-
Notifications
You must be signed in to change notification settings - Fork 586
/
geany_rust.c
982 lines (888 loc) · 22.7 KB
/
geany_rust.c
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
/*
*
* This source code is released for free distribution under the terms of the
* GNU General Public License version 2 or (at your option) any later version.
*
* This module contains functions for generating tags for Rust files.
*/
/*
* INCLUDE FILES
*/
#include "general.h" /* must always come first */
#include <string.h>
#include "keyword.h"
#include "parse.h"
#include "entry.h"
#include "options.h"
#include "read.h"
#include "routines.h"
#include "vstring.h"
/*
* MACROS
*/
#define MAX_STRING_LENGTH 256
/*
* DATA DECLARATIONS
*/
typedef enum {
K_MOD,
K_STRUCT,
K_TRAIT,
K_IMPL,
K_FN,
K_ENUM,
K_TYPE,
K_STATIC,
K_MACRO,
K_FIELD,
K_VARIANT,
K_METHOD,
K_NONE
} RustKind;
static kindDefinition rustKinds[] = {
{true, 'n', "module", "module"},
{true, 's', "struct", "structural type"},
{true, 'i', "interface", "trait interface"},
{true, 'c', "implementation", "implementation"},
{true, 'f', "function", "Function"},
{true, 'g', "enum", "Enum"},
{true, 't', "typedef", "Type Alias"},
{true, 'v', "variable", "Global variable"},
{true, 'M', "macro", "Macro Definition"},
{true, 'm', "field", "A struct field"},
{true, 'e', "enumerator", "An enum variant"},
{true, 'P', "method", "A method"},
};
typedef enum {
TOKEN_WHITESPACE,
TOKEN_STRING,
TOKEN_IDENT,
TOKEN_LSHIFT,
TOKEN_RSHIFT,
TOKEN_RARROW,
TOKEN_EOF
} tokenType;
typedef struct {
/* Characters */
int cur_c;
int next_c;
/* Tokens */
int cur_token;
vString* token_str;
unsigned long line;
MIOPos pos;
} lexerState;
/*
* FUNCTION PROTOTYPES
*/
static void parseBlock (lexerState *lexer, bool delim, int kind, vString *scope);
/*
* FUNCTION DEFINITIONS
*/
/* Resets the scope string to the old length */
static void resetScope (vString *scope, size_t old_len)
{
scope->length = old_len;
scope->buffer[old_len] = '\0';
}
/* Adds a name to the end of the scope string */
static void addToScope (vString *scope, vString *name)
{
if (vStringLength(scope) > 0)
vStringCatS(scope, "::");
vStringCat(scope, name);
}
/* Write the lexer's current token to string, taking care of special tokens */
static void writeCurTokenToStr (lexerState *lexer, vString *out_str)
{
switch (lexer->cur_token)
{
case TOKEN_IDENT:
vStringCat(out_str, lexer->token_str);
break;
case TOKEN_STRING:
vStringCat(out_str, lexer->token_str);
break;
case TOKEN_WHITESPACE:
vStringPut(out_str, ' ');
break;
case TOKEN_LSHIFT:
vStringCatS(out_str, "<<");
break;
case TOKEN_RSHIFT:
vStringCatS(out_str, ">>");
break;
case TOKEN_RARROW:
vStringCatS(out_str, "->");
break;
default:
vStringPut(out_str, (char) lexer->cur_token);
}
}
/* Reads a character from the file */
static void advanceChar (lexerState *lexer)
{
lexer->cur_c = lexer->next_c;
lexer->next_c = getcFromInputFile();
}
/* Reads N characters from the file */
static void advanceNChar (lexerState *lexer, int n)
{
while (n--)
advanceChar(lexer);
}
/* Store the current character in lexerState::token_str if there is space
* (set by MAX_STRING_LENGTH), and then read the next character from the file */
static void advanceAndStoreChar (lexerState *lexer)
{
if (vStringLength(lexer->token_str) < MAX_STRING_LENGTH)
vStringPut(lexer->token_str, (char) lexer->cur_c);
advanceChar(lexer);
}
static bool isWhitespace (int c)
{
return c == ' ' || c == '\t' || c == '\r' || c == '\n';
}
static bool isAscii (int c)
{
return (c >= 0) && (c < 0x80);
}
/* This isn't quite right for Unicode identifiers */
static bool isIdentifierStart (int c)
{
return (isAscii(c) && (isalpha(c) || c == '_')) || !isAscii(c);
}
/* This isn't quite right for Unicode identifiers */
static bool isIdentifierContinue (int c)
{
return (isAscii(c) && (isalnum(c) || c == '_')) || !isAscii(c);
}
static void scanWhitespace (lexerState *lexer)
{
while (isWhitespace(lexer->cur_c))
advanceChar(lexer);
}
/* Normal line comments start with two /'s and continue until the next \n
* (potentially after a \r). Additionally, a shebang in the beginning of the
* file also counts as a line comment as long as it is not this sequence: #![ .
