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
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
|
header "pre_include_hpp" {
#include "driver.h"
#include "JavaAST.hpp"
#include <qlistview.h>
#include <kdebug.h>
#define SET_POSITION(ast,t)\
{ \
RefJavaAST(ast)->setLine( t->getLine() );\
RefJavaAST(ast)->setColumn( t->getColumn() ); \
}
}
options {
language="Cpp";
}
/** Java 1.3 Recognizer
*
* Run 'java Main [-showtree] directory-full-of-java-files'
*
* [The -showtree option pops up a Swing frame that shows
* the AST constructed from the parser.]
*
* Run 'java Main <directory full of java files>'
*
* Contributing authors:
* John Mitchell [email protected]
* Terence Parr [email protected]
* John Lilley [email protected]
* Scott Stanchfield [email protected]
* Markus Mohnen [email protected]
* Peter Williams [email protected]
* Allan Jacobs [email protected]
* Steve Messick [email protected]
* John Pybus [email protected]
*
* Version 1.00 December 9, 1997 -- initial release
* Version 1.01 December 10, 1997
* fixed bug in octal def (0..7 not 0..8)
* Version 1.10 August 1998 (parrt)
* added tree construction
* fixed definition of WS,comments for mac,pc,unix newlines
* added unary plus
* Version 1.11 (Nov 20, 1998)
* Added "shutup" option to turn off last ambig warning.
* Fixed inner class def to allow named class defs as statements
* synchronized requires compound not simple statement
* add [] after builtInType DOT class in primaryExpression
* "const" is reserved but not valid..removed from modifiers
* Version 1.12 (Feb 2, 1999)
* Changed LITERAL_xxx to xxx in tree grammar.
* Updated java.g to use tokens {...} now for 2.6.0 (new feature).
*
* Version 1.13 (Apr 23, 1999)
* Didn't have (stat)? for else clause in tree parser.
* Didn't gen ASTs for interface extends. Updated tree parser too.
* Updated to 2.6.0.
* Version 1.14 (Jun 20, 1999)
* Allowed final/abstract on local classes.
* Removed local interfaces from methods
* Put instanceof precedence where it belongs...in relationalExpr
* It also had expr not type as arg; fixed it.
* Missing ! on SEMI in classBlock
* fixed: (expr) + "string" was parsed incorrectly (+ as unary plus).
* fixed: didn't like Object[].class in parser or tree parser
* Version 1.15 (Jun 26, 1999)
* Screwed up rule with instanceof in it. :( Fixed.
* Tree parser didn't like (expr).something; fixed.
* Allowed multiple inheritance in tree grammar. oops.
* Version 1.16 (August 22, 1999)
* Extending an interface built a wacky tree: had extra EXTENDS.
* Tree grammar didn't allow multiple superinterfaces.
* Tree grammar didn't allow empty var initializer: {}
* Version 1.17 (October 12, 1999)
* ESC lexer rule allowed 399 max not 377 max.
* java.tree.g didn't handle the expression of synchronized
* statements.
* Version 1.18 (August 12, 2001)
* Terence updated to Java 2 Version 1.3 by
* observing/combining work of Allan Jacobs and Steve
* Messick. Handles 1.3 src. Summary:
* o primary didn't include boolean.class kind of thing
* o constructor calls parsed explicitly now:
* see explicitConstructorInvocation
* o add strictfp modifier
* o missing objBlock after new expression in tree grammar
* o merged local class definition alternatives, moved after declaration
* o fixed problem with ClassName.super.field
* o reordered some alternatives to make things more efficient
* o long and double constants were not differentiated from int/float
* o whitespace rule was inefficient: matched only one char
* o add an examples directory with some nasty 1.3 cases
* o made Main.java use buffered IO and a Reader for Unicode support
* o supports UNICODE?
* Using Unicode charVocabulay makes code file big, but only
* in the bitsets at the end. I need to make ANTLR generate
* unicode bitsets more efficiently.
* Version 1.19 (April 25, 2002)
* Terence added in nice fixes by John Pybus concerning floating
* constants and problems with super() calls. John did a nice
* reorg of the primary/postfix expression stuff to read better
* and makes f.g.super() parse properly (it was METHOD_CALL not
* a SUPER_CTOR_CALL). Also:
*
* o "finally" clause was a root...made it a child of "try"
* o Added stuff for asserts too for Java 1.4, but *commented out*
* as it is not backward compatible.
*
* Version 1.20 (October 27, 2002)
*
* Terence ended up reorging John Pybus' stuff to
* remove some nondeterminisms and some syntactic predicates.
* Note that the grammar is stricter now; e.g., this(...) must
* be the first statement.
*
* Trinary ?: operator wasn't working as array name:
* (isBig ? bigDigits : digits)[i];
*
* Checked parser/tree parser on source for
* Resin-2.0.5, jive-2.1.1, jdk 1.3.1, Lucene, antlr 2.7.2a4,
* and the 110k-line jGuru server source.
