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 /* Version 2 checksumming does proper tokenization; version 1 wasn't
62 /* We don't do multiple input files. */
68 /* Keep track of our location in the original source files. */
69 ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME;
73 /* Ignore all other whitespace. */
77 {STRING} return STRING;
81 /* The Pedant requires that the other C multi-character tokens be
82 recognized as tokens. We don't actually use them since we don't
83 parse expressions, but we do want whitespace to be arranged
84 around them properly. */
85 <V2_TOKENS>{MC_TOKEN} return OTHER;
86 <V2_TOKENS>{INT} return INT;
87 <V2_TOKENS>{REAL} return REAL;
91 /* All other tokens are single characters. */
97 /* Bring in the keyword recognizer. */
102 /* Macros to append to our phrase collection list. */
104 #define _APP(T,L) do { \
105 cur_node = next_node; \
106 next_node = xmalloc(sizeof(*next_node)); \
107 next_node->next = cur_node; \
108 cur_node->string = memcpy(xmalloc(L+1), T, L+1); \
109 cur_node->tag = SYM_NORMAL; \
112 #define APP _APP(yytext, yyleng)
115 /* The second stage lexer. Here we incorporate knowledge of the state
116 of the parser to tailor the tokens that are returned. */
122 ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_BRACKET, ST_BRACE,
123 ST_EXPRESSION, ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
124 ST_TABLE_5, ST_TABLE_6
125 } lexstate = ST_NOTSTARTED;
127 static int suppress_type_lookup, dont_want_brace_phrase;
128 static struct string_list *next_node;
130 int token, count = 0;
131 struct string_list *cur_node;
133 if (lexstate == ST_NOTSTARTED)
136 next_node = xmalloc(sizeof(*next_node));
137 next_node->next = NULL;
138 lexstate = ST_NORMAL;
146 else if (token == FILENAME)
150 /* Save the filename and line number for later error messages. */
155 file = strchr(yytext, '\"')+1;
156 e = strchr(file, '\"');
158 cur_filename = memcpy(xmalloc(e-file+1), file, e-file+1);
159 cur_line = atoi(yytext+2);
172 const struct resword *r = is_reserved_word(yytext, yyleng);
175 switch (token = r->token)
178 lexstate = ST_ATTRIBUTE;
188 dont_want_brace_phrase = 3;
190 suppress_type_lookup = 2;
193 case EXPORT_SYMBOL_KEYW:
197 if (!suppress_type_lookup)
199 struct symbol *sym = find_symbol(yytext, SYM_TYPEDEF);
200 if (sym && sym->type == SYM_TYPEDEF)
208 lexstate = ST_BRACKET;
214 if (dont_want_brace_phrase)
222 lexstate = ST_EXPRESSION;
242 lexstate = ST_NORMAL;
243 token = ATTRIBUTE_PHRASE;
262 lexstate = ST_NORMAL;
282 lexstate = ST_NORMAL;
283 token = BRACKET_PHRASE;
302 lexstate = ST_NORMAL;
303 token = BRACE_PHRASE;
315 case '(': case '[': case '{':
319 case ')': case ']': case '}':
326 /* Put back the token we just read so's we can find it again
327 after registering the expression. */
330 lexstate = ST_NORMAL;
331 token = EXPRESSION_PHRASE;
346 if (token == IDENT && yyleng == 1 && yytext[0] == 'X')
348 token = EXPORT_SYMBOL_KEYW;
349 lexstate = ST_TABLE_5;
353 lexstate = ST_TABLE_6;
359 case '{': case '[': case '(':
362 case '}': case ']': case ')':
367 lexstate = ST_TABLE_2;
377 lexstate = ST_NORMAL;
385 lexstate = ST_TABLE_2;
399 if (suppress_type_lookup > 0)
400 --suppress_type_lookup;
401 if (dont_want_brace_phrase > 0)
402 --dont_want_brace_phrase;
404 yylval = &next_node->next;