Source

pida-poelzi-antlr / antlr / grammars / ES3.g

   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
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
/*

Copyrights 2008 Xebic Reasearch BV. All rights reserved (see license.txt).
Owner : Patrick Hulsmeijer.

This ANTLR 3 LL(*) grammar is based on Ecma-262 3rd edition (JavaScript 1.5, JScript 5.5). 
The annotations refer to the "A Grammar Summary" section (e.g. A.1 Lexical Grammar) and the numbers in parenthesis to the paragraph numbers (e.g. (7.8) ).
This document is best viewed with ANTLRWorks (www.antlr.org).


The major challenges faced in defining this grammar were:

-1- Ambiguity surrounding the DIV sign in relation to the multiplicative expression and the regular expression literal.
This is solved with some lexer driven magic: a gated semantical predicate turns the recognition of regular expressions on or off, based on the
value of the RegularExpressionsEnabled property. When regular expressions are enabled they take precedence over division expressions. The decision whether
regular expressions are enabled is based on the heuristics that the previous token can be considered as last token of a left-hand-side operand of a division.

-2- Automatic semicolon insertion.
This is solved within the parser. The semicolons are not physically inserted but the situations in which they should are recognized and treated as if they were.
The physical insertion of semicolons would be undesirable because of several reasons:
- performance degration because of how ANTLR handles tokens in token streams
- the alteration of the input, which we need to have unchanged
- it is superfluous being of no interest to AST construction

-3- Unicode identifiers
Because ANTLR couldn't handle the unicode tables defined in the specification well and for performance reasons unicode identifiers are implemented as an action 
driven alternative to ASCII identifiers. First the ASCII version is tried that is defined in detail in this grammar and then the unicode alternative is tried action driven.
Because of the fact that the ASCII version is defined in detail the mTokens switch generation in the lexer can predict identifiers appropriately.
For details see the identifier rules.


The minor challenges were related to converting the grammar to an ANTLR LL(*) grammar:
- Resolving the ambiguity between functionDeclaration vs functionExpression and block vs objectLiteral stemming from the expressionStatement production.
- Left recursive nature of the left hand side expressions.
- The assignmentExpression production.
- The forStatement production.
The grammar was kept as close as possible to the grammar in the "A Grammar Summary" section of Ecma-262.

*/

/*
 pida-internal: ecma3
 pida-alias: JavaScript javascript
 pida-human: ECMAScript
 pida-glob: *.js *.as 
 pida-mime: text/x-javascript
*/

grammar ES3 ;

options
{
	output = AST ;
    language = Python;
}

tokens
{
// Reserved words
	NULL		= 'null' ;
	TRUE		= 'true' ;
	FALSE		= 'false' ;

// Keywords
	BREAK		= 'break' ;
	CASE		= 'case' ;
	CATCH 		= 'catch' ;
	CONTINUE 	= 'continue' ;
	DEFAULT		= 'default' ;
	DELETE		= 'delete' ;
	DO 		= 'do' ;
	ELSE 		= 'else' ;
	FINALLY 	= 'finally' ;
	FOR 		= 'for' ;
	FUNCTION 	= 'function' ;
	IF 		= 'if' ;
	IN 		= 'in' ;
	INSTANCEOF 	= 'instanceof' ;
	NEW 		= 'new' ;
	RETURN 		= 'return' ;
	SWITCH 		= 'switch' ;
	THIS 		= 'this' ;
	THROW 		= 'throw' ;
	TRY 		= 'try' ;
	TYPEOF 		= 'typeof' ;
	VAR 		= 'var' ;
	VOID 		= 'void' ;
	WHILE 		= 'while' ;
	WITH 		= 'with' ;

// Future reserved words
	ABSTRACT	= 'abstract' ;
	BOOLEAN 	= 'boolean' ;
	BYTE 		= 'byte' ;
	CHAR 		= 'char' ;
	CLASS 		= 'class' ;
	CONST 		= 'const' ;
	DEBUGGER 	= 'debugger' ;
	DOUBLE		= 'double' ;
	ENUM 		= 'enum' ;
	EXPORT 		= 'export' ;
	EXTENDS		= 'extends' ;
	FINAL 		= 'final' ;
	FLOAT 		= 'float' ;
	GOTO 		= 'goto' ;
	IMPLEMENTS 	= 'implements' ;
	IMPORT		= 'import' ;
	INT 		= 'int' ;
	INTERFACE 	= 'interface' ;
	LONG 		= 'long' ;
	NATIVE 		= 'native' ;
	PACKAGE 	= 'package' ;
	PRIVATE 	= 'private' ;
	PROTECTED 	= 'protected' ;
	PUBLIC		= 'public' ;
	SHORT 		= 'short' ;
	STATIC 		= 'static' ;
	SUPER 		= 'super' ;
	SYNCHRONIZED 	= 'synchronized' ;
	THROWS 		= 'throws' ;
	TRANSIENT 	= 'transient' ;
	VOLATILE 	= 'volatile' ;