*
* Version tracking now done with following ID:
*
* $Id$
*
* This grammar is in the PUBLIC DOMAIN
*/
class JavaRecognizer extends Parser;
options {
k = 2; // two token lookahead
exportVocab=Java; // Call its vocabulary "Java"
codeGenMakeSwitchThreshold = 2; // Some optimizations
codeGenBitsetTestThreshold = 3;
defaultErrorHandler = true;
buildAST = true;
ASTLabelType = "RefJavaAST";
}
tokens {
BLOCK; MODIFIERS; OBJBLOCK; SLIST; CTOR_DEF; METHOD_DEF; VARIABLE_DEF;
INSTANCE_INIT; STATIC_INIT; TYPE; CLASS_DEF; INTERFACE_DEF;
PACKAGE_DEF; ARRAY_DECLARATOR; EXTENDS_CLAUSE; IMPLEMENTS_CLAUSE;
PARAMETERS; PARAMETER_DEF; LABELED_STAT; TYPECAST; INDEX_OP;
POST_INC; POST_DEC; METHOD_CALL; EXPR; ARRAY_INIT;
IMPORT; UNARY_MINUS; UNARY_PLUS; CASE_GROUP; ELIST; FOR_INIT; FOR_CONDITION;
FOR_ITERATOR; EMPTY_STAT; FINAL="final"; ABSTRACT="abstract";
STRICTFP="strictfp"; SUPER_CTOR_CALL; CTOR_CALL;
}
{
private:
Driver* m_driver;
public:
void setDriver( Driver* d ) { m_driver = d; }
void setFileName( const QString& fileName ) { m_driver->currentFileName() = fileName; }
void reportError( const ANTLR_USE_NAMESPACE(antlr)RecognitionException& ex ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(ex.getMessage().c_str()), ex.getLine(), ex.getColumn()) );
}
void reportError( const ANTLR_USE_NAMESPACE(std)string& errorMessage ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(errorMessage.c_str()), LT(1)->getLine(), LT(1)->getColumn()) );
}
void reportMessage( const ANTLR_USE_NAMESPACE(std)string& message ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(message.c_str()), LT(1)->getLine(), LT(1)->getColumn()) );
}
}
// Compilation Unit: In Java, this is a single file. This is the start
// rule for this parser
compilationUnit
: // A compilation unit starts with an optional package definition
( packageDefinition
| /* nothing */
)
// Next we have a series of zero or more import statements
( importDefinition )*
// Wrapping things up with any number of class or interface
// definitions
( typeDefinition )*
EOF!
;
// Package statement: "package" followed by an identifier.
packageDefinition
options {defaultErrorHandler = true;} // let ANTLR handle errors
: p:"package"^ {#p->setType(PACKAGE_DEF);} identifier SEMI!
;
// Import statement: import followed by a package or class name
importDefinition
options {defaultErrorHandler = true;}
: i:"import"^ {#i->setType(IMPORT);} identifierStar SEMI!
;
// A type definition in a file is either a class or interface definition.
typeDefinition
options {defaultErrorHandler = true;}
: m:modifiers!
( classDefinition[#m]
| interfaceDefinition[#m]
)
| SEMI!
;
/** A declaration is the creation of a reference or primitive-type variable
* Create a separate Type/Var tree for each var in the var list.
*/
declaration!
: m:modifiers t:typeSpec[false] v:variableDefinitions[#m,#t]
{#declaration = #v;}
;
// A type specification is a type name with possible brackets afterwards
// (which would make it an array type).
typeSpec[bool addImagNode]
: classTypeSpec[addImagNode]
| builtInTypeSpec[addImagNode]
;
// A class type specification is a class type with possible brackets afterwards
// (which would make it an array type).
classTypeSpec[bool addImagNode]
: identifier (lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);} RBRACK!)*
{
if ( addImagNode ) {
#classTypeSpec = #(#[TYPE,"TYPE"], #classTypeSpec);
}
}
;
// A builtin type specification is a builtin type with possible brackets
// afterwards (which would make it an array type).
builtInTypeSpec[bool addImagNode]
: builtInType (lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);} RBRACK!)*
{
if ( addImagNode ) {
#builtInTypeSpec = #(#[TYPE,"TYPE"], #builtInTypeSpec);
}
}
;
// A type name. which is either a (possibly qualified) class name or
// a primitive (builtin) type
type
: identifier
| builtInType
;
// The primitive types.
builtInType
: "void"
| "boolean"
| "byte"
| "char"
| "short"
| "int"
| "float"
| "long"
| "double"
;
// A (possibly-qualified) java identifier. We start with the first IDENT
// and expand its name by adding dots and following IDENTS
identifier
: IDENT ( DOT^ IDENT )*
;
identifierStar
: IDENT
( DOT^ IDENT )*
( DOT^ STAR )?
