File: CxxScanner.l

package info (click to toggle)
codelite 17.0.0%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 136,204 kB
  • sloc: cpp: 491,547; ansic: 280,393; php: 10,259; sh: 8,930; lisp: 7,664; vhdl: 6,518; python: 6,020; lex: 4,920; yacc: 3,123; perl: 2,385; javascript: 1,715; cs: 1,193; xml: 1,110; makefile: 804; cobol: 741; sql: 709; ruby: 620; f90: 566; ada: 534; asm: 464; fortran: 350; objc: 289; tcl: 258; java: 157; erlang: 61; pascal: 51; ml: 49; awk: 44; haskell: 36
file content (538 lines) | stat: -rw-r--r-- 16,743 bytes parent folder | download | duplicates (2)
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
%{
//
//====================--------------------------------------------------------------
// Eran Ifrah 2014 (c)
//====================--------------------------------------------------------------
//
// To generate a source file from this .l file, you will need
// a flex version 2.5.34 and later
// Under Windows, you will need to run the following command
// from within *MSYS* terminal (or run codelite from an MSYS shell):
// /usr/bin/flex --noline --batch --outfile=CxxLexer.cpp CxxScanner.l
//
//====================--------------------------------------------------------------
//
extern "C" int yywrap(void*) { return 1; }

#include <wx/string.h>
#include <string>
#include <wx/filename.h>
#include "CxxLexerAPI.h"
#include "CxxScannerTokens.h"

#define YY_FATAL_ERROR(x)
#define YYSTYPE char*
#define ECHO
#define P(s)

#define YY_NO_UNISTD_H
#define YY_USER_ACTION  yycolumn += yyleng;
#define RETURN_WHITESPACE()                                         \
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r; \
    if(userData->IsCollectingWhitespace()) {                        \
        return T_WHITESPACE;                                        \
    }
#define RETURN_NEWLINE()                                            \
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r; \
    if(userData->IsCollectingWhitespace()) {                        \
        return T_NEWLINE;                                           \
    }

%}

/* regex and modes */

/* options */
%option yylineno
%option default
%option reentrant

%x PREPR
%x WRAP_PREP
%x CPP_COMMENT
%x C_COMMENT
%x INCLUDE
%x RAW_STRING

identifier [a-zA-Z_][0-9a-zA-Z_]*
exponent_part [eE][-+]?[0-9]+
fractional_constant ([0-9]*"."[0-9]+)|([0-9]+".")
floating_constant (({fractional_constant}{exponent_part}?)|([0-9]+{exponent_part}))[FfLl]?
dchar_seq [^()\\[:space:]]{0,16}

integer_suffix_opt ([uU]?[lL]?)|([lL][uU])
decimal_constant [1-9][0-9]*{integer_suffix_opt}
octal_constant "0"[0-7]*{integer_suffix_opt}
hex_constant "0"[xX][0-9a-fA-F]+{integer_suffix_opt}

simple_escape [abfnrtv'"?\\]
octal_escape  [0-7]{1,3}
hex_escape "x"[0-9a-fA-F]+

escape_sequence [\\]({simple_escape}|{octal_escape}|{hex_escape})
c_char [^'\\\n]|{escape_sequence}
s_char [^"\\\n]|{escape_sequence}

h_tab [\011]
form_feed [\014]
v_tab [\013]
c_return [\015]