// Punctuators
	LBRACE		= '{' ;
	RBRACE		= '}' ;
	LPAREN		= '(' ;
	RPAREN		= ')' ;
	LBRACK		= '[' ;
	RBRACK		= ']' ;
	DOT		= '.' ;
	SEMIC		= ';' ;
	COMMA		= ',' ;
	LT		= '<' ;
	GT		= '>' ;
	LTE		= '<=' ;
	GTE		= '>=' ;
	EQ		= '==' ;
	NEQ		= '!=' ;
	SAME		= '===' ;
	NSAME		= '!==' ;
	ADD		= '+' ;
	SUB		= '-' ;
	MUL		= '*' ;
	MOD		= '%' ;
	INC		= '++' ;
	DEC		= '--' ;
	SHL		= '<<' ;
	SHR		= '>>' ;
	SHU		= '>>>' ;
	AND		= '&' ;
	OR		= '|' ;
	XOR		= '^' ;
	NOT		= '!' ;
	INV		= '~' ;
	LAND		= '&&' ;
	LOR		= '||' ;
	QUE		= '?' ;
	COLON		= ':' ;
	ASSIGN		= '=' ;
	ADDASS		= '+=' ;
	SUBASS		= '-=' ;
	MULASS		= '*=' ;
	MODASS		= '%=' ;
	SHLASS		= '<<=' ;
	SHRASS		= '>>=' ;
	SHUASS		= '>>>=' ;
	ANDASS		= '&=' ;
	ORASS		= '|=' ;
	XORASS		= '^=' ;
	DIV		= '/' ;
	DIVASS		= '/=' ;
	
// Imaginary
	ARGS ;
	ARRAY ;
	BLOCK ;
	BYFIELD ;
	BYINDEX ;
	CALL ;
	CEXPR ;
	EXPR ;
	FORITER ;
	FORSTEP ;
	ITEM ;
	LABELLED ;
	NAMEDVALUE ;
	NEG ;
	OBJECT ;
	PAREXPR ;
	PDEC ;
	PINC ;
	POS ;
}

@lexer::members
{
private Token last;

private final boolean areRegularExpressionsEnabled()
{
	if (last == null)
	{
		return true;
	}
	switch (last.getType())
	{
	// identifier
		case Identifier:
	// literals
		case NULL:
		case TRUE:
		case FALSE:
		case THIS:
		case OctalIntegerLiteral:
		case DecimalLiteral:
		case HexIntegerLiteral:
		case StringLiteral:
	// member access ending 
		case RBRACK:
	// function call or nested expression ending
		case RPAREN:
			return false;
	// otherwise OK
		default:
			return true;
	}
}
	
private final void consumeIdentifierUnicodeStart() throws RecognitionException, NoViableAltException
{
	int ch = input.LA(1);
	if (isIdentifierStartUnicode(ch))
	{
		matchAny();
		do
		{
			ch = input.LA(1);
			if (ch == '$' || (ch >= '0' && ch <= '9') || (ch >= 'A' && ch <= 'Z') || ch == '\\' || ch == '_' || (ch >= 'a' && ch <= 'z') || isIdentifierPartUnicode(ch))
			{
				mIdentifierPart();
			}
			else
			{
				return;
			}
		}
		while (true);
	}
	else
	{
		throw new NoViableAltException();
	}
}
	
private final boolean isIdentifierPartUnicode(int ch)
{
	return Character.isJavaIdentifierPart(ch);
}
	
private final boolean isIdentifierStartUnicode(int ch)
{
	return Character.isJavaIdentifierStart(ch);
}

public Token nextToken()
{
	Token result = super.nextToken();
	if (result.getChannel() == Token.DEFAULT_CHANNEL)
	{
		last = result;
	}
	return result;		
}
}

@parser::members
{
private final boolean isLeftHandSideAssign(RuleReturnScope lhs, Object[] cached)
{
	if (cached[0] != null)
	{
		return ((Boolean)cached[0]).booleanValue();
	}
	
	boolean result;
	if (isLeftHandSideExpression(lhs))
	{
		switch (input.LA(1))
		{
			case ASSIGN:
			case MULASS:
			case DIVASS:
			case MODASS:
			case ADDASS:
			case SUBASS:
			case SHLASS:
			case SHRASS:
			case SHUASS:
			case ANDASS:
			case XORASS:
			case ORASS:
				result = true;
				break;
			default:
				result = false;
				break;
		}
	}
	else
	{
		result = false;
	}
	
	cached[0] = new Boolean(result);
	return result;
}

private final static boolean isLeftHandSideExpression(RuleReturnScope lhs)
{
	if (lhs.getTree() == null) // e.g. during backtracking
	{
		return true;
	}
	else
	{
		switch (((Tree)lhs.getTree()).getType())
		{
		// primaryExpression
			case THIS:
			case Identifier:
			case NULL:
			case TRUE:
			case FALSE:
			case DecimalLiteral:
			case OctalIntegerLiteral:
			case HexIntegerLiteral:
			case StringLiteral:
			case RegularExpressionLiteral:
			case ARRAY:
			case OBJECT:
			case PAREXPR:
		// functionExpression
			case FUNCTION:
		// newExpression
			case NEW:
		// leftHandSideExpression
			case CALL:
			case BYFIELD:
			case BYINDEX:
				return true;
			
			default:
				return false;
		}
	}
}
	
private final boolean isLeftHandSideIn(RuleReturnScope lhs, Object[] cached)
{
	if (cached[0] != null)
	{
		return ((Boolean)cached[0]).booleanValue();
	}
	
	boolean result = isLeftHandSideExpression(lhs) && (input.LA(1) == IN);
	cached[0] = new Boolean(result);
	return result;
}

private final void promoteEOL(ParserRuleReturnScope rule)
{
	// Get current token and its type (the possibly offending token).
	Token lt = input.LT(1);
	int la = lt.getType();
	
