[527231]: lexers / LexHaskell.cxx Maximize Restore History

Download this file

LexHaskell.cxx    908 lines (782 with data), 28.8 kB

  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
/******************************************************************
* LexHaskell.cxx
*
* A haskell lexer for the scintilla code control.
* Some stuff "lended" from LexPython.cxx and LexCPP.cxx.
* External lexer stuff inspired from the caml external lexer.
* Folder copied from Python's.
*
* Written by Tobias Engvall - tumm at dtek dot chalmers dot se
*
* Several bug fixes by Krasimir Angelov - kr.angelov at gmail.com
*
* Improved by kudah <kudahkukarek@gmail.com>
*
* TODO:
* * A proper lexical folder to fold group declarations, comments, pragmas,
* #ifdefs, explicit layout, lists, tuples, quasi-quotes, splces, etc, etc,
* etc.
*
*****************************************************************/
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <stdarg.h>
#include <assert.h>
#include <ctype.h>
#include <string>
#include <map>
#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "PropSetSimple.h"
#include "WordList.h"
#include "LexAccessor.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
#include "OptionSet.h"
#ifdef SCI_NAMESPACE
using namespace Scintilla;
#endif
#define HA_MODE_DEFAULT 0
#define HA_MODE_IMPORT1 1
#define HA_MODE_IMPORT2 2
#define HA_MODE_IMPORT3 3
#define HA_MODE_MODULE 4
#define HA_MODE_FFI 5
#define HA_MODE_TYPE 6
#define HA_MODE_PRAGMA 7
#define INDENT_OFFSET 1
static int u_iswalpha(int);
static int u_iswalnum(int);
static int u_iswupper(int);
static int u_IsHaskellSymbol(int);
// #define HASKELL_UNICODE
#ifndef HASKELL_UNICODE
// Stubs
static int u_iswalpha(int) {
return 0;
}
static int u_iswalnum(int) {
return 0;
}
static int u_iswupper(int) {
return 0;
}
static int u_IsHaskellSymbol(int) {
return 0;
}
#endif
static inline bool IsHaskellLetter(const int ch) {
if (IsASCII(ch)) {
return (ch >= 'a' && ch <= 'z')
|| (ch >= 'A' && ch <= 'Z');
} else {
return u_iswalpha(ch) != 0;
}
}
static inline bool IsHaskellAlphaNumeric(const int ch) {
if (IsASCII(ch)) {
return IsAlphaNumeric(ch);
} else {
return u_iswalnum(ch) != 0;
}
}
static inline bool IsHaskellUpperCase(const int ch) {
if (IsASCII(ch)) {
return ch >= 'A' && ch <= 'Z';
} else {
return u_iswupper(ch) != 0;
}
}
static inline bool IsAnHaskellOperatorChar(const int ch) {
if (IsASCII(ch)) {
return
( ch == '!' || ch == '#' || ch == '$' || ch == '%'
|| ch == '&' || ch == '*' || ch == '+' || ch == '-'
|| ch == '.' || ch == '/' || ch == ':' || ch == '<'
|| ch == '=' || ch == '>' || ch == '?' || ch == '@'
|| ch == '^' || ch == '|' || ch == '~' || ch == '\\');
} else {
return u_IsHaskellSymbol(ch) != 0;
}
}
static inline bool IsAHaskellWordStart(const int ch) {
return IsHaskellLetter(ch) || ch == '_';
}
static inline bool IsAHaskellWordChar(const int ch) {
return ( IsHaskellAlphaNumeric(ch)
|| ch == '_'
|| ch == '\'');
}
static inline bool IsCommentBlockStyle(int style) {
return (style >= SCE_HA_COMMENTBLOCK && style <= SCE_HA_COMMENTBLOCK3);
}
static inline bool IsCommentStyle(int style) {
return (style >= SCE_HA_COMMENTLINE && style <= SCE_HA_COMMENTBLOCK3);
}
inline int StyleFromNestLevel(const int nestLevel) {
return SCE_HA_COMMENTBLOCK + (nestLevel % 3);
}
struct OptionsHaskell {
bool magicHash;
bool allowQuotes;
bool implicitParams;
bool highlightSafe;
bool stylingWithinPreprocessor;
bool fold;
bool foldComment;
bool foldCompact;
bool foldImports;
bool foldIndentedImports;
OptionsHaskell() {
magicHash = true; // Widespread use, enabled by default.
