keyword, scan forward and grab word, then check
                // if it's really one; if yes, disambiguation test is performed
                // otherwise it is always a bareword and we skip a lot of scanning
                // note: keywords assumed to be limited to [_a-zA-Z] only
                if (state == SCE_PL_WORD) {
                    while (isWordStart(styler.SafeGetCharAt(kw))) kw++;
                    if (!isPerlKeyword(styler.GetStartSegment(), kw, keywords, styler)) {
                        state = SCE_PL_IDENTIFIER;
                    }
                }
                // if already SCE_PL_IDENTIFIER, then no ambiguity, skip this
                // for quote-like delimiters/keywords, attempt to disambiguate
                // to select for bareword, change state -> SCE_PL_IDENTIFIER
                if (state != SCE_PL_IDENTIFIER && i > 0) {
                    unsigned int j = i;
                    bool moreback = false;      // true if passed newline/comments
                    bool brace = false;         // true if opening brace found
                    char ch2;
                    // first look backwards past whitespace/comments for EOLs
                    // if BACK_NONE, neither operator nor keyword, so skip test
                    if (backflag != BACK_NONE) {
                        while (--j > backPos) {
                            if (isEOLChar(styler.SafeGetCharAt(j)))
                                moreback = true;
                        }
                        ch2 = styler.SafeGetCharAt(j);
                        if (ch2 == '{' && !moreback) {
                            // {bareword: possible variable spec
                            brace = true;
                        } else if ((ch2 == '&' && styler.SafeGetCharAt(j - 1) != '&')
                                // &bareword: subroutine call
                                || (ch2 == '>' && styler.SafeGetCharAt(j - 1) == '-')
                                // ->bareword: part of variable spec
                                || (ch2 == 'b' && styler.Match(j - 2, "su"))) {
                                // sub bareword: subroutine declaration
                                // (implied BACK_KEYWORD, no keywords end in 'sub'!)
                            state = SCE_PL_IDENTIFIER;
                        }
                        // if status still ambiguous, look forward after word past
                        // tabs/spaces only; if ch2 isn't one of '[{(,' it can never
                        // match anything, so skip the whole thing
                        j = kw;
                        if (state != SCE_PL_IDENTIFIER
                            && (ch2 == '{' || ch2 == '(' || ch2 == '['|| ch2 == ',')
                            && kw < lengthDoc) {
                            while (ch2 = styler.SafeGetCharAt(j),
                                   (ch2 == ' ' || ch2 == '\t') && j < lengthDoc) {
                                j++;
                            }
                            if ((ch2 == '}' && brace)
                             // {bareword}: variable spec
                             || (ch2 == '=' && styler.SafeGetCharAt(j + 1) == '>')) {
                             // [{(, bareword=>: hash literal
                                state = SCE_PL_IDENTIFIER;
                            }
                        }
                    }
                }
                backflag = BACK_NONE;
                // an identifier or bareword
                if (state == SCE_PL_IDENTIFIER) {
                    if ((!isWordStart(chNext) && chNext != '\'')
                        || (chNext == '.' && chNext2 == '.')) {
                        // We need that if length of word == 1!
                        // This test is copied from the SCE_PL_WORD handler.