* Block comments start with / followed by a * and end with a * followed by a /.
* Unlike in C/C++ they nest. */
static void scanComments (lexerState *lexer)
{
/* // */
if (lexer->next_c == '/')
{
advanceNChar(lexer, 2);
while (lexer->cur_c != EOF && lexer->cur_c != '\n')
advanceChar(lexer);
}
/* #! */
else if (lexer->next_c == '!')
{
advanceNChar(lexer, 2);
/* If it is exactly #![ then it is not a comment, but an attribute */
if (lexer->cur_c == '[')
return;
while (lexer->cur_c != EOF && lexer->cur_c != '\n')
advanceChar(lexer);
}
/* block comment */
else if (lexer->next_c == '*')
{
int level = 1;
advanceNChar(lexer, 2);
while (lexer->cur_c != EOF && level > 0)
{
if (lexer->cur_c == '*' && lexer->next_c == '/')
{
level--;
advanceNChar(lexer, 2);
}
else if (lexer->cur_c == '/' && lexer->next_c == '*')
{
level++;
advanceNChar(lexer, 2);
}
else
{
advanceChar(lexer);
}
}
}
}
static void scanIdentifier (lexerState *lexer)
{
vStringClear(lexer->token_str);
do
{
advanceAndStoreChar(lexer);
} while(lexer->cur_c != EOF && isIdentifierContinue(lexer->cur_c));
}
/* Double-quoted strings, we only care about the \" escape. These
* last past the end of the line, so be careful not too store too much
* of them (see MAX_STRING_LENGTH). The only place we look at their
* contents is in the function definitions, and there the valid strings are
* things like "C" and "Rust" */
static void scanString (lexerState *lexer)
{
vStringClear(lexer->token_str);
advanceAndStoreChar(lexer);
while (lexer->cur_c != EOF && lexer->cur_c != '"')
{
if (lexer->cur_c == '\\' && lexer->next_c == '"')
advanceAndStoreChar(lexer);
advanceAndStoreChar(lexer);
}
advanceAndStoreChar(lexer);
}
/* Raw strings look like this: r"" or r##""## where the number of
* hashes must match */
static void scanRawString (lexerState *lexer)
{
size_t num_initial_hashes = 0;
vStringClear(lexer->token_str);
advanceAndStoreChar(lexer);
/* Count how many leading hashes there are */
while (lexer->cur_c == '#')
{
num_initial_hashes++;
advanceAndStoreChar(lexer);
}
if (lexer->cur_c != '"')
return;
advanceAndStoreChar(lexer);
while (lexer->cur_c != EOF)
{
/* Count how many trailing hashes there are. If the number is equal or more
* than the number of leading hashes, break. */
if (lexer->cur_c == '"')
{
size_t num_trailing_hashes = 0;
advanceAndStoreChar(lexer);
while (lexer->cur_c == '#' && num_trailing_hashes < num_initial_hashes)
{
num_trailing_hashes++;
advanceAndStoreChar(lexer);
}
if (num_trailing_hashes == num_initial_hashes)
break;
}
else
{
advanceAndStoreChar(lexer);
}
}
}
/* This deals with character literals: 'n', '\n', '\uFFFF'; and lifetimes:
* 'lifetime. We'll use this approximate regexp for the literals:
* \' \\ [^']+ \' or \' [^'] \' or \' \\ \' \'. Either way, we'll treat this
* token as a string, so it gets preserved as is for function signatures with
* lifetimes. */
static void scanCharacterOrLifetime (lexerState *lexer)
{
vStringClear(lexer->token_str);
advanceAndStoreChar(lexer);
if (lexer->cur_c == '\\')
{
advanceAndStoreChar(lexer);
/* The \' \\ \' \' (literally '\'') case */
if (lexer->cur_c == '\'' && lexer->next_c == '\'')
{
advanceAndStoreChar(lexer);
advanceAndStoreChar(lexer);
}
/* The \' \\ [^']+ \' case */
else
{
while (lexer->cur_c != EOF && lexer->cur_c != '\'')
advanceAndStoreChar(lexer);
}
}
/* The \' [^'] \' case */
else if (lexer->cur_c != '\'' && lexer->next_c == '\'')
{
advanceAndStoreChar(lexer);
advanceAndStoreChar(lexer);
}
/* Otherwise it is malformed, or a lifetime */
}
/* Advances the parser one token, optionally skipping whitespace
* (otherwise it is concatenated and returned as a single whitespace token).