allowQuotes = true; // Widespread use, enabled by default.
implicitParams = false; // Fell out of favor, seldom used, disabled.
highlightSafe = true; // Moderately used, doesn't hurt to enable.
stylingWithinPreprocessor = false;
fold = false;
foldComment = false;
foldCompact = false;
foldImports = false;
foldIndentedImports = true;
}
};
static const char * const haskellWordListDesc[] = {
"Keywords",
"FFI",
0
};
struct OptionSetHaskell : public OptionSet<OptionsHaskell> {
OptionSetHaskell() {
DefineProperty("lexer.haskell.allow.hash", &OptionsHaskell::magicHash,
"Set to 0 to disallow the '#' character at the end of identifiers and "
"literals with the haskell lexer "
"(GHC -XMagicHash extension)");
DefineProperty("lexer.haskell.allow.quotes", &OptionsHaskell::allowQuotes,
"Set to 0 to disable highlighting of Template Haskell name quotations "
"and promoted constructors "
"(GHC -XTemplateHaskell and -XDataKinds extensions)");
DefineProperty("lexer.haskell.allow.questionmark", &OptionsHaskell::implicitParams,
"Set to 1 to allow the '?' character at the start of identifiers "
"with the haskell lexer "
"(GHC & Hugs -XImplicitParams extension)");
DefineProperty("lexer.haskell.import.safe", &OptionsHaskell::highlightSafe,
"Set to 0 to disallow \"safe\" keyword in imports "
"(GHC -XSafe, -XTrustworthy, -XUnsafe extensions)");
DefineProperty("styling.within.preprocessor", &OptionsHaskell::stylingWithinPreprocessor,
"For Haskell code, determines whether all preprocessor code is styled in the "
"preprocessor style (0, the default) or only from the initial # to the end "
"of the command word(1)."
);
DefineProperty("fold", &OptionsHaskell::fold);
DefineProperty("fold.comment", &OptionsHaskell::foldComment);
DefineProperty("fold.compact", &OptionsHaskell::foldCompact);
DefineProperty("fold.haskell.imports", &OptionsHaskell::foldImports,
"Set to 1 to enable folding of import declarations");
DefineProperty("fold.haskell.imports.indented", &OptionsHaskell::foldIndentedImports,
"Set this property to 0 to disable folding imports not starting at "
"column 0 when fold.haskell.imports=1");
DefineWordListSets(haskellWordListDesc);
}
};
class LexerHaskell : public ILexer {
int firstImportLine;
WordList keywords;
WordList ffi;
WordList reserved_operators;
OptionsHaskell options;
OptionSetHaskell osHaskell;
inline void skipMagicHash(StyleContext &sc, const bool twoHashes) {
if (options.magicHash && sc.ch == '#') {
sc.Forward();
if (twoHashes && sc.ch == '#') {
sc.Forward();
}
}
}
bool LineContainsImport(const int line, Accessor &styler) {
if (options.foldImports) {
int currentPos = styler.LineStart(line);
int style = styler.StyleAt(currentPos);
if (options.foldIndentedImports) {
int eol_pos = styler.LineStart(line + 1) - 1;
while (currentPos < eol_pos) {
int ch = styler[currentPos];
style = styler.StyleAt(currentPos);
if (ch == ' ' || ch == '\t'
|| IsCommentBlockStyle(style)) {
currentPos++;
} else {
break;
}
}
}
return (style == SCE_HA_KEYWORD
&& styler.Match(currentPos, "import"));
} else {
return false;
}
}
public:
LexerHaskell() : firstImportLine(-1) {}
virtual ~LexerHaskell() {}
void SCI_METHOD Release() {
delete this;
}