	// We only need to promote an EOL when the current token is offending (not a SEMIC, EOF, RBRACE, EOL or MultiLineComment).
	// EOL and MultiLineComment are not offending as they're already promoted in a previous call to this method.
	// Promoting an EOL means switching it from off channel to on channel.
	// A MultiLineComment gets promoted when it contains an EOL.
	if (!(la == SEMIC || la == EOF || la == RBRACE || la == EOL || la == MultiLineComment))
	{
		// Start on the possition before the current token and scan backwards off channel tokens until the previous on channel token.
		for (int ix = lt.getTokenIndex() - 1; ix > 0; ix--)
		{
			lt = input.get(ix);
			if (lt.getChannel() == Token.DEFAULT_CHANNEL)
			{
				// On channel token found: stop scanning.
				break;
			}
			else if (lt.getType() == EOL || (lt.getType() == MultiLineComment && lt.getText().matches("/.*\r\n|\r|\n")))
			{
				// We found our EOL: promote the token to on channel, position the input on it and reset the rule start.
				lt.setChannel(Token.DEFAULT_CHANNEL);
				input.seek(lt.getTokenIndex());
				if (rule != null)
				{
					rule.start = lt;
				}
				break;
			}
		}
	}
}	
}

//
// $<	A.1 Lexical Grammar (7)
//

// Added for lexing purposes

fragment BSLASH
	: '\\'
	;
	
fragment DQUOTE
	: '"'
	;
	
fragment SQUOTE
	: '\''
	;

// $<	Whitespace (7.2)

fragment TAB
	: '\u0009'
	;

fragment VT // Vertical TAB
	: '\u000b'
	;

fragment FF // Form Feed
	: '\u000c'
	;

fragment SP // Space
	: '\u0020'
	;

fragment NBSP // Non-Breaking Space
	: '\u00a0'
	;

fragment USP // Unicode Space Separator (rest of Unicode category Zs)
	: '\u1680'  // OGHAM SPACE MARK
	| '\u180E'  // MONGOLIAN VOWEL SEPARATOR
	| '\u2000'  // EN QUAD
	| '\u2001'  // EM QUAD
	| '\u2002'  // EN SPACE
	| '\u2003'  // EM SPACE
	| '\u2004'  // THREE-PER-EM SPACE
	| '\u2005'  // FOUR-PER-EM SPACE
	| '\u2006'  // SIX-PER-EM SPACE
	| '\u2007'  // FIGURE SPACE
	| '\u2008'  // PUNCTUATION SPACE
	| '\u2009'  // THIN SPACE
	| '\u200A'  // HAIR SPACE
	| '\u202F'  // NARROW NO-BREAK SPACE
	| '\u205F'  // MEDIUM MATHEMATICAL SPACE
	| '\u3000'  // IDEOGRAPHIC SPACE
	;

WhiteSpace
	: ( TAB | VT | FF | SP | NBSP | USP )+ { $channel = HIDDEN; }
	;

// $>

// $<	Line terminators (7.3)

fragment LF // Line Feed
	: '\n'
	;

fragment CR // Carriage Return
	: '\r'
	;

fragment LS // Line Separator
	: '\u2028'
	;

fragment PS // Paragraph Separator
	: '\u2029'
	;

fragment LineTerminator
	: CR | LF | LS | PS
	;
		
EOL
	: ( ( CR LF? ) | LF | LS | PS ) { $channel = HIDDEN; }
	;
// $>

// $<	Comments (7.4)

MultiLineComment
	: '/*' ( options { greedy = false; } : . )* '*/' { $channel = HIDDEN; }
	;

SingleLineComment
	: '//' ( ~( LineTerminator ) )* { $channel = HIDDEN; }
	;

// $>

// $<	Tokens (7.5)

token
	: reservedWord
	| Identifier
	| punctuator
	| numericLiteral
	| StringLiteral
	;

// $<	Reserved words (7.5.1)

reservedWord
	: keyword
	| futureReservedWord
	| NULL
	| booleanLiteral
	;

// $>
	
// $<	Keywords (7.5.2)

keyword
	: BREAK
	| CASE
	| CATCH
	| CONTINUE
	| DEFAULT
	| DELETE
	| DO
	| ELSE
	| FINALLY
	| FOR
	| FUNCTION
	| IF
	| IN
	| INSTANCEOF
	| NEW
	| RETURN
	| SWITCH
	| THIS
	| THROW
	| TRY
	| TYPEOF
	| VAR
	| VOID
	| WHILE
	| WITH
	;