                        styler.ColourTo(i, SCE_PL_IDENTIFIER);
                        state = SCE_PL_DEFAULT;
                    }
                // a keyword
                } else if (state == SCE_PL_WORD) {
                    i = kw - 1;
                    if (ch == '_' && chNext == '_' &&
                        (isMatch(styler, lengthDoc, styler.GetStartSegment(), "__DATA__")
                      || isMatch(styler, lengthDoc, styler.GetStartSegment(), "__END__"))) {
                        styler.ColourTo(i, SCE_PL_DATASECTION);
                        state = SCE_PL_DATASECTION;
                    } else {
                        styler.ColourTo(i, SCE_PL_WORD);
                        state = SCE_PL_DEFAULT;
                        backflag = BACK_KEYWORD;
                        backPos = i;
                    }
                    ch = styler.SafeGetCharAt(i);
                    chNext = styler.SafeGetCharAt(i + 1);
                // a repetition operator 'x'
                } else if (state == SCE_PL_OPERATOR) {
                    styler.ColourTo(i, SCE_PL_OPERATOR);
                    state = SCE_PL_DEFAULT;
                // quote-like delimiter, skip one char if double-char delimiter
                } else {
                    i = kw - 1;
                    chNext = styler.SafeGetCharAt(i + 1);
                }
			} else if (ch == '#') {
				state = SCE_PL_COMMENTLINE;
			} else if (ch == '\"') {
				state = SCE_PL_STRING;
				Quote.New(1);
				Quote.Open(ch);
                backflag = BACK_NONE;
			} else if (ch == '\'') {
				if (chPrev == '&') {
					// Archaic call
					styler.ColourTo(i, state);
				} else {
					state = SCE_PL_CHARACTER;
					Quote.New(1);
					Quote.Open(ch);
				}
                backflag = BACK_NONE;
			} else if (ch == '`') {
				state = SCE_PL_BACKTICKS;
				Quote.New(1);
				Quote.Open(ch);
                backflag = BACK_NONE;
			} else if (ch == '$') {
				if ((chNext == '{') || isspacechar(chNext)) {
					styler.ColourTo(i, SCE_PL_SCALAR);
				} else {
					state = SCE_PL_SCALAR;
					if ((chNext == '`' && chNext2 == '`')
                     || (chNext == ':' && chNext2 == ':')) {
						i += 2;
						ch = styler.SafeGetCharAt(i);
						chNext = styler.SafeGetCharAt(i + 1);
					} else {
						i++;
						ch = chNext;
						chNext = chNext2;
					}
				}
                backflag = BACK_NONE;
			} else if (ch == '@') {
				if (!isascii(chNext) || isalpha(chNext) || chNext == '#' || chNext == '$'
					|| chNext == '_' || chNext == '+' || chNext == '-') {
					state = SCE_PL_ARRAY;
                } else if (chNext == ':' && chNext2 == ':') {
                    state = SCE_PL_ARRAY;
                    i += 2;
                    ch = styler.SafeGetCharAt(i);
                    chNext = styler.SafeGetCharAt(i + 1);
				} else if (chNext != '{' && chNext != '[') {
					styler.ColourTo(i, SCE_PL_ARRAY);
				} else {
					styler.ColourTo(i, SCE_PL_ARRAY);
				}
                backflag = BACK_NONE;
			} else if (ch == '%') {
				if (!isascii(chNext) || isalpha(chNext) || chNext == '#' || chNext == '$'
                    || chNext == '_' || chNext == '!' || chNext == '^') {
					state = SCE_PL_HASH;
                    i++;
                    ch = chNext;
                    chNext = chNext2;
                } else if (chNext == ':' && chNext2 == ':') {
                    state = SCE_PL_HASH;
                    i += 2;
                    ch = styler.SafeGetCharAt(i);
                    chNext = styler.SafeGetCharAt(i + 1);
				} else if (chNext == '{') {
					styler.ColourTo(i, SCE_PL_HASH);
				} else {
					styler.ColourTo(i, SCE_PL_OPERATOR);
				}
                backflag = BACK_NONE;
			} else if (ch == '*') {
                char strch[2];
                strch[0] = chNext;
                strch[1] = '\0';
                if (chNext == ':' && chNext2 == ':') {
                    state = SCE_PL_SYMBOLTABLE;
                    i += 2;
                    ch = styler.SafeGetCharAt(i);
                    chNext = styler.SafeGetCharAt(i + 1);
				} else if (!isascii(chNext) || isalpha(chNext) || chNext == '_'
                        || NULL != strstr("^/|,\\\";#%^:?<>)[]", strch)) {
					state = SCE_PL_SYMBOLTABLE;
                    i++;
                    ch = chNext;
                    chNext = chNext2;
				} else if (chNext == '{') {
					styler.ColourTo(i, SCE_PL_SYMBOLTABLE);
				} else {
					if (chNext == '*') {	// exponentiation
						i++;
						ch = chNext;
						chNext = chNext2;
					}
					styler.ColourTo(i, SCE_PL_OPERATOR);
				}
                backflag = BACK_NONE;
			} else if (ch == '/' || (ch == '<' && chNext == '<')) {
				// Explicit backward peeking to set a consistent preferRE for
				// any slash found, so no longer need to track preferRE state.
				// Find first previous significant lexed element and interpret.