int SCI_METHOD Version() const {
return lvOriginal;
}
const char * SCI_METHOD PropertyNames() {
return osHaskell.PropertyNames();
}
int SCI_METHOD PropertyType(const char *name) {
return osHaskell.PropertyType(name);
}
const char * SCI_METHOD DescribeProperty(const char *name) {
return osHaskell.DescribeProperty(name);
}
int SCI_METHOD PropertySet(const char *key, const char *val);
const char * SCI_METHOD DescribeWordListSets() {
return osHaskell.DescribeWordListSets();
}
int SCI_METHOD WordListSet(int n, const char *wl);
void SCI_METHOD Lex(unsigned int startPos, int length, int initStyle, IDocument *pAccess);
void SCI_METHOD Fold(unsigned int startPos, int length, int initStyle, IDocument *pAccess);
void * SCI_METHOD PrivateCall(int, void *) {
return 0;
}
static ILexer *LexerFactoryHaskell() {
return new LexerHaskell();
}
};
int SCI_METHOD LexerHaskell::PropertySet(const char *key, const char *val) {
if (osHaskell.PropertySet(&options, key, val)) {
return 0;
}
return -1;
}
int SCI_METHOD LexerHaskell::WordListSet(int n, const char *wl) {
WordList *wordListN = 0;
switch (n) {
case 0:
wordListN = &keywords;
break;
case 1:
wordListN = &ffi;
break;
case 2:
wordListN = &reserved_operators;
break;
}
int firstModification = -1;
if (wordListN) {
WordList wlNew;
wlNew.Set(wl);
if (*wordListN != wlNew) {
wordListN->Set(wl);
firstModification = 0;
}
}
return firstModification;
}
void SCI_METHOD LexerHaskell::Lex(unsigned int startPos, int length, int initStyle
,IDocument *pAccess) {
LexAccessor styler(pAccess);
// Do not leak onto next line
if (initStyle == SCE_HA_STRINGEOL)
initStyle = SCE_HA_DEFAULT;
StyleContext sc(startPos, length, initStyle, styler);
int lineCurrent = styler.GetLine(startPos);
int state = lineCurrent ? styler.GetLineState(lineCurrent-1) : 0;
int mode = state & 0x7;
int nestLevel = state >> 3;
int base = 10;
bool inDashes = false;
assert(!(IsCommentBlockStyle(initStyle) && nestLevel <= 0));
while (sc.More()) {
// Check for state end
// For line numbering (and by extension, nested comments) to work,
// states should either only forward one character at a time, or check
// that characters they're skipping are not newlines. If states match on
// line end, they should skip it to prevent double counting.
if (sc.atLineEnd) {
// Remember the line state for future incremental lexing
styler.SetLineState(lineCurrent, (nestLevel << 3) | mode);
lineCurrent++;
}
if (sc.atLineStart && (sc.state == SCE_HA_STRING || sc.state == SCE_HA_CHARACTER)) {
// Prevent SCE_HA_STRINGEOL from leaking back to previous line
sc.SetState(sc.state);
}
// Handle line continuation generically.
if (sc.ch == '\\' &&
( sc.state == SCE_HA_STRING
|| sc.state == SCE_HA_PREPROCESSOR)) {
if (sc.chNext == '\n' || sc.chNext == '\r') {
sc.Forward();
// Remember the line state for future incremental lexing
styler.SetLineState(lineCurrent, (nestLevel << 3) | mode);
lineCurrent++;
if (sc.ch == '\r' && sc.chNext == '\n') {
sc.Forward();
}
sc.Forward();
continue;
}
}
// Operator
if (sc.state == SCE_HA_OPERATOR) {
int style = SCE_HA_OPERATOR;
if (sc.ch == ':' &&
// except "::"
!(sc.chNext == ':' && !IsAnHaskellOperatorChar(sc.GetRelative(2)))) {
style = SCE_HA_CAPITAL;
}