;
// A list of zero or more modifiers. We could have used (modifier)* in
// place of a call to modifiers, but I thought it was a good idea to keep
// this rule separate so they can easily be collected in a Vector if
// someone so desires
modifiers
: ( modifier )*
{#modifiers = #([MODIFIERS, "MODIFIERS"], #modifiers);}
;
// modifiers for Java classes, interfaces, class/instance vars and methods
modifier
: "private"
| "public"
| "protected"
| "static"
| "transient"
| "final"
| "abstract"
| "native"
| "threadsafe"
| "synchronized"
// | "const" // reserved word, but not valid
| "volatile"
| "strictfp"
;
// Definition of a Java class
classDefinition![RefJavaAST modifiers]
: "class" IDENT
// it _might_ have a superclass...
sc:superClassClause
// it might implement some interfaces...
ic:implementsClause
// now parse the body of the class
cb:classBlock
{#classDefinition = #(#[CLASS_DEF,"CLASS_DEF"],
modifiers,IDENT,sc,ic,cb);}
;
superClassClause!
: ( "extends" id:identifier )?
{#superClassClause = #(#[EXTENDS_CLAUSE,"EXTENDS_CLAUSE"],id);}
;
// Definition of a Java Interface
interfaceDefinition![RefJavaAST modifiers]
: "interface" IDENT
// it might extend some other interfaces
ie:interfaceExtends
// now parse the body of the interface (looks like a class...)
cb:classBlock
{#interfaceDefinition = #(#[INTERFACE_DEF,"INTERFACE_DEF"],
modifiers,IDENT,ie,cb);}
;
// This is the body of a class. You can have fields and extra semicolons,
// That's about it (until you see what a field is...)
classBlock
: LCURLY!
( field | SEMI! )*
RCURLY!
{#classBlock = #([OBJBLOCK, "OBJBLOCK"], #classBlock);}
;
// An interface can extend several other interfaces...
interfaceExtends
: (
e:"extends"!
identifier ( COMMA! identifier )*
)?
{#interfaceExtends = #(#[EXTENDS_CLAUSE,"EXTENDS_CLAUSE"],
#interfaceExtends);}
;
// A class can implement several interfaces...
implementsClause
: (
i:"implements"! identifier ( COMMA! identifier )*
)?
{#implementsClause = #(#[IMPLEMENTS_CLAUSE,"IMPLEMENTS_CLAUSE"],
#implementsClause);}
;
// Now the various things that can be defined inside a class or interface...
// Note that not all of these are really valid in an interface (constructors,
// for example), and if this grammar were used for a compiler there would
// need to be some semantic checks to make sure we're doing the right thing...
field!
: // method, constructor, or variable declaration
mods:modifiers
( h:ctorHead s:constructorBody // constructor
{#field = #(#[CTOR_DEF,"CTOR_DEF"], mods, h, s);}
| cd:classDefinition[#mods] // inner class
{#field = #cd;}
| id:interfaceDefinition[#mods] // inner interface
{#field = #id;}
| t:typeSpec[false] // method or variable declaration(s)
( IDENT // the name of the method
// parse the formal parameter declarations.
LPAREN! param:parameterDeclarationList RPAREN!
rt:declaratorBrackets[#t]
// get the list of exceptions that this method is
// declared to throw
(tc:throwsClause)?
( s2:compoundStatement | SEMI )
{#field = #(#[METHOD_DEF,"METHOD_DEF"],
mods,
#(#[TYPE,"TYPE"],rt),
IDENT,
param,
tc,
s2);}
| v:variableDefinitions[#mods,#t] SEMI
// {#field = #(#[VARIABLE_DEF,"VARIABLE_DEF"], v);}
{#field = #v;}
)
)
// "static { ... }" class initializer
| "static" s3:compoundStatement
{#field = #(#[STATIC_INIT,"STATIC_INIT"], s3);}
// "{ ... }" instance initializer
| s4:compoundStatement
{#field = #(#[INSTANCE_INIT,"INSTANCE_INIT"], s4);}
;
constructorBody
: lc:LCURLY^ {#lc->setType(SLIST);}
( options { greedy=true; } : explicitConstructorInvocation)?
(statement)*
RCURLY!
;
/** Catch obvious constructor calls, but not the expr.super(...) calls */
explicitConstructorInvocation
: "this"! lp1:LPAREN^ argList RPAREN! SEMI!
{#lp1->setType(CTOR_CALL);}
| "super"! lp2:LPAREN^ argList RPAREN! SEMI!