                // Test for HERE doc start '<<' shares this code, helps to
                // determine if it should be an operator.
				bool preferRE = false;
                bool isHereDoc = (ch == '<');
                bool hereDocSpace = false;      // these are for corner case:
                bool hereDocScalar = false;     // SCALAR [whitespace] '<<'
				unsigned int bk = (i > 0)? i - 1: 0;
				char bkch;
				styler.Flush();
                if (styler.StyleAt(bk) == SCE_PL_DEFAULT)
                    hereDocSpace = true;
				while ((bk > 0) && (styler.StyleAt(bk) == SCE_PL_DEFAULT ||
					styler.StyleAt(bk) == SCE_PL_COMMENTLINE)) {
					bk--;
				}
				if (bk == 0) {
					// position 0 won't really be checked; rarely happens
					// hard to fix due to an unsigned index i
					preferRE = true;
				} else {
					int bkstyle = styler.StyleAt(bk);
					bkch = styler.SafeGetCharAt(bk);
					switch(bkstyle) {
					case SCE_PL_OPERATOR:
						preferRE = true;
						if (bkch == ')' || bkch == ']') {
							preferRE = false;
						} else if (bkch == '}') {
							// backtrack further, count balanced brace pairs
							// if a brace pair found, see if it's a variable
							int braceCount = 1;
							while (--bk > 0) {
								bkstyle = styler.StyleAt(bk);
								if (bkstyle == SCE_PL_OPERATOR) {
									bkch = styler.SafeGetCharAt(bk);
									if (bkch == ';') {	// early out
										break;
									} else if (bkch == '}') {
										braceCount++;
									} else if (bkch == '{') {
										if (--braceCount == 0)
											break;
									}
								}
							}
							if (bk == 0) {
								// at beginning, true
							} else if (braceCount == 0) {
								// balanced { found, bk>0, skip more whitespace
								if (styler.StyleAt(--bk) == SCE_PL_DEFAULT) {
									while (bk > 0) {
										bkstyle = styler.StyleAt(--bk);
										if (bkstyle != SCE_PL_DEFAULT)
											break;
									}
								}
								bkstyle = styler.StyleAt(bk);
								if (bkstyle == SCE_PL_SCALAR
								 || bkstyle == SCE_PL_ARRAY
								 || bkstyle == SCE_PL_HASH
								 || bkstyle == SCE_PL_SYMBOLTABLE
								 || bkstyle == SCE_PL_OPERATOR) {
									preferRE = false;
								}
							}
						}
						break;
					case SCE_PL_IDENTIFIER:
						preferRE = true;
						if (bkch == '>') {	// inputsymbol
							preferRE = false;
							break;
						}
						// backtrack to find "->" or "::" before identifier
						while (bk > 0 && styler.StyleAt(bk) == SCE_PL_IDENTIFIER) {
							bk--;
						}
						while (bk > 0) {
							bkstyle = styler.StyleAt(bk);
							if (bkstyle == SCE_PL_DEFAULT ||
							    bkstyle == SCE_PL_COMMENTLINE) {
							} else if (bkstyle == SCE_PL_OPERATOR) {
								// gcc 3.2.3 bloats if more compact form used
								bkch = styler.SafeGetCharAt(bk);
								if (bkch == '>') { // "->"
									if (styler.SafeGetCharAt(bk - 1) == '-') {
										preferRE = false;
										break;
									}
								} else if (bkch == ':') { // "::"
									if (styler.SafeGetCharAt(bk - 1) == ':') {
										preferRE = false;
										break;
									}
								}
							} else {// bare identifier, usually a function call but Perl
								// optimizes them as pseudo-constants, then the next
								// '/' will be a divide; favour divide over regex
								// if there is a whitespace after the '/'
								if (isspacechar(chNext)) {
									preferRE = false;
								}
								break;
							}
							bk--;
						}
						break;
                    case SCE_PL_SCALAR:     // for $var<< case
                        hereDocScalar = true;
                        break;
					// other styles uses the default, preferRE=false
					case SCE_PL_WORD:
					case SCE_PL_POD:
					case SCE_PL_POD_VERB:
					case SCE_PL_HERE_Q:
					case SCE_PL_HERE_QQ:
					case SCE_PL_HERE_QX:
						preferRE = true;
						break;
					}
				}
                if (isHereDoc) {    // handle HERE doc
                    // if SCALAR whitespace '<<', *always* a HERE doc
                    if (preferRE || (hereDocSpace && hereDocScalar)) {
                        state = SCE_PL_HERE_DELIM;
