X-Git-Url: http://git.sourceforge.jp/view?a=blobdiff_plain;f=gcc%2Fc-lex.c;h=53a3b06a63b0ff613a491e39e37561f7daf31db2;hb=1be3b8e5752db5a415c4690d7331643db4418901;hp=052c3f691221dfbe2e2734bc20d3da73be9d0f02;hpb=8b6866afc342340bd8d8674caf6d773afe0de5f1;p=pf3gnuchains%2Fgcc-fork.git diff --git a/gcc/c-lex.c b/gcc/c-lex.c index 052c3f69122..53a3b06a63b 100644 --- a/gcc/c-lex.c +++ b/gcc/c-lex.c @@ -1,13 +1,13 @@ /* Mainly the interface between cpplib and the C front ends. Copyright (C) 1987, 1988, 1989, 1992, 1994, 1995, 1996, 1997 - 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005 + 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2007, 2008 Free Software Foundation, Inc. This file is part of GCC. GCC 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, or (at your option) any later +Software Foundation; either version 3, or (at your option) any later version. GCC is distributed in the hope that it will be useful, but WITHOUT ANY @@ -16,9 +16,8 @@ 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 GCC; see the file COPYING. If not, write to the Free -Software Foundation, 59 Temple Place - Suite 330, Boston, MA -02111-1307, USA. */ +along with GCC; see the file COPYING3. If not see +. */ #include "config.h" #include "system.h" @@ -26,7 +25,7 @@ Software Foundation, 59 Temple Place - Suite 330, Boston, MA #include "tm.h" #include "real.h" -#include "rtl.h" +#include "fixed-value.h" #include "tree.h" #include "input.h" #include "output.h" @@ -38,9 +37,9 @@ Software Foundation, 59 Temple Place - Suite 330, Boston, MA #include "c-pragma.h" #include "toplev.h" #include "intl.h" -#include "tm_p.h" #include "splay-tree.h" #include "debug.h" +#include "target.h" /* We may keep statistics about how long which files took to compile. */ static int header_time, body_time; @@ -49,23 +48,14 @@ static splay_tree file_info_tree; int pending_lang_change; /* If we need to switch languages - C++ only */ int c_header_level; /* depth in C headers - C++ only */ -/* If we need to translate characters received. This is tri-state: - 0 means use only the untranslated string; 1 means use only - the translated string; -1 means chain the translated string - to the untranslated one. */ -int c_lex_string_translate = 1; - -/* True if strings should be passed to the caller of c_lex completely - unmolested (no concatenation, no translation). */ -bool c_lex_return_raw_strings = false; - static tree interpret_integer (const cpp_token *, unsigned int); static tree interpret_float (const cpp_token *, unsigned int); +static tree interpret_fixed (const cpp_token *, unsigned int); static enum integer_type_kind narrowest_unsigned_type (unsigned HOST_WIDE_INT, unsigned HOST_WIDE_INT, unsigned int); static enum integer_type_kind narrowest_signed_type (unsigned HOST_WIDE_INT, unsigned HOST_WIDE_INT, unsigned int); -static enum cpp_ttype lex_string (const cpp_token *, tree *, bool); +static enum cpp_ttype lex_string (const cpp_token *, tree *, bool, bool); static tree lex_charconst (const cpp_token *); static void update_header_times (const char *); static int dump_one_header (splay_tree_node, void *); @@ -102,7 +92,7 @@ init_c_lex (void) /* Set the debug callbacks if we can use them. */ if (debug_info_level == DINFO_LEVEL_VERBOSE && (write_symbols == DWARF2_DEBUG - || write_symbols == VMS_AND_DWARF2_DEBUG)) + || write_symbols == VMS_AND_DWARF2_DEBUG)) { cb->define = cb_define; cb->undef = cb_undef; @@ -183,10 +173,10 @@ cb_ident (cpp_reader * ARG_UNUSED (pfile), { /* Convert escapes in the string. */ cpp_string cstr = { 0, 0 }; - if (cpp_interpret_string (pfile, str, 1, &cstr, false)) + if (cpp_interpret_string (pfile, str, 1, &cstr, CPP_STRING)) { ASM_OUTPUT_IDENT (asm_out_file, (const char *) cstr.text); - free ((void *) cstr.text); + free (CONST_CAST (unsigned char *, cstr.text)); } } #endif @@ -199,15 +189,7 @@ cb_line_change (cpp_reader * ARG_UNUSED (pfile), const cpp_token *token, int parsing_args) { if (token->type != CPP_EOF && !parsing_args) -#ifdef USE_MAPPED_LOCATION input_location = token->src_loc; -#else - { - source_location loc = token->src_loc; - const struct line_map *map = linemap_lookup (&line_table, loc); - input_line = SOURCE_LINE (map, loc); - } -#endif } void @@ -222,18 +204,13 @@ fe_file_change (const struct line_map *new_map) we already did in compile_file. */ if (!MAIN_FILE_P (new_map)) { -#ifdef USE_MAPPED_LOCATION - int included_at = LAST_SOURCE_LINE_LOCATION (new_map - 1); + unsigned int included_at = LAST_SOURCE_LINE_LOCATION (new_map - 1); + int line = 0; + if (included_at > BUILTINS_LOCATION) + line = SOURCE_LINE (new_map - 1, included_at); - input_location = included_at; - push_srcloc (new_map->start_location); -#else - int included_at = LAST_SOURCE_LINE (new_map - 1); - - input_line = included_at; - push_srcloc (new_map->to_file, 1); -#endif - (*debug_hooks->start_source_file) (included_at, new_map->to_file); + input_location = new_map->start_location; + (*debug_hooks->start_source_file) (line, new_map->to_file); #ifndef NO_IMPLICIT_EXTERN_C if (c_header_level) ++c_header_level; @@ -255,19 +232,13 @@ fe_file_change (const struct line_map *new_map) --pending_lang_change; } #endif - pop_srcloc (); + input_location = new_map->start_location; (*debug_hooks->end_source_file) (new_map->to_line); } update_header_times (new_map->to_file); - in_system_header = new_map->sysp != 0; -#ifdef USE_MAPPED_LOCATION input_location = new_map->start_location; -#else - input_filename = new_map->to_file; - input_line = new_map->to_line; -#endif } static void @@ -280,14 +251,7 @@ cb_def_pragma (cpp_reader *pfile, source_location loc) { const unsigned char *space, *name; const cpp_token *s; -#ifndef USE_MAPPED_LOCATION - location_t fe_loc; - const struct line_map *map = linemap_lookup (&line_table, loc); - fe_loc.file = map->to_file; - fe_loc.line = SOURCE_LINE (map, loc); -#else location_t fe_loc = loc; -#endif space = name = (const unsigned char *) ""; s = cpp_get_token (pfile); @@ -299,7 +263,8 @@ cb_def_pragma (cpp_reader *pfile, source_location loc) name = cpp_token_as_text (pfile, s); } - warning (0, "%Hignoring #pragma %s %s", &fe_loc, space, name); + warning_at (fe_loc, OPT_Wunknown_pragmas, "ignoring #pragma %s %s", + space, name); } } @@ -307,7 +272,7 @@ cb_def_pragma (cpp_reader *pfile, source_location loc) static void cb_define (cpp_reader *pfile, source_location loc, cpp_hashnode *node) { - const struct line_map *map = linemap_lookup (&line_table, loc); + const struct line_map *map = linemap_lookup (line_table, loc); (*debug_hooks->define) (SOURCE_LINE (map, loc), (const char *) cpp_macro_definition (pfile, node)); } @@ -317,7 +282,7 @@ static void cb_undef (cpp_reader * ARG_UNUSED (pfile), source_location loc, cpp_hashnode *node) { - const struct line_map *map = linemap_lookup (&line_table, loc); + const struct line_map *map = linemap_lookup (line_table, loc); (*debug_hooks->undef) (SOURCE_LINE (map, loc), (const char *) NODE_NAME (node)); } @@ -327,30 +292,27 @@ cb_undef (cpp_reader * ARG_UNUSED (pfile), source_location loc, non-NULL. */ enum cpp_ttype -c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) +c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags, + int lex_flags) { static bool no_more_pch; const cpp_token *tok; enum cpp_ttype type; + unsigned char add_flags = 0; timevar_push (TV_CPP); retry: - tok = cpp_get_token (parse_in); + tok = cpp_get_token_with_location (parse_in, loc); type = tok->type; - + retry_after_at: -#ifdef USE_MAPPED_LOCATION - *loc = tok->src_loc; -#else - *loc = input_location; -#endif