{#lp2->setType(SUPER_CTOR_CALL);}
;
variableDefinitions[RefJavaAST mods, RefJavaAST t]
: variableDeclarator[(RefJavaAST)getASTFactory()->dupTree((antlr::RefAST)mods),
(RefJavaAST)getASTFactory()->dupTree((antlr::RefAST)t)]
( COMMA!
variableDeclarator[(RefJavaAST)getASTFactory()->dupTree((antlr::RefAST)mods),
(RefJavaAST)getASTFactory()->dupTree((antlr::RefAST)t)]
)*
;
/** Declaration of a variable. This can be a class/instance variable,
* or a local variable in a method
* It can also include possible initialization.
*/
variableDeclarator![RefJavaAST mods, RefJavaAST t]
: id:IDENT d:declaratorBrackets[t] v:varInitializer
{#variableDeclarator = #(#[VARIABLE_DEF,"VARIABLE_DEF"], mods, #(#[TYPE,"TYPE"],d), id, v);}
;
declaratorBrackets[RefJavaAST typ]
: {#declaratorBrackets=typ;}
(lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);} RBRACK!)*
;
varInitializer
: ( ASSIGN^ initializer )?
;
// This is an initializer used to set up an array.
arrayInitializer
: lc:LCURLY^ {#lc->setType(ARRAY_INIT);}
( initializer
(
// CONFLICT: does a COMMA after an initializer start a new
// initializer or start the option ',' at end?
// ANTLR generates proper code by matching
// the comma as soon as possible.
options {
warnWhenFollowAmbig = false;
}
:
COMMA! initializer
)*
(COMMA!)?
)?
RCURLY!
;
// The two "things" that can initialize an array element are an expression
// and another (nested) array initializer.
initializer
: expression
| arrayInitializer
;
// This is the header of a method. It includes the name and parameters
// for the method.
// This also watches for a list of exception classes in a "throws" clause.
ctorHead
: IDENT // the name of the method
// parse the formal parameter declarations.
LPAREN! parameterDeclarationList RPAREN!
// get the list of exceptions that this method is declared to throw
(throwsClause)?
;
// This is a list of exception classes that the method is declared to throw
throwsClause
: "throws"^ identifier ( COMMA! identifier )*
;
// A list of formal parameters
parameterDeclarationList
: ( parameterDeclaration ( COMMA! parameterDeclaration )* )?
{#parameterDeclarationList = #(#[PARAMETERS,"PARAMETERS"],
#parameterDeclarationList);}
;
// A formal parameter.
parameterDeclaration!
: pm:parameterModifier t:typeSpec[false] id:IDENT
pd:declaratorBrackets[#t]
{#parameterDeclaration = #(#[PARAMETER_DEF,"PARAMETER_DEF"],
pm, #([TYPE,"TYPE"],pd), id);}
;
parameterModifier
: (f:"final")?
{#parameterModifier = #(#[MODIFIERS,"MODIFIERS"], f);}
;
// Compound statement. This is used in many contexts:
// Inside a class definition prefixed with "static":
// it is a class initializer
// Inside a class definition without "static":
// it is an instance initializer
// As the body of a method
// As a completely indepdent braced block of code inside a method
// it starts a new scope for variable definitions
compoundStatement
: lc:LCURLY^ {#lc->setType(SLIST);}
// include the (possibly-empty) list of statements
(statement)*
RCURLY!
;
statement
// A list of statements in curly braces -- start a new scope!
: compoundStatement
// declarations are ambiguous with "ID DOT" relative to expression
// statements. Must backtrack to be sure. Could use a semantic
// predicate to test symbol table to see what the type was coming
// up, but that's pretty hard without a symbol table ;)
| (declaration)=> declaration SEMI!
// An expression statement. This could be a method call,
// assignment statement, or any other expression evaluated for
// side-effects.
| expression SEMI!
// class definition
| m:modifiers! classDefinition[#m]
// Attach a label to the front of a statement
| IDENT c:COLON^ {#c->setType(LABELED_STAT);} statement
// If-else statement
| "if"^ LPAREN! expression RPAREN! statement
(
// CONFLICT: the old "dangling-else" problem...
// ANTLR generates proper code matching
// as soon as possible. Hush warning.
options {
warnWhenFollowAmbig = false;
}
:
"else"! statement
)?
// For statement
| "for"^
LPAREN!
forInit SEMI! // initializer
forCond SEMI! // condition test
forIter // updater
RPAREN!
statement // statement to loop over
// While statement
| "while"^ LPAREN! expression RPAREN! statement
// do-while statement
| "do"^ statement "while"! LPAREN! expression RPAREN! SEMI!
// get out of a loop (or switch)
| "break"^ (IDENT)? SEMI!
// do next iteration of a loop
| "continue"^ (IDENT)? SEMI!
// Return an expression
| "return"^ (expression)? SEMI!
// switch/case statement
| "switch"^ LPAREN! expression RPAREN! LCURLY!
( casesGroup )*
RCURLY!