                        HereDoc.State = 0;
                    } else {        // << operator
						i++;
						ch = chNext;
						chNext = chNext2;
                        styler.ColourTo(i, SCE_PL_OPERATOR);
                    }
                } else {            // handle regexp
                    if (preferRE) {
                        state = SCE_PL_REGEX;
                        Quote.New(1);
                        Quote.Open(ch);
                    } else {        // / operator
                        styler.ColourTo(i, SCE_PL_OPERATOR);
                    }
                }
                backflag = BACK_NONE;
			} else if (ch == '<') {
				// looks forward for matching > on same line
				unsigned int fw = i + 1;
				while (fw < lengthDoc) {
					char fwch = styler.SafeGetCharAt(fw);
					if (fwch == ' ') {
						if (styler.SafeGetCharAt(fw-1) != '\\' ||
						    styler.SafeGetCharAt(fw-2) != '\\')
						break;
					} else if (isEOLChar(fwch) || isspacechar(fwch)) {
						break;
					} else if (fwch == '>') {
						if ((fw - i) == 2 &&	// '<=>' case
						    styler.SafeGetCharAt(fw-1) == '=') {
							styler.ColourTo(fw, SCE_PL_OPERATOR);
						} else {
							styler.ColourTo(fw, SCE_PL_IDENTIFIER);
						}
						i = fw;
						ch = fwch;
						chNext = styler.SafeGetCharAt(i+1);
					}
					fw++;
				}
				styler.ColourTo(i, SCE_PL_OPERATOR);
                backflag = BACK_NONE;
			} else if (ch == '='	// POD
			           && isalpha(chNext)
			           && (isEOLChar(chPrev))) {
				state = SCE_PL_POD;
                backflag = BACK_NONE;
				//sookedpos = 0;
				//sooked[sookedpos] = '\0';
			} else if (ch == '-'	// file test operators
			           && isSingleCharOp(chNext)
			           && !isalnum((chNext2 = styler.SafeGetCharAt(i+2)))) {
				styler.ColourTo(i + 1, SCE_PL_WORD);
				state = SCE_PL_DEFAULT;
				i++;
				ch = chNext;
				chNext = chNext2;
                backflag = BACK_NONE;
			} else if (isPerlOperator(ch)) {
				if (ch == '.' && chNext == '.') { // .. and ...
					i++;
					if (chNext2 == '.') { i++; }
					state = SCE_PL_DEFAULT;
					ch = styler.SafeGetCharAt(i);
					chNext = styler.SafeGetCharAt(i + 1);
				}
				styler.ColourTo(i, SCE_PL_OPERATOR);
                backflag = BACK_OPERATOR;
                backPos = i;
			} else {
				// keep colouring defaults to make restart easier
				styler.ColourTo(i, SCE_PL_DEFAULT);
			}
		} else if (state == SCE_PL_NUMBER) {
			if (ch == '.') {
				if (chNext == '.') {
					// double dot is always an operator
					goto numAtEnd;
				} else if (numState <= PERLNUM_FLOAT) {
					// non-decimal number or float exponent, consume next dot
					styler.ColourTo(i - 1, SCE_PL_NUMBER);
					styler.ColourTo(i, SCE_PL_OPERATOR);
					state = SCE_PL_DEFAULT;
				} else { // decimal or vectors allows dots
					dotCount++;
					if (numState == PERLNUM_DECIMAL) {
						if (dotCount > 1) {
							if (isdigit(chNext)) { // really a vector
								numState = PERLNUM_VECTOR;
							} else	// number then dot
								goto numAtEnd;
						}
					} else { // vectors
						if (!isdigit(chNext))	// vector then dot
							goto numAtEnd;
					}
				}
			} else if (ch == '_' && numState == PERLNUM_DECIMAL) {
				if (!isdigit(chNext)) {
					goto numAtEnd;
				}
			} else if (!isascii(ch) || isalnum(ch)) {
				if (numState == PERLNUM_VECTOR || numState == PERLNUM_V_VECTOR) {
					if (!isascii(ch) || isalpha(ch)) {
						if (dotCount == 0) { // change to word
							state = SCE_PL_IDENTIFIER;
						} else { // vector then word
							goto numAtEnd;
						}
					}
				} else if (numState == PERLNUM_DECIMAL) {
					if (ch == 'E' || ch == 'e') { // exponent
						numState = PERLNUM_FLOAT;
						if (chNext == '+' || chNext == '-') {
							i++;
							ch = chNext;
							chNext = chNext2;
						}
					} else if (!isascii(ch) || !isdigit(ch)) { // number then word
						goto numAtEnd;
					}
				} else if (numState == PERLNUM_FLOAT) {
					if (!isdigit(ch)) { // float then word
						goto numAtEnd;
					}
				} else if (numState == PERLNUM_OCTAL) {