horizontal_white [ ]|{h_tab}

%%
<<EOF>> {yyterminate();}
<INITIAL>alignas          { return T_ALIGNAS; }
<INITIAL>alignof          { return T_ALIGNOF; }
<INITIAL>and              { return T_AND;     }
<INITIAL>and_eq           { return T_AND_EQ;  }
<INITIAL>asm              { return T_ASM;     }
<INITIAL>auto             { return T_AUTO;    }
<INITIAL>bitand           { return T_BITAND;  }
<INITIAL>bitor            { return T_BITOR;   }
<INITIAL>bool             { return T_BOOL;    }
<INITIAL>break            { return T_BREAK;   }
<INITIAL>case             { return T_CASE;   }
<INITIAL>catch            { return T_CATCH;}
<INITIAL>char             { return T_CHAR;}
<INITIAL>char16_t         { return T_CHAR16_T;}
<INITIAL>char32_t         { return T_CHAR32_T;}
<INITIAL>class            { return T_CLASS;}
<INITIAL>compl            { return T_COMPL;}
<INITIAL>const            { return T_CONST;}
<INITIAL>constexpr        { return T_CONSTEXPR;}
<INITIAL>const_cast       { return T_CONST_CAST;}
<INITIAL>continue         { return T_CONTINUE;}
<INITIAL>decltype         { return T_DECLTYPE;}
<INITIAL>default          { return T_DEFAULT;}
<INITIAL>delete           { return T_DELETE;}
<INITIAL>do               { return T_DO;}
<INITIAL>double           { return T_DOUBLE;}
<INITIAL>dynamic_cast     { return T_DYNAMIC_CAST;}
<INITIAL>else             { return T_ELSE;}
<INITIAL>enum             { return T_ENUM;}
<INITIAL>explicit         { return T_EXPLICIT;}
<INITIAL>export           { return T_EXPORT;}
<INITIAL>extern           { return T_EXTERN;}
<INITIAL>false            { return T_FALSE;}
<INITIAL>final            { return T_FINAL;}
<INITIAL>float            { return T_FLOAT;}
<INITIAL>for              { return T_FOR;}
<INITIAL>friend           { return T_FRIEND;}
<INITIAL>goto             { return T_GOTO;}
<INITIAL>if               { return T_IF;}
<INITIAL>inline           { return T_INLINE;}
<INITIAL>int              { return T_INT;}
<INITIAL>long             { return T_LONG;}
<INITIAL>mutable          { return T_MUTABLE;}
<INITIAL>namespace        { return T_NAMESPACE;}
<INITIAL>new              { return T_NEW;}
<INITIAL>noexcept         { return T_NOEXCEPT;}
<INITIAL>not              { return T_NOT;}
<INITIAL>not_eq           { return T_NOT_EQ;}
<INITIAL>nullptr          { return T_NULLPTR;}
<INITIAL>operator         { return T_OPERATOR;}
<INITIAL>or               { return T_OR;}
<INITIAL>or_eq            { return T_OR_EQ;}
<INITIAL>override         { return T_OVERRIDE;}
<INITIAL>private          { return T_PRIVATE;}
<INITIAL>protected        { return T_PROTECTED;}
<INITIAL>public           { return T_PUBLIC;}
<INITIAL>register         { return T_REGISTER;}
<INITIAL>reinterpret_cast { return T_REINTERPRET_CAST;}
<INITIAL>return           { return T_RETURN;}
<INITIAL>short            { return T_SHORT;}
<INITIAL>signed           { return T_SIGNED;}
<INITIAL>sizeof           { return T_SIZEOF;}
<INITIAL>static           { return T_STATIC;}
<INITIAL>static_assert    { return T_STATIC_ASSERT;}
<INITIAL>static_cast      { return T_STATIC_CAST;}
