From da7267e889a72edd86896f7487a6a8e4d1216441 Mon Sep 17 00:00:00 2001 From: Paul Eggert Date: Mon, 27 Jan 2020 23:27:46 -0800 Subject: [PATCH] Update from Gnulib This incorporates: 2020-01-27 regex: port to non-GCC pre-IEC-60559 2020-01-24 regex: port to Gawk on nonstandard platforms 2020-01-21 regex: fix bug with >=16 subexpressions 2020-01-21 regex: simplify definition of BITSET_WORD_BITS * lib/regex.c, lib/regex_internal.h: Copy from Gnulib. --- lib/regex.c | 2 ++ lib/regex_internal.h | 53 ++++++++++++++++++-------------------------- 2 files changed, 23 insertions(+), 32 deletions(-) diff --git a/lib/regex.c b/lib/regex.c index 6bdd77f50b2..88173bb1052 100644 --- a/lib/regex.c +++ b/lib/regex.c @@ -17,6 +17,8 @@ License along with the GNU C Library; if not, see . */ +#define __STDC_WANT_IEC_60559_BFP_EXT__ + #ifndef _LIBC # include diff --git a/lib/regex_internal.h b/lib/regex_internal.h index 5c9cbf3b4fe..f6ebfb003e8 100644 --- a/lib/regex_internal.h +++ b/lib/regex_internal.h @@ -141,6 +141,24 @@ #ifndef SSIZE_MAX # define SSIZE_MAX ((ssize_t) (SIZE_MAX / 2)) #endif +#ifndef ULONG_WIDTH +# define ULONG_WIDTH REGEX_UINTEGER_WIDTH (ULONG_MAX) +/* The number of usable bits in an unsigned integer type with maximum + value MAX, as an int expression suitable in #if. Cover all known + practical hosts. This implementation exploits the fact that MAX is + 1 less than a power of 2, and merely counts the number of 1 bits in + MAX; "COBn" means "count the number of 1 bits in the low-order n bits". */ +# define REGEX_UINTEGER_WIDTH(max) REGEX_COB128 (max) +# define REGEX_COB128(n) (REGEX_COB64 ((n) >> 31 >> 31 >> 2) + REGEX_COB64 (n)) +# define REGEX_COB64(n) (REGEX_COB32 ((n) >> 31 >> 1) + REGEX_COB32 (n)) +# define REGEX_COB32(n) (REGEX_COB16 ((n) >> 16) + REGEX_COB16 (n)) +# define REGEX_COB16(n) (REGEX_COB8 ((n) >> 8) + REGEX_COB8 (n)) +# define REGEX_COB8(n) (REGEX_COB4 ((n) >> 4) + REGEX_COB4 (n)) +# define REGEX_COB4(n) (!!((n) & 8) + !!((n) & 4) + !!((n) & 2) + ((n) & 1)) +# if ULONG_MAX / 2 + 1 != 1ul << (ULONG_WIDTH - 1) +# error "ULONG_MAX out of range" +# endif +#endif /* The type of indexes into strings. This is signed, not size_t, since the API requires indexes to fit in regoff_t anyway, and using @@ -164,36 +182,8 @@ typedef __re_size_t re_hashval_t; typedef unsigned long int bitset_word_t; /* All bits set in a bitset_word_t. */ #define BITSET_WORD_MAX ULONG_MAX - -/* Number of bits in a bitset_word_t. For portability to hosts with - padding bits, do not use '(sizeof (bitset_word_t) * CHAR_BIT)'; - instead, deduce it directly from BITSET_WORD_MAX. Avoid - greater-than-32-bit integers and unconditional shifts by more than - 31 bits, as they're not portable. */ -#if BITSET_WORD_MAX == 0xffffffffUL -# define BITSET_WORD_BITS 32 -#elif BITSET_WORD_MAX >> 31 >> 4 == 1 -# define BITSET_WORD_BITS 36 -#elif BITSET_WORD_MAX >> 31 >> 16 == 1 -# define BITSET_WORD_BITS 48 -#elif BITSET_WORD_MAX >> 31 >> 28 == 1 -# define BITSET_WORD_BITS 60 -#elif BITSET_WORD_MAX >> 31 >> 31 >> 1 == 1 -# define BITSET_WORD_BITS 64 -#elif BITSET_WORD_MAX >> 31 >> 31 >> 9 == 1 -# define BITSET_WORD_BITS 72 -#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 3 == 1 -# define BITSET_WORD_BITS 128 -#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 7 == 1 -# define BITSET_WORD_BITS 256 -#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 7 > 1 -# define BITSET_WORD_BITS 257 /* any value > SBC_MAX will do here */ -# if BITSET_WORD_BITS <= SBC_MAX -# error "Invalid SBC_MAX" -# endif -#else -# error "Add case for new bitset_word_t size" -#endif +/* Number of bits in a bitset_word_t. */ +#define BITSET_WORD_BITS ULONG_WIDTH /* Number of bitset_word_t values in a bitset_t. */ #define BITSET_WORDS ((SBC_MAX + BITSET_WORD_BITS - 1) / BITSET_WORD_BITS) @@ -601,9 +591,8 @@ struct re_backref_cache_entry Idx str_idx; Idx subexp_from; Idx subexp_to; + bitset_word_t eps_reachable_subexps_map; char more; - char unused; - unsigned short int eps_reachable_subexps_map; }; typedef struct -- 2.39.2