1 /* Lexical analysis for genksyms.
2 Copyright 1996, 1997 Linux International.
4 New implementation contributed by Richard Henderson <rth@tamu.edu>
5 Based on original work by Bjorn Ekwall <bj0rn@blox.se>
7 Taken from Linux modutils 2.4.22.
9 This program is free software; you can redistribute it and/or modify it
10 under the terms of the GNU General Public License as published by the
11 Free Software Foundation; either version 2 of the License, or (at your
12 option) any later version.
14 This program is distributed in the hope that it will be useful, but
15 WITHOUT ANY WARRANTY; without even the implied warranty of
16 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 General Public License for more details.
19 You should have received a copy of the GNU General Public License
20 along with this program; if not, write to the Free Software Foundation,
21 Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
34 /* We've got a two-level lexer here. We let flex do basic tokenization
35 and then we categorize those basic tokens in the second stage. */
36 #define YY_DECL static int yylex1(void)
40 IDENT [A-Za-z_\$][A-Za-z0-9_\$]*
44 X_INT 0[Xx][0-9A-Fa-f]+
45 I_SUF [Uu]|[Ll]|[Uu][Ll]|[Ll][Uu]
46 INT ({O_INT}|{D_INT}|{X_INT}){I_SUF}?
48 FRAC ([0-9]*\.[0-9]+)|([0-9]+\.)
51 REAL ({FRAC}{EXP}?{F_SUF}?)|([0-9]+{EXP}{F_SUF}?)
53 STRING L?\"([^\\\"]*\\.)*[^\\\"]*\"
54 CHAR L?\'([^\\\']*\\.)*[^\\\']*\'
56 MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>)
58 /* We don't do multiple input files. */
66 /* Keep track of our location in the original source files. */
67 ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME;
71 /* Ignore all other whitespace. */
75 {STRING} return STRING;
79 /* The Pedant requires that the other C multi-character tokens be
80 recognized as tokens. We don't actually use them since we don't
81 parse expressions, but we do want whitespace to be arranged
82 around them properly. */
83 {MC_TOKEN} return OTHER;
89 /* All other tokens are single characters. */
95 /* Bring in the keyword recognizer. */
100 /* Macros to append to our phrase collection list. */
102 #define _APP(T,L) do { \
103 cur_node = next_node; \
104 next_node = xmalloc(sizeof(*next_node)); \
105 next_node->next = cur_node; \
106 cur_node->string = memcpy(xmalloc(L+1), T, L+1); \
107 cur_node->tag = SYM_NORMAL; \
110 #define APP _APP(yytext, yyleng)
113 /* The second stage lexer. Here we incorporate knowledge of the state
114 of the parser to tailor the tokens that are returned. */
120 ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_BRACKET, ST_BRACE,
121 ST_EXPRESSION, ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
122 ST_TABLE_5, ST_TABLE_6
123 } lexstate = ST_NOTSTARTED;
125 static int suppress_type_lookup, dont_want_brace_phrase;
126 static struct string_list *next_node;
128 int token, count = 0;
129 struct string_list *cur_node;
131 if (lexstate == ST_NOTSTARTED)
133 next_node = xmalloc(sizeof(*next_node));
134 next_node->next = NULL;
135 lexstate = ST_NORMAL;
143 else if (token == FILENAME)
147 /* Save the filename and line number for later error messages. */
152 file = strchr(yytext, '\"')+1;
153 e = strchr(file, '\"');
155 cur_filename = memcpy(xmalloc(e-file+1), file, e-file+1);
156 cur_line = atoi(yytext+2);
169 const struct resword *r = is_reserved_word(yytext, yyleng);
172 switch (token = r->token)
175 lexstate = ST_ATTRIBUTE;
185 dont_want_brace_phrase = 3;
187 suppress_type_lookup = 2;
190 case EXPORT_SYMBOL_KEYW:
194 if (!suppress_type_lookup)
196 if (find_symbol(yytext, SYM_TYPEDEF, 1))
204 lexstate = ST_BRACKET;
210 if (dont_want_brace_phrase)
218 lexstate = ST_EXPRESSION;
238 lexstate = ST_NORMAL;
239 token = ATTRIBUTE_PHRASE;
258 lexstate = ST_NORMAL;
278 lexstate = ST_NORMAL;
279 token = BRACKET_PHRASE;
298 lexstate = ST_NORMAL;
299 token = BRACE_PHRASE;
311 case '(': case '[': case '{':
315 case ')': case ']': case '}':
322 /* Put back the token we just read so's we can find it again
323 after registering the expression. */
326 lexstate = ST_NORMAL;
327 token = EXPRESSION_PHRASE;
342 if (token == IDENT && yyleng == 1 && yytext[0] == 'X')
344 token = EXPORT_SYMBOL_KEYW;
345 lexstate = ST_TABLE_5;
349 lexstate = ST_TABLE_6;
355 case '{': case '[': case '(':
358 case '}': case ']': case ')':
363 lexstate = ST_TABLE_2;
373 lexstate = ST_NORMAL;
381 lexstate = ST_TABLE_2;
395 if (suppress_type_lookup > 0)
396 --suppress_type_lookup;
397 if (dont_want_brace_phrase > 0)
398 --dont_want_brace_phrase;
400 yylval = &next_node->next;