// $>

// $<	Future reserved words (7.5.3)

futureReservedWord
	: ABSTRACT
	| BOOLEAN
	| BYTE
	| CHAR
	| CLASS
	| CONST
	| DEBUGGER
	| DOUBLE
	| ENUM
	| EXPORT
	| EXTENDS
	| FINAL
	| FLOAT
	| GOTO
	| IMPLEMENTS
	| IMPORT
	| INT
	| INTERFACE
	| LONG
	| NATIVE
	| PACKAGE
	| PRIVATE
	| PROTECTED
	| PUBLIC
	| SHORT
	| STATIC
	| SUPER
	| SYNCHRONIZED
	| THROWS
	| TRANSIENT
	| VOLATILE
	;

// $>

// $>
	
// $<	Identifiers (7.6)

fragment IdentifierStartASCII
	: 'a'..'z' | 'A'..'Z'
	| '$'
	| '_'
	| BSLASH 'u' HexDigit HexDigit HexDigit HexDigit // UnicodeEscapeSequence
	;

/*
The first two alternatives define how ANTLR can match ASCII characters which can be considered as part of an identifier.
The last alternative matches other characters in the unicode range that can be sonsidered as part of an identifier.
*/
fragment IdentifierPart
	: DecimalDigit
	| IdentifierStartASCII
	| { isIdentifierPartUnicode(input.LA(1)) }? { matchAny(); }
	;

fragment IdentifierNameASCIIStart
	: IdentifierStartASCII IdentifierPart*
	;

/*
The second alternative acts as an action driven fallback to evaluate other characters in the unicode range than the ones in the ASCII subset.
Due to the first alternative this grammar defines enough so that ANTLR can generate a lexer that correctly predicts identifiers with characters in the ASCII range.
In that way keywords, other reserved words and ASCII identifiers are recognized with standard ANTLR driven logic. When the first character for an identifier fails to 
match this ASCII definition, the lexer calls consumeIdentifierUnicodeStart because of the action in the alternative. This method checks whether the character matches 
as first character in ranges other than ASCII and consumes further characters belonging to the identifier with help of mIdentifierPart generated out of the 
IdentifierPart rule above.
*/
Identifier
	: IdentifierNameASCIIStart
	| { consumeIdentifierUnicodeStart(); }
	;

// $>

// $<	Punctuators (7.7)

punctuator
	: LBRACE
	| RBRACE
	| LPAREN
	| RPAREN
	| LBRACK
	| RBRACK
	| DOT
	| SEMIC
	| COMMA
	| LT
	| GT
	| LTE
	| GTE
	| EQ
	| NEQ
	| SAME
	| NSAME
	| ADD
	| SUB
	| MUL
	| MOD
	| INC
	| DEC
	| SHL
	| SHR
	| SHU
	| AND
	| OR
	| XOR
	| NOT
	| INV
	| LAND
	| LOR
	| QUE
	| COLON
	| ASSIGN
	| ADDASS
	| SUBASS
	| MULASS
	| MODASS
	| SHLASS
	| SHRASS
	| SHUASS
	| ANDASS
	| ORASS
	| XORASS
	| DIV
	| DIVASS
	;

// $>

// $<	Literals (7.8)

literal
	: NULL
	| booleanLiteral
	| numericLiteral
	| StringLiteral
	| RegularExpressionLiteral
	;

booleanLiteral
	: TRUE
	| FALSE
	;

// $<	Numeric literals (7.8.3)

/*
Note: octal literals are described in the B Compatibility section.
These are removed from the standards but are here for backwards compatibility with earlier ECMAScript definitions.
*/

fragment DecimalDigit
	: '0'..'9'
	;

fragment HexDigit
	: DecimalDigit | 'a'..'f' | 'A'..'F'
	;

fragment OctalDigit
	: '0'..'7'
	;

fragment ExponentPart
	: ( 'e' | 'E' ) ( '+' | '-' )? DecimalDigit+
	;

fragment DecimalIntegerLiteral
	: '0'
	| '1'..'9' DecimalDigit*
	;

DecimalLiteral
	: DecimalIntegerLiteral '.' DecimalDigit* ExponentPart?
	| '.' DecimalDigit+ ExponentPart?
	| DecimalIntegerLiteral ExponentPart?
	;

OctalIntegerLiteral
	: '0' OctalDigit+
	;

HexIntegerLiteral
	: ( '0x' | '0X' ) HexDigit+
	;

numericLiteral
	: DecimalLiteral
	| OctalIntegerLiteral
	| HexIntegerLiteral
	;

// $>

// $<	String literals (7.8.4)