* Whitespace is needed to properly render function signatures. Unrecognized
* token starts are stored literally, e.g. token may equal to a character '#'. */
static int advanceToken (lexerState *lexer, bool skip_whitspace)
{
bool have_whitespace = false;
lexer->line = getInputLineNumber();
lexer->pos = getInputFilePosition();
while (lexer->cur_c != EOF)
{
if (isWhitespace(lexer->cur_c))
{
scanWhitespace(lexer);
have_whitespace = true;
}
else if (lexer->cur_c == '/' && (lexer->next_c == '/' || lexer->next_c == '*'))
{
scanComments(lexer);
have_whitespace = true;
}
else
{
if (have_whitespace && !skip_whitspace)
return lexer->cur_token = TOKEN_WHITESPACE;
break;
}
}
lexer->line = getInputLineNumber();
lexer->pos = getInputFilePosition();
while (lexer->cur_c != EOF)
{
if (lexer->cur_c == '"')
{
scanString(lexer);
return lexer->cur_token = TOKEN_STRING;
}
else if (lexer->cur_c == 'r' && (lexer->next_c == '#' || lexer->next_c == '"'))
{
scanRawString(lexer);
return lexer->cur_token = TOKEN_STRING;
}
else if (lexer->cur_c == '\'')
{
scanCharacterOrLifetime(lexer);
return lexer->cur_token = TOKEN_STRING;
}
else if (isIdentifierStart(lexer->cur_c))
{
scanIdentifier(lexer);
return lexer->cur_token = TOKEN_IDENT;
}
/* These shift tokens aren't too important for tag-generation per se,
* but they confuse the skipUntil code which tracks the <> pairs. */
else if (lexer->cur_c == '>' && lexer->next_c == '>')
{
advanceNChar(lexer, 2);
return lexer->cur_token = TOKEN_RSHIFT;
}
else if (lexer->cur_c == '<' && lexer->next_c == '<')
{
advanceNChar(lexer, 2);
return lexer->cur_token = TOKEN_LSHIFT;
}
else if (lexer->cur_c == '-' && lexer->next_c == '>')
{
advanceNChar(lexer, 2);
return lexer->cur_token = TOKEN_RARROW;
}
else
{
int c = lexer->cur_c;
advanceChar(lexer);
return lexer->cur_token = c;
}
}
return lexer->cur_token = TOKEN_EOF;
}
static void initLexer (lexerState *lexer)
{
advanceNChar(lexer, 2);
lexer->token_str = vStringNew();
if (lexer->cur_c == '#' && lexer->next_c == '!')
scanComments(lexer);
advanceToken(lexer, true);
}
static void deInitLexer (lexerState *lexer)
{
vStringDelete(lexer->token_str);
lexer->token_str = NULL;
}
static void addTag (vString* ident, const char* type, const char* arg_list, int kind, unsigned long line, MIOPos pos, vString *scope, int parent_kind)
{
if (kind == K_NONE)
return;
tagEntryInfo tag;
initTagEntry(&tag, ident->buffer, kind);
tag.lineNumber = line;
tag.filePosition = pos;
tag.sourceFileName = getInputFileName();
tag.extensionFields.signature = arg_list;
tag.extensionFields.typeRef[1] = type;
if (parent_kind != K_NONE)
{
tag.extensionFields.scopeKindIndex = parent_kind;
tag.extensionFields.scopeName = scope->buffer;
}
makeTagEntry(&tag);
}
/* Skip tokens until one of the goal tokens is hit. Escapes when level = 0 if there are no goal tokens.
