diff options
Diffstat (limited to 'scripts/genksyms/lex.l')
| -rw-r--r-- | scripts/genksyms/lex.l | 409 |
1 files changed, 409 insertions, 0 deletions
diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l new file mode 100644 index 00000000..fe50ff9d --- /dev/null +++ b/scripts/genksyms/lex.l @@ -0,0 +1,409 @@ +/* Lexical analysis for genksyms. + Copyright 1996, 1997 Linux International. + + New implementation contributed by Richard Henderson <rth@tamu.edu> + Based on original work by Bjorn Ekwall <bj0rn@blox.se> + + Taken from Linux modutils 2.4.22. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2 of the License, or (at your + option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + + +%{ + +#include <limits.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> + +#include "genksyms.h" +#include "parse.h" + +/* We've got a two-level lexer here. We let flex do basic tokenization + and then we categorize those basic tokens in the second stage. */ +#define YY_DECL static int yylex1(void) + +%} + +IDENT [A-Za-z_\$][A-Za-z0-9_\$]* + +O_INT 0[0-7]* +D_INT [1-9][0-9]* +X_INT 0[Xx][0-9A-Fa-f]+ +I_SUF [Uu]|[Ll]|[Uu][Ll]|[Ll][Uu] +INT ({O_INT}|{D_INT}|{X_INT}){I_SUF}? + +FRAC ([0-9]*\.[0-9]+)|([0-9]+\.) +EXP [Ee][+-]?[0-9]+ +F_SUF [FfLl] +REAL ({FRAC}{EXP}?{F_SUF}?)|([0-9]+{EXP}{F_SUF}?) + +STRING L?\"([^\\\"]*\\.)*[^\\\"]*\" +CHAR L?\'([^\\\']*\\.)*[^\\\']*\' + +MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) + +/* Version 2 checksumming does proper tokenization; version 1 wasn't + quite so pedantic. */ +%s V2_TOKENS + +/* We don't do multiple input files. */ +%option noyywrap + +%option noinput + +%% + + + /* Keep track of our location in the original source files. */ +^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME; +^#.*\n cur_line++; +\n cur_line++; + + /* Ignore all other whitespace. */ +[ \t\f\v\r]+ ; + + +{STRING} return STRING; +{CHAR} return CHAR; +{IDENT} return IDENT; + + /* The Pedant requires that the other C multi-character tokens be + recognized as tokens. We don't actually use them since we don't + parse expressions, but we do want whitespace to be arranged + around them properly. */ +<V2_TOKENS>{MC_TOKEN} return OTHER; +<V2_TOKENS>{INT} return INT; +<V2_TOKENS>{REAL} return REAL; + +"..." return DOTS; + + /* All other tokens are single characters. */ +. return yytext[0]; + + +%% + +/* Bring in the keyword recognizer. */ + +#include "keywords.c" + + +/* Macros to append to our phrase collection list. */ + +#define _APP(T,L) do { \ + cur_node = next_node; \ + next_node = xmalloc(sizeof(*next_node)); \ + next_node->next = cur_node; \ + cur_node->string = memcpy(xmalloc(L+1), T, L+1); \ + cur_node->tag = SYM_NORMAL; \ + } while (0) + +#define APP _APP(yytext, yyleng) + + +/* The second stage lexer. Here we incorporate knowledge of the state + of the parser to tailor the tokens that are returned. */ + +int +yylex(void) +{ + static enum { + ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_BRACKET, ST_BRACE, + ST_EXPRESSION, ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4, + ST_TABLE_5, ST_TABLE_6 + } lexstate = ST_NOTSTARTED; + + static int suppress_type_lookup, dont_want_brace_phrase; + static struct string_list *next_node; + + int token, count = 0; + struct string_list *cur_node; + + if (lexstate == ST_NOTSTARTED) + { + BEGIN(V2_TOKENS); + next_node = xmalloc(sizeof(*next_node)); + next_node->next = NULL; + lexstate = ST_NORMAL; + } + +repeat: + token = yylex1(); + + if (token == 0) + return 0; + else if (token == FILENAME) + { + char *file, *e; + + /* Save the filename and line number for later