                    if (!isdigit(ch))
                        goto numAtEnd;
                    else if (ch > '7')
                        numState = PERLNUM_BAD;
                } else if (numState == PERLNUM_BINARY) {
                    if (!isdigit(ch))
                        goto numAtEnd;
                    else if (ch > '1')
                        numState = PERLNUM_BAD;
                } else if (numState == PERLNUM_HEX) {
                    int ch2 = toupper(ch);
                    if (!isdigit(ch) && !(ch2 >= 'A' && ch2 <= 'F'))
                        goto numAtEnd;
				} else {//(numState == PERLNUM_BAD) {
                    if (!isdigit(ch))
                        goto numAtEnd;
                }
			} else {
				// complete current number or vector
			numAtEnd:
				styler.ColourTo(i - 1, actualNumStyle(numState));
				state = SCE_PL_DEFAULT;
				goto restartLexer;
			}
		} else if (state == SCE_PL_IDENTIFIER) {
			if (!isWordStart(chNext) && chNext != '\'') {
				styler.ColourTo(i, SCE_PL_IDENTIFIER);
				state = SCE_PL_DEFAULT;
				ch = ' ';
			}
		} else {
			if (state == SCE_PL_COMMENTLINE) {
				if (isEOLChar(ch)) {
					styler.ColourTo(i - 1, state);
					state = SCE_PL_DEFAULT;
					goto restartLexer;
				} else if (isEOLChar(chNext)) {
					styler.ColourTo(i, state);
					state = SCE_PL_DEFAULT;
				}
			} else if (state == SCE_PL_HERE_DELIM) {
				//
				// From perldata.pod:
				// ------------------
				// A line-oriented form of quoting is based on the shell ``here-doc''
				// syntax.
				// Following a << you specify a string to terminate the quoted material,
				// and all lines following the current line down to the terminating
				// string are the value of the item.
				// The terminating string may be either an identifier (a word),
				// or some quoted text.
				// If quoted, the type of quotes you use determines the treatment of
				// the text, just as in regular quoting.
				// An unquoted identifier works like double quotes.
				// There must be no space between the << and the identifier.
				// (If you put a space it will be treated as a null identifier,
				// which is valid, and matches the first empty line.)
				// (This is deprecated, -w warns of this syntax)
				// The terminating string must appear by itself (unquoted and with no
				// surrounding whitespace) on the terminating line.
				//
				// From Bash info:
				// ---------------
				// Specifier format is: <<[-]WORD
				// Optional '-' is for removal of leading tabs from here-doc.
				// Whitespace acceptable after <<[-] operator.
				//
				if (HereDoc.State == 0) { // '<<' encountered
                    bool gotspace = false;
                    unsigned int oldi = i;
                    if (chNext == ' ' || chNext == '\t') {
                        // skip whitespace; legal for quoted delimiters
                        gotspace = true;
                        do {
                            i++;
                            chNext = styler.SafeGetCharAt(i + 1);
                        } while ((i + 1 < lengthDoc) && (chNext == ' ' || chNext == '\t'));
                        chNext2 = styler.SafeGetCharAt(i + 2);
                    }
					HereDoc.State = 1;
					HereDoc.Quote = chNext;
					HereDoc.Quoted = false;
					HereDoc.DelimiterLength = 0;
					HereDoc.Delimiter[HereDoc.DelimiterLength] = '\0';
					if (chNext == '\'' || chNext == '"' || chNext == '`') {
                        // a quoted here-doc delimiter
						i++;
						ch = chNext;
						chNext = chNext2;
						HereDoc.Quoted = true;
					} else if (isspacechar(chNext) || isdigit(chNext) || chNext == '\\'
						|| chNext == '=' || chNext == '$' || chNext == '@'
                        || ((isalpha(chNext) || chNext == '_') && gotspace)) {
						// left shift << or <<= operator cases
                        // restore position if operator
                        i = oldi;
						styler.ColourTo(i, SCE_PL_OPERATOR);
						state = SCE_PL_DEFAULT;
						HereDoc.State = 0;
                        goto restartLexer;
					} else {