<INITIAL>struct           { return T_STRUCT;}
<INITIAL>switch           { return T_SWITCH;}
<INITIAL>template         { return T_TEMPLATE;}
<INITIAL>this             { return T_THIS;}
<INITIAL>thread_local     { return T_THREAD_LOCAL;}
<INITIAL>throw            { return T_THROW;}
<INITIAL>true             { return T_TRUE;}
<INITIAL>try              { return T_TRY;}
<INITIAL>typedef          { return T_TYPEDEF;}
<INITIAL>typeid           { return T_TYPEID;}
<INITIAL>typename         { return T_TYPENAME;}
<INITIAL>union            { return T_UNION;}
<INITIAL>unsigned         { return T_UNSIGNED;}
<INITIAL>using            { return T_USING;}
<INITIAL>virtual          { return T_VIRTUAL;}
<INITIAL>void             { return T_VOID;}
<INITIAL>volatile         { return T_VOLATILE;}
<INITIAL>wchar_t          { return T_WCHAR_T;}
<INITIAL>while            { return T_WHILE;}
<INITIAL>xor              { return T_XOR;}
<INITIAL>xor_eq           { return T_XOR_EQ;}
<INITIAL>\n               {}
<INITIAL>{horizontal_white}+ { RETURN_WHITESPACE(); }
<INITIAL>({v_tab}|{c_return}|{form_feed})+ {RETURN_WHITESPACE();}
<INITIAL>({horizontal_white}|{v_tab}|{c_return}|{form_feed})*"\n" { RETURN_NEWLINE(); }
<INITIAL>{decimal_constant}  { return T_DEC_NUMBER;}
<INITIAL>{octal_constant}    { return T_OCTAL_NUMBER;}
<INITIAL>{hex_constant}      { return T_HEX_NUMBER; }
<INITIAL>{floating_constant} { return T_FLOAT_NUMBER;}
<INITIAL>".*"                { return T_DOT_STAR; }
<INITIAL>"::"                { return T_DOUBLE_COLONS; }
<INITIAL>"->"                { return T_ARROW; }
<INITIAL>"->*"               { return T_ARROW_STAR; }
<INITIAL>"++"                { return T_PLUS_PLUS; }
<INITIAL>"--"                { return T_MINUS_MINUS; }
<INITIAL>"<<"                { return T_LS; }
<INITIAL>"<="                { return T_LE; }
<INITIAL>">="                { return T_GE; }
<INITIAL>"=="                { return T_EQUAL; }
<INITIAL>"!="                { return T_NOT_EQUAL; }
<INITIAL>"&&"                { return T_AND_AND;}
<INITIAL>"||"                { return T_OR_OR;}
<INITIAL>"*="                { return T_STAR_EQUAL;}
<INITIAL>"/="                { return T_SLASH_EQUAL;}
<INITIAL>"%="                { return T_DIV_EQUAL;}
<INITIAL>"+="                { return T_PLUS_EQUAL;}
<INITIAL>"-="                { return T_MINUS_EQUAL;}
<INITIAL>"<<="               { return T_LS_ASSIGN;}
<INITIAL>">>="               { return T_RS_ASSIGN;}
<INITIAL>"&="                { return T_AND_EQUAL;}
<INITIAL>"^="                { return T_POW_EQUAL;}
<INITIAL>"|="                { return T_OR_EQUAL;}
<INITIAL>"..."               { return T_3_DOTS;}
<INITIAL>"L"?[']{c_char}+['] {
    return T_STRING;
}
<INITIAL>"L"?["]{s_char}*["] {
    return T_STRING;
}
<INITIAL>R["]{dchar_seq}[(] {
    BEGIN(RAW_STRING);
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    // R"<d-char>(
    userData->set_raw_string_label(yytext + 2 /* skip the `R"` */, yyleng - 3 /* we want just the d-char */);
    userData->clear_raw_string();
}
<INITIAL>"/*" {
    // Clear the comment collected
    BEGIN C_COMMENT;