* Keeps track of balanced <>'s, ()'s, []'s, and {}'s and ignores the goal tokens within those pairings */
static void skipUntil (lexerState *lexer, int goal_tokens[], int num_goal_tokens)
{
int angle_level = 0;
int paren_level = 0;
int brace_level = 0;
int bracket_level = 0;
while (lexer->cur_token != TOKEN_EOF)
{
if (angle_level == 0 && paren_level == 0 && brace_level == 0
&& bracket_level == 0)
{
int ii = 0;
for(ii = 0; ii < num_goal_tokens; ii++)
{
if (lexer->cur_token == goal_tokens[ii])
{
break;
}
}
if (ii < num_goal_tokens)
break;
}
switch (lexer->cur_token)
{
case '<':
angle_level++;
break;
case '(':
paren_level++;
break;
case '{':
brace_level++;
break;
case '[':
bracket_level++;
break;
case '>':
angle_level--;
break;
case ')':
paren_level--;
break;
case '}':
brace_level--;
break;
case ']':
bracket_level--;
break;
case TOKEN_RSHIFT:
if (angle_level >= 2)
angle_level -= 2;
break;
/* TOKEN_LSHIFT is never interpreted as two <'s in valid Rust code */
default:
break;
}
/* Has to be after the token switch to catch the case when we start with the initial level token */
if (num_goal_tokens == 0 && angle_level == 0 && paren_level == 0 && brace_level == 0
&& bracket_level == 0)
break;
advanceToken(lexer, true);
}
}
/* Function format:
* "fn" <ident>[<type_bounds>] "(" [<args>] ")" ["->" <ret_type>] "{" [<body>] "}"*/
static void parseFn (lexerState *lexer, vString *scope, int parent_kind)
{
int kind = (parent_kind == K_TRAIT || parent_kind == K_IMPL) ? K_METHOD : K_FN;
vString *name;
vString *arg_list;
unsigned long line;
MIOPos pos;
int paren_level = 0;
bool found_paren = false;
bool valid_signature = true;
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
name = vStringNewCopy(lexer->token_str);
arg_list = vStringNew();
line = lexer->line;
pos = lexer->pos;
advanceToken(lexer, true);
/* HACK: This is a bit coarse as far as what tag entry means by
* 'arglist'... */
while (lexer->cur_token != '{' && lexer->cur_token != ';')
{
if (lexer->cur_token == '}')
{
valid_signature = false;
break;
}
else if (lexer->cur_token == '(')
{
found_paren = true;
paren_level++;
}
else if (lexer->cur_token == ')')
{
paren_level--;
if (paren_level < 0)
{
valid_signature = false;
break;
}
}
else if (lexer->cur_token == TOKEN_EOF)
{
valid_signature = false;
break;
}
writeCurTokenToStr(lexer, arg_list);
advanceToken(lexer, false);
}
if (!found_paren || paren_level != 0)
valid_signature = false;
if (valid_signature)
{
vStringStripTrailing(arg_list);
addTag(name, NULL, arg_list->buffer, kind, line, pos, scope, parent_kind);
addToScope(scope, name);
parseBlock(lexer, true, kind, scope);
}
vStringDelete(name);
vStringDelete(arg_list);
}
/* Mod format:
* "mod" <ident> "{" [<body>] "}"
* "mod" <ident> ";"*/
static void parseMod (lexerState *lexer, vString *scope, int parent_kind)
{
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, K_MOD, lexer->line, lexer->pos, scope, parent_kind);
addToScope(scope, lexer->token_str);
advanceToken(lexer, true);
parseBlock(lexer, true, K_MOD, scope);
}
/* Trait format:
* "trait" <ident> [<type_bounds>] "{" [<body>] "}"
*/
static void parseTrait (lexerState *lexer, vString *scope, int parent_kind)
{
int goal_tokens[] = {'{'};
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, K_TRAIT, lexer->line, lexer->pos, scope, parent_kind);
addToScope(scope, lexer->token_str);
advanceToken(lexer, true);
skipUntil(lexer, goal_tokens, 1);
parseBlock(lexer, true, K_TRAIT, scope);
}
/* Skips type blocks of the form <T:T<T>, ...> */
static void skipTypeBlock (lexerState *lexer)
{
if (lexer->cur_token == '<')
{
skipUntil(lexer, NULL, 0);
advanceToken(lexer, true);
}
}
/* Essentially grabs the last ident before 'for', '<' and '{', which
* tends to correspond to what we want as the impl tag entry name */
static void parseQualifiedType (lexerState *lexer, vString* name)