while (IsAnHaskellOperatorChar(sc.ch))
sc.Forward();
char s[100];
sc.GetCurrent(s, sizeof(s));
if (reserved_operators.InList(s))
style = SCE_HA_RESERVED_OPERATOR;
styler.ColourTo(sc.currentPos - 1, style);
sc.ChangeState(SCE_HA_DEFAULT);
}
// String
else if (sc.state == SCE_HA_STRING) {
if (sc.atLineEnd) {
sc.ChangeState(SCE_HA_STRINGEOL);
sc.ForwardSetState(SCE_HA_DEFAULT);
} else if (sc.ch == '\"') {
sc.Forward();
skipMagicHash(sc, false);
sc.SetState(SCE_HA_DEFAULT);
} else if (sc.ch == '\\') {
sc.Forward(2);
} else {
sc.Forward();
}
}
// Char
else if (sc.state == SCE_HA_CHARACTER) {
if (sc.atLineEnd) {
sc.ChangeState(SCE_HA_STRINGEOL);
sc.ForwardSetState(SCE_HA_DEFAULT);
} else if (sc.ch == '\'') {
sc.Forward();
skipMagicHash(sc, false);
sc.SetState(SCE_HA_DEFAULT);
} else if (sc.ch == '\\') {
sc.Forward(2);
} else {
sc.Forward();
}
}
// Number
else if (sc.state == SCE_HA_NUMBER) {
if (IsADigit(sc.ch, base) ||
(sc.ch=='.' && IsADigit(sc.chNext, base))) {
sc.Forward();
} else if ((base == 10) &&
(sc.ch == 'e' || sc.ch == 'E') &&
(IsADigit(sc.chNext) || sc.chNext == '+' || sc.chNext == '-')) {
sc.Forward();
if (sc.ch == '+' || sc.ch == '-')
sc.Forward();
} else {
skipMagicHash(sc, true);
sc.SetState(SCE_HA_DEFAULT);
}
}
// Keyword or Identifier
else if (sc.state == SCE_HA_IDENTIFIER) {
int style = IsHaskellUpperCase(sc.ch) ? SCE_HA_CAPITAL : SCE_HA_IDENTIFIER;
assert(IsAHaskellWordStart(sc.ch));
sc.Forward();
while (sc.More()) {
if (IsAHaskellWordChar(sc.ch)) {
sc.Forward();
} else if (sc.ch == '#' && options.magicHash) {
sc.Forward();
break;
} else if (sc.ch == '.' && style == SCE_HA_CAPITAL) {
if (IsHaskellUpperCase(sc.chNext)) {
sc.Forward();
style = SCE_HA_CAPITAL;
} else if (IsAHaskellWordStart(sc.chNext)) {
sc.Forward();
style = SCE_HA_IDENTIFIER;
} else if (IsAnHaskellOperatorChar(sc.chNext)) {
sc.Forward();
style = sc.ch == ':' ? SCE_HA_CAPITAL : SCE_HA_OPERATOR;
while (IsAnHaskellOperatorChar(sc.ch))
sc.Forward();
break;
} else {
break;
}
} else {
break;
}
}
char s[100];
sc.GetCurrent(s, sizeof(s));
int new_mode = HA_MODE_DEFAULT;
if (keywords.InList(s)) {
style = SCE_HA_KEYWORD;
} else if (style == SCE_HA_CAPITAL) {
if (mode == HA_MODE_IMPORT1 || mode == HA_MODE_IMPORT3) {
style = SCE_HA_MODULE;
new_mode = HA_MODE_IMPORT2;
} else if (mode == HA_MODE_MODULE) {
style = SCE_HA_MODULE;
}
} else if (mode == HA_MODE_IMPORT1 &&
strcmp(s,"qualified") == 0) {
style = SCE_HA_KEYWORD;
new_mode = HA_MODE_IMPORT1;
} else if (options.highlightSafe &&
mode == HA_MODE_IMPORT1 &&
strcmp(s,"safe") == 0) {
style = SCE_HA_KEYWORD;
new_mode = HA_MODE_IMPORT1;
} else if (mode == HA_MODE_IMPORT2) {
if (strcmp(s,"as") == 0) {
style = SCE_HA_KEYWORD;
new_mode = HA_MODE_IMPORT3;
} else if (strcmp(s,"hiding") == 0) {
style = SCE_HA_KEYWORD;
}
} else if (mode == HA_MODE_TYPE) {
if (strcmp(s,"family") == 0)
style = SCE_HA_KEYWORD;
}
if (mode == HA_MODE_FFI) {
if (ffi.InList(s)) {
style = SCE_HA_KEYWORD;
new_mode = HA_MODE_FFI;
}
}
styler.ColourTo(sc.currentPos - 1, style);
if (strcmp(s,"import") == 0 && mode != HA_MODE_FFI)
new_mode = HA_MODE_IMPORT1;
else if (strcmp(s,"module") == 0)
new_mode = HA_MODE_MODULE;
else if (strcmp(s,"foreign") == 0)