    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->ClearComment();
        userData->AppendToComment("/*");
        userData->SetCommentStartLine(yylineno);
    }
}
<C_COMMENT>"*/" {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment("*/");
        userData->SetCommentEndLine(yylineno);
    }
    BEGIN INITIAL;
    if(userData->IsCollectingComments()) {
        return T_C_COMMENT;
    }
}
<C_COMMENT>"\n" {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment("\n");
    }
}
<C_COMMENT>. {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment(yytext[0]);
    }
}

<INITIAL,PREPR>"//" {
    int oldState = yyg->yy_start;
    BEGIN CPP_COMMENT;
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->ClearComment();
        userData->AppendToComment("//");
        userData->SetCommentStartLine(yylineno);
    }
    if((1 + 2 * PREPR) == oldState) {
        return T_PP_STATE_EXIT;
    }
}

<CPP_COMMENT>"\\\n" {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment("\\\n");
    }
}
<CPP_COMMENT>"\\\r\n" {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment("\\\r\n");
    }
}
<CPP_COMMENT>"\n" {
    BEGIN INITIAL;
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment("\n");
        return T_CXX_COMMENT;
    }
}
<CPP_COMMENT>. {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    if(userData->IsCollectingComments()) {
        userData->AppendToComment(yytext[0]);
    }
}
<INITIAL>{identifier} {
    return T_IDENTIFIER;
}
<INITIAL>"#" {
    BEGIN(PREPR);
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    userData->SetPreProcessorSection(true);
}
<INITIAL>. {
    return yytext[0];
}
<PREPR>"\\\n" {
    /* keep the current state */
}
<PREPR>"\\\r\n" {
    /* keep the current state */
}
<PREPR>[ \t\r\v\b]+ {
    /* do nothing */
    RETURN_WHITESPACE();
}
<PREPR>"\n" {
    BEGIN(INITIAL);
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    userData->SetPreProcessorSection(false);
    return T_PP_STATE_EXIT;
}
<PREPR>"define" {
    return T_PP_DEFINE;
}
<PREPR>"defined" {
    return T_PP_DEFINED;
}
<PREPR>"if" {
    return T_PP_IF;
}
<PREPR>"ifdef" {
    return T_PP_IFDEF;
}
<PREPR>"ifndef" {
    return T_PP_IFNDEF;
}
<PREPR>"else" {
    return T_PP_ELSE;
}
<PREPR>"elif" {
    return T_PP_ELIF;
}
<PREPR>"endif" {
    return T_PP_ENDIF;
}
<PREPR>"line" {
    return T_PP_LINE;
}
<PREPR>"pragma" {
    return T_PP_PRAGMA;
}
<PREPR>"undef" {
    return T_PP_UNDEF;
}
<PREPR>"error" {
    return T_PP_ERROR;
}
<PREPR>"&&" {
    return T_PP_AND;
}
<PREPR>"||" {
    return T_PP_OR;
}
<PREPR>">" {
    return T_PP_GT;
}
<PREPR>">=" {
    return T_PP_GTEQ;
}
<PREPR>"<" {
    return T_PP_LT;
}
<PREPR>"<=" {
    return T_PP_LTEQ;
}
<PREPR>"include" {
    BEGIN(INCLUDE);
}
<PREPR>"L"?[']{c_char}+['] {
    return T_PP_STRING;
}
<PREPR>"L"?["]{s_char}*["] {
    return T_PP_STRING;
}
<PREPR>{decimal_constant}  { return T_PP_DEC_NUMBER;}
<PREPR>{octal_constant}    { return T_PP_OCTAL_NUMBER;}
<PREPR>{hex_constant}      { return T_PP_HEX_NUMBER; }
<PREPR>{floating_constant} { return T_PP_FLOAT_NUMBER;}
<PREPR>{identifier} {
    return T_PP_IDENTIFIER;
}
<PREPR>. {
    return yytext[0];
}
<RAW_STRING>[)]{dchar_seq}["] {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    std::string delim_found(yytext + 1, yyleng - 2); // we just want the `dchar_seq` sequence
    if(delim_found == userData->get_raw_string_label()) {
        BEGIN(INITIAL);
        return T_RAW_STRING;
    } else {
        userData->append_raw_string(yytext, yyleng);
    }
}
<RAW_STRING>\n {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    userData->append_raw_string('\n');
}
<RAW_STRING>. {
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    userData->append_raw_string(yytext[0]);
}
<INCLUDE>\n {
    BEGIN(INITIAL);
    CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
    userData->SetPreProcessorSection(false);
    return T_PP_STATE_EXIT;
}
<INCLUDE>[ \t]* { RETURN_WHITESPACE(); }
<INCLUDE>["<][^ \t\n]+[">] { /* got the include file name */
    return T_PP_INCLUDE_FILENAME;
}

