2 * This file is part of cparser.
3 * Copyright (C) 2007-2009 Matthias Braun <matze@braunis.de>
5 * This program is free software; you can redistribute it and/or
6 * modify it under the terms of the GNU General Public License
7 * as published by the Free Software Foundation; either version 2
8 * of the License, or (at your option) any later version.
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
29 #include "lang_features.h"
30 #include "adt/array.h"
31 #include "adt/error.h"
34 static symbol_t *token_symbols[T_LAST_TOKEN];
36 const source_position_t builtin_source_position = { "<built-in>", 0, 0, true };
38 static token_kind_t last_id;
40 static symbol_t *intern_register_token(token_kind_t id, const char *string)
42 assert(id < T_LAST_TOKEN);
43 symbol_t *symbol = symbol_table_insert(string);
44 if (token_symbols[id] == NULL)
45 token_symbols[id] = symbol;
49 static void register_token(unsigned mode, token_kind_t id, const char *string)
52 assert(id >= last_id);
56 symbol_t *symbol = intern_register_token(id, string);
61 static void register_pp_token(pp_token_kind_t const id, char const *const string)
63 assert(id < TP_LAST_TOKEN);
64 symbol_t *const symbol = symbol_table_insert(string);
68 void init_tokens(void)
70 memset(token_symbols, 0, T_LAST_TOKEN * sizeof(token_symbols[0]));
72 #define T(mode,x,str,val) register_token(mode, T_##x, str);
73 #define TS(x,str,val) intern_register_token(T_##x, str);
78 #define T(token) register_pp_token(TP_##token, #token);
79 #include "tokens_preprocessor.inc"
83 void exit_tokens(void)
87 void print_token_kind(FILE *f, token_kind_t token_kind)
89 if(token_kind == T_EOF) {
90 fputs("end of file", f);
94 if (token_kind >= lengthof(token_symbols)) {
95 fputs("invalid token", f);
99 const symbol_t *symbol = token_symbols[token_kind];
101 fputs(symbol->string, f);
103 if (token_kind < 256) {
104 fputc(token_kind, f);
107 fputs("unknown token", f);
111 char const *get_string_encoding_prefix(string_encoding_t const enc)
114 case STRING_ENCODING_CHAR: return "";
115 case STRING_ENCODING_WIDE: return "L";
117 panic("invalid string encoding");
120 static void print_stringrep(const string_t *string, FILE *f)
122 for (size_t i = 0; i < string->size; ++i) {
123 fputc(string->begin[i], f);
127 void print_token(FILE *f, const token_t *token)
129 switch(token->kind) {
131 fprintf(f, "identifier '%s'", token->base.symbol->string);
135 fprintf(f, "number '%s'", token->literal.string.begin);
139 case T_STRING_LITERAL: delim = '"'; goto print_string;
140 case T_CHARACTER_CONSTANT: delim = '\''; goto print_string;
142 print_token_kind(f, (token_kind_t)token->kind);
143 fprintf(f, " %s%c", get_string_encoding_prefix(token->literal.string.encoding), delim);
144 print_stringrep(&token->literal.string, f);
149 if (token->base.symbol) {
150 fprintf(f, "'%s'", token->base.symbol->string);
153 print_token_kind(f, (token_kind_t)token->kind);
160 bool tokens_would_paste(token_kind_t token1, token_kind_t token2)
162 char const c = token2 < 256 ? (char)token2 : token_symbols[token2]->string[0];
165 case '>': return c == '>' || c == '=';
166 case '<': return c == '<' || c == '=' || c == '%' || c == ':';
167 case '+': return c == '+' || c == '=';
168 case '-': return c == '-' || c == '>';
169 case '/': return c == '/' || c == '=' || c == '*';
170 case '%': return c == ':' || c == '=' || c == '>';
171 case '&': return c == '&' || c == '=';
172 case '|': return c == '|' || c == '=';
173 case ':': return c == ':' || c == '>';
174 case '*': return c == '*' || c == '=';
175 case '.': return c == '.' || c == '%' || token2 == T_NUMBER;
176 case '#': return c == '#' || c == '%';
177 case T_GREATERGREATER: return c == '=';
178 case T_LESSLESS: return c == '=';
179 case '^': return c == '=';
180 case '!': return c == '=';
183 return token2 == T_CHARACTER_CONSTANT ||
184 token2 == T_IDENTIFIER ||
185 token2 == T_NUMBER ||
186 token2 == T_STRING_LITERAL; /* L */
189 return token2 == T_IDENTIFIER || token2 == T_NUMBER ||
190 token2 == '.' || token2 == '+' || token2 == '-';