new_mode = HA_MODE_FFI;
else if (strcmp(s,"type") == 0
|| strcmp(s,"data") == 0)
new_mode = HA_MODE_TYPE;
sc.ChangeState(SCE_HA_DEFAULT);
mode = new_mode;
}
// Comments
// Oneliner
else if (sc.state == SCE_HA_COMMENTLINE) {
if (sc.atLineEnd) {
sc.SetState(mode == HA_MODE_PRAGMA ? SCE_HA_PRAGMA : SCE_HA_DEFAULT);
sc.Forward(); // prevent double counting a line
} else if (inDashes && sc.ch != '-' && mode != HA_MODE_PRAGMA) {
inDashes = false;
if (IsAnHaskellOperatorChar(sc.ch))
sc.ChangeState(SCE_HA_OPERATOR);
} else {
sc.Forward();
}
}
// Nested
else if (IsCommentBlockStyle(sc.state)) {
if (sc.Match('{','-')) {
sc.SetState(StyleFromNestLevel(nestLevel));
sc.Forward(2);
nestLevel++;
} else if (sc.Match('-','}')
&& !(mode == HA_MODE_PRAGMA && sc.chPrev == '#')) {
sc.Forward(2);
nestLevel--;
assert(nestLevel >= 0);
sc.SetState(
nestLevel <= 0
? (mode == HA_MODE_PRAGMA ? SCE_HA_PRAGMA : SCE_HA_DEFAULT)
: StyleFromNestLevel(nestLevel - 1));
} else {
sc.Forward();
}
}
// Pragma
else if (sc.state == SCE_HA_PRAGMA) {
// GHC pragma end should always be indented further than it's start.
if (sc.Match("#-}") && !sc.atLineStart) {
mode = HA_MODE_DEFAULT;
sc.Forward(3);
sc.SetState(SCE_HA_DEFAULT);
} else if (sc.Match('-','-')) {
sc.SetState(SCE_HA_COMMENTLINE);
sc.Forward(2);
inDashes = false;
} else if (sc.Match('{','-')) {
sc.SetState(StyleFromNestLevel(nestLevel));
sc.Forward(2);
nestLevel++;
} else {
sc.Forward();
}
}
// Preprocessor
else if (sc.state == SCE_HA_PREPROCESSOR) {
if (sc.atLineEnd) {
sc.SetState(SCE_HA_DEFAULT);
sc.Forward(); // prevent double counting a line
} else if (options.stylingWithinPreprocessor && !IsHaskellLetter(sc.ch)) {
sc.SetState(SCE_HA_DEFAULT);
} else {
sc.Forward();
}
}
// New state?
else if (sc.state == SCE_HA_DEFAULT) {
// Digit
if (IsADigit(sc.ch)) {
sc.SetState(SCE_HA_NUMBER);
if (sc.ch == '0' && (sc.chNext == 'X' || sc.chNext == 'x')) {
// Match anything starting with "0x" or "0X", too
sc.Forward(2);
base = 16;
} else if (sc.ch == '0' && (sc.chNext == 'O' || sc.chNext == 'o')) {
// Match anything starting with "0o" or "0O", too
sc.Forward(2);
base = 8;
} else {
sc.Forward();
base = 10;
}
mode = HA_MODE_DEFAULT;
}
// Pragma
else if (sc.Match("{-#")) {
mode = HA_MODE_PRAGMA;
sc.SetState(SCE_HA_PRAGMA);
sc.Forward(3);
}
// Comment line
else if (sc.Match('-','-')) {
sc.SetState(SCE_HA_COMMENTLINE);
sc.Forward(2);
inDashes = true;
}
// Comment block
else if (sc.Match('{','-')) {
sc.SetState(StyleFromNestLevel(nestLevel));
sc.Forward(2);
nestLevel++;
}
// String
else if (sc.ch == '\"') {
sc.SetState(SCE_HA_STRING);
sc.Forward();
}
// Character or quoted name
else if (sc.ch == '\'') {
sc.SetState(SCE_HA_CHARACTER);
sc.Forward();
if (options.allowQuotes) {
// Quoted type ''T
if (sc.ch=='\'' && IsAHaskellWordStart(sc.chNext)) {
sc.Forward();
sc.ChangeState(SCE_HA_IDENTIFIER);
} else if (sc.chNext != '\'') {
// Quoted value or promoted constructor 'N
if (IsAHaskellWordStart(sc.ch)) {
sc.ChangeState(SCE_HA_IDENTIFIER);
// Promoted constructor operator ':~>
} else if (sc.ch == ':') {
sc.ChangeState(SCE_HA_OPERATOR);
// Promoted list or tuple '[T]
} else if (sc.ch == '[' || sc.ch== '(') {
