From c9a464483e3341ccb828ca0a6a5fd1b698d56cee Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Fri, 29 Nov 2024 09:37:43 -0800 Subject: [PATCH v16 1/4] Control ctype behavior internally with a method table. Previously, pattern matching and case mapping behavior branched based on the provider. Refactor to use a method table, which is less error-prone and easier to hook. --- src/backend/regex/regc_pg_locale.c | 429 ++++------------------ src/backend/utils/adt/like.c | 22 +- src/backend/utils/adt/like_support.c | 7 +- src/backend/utils/adt/pg_locale.c | 121 +++--- src/backend/utils/adt/pg_locale_builtin.c | 111 +++++- src/backend/utils/adt/pg_locale_icu.c | 119 +++++- src/backend/utils/adt/pg_locale_libc.c | 331 +++++++++++++++-- src/include/utils/pg_locale.h | 53 +++ src/tools/pgindent/typedefs.list | 1 - 9 files changed, 686 insertions(+), 508 deletions(-) diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c index 78193cfb964..d9eab5357bc 100644 --- a/src/backend/regex/regc_pg_locale.c +++ b/src/backend/regex/regc_pg_locale.c @@ -20,58 +20,13 @@ #include "common/unicode_category.h" #include "utils/pg_locale.h" -/* - * For the libc provider, to provide as much functionality as possible on a - * variety of platforms without going so far as to implement everything from - * scratch, we use several implementation strategies depending on the - * situation: - * - * 1. In C/POSIX collations, we use hard-wired code. We can't depend on - * the functions since those will obey LC_CTYPE. Note that these - * collations don't give a fig about multibyte characters. - * - * 2. When working in UTF8 encoding, we use the functions. - * This assumes that every platform uses Unicode codepoints directly - * as the wchar_t representation of Unicode. (XXX: ICU makes this assumption - * even for non-UTF8 encodings, which may be a problem.) On some platforms - * wchar_t is only 16 bits wide, so we have to punt for codepoints > 0xFFFF. - * - * 3. In all other encodings, we use the functions for pg_wchar - * values up to 255, and punt for values above that. This is 100% correct - * only in single-byte encodings such as LATINn. However, non-Unicode - * multibyte encodings are mostly Far Eastern character sets for which the - * properties being tested here aren't very relevant for higher code values - * anyway. The difficulty with using the functions with - * non-Unicode multibyte encodings is that we can have no certainty that - * the platform's wchar_t representation matches what we do in pg_wchar - * conversions. - * - * As a special case, in the "default" collation, (2) and (3) force ASCII - * letters to follow ASCII upcase/downcase rules, while in a non-default - * collation we just let the library functions do what they will. The case - * where this matters is treatment of I/i in Turkish, and the behavior is - * meant to match the upper()/lower() SQL functions. - * - * We store the active collation setting in static variables. In principle - * it could be passed down to here via the regex library's "struct vars" data - * structure; but that would require somewhat invasive changes in the regex - * library, and right now there's no real benefit to be gained from that. - * - * NB: the coding here assumes pg_wchar is an unsigned type. - */ - -typedef enum -{ - PG_REGEX_STRATEGY_C, /* C locale (encoding independent) */ - PG_REGEX_STRATEGY_BUILTIN, /* built-in Unicode semantics */ - PG_REGEX_STRATEGY_LIBC_WIDE, /* Use locale_t functions */ - PG_REGEX_STRATEGY_LIBC_1BYTE, /* Use locale_t functions */ - PG_REGEX_STRATEGY_ICU, /* Use ICU uchar.h functions */ -} PG_Locale_Strategy; - -static PG_Locale_Strategy pg_regex_strategy; static pg_locale_t pg_regex_locale; +static struct pg_locale_struct dummy_c_locale = { + .collate_is_c = true, + .ctype_is_c = true, +}; + /* * Hard-wired character properties for C locale */ @@ -228,7 +183,6 @@ void pg_set_regex_collation(Oid collation) { pg_locale_t locale = 0; - PG_Locale_Strategy strategy; if (!OidIsValid(collation)) { @@ -249,8 +203,7 @@ pg_set_regex_collation(Oid collation) * catalog access is available, so we can't call * pg_newlocale_from_collation(). */ - strategy = PG_REGEX_STRATEGY_C; - locale = 0; + locale = &dummy_c_locale; } else { @@ -267,113 +220,41 @@ pg_set_regex_collation(Oid collation) * C/POSIX collations use this path regardless of database * encoding */ - strategy = PG_REGEX_STRATEGY_C; - locale = 0; - } - else if (locale->provider == COLLPROVIDER_BUILTIN) - { - Assert(GetDatabaseEncoding() == PG_UTF8); - strategy = PG_REGEX_STRATEGY_BUILTIN; - } -#ifdef USE_ICU - else if (locale->provider == COLLPROVIDER_ICU) - { - strategy = PG_REGEX_STRATEGY_ICU; - } -#endif - else - { - Assert(locale->provider == COLLPROVIDER_LIBC); - if (GetDatabaseEncoding() == PG_UTF8) - strategy = PG_REGEX_STRATEGY_LIBC_WIDE; - else - strategy = PG_REGEX_STRATEGY_LIBC_1BYTE; + locale = &dummy_c_locale; } } - pg_regex_strategy = strategy; pg_regex_locale = locale; } static int pg_wc_isdigit(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISDIGIT)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isdigit(c, !pg_regex_locale->info.builtin.casemap_full); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswdigit_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isdigit_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isdigit(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISDIGIT)); + else + return pg_regex_locale->ctype->wc_isdigit(c, pg_regex_locale); } static int pg_wc_isalpha(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISALPHA)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isalpha(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswalpha_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isalpha_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isalpha(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISALPHA)); + else + return pg_regex_locale->ctype->wc_isalpha(c, pg_regex_locale); } static int pg_wc_isalnum(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISALNUM)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isalnum(c, !pg_regex_locale->info.builtin.casemap_full); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswalnum_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isalnum_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isalnum(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISALNUM)); + else + return pg_regex_locale->ctype->wc_isalnum(c, pg_regex_locale); } static int @@ -388,231 +269,87 @@ pg_wc_isword(pg_wchar c) static int pg_wc_isupper(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISUPPER)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isupper(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswupper_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isupper_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isupper(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISUPPER)); + else + return pg_regex_locale->ctype->wc_isupper(c, pg_regex_locale); } static int pg_wc_islower(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISLOWER)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_islower(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswlower_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - islower_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_islower(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISLOWER)); + else + return pg_regex_locale->ctype->wc_islower(c, pg_regex_locale); } static int pg_wc_isgraph(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISGRAPH)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isgraph(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswgraph_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isgraph_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isgraph(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISGRAPH)); + else + return pg_regex_locale->ctype->wc_isgraph(c, pg_regex_locale); } static int pg_wc_isprint(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISPRINT)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isprint(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswprint_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isprint_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isprint(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISPRINT)); + else + return pg_regex_locale->ctype->wc_isprint(c, pg_regex_locale); } static int pg_wc_ispunct(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISPUNCT)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_ispunct(c, !pg_regex_locale->info.builtin.casemap_full); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswpunct_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - ispunct_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_ispunct(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISPUNCT)); + else + return pg_regex_locale->ctype->wc_ispunct(c, pg_regex_locale); } static