1 lexer grammar RustLexer;
4 public boolean is_at(int pos) {
5 return _input.index() == pos;
11 EQ, LT, LE, EQEQ, NE, GE, GT, ANDAND, OROR, NOT, TILDE, PLUS,
12 MINUS, STAR, SLASH, PERCENT, CARET, AND, OR, SHL, SHR, BINOP,
13 BINOPEQ, AT, DOT, DOTDOT, DOTDOTDOT, COMMA, SEMI, COLON,
14 MOD_SEP, RARROW, FAT_ARROW, LPAREN, RPAREN, LBRACKET, RBRACKET,
15 LBRACE, RBRACE, POUND, DOLLAR, UNDERSCORE, LIT_CHAR, LIT_BYTE,
16 LIT_INTEGER, LIT_FLOAT, LIT_STR, LIT_STR_RAW, LIT_BINARY,
17 LIT_BINARY_RAW, QUESTION, IDENT, LIFETIME, WHITESPACE, DOC_COMMENT,
18 COMMENT, SHEBANG, UTF8_BOM
21 import xidstart , xidcontinue;
24 /* Expression-operator symbols */
63 /* "Structural symbols" */
94 | 'u' HEXIT HEXIT HEXIT HEXIT
95 | 'U' HEXIT HEXIT HEXIT HEXIT HEXIT HEXIT HEXIT HEXIT
97 | 'u{' HEXIT HEXIT '}'
98 | 'u{' HEXIT HEXIT HEXIT '}'
99 | 'u{' HEXIT HEXIT HEXIT HEXIT '}'
100 | 'u{' HEXIT HEXIT HEXIT HEXIT HEXIT '}'
101 | 'u{' HEXIT HEXIT HEXIT HEXIT HEXIT HEXIT '}'
108 fragment INTEGER_SUFFIX
109 : { _input.LA(1) != 'e' && _input.LA(1) != 'E' }? SUFFIX
113 : '\'' ( '\\' CHAR_ESCAPE
115 | '\ud800' .. '\udbff' '\udc00' .. '\udfff'
121 : 'b\'' ( '\\' ( [xX] HEXIT HEXIT
123 | ~[\\'\n\t\r] '\udc00'..'\udfff'?
130 : [0-9][0-9_]* INTEGER_SUFFIX?
131 | '0b' [01_]+ INTEGER_SUFFIX?
132 | '0o' [0-7_]+ INTEGER_SUFFIX?
133 | '0x' [0-9a-fA-F_]+ INTEGER_SUFFIX?
137 : [0-9][0-9_]* ('.' {
138 /* dot followed by another dot is a range, not a float */
139 _input.LA(1) != '.' &&
140 /* dot followed by an identifier is an integer with a function call, not a float */
141 _input.LA(1) != '_' &&
142 !(_input.LA(1) >= 'a' && _input.LA(1) <= 'z') &&
143 !(_input.LA(1) >= 'A' && _input.LA(1) <= 'Z')
144 }? | ('.' [0-9][0-9_]*)? ([eE] [-+]? [0-9][0-9_]*)? SUFFIX?)
148 : '"' ('\\\n' | '\\\r\n' | '\\' CHAR_ESCAPE | .)*? '"' SUFFIX?
151 LIT_BINARY : 'b' LIT_STR ;
152 LIT_BINARY_RAW : 'b' LIT_STR_RAW ;
154 /* this is a bit messy */
156 fragment LIT_STR_RAW_INNER
161 fragment LIT_STR_RAW_INNER2
162 : POUND LIT_STR_RAW_INNER POUND
166 : 'r' LIT_STR_RAW_INNER SUFFIX?
172 IDENT : XID_Start XID_Continue* ;
174 fragment QUESTION_IDENTIFIER : QUESTION? IDENT;
176 LIFETIME : '\'' IDENT ;
178 WHITESPACE : [ \r\n\t]+ ;
180 UNDOC_COMMENT : '////' ~[\n]* -> type(COMMENT) ;
181 YESDOC_COMMENT : '///' ~[\r\n]* -> type(DOC_COMMENT) ;
182 OUTER_DOC_COMMENT : '//!' ~[\r\n]* -> type(DOC_COMMENT) ;
183 LINE_COMMENT : '//' ( ~[/\n] ~[\n]* )? -> type(COMMENT) ;
186 : ('/**' ~[*] | '/*!') (DOC_BLOCK_COMMENT | .)*? '*/' -> type(DOC_COMMENT)
189 BLOCK_COMMENT : '/*' (BLOCK_COMMENT | .)*? '*/' -> type(COMMENT) ;
191 /* these appear at the beginning of a file */
193 SHEBANG : '#!' { is_at(2) && _input.LA(1) != '[' }? ~[\r\n]* -> type(SHEBANG) ;
195 UTF8_BOM : '\ufeff' { is_at(1) }? -> skip ;