{
while (lexer->cur_token != TOKEN_EOF)
{
if (lexer->cur_token == TOKEN_IDENT)
{
if (strcmp(lexer->token_str->buffer, "for") == 0
|| strcmp(lexer->token_str->buffer, "where") == 0)
break;
vStringClear(name);
vStringCat(name, lexer->token_str);
}
else if (lexer->cur_token == '<' || lexer->cur_token == '{')
{
break;
}
advanceToken(lexer, true);
}
skipTypeBlock(lexer);
}
/* Impl format:
* "impl" [<type_bounds>] <qualified_ident>[<type_bounds>] ["for" <qualified_ident>[<type_bounds>]] "{" [<body>] "}"
*/
static void parseImpl (lexerState *lexer, vString *scope, int parent_kind)
{
unsigned long line;
MIOPos pos;
vString *name;
advanceToken(lexer, true);
line = lexer->line;
pos = lexer->pos;
skipTypeBlock(lexer);
name = vStringNew();
parseQualifiedType(lexer, name);
if (lexer->cur_token == TOKEN_IDENT && strcmp(lexer->token_str->buffer, "for") == 0)
{
advanceToken(lexer, true);
parseQualifiedType(lexer, name);
}
addTag(name, NULL, NULL, K_IMPL, line, pos, scope, parent_kind);
addToScope(scope, name);
parseBlock(lexer, true, K_IMPL, scope);
vStringDelete(name);
}
/* Static format:
* "static" ["mut"] <ident>
*/
static void parseStatic (lexerState *lexer, vString *scope, int parent_kind)
{
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
if (strcmp(lexer->token_str->buffer, "mut") == 0)
{
advanceToken(lexer, true);
}
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, K_STATIC, lexer->line, lexer->pos, scope, parent_kind);
}
/* Type format:
* "type" <ident>
*/
static void parseType (lexerState *lexer, vString *scope, int parent_kind)
{
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, K_TYPE, lexer->line, lexer->pos, scope, parent_kind);
}
/* Structs and enums are very similar syntax-wise.
* It is possible to parse variants a bit more cleverly (e.g. make tuple variants functions and
* struct variants structs) but it'd be too clever and the signature wouldn't make too much sense without
* the enum's definition (e.g. for the type bounds)
*
* Struct/Enum format:
* "struct/enum" <ident>[<type_bounds>] "{" [<ident>,]+ "}"
* "struct/enum" <ident>[<type_bounds>] ";"
* */
static void parseStructOrEnum (lexerState *lexer, vString *scope, int parent_kind, bool is_struct)
{
int kind = is_struct ? K_STRUCT : K_ENUM;
int field_kind = is_struct ? K_FIELD : K_VARIANT;
int goal_tokens1[] = {';', '{'};
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, kind, lexer->line, lexer->pos, scope, parent_kind);
addToScope(scope, lexer->token_str);
skipUntil(lexer, goal_tokens1, 2);
if (lexer->cur_token == '{')
{
vString *field_name = vStringNew();
while (lexer->cur_token != TOKEN_EOF)
{
int goal_tokens2[] = {'}', ','};
/* Skip attributes. Format:
* #[..] or #![..]
* */
if (lexer->cur_token == '#')
{
advanceToken(lexer, true);
if (lexer->cur_token == '!')
advanceToken(lexer, true);
if (lexer->cur_token == '[')
{
/* It's an attribute, skip it. */
skipUntil(lexer, NULL, 0);
}
else
{
/* Something's up with this field, skip to the next one */
skipUntil(lexer, goal_tokens2, 2);
continue;
}
}
if (lexer->cur_token == TOKEN_IDENT)
{
if (strcmp(lexer->token_str->buffer, "priv") == 0
|| strcmp(lexer->token_str->buffer, "pub") == 0)
{
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
{
/* Something's up with this field, skip to the next one */
skipUntil(lexer, goal_tokens2, 2);
continue;
}
}
vStringClear(field_name);
vStringCat(field_name, lexer->token_str);
addTag(field_name, NULL, NULL, field_kind, lexer->line, lexer->pos, scope, kind);
skipUntil(lexer, goal_tokens2, 2);
}
if (lexer->cur_token == '}')
{
advanceToken(lexer, true);
break;
}
advanceToken(lexer, true);
}
vStringDelete(field_name);
}
}
/* Skip the body of the macro. Can't use skipUntil here as
* the body of the macro may have arbitrary code which confuses it (e.g.
