diff options
Diffstat (limited to 'lib/regex_internal.h')
| -rw-r--r-- | lib/regex_internal.h | 49 |
1 files changed, 19 insertions, 30 deletions
diff --git a/lib/regex_internal.h b/lib/regex_internal.h index 5827597d2c4..57a455b1f43 100644 --- a/lib/regex_internal.h +++ b/lib/regex_internal.h @@ -116,10 +116,6 @@ # define gettext_noop(String) String #endif -#if (defined MB_CUR_MAX && HAVE_WCTYPE_H && HAVE_ISWCTYPE) || _LIBC -# define RE_ENABLE_I18N -#endif - /* Number of ASCII characters. */ #define ASCII_CHARS 0x80 @@ -150,6 +146,11 @@ # define __regfree regfree #endif /* not _LIBC */ +/* Types related to integers. Unless protected by #ifdef _LIBC, the + regex code should avoid exact-width types like int32_t and uint64_t + as some non-GCC platforms lack them, an issue when this code is + used in Gnulib. */ + #ifndef SSIZE_MAX # define SSIZE_MAX ((ssize_t) (SIZE_MAX / 2)) #endif @@ -246,10 +247,8 @@ typedef enum SIMPLE_BRACKET = 3, OP_BACK_REF = 4, OP_PERIOD = 5, -#ifdef RE_ENABLE_I18N COMPLEX_BRACKET = 6, OP_UTF8_PERIOD = 7, -#endif /* RE_ENABLE_I18N */ /* We define EPSILON_BIT as a macro so that OP_OPEN_SUBEXP is used when the debugger shows values of this enum type. */ @@ -287,30 +286,29 @@ typedef enum } re_token_type_t; -#ifdef RE_ENABLE_I18N typedef struct { /* Multibyte characters. */ wchar_t *mbchars; +#ifdef _LIBC /* Collating symbols. */ -# ifdef _LIBC int32_t *coll_syms; -# endif +#endif +#ifdef _LIBC /* Equivalence classes. */ -# ifdef _LIBC int32_t *equiv_classes; -# endif +#endif /* Range expressions. */ -# ifdef _LIBC +#ifdef _LIBC uint32_t *range_starts; uint32_t *range_ends; -# else /* not _LIBC */ +#else wchar_t *range_starts; wchar_t *range_ends; -# endif /* not _LIBC */ +#endif /* Character classes. */ wctype_t *char_classes; @@ -333,7 +331,6 @@ typedef struct /* # of character classes. */ Idx nchar_classes; } re_charset_t; -#endif /* RE_ENABLE_I18N */ typedef struct { @@ -341,9 +338,7 @@ typedef struct { unsigned char c; /* for CHARACTER */ re_bitset_ptr_t sbcset; /* for SIMPLE_BRACKET */ -#ifdef RE_ENABLE_I18N re_charset_t *mbcset; /* for COMPLEX_BRACKET */ -#endif /* RE_ENABLE_I18N */ Idx idx; /* for BACK_REF */ re_context_type ctx_type; /* for ANCHOR */ } opr; @@ -355,12 +350,10 @@ typedef struct unsigned int constraint : 10; /* context constraint */ unsigned int duplicated : 1; unsigned int opt_subexp : 1; -#ifdef RE_ENABLE_I18N unsigned int accept_mb : 1; /* These 2 bits can be moved into the union if needed (e.g. if running out of bits; move opr.c to opr.c.c and move the flags to opr.c.flags). */ unsigned int mb_partial : 1; -#endif unsigned int word_char : 1; } re_token_t; @@ -375,12 +368,10 @@ struct re_string_t REG_ICASE, upper cases of the string are stored, otherwise MBS points the same address that RAW_MBS points. */ unsigned char *mbs; -#ifdef RE_ENABLE_I18N /* Store the wide character string which is corresponding to MBS. */ wint_t *wcs; Idx *offsets; mbstate_t cur_state; -#endif /* Index in RAW_MBS. Each character mbs[i] corresponds to raw_mbs[raw_mbs_idx + i]. */ Idx raw_mbs_idx; @@ -779,7 +770,6 @@ bitset_mask (bitset_t dest, const bitset_t src) dest[bitset_i] &= src[bitset_i]; } -#ifdef RE_ENABLE_I18N /* Functions for re_string. */ static int __attribute__ ((pure, unused)) @@ -803,15 +793,15 @@ re_string_wchar_at (const re_string_t *pstr, Idx idx) return (wint_t) pstr->wcs[idx]; } -# ifdef _LIBC -# include <locale/weight.h> -# endif +#ifdef _LIBC +# include <locale/weight.h> +#endif static int __attribute__ ((pure, unused)) re_string_elem_size_at (const re_string_t *pstr, Idx idx) { -# ifdef _LIBC +#ifdef _LIBC const unsigned char *p, *extra; const int32_t *table, *indirect; uint_fast32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); @@ -827,11 +817,10 @@ re_string_elem_size_at (const re_string_t *pstr, Idx idx) findidx (table, indirect, extra, &p, pstr->len - idx); return p - pstr->mbs - idx; } - else -# endif /* _LIBC */ - return 1; +#endif /* _LIBC */ + + return 1; } -#endif /* RE_ENABLE_I18N */ #ifdef _LIBC # if __GNUC__ >= 7 |