IngInversaJava/JavaLexer.g4 at develop · GuidoDebandi/IngInversaJava · GitHub

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
lexer grammar JavaLexer;

// import JavaFragments;

@header{
    package gramaticas;
}
ABSTRACT:           'abstract';
ASSERT:             'assert';
BOOLEAN:            'boolean';
BREAK:              'break';
BYTE:               'byte';
CASE:               'case';
CATCH:              'catch';
CHAR:               'char';
CLASS:              'class';
CONST:              'const';
CONTINUE:           'continue';
DEFAULT:            'default';
DO:                 'do';
DOUBLE:             'double';
ELSE:               'else';
ENUM:               'enum';
EXTENDS:            'extends';
FINAL:              'final';
FINALLY:            'finally';
FLOAT:              'float';
FOR:                'for';
IF:                 'if';
GOTO:               'goto';
IMPLEMENTS:         'implements';
IMPORT:             'import';
INSTANCEOF:         'instanceof';
INT:                'int';
INTERFACE:          'interface';
LONG:               'long';
NATIVE:             'native';
NEW:                'new';
PACKAGE:            'package';
PRIVATE:            'private';
PROTECTED:          'protected';
PUBLIC:             'public';
RETURN:             'return';
SHORT:              'short';
STATIC:             'static';
STRICTFP:           'strictfp';
SUPER:              'super';
SWITCH:             'switch';
SYNCHRONIZED:       'synchronized';
THIS:               'this';
THROW:              'throw';
THROWS:             'throws';
TRANSIENT:          'transient';
TRY:                'try';
VOID:               'void';
VOLATILE:           'volatile';
WHILE:              'while';

// Literals

DECIMAL_LITERAL:    ('0' | [1-9] (Digits? | '_'+ Digits)) [lL]?;
HEX_LITERAL:        '0' [xX] [0-9a-fA-F] ([0-9a-fA-F_]* [0-9a-fA-F])? [lL]?;
OCT_LITERAL:        '0' '_'* [0-7] ([0-7_]* [0-7])? [lL]?;
BINARY_LITERAL:     '0' [bB] [01] ([01_]* [01])? [lL]?;

FLOAT_LITERAL:      (Digits '.' Digits? | '.' Digits) ExponentPart? [fFdD]?
             |       Digits (ExponentPart [fFdD]? | [fFdD])
             ;

HEX_FLOAT_LITERAL:  '0' [xX] (HexDigits '.'? | HexDigits? '.' HexDigits) [pP] [+-]? Digits [fFdD]?;

BOOL_LITERAL:       'true'
            |       'false'
            ;

CHAR_LITERAL:       '\'' (~['\\\r\n] | EscapeSequence) '\'';

STRING_LITERAL:     '"' (~["\\\r\n] | EscapeSequence)* '"';
NULL_LITERAL:       'null';
// Separators
LPAREN:             '(';
RPAREN:             ')';
LBRACE:             '{';
RBRACE:             '}';
LBRACK:             '[';
RBRACK:             ']';
SEMI:               ';';
COMMA:              ',';
DOT:                '.';
// Operators
ASSIGN:             '=';
GT:                 '>';
LT:                 '<';
BANG:               '!';
TILDE:              '~';
QUESTION:           '?';
COLON:              ':';
EQUAL:              '==';
LE:                 '<=';
GE:                 '>=';
NOTEQUAL:           '!=';
AND:                '&&';
OR:                 '||';
INC:                '++';
DEC:                '--';
ADD:                '+';
SUB:                '-';
MUL:                '*';
DIV:                '/';
BITAND:             '&';
BITOR:              '|';
CARET:              '^';
MOD:                '%';
ADD_ASSIGN:         '+=';
SUB_ASSIGN:         '-=';
MUL_ASSIGN:         '*=';
DIV_ASSIGN:         '/=';
AND_ASSIGN:         '&=';
OR_ASSIGN:          '|=';
XOR_ASSIGN:         '^=';
MOD_ASSIGN:         '%=';
LSHIFT_ASSIGN:      '<<=';
RSHIFT_ASSIGN:      '>>=';
URSHIFT_ASSIGN:     '>>>=';
// Java 8 tokens
ARROW:              '->';
COLONCOLON:         '::';
// Additional symbols not defined in the lexical specification
AT:                 '@';
ELLIPSIS:           '...';
// Whitespace and comments
WS:                 [ \t\r\n\u000C]+ -> channel(HIDDEN);
COMMENT:            '/*' .*? '*/'    -> channel(HIDDEN);
LINE_COMMENT:       '//' ~[\r\n]*    -> channel(HIDDEN);

// Identifiers

IDENTIFIER:         Letter LetterOrDigit*;

// Fragment rules

fragment ExponentPart
    : [eE] [+-]? Digits
    ;

fragment EscapeSequence
    : '\\' [btnfr"'\\]
    | '\\' ([0-3]? [0-7])? [0-7]
    | '\\' 'u'+ HexDigit HexDigit HexDigit HexDigit
    ;
fragment HexDigits
    : HexDigit ((HexDigit | '_')* HexDigit)?
    ;
fragment HexDigit
    : [0-9a-fA-F]
    ;
fragment Digits
    : [0-9] ([0-9_]* [0-9])?
    ;
fragment LetterOrDigit
    : Letter
    | [0-9]
    ;
fragment Letter
    : [a-zA-Z$_] // these are the "java letters" below 0x7F
    | ~[\u0000-\u007F\uD800-\uDBFF] // covers all characters above 0x7F which are not a surrogate
    | [\uD800-\uDBFF] [\uDC00-\uDFFF] // covers UTF-16 surrogate pairs encodings for U+10000 to U+10FFFF
    ;