// exception try-catch block
| tryBlock
// throw an exception
| "throw"^ expression SEMI!
// synchronize a statement
| "synchronized"^ LPAREN! expression RPAREN! compoundStatement
// asserts (uncomment if you want 1.4 compatibility)
// | "assert"^ expression ( COLON! expression )? SEMI!
// empty statement
| s:SEMI {#s->setType(EMPTY_STAT);}
;
casesGroup
: ( // CONFLICT: to which case group do the statements bind?
// ANTLR generates proper code: it groups the
// many "case"/"default" labels together then
// follows them with the statements
options {
greedy = true;
}
:
aCase
)+
caseSList
{#casesGroup = #([CASE_GROUP, "CASE_GROUP"], #casesGroup);}
;
aCase
: ("case"^ expression | "default") COLON!
;
caseSList
: (statement)*
{#caseSList = #(#[SLIST,"SLIST"],#caseSList);}
;
// The initializer for a for loop
forInit
// if it looks like a declaration, it is
: ( (declaration)=> declaration
// otherwise it could be an expression list...
| expressionList
)?
{#forInit = #(#[FOR_INIT,"FOR_INIT"],#forInit);}
;
forCond
: (expression)?
{#forCond = #(#[FOR_CONDITION,"FOR_CONDITION"],#forCond);}
;
forIter
: (expressionList)?
{#forIter = #(#[FOR_ITERATOR,"FOR_ITERATOR"],#forIter);}
;
// an exception handler try/catch block
tryBlock
: "try"^ compoundStatement
(handler)*
( finallyClause )?
;
finallyClause
: "finally"^ compoundStatement
;
// an exception handler
handler
: "catch"^ LPAREN! parameterDeclaration RPAREN! compoundStatement
;
// expressions
// Note that most of these expressions follow the pattern
// thisLevelExpression :
// nextHigherPrecedenceExpression
// (OPERATOR nextHigherPrecedenceExpression)*
// which is a standard recursive definition for a parsing an expression.
// The operators in java have the following precedences:
// lowest (13) = *= /= %= += -= <<= >>= >>>= &= ^= |=
// (12) ?:
// (11) ||
// (10) &&
// ( 9) |
// ( 8) ^
// ( 7) &
// ( 6) == !=
// ( 5) < <= > >=
// ( 4) << >>
// ( 3) +(binary) -(binary)
// ( 2) * / %
// ( 1) ++ -- +(unary) -(unary) ~ ! (type)
// [] () (method call) . (dot -- identifier qualification)
// new () (explicit parenthesis)
//
// the last two are not usually on a precedence chart; I put them in
// to point out that new has a higher precedence than '.', so you
// can validy use
// new Frame().show()
//
// Note that the above precedence levels map to the rules below...
// Once you have a precedence chart, writing the appropriate rules as below
// is usually very straightfoward
// the mother of all expressions
expression
: assignmentExpression
{#expression = #(#[EXPR,"EXPR"],#expression);}
;
// This is a list of expressions.
expressionList
: expression (COMMA! expression)*
{#expressionList = #(#[ELIST,"ELIST"], expressionList);}
;
// assignment expression (level 13)
assignmentExpression
: conditionalExpression
( ( ASSIGN^
| PLUS_ASSIGN^
| MINUS_ASSIGN^
| STAR_ASSIGN^
| DIV_ASSIGN^
| MOD_ASSIGN^
| SR_ASSIGN^
| BSR_ASSIGN^
| SL_ASSIGN^
| BAND_ASSIGN^
| BXOR_ASSIGN^
| BOR_ASSIGN^
)
assignmentExpression
)?
;
// conditional test (level 12)
conditionalExpression
: logicalOrExpression
( QUESTION^ assignmentExpression COLON! conditionalExpression )?