/*
Note: octal escape sequences are described in the B Compatibility section.
These are removed from the standards but are here for backwards compatibility with earlier ECMAScript definitions.
*/
	
fragment CharacterEscapeSequence
	: ~( DecimalDigit | 'x' | 'u' | LineTerminator ) // Concatenation of SingleEscapeCharacter and NonEscapeCharacter
	;

fragment ZeroToThree
	: '0'..'3'
	;
	
fragment OctalEscapeSequence
	: OctalDigit
	| ZeroToThree OctalDigit
	| '4'..'7' OctalDigit
	| ZeroToThree OctalDigit OctalDigit
	;
	
fragment HexEscapeSequence
	: 'x' HexDigit HexDigit
	;
	
fragment UnicodeEscapeSequence
	: 'u' HexDigit HexDigit HexDigit HexDigit
	;

fragment EscapeSequence
	:
	BSLASH 
	(
		CharacterEscapeSequence 
		| OctalEscapeSequence
		| HexEscapeSequence
		| UnicodeEscapeSequence
	)
	;

StringLiteral
	: SQUOTE ( ~( SQUOTE | BSLASH | LineTerminator ) | EscapeSequence )* SQUOTE
	| DQUOTE ( ~( DQUOTE | BSLASH | LineTerminator ) | EscapeSequence )* DQUOTE
	;

// $>

// $<	Regular expression literals (7.8.5)

fragment BackslashSequence
	: BSLASH ~( LineTerminator )
	;

fragment RegularExpressionFirstChar
	: ~ ( LineTerminator | MUL | BSLASH | DIV )
	| BackslashSequence
	;

fragment RegularExpressionChar
	: ~ ( LineTerminator | BSLASH | DIV )
	| BackslashSequence
	;

RegularExpressionLiteral
	: { areRegularExpressionsEnabled() }?=> DIV RegularExpressionFirstChar RegularExpressionChar* DIV IdentifierPart*
	;

// $>

// $>

// $>

//
// $<	A.3 Expressions (11)
//

// $<Primary expressions (11.1)

primaryExpression
	: THIS
	| Identifier
	| literal
	| arrayLiteral
	| objectLiteral
	| lpar=LPAREN expression RPAREN -> ^( PAREXPR[$lpar, "PAREXPR"] expression )
	;

arrayLiteral
	: lb=LBRACK ( arrayItem ( COMMA arrayItem )* )? RBRACK
	-> ^( ARRAY[$lb, "ARRAY"] arrayItem* )
	;

arrayItem
	: ( expr=assignmentExpression | { input.LA(1) == COMMA }? )
	-> ^( ITEM $expr? )
	;

objectLiteral
	: lb=LBRACE ( nameValuePair ( COMMA nameValuePair )* )? RBRACE
	-> ^( OBJECT[$lb, "OBJECT"] nameValuePair* )
	;
	
nameValuePair
	: propertyName COLON assignmentExpression
	-> ^( NAMEDVALUE propertyName assignmentExpression )
	;

propertyName
	: Identifier
	| StringLiteral
	| numericLiteral
	;

// $>

// $<Left-hand-side expressions (11.2)

/*
Refactored some rules to make them LL(*) compliant:
all the expressions surrounding member selection and calls have been moved to leftHandSideExpression to make them right recursive
*/

memberExpression
	: primaryExpression
	| functionExpression
	| newExpression
	;

newExpression
	: NEW^ primaryExpression
	;

	
arguments
	: LPAREN ( assignmentExpression ( COMMA assignmentExpression )* )? RPAREN
	-> ^( ARGS assignmentExpression* )
	;
	
leftHandSideExpression
	:
	(
		memberExpression 		-> memberExpression
	)
	(
		arguments			-> ^( CALL $leftHandSideExpression arguments )
		| LBRACK expression RBRACK	-> ^( BYINDEX $leftHandSideExpression expression )
		| DOT Identifier		-> ^( BYFIELD $leftHandSideExpression Identifier )
	)*
	;

// $>

// $<Postfix expressions (11.3)

/*
The specification states that there are no line terminators allowed before the postfix operators.
This is enforced by the call to promoteEOL in the action before ( INC | DEC ).
We only must promote EOLs when the la is INC or DEC because this production is chained as all expression rules.
In other words: only promote EOL when we are really in a postfix expression. A check on the la will ensure this.
*/
postfixExpression
	: leftHandSideExpression { if (input.LA(1) == INC || input.LA(1) == DEC) promoteEOL(null); } ( postfixOperator^ )?
	;
	
postfixOperator
	: op=INC { $op.setType(PINC); }
	| op=DEC { $op.setType(PDEC); }
	;

// $>

// $<Unary operators (11.4)

unaryExpression
	: postfixExpression
	| unaryOperator^ unaryExpression
	;
	
unaryOperator
	: DELETE
	| VOID
	| TYPEOF
	| INC
	| DEC
	| op=ADD { $op.setType(POS); }
	| op=SUB { $op.setType(NEG); }
	| INV
	| NOT
	;

// $>

// $<Multiplicative operators (11.5)

multiplicativeExpression
	: unaryExpression ( ( MUL | DIV | MOD )^ unaryExpression )*
	;

// $>

// $<Additive operators (11.6)

additiveExpression
	: multiplicativeExpression ( ( ADD | SUB )^ multiplicativeExpression )*
	;

// $>
	
// $<Bitwise shift operators (11.7)

shiftExpression
	: additiveExpression ( ( SHL | SHR | SHU )^ additiveExpression )*
	;