* bitshift operators/function return arrows) */
static void skipMacro (lexerState *lexer)
{
int level = 0;
int plus_token = 0;
int minus_token = 0;
advanceToken(lexer, true);
switch (lexer->cur_token)
{
case '(':
plus_token = '(';
minus_token = ')';
break;
case '{':
plus_token = '{';
minus_token = '}';
break;
case '[':
plus_token = '[';
minus_token = ']';
break;
default:
return;
}
while (lexer->cur_token != TOKEN_EOF)
{
if (lexer->cur_token == plus_token)
level++;
else if (lexer->cur_token == minus_token)
level--;
if (level == 0)
break;
advanceToken(lexer, true);
}
advanceToken(lexer, true);
}
/*
* Macro rules format:
* "macro_rules" "!" <ident> <macro_body>
*/
static void parseMacroRules (lexerState *lexer, vString *scope, int parent_kind)
{
advanceToken(lexer, true);
if (lexer->cur_token != '!')
return;
advanceToken(lexer, true);
if (lexer->cur_token != TOKEN_IDENT)
return;
addTag(lexer->token_str, NULL, NULL, K_MACRO, lexer->line, lexer->pos, scope, parent_kind);
skipMacro(lexer);
}
/*
* Rust is very liberal with nesting, so this function is used pretty much for any block
*/
static void parseBlock (lexerState *lexer, bool delim, int kind, vString *scope)
{
int level = 1;
if (delim)
{
if (lexer->cur_token != '{')
return;
advanceToken(lexer, true);
}
while (lexer->cur_token != TOKEN_EOF)
{
if (lexer->cur_token == TOKEN_IDENT)
{
size_t old_scope_len = vStringLength(scope);
if (strcmp(lexer->token_str->buffer, "fn") == 0)
{
parseFn(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "mod") == 0)
{
parseMod(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "static") == 0)
{
parseStatic(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "trait") == 0)
{
parseTrait(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "type") == 0)
{
parseType(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "impl") == 0)
{
parseImpl(lexer, scope, kind);
}
else if(strcmp(lexer->token_str->buffer, "struct") == 0)
{
parseStructOrEnum(lexer, scope, kind, true);
}
else if(strcmp(lexer->token_str->buffer, "enum") == 0)
{
parseStructOrEnum(lexer, scope, kind, false);
}
else if(strcmp(lexer->token_str->buffer, "macro_rules") == 0)
{
parseMacroRules(lexer, scope, kind);
}
else
{
advanceToken(lexer, true);
if (lexer->cur_token == '!')
{
skipMacro(lexer);
}
}
resetScope(scope, old_scope_len);
}
else if (lexer->cur_token == '{')
{
level++;
advanceToken(lexer, true);
}
else if (lexer->cur_token == '}')
{
level--;
advanceToken(lexer, true);
}
else if (lexer->cur_token == '\'')
{
/* Skip over the 'static lifetime, as it confuses the static parser above */
advanceToken(lexer, true);
if (lexer->cur_token == TOKEN_IDENT && strcmp(lexer->token_str->buffer, "static") == 0)
advanceToken(lexer, true);
}
else
{
advanceToken(lexer, true);
}
if (delim && level <= 0)
break;
}
}
static void findRustTags (void)
{
lexerState lexer;
vString* scope = vStringNew();
initLexer(&lexer);
parseBlock(&lexer, false, K_NONE, scope);
vStringDelete(scope);
deInitLexer(&lexer);
}
extern parserDefinition *RustParser (void)
{
static const char *const extensions[] = { "rs", NULL };
parserDefinition *def = parserNew ("Rust");
def->kindTable = rustKinds;
def->kindCount = ARRAY_SIZE (rustKinds);
def->extensions = extensions;
def->parser = findRustTags;
return def;
}