;
// logical or (||) (level 11)
logicalOrExpression
: logicalAndExpression (LOR^ logicalAndExpression)*
;
// logical and (&&) (level 10)
logicalAndExpression
: inclusiveOrExpression (LAND^ inclusiveOrExpression)*
;
// bitwise or non-short-circuiting or (|) (level 9)
inclusiveOrExpression
: exclusiveOrExpression (BOR^ exclusiveOrExpression)*
;
// exclusive or (^) (level 8)
exclusiveOrExpression
: andExpression (BXOR^ andExpression)*
;
// bitwise or non-short-circuiting and (&) (level 7)
andExpression
: equalityExpression (BAND^ equalityExpression)*
;
// equality/inequality (==/!=) (level 6)
equalityExpression
: relationalExpression ((NOT_EQUAL^ | EQUAL^) relationalExpression)*
;
// boolean relational expressions (level 5)
relationalExpression
: shiftExpression
( ( ( LT_^
| GT^
| LE^
| GE^
)
shiftExpression
)*
| "instanceof"^ typeSpec[true]
)
;
// bit shift expressions (level 4)
shiftExpression
: additiveExpression ((SL^ | SR^ | BSR^) additiveExpression)*
;
// binary addition/subtraction (level 3)
additiveExpression
: multiplicativeExpression ((PLUS^ | MINUS^) multiplicativeExpression)*
;
// multiplication/division/modulo (level 2)
multiplicativeExpression
: unaryExpression ((STAR^ | DIV^ | MOD^ ) unaryExpression)*
;
unaryExpression
: INC^ unaryExpression
| DEC^ unaryExpression
| MINUS^ {#MINUS->setType(UNARY_MINUS);} unaryExpression
| PLUS^ {#PLUS->setType(UNARY_PLUS);} unaryExpression
| unaryExpressionNotPlusMinus
;
unaryExpressionNotPlusMinus
: BNOT^ unaryExpression
| LNOT^ unaryExpression
| ( // subrule allows option to shut off warnings
options {
// "(int" ambig with postfixExpr due to lack of sequence
// info in linear approximate LL(k). It's ok. Shut up.
generateAmbigWarnings=false;
}
: // If typecast is built in type, must be numeric operand
// Also, no reason to backtrack if type keyword like int, float...
lpb:LPAREN^ {#lpb->setType(TYPECAST);} builtInTypeSpec[true] RPAREN!
unaryExpression
// Have to backtrack to see if operator follows. If no operator
// follows, it's a typecast. No semantic checking needed to parse.
// if it _looks_ like a cast, it _is_ a cast; else it's a "(expr)"
| (LPAREN classTypeSpec[true] RPAREN unaryExpressionNotPlusMinus)=>
lp:LPAREN^ {#lp->setType(TYPECAST);} classTypeSpec[true] RPAREN!
unaryExpressionNotPlusMinus
| postfixExpression
)
;
// qualified names, array expressions, method invocation, post inc/dec
postfixExpression
:
/*
"this"! lp1:LPAREN^ argList RPAREN!
{#lp1->setType(CTOR_CALL);}
| "super"! lp2:LPAREN^ argList RPAREN!
{#lp2->setType(SUPER_CTOR_CALL);}
|
*/
primaryExpression
(
/*
options {
// the use of postfixExpression in SUPER_CTOR_CALL adds DOT
// to the lookahead set, and gives loads of false non-det
// warnings.
// shut them off.
generateAmbigWarnings=false;
}
: */
DOT^ IDENT
( lp:LPAREN^ {#lp->setType(METHOD_CALL);}
argList
RPAREN!
)?
| DOT^ "this"
| DOT^ "super"
( // (new Outer()).super() (create enclosing instance)
lp3:LPAREN^ argList RPAREN!
{#lp3->setType(SUPER_CTOR_CALL);}
| DOT^ IDENT
( lps:LPAREN^ {#lps->setType(METHOD_CALL);}
argList
RPAREN!
)?
)
| DOT^ newExpression
| lb:LBRACK^ {#lb->setType(INDEX_OP);} expression RBRACK!
)*
( // possibly add on a post-increment or post-decrement.
// allows INC/DEC on too much, but semantics can check
in:INC^ {#in->setType(POST_INC);}
| de:DEC^ {#de->setType(POST_DEC);}
)?
;
// the basic element of an expression
primaryExpression
: identPrimary ( options {greedy=true;} : DOT^ "class" )?
| constant
| "true"
| "false"
| "null"
| newExpression
| "this"
| "super"
| LPAREN! assignmentExpression RPAREN!
// look for int.class and int[].class
| builtInType
( lbt:LBRACK^ {#lbt->setType(ARRAY_DECLARATOR);} RBRACK! )*
DOT^ "class"
;
/** Match a, a.b.c refs, a.b.c(...) refs, a.b.c[], a.b.c[].class,
* and a.b.c.class refs. Also this(...) and super(...). Match
* this or super.
*/
identPrimary
: IDENT
(
options {
// .ident could match here or in postfixExpression.
// We do want to match here. Turn off warning.
greedy=true;
}
: DOT^ IDENT
)*
(
options {
// ARRAY_DECLARATOR here conflicts with INDEX_OP in
// postfixExpression on LBRACK RBRACK.
// We want to match [] here, so greedy. This overcomes
// limitation of linear approximate lookahead.
greedy=true;
}
: ( lp:LPAREN^ {#lp->setType(METHOD_CALL);} argList RPAREN! )
| ( options {greedy=true;} :
lbc:LBRACK^ {#lbc->setType(ARRAY_DECLARATOR);} RBRACK!
)+
)?
;
/** object instantiation.