// $>
	
// $<Relational operators (11.8)

relationalExpression
	: shiftExpression ( ( LT | GT | LTE | GTE | INSTANCEOF | IN )^ shiftExpression )*
	;

relationalExpressionNoIn
	: shiftExpression ( ( LT | GT | LTE | GTE | INSTANCEOF )^ shiftExpression )*
	;

// $>
	
// $<Equality operators (11.9)

equalityExpression
	: relationalExpression ( ( EQ | NEQ | SAME | NSAME )^ relationalExpression )*
	;

equalityExpressionNoIn
	: relationalExpressionNoIn ( ( EQ | NEQ | SAME | NSAME )^ relationalExpressionNoIn )*
	;

// $>
		
// $<Binary bitwise operators (11.10)

bitwiseANDExpression
	: equalityExpression ( AND^ equalityExpression )*
	;

bitwiseANDExpressionNoIn
	: equalityExpressionNoIn ( AND^ equalityExpressionNoIn )*
	;
		
bitwiseXORExpression
	: bitwiseANDExpression ( XOR^ bitwiseANDExpression )*
	;
		
bitwiseXORExpressionNoIn
	: bitwiseANDExpressionNoIn ( XOR^ bitwiseANDExpressionNoIn )*
	;
	
bitwiseORExpression
	: bitwiseXORExpression ( OR^ bitwiseXORExpression )*
	;
	
bitwiseORExpressionNoIn
	: bitwiseXORExpressionNoIn ( OR^ bitwiseXORExpressionNoIn )*
	;

// $>
	
// $<Binary logical operators (11.11)

logicalANDExpression
	: bitwiseORExpression ( LAND^ bitwiseORExpression )*
	;

logicalANDExpressionNoIn
	: bitwiseORExpressionNoIn ( LAND^ bitwiseORExpressionNoIn )*
	;
	
logicalORExpression
	: logicalANDExpression ( LOR^ logicalANDExpression )*
	;
	
logicalORExpressionNoIn
	: logicalANDExpressionNoIn ( LOR^ logicalANDExpressionNoIn )*
	;

// $>
	
// $<Conditional operator (11.12)

conditionalExpression
	: logicalORExpression ( QUE^ assignmentExpression COLON! assignmentExpression )?
	;

conditionalExpressionNoIn
	: logicalORExpressionNoIn ( QUE^ assignmentExpressionNoIn COLON! assignmentExpressionNoIn )?
	;
	
// $>

// $<Assignment operators (11.13)

/*
The specification defines the AssignmentExpression rule as follows:
AssignmentExpression :
	ConditionalExpression 
	LeftHandSideExpression AssignmentOperator AssignmentExpression
This rule has a LL(*) conflict. Resolving this with a syntactical predicate will yield something like this:

assignmentExpression
	: ( leftHandSideExpression assignmentOperator )=> leftHandSideExpression assignmentOperator^ assignmentExpression
	| conditionalExpression
	;
assignmentOperator
	: ASSIGN | MULASS | DIVASS | MODASS | ADDASS | SUBASS | SHLASS | SHRASS | SHUASS | ANDASS | XORASS | ORASS
	;
	
But that didn't seem to work. Terence Par writes in his book that LL(*) conflicts in general can best be solved with auto backtracking. But that would be 
a performance killer for such a heavy used rule.
The solution I came up with is to always invoke the conditionalExpression first and than decide what to do based on the result of that rule.
When the rule results in a Tree that can't be coming from a left hand side expression, then we're done.
When it results in a Tree that is coming from a left hand side expression and the LA(1) is an assignment operator then parse the assignment operator
followed by the right recursive call.
*/
assignmentExpression
@init
{
	Object[] isLhs = new Object[1];
}
	: lhs=conditionalExpression
	( { isLeftHandSideAssign(lhs, isLhs) }? assignmentOperator^ assignmentExpression )?	
	;

assignmentOperator
	: ASSIGN | MULASS | DIVASS | MODASS | ADDASS | SUBASS | SHLASS | SHRASS | SHUASS | ANDASS | XORASS | ORASS
	;

assignmentExpressionNoIn
@init
{
	Object[] isLhs = new Object[1];
}
	: lhs=conditionalExpressionNoIn
	( { isLeftHandSideAssign(lhs, isLhs) }? assignmentOperator^ assignmentExpressionNoIn )?
	;
	
// $>
	
// $<Comma operator (11.14)

expression
	: exprs+=assignmentExpression ( COMMA exprs+=assignmentExpression )*
	-> { $exprs.size() > 1 }? ^( CEXPR $exprs+ )
	-> $exprs
	;

expressionNoIn
	: exprs+=assignmentExpressionNoIn ( COMMA exprs+=assignmentExpressionNoIn )*
	-> { $exprs.size() > 1 }? ^( CEXPR $exprs+ )
	-> $exprs
	;

// $>

// $>
	
//
// $<	A.4 Statements (12)
//

/*
This rule handles semicolons reported by the lexer and situations where the ECMA 3 specification states there should be semicolons automaticly inserted.
The auto semicolons are not actually inserted but this rule behaves as if they were.