						// an unquoted here-doc delimiter, no special handling
                        // (cannot be prefixed by spaces/tabs), or
						// symbols terminates; deprecated zero-length delimiter
					}

				} else if (HereDoc.State == 1) { // collect the delimiter
                    backflag = BACK_NONE;
					if (HereDoc.Quoted) { // a quoted here-doc delimiter
						if (ch == HereDoc.Quote) { // closing quote => end of delimiter
							styler.ColourTo(i, state);
							state = SCE_PL_DEFAULT;
						} else {
							if (ch == '\\' && chNext == HereDoc.Quote) { // escaped quote
								i++;
								ch = chNext;
								chNext = chNext2;
							}
							HereDoc.Delimiter[HereDoc.DelimiterLength++] = ch;
							HereDoc.Delimiter[HereDoc.DelimiterLength] = '\0';
						}
					} else { // an unquoted here-doc delimiter
						if (isalnum(ch) || ch == '_') {
							HereDoc.Delimiter[HereDoc.DelimiterLength++] = ch;
							HereDoc.Delimiter[HereDoc.DelimiterLength] = '\0';
						} else {
							styler.ColourTo(i - 1, state);
							state = SCE_PL_DEFAULT;
							goto restartLexer;
						}
					}
					if (HereDoc.DelimiterLength >= HERE_DELIM_MAX - 1) {
						styler.ColourTo(i - 1, state);
						state = SCE_PL_ERROR;
						goto restartLexer;
					}
				}
			} else if (HereDoc.State == 2) {
				// state == SCE_PL_HERE_Q || state == SCE_PL_HERE_QQ || state == SCE_PL_HERE_QX
				if (isEOLChar(chPrev) && isMatch(styler, lengthDoc, i, HereDoc.Delimiter)) {
					i += HereDoc.DelimiterLength;
					chPrev = styler.SafeGetCharAt(i - 1);
					ch = styler.SafeGetCharAt(i);
					if (isEOLChar(ch)) {
						styler.ColourTo(i - 1, state);
						state = SCE_PL_DEFAULT;
                        backflag = BACK_NONE;
						HereDoc.State = 0;
						goto restartLexer;
					}
					chNext = styler.SafeGetCharAt(i + 1);
				}
			} else if (state == SCE_PL_POD
				|| state == SCE_PL_POD_VERB) {
				if (isEOLChar(chPrev)) {
					if (ch == ' ' || ch == '\t') {
						styler.ColourTo(i - 1, state);
						state = SCE_PL_POD_VERB;
					} else {
						styler.ColourTo(i - 1, state);
						state = SCE_PL_POD;
						if (ch == '=') {
							if (isMatch(styler, lengthDoc, i, "=cut")) {
								styler.ColourTo(i - 1 + 4, state);
								i += 4;
								state = SCE_PL_DEFAULT;
								ch = styler.SafeGetCharAt(i);
								//chNext = styler.SafeGetCharAt(i + 1);
								goto restartLexer;
							}
						}
					}
				}
			} else if (state == SCE_PL_SCALAR	// variable names
				|| state == SCE_PL_ARRAY
				|| state == SCE_PL_HASH
				|| state == SCE_PL_SYMBOLTABLE) {
				if (ch == ':' && chNext == ':') {	// skip ::
					i++;
					ch = chNext;
					chNext = chNext2;
				}
				else if (isEndVar(ch)) {
					if (i == (styler.GetStartSegment() + 1)) {
						// Special variable: $(, $_ etc.
						styler.ColourTo(i, state);
						state = SCE_PL_DEFAULT;
					} else {
						styler.ColourTo(i - 1, state);
						state = SCE_PL_DEFAULT;
						goto restartLexer;
					}
				}
			} else if (state == SCE_PL_REGEX
				|| state == SCE_PL_STRING_QR
				) {
				if (!Quote.Up && !isspacechar(ch)) {
					Quote.Open(ch);
				} else if (ch == '\\' && Quote.Up != '\\') {
					// SG: Is it save to skip *every* escaped char?
					i++;
					ch = chNext;
					chNext = styler.SafeGetCharAt(i + 1);
				} else {
					if (ch == Quote.Down /*&& chPrev != '\\'*/) {
						Quote.Count--;
						if (Quote.Count == 0) {
							Quote.Rep--;
							if (Quote.Up == Quote.Down) {
								Quote.Count++;
							}
						}
						if (!isalpha(chNext)) {
							if (Quote.Rep <= 0) {
								styler.ColourTo(i, state);
								state = SCE_PL_DEFAULT;
								ch = ' ';
							}
						}
					} else if (ch == Quote.Up /*&& chPrev != '\\'*/) {
						Quote.Count++;
					} else if (!isascii(chNext) || !isalpha(chNext)) {
						if (Quote.Rep <= 0) {
							styler.ColourTo(i, state);
							state = SCE_PL_DEFAULT;
							ch = ' ';
						}
					}
				}
			} else if (state == SCE_PL_REGSUBST) {
				if (!Quote.Up && !isspacechar(ch)) {
					Quote.Open(ch);
				} else if (ch == '\\' && Quote.Up != '\\') {
					// SG: Is it save to skip *every* escaped char?