* Trees are built as illustrated by the following input/tree pairs:
*
* new T()
*
* new
* |
* T -- ELIST
* |
* arg1 -- arg2 -- .. -- argn
*
* new int[]
*
* new
* |
* int -- ARRAY_DECLARATOR
*
* new int[] {1,2}
*
* new
* |
* int -- ARRAY_DECLARATOR -- ARRAY_INIT
* |
* EXPR -- EXPR
* | |
* 1 2
*
* new int[3]
* new
* |
* int -- ARRAY_DECLARATOR
* |
* EXPR
* |
* 3
*
* new int[1][2]
*
* new
* |
* int -- ARRAY_DECLARATOR
* |
* ARRAY_DECLARATOR -- EXPR
* | |
* EXPR 1
* |
* 2
*
*/
newExpression
: "new"^ type
( LPAREN! argList RPAREN! (classBlock)?
//java 1.1
// Note: This will allow bad constructs like
// new int[4][][3] {exp,exp}.
// There needs to be a semantic check here...
// to make sure:
// a) [ expr ] and [ ] are not mixed
// b) [ expr ] and an init are not used together
| newArrayDeclarator (arrayInitializer)?
)
;
argList
: ( expressionList
| /*nothing*/
{#argList = #[ELIST,"ELIST"];}
)
;
newArrayDeclarator
: (
// CONFLICT:
// newExpression is a primaryExpression which can be
// followed by an array index reference. This is ok,
// as the generated code will stay in this loop as
// long as it sees an LBRACK (proper behavior)
options {
warnWhenFollowAmbig = false;
}
:
lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);}
(expression)?
RBRACK!
)+
;
constant
: NUM_INT
| CHAR_LITERAL
| STRING_LITERAL
| NUM_FLOAT
| NUM_LONG
| NUM_DOUBLE
;
//----------------------------------------------------------------------------
// The Java scanner
//----------------------------------------------------------------------------
{
#include <string>
}
class JavaLexer extends Lexer;
options {
exportVocab=Java; // call the vocabulary "Java"
testLiterals=false; // don't automatically test for literals
defaultErrorHandler=false;
k=4; // four characters of lookahead
// charVocabulary='\u0003'..'\uFFFF';
charVocabulary='\u0003'..'\u00FF';
// without inlining some bitset tests, couldn't do unicode;
// I need to make ANTLR generate smaller bitsets; see
// bottom of JavaLexer.java
codeGenBitsetTestThreshold=20;
}
{
private:
Driver* m_driver;
public:
void setDriver( Driver* d ) { m_driver = d; }
void setFileName( const QString& fileName ) { m_driver->currentFileName() = fileName; }
virtual void reportError( const ANTLR_USE_NAMESPACE(antlr)RecognitionException& ex ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(ex.getMessage().c_str()), ex.getLine(), ex.getColumn()) );
}
virtual void reportError( const ANTLR_USE_NAMESPACE(std)string& errorMessage ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(errorMessage.c_str()), getLine(), getColumn()) );
}
virtual void reportWarning( const ANTLR_USE_NAMESPACE(std)string& warnMessage ){
m_driver->addProblem( m_driver->currentFileName(), Problem( QString::fromLocal8Bit(warnMessage.c_str()), getLine(), getColumn()) );
}
}
// OPERATORS
QUESTION : '?' ;
LPAREN : '(' ;
RPAREN : ')' ;
LBRACK : '[' ;
RBRACK : ']' ;
LCURLY : '{' ;
RCURLY : '}' ;
COLON : ':' ;
COMMA : ',' ;
//DOT : '.' ;
ASSIGN : '=' ;
EQUAL : "==" ;
LNOT : '!' ;
BNOT : '~' ;
NOT_EQUAL : "!=" ;
DIV : '/' ;
DIV_ASSIGN : "/=" ;
PLUS : '+' ;
PLUS_ASSIGN : "+=" ;
INC : "++" ;
MINUS : '-' ;
MINUS_ASSIGN : "-=" ;
DEC : "--" ;
STAR : '*' ;
STAR_ASSIGN : "*=" ;
MOD : '%' ;
MOD_ASSIGN : "%=" ;
SR : ">>" ;
SR_ASSIGN : ">>=" ;
BSR : ">>>" ;
BSR_ASSIGN : ">>>=" ;
GE : ">=" ;
GT : ">" ;
SL : "<<" ;
SL_ASSIGN : "<<=" ;
LE : "<=" ;
LT_ : '<' ;
BXOR : '^' ;
BXOR_ASSIGN : "^=" ;
BOR : '|' ;
BOR_ASSIGN : "|=" ;
LOR : "||" ;
BAND : '&' ;
BAND_ASSIGN : "&=" ;
LAND : "&&" ;
SEMI : ';' ;
// Whitespace -- ignored
WS : ( ' '
| '\t'
| '\f'
// handle newlines
| ( options {generateAmbigWarnings=false;}
: "\r\n" // Evil DOS
| '\r' // Macintosh
| '\n' // Unix (the right way)
)
{ newline(); }
)+
{ $setType(ANTLR_USE_NAMESPACE(antlr)Token::SKIP); }
;
// Single-line comments
SL_COMMENT
: "//"
(~('\n'|'\r'))* ('\n'|'\r'('\n')?)