switch (type) { case CPP_PADDING: goto retry; - + case CPP_NAME: - *value = HT_IDENT_TO_GCC_IDENT (HT_NODE (tok->val.node)); + *value = HT_IDENT_TO_GCC_IDENT (HT_NODE (tok->val.node.node)); break; case CPP_NUMBER: @@ -362,9 +324,14 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) case CPP_N_INVALID: /* cpplib has issued an error. */ *value = error_mark_node; + errorcount++; break; case CPP_N_INTEGER: + /* C++ uses '0' to mark virtual functions as pure. + Set PURE_ZERO to pass this information to the C++ parser. */ + if (tok->val.str.len == 1 && *tok->val.str.text == '0') + add_flags = PURE_ZERO; *value = interpret_integer (tok, flags); break; @@ -382,23 +349,27 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) /* An @ may give the next token special significance in Objective-C. */ if (c_dialect_objc ()) { - location_t atloc = input_location; - + location_t atloc = *loc; + location_t newloc; + retry_at: - tok = cpp_get_token (parse_in); + tok = cpp_get_token_with_location (parse_in, &newloc); type = tok->type; switch (type) { case CPP_PADDING: goto retry_at; - + case CPP_STRING: case CPP_WSTRING: - type = lex_string (tok, value, true); + case CPP_STRING16: + case CPP_STRING32: + case CPP_UTF8STRING: + type = lex_string (tok, value, true, true); break; case CPP_NAME: - *value = HT_IDENT_TO_GCC_IDENT (HT_NODE (tok->val.node)); + *value = HT_IDENT_TO_GCC_IDENT (HT_NODE (tok->val.node.node)); if (objc_is_reserved_word (*value)) { type = CPP_AT_NAME; @@ -408,7 +379,8 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) default: /* ... or not. */ - error ("%Hstray %<@%> in program", &atloc); + error_at (atloc, "stray %<@%> in program"); + *loc = newloc; goto retry_after_at; } break; @@ -418,13 +390,13 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) case CPP_HASH: case CPP_PASTE: { - unsigned char name[4]; - + unsigned char name[8]; + *cpp_spell_token (parse_in, tok, name, true) = 0; - + error ("stray %qs in program", name); } - + goto retry; case CPP_OTHER: @@ -442,21 +414,27 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) case CPP_CHAR: case CPP_WCHAR: + case CPP_CHAR16: + case CPP_CHAR32: *value = lex_charconst (tok); break; case CPP_STRING: case CPP_WSTRING: - if (!c_lex_return_raw_strings) + case CPP_STRING16: + case CPP_STRING32: + case CPP_UTF8STRING: + if ((lex_flags & C_LEX_STRING_NO_JOIN) == 0) { - type = lex_string (tok, value, false); + type = lex_string (tok, value, false, + (lex_flags & C_LEX_STRING_NO_TRANSLATE) == 0); break; } - - /* FALLTHROUGH */ + *value = build_string (tok->val.str.len, (const char *) tok->val.str.text); + break; case CPP_PRAGMA: - *value = build_string (tok->val.str.len, (char *) tok->val.str.text); + *value = build_int_cst (NULL, tok->val.pragma); break; /* These tokens should not be visible outside cpplib. */ @@ -471,24 +449,17 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags) } if (cpp_flags) - *cpp_flags = tok->flags; + *cpp_flags = tok->flags | add_flags; if (!no_more_pch) { no_more_pch = true; c_common_no_more_pch (); } - + timevar_pop (TV_CPP); - - return type; -} -enum cpp_ttype -c_lex (tree *value) -{ - location_t loc; - return c_lex_with_flags (value, &loc, NULL); + return type; } /* Returns the narrowest C-visible unsigned type, starting with the @@ -500,7 +471,7 @@ narrowest_unsigned_type (unsigned HOST_WIDE_INT low, unsigned HOST_WIDE_INT high, unsigned int flags) { - enum integer_type_kind itk; + int itk; if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) itk = itk_unsigned_int; @@ -516,7 +487,7 @@ narrowest_unsigned_type (unsigned HOST_WIDE_INT low, if ((unsigned HOST_WIDE_INT) TREE_INT_CST_HIGH (upper) > high || ((unsigned HOST_WIDE_INT) TREE_INT_CST_HIGH (upper) == high && TREE_INT_CST_LOW (upper) >= low)) - return itk; + return (enum integer_type_kind) itk; } return itk_none; @@ -527,7 +498,7 @@ static enum integer_type_kind narrowest_signed_type (unsigned HOST_WIDE_INT low, unsigned HOST_WIDE_INT high, unsigned int flags) { - enum integer_type_kind itk; + int itk; if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) itk = itk_int; @@ -540,11 +511,11 @@ narrowest_signed_type (unsigned HOST_WIDE_INT low, for (; itk < itk_none; itk += 2 /* skip signed types */) { tree upper = TYPE_MAX_VALUE (integer_types[itk]); - + if ((unsigned HOST_WIDE_INT) TREE_INT_CST_HIGH (upper) > high || ((unsigned HOST_WIDE_INT) TREE_INT_CST_HIGH (upper) == high && TREE_INT_CST_LOW (upper) >= low)) - return itk; + return (enum integer_type_kind) itk; } return itk_none; @@ -612,13 +583,18 @@ interpret_integer (const cpp_token *token, unsigned int flags) ? widest_unsigned_literal_type_node : widest_integer_literal_type_node); else - type = integer_types[itk]; - - if (itk > itk_unsigned_long - && (flags & CPP_N_WIDTH) != CPP_N_LARGE - && !in_system_header && !flag_isoc99) - pedwarn ("integer constant is too large for %qs type", - (flags & CPP_N_UNSIGNED) ? "unsigned long" : "long"); + { + type = integer_types[itk]; + if (itk > itk_unsigned_long + && (flags & CPP_N_WIDTH) != CPP_N_LARGE) + emit_diagnostic + ((c_dialect_cxx () ? cxx_dialect == cxx98 : !flag_isoc99) + ? DK_PEDWARN : DK_WARNING, + input_location, OPT_Wlong_long, + (flags & CPP_N_UNSIGNED) + ? "integer constant is too large for % type" + : "integer constant is too large for % type"); + } value = build_int_cst_wide (type, integer.low, integer.high); @@ -635,70 +611,274 @@ static tree interpret_float (const cpp_token *token, unsigned int flags) { tree type; + tree const_type; tree value; REAL_VALUE_TYPE real; + REAL_VALUE_TYPE real_trunc; char *copy; size_t copylen; - const char *type_name; - /* FIXME: make %T work in error/warning, then we don't need type_name. */ - if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) - { - type = long_double_type_node; - type_name = "long double"; - } - else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL - || flag_single_precision_constant) + /* Default (no suffix) depends on whether the FLOAT_CONST_DECIMAL64 + pragma has been used and is either double or _Decimal64. Types + that are not allowed with decimal float default to double. */ + if (flags & CPP_N_DEFAULT) { - type = float_type_node; - type_name = "float"; + flags ^= CPP_N_DEFAULT; + flags |= CPP_N_MEDIUM; + + if (((flags & CPP_N_HEX) == 0) && ((flags & CPP_N_IMAGINARY) == 0)) + { + warning (OPT_Wunsuffixed_float_constants, + "unsuffixed float constant"); + if (float_const_decimal64_p ()) + flags |= CPP_N_DFLOAT; + } } + + /* Decode _Fract and _Accum. */ + if (flags & CPP_N_FRACT || flags & CPP_N_ACCUM) + return interpret_fixed (token, flags); + + /* Decode type based on width and properties. */ + if (flags & CPP_N_DFLOAT) + if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + type = dfloat128_type_node; + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) + type = dfloat32_type_node; + else + type = dfloat64_type_node; else - { + if (flags & CPP_N_WIDTH_MD) + { + char suffix; + enum machine_mode mode; + + if ((flags & CPP_N_WIDTH_MD) == CPP_N_MD_W) + suffix = 'w'; + else + suffix = 'q'; + + mode = targetm.c.mode_for_suffix (suffix); + if (mode == VOIDmode) + { + error ("unsupported non-standard suffix on floating constant"); + errorcount++; + + return error_mark_node; + } + else + pedwarn (input_location, OPT_pedantic, "non-standard suffix on floating constant"); + + type = c_common_type_for_mode (mode, 0); + gcc_assert (type); + } + else if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + type = long_double_type_node; + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL + || flag_single_precision_constant) + type = float_type_node; + else type = double_type_node; - type_name = "double"; - } + + const_type = excess_precision_type (type); + if (!const_type) + const_type = type; /* Copy the constant to a nul-terminated buffer. If the constant has any suffixes, cut them off; REAL_VALUE_ATOF/ REAL_VALUE_HTOF can't handle them. */ copylen = token->val.str.len; - if ((flags & CPP_N_WIDTH) != CPP_N_MEDIUM) - /* Must be an F or L suffix. */ - copylen--; - if (flags & CPP_N_IMAGINARY) - /* I or J suffix. */ - copylen--; + if (flags & CPP_N_DFLOAT) + copylen -= 2; + else + { + if ((flags & CPP_N_WIDTH) != CPP_N_MEDIUM) + /* Must be an F or L or machine defined suffix. */ + copylen--; + if (flags & CPP_N_IMAGINARY) + /* I or J suffix. */ + copylen--; + } copy = (char *) alloca (copylen + 1); memcpy (copy, token->val.str.text, copylen); copy[copylen] = '\0'; - real_from_string (&real, copy); - real_convert (&real, TYPE_MODE (type), &real); + real_from_string3 (&real, copy, TYPE_MODE (const_type)); + if (const_type != type) + /* Diagnosing if the result of converting the value with excess + precision to the semantic type would overflow (with associated + double rounding) is more appropriate than diagnosing if the + result of converting the string directly to the semantic type + would overflow. */ + real_convert (&real_trunc, TYPE_MODE (type), &real); /* Both C and C++ require a diagnostic for a floating constant outside the range of representable values of its type. Since we - have __builtin_inf* to produce an infinity, it might now be - appropriate for this to be a mandatory pedwarn rather than - conditioned on -pedantic. */ - if (REAL_VALUE_ISINF (real) && pedantic) - pedwarn ("floating constant exceeds range of %<%s%>", type_name); + have __builtin_inf* to produce an infinity, this is now a + mandatory pedwarn if the target does not support infinities. */ + if (REAL_VALUE_ISINF (real) + || (const_type != type && REAL_VALUE_ISINF (real_trunc))) + { + if (!MODE_HAS_INFINITIES (TYPE_MODE (type))) + pedwarn (input_location, 0, "floating constant exceeds range of %qT", type); + else + warning (OPT_Woverflow, "floating constant exceeds range of %qT", type); + } + /* We also give a warning if the value underflows. */ + else if (REAL_VALUES_EQUAL (real, dconst0) + || (const_type != type && REAL_VALUES_EQUAL (real_trunc, dconst0))) + { + REAL_VALUE_TYPE realvoidmode; + int overflow = real_from_string (&realvoidmode, copy); + if (overflow < 0 || !REAL_VALUES_EQUAL (realvoidmode, dconst0)) + warning (OPT_Woverflow, "floating constant truncated to zero"); + } /* Create a node with determined type and value. */ - value = build_real (type, real); + value = build_real (const_type, real); if (flags & CPP_N_IMAGINARY) - value = build_complex (NULL_TREE, convert (type, integer_zero_node), value); + value = build_complex (NULL_TREE, convert (const_type, integer_zero_node), + value); + + if (type != const_type) + value = build1 (EXCESS_PRECISION_EXPR, type, value); return value; } -/* Convert a series of STRING and/or WSTRING tokens into a tree, - performing string constant concatenation. TOK is the first of - these. VALP is the location to write the string into. OBJC_STRING - indicates whether an '@' token preceded the incoming token. +/* Interpret TOKEN, a fixed-point number with FLAGS as classified + by cpplib. */ + +static tree +interpret_fixed (const cpp_token *token, unsigned int flags) +{ + tree type; + tree value; + FIXED_VALUE_TYPE fixed; + char *copy; + size_t copylen; + + copylen = token->val.str.len; + + if (flags & CPP_N_FRACT) /* _Fract. */ + { + if (flags & CPP_N_UNSIGNED) /* Unsigned _Fract. */ + { + if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + { + type = unsigned_long_long_fract_type_node; + copylen -= 4; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_MEDIUM) + { + type = unsigned_long_fract_type_node; + copylen -= 3; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) + { + type = unsigned_short_fract_type_node; + copylen -= 3; + } + else + { + type = unsigned_fract_type_node; + copylen -= 2; + } + } + else /* Signed _Fract. */ + { + if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + { + type = long_long_fract_type_node; + copylen -= 3; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_MEDIUM) + { + type = long_fract_type_node; + copylen -= 2; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) + { + type = short_fract_type_node; + copylen -= 2; + } + else + { + type = fract_type_node; + copylen --; + } + } + } + else /* _Accum. */ + { + if (flags & CPP_N_UNSIGNED) /* Unsigned _Accum. */ + { + if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + { + type = unsigned_long_long_accum_type_node; + copylen -= 4; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_MEDIUM) + { + type = unsigned_long_accum_type_node; + copylen -= 3; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) + { + type = unsigned_short_accum_type_node; + copylen -= 3; + } + else + { + type = unsigned_accum_type_node; + copylen -= 2; + } + } + else /* Signed _Accum. */ + { + if ((flags & CPP_N_WIDTH) == CPP_N_LARGE) + { + type = long_long_accum_type_node; + copylen -= 3; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_MEDIUM) + { + type = long_accum_type_node; + copylen -= 2; + } + else if ((flags & CPP_N_WIDTH) == CPP_N_SMALL) + { + type = short_accum_type_node; + copylen -= 2; + } + else + { + type = accum_type_node; + copylen --; + } + } + } + + copy = (char *) alloca (copylen + 1); + memcpy (copy, token->val.str.text, copylen); + copy[copylen] = '\0'; + + fixed_from_string (&fixed, copy, TYPE_MODE (type)); + + /* Create a node with determined type and value. */ + value = build_fixed (type, fixed); + + return value; +} + +/* Convert a series of STRING, WSTRING, STRING16, STRING32 and/or + UTF8STRING tokens into a tree, performing string constant + concatenation. TOK is the first of these. VALP is the location + to write the string into. OBJC_STRING indicates whether an '@' token + preceded the incoming token. Returns the CPP token type of the result (CPP_STRING, CPP_WSTRING, - or CPP_OBJC_STRING). + CPP_STRING32, CPP_STRING16, CPP_UTF8STRING, or CPP_OBJC_STRING). This is unfortunately more work than it should be. If any of the strings in the series has an L prefix, the result is a wide string @@ -710,22 +890,19 @@ interpret_float (const cpp_token *token, unsigned int flags) we must arrange to provide. */ static enum cpp_ttype -lex_string (const cpp_token *tok, tree *valp, bool objc_string) +lex_string (const cpp_token *tok, tree *valp, bool objc_string, bool translate) { tree value; - bool wide = false; size_t concats = 0; struct obstack str_ob; cpp_string istr; + enum cpp_ttype type = tok->type; /* Try to avoid the overhead of creating and destroying an obstack for the common case of just one string. */ cpp_string str = tok->val.str; cpp_string *strs = &str; - if (tok->type == CPP_WSTRING) - wide = true; - retry: tok = cpp_get_token (parse_in); switch (tok->type) @@ -739,21 +916,29 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string) goto retry; } /* FALLTHROUGH */ - + default: break; - + case CPP_WSTRING: - wide = true; - /* FALLTHROUGH */ - + case CPP_STRING16: + case CPP_STRING32: + case CPP_UTF8STRING: + if (type != tok->type) + { + if (type == CPP_STRING) + type = tok->type; + else + error ("unsupported non-standard concatenation of string literals"); + } + case CPP_STRING: if (!concats) { gcc_obstack_init (&str_ob); obstack_grow (&str_ob, &str, sizeof (cpp_string)); } - + concats++; obstack_grow (&str_ob, &tok->val.str, sizeof (cpp_string)); goto retry; @@ -762,62 +947,72 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string) /* We have read one more token than we want. */ _cpp_backup_tokens (parse_in, 1); if (concats) - strs = (cpp_string *) obstack_finish (&str_ob); + strs = XOBFINISH (&str_ob, cpp_string *); if (concats && !objc_string && !in_system_header) warning (OPT_Wtraditional, "traditional C rejects string constant concatenation"); - if ((c_lex_string_translate + if ((translate ? cpp_interpret_string : cpp_interpret_string_notranslate) - (parse_in, strs, concats + 1, &istr, wide)) + (parse_in, strs, concats + 1, &istr, type)) { - value = build_string (istr.len, (char *) istr.text); - free ((void *) istr.text); - - if (c_lex_string_translate == -1) - { - int xlated = cpp_interpret_string_notranslate (parse_in, strs, - concats + 1, - &istr, wide); - /* Assume that, if we managed to translate the string above, - then the untranslated parsing will always succeed. */ - gcc_assert (xlated); - - if (TREE_STRING_LENGTH (value) != (int) istr.len - || 0 != strncmp (TREE_STRING_POINTER (value), (char *) istr.text, - istr.len)) - { - /* Arrange for us to return the untranslated string in - *valp, but to set up the C type of the translated - one. */ - *valp = build_string (istr.len, (char *) istr.text); - valp = &TREE_CHAIN (*valp); - } - free ((void *) istr.text); - } + value = build_string (istr.len, (const char *) istr.text); + free (CONST_CAST (unsigned char *, istr.text)); } else { /* Callers cannot generally handle error_mark_node in this context, so return the empty string instead. cpp_interpret_string has issued an error. */ - if (wide) - value = build_string (TYPE_PRECISION (wchar_type_node) - / TYPE_PRECISION (char_type_node), - "\0\0\0"); /* widest supported wchar_t - is 32 bits */ - else - value = build_string (1, ""); + switch (type) + { + default: + case CPP_STRING: + case CPP_UTF8STRING: + value = build_string (1, ""); + break; + case CPP_STRING16: + value = build_string (TYPE_PRECISION (char16_type_node) + / TYPE_PRECISION (char_type_node), + "\0"); /* char16_t is 16 bits */ + break; + case CPP_STRING32: + value = build_string (TYPE_PRECISION (char32_type_node) + / TYPE_PRECISION (char_type_node), + "\0\0\0"); /* char32_t is 32 bits */ + break; + case CPP_WSTRING: + value = build_string (TYPE_PRECISION (wchar_type_node) + / TYPE_PRECISION (char_type_node), + "\0\0\0"); /* widest supported wchar_t + is 32 bits */ + break; + } } - TREE_TYPE (value) = wide ? wchar_array_type_node : char_array_type_node; + switch (type) + { + default: + case CPP_STRING: + case CPP_UTF8STRING: + TREE_TYPE (value) = char_array_type_node; + break; + case CPP_STRING16: + TREE_TYPE (value) = char16_array_type_node; + break; + case CPP_STRING32: + TREE_TYPE (value) = char32_array_type_node; + break; + case CPP_WSTRING: + TREE_TYPE (value) = wchar_array_type_node; + } *valp = fix_string_type (value); if (concats) obstack_free (&str_ob, 0); - return objc_string ? CPP_OBJC_STRING : wide ? CPP_WSTRING : CPP_STRING; + return objc_string ? CPP_OBJC_STRING : type; } /* Converts a (possibly wide) character constant token into a tree. */ @@ -827,13 +1022,17 @@ lex_charconst (const cpp_token *token) cppchar_t result; tree type, value; unsigned int chars_seen; - int unsignedp; + int unsignedp = 0; result = cpp_interpret_charconst (parse_in, token, &chars_seen, &unsignedp); if (token->type == CPP_WCHAR) type = wchar_type_node; + else if (token->type == CPP_CHAR32) + type = char32_type_node; + else if (token->type == CPP_CHAR16) + type = char16_type_node; /* In C, a character constant has type 'int'. In C++ 'char', but multi-char charconsts have type 'int'. */ else if (!c_dialect_cxx () || chars_seen > 1)