					i++;
					ch = chNext;
					chNext = styler.SafeGetCharAt(i + 1);
				} else {
					if (Quote.Count == 0 && Quote.Rep == 1) {
						/* We matched something like s(...) or tr{...}
						* and are looking for the next matcher characters,
						* which could be either bracketed ({...}) or non-bracketed
						* (/.../).
						*
						* Number-signs are problematic.  If they occur after
						* the close of the first part, treat them like
						* a Quote.Up char, even if they actually start comments.
						*
						* If we find an alnum, we end the regsubst, and punt.
						*
						* Eric Promislow   ericp@activestate.com  Aug 9,2000
						*/
						if (isspacechar(ch)) {
							// Keep going
						}
						else if (!isascii(ch) || isalnum(ch)) {
							styler.ColourTo(i, state);
							state = SCE_PL_DEFAULT;
							ch = ' ';
						} else {
							Quote.Open(ch);
						}
					} else if (ch == Quote.Down /*&& chPrev != '\\'*/) {
						Quote.Count--;
						if (Quote.Count == 0) {
							Quote.Rep--;
						}
						if (!isascii(chNext) || !isalpha(chNext)) {
							if (Quote.Rep <= 0) {
								styler.ColourTo(i, state);
								state = SCE_PL_DEFAULT;
								ch = ' ';
							}
						}
						if (Quote.Up == Quote.Down) {
							Quote.Count++;
						}
					} else if (ch == Quote.Up /*&& chPrev != '\\'*/) {
						Quote.Count++;
					} else if (!isascii(chNext) || !isalpha(chNext)) {
						if (Quote.Rep <= 0) {
							styler.ColourTo(i, state);
							state = SCE_PL_DEFAULT;
							ch = ' ';
						}
					}
				}
			} else if (state == SCE_PL_STRING_Q
				|| state == SCE_PL_STRING_QQ
				|| state == SCE_PL_STRING_QX
				|| state == SCE_PL_STRING_QW
				|| state == SCE_PL_STRING
				|| state == SCE_PL_CHARACTER
				|| state == SCE_PL_BACKTICKS
				) {
				if (!Quote.Down && !isspacechar(ch)) {
					Quote.Open(ch);
				} else if (ch == '\\' && Quote.Up != '\\') {
					i++;
					ch = chNext;
					chNext = styler.SafeGetCharAt(i + 1);
				} else if (ch == Quote.Down) {
					Quote.Count--;
					if (Quote.Count == 0) {
						Quote.Rep--;
						if (Quote.Rep <= 0) {
							styler.ColourTo(i, state);
							state = SCE_PL_DEFAULT;
							ch = ' ';
						}
						if (Quote.Up == Quote.Down) {
							Quote.Count++;
						}
					}
				} else if (ch == Quote.Up) {
					Quote.Count++;
				}
			}
		}
		if (state == SCE_PL_ERROR) {
			break;
		}
		chPrev = ch;
	}
	styler.ColourTo(lengthDoc - 1, state);
}

static bool IsCommentLine(int line, Accessor &styler) {
	int pos = styler.LineStart(line);
	int eol_pos = styler.LineStart(line + 1) - 1;
	for (int i = pos; i < eol_pos; i++) {
		char ch = styler[i];
        int style = styler.StyleAt(i);
		if (ch == '#' && style == SCE_PL_COMMENTLINE)
			return true;
		else if (ch != ' ' && ch != '\t')
			return false;
	}
	return false;
}

static void FoldPerlDoc(unsigned int startPos, int length, int, WordList *[],
                            Accessor &styler) {
	bool foldComment = styler.GetPropertyInt("fold.comment") != 0;
	bool foldCompact = styler.GetPropertyInt("fold.compact", 1) != 0;
	// Custom folding of POD and packages
	bool foldPOD = styler.GetPropertyInt("fold.perl.pod", 1) != 0;
	bool foldPackage = styler.GetPropertyInt("fold.perl.package", 1) != 0;
	unsigned int endPos = startPos + length;
	int visibleChars = 0;
	int lineCurrent = styler.GetLine(startPos);
	int levelPrev = SC_FOLDLEVELBASE;
	if (lineCurrent > 0)
		levelPrev = styler.LevelAt(lineCurrent - 1) >> 16;
	int levelCurrent = levelPrev;