styler.ColourTo(sc.currentPos - 1, SCE_HA_OPERATOR);
sc.ChangeState(SCE_HA_DEFAULT);
}
}
}
}
// Operator starting with '?' or an implicit parameter
else if (sc.ch == '?') {
sc.SetState(SCE_HA_OPERATOR);
if ( options.implicitParams
&& IsAHaskellWordStart(sc.chNext)
&& !IsHaskellUpperCase(sc.chNext)) {
sc.Forward();
sc.ChangeState(SCE_HA_IDENTIFIER);
}
}
// Preprocessor
else if (sc.atLineStart && sc.ch == '#') {
mode = HA_MODE_DEFAULT;
sc.SetState(SCE_HA_PREPROCESSOR);
sc.Forward();
}
// Operator
else if (IsAnHaskellOperatorChar(sc.ch)) {
mode = HA_MODE_DEFAULT;
sc.SetState(SCE_HA_OPERATOR);
}
// Braces and punctuation
else if (sc.ch == ',' || sc.ch == ';'
|| sc.ch == '(' || sc.ch == ')'
|| sc.ch == '[' || sc.ch == ']'
|| sc.ch == '{' || sc.ch == '}') {
sc.SetState(SCE_HA_OPERATOR);
sc.ForwardSetState(SCE_HA_DEFAULT);
}
// Keyword or Identifier
else if (IsAHaskellWordStart(sc.ch)) {
sc.SetState(SCE_HA_IDENTIFIER);
// Something we don't care about
} else {
sc.Forward();
}
}
}
styler.SetLineState(lineCurrent, (nestLevel << 3) | mode);
sc.Complete();
}
static bool LineStartsWithACommentOrPreprocessor(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++) {
int style = styler.StyleAt(i);
if (IsCommentStyle(style) || style == SCE_HA_PREPROCESSOR) {
return true;
}
int ch = styler[i];
if ( ch != ' '
&& ch != '\t') {
return false;
}
}
return true;
}
void SCI_METHOD LexerHaskell::Fold(unsigned int startPos, int length, int // initStyle
,IDocument *pAccess) {
if (!options.fold)
return;
Accessor styler(pAccess, NULL);
const int maxPos = startPos + length;
const int maxLines =
maxPos == styler.Length()
? styler.GetLine(maxPos)
: styler.GetLine(maxPos - 1); // Requested last line
const int docLines = styler.GetLine(styler.Length()); // Available last line
// Backtrack to previous non-blank line so we can determine indent level
// for any white space lines
// and so we can fix any preceding fold level (which is why we go back
// at least one line in all cases)
int spaceFlags = 0;
int lineCurrent = styler.GetLine(startPos);
bool importHere = LineContainsImport(lineCurrent, styler);
int indentCurrent = styler.IndentAmount(lineCurrent, &spaceFlags, NULL);
while (lineCurrent > 0) {
lineCurrent--;
importHere = LineContainsImport(lineCurrent, styler);
indentCurrent = styler.IndentAmount(lineCurrent, &spaceFlags, NULL);
if (!(indentCurrent & SC_FOLDLEVELWHITEFLAG) &&
!LineStartsWithACommentOrPreprocessor(lineCurrent, styler))
break;
}
int indentCurrentLevel = indentCurrent & SC_FOLDLEVELNUMBERMASK;
int indentCurrentMask = indentCurrent & ~SC_FOLDLEVELNUMBERMASK;
if (indentCurrentLevel != (SC_FOLDLEVELBASE & SC_FOLDLEVELNUMBERMASK)) {
indentCurrent = (indentCurrentLevel + INDENT_OFFSET) | indentCurrentMask;
}
if (lineCurrent <= firstImportLine) {
firstImportLine = -1; // readjust first import position
}
if (importHere) {
if (firstImportLine == -1) {
firstImportLine = lineCurrent;
}
if (firstImportLine != lineCurrent) {
indentCurrentLevel++;
}
indentCurrent = indentCurrentLevel | indentCurrentMask;
}
// Process all characters to end of requested range
//that hangs over the end of the range. Cap processing in all cases
// to end of document.
