X-Git-Url: http://nsz.repo.hu/git/?a=blobdiff_plain;ds=sidebyside;f=token.c;h=a0bcb940ed734c04d970b00b0aaaa45e9ee41d47;hb=7473d9545525216a1276296dbc1759e07972cf96;hp=c9b0de859dfae002c8b8d6a37f16139866cd362c;hpb=1b57101d07318feaae6f83b5ebc882aaaaeee2ae;p=cparser diff --git a/token.c b/token.c index c9b0de8..a0bcb94 100644 --- a/token.c +++ b/token.c @@ -1,21 +1,6 @@ /* * 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. + * Copyright (C) 2012 Matthias Braun */ #include @@ -23,17 +8,16 @@ #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" +#include "symbol_table.h" -static symbol_t *token_symbols[T_LAST_TOKEN]; -static symbol_t *pp_token_symbols[TP_LAST_TOKEN]; +symbol_t *token_symbols[T_LAST_TOKEN]; -const source_position_t builtin_source_position = { "", 0, 0, true }; +const position_t builtin_position = { "", 0, 0, true }; static token_kind_t last_id; @@ -46,15 +30,6 @@ static symbol_t *intern_register_token(token_kind_t id, const char *string) return symbol; } -static symbol_t *intern_register_pp_token(preprocessor_token_kind_t id, const char *string) -{ - assert(id < TP_LAST_TOKEN); - symbol_t *symbol = symbol_table_insert(string); - if (pp_token_symbols[id] == NULL) - pp_token_symbols[id] = symbol; - return symbol; -} - static void register_token(unsigned mode, token_kind_t id, const char *string) { if (id > 255) { @@ -67,31 +42,28 @@ static void register_token(unsigned mode, token_kind_t id, const char *string) } } -static void register_pp_token(unsigned mode, preprocessor_token_kind_t id, - const char *string) +static void register_pp_token(pp_token_kind_t const id, char const *const string) { - if (! (c_mode & mode)) - return; - - symbol_t *symbol = intern_register_pp_token(id, string); + assert(id < TP_LAST_TOKEN); + symbol_t *const symbol = symbol_table_insert(string); symbol->pp_ID = id; } void init_tokens(void) { + static bool tokens_initialized = false; + if (tokens_initialized) + return; + tokens_initialized = true; + memset(token_symbols, 0, T_LAST_TOKEN * sizeof(token_symbols[0])); - memset(pp_token_symbols, 0, TP_LAST_TOKEN * sizeof(pp_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); +#define T(mode,x,str,val) register_token(mode, x, str); #include "tokens.inc" -#undef TS #undef T -#define T(mode,x,str,val) register_pp_token(mode, TP_##x, str); -#define TS(x,str,val) intern_register_pp_token(TP_##x, str); +#define T(token) register_pp_token(TP_##token, #token); #include "tokens_preprocessor.inc" -#undef TS #undef T } @@ -101,122 +73,60 @@ void exit_tokens(void) void print_token_kind(FILE *f, token_kind_t token_kind) { - if(token_kind == T_EOF) { - fputs("end of file", f); - return; - } - if (token_kind >= lengthof(token_symbols)) { fputs("invalid token", f); return; } - const symbol_t *symbol = token_symbols[token_kind]; - if(symbol != NULL) { - fputs(symbol->string, f); - } else { - if (token_kind < 256) { - fputc(token_kind, f); - return; - } - fputs("unknown token", f); - } + fputs(token_symbols[token_kind]->string, f); } -static void print_stringrep(const string_t *string, FILE *f) +char const *get_string_encoding_prefix(string_encoding_t const enc) { - for (size_t i = 0; i < string->size; ++i) { - fputc(string->begin[i], f); + switch (enc) { + case STRING_ENCODING_CHAR: return ""; + case STRING_ENCODING_CHAR16: return "u"; + case STRING_ENCODING_CHAR32: return "U"; + case STRING_ENCODING_UTF8: return "u8"; + case STRING_ENCODING_WIDE: return "L"; } + panic("invalid string encoding"); } void print_token(FILE *f, const token_t *token) { - switch(token->kind) { + char delim = '\''; + char const *enc = ""; + char const *val; + switch (token->kind) { case T_IDENTIFIER: - fprintf(f, "identifier '%s'", token->base.symbol->string); - break; - case T_INTEGER: - case T_FLOATINGPOINT: - print_token_kind(f, (token_kind_t)token->kind); - fputs(" '", f); - print_stringrep(&token->number.number, f); - if (token->number.suffix.size > 0) - print_stringrep(&token->number.suffix, f); - fputc('\'', f); + case T_MACRO_PARAMETER: + case T_UNKNOWN_CHAR: + val = token->base.symbol->string; break; - case T_WIDE_STRING_LITERAL: + case T_STRING_LITERAL: - print_token_kind(f, (token_kind_t)token->kind); - fprintf(f, " \"%s\"", token->string.string.begin); - break; + delim = '"'; + /* FALLTHROUGH */ case T_CHARACTER_CONSTANT: - case T_WIDE_CHARACTER_CONSTANT: - print_token_kind(f, (token_kind_t)token->kind); - fputs(" \'", f); - print_stringrep(&token->string.string, f); - fputs("'", f); - break; - - default: - 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); - } + enc = get_string_encoding_prefix(token->literal.string.encoding); + /* FALLTHROUGH */ + case T_NUMBER: + val = token->literal.string.begin; break; - } -} -void print_pp_token_kind(FILE *f, int token_kind) -{ - if (token_kind == TP_EOF) { - fputs("end of file", f); + default: { + char const *kind = (token->base.symbol ? token->base.symbol : token_symbols[token->kind])->string; + fprintf(f, "'%s'", kind); return; } - - int token_symbols_len = TP_LAST_TOKEN; - if (token_kind < 0 || token_kind >= token_symbols_len) { - fputs("invalid token", f); - return; - } - - const symbol_t *symbol = pp_token_symbols[token_kind]; - if (symbol != NULL) { - fputs(symbol->string, f); - } else { - if(token_kind >= 0 && token_kind < 256) { - fputc(token_kind, f); - return; - } - fputs("unknown token", f); } + fprintf(f, "%s %s%c%s%c", token_symbols[token->kind]->string, enc, delim, val, delim); } -void print_pp_token(FILE *f, const token_t *token) +bool tokens_would_paste(token_kind_t token1, token_kind_t token2) { - switch((preprocessor_token_kind_t) token->kind) { - case TP_IDENTIFIER: - fprintf(f, "identifier '%s'", token->base.symbol->string); - break; - case TP_NUMBER: - fprintf(f, "number '%s'", token->number.number.begin); - break; - case TP_STRING_LITERAL: - fprintf(f, "string \"%s\"", token->string.string.begin); - break; - default: - print_pp_token_kind(f, (preprocessor_token_kind_t) token->kind); - break; - } -} - -bool tokens_would_paste(preprocessor_token_kind_t token1, - preprocessor_token_kind_t token2) -{ - char c = token2 < 256 ? (char) token2 : pp_token_symbols[token2]->string[0]; + char const c = token_symbols[token2]->string[0]; switch (token1) { case '>': return c == '>' || c == '='; @@ -229,21 +139,23 @@ bool tokens_would_paste(preprocessor_token_kind_t token1, case '|': return c == '|' || c == '='; case ':': return c == ':' || c == '>'; case '*': return c == '*' || c == '='; - case '.': return c == '.' || c == '%' || token2 == TP_NUMBER; + case '.': return c == '.' || c == '%' || token2 == T_NUMBER; case '#': return c == '#' || c == '%'; - case TP_GREATERGREATER: return c == '='; - case TP_LESSLESS: return c == '='; - case '^': return c == '='; - case '!': return c == '='; - case TP_IDENTIFIER: - return token2 == TP_IDENTIFIER || token2 == TP_NUMBER || - token2 == TP_CHARACTER_CONSTANT || - token2 == TP_WIDE_CHARACTER_CONSTANT || - token2 == TP_WIDE_STRING_LITERAL || - token2 == TP_STRING_LITERAL; /* L */ - case TP_NUMBER: - return token2 == TP_NUMBER || token2 == TP_IDENTIFIER || + 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; }