scan.l revision 1.141 1 %{
2 /* $NetBSD: scan.l,v 1.141 2024/05/11 16:12:28 rillig Exp $ */
3
4 /*
5 * Copyright (c) 1996 Christopher G. Demetriou. All Rights Reserved.
6 * Copyright (c) 1994, 1995 Jochen Pohl
7 * All Rights Reserved.
8 *
9 * Redistribution and use in source and binary forms, with or without
10 * modification, are permitted provided that the following conditions
11 * are met:
12 * 1. Redistributions of source code must retain the above copyright
13 * notice, this list of conditions and the following disclaimer.
14 * 2. Redistributions in binary form must reproduce the above copyright
15 * notice, this list of conditions and the following disclaimer in the
16 * documentation and/or other materials provided with the distribution.
17 * 3. All advertising materials mentioning features or use of this software
18 * must display the following acknowledgement:
19 * This product includes software developed by Jochen Pohl for
20 * The NetBSD Project.
21 * 4. The name of the author may not be used to endorse or promote products
22 * derived from this software without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
25 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
26 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
27 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
28 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
29 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
30 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
31 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
32 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
33 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 */
35
36 #include <sys/cdefs.h>
37 #if defined(__RCSID)
38 __RCSID("$NetBSD: scan.l,v 1.141 2024/05/11 16:12:28 rillig Exp $");
39 #endif
40
41 #include "lint1.h"
42 #include "cgram.h"
43
44 %}
45
46
47 HEX [0-9A-Fa-f]
48 EXP ([eE][+-]?[0-9]+)
49 PEXP (p[+-]?[0-9A-Fa-f]+)
50 FSUF ([fFlL]?[i]?)
51
52 %option nounput
53
54 %%
55
56 [_A-Za-z][_A-Za-z0-9]* return lex_name(yytext, yyleng);
57 0[bB][01]+[lLuU]* return lex_integer_constant(yytext, yyleng, 2);
58 0[0-7]*[lLuU]* return lex_integer_constant(yytext, yyleng, 8);
59 [1-9][0-9]*[lLuU]* return lex_integer_constant(yytext, yyleng, 10);
60 0[xX]{HEX}+[lLuU]* return lex_integer_constant(yytext, yyleng, 16);
61 [0-9]+\.[0-9]*{EXP}?{FSUF} |
62 [0-9]+{EXP}{FSUF} |
63 0[xX]{HEX}+\.{HEX}*{PEXP}{FSUF} |
64 0[xX]{HEX}+{PEXP}{FSUF} |
65 \.[0-9]+{EXP}?{FSUF} return lex_floating_constant(yytext, yyleng);
66 "=" return T_ASSIGN;
67 "*=" return lex_operator(T_OPASSIGN, MULASS);
68 "/=" return lex_operator(T_OPASSIGN, DIVASS);
69 "%=" return lex_operator(T_OPASSIGN, MODASS);
70 "+=" return lex_operator(T_OPASSIGN, ADDASS);
71 "-=" return lex_operator(T_OPASSIGN, SUBASS);
72 "<<=" return lex_operator(T_OPASSIGN, SHLASS);
73 ">>=" return lex_operator(T_OPASSIGN, SHRASS);
74 "&=" return lex_operator(T_OPASSIGN, ANDASS);
75 "^=" return lex_operator(T_OPASSIGN, XORASS);
76 "|=" return lex_operator(T_OPASSIGN, ORASS);
77 "||" return T_LOGOR;
78 "&&" return T_LOGAND;
79 "|" return T_BITOR;
80 "&" return T_AMPER;
81 "^" return T_BITXOR;
82 "==" return lex_operator(T_EQUALITY, EQ);
83 "!=" return lex_operator(T_EQUALITY, NE);
84 "<" return lex_operator(T_RELATIONAL, LT);
85 ">" return lex_operator(T_RELATIONAL, GT);
86 "<=" return lex_operator(T_RELATIONAL, LE);
87 ">=" return lex_operator(T_RELATIONAL, GE);
88 "<<" return lex_operator(T_SHIFT, SHL);
89 ">>" return lex_operator(T_SHIFT, SHR);
90 "++" return yylval.y_inc = true, T_INCDEC;
91 "--" return yylval.y_inc = false, T_INCDEC;
92 "->" return T_ARROW;
93 "." return T_POINT;
94 "+" return lex_operator(T_ADDITIVE, PLUS);
95 "-" return lex_operator(T_ADDITIVE, MINUS);
96 "*" return T_ASTERISK;
97 "/" return lex_operator(T_MULTIPLICATIVE, DIV);
98 "%" return lex_operator(T_MULTIPLICATIVE, MOD);
99 "!" return T_LOGNOT;
100 "~" return T_COMPLEMENT;
101 "\"" return lex_string();
102 "L\"" return lex_wide_string();
103 ";" return T_SEMI;
104 "{" return T_LBRACE;
105 "}" return T_RBRACE;
106 "," return T_COMMA;
107 ":" return T_COLON;
108 "?" return T_QUEST;
109 "[" return T_LBRACK;
110 "]" return T_RBRACK;
111 "(" return T_LPAREN;
112 ")" return T_RPAREN;
113 "..." return T_ELLIPSIS;
114 "::" return T_DCOLON;
115 "'" return lex_character_constant();
116 "L'" return lex_wide_character_constant();
117 ^#.*$ lex_directive(yytext);
118 \n lex_next_line();
119 \t|" "|\f|\v ;
120 "/*" lex_comment();
121 "//" lex_slash_slash_comment();
122 . lex_unknown_character(yytext[0]);
123
124 %%
125
126 /*
127 * In the above list of regular expressions, the tokens for character
128 * constants, string literals and comments are incomplete; they only match
129 * a prefix. The remainder of these tokens is scanned by reading bytes
130 * directly from the input stream.
131 */
132 int
133 lex_input(void)
134 {
135 return input();
136 }
137