{
$setType(ANTLR_USE_NAMESPACE(antlr)Token::SKIP);
newline();
}
;
// multiple-line comments
ML_COMMENT
: "/*"
( /* '\r' '\n' can be matched in one alternative or by matching
'\r' in one iteration and '\n' in another. I am trying to
handle any flavor of newline that comes in, but the language
that allows both "\r\n" and "\r" and "\n" to all be valid
newline is ambiguous. Consequently, the resulting grammar
must be ambiguous. I'm shutting this warning off.
*/
options {
generateAmbigWarnings=false;
}
:
{ LA(2)!='/' }? '*'
| '\r' '\n' {newline();}
| '\r' {newline();}
| '\n' {newline();}
| ~('*'|'\n'|'\r')
)*
"*/"
{$setType(ANTLR_USE_NAMESPACE(antlr)Token::SKIP);}
;
// character literals
CHAR_LITERAL
: '\'' ( ESC | ~'\'' ) '\''
;
// string literals
STRING_LITERAL
: '"' (ESC|~('"'|'\\'))* '"'
;
// escape sequence -- note that this is protected; it can only be called
// from another lexer rule -- it will not ever directly return a token to
// the parser
// There are various ambiguities hushed in this rule. The optional
// '0'...'9' digit matches should be matched here rather than letting
// them go back to STRING_LITERAL to be matched. ANTLR does the
// right thing by matching immediately; hence, it's ok to shut off
// the FOLLOW ambig warnings.
protected
ESC
: '\\'
( 'n'
| 'r'
| 't'
| 'b'
| 'f'
| '"'
| '\''
| '\\'
| ('u')+ HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT
| '0'..'3'
(
options {
warnWhenFollowAmbig = false;
}
: '0'..'7'
(
options {
warnWhenFollowAmbig = false;
}
: '0'..'7'
)?
)?
| '4'..'7'
(
options {
warnWhenFollowAmbig = false;
}
: '0'..'7'
)?
)
;
// hexadecimal digit (again, note it's protected!)
protected
HEX_DIGIT
: ('0'..'9'|'A'..'F'|'a'..'f')
;
// a dummy rule to force vocabulary to be all characters (except special
// ones that ANTLR uses internally (0 to 2)
protected
VOCAB
: '\3'..'\377'
;
// an identifier. Note that testLiterals is set to true! This means
// that after we match the rule, we look in the literals table to see
// if it's a literal or really an identifer
IDENT
options {testLiterals=true;}
: ('a'..'z'|'A'..'Z'|'_'|'$') ('a'..'z'|'A'..'Z'|'_'|'0'..'9'|'$')*
;
// a numeric literal
NUM_INT
{
bool isDecimal = false;
ANTLR_USE_NAMESPACE(antlr)RefToken t = ANTLR_USE_NAMESPACE(antlr)nullToken;
}
: '.' {_ttype = DOT;}
( ('0'..'9')+ (EXPONENT)? (f1:FLOAT_SUFFIX {t=f1;})?
{
if ( t &&
(t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos ||
t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
_ttype = NUM_FLOAT;
}
else {
_ttype = NUM_DOUBLE; // assume double
}
}
)?
| ( '0' {isDecimal = true;} // special case for just '0'
( ('x'|'X')
( // hex
// the 'e'|'E' and float suffix stuff look
// like hex digits, hence the (...)+ doesn't
// know when to stop: ambig. ANTLR resolves
// it correctly by matching immediately. It
// is therefor ok to hush warning.
options {
warnWhenFollowAmbig=false;
}
: HEX_DIGIT
)+
| ('0'..'7')+ // octal
)?
| ('1'..'9') ('0'..'9')* {isDecimal=true;} // non-zero decimal
)
( ('l'|'L') { _ttype = NUM_LONG; }
// only check to see if it's a float if looks like decimal so far
| {isDecimal}?
( '.' ('0'..'9')* (EXPONENT)? (f2:FLOAT_SUFFIX {t=f2;})?
| EXPONENT (f3:FLOAT_SUFFIX {t=f3;})?
| f4:FLOAT_SUFFIX {t=f4;}
)
{
if ( t &&
(t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos ||
t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
_ttype = NUM_FLOAT;
}
else {
_ttype = NUM_DOUBLE; // assume double
}
}
)?
;
// a couple protected methods to assist in matching floating point numbers
protected
EXPONENT
: ('e'|'E') ('+'|'-')? ('0'..'9')+
;
protected
FLOAT_SUFFIX
: 'f'|'F'|'d'|'D'
;
|