int pg_wc_isspace(pg_wchar c) { - switch (pg_regex_strategy) - { - case PG_REGEX_STRATEGY_C: - return (c <= (pg_wchar) 127 && - (pg_char_properties[c] & PG_ISSPACE)); - case PG_REGEX_STRATEGY_BUILTIN: - return pg_u_isspace(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswspace_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - return (c <= (pg_wchar) UCHAR_MAX && - isspace_l((unsigned char) c, pg_regex_locale->info.lt)); - break; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_isspace(c); -#endif - break; - } - return 0; /* can't get here, but keep compiler quiet */ + if (pg_regex_locale->ctype_is_c) + return (c <= (pg_wchar) 127 && + (pg_char_properties[c] & PG_ISSPACE)); + else + return pg_regex_locale->ctype->wc_isspace(c, pg_regex_locale); } static pg_wchar pg_wc_toupper(pg_wchar c) { - switch (pg_regex_strategy) + if (pg_regex_locale->ctype_is_c) { - case PG_REGEX_STRATEGY_C: - if (c <= (pg_wchar) 127) - return pg_ascii_toupper((unsigned char) c); - return c; - case PG_REGEX_STRATEGY_BUILTIN: - return unicode_uppercase_simple(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - /* force C behavior for ASCII characters, per comments above */ - if (pg_regex_locale->is_default && c <= (pg_wchar) 127) - return pg_ascii_toupper((unsigned char) c); - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return towupper_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - /* force C behavior for ASCII characters, per comments above */ - if (pg_regex_locale->is_default && c <= (pg_wchar) 127) - return pg_ascii_toupper((unsigned char) c); - if (c <= (pg_wchar) UCHAR_MAX) - return toupper_l((unsigned char) c, pg_regex_locale->info.lt); - return c; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_toupper(c); -#endif - break; + if (c <= (pg_wchar) 127) + return pg_ascii_toupper((unsigned char) c); + return c; } - return 0; /* can't get here, but keep compiler quiet */ + else + return pg_regex_locale->ctype->wc_toupper(c, pg_regex_locale); } static pg_wchar pg_wc_tolower(pg_wchar c) { - switch (pg_regex_strategy) + if (pg_regex_locale->ctype_is_c) { - case PG_REGEX_STRATEGY_C: - if (c <= (pg_wchar) 127) - return pg_ascii_tolower((unsigned char) c); - return c; - case PG_REGEX_STRATEGY_BUILTIN: - return unicode_lowercase_simple(c); - case PG_REGEX_STRATEGY_LIBC_WIDE: - /* force C behavior for ASCII characters, per comments above */ - if (pg_regex_locale->is_default && c <= (pg_wchar) 127) - return pg_ascii_tolower((unsigned char) c); - if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return towlower_l((wint_t) c, pg_regex_locale->info.lt); - /* FALL THRU */ - case PG_REGEX_STRATEGY_LIBC_1BYTE: - /* force C behavior for ASCII characters, per comments above */ - if (pg_regex_locale->is_default && c <= (pg_wchar) 127) - return pg_ascii_tolower((unsigned char) c); - if (c <= (pg_wchar) UCHAR_MAX) - return tolower_l((unsigned char) c, pg_regex_locale->info.lt); - return c; - case PG_REGEX_STRATEGY_ICU: -#ifdef USE_ICU - return u_tolower(c); -#endif - break; + if (c <= (pg_wchar) 127) + return pg_ascii_tolower((unsigned char) c); + return c; } - return 0; /* can't get here, but keep compiler quiet */ + else + return pg_regex_locale->ctype->wc_tolower(c, pg_regex_locale); } @@ -738,37 +475,25 @@ pg_ctype_get_cache(pg_wc_probefunc probefunc, int cclasscode) * would always be true for production values of MAX_SIMPLE_CHR, but it's * useful to allow it to be small for testing purposes.) */ - switch (pg_regex_strategy) + if (pg_regex_locale->ctype_is_c) { - case PG_REGEX_STRATEGY_C: #if MAX_SIMPLE_CHR >= 127 - max_chr = (pg_wchar) 127; - pcc->cv.cclasscode = -1; + max_chr = (pg_wchar) 127; + pcc->cv.cclasscode = -1; #else - max_chr = (pg_wchar) MAX_SIMPLE_CHR; + max_chr = (pg_wchar) MAX_SIMPLE_CHR; #endif - break; - case PG_REGEX_STRATEGY_BUILTIN: - max_chr = (pg_wchar) MAX_SIMPLE_CHR; - break; - case PG_REGEX_STRATEGY_LIBC_WIDE: - max_chr = (pg_wchar) MAX_SIMPLE_CHR; - break; - case PG_REGEX_STRATEGY_LIBC_1BYTE: -#if MAX_SIMPLE_CHR >= UCHAR_MAX - max_chr = (pg_wchar) UCHAR_MAX; + } + else + { + if (pg_regex_locale->ctype->max_chr != 0 && + pg_regex_locale->ctype->max_chr <= MAX_SIMPLE_CHR) + { + max_chr = pg_regex_locale->ctype->max_chr; pcc->cv.cclasscode = -1; -#else - max_chr = (pg_wchar) MAX_SIMPLE_CHR; -#endif - break; - case PG_REGEX_STRATEGY_ICU: + } + else max_chr = (pg_wchar) MAX_SIMPLE_CHR; - break; - default: - Assert(false); - max_chr = 0; /* can't get here, but keep compiler quiet */ - break; } /* diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c index 7f4cf614585..4216ac17f43 100644 --- a/src/backend/utils/adt/like.c +++ b/src/backend/utils/adt/like.c @@ -98,7 +98,7 @@ SB_lower_char(unsigned char c, pg_locale_t locale) else if (locale->is_default) return pg_tolower(c); else - return tolower_l(c, locale->info.lt); + return char_tolower(c, locale); } @@ -209,7 +209,17 @@ Generic_Text_IC_like(text *str, text *pat, Oid collation) * way. */ - if (pg_database_encoding_max_length() > 1 || (locale->provider == COLLPROVIDER_ICU)) + if (locale->ctype_is_c || + (char_tolower_enabled(locale) && + pg_database_encoding_max_length() == 1)) + { + p = VARDATA_ANY(pat); + plen = VARSIZE_ANY_EXHDR(pat); + s = VARDATA_ANY(str); + slen = VARSIZE_ANY_EXHDR(str); + return SB_IMatchText(s, slen, p, plen, locale); + } + else { pat = DatumGetTextPP(DirectFunctionCall1Coll(lower, collation, PointerGetDatum(pat))); @@ -224,14 +234,6 @@ Generic_Text_IC_like(text *str, text *pat, Oid collation) else return MB_MatchText(s, slen, p, plen, 0); } - else - { - p = VARDATA_ANY(pat); - plen = VARSIZE_ANY_EXHDR(pat); - s = VARDATA_ANY(str); - slen = VARSIZE_ANY_EXHDR(str); - return SB_IMatchText(s, slen, p, plen, locale); - } } /* diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c index 8fdc677371f..999f23f86d5 100644 --- a/src/backend/utils/adt/like_support.c +++ b/src/backend/utils/adt/like_support.c @@ -1495,13 +1495,8 @@ pattern_char_isalpha(char c, bool is_multibyte, { if (locale->ctype_is_c) return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); - else if (is_multibyte && IS_HIGHBIT_SET(c)) - return true; - else if (locale->provider != COLLPROVIDER_LIBC) - return IS_HIGHBIT_SET(c) || - (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); else - return isalpha_l((unsigned char) c, locale->info.lt); + return char_is_cased(c, locale); } diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index f5e31c433a0..451ac4e2d9b 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -80,31 +80,6 @@ extern pg_locale_t create_pg_locale_icu(Oid collid, MemoryContext context); extern pg_locale_t create_pg_locale_libc(Oid collid, MemoryContext context); extern char *get_collation_actual_version_libc(const char *collcollate); -extern size_t strlower_builtin(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_builtin(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_builtin(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strfold_builtin(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); - -extern size_t strlower_icu(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_icu(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_icu(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strfold_icu(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); - -extern size_t strlower_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); - /* GUC settings */ char *locale_messages; char *locale_monetary; @@ -1093,6 +1068,9 @@ create_pg_locale(Oid collid, MemoryContext context) Assert((result->collate_is_c && result->collate == NULL) || (!result->collate_is_c && result->collate != NULL)); + Assert((result->ctype_is_c && result->ctype == NULL) || + (!result->ctype_is_c && result->ctype != NULL)); + datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion, &isnull); if (!isnull) @@ -1257,77 +1235,31 @@ size_t pg_strlower(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale) { - if (locale->provider == COLLPROVIDER_BUILTIN) - return strlower_builtin(dst, dstsize, src, srclen, locale); -#ifdef USE_ICU - else if (locale->provider == COLLPROVIDER_ICU) - return strlower_icu(dst, dstsize, src, srclen, locale); -#endif - else if (locale->provider == COLLPROVIDER_LIBC) - return strlower_libc(dst, dstsize, src, srclen, locale); - else - /* shouldn't happen */ - PGLOCALE_SUPPORT_ERROR(locale->provider); - - return 0; /* keep compiler quiet */ + return locale->ctype->strlower(dst, dstsize, src, srclen, locale); } size_t pg_strtitle(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale) { - if (locale->provider == COLLPROVIDER_BUILTIN) - return strtitle_builtin(dst, dstsize, src, srclen, locale); -#ifdef USE_ICU - else if (locale->provider == COLLPROVIDER_ICU) - return strtitle_icu(dst, dstsize, src, srclen, locale); -#endif - else if (locale->provider == COLLPROVIDER_LIBC) - return strtitle_libc(dst, dstsize, src, srclen, locale); - else - /* shouldn't happen */ - PGLOCALE_SUPPORT_ERROR(locale->provider); - - return 0; /* keep compiler quiet */ + return locale->ctype->strtitle(dst, dstsize, src, srclen, locale); } size_t pg_strupper(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale) { - if (locale->provider == COLLPROVIDER_BUILTIN) - return strupper_builtin(dst, dstsize, src, srclen, locale); -#ifdef USE_ICU - else if (locale->provider == COLLPROVIDER_ICU) - return strupper_icu(dst, dstsize, src, srclen, locale); -#endif - else if (locale->provider == COLLPROVIDER_LIBC) - return strupper_libc(dst, dstsize, src, srclen, locale); - else - /* shouldn't happen */ - PGLOCALE_SUPPORT_ERROR(locale->provider); - - return 0; /* keep compiler quiet */ + return locale->ctype->strupper(dst, dstsize, src, srclen, locale); } size_t pg_strfold(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale) { - if (locale->provider == COLLPROVIDER_BUILTIN) - return strfold_builtin(dst, dstsize, src, srclen, locale); -#ifdef USE_ICU - else if (locale->provider == COLLPROVIDER_ICU) - return strfold_icu(dst, dstsize, src, srclen, locale); -#endif - /* for libc, just use strlower */ - else if (locale->provider == COLLPROVIDER_LIBC) - return strlower_libc(dst, dstsize, src, srclen, locale); + if (locale->ctype->strfold) + return locale->ctype->strfold(dst, dstsize, src, srclen, locale); else - /* shouldn't happen */ - PGLOCALE_SUPPORT_ERROR(locale->provider); - - return 0; /* keep compiler quiet */ + return locale->ctype->strlower(dst, dstsize, src, srclen, locale); } /* @@ -1464,6 +1396,41 @@ pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src, return locale->collate->strnxfrm_prefix(dest, destsize, src, srclen, locale); } +/* + * char_is_cased() + * + * Fuzzy test of whether the given char is case-varying or not. The argument + * is a single byte, so in a multibyte encoding, just assume any non-ASCII + * char is case-varying. + */ +bool +char_is_cased(char ch, pg_locale_t locale) +{ + return locale->ctype->char_is_cased(ch, locale); +} + +/* + * char_tolower_enabled() + * + * Does the provider support char_tolower()? + */ +bool +char_tolower_enabled(pg_locale_t locale) +{ + return (locale->ctype->char_tolower != NULL); +} + +/* + * char_tolower() + * + * Convert char (single-byte encoding) to lowercase. + */ +char +char_tolower(unsigned char ch, pg_locale_t locale) +{ + return locale->ctype->char_tolower(ch, locale); +} + /* * Return required encoding ID for the given locale, or -1 if any encoding is * valid for the locale. diff --git a/src/backend/utils/adt/pg_locale_builtin.c b/src/backend/utils/adt/pg_locale_builtin.c index f51768830cd..6fe090708ff 100644 --- a/src/backend/utils/adt/pg_locale_builtin.c +++ b/src/backend/utils/adt/pg_locale_builtin.c @@ -25,15 +25,6 @@ extern pg_locale_t create_pg_locale_builtin(Oid collid, MemoryContext context); extern char *get_collation_actual_version_builtin(const char *collcollate); -extern size_t strlower_builtin(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_builtin(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_builtin(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strfold_builtin(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); - struct WordBoundaryState { @@ -77,7 +68,7 @@ initcap_wbnext(void *state) return wbstate->len; } -size_t +static size_t strlower_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -85,7 +76,7 @@ strlower_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, locale->info.builtin.casemap_full); } -size_t +static size_t strtitle_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -103,7 +94,7 @@ strtitle_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, initcap_wbnext, &wbstate); } -size_t +static size_t strupper_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -111,7 +102,7 @@ strupper_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, locale->info.builtin.casemap_full); } -size_t +static size_t strfold_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -119,6 +110,98 @@ strfold_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, locale->info.builtin.casemap_full); } +static bool +wc_isdigit_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isdigit(wc, !locale->info.builtin.casemap_full); +} + +static bool +wc_isalpha_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isalpha(wc); +} + +static bool +wc_isalnum_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isalnum(wc, !locale->info.builtin.casemap_full); +} + +static