In the following situations an ECMA 3 parser should auto insert absent but grammaticly required semicolons:
- the current token is a right brace
- the current token is the end of file (EOF) token
- there is at least one end of line (EOL) token between the current token and the previous token.

The RBRACE is handled by matching it but not consuming it.
The EOF needs no further handling because it is not consumed by default.
The EOL situation is handled by promoting the EOL or MultiLineComment with an EOL present from off channel to on channel
and thus making it parseable instead of handling it as white space. This promoting is done in the action promoteEOL.
*/
semic
@init
{
	// Mark current position so we can unconsume a RBRACE.
	int marker = input.mark();
	// Promote EOL if appropriate	
	promoteEOL(retval);
}
	: SEMIC
	| EOF
	| RBRACE { input.rewind(marker); }
	| EOL | MultiLineComment // (with EOL in it)
	;

/*
To solve the ambiguity between block and objectLiteral via expressionStatement all but the block alternatives have been moved to statementTail.
Now when k = 1 and a semantical predicate is defined ANTLR generates code that always will prefer block when the LA(1) is a LBRACE.
This will result in the same behaviour that is described in the specification under 12.4 on the expressionStatement rule.
*/
statement
options
{
	k = 1 ;
}
	: { input.LA(1) == LBRACE }? block
	| statementTail
	;
	
statementTail
	: variableStatement
	| emptyStatement
	| expressionStatement
	| ifStatement
	| iterationStatement
	| continueStatement
	| breakStatement
	| returnStatement
	| withStatement
	| labelledStatement
	| switchStatement
	| throwStatement
	| tryStatement
	;

// $<Block (12.1)

block
	: lb=LBRACE statement* RBRACE
	-> ^( BLOCK[$lb, "BLOCK"] statement* )
	;

// $>
	
// $<Variable statement 12.2)

variableStatement
	: VAR variableDeclaration ( COMMA variableDeclaration )* semic
	-> ^( VAR variableDeclaration+ )
	;

variableDeclaration
	: Identifier ( ASSIGN^ assignmentExpression )?
	;
	
variableDeclarationNoIn
	: Identifier ( ASSIGN^ assignmentExpressionNoIn )?
	;

// $>
	
// $<Empty statement (12.3)

emptyStatement
	: SEMIC!
	;

// $>
	
// $<Expression statement (12.4)

/*
The look ahead check on LBRACE and FUNCTION the specification mentions has been left out and its function, resolving the ambiguity between:
- functionExpression and functionDeclaration
- block and objectLiteral
are moved to the statement and sourceElement rules.
*/
expressionStatement
	: expression semic!
	;

// $>
	
// $<The if statement (12.5)

ifStatement
// The predicate is there just to get rid of the warning. ANTLR will handle the dangling else just fine.
	: IF LPAREN expression RPAREN statement ( { input.LA(1) == ELSE }? ELSE statement )?
	-> ^( IF expression statement+ )
	;

// $>
	
// $<Iteration statements (12.6)

iterationStatement
	: doStatement
	| whileStatement
	| forStatement
	;
	
doStatement
	: DO statement WHILE LPAREN expression RPAREN semic
	-> ^( DO statement expression )
	;
	
whileStatement
	: WHILE^ LPAREN! expression RPAREN! statement
	;

/*
The forStatement production is refactored considerably as the specification contains a very none LL(*) compliant definition.
The initial version was like this:	

forStatement
	: FOR^ LPAREN! forControl RPAREN! statement
	;
forControl
options
{
	backtrack = true ;
	//k = 3 ;
}
	: stepClause
	| iterationClause
	;
stepClause
options
{
	memoize = true ;
}
	: ( ex1=expressionNoIn | var=VAR variableDeclarationNoIn ( COMMA variableDeclarationNoIn )* )? SEMIC ex2=expression? SEMIC ex3=expression?
	-> { $var != null }? ^( FORSTEP ^( VAR[$var] variableDeclarationNoIn+ ) ^( EXPR $ex2? ) ^( EXPR $ex3? ) )
	-> ^( FORSTEP ^( EXPR $ex1? ) ^( EXPR $ex2? ) ^( EXPR $ex3? ) )
	;
iterationClause
options
{
	memoize = true ;
}
	: ( leftHandSideExpression | var=VAR variableDeclarationNoIn ) IN expression
	-> { $var != null }? ^( FORITER ^( VAR[$var] variableDeclarationNoIn ) ^( EXPR expression ) )
	-> ^( FORITER ^( EXPR leftHandSideExpression ) ^( EXPR expression ) )
	;
	