while (lineCurrent <= docLines && lineCurrent <= maxLines) {
// Gather info
int lineNext = lineCurrent + 1;
importHere = LineContainsImport(lineNext, styler);
int indentNext = indentCurrent;
if (lineNext <= docLines) {
// Information about next line is only available if not at end of document
indentNext = styler.IndentAmount(lineNext, &spaceFlags, NULL);
}
if (indentNext & SC_FOLDLEVELWHITEFLAG)
indentNext = SC_FOLDLEVELWHITEFLAG | indentCurrentLevel;
// Skip past any blank lines for next indent level info; we skip also
// comments (all comments, not just those starting in column 0)
// which effectively folds them into surrounding code rather
// than screwing up folding.
while ((lineNext < docLines) &&
((indentNext & SC_FOLDLEVELWHITEFLAG) ||
(lineNext <= docLines && LineStartsWithACommentOrPreprocessor(lineNext, styler)))) {
lineNext++;
importHere = LineContainsImport(lineNext, styler);
indentNext = styler.IndentAmount(lineNext, &spaceFlags, NULL);
}
int indentNextLevel = indentNext & SC_FOLDLEVELNUMBERMASK;
int indentNextMask = indentNext & ~SC_FOLDLEVELNUMBERMASK;
if (indentNextLevel != (SC_FOLDLEVELBASE & SC_FOLDLEVELNUMBERMASK)) {
indentNext = (indentNextLevel + INDENT_OFFSET) | indentNextMask;
}
if (importHere) {
if (firstImportLine == -1) {
firstImportLine = lineNext;
}
if (firstImportLine != lineNext) {
indentNextLevel++;
}
indentNext = indentNextLevel | indentNextMask;
}
const int levelBeforeComments = Maximum(indentCurrentLevel,indentNextLevel);
// Now set all the indent levels on the lines we skipped
// Do this from end to start. Once we encounter one line
// which is indented more than the line after the end of
// the comment-block, use the level of the block before
int skipLine = lineNext;
int skipLevel = indentNextLevel;
while (--skipLine > lineCurrent) {
int skipLineIndent = styler.IndentAmount(skipLine, &spaceFlags, NULL);
if (options.foldCompact) {
if ((skipLineIndent & SC_FOLDLEVELNUMBERMASK) > indentNextLevel) {
skipLevel = levelBeforeComments;
}
int whiteFlag = skipLineIndent & SC_FOLDLEVELWHITEFLAG;
styler.SetLevel(skipLine, skipLevel | whiteFlag);
} else {
if ( (skipLineIndent & SC_FOLDLEVELNUMBERMASK) > indentNextLevel
&& !(skipLineIndent & SC_FOLDLEVELWHITEFLAG)
&& !LineStartsWithACommentOrPreprocessor(skipLine, styler)) {
skipLevel = levelBeforeComments;
}
styler.SetLevel(skipLine, skipLevel);
}
}
int lev = indentCurrent;
if (!(indentCurrent & SC_FOLDLEVELWHITEFLAG)) {
if ((indentCurrent & SC_FOLDLEVELNUMBERMASK) < (indentNext & SC_FOLDLEVELNUMBERMASK))
lev |= SC_FOLDLEVELHEADERFLAG;
}
// Set fold level for this line and move to next line
styler.SetLevel(lineCurrent, options.foldCompact ? lev : lev & ~SC_FOLDLEVELWHITEFLAG);
indentCurrent = indentNext;
lineCurrent = lineNext;
}
// NOTE: Cannot set level of last line here because indentCurrent doesn't have
// header flag set; the loop above is crafted to take care of this case!
//styler.SetLevel(lineCurrent, indentCurrent);
}
LexerModule lmHaskell(SCLEX_HASKELL, LexerHaskell::LexerFactoryHaskell, "haskell", haskellWordListDesc);