Menu

[r687]: / trunk / ext / scintilla / lexers / LexAsm.cxx  Maximize  Restore  History

Download this file

461 lines (415 with data), 13.8 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
// Scintilla source code edit control
/** @file LexAsm.cxx
** Lexer for Assembler, just for the MASM syntax
** Written by The Black Horus
** Enhancements and NASM stuff by Kein-Hong Man, 2003-10
** SCE_ASM_COMMENTBLOCK and SCE_ASM_CHARACTER are for future GNU as colouring
** Converted to lexer object and added further folding features/properties by "Udo Lechner" <dlchnr(at)gmx(dot)net>
**/
// Copyright 1998-2003 by Neil Hodgson <neilh@scintilla.org>
// The License.txt file describes the conditions under which this software may be distributed.
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <stdarg.h>
#include <assert.h>
#include <ctype.h>
#include <string>
#include <map>
#include <set>
#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "WordList.h"
#include "LexAccessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
#include "OptionSet.h"
#ifdef SCI_NAMESPACE
using namespace Scintilla;
#endif
static inline bool IsAWordChar(const int ch) {
return (ch < 0x80) && (isalnum(ch) || ch == '.' ||
ch == '_' || ch == '?');
}
static inline bool IsAWordStart(const int ch) {
return (ch < 0x80) && (isalnum(ch) || ch == '_' || ch == '.' ||
ch == '%' || ch == '@' || ch == '$' || ch == '?');
}
static inline bool IsAsmOperator(const int ch) {
if ((ch < 0x80) && (isalnum(ch)))
return false;
// '.' left out as it is used to make up numbers
if (ch == '*' || ch == '/' || ch == '-' || ch == '+' ||
ch == '(' || ch == ')' || ch == '=' || ch == '^' ||
ch == '[' || ch == ']' || ch == '<' || ch == '&' ||
ch == '>' || ch == ',' || ch == '|' || ch == '~' ||
ch == '%' || ch == ':')
return true;
return false;
}
static bool IsStreamCommentStyle(int style) {
return style == SCE_ASM_COMMENTDIRECTIVE || style == SCE_ASM_COMMENTBLOCK;
}
static inline int LowerCase(int c) {
if (c >= 'A' && c <= 'Z')
return 'a' + c - 'A';
return c;
}
// An individual named option for use in an OptionSet
// Options used for LexerAsm
struct OptionsAsm {
std::string delimiter;
bool fold;
bool foldSyntaxBased;
bool foldCommentMultiline;
bool foldCommentExplicit;
std::string foldExplicitStart;
std::string foldExplicitEnd;
bool foldExplicitAnywhere;
bool foldCompact;
OptionsAsm() {
delimiter = "";
fold = false;
foldSyntaxBased = true;
foldCommentMultiline = false;
foldCommentExplicit = false;
foldExplicitStart = "";
foldExplicitEnd = "";
foldExplicitAnywhere = false;
foldCompact = true;
}
};
static const char * const asmWordListDesc[] = {
"CPU instructions",
"FPU instructions",
"Registers",
"Directives",
"Directive operands",
"Extended instructions",
"Directives4Foldstart",
"Directives4Foldend",
0
};
struct OptionSetAsm : public OptionSet<OptionsAsm> {
OptionSetAsm() {
DefineProperty("lexer.asm.comment.delimiter", &OptionsAsm::delimiter,
"Character used for COMMENT directive's delimiter, replacing the standard \"~\".");
DefineProperty("fold", &OptionsAsm::fold);
DefineProperty("fold.asm.syntax.based", &OptionsAsm::foldSyntaxBased,
"Set this property to 0 to disable syntax based folding.");
DefineProperty("fold.asm.comment.multiline", &OptionsAsm::foldCommentMultiline,
"Set this property to 1 to enable folding multi-line comments.");
DefineProperty("fold.asm.comment.explicit", &OptionsAsm::foldCommentExplicit,
"This option enables folding explicit fold points when using the Asm lexer. "
"Explicit fold points allows adding extra folding by placing a ;{ comment at the start and a ;} "
"at the end of a section that should fold.");
DefineProperty("fold.asm.explicit.start", &OptionsAsm::foldExplicitStart,
"The string to use for explicit fold start points, replacing the standard ;{.");
DefineProperty("fold.asm.explicit.end", &OptionsAsm::foldExplicitEnd,
"The string to use for explicit fold end points, replacing the standard ;}.");
DefineProperty("fold.asm.explicit.anywhere", &OptionsAsm::foldExplicitAnywhere,
"Set this property to 1 to enable explicit fold points anywhere, not just in line comments.");
DefineProperty("fold.compact", &OptionsAsm::foldCompact);
DefineWordListSets(asmWordListDesc);
}
};
class LexerAsm : public ILexer {
WordList cpuInstruction;
WordList mathInstruction;
WordList registers;
WordList directive;
WordList directiveOperand;
WordList extInstruction;