error messages. */ + + if (cur_filename) + free(cur_filename); + + file = strchr(yytext, '\"')+1; + e = strchr(file, '\"'); + *e = '\0'; + cur_filename = memcpy(xmalloc(e-file+1), file, e-file+1); + cur_line = atoi(yytext+2); + + goto repeat; + } + + switch (lexstate) + { + case ST_NORMAL: + switch (token) + { + case IDENT: + APP; + { + const struct resword *r = is_reserved_word(yytext, yyleng); + if (r) + { + switch (token = r->token) + { + case ATTRIBUTE_KEYW: + lexstate = ST_ATTRIBUTE; + count = 0; + goto repeat; + case ASM_KEYW: + lexstate = ST_ASM; + count = 0; + goto repeat; + + case STRUCT_KEYW: + case UNION_KEYW: + dont_want_brace_phrase = 3; + case ENUM_KEYW: + suppress_type_lookup = 2; + goto fini; + + case EXPORT_SYMBOL_KEYW: + goto fini; + } + } + if (!suppress_type_lookup) + { + struct symbol *sym = find_symbol(yytext, SYM_TYPEDEF); + if (sym && sym->type == SYM_TYPEDEF) + token = TYPE; + } + } + break; + + case '[': + APP; + lexstate = ST_BRACKET; + count = 1; + goto repeat; + + case '{': + APP; + if (dont_want_brace_phrase) + break; + lexstate = ST_BRACE; + count = 1; + goto repeat; + + case '=': case ':': + APP; + lexstate = ST_EXPRESSION; + break; + + case DOTS: + default: + APP; + break; + } + break; + + case ST_ATTRIBUTE: + APP; + switch (token) + { + case '(': + ++count; + goto repeat; + case ')': + if (--count == 0) + { + lexstate = ST_NORMAL; + token = ATTRIBUTE_PHRASE; + break; + } + goto repeat; + default: + goto repeat; + } + break; + + case ST_ASM: + APP; + switch (token) + { + case '(': + ++count; + goto repeat; + case ')': + if (--count == 0) + { + lexstate = ST_NORMAL; + token = ASM_PHRASE; + break; + } + goto repeat; + default: + goto repeat; + } + break; + + case ST_BRACKET: + APP; + switch (token) + { + case '[': + ++count; + goto repeat; + case ']': + if (--count == 0) + { + lexstate = ST_NORMAL; + token = BRACKET_PHRASE; + break; + } + goto repeat; + default: + goto repeat; + } + break; + + case ST_BRACE: + APP; + switch (token) + { + case '{': + ++count; + goto repeat; + case '}': + if (--count == 0) + { + lexstate = ST_NORMAL; + token = BRACE_PHRASE; + break; + } + goto repeat; + default: + goto repeat; + } + break; + + case ST_EXPRESSION: + switch (token) + { + case '(': case '[': case '{': + ++count; + APP; + goto repeat; + case ')': case ']': case '}': + --count; + APP; + goto repeat; + case ',': case ';': + if (count == 0) + { + /* Put back the token we just read so's we can find it again + after registering the expression. */ + unput(token); + + lexstate = ST_NORMAL; + token = EXPRESSION_PHRASE; + break; + } + APP; + goto repeat; + default: + APP; + goto repeat; + } + break; + + case ST_TABLE_1: + goto repeat; + + case ST_TABLE_2: + if (token == IDENT && yyleng == 1 && yytext[0] == 'X') + { + token = EXPORT_SYMBOL_KEYW; + lexstate = ST_TABLE_5; + APP; + break; + } + lexstate = ST_TABLE_6; + /* FALLTHRU */ + + case ST_TABLE_6: + switch (token) + { + case '{': case '[': case '(': + ++count; + break; + case '}': case ']': case ')': + --count; + break; + case ',': + if (count == 0) + lexstate = ST_TABLE_2; + break; + }; + goto repeat; + + case ST_TABLE_3: + goto repeat; + + case ST_TABLE_4: + if (token == ';') + lexstate = ST_NORMAL; + goto repeat; + + case ST_TABLE_5: + switch (token) + { + case ',': + token = ';'; + lexstate = ST_TABLE_2; + APP; + break; + default: + APP; + break; + } + break; + + default: + exit(1); + } +fini: + + if (suppress_type_lookup > 0) + --suppress_type_lookup; + if (dont_want_brace_phrase > 0) + --dont_want_brace_phrase; + + yylval = &next_node->next; + + return token; +} |