	char chNext = styler[startPos];
	char chPrev = styler.SafeGetCharAt(startPos - 1);
	int styleNext = styler.StyleAt(startPos);
	// Used at end of line to determine if the line was a package definition
	bool isPackageLine = false;
	bool isPodHeading = false;
	for (unsigned int i = startPos; i < endPos; i++) {
		char ch = chNext;
		chNext = styler.SafeGetCharAt(i + 1);
		int style = styleNext;
		styleNext = styler.StyleAt(i + 1);
		bool atEOL = (ch == '\r' && chNext != '\n') || (ch == '\n');
		bool atLineStart = isEOLChar(chPrev) || i == 0;
        // Comment folding
		if (foldComment && atEOL && IsCommentLine(lineCurrent, styler))
        {
            if (!IsCommentLine(lineCurrent - 1, styler)
                && IsCommentLine(lineCurrent + 1, styler))
                levelCurrent++;
            else if (IsCommentLine(lineCurrent - 1, styler)
                     && !IsCommentLine(lineCurrent+1, styler))
                levelCurrent--;
        }
		if (style == SCE_C_OPERATOR) {
			if (ch == '{') {
				levelCurrent++;
			} else if (ch == '}') {
				levelCurrent--;
			}
		}
		// Custom POD folding
		if (foldPOD && atLineStart) {
			int stylePrevCh = (i) ? styler.StyleAt(i - 1):SCE_PL_DEFAULT;
			if (style == SCE_PL_POD) {
				if (stylePrevCh != SCE_PL_POD && stylePrevCh != SCE_PL_POD_VERB)
					levelCurrent++;
				else if (styler.Match(i, "=cut"))
					levelCurrent--;
				else if (styler.Match(i, "=head"))
					isPodHeading = true;
			} else if (style == SCE_PL_DATASECTION) {
                if (ch == '=' && isalpha(chNext) && levelCurrent == SC_FOLDLEVELBASE)
                    levelCurrent++;
                else if (styler.Match(i, "=cut") && levelCurrent > SC_FOLDLEVELBASE)
                    levelCurrent--;
                else if (styler.Match(i, "=head"))
					isPodHeading = true;
                // if package used or unclosed brace, level > SC_FOLDLEVELBASE!
                // reset needed as level test is vs. SC_FOLDLEVELBASE
                else if (styler.Match(i, "__END__"))
                    levelCurrent = SC_FOLDLEVELBASE;
            }
		}
		// Custom package folding
		if (foldPackage && atLineStart) {
			if (style == SCE_PL_WORD && styler.Match(i, "package")) {
				isPackageLine = true;
			}
		}

		if (atEOL) {
			int lev = levelPrev;
			if (isPodHeading) {
                lev = levelPrev - 1;
                lev |= SC_FOLDLEVELHEADERFLAG;
                isPodHeading = false;
			}
			// Check if line was a package declaration
			// because packages need "special" treatment
			if (isPackageLine) {
				lev = SC_FOLDLEVELBASE | SC_FOLDLEVELHEADERFLAG;
				levelCurrent = SC_FOLDLEVELBASE + 1;
				isPackageLine = false;
			}
            lev |= levelCurrent << 16;
			if (visibleChars == 0 && foldCompact)
				lev |= SC_FOLDLEVELWHITEFLAG;
			if ((levelCurrent > levelPrev) && (visibleChars > 0))
				lev |= SC_FOLDLEVELHEADERFLAG;
			if (lev != styler.LevelAt(lineCurrent)) {
				styler.SetLevel(lineCurrent, lev);
			}
			lineCurrent++;
			levelPrev = levelCurrent;
			visibleChars = 0;
		}
		if (!isspacechar(ch))
			visibleChars++;
		chPrev = ch;
	}
	// Fill in the real level of the next line, keeping the current flags as they will be filled in later
	int flagsNext = styler.LevelAt(lineCurrent) & ~SC_FOLDLEVELNUMBERMASK;
	styler.SetLevel(lineCurrent, levelPrev | flagsNext);
}

static const char * const perlWordListDesc[] = {
	"Keywords",
	0
};

LexerModule lmPerl(SCLEX_PERL, ColourisePerlDoc, "perl", FoldPerlDoc, perlWordListDesc);