WordList directives4foldstart;
WordList directives4foldend;
OptionsAsm options;
OptionSetAsm osAsm;
public:
LexerAsm() {
}
~LexerAsm() {
}
void SCI_METHOD Release() {
delete this;
}
int SCI_METHOD Version() const {
return lvOriginal;
}
const char * SCI_METHOD PropertyNames() {
return osAsm.PropertyNames();
}
int SCI_METHOD PropertyType(const char *name) {
return osAsm.PropertyType(name);
}
const char * SCI_METHOD DescribeProperty(const char *name) {
return osAsm.DescribeProperty(name);
}
int SCI_METHOD PropertySet(const char *key, const char *val);
const char * SCI_METHOD DescribeWordListSets() {
return osAsm.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 *LexerFactoryAsm() {
return new LexerAsm();
}
};
int SCI_METHOD LexerAsm::PropertySet(const char *key, const char *val) {
if (osAsm.PropertySet(&options, key, val)) {
return 0;
}
return -1;
}
int SCI_METHOD LexerAsm::WordListSet(int n, const char *wl) {
WordList *wordListN = 0;
switch (n) {
case 0:
wordListN = &cpuInstruction;
break;
case 1:
wordListN = &mathInstruction;
break;
case 2:
wordListN = &registers;
break;
case 3:
wordListN = &directive;
break;
case 4:
wordListN = &directiveOperand;
break;
case 5:
wordListN = &extInstruction;
break;
case 6:
wordListN = &directives4foldstart;
break;
case 7:
wordListN = &directives4foldend;
break;
}
int firstModification = -1;
if (wordListN) {
WordList wlNew;
wlNew.Set(wl);
if (*wordListN != wlNew) {
wordListN->Set(wl);
firstModification = 0;
}
}
return firstModification;
}
void SCI_METHOD LexerAsm::Lex(unsigned int startPos, int length, int initStyle, IDocument *pAccess) {
LexAccessor styler(pAccess);
// Do not leak onto next line
if (initStyle == SCE_ASM_STRINGEOL)
initStyle = SCE_ASM_DEFAULT;
StyleContext sc(startPos, length, initStyle, styler);
for (; sc.More(); sc.Forward())
{
// Prevent SCE_ASM_STRINGEOL from leaking back to previous line
if (sc.atLineStart && (sc.state == SCE_ASM_STRING)) {
sc.SetState(SCE_ASM_STRING);
} else if (sc.atLineStart && (sc.state == SCE_ASM_CHARACTER)) {
sc.SetState(SCE_ASM_CHARACTER);
}
// Handle line continuation generically.
if (sc.ch == '\\') {
if (sc.chNext == '\n' || sc.chNext == '\r') {
sc.Forward();
if (sc.ch == '\r' && sc.chNext == '\n') {
sc.Forward();
}
continue;
}
}
// Determine if the current state should terminate.
if (sc.state == SCE_ASM_OPERATOR) {
if (!IsAsmOperator(sc.ch)) {
sc.SetState(SCE_ASM_DEFAULT);
}
} else if (sc.state == SCE_ASM_NUMBER) {
if (!IsAWordChar(sc.ch)) {
sc.SetState(SCE_ASM_DEFAULT);
}
} else if (sc.state == SCE_ASM_IDENTIFIER) {
if (!IsAWordChar(sc.ch) ) {
char s[100];
sc.GetCurrentLowered(s, sizeof(s));
bool IsDirective = false;
if (cpuInstruction.InList(s)) {
sc.ChangeState(SCE_ASM_CPUINSTRUCTION);
} else if (mathInstruction.InList(s)) {
sc.ChangeState(SCE_ASM_MATHINSTRUCTION);
} else if (registers.InList(s)) {
sc.ChangeState(SCE_ASM_REGISTER);
} else if (directive.InList(s)) {
sc.ChangeState(SCE_ASM_DIRECTIVE);
IsDirective = true;
} else if (directiveOperand.InList(s)) {
sc.ChangeState(SCE_ASM_DIRECTIVEOPERAND);
} else if (extInstruction.InList(s)) {
sc.ChangeState(SCE_ASM_EXTINSTRUCTION);
}
sc.SetState(SCE_ASM_DEFAULT);
if (IsDirective && !strcmp(s, "comment")) {
char delimiter = options.delimiter.empty() ? '~' : options.delimiter.c_str()[0];
while (IsASpaceOrTab(sc.ch) && !sc.atLineEnd) {
sc.ForwardSetState(SCE_ASM_DEFAULT);
}
if (sc.ch == delimiter) {
sc.SetState(SCE_ASM_COMMENTDIRECTIVE);
}
}
}
} else if (sc.state == SCE_ASM_COMMENTDIRECTIVE) {
char delimiter = options.delimiter.empty() ? '~' : options.delimiter.c_str()[0];
if (sc.ch == delimiter) {
while (!sc.atLineEnd) {
sc.Forward();
}
sc.SetState(SCE_ASM_DEFAULT);
}
} else if (sc.state == SCE_ASM_COMMENT ) {
if (sc.atLineEnd) {
sc.SetState(SCE_ASM_DEFAULT);
}
} else if (sc.state == SCE_ASM_STRING) {
if (sc.ch == '\\') {
if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
sc.Forward();
}
} else if (sc.ch == '\"') {
sc.ForwardSetState(SCE_ASM_DEFAULT);
} else if (sc.atLineEnd) {
sc.ChangeState(SCE_ASM_STRINGEOL);
sc.ForwardSetState(SCE_ASM_DEFAULT);
}
} else if (sc.state == SCE_ASM_CHARACTER) {
if (sc.ch == '\\') {
if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
sc.Forward();
}
} else if (sc.ch == '\'') {
sc.ForwardSetState(SCE_ASM_DEFAULT);
} else if (sc.atLineEnd) {
sc.ChangeState(SCE_ASM_STRINGEOL);
sc.ForwardSetState(SCE_ASM_DEFAULT);
}
}
// Determine if a new state should be entered.
