X-Git-Url: http://nsz.repo.hu/git/?a=blobdiff_plain;f=token.c;h=e7c7abc8eb9550e77d7d75edf79827506a1224d0;hb=3c9d1105cdebe8a419b5e8a2b53e52ef4fa386a0;hp=15cc4bbf668d29efa005d77f324ca1addac161cf;hpb=c1bde668c4e8022590b1099b60d97caa16d3e760;p=cparser diff --git a/token.c b/token.c index 15cc4bb..e7c7abc 100644 --- a/token.c +++ b/token.c @@ -1,44 +1,82 @@ +/* + * This file is part of cparser. + * Copyright (C) 2007-2009 Matthias Braun + * + * 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 #include "token_t.h" +#include "symbol_t.h" #include #include #include "symbol.h" +#include "lang_features.h" #include "adt/array.h" +#include "adt/error.h" +#include "adt/util.h" static symbol_t *token_symbols[T_LAST_TOKEN]; -void init_tokens(void) +const source_position_t builtin_source_position = { "", 0, 0, true }; + +static token_kind_t last_id; + +static symbol_t *intern_register_token(token_kind_t id, const char *string) { - symbol_t *symbol; + assert(id < T_LAST_TOKEN); + symbol_t *symbol = symbol_table_insert(string); + if (token_symbols[id] == NULL) + token_symbols[id] = symbol; + return symbol; +} - memset(token_symbols, 0, T_LAST_TOKEN * sizeof(token_symbols[0])); +static void register_token(unsigned mode, token_kind_t id, const char *string) +{ + if (id > 255) { + assert(id >= last_id); + last_id = id; + } + if (c_mode & mode) { + symbol_t *symbol = intern_register_token(id, string); + symbol->ID = id; + } +} -#define T(x,str,val) \ - assert(T_##x >= 0 && T_##x < T_LAST_TOKEN); \ - symbol = symbol_table_insert(str); \ - symbol->ID = T_##x; \ - token_symbols[T_##x] = symbol; +static void register_pp_token(pp_token_kind_t const id, char const *const string) +{ + assert(id < TP_LAST_TOKEN); + symbol_t *const symbol = symbol_table_insert(string); + symbol->pp_ID = id; +} -#define TS(x,str,val) \ - assert(T_##x >= 0 && T_##x < T_LAST_TOKEN); \ - symbol = symbol_table_insert(str); \ - token_symbols[T_##x] = symbol; +void init_tokens(void) +{ + memset(token_symbols, 0, T_LAST_TOKEN * sizeof(token_symbols[0])); +#define T(mode,x,str,val) register_token(mode, T_##x, str); +#define TS(x,str,val) intern_register_token(T_##x, str); #include "tokens.inc" - #undef TS #undef T -#define T(x,str,val) \ - assert(TP_##x >= 0 && TP_##x < TP_LAST_TOKEN); \ - symbol = symbol_table_insert(str); \ - symbol->pp_ID = TP_##x; - +#define T(token) register_pp_token(TP_##token, #token); #include "tokens_preprocessor.inc" - #undef T } @@ -46,52 +84,105 @@ void exit_tokens(void) { } -void print_token_type(FILE *f, token_type_t token_type) +void print_token_kind(FILE *f, token_kind_t token_kind) { - if(token_type == T_EOF) { + if(token_kind == T_EOF) { fputs("end of file", f); return; } - if(token_type == T_ERROR) { - fputs("error", f); - return; - } - int token_symbols_len = T_LAST_TOKEN; - if(token_type < 0 || token_type >= token_symbols_len) { + if (token_kind >= lengthof(token_symbols)) { fputs("invalid token", f); return; } - const symbol_t *symbol = token_symbols[token_type]; - if(symbol != NULL) { - fprintf(f, "'%s'", symbol->string); - } else { - if(token_type >= 0 && token_type < 256) { - fprintf(f, "'%c'", token_type); - return; - } - fputs("unknown token", f); + fputs(token_symbols[token_kind]->string, f); +} + +char const *get_string_encoding_prefix(string_encoding_t const enc) +{ + switch (enc) { + case STRING_ENCODING_CHAR: return ""; + case STRING_ENCODING_WIDE: return "L"; + } + panic("invalid string encoding"); +} + +static void print_stringrep(const string_t *string, FILE *f) +{ + for (size_t i = 0; i < string->size; ++i) { + fputc(string->begin[i], f); } } void print_token(FILE *f, const token_t *token) { - switch(token->type) { + switch(token->kind) { case T_IDENTIFIER: - fprintf(f, "symbol '%s'", token->v.symbol->string); - break; - case T_INTEGER: - fprintf(f, "integer number %d", token->v.intvalue); + case T_UNKNOWN_CHAR: + print_token_kind(f, (token_kind_t)token->kind); + fprintf(f, " '%s'", token->base.symbol->string); break; - case T_FLOATINGPOINT: - fprintf(f, "floatingpointer number %f", token->v.floatvalue); + + case T_NUMBER: + fprintf(f, "number '%s'", token->literal.string.begin); break; - case T_STRING_LITERAL: - fprintf(f, "string '%s'", token->v.string); + + char delim; + case T_STRING_LITERAL: delim = '"'; goto print_string; + case T_CHARACTER_CONSTANT: delim = '\''; goto print_string; +print_string: + print_token_kind(f, (token_kind_t)token->kind); + fprintf(f, " %s%c", get_string_encoding_prefix(token->literal.string.encoding), delim); + print_stringrep(&token->literal.string, f); + fputc(delim, f); break; + default: - print_token_type(f, (token_type_t)token->type); + if (token->base.symbol) { + fprintf(f, "'%s'", token->base.symbol->string); + } else { + fputc('\'', f); + print_token_kind(f, (token_kind_t)token->kind); + fputc('\'', f); + } break; } } + +bool tokens_would_paste(token_kind_t token1, token_kind_t token2) +{ + char const c = token_symbols[token2]->string[0]; + + switch (token1) { + case '>': return c == '>' || c == '='; + case '<': return c == '<' || c == '=' || c == '%' || c == ':'; + case '+': return c == '+' || c == '='; + case '-': return c == '-' || c == '>'; + case '/': return c == '/' || c == '=' || c == '*'; + case '%': return c == ':' || c == '=' || c == '>'; + case '&': return c == '&' || c == '='; + case '|': return c == '|' || c == '='; + case ':': return c == ':' || c == '>'; + case '*': return c == '*' || c == '='; + case '.': return c == '.' || c == '%' || token2 == T_NUMBER; + case '#': return c == '#' || c == '%'; + case T_GREATERGREATER: return c == '='; + case T_LESSLESS: return c == '='; + case '^': return c == '='; + case '!': return c == '='; + + case T_IDENTIFIER: + return token2 == T_CHARACTER_CONSTANT || + token2 == T_IDENTIFIER || + token2 == T_NUMBER || + token2 == T_STRING_LITERAL; /* L */ + + case T_NUMBER: + return token2 == T_IDENTIFIER || token2 == T_NUMBER || + token2 == '.' || token2 == '+' || token2 == '-'; + + default: + return false; + } +}