But this completely relies on the backtrack feature and capabilities of ANTLR. 
Furthermore backtracking seemed to have 3 major drawbacks:
- the performance cost of backtracking is considerably
- didn't seem to work well with ANTLRWorks
- when introducing a k value to optimize the backtracking away, ANTLR runs out of heap space
*/
forStatement
	: FOR^ LPAREN! forControl RPAREN! statement
	;

forControl
	: forControlVar
	| forControlExpression
	| forControlSemic
	;

forControlVar
	: VAR variableDeclarationNoIn
	(
		(
			IN expression
			-> ^( FORITER ^( VAR variableDeclarationNoIn ) ^( EXPR expression ) )
		)
		|
		(
			( COMMA variableDeclarationNoIn )* SEMIC ex1=expression? SEMIC ex2=expression?
			-> ^( FORSTEP ^( VAR variableDeclarationNoIn+ ) ^( EXPR $ex1? ) ^( EXPR $ex2? ) )
		)
	)
	;

forControlExpression
@init
{
	Object[] isLhs = new Object[1];
}
	: ex1=expressionNoIn
	( 
		{ isLeftHandSideIn(ex1, isLhs) }? (
			IN ex2=expression
			-> ^( FORITER ^( EXPR $ex1 ) ^( EXPR $ex2 ) )
		)
		|
		(
			SEMIC ex2=expression? SEMIC ex3=expression?
			-> ^( FORSTEP ^( EXPR $ex1 ) ^( EXPR $ex2? ) ^( EXPR $ex3? ) )
		)
	)
	;

forControlSemic
	: SEMIC ex1=expression? SEMIC ex2=expression?
	-> ^( FORSTEP ^( EXPR ) ^( EXPR $ex1? ) ^( EXPR $ex2? ) )
	;

// $>
	
// $<The continue statement (12.7)

/*
The action with the call to promoteEOL after CONTINUE is to enforce the semicolon insertion rule of the specification that there are
no line terminators allowed beween CONTINUE and the optional identifier.
As an optimization we check the la first to decide whether there is an identier following.
*/
continueStatement
	: CONTINUE^ { if (input.LA(1) == Identifier) promoteEOL(null); } Identifier? semic!
	;

// $>
	
// $<The break statement (12.8)

/*
The action with the call to promoteEOL after BREAK is to enforce the semicolon insertion rule of the specification that there are
no line terminators allowed beween BREAK and the optional identifier.
As an optimization we check the la first to decide whether there is an identier following.
*/
breakStatement
	: BREAK^ { if (input.LA(1) == Identifier) promoteEOL(null); } Identifier? semic!
	;

// $>
	
// $<The return statement (12.9)

/*
The action calling promoteEOL after RETURN ensures that there are no line terminators between RETURN and the optional expression as the specification states.
When there are these get promoted to on channel and thus virtual semicolon wannabees.
So the folowing code:

return
1

will be parsed as:

return;
1;
*/
returnStatement
	: RETURN^ { promoteEOL(null); } expression? semic!
	;

// $>
	
// $<The with statement (12.10)

withStatement
	: WITH^ LPAREN! expression RPAREN! statement
	;

// $>
	
// $<The switch statement (12.11)

switchStatement
@init
{
	int defaultClauseCount = 0;
}
	: SWITCH LPAREN expression RPAREN LBRACE ( { defaultClauseCount == 0 }?=> defaultClause { defaultClauseCount++; } | caseClause )* RBRACE
	-> ^( SWITCH expression defaultClause? caseClause* )
	;

caseClause
	: CASE^ expression COLON! statement*
	;
	
defaultClause
	: DEFAULT^ COLON! statement*
	;

// $>
	
// $<Labelled statements (12.12)

labelledStatement
	: Identifier COLON statement
	-> ^( LABELLED Identifier statement )
	;

// $>
	
// $<The throw statement (12.13)

/*
The action calling promoteEOL after THROW ensures that there are no line terminators between THROW and the expression as the specification states.
When there are line terminators these get promoted to on channel and thus to virtual semicolon wannabees.
So the folowing code:

throw
new Error()

will be parsed as:

throw;
new Error();

which will yield a recognition exception!
*/
throwStatement
	: THROW^ { promoteEOL(null); } expression semic!
	;

// $>
	
// $<The try statement (12.14)

tryStatement
	: TRY^ block ( catchClause finallyClause? | finallyClause )
	;
	
catchClause
	: CATCH^ LPAREN! Identifier RPAREN! block
	;
	
finallyClause
	: FINALLY^ block
	;

// $>

// $>

//
// $<	A.5 Functions and Programs (13, 14)
//

// $<	Function Definition (13)

functionDeclaration
	: FUNCTION name=Identifier formalParameterList functionBody
	-> ^( FUNCTION $name formalParameterList functionBody )
	;

functionExpression
	: FUNCTION name=Identifier? formalParameterList functionBody
	-> ^( FUNCTION $name? formalParameterList functionBody )
	;

formalParameterList
	: LPAREN ( args+=Identifier ( COMMA args+=Identifier )* )? RPAREN
	-> ^( ARGS $args* )
	;

functionBody
	: lb=LBRACE sourceElement* RBRACE
	-> ^( BLOCK[$lb, "BLOCK"] sourceElement* )
	;

// $>
	
// $<	Program (14)

program
	: sourceElement*
	;

/*
By setting k  to 1 for this rule and adding the semantical predicate ANTRL will generate code that will always prefer functionDeclararion over functionExpression
here and therefor remove the ambiguity between these to production.
This will result in the same behaviour that is described in the specification under 12.4 on the expressionStatement rule.
*/
sourceElement
options
{
	k = 1 ;
}
	: { input.LA(1) == FUNCTION }? functionDeclaration
	| statement
	;

// $>

// $>
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.