if (sc.state == SCE_ASM_DEFAULT) {
if (sc.ch == ';'){
sc.SetState(SCE_ASM_COMMENT);
} else if (isascii(sc.ch) && (isdigit(sc.ch) || (sc.ch == '.' && isascii(sc.chNext) && isdigit(sc.chNext)))) {
sc.SetState(SCE_ASM_NUMBER);
} else if (IsAWordStart(sc.ch)) {
sc.SetState(SCE_ASM_IDENTIFIER);
} else if (sc.ch == '\"') {
sc.SetState(SCE_ASM_STRING);
} else if (sc.ch == '\'') {
sc.SetState(SCE_ASM_CHARACTER);
} else if (IsAsmOperator(sc.ch)) {
sc.SetState(SCE_ASM_OPERATOR);
}
}
}
sc.Complete();
}
// Store both the current line's fold level and the next lines in the
// level store to make it easy to pick up with each increment
// and to make it possible to fiddle the current level for "else".
void SCI_METHOD LexerAsm::Fold(unsigned int startPos, int length, int initStyle, IDocument *pAccess) {
if (!options.fold)
return;
LexAccessor styler(pAccess);
unsigned int endPos = startPos + length;
int visibleChars = 0;
int lineCurrent = styler.GetLine(startPos);
int levelCurrent = SC_FOLDLEVELBASE;
if (lineCurrent > 0)
levelCurrent = styler.LevelAt(lineCurrent-1) >> 16;
int levelNext = levelCurrent;
char chNext = styler[startPos];
int styleNext = styler.StyleAt(startPos);
int style = initStyle;
char word[100];
int wordlen = 0;
const bool userDefinedFoldMarkers = !options.foldExplicitStart.empty() && !options.foldExplicitEnd.empty();
for (unsigned int i = startPos; i < endPos; i++) {
char ch = chNext;
chNext = styler.SafeGetCharAt(i + 1);
int stylePrev = style;
style = styleNext;
styleNext = styler.StyleAt(i + 1);
bool atEOL = (ch == '\r' && chNext != '\n') || (ch == '\n');
if (options.foldCommentMultiline && IsStreamCommentStyle(style)) {
if (!IsStreamCommentStyle(stylePrev)) {
levelNext++;
} else if (!IsStreamCommentStyle(styleNext) && !atEOL) {
// Comments don't end at end of line and the next character may be unstyled.
levelNext--;
}
}
if (options.foldCommentExplicit && ((style == SCE_ASM_COMMENT) || options.foldExplicitAnywhere)) {
if (userDefinedFoldMarkers) {
if (styler.Match(i, options.foldExplicitStart.c_str())) {
levelNext++;
} else if (styler.Match(i, options.foldExplicitEnd.c_str())) {
levelNext--;
}
} else {
if (ch == ';') {
if (chNext == '{') {
levelNext++;
} else if (chNext == '}') {
levelNext--;
}
}
}
}
if (options.foldSyntaxBased && (style == SCE_ASM_DIRECTIVE)) {
word[wordlen++] = static_cast<char>(LowerCase(ch));
if (wordlen == 100) { // prevent overflow
word[0] = '\0';
wordlen = 1;
}
if (styleNext != SCE_ASM_DIRECTIVE) { // reading directive ready
word[wordlen] = '\0';
wordlen = 0;
if (directives4foldstart.InList(word)) {
levelNext++;
} else if (directives4foldend.InList(word)){
levelNext--;
}
}
}
if (!IsASpace(ch))
visibleChars++;
if (atEOL || (i == endPos-1)) {
int levelUse = levelCurrent;
int lev = levelUse | levelNext << 16;
if (visibleChars == 0 && options.foldCompact)
lev |= SC_FOLDLEVELWHITEFLAG;
if (levelUse < levelNext)
lev |= SC_FOLDLEVELHEADERFLAG;
if (lev != styler.LevelAt(lineCurrent)) {
styler.SetLevel(lineCurrent, lev);
}
lineCurrent++;
levelCurrent = levelNext;
if (atEOL && (i == static_cast<unsigned int>(styler.Length()-1))) {
// There is an empty line at end of file so give it same level and empty
styler.SetLevel(lineCurrent, (levelCurrent | levelCurrent << 16) | SC_FOLDLEVELWHITEFLAG);
}
visibleChars = 0;
}
}
}
LexerModule lmAsm(SCLEX_ASM, LexerAsm::LexerFactoryAsm, "asm", asmWordListDesc);
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.