%%

//=============-------------------------------
// API methods implementation
//=============-------------------------------

void* LexerNew(const wxString& content, size_t options )
{
    yyscan_t scanner;
    yylex_init(&scanner);
    struct yyguts_t * yyg = (struct yyguts_t*)scanner;
    CppLexerUserData *userData = new CppLexerUserData(options);

    // keep the file pointer (and make sure we close it at the end)
    userData->SetCurrentPF(NULL);
    yyg->yyextra_r = userData;

    wxCharBuffer cb = content.mb_str(wxConvUTF8);
    yy_switch_to_buffer(yy_scan_string(cb.data(), scanner), scanner);
    yycolumn = 0;
    yylineno = 0;
    return scanner;
}

void* LexerNew(const wxFileName& filename, size_t options )
{
    wxFileName fn = filename;
    if(fn.IsRelative()) {
        fn.MakeAbsolute();
    }

    FILE* fp = ::fopen(fn.GetFullPath().mb_str(wxConvUTF8).data(), "rb");
    if(!fp) {
        return NULL;
    }
    yyscan_t scanner;
    yylex_init(&scanner);
    struct yyguts_t * yyg = (struct yyguts_t*)scanner;
    CppLexerUserData *userData = new CppLexerUserData(options);

    // keep the file pointer (and make sure we close it at the end)
    userData->SetCurrentPF(fp);
    yyg->yyextra_r = userData;

    yy_switch_to_buffer(yy_create_buffer(fp, YY_BUF_SIZE, scanner), scanner);
    yycolumn = 1;
    yylineno = 0;
    return scanner;
}

void LexerDestroy(void** scanner)
{
    struct yyguts_t * yyg = (struct yyguts_t*)(*scanner);
    delete (CppLexerUserData*)yyg->yyextra_r;
    yy_delete_buffer(YY_CURRENT_BUFFER, *scanner);

    yylex_destroy(*scanner);
    *scanner = NULL;
}

void LexerUnget(void* scanner)
{
    // return the entire token back to the input stream
    struct yyguts_t * yyg = (struct yyguts_t*)scanner;
    yyless(0);
}

bool LexerNext(void* scanner, CxxLexerToken& token)
{
    token.SetColumn(0);
    token.SetType(yylex(scanner));
    token.ClearComment();
    token.ClearRawString();
    if(!token.IsEOF()) {
        struct yyguts_t * yyg = (struct yyguts_t*)scanner;
        CppLexerUserData* userData = (CppLexerUserData*)yyg->yyextra_r;
        switch(token.GetType()) {
        case T_RAW_STRING:
            token.SetLineNumber(yylineno);
            token.SetRawString(userData->get_raw_string());
            userData->clear_raw_string_label();
            break;
        case T_CXX_COMMENT:
            // One line up for CXX comments
            token.SetLineNumber(userData->GetCommentStartLine());
            token.SetComment(userData->GetComment());
            userData->ClearComment();
            break;
        case T_C_COMMENT:
            token.SetLineNumber(userData->GetCommentStartLine());
            token.SetComment(userData->GetComment());
            userData->ClearComment();
            break;
        default:
            token.SetLineNumber(yylineno);
            token.SetText(yytext);
            token.SetColumn(yycolumn);
            break;
        }

    } else {
        token.SetText(NULL);
        token.SetLineNumber(0);
        token.SetColumn(0);
    }
    return !token.IsEOF();
}

wxString LexerCurrentToken(void* scanner)
{
    struct yyguts_t * yyg = (struct yyguts_t*)scanner;
    return yytext;
}

CppLexerUserData* LexerGetUserData(void* scanner)
{
    struct yyguts_t * yyg = (struct yyguts_t*)scanner;
    return (CppLexerUserData*) yyg->yyextra_r;
}