bool +wc_isupper_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isupper(wc); +} + +static bool +wc_islower_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_islower(wc); +} + +static bool +wc_isgraph_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isgraph(wc); +} + +static bool +wc_isprint_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isprint(wc); +} + +static bool +wc_ispunct_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_ispunct(wc, !locale->info.builtin.casemap_full); +} + +static bool +wc_isspace_builtin(pg_wchar wc, pg_locale_t locale) +{ + return pg_u_isspace(wc); +} + +static bool +char_is_cased_builtin(char ch, pg_locale_t locale) +{ + return IS_HIGHBIT_SET(ch) || + (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z'); +} + +static pg_wchar +wc_toupper_builtin(pg_wchar wc, pg_locale_t locale) +{ + return unicode_uppercase_simple(wc); +} + +static pg_wchar +wc_tolower_builtin(pg_wchar wc, pg_locale_t locale) +{ + return unicode_lowercase_simple(wc); +} + +static const struct ctype_methods ctype_methods_builtin = { + .strlower = strlower_builtin, + .strtitle = strtitle_builtin, + .strupper = strupper_builtin, + .strfold = strfold_builtin, + .wc_isdigit = wc_isdigit_builtin, + .wc_isalpha = wc_isalpha_builtin, + .wc_isalnum = wc_isalnum_builtin, + .wc_isupper = wc_isupper_builtin, + .wc_islower = wc_islower_builtin, + .wc_isgraph = wc_isgraph_builtin, + .wc_isprint = wc_isprint_builtin, + .wc_ispunct = wc_ispunct_builtin, + .wc_isspace = wc_isspace_builtin, + .char_is_cased = char_is_cased_builtin, + .wc_tolower = wc_tolower_builtin, + .wc_toupper = wc_toupper_builtin, +}; + pg_locale_t create_pg_locale_builtin(Oid collid, MemoryContext context) { @@ -162,6 +245,8 @@ create_pg_locale_builtin(Oid collid, MemoryContext context) result->deterministic = true; result->collate_is_c = true; result->ctype_is_c = (strcmp(locstr, "C") == 0); + if (!result->ctype_is_c) + result->ctype = &ctype_methods_builtin; return result; } diff --git a/src/backend/utils/adt/pg_locale_icu.c b/src/backend/utils/adt/pg_locale_icu.c index a32c32a0744..1f4ee2d1990 100644 --- a/src/backend/utils/adt/pg_locale_icu.c +++ b/src/backend/utils/adt/pg_locale_icu.c @@ -48,19 +48,22 @@ #define TEXTBUFLEN 1024 extern pg_locale_t create_pg_locale_icu(Oid collid, MemoryContext context); -extern size_t strlower_icu(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_icu(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_icu(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strfold_icu(char *dest, size_t destsize, const char *src, - ssize_t srclen, pg_locale_t locale); #ifdef USE_ICU extern UCollator *pg_ucol_open(const char *loc_str); +static size_t strlower_icu(char *dest, size_t destsize, const char *src, + ssize_t srclen, pg_locale_t locale); +static size_t strtitle_icu(char *dest, size_t destsize, const char *src, + ssize_t srclen, pg_locale_t locale); +static size_t strupper_icu(char *dest, size_t destsize, const char *src, + ssize_t srclen, pg_locale_t locale); +static size_t strfold_icu(char *dest, size_t destsize, const char *src, + ssize_t srclen, pg_locale_t locale); +static int strncoll_icu(const char *arg1, ssize_t len1, + const char *arg2, ssize_t len2, + pg_locale_t locale); static size_t strnxfrm_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); @@ -118,6 +121,25 @@ static int32_t u_strFoldCase_default(UChar *dest, int32_t destCapacity, const char *locale, UErrorCode *pErrorCode); +static bool +char_is_cased_icu(char ch, pg_locale_t locale) +{ + return IS_HIGHBIT_SET(ch) || + (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z'); +} + +static pg_wchar +toupper_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_toupper(wc); +} + +static pg_wchar +tolower_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_tolower(wc); +} + static const struct collate_methods collate_methods_icu = { .strncoll = strncoll_icu, .strnxfrm = strnxfrm_icu, @@ -136,6 +158,78 @@ static const struct collate_methods collate_methods_icu_utf8 = { .strxfrm_is_safe = true, }; +static bool +wc_isdigit_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isdigit(wc); +} + +static bool +wc_isalpha_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isalpha(wc); +} + +static bool +wc_isalnum_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isalnum(wc); +} + +static bool +wc_isupper_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isupper(wc); +} + +static bool +wc_islower_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_islower(wc); +} + +static bool +wc_isgraph_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isgraph(wc); +} + +static bool +wc_isprint_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isprint(wc); +} + +static bool +wc_ispunct_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_ispunct(wc); +} + +static bool +wc_isspace_icu(pg_wchar wc, pg_locale_t locale) +{ + return u_isspace(wc); +} + +static const struct ctype_methods ctype_methods_icu = { + .strlower = strlower_icu, + .strtitle = strtitle_icu, + .strupper = strupper_icu, + .strfold = strfold_icu, + .wc_isdigit = wc_isdigit_icu, + .wc_isalpha = wc_isalpha_icu, + .wc_isalnum = wc_isalnum_icu, + .wc_isupper = wc_isupper_icu, + .wc_islower = wc_islower_icu, + .wc_isgraph = wc_isgraph_icu, + .wc_isprint = wc_isprint_icu, + .wc_ispunct = wc_ispunct_icu, + .wc_isspace = wc_isspace_icu, + .char_is_cased = char_is_cased_icu, + .wc_toupper = toupper_icu, + .wc_tolower = tolower_icu, +}; #endif pg_locale_t @@ -206,6 +300,7 @@ create_pg_locale_icu(Oid collid, MemoryContext context) result->collate = &collate_methods_icu_utf8; else result->collate = &collate_methods_icu; + result->ctype = &ctype_methods_icu; return result; #else @@ -379,7 +474,7 @@ make_icu_collator(const char *iculocstr, const char *icurules) } } -size_t +static size_t strlower_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -399,7 +494,7 @@ strlower_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, return result_len; } -size_t +static size_t strtitle_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -419,7 +514,7 @@ strtitle_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, return result_len; } -size_t +static size_t strupper_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { @@ -439,7 +534,7 @@ strupper_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, return result_len; } -size_t +static size_t strfold_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c index 199857e22db..be714db5283 100644 --- a/src/backend/utils/adt/pg_locale_libc.c +++ b/src/backend/utils/adt/pg_locale_libc.c @@ -33,6 +33,46 @@ #include #endif +/* + * For the libc provider, to provide as much functionality as possible on a + * variety of platforms without going so far as to implement everything from + * scratch, we use several implementation strategies depending on the + * situation: + * + * 1. In C/POSIX collations, we use hard-wired code. We can't depend on + * the functions since those will obey LC_CTYPE. Note that these + * collations don't give a fig about multibyte characters. + * + * 2. When working in UTF8 encoding, we use the functions. + * This assumes that every platform uses Unicode codepoints directly + * as the wchar_t representation of Unicode. (XXX: ICU makes this assumption + * even for non-UTF8 encodings, which may be a problem.) On some platforms + * wchar_t is only 16 bits wide, so we have to punt for codepoints > 0xFFFF. + * + * 3. In all other encodings, we use the functions for pg_wchar + * values up to 255, and punt for values above that. This is 100% correct + * only in single-byte encodings such as LATINn. However, non-Unicode + * multibyte encodings are mostly Far Eastern character sets for which the + * properties being tested here aren't very relevant for higher code values + * anyway. The difficulty with using the functions with + * non-Unicode multibyte encodings is that we can have no certainty that + * the platform's wchar_t representation matches what we do in pg_wchar + * conversions. + * + * As a special case, in the "default" collation, (2) and (3) force ASCII + * letters to follow ASCII upcase/downcase rules, while in a non-default + * collation we just let the library functions do what they will. The case + * where this matters is treatment of I/i in Turkish, and the behavior is + * meant to match the upper()/lower() SQL functions. + * + * We store the active collation setting in static variables. In principle + * it could be passed down to here via the regex library's "struct vars" data + * structure; but that would require somewhat invasive changes in the regex + * library, and right now there's no real benefit to be gained from that. + * + * NB: the coding here assumes pg_wchar is an unsigned type. + */ + /* * Size of stack buffer to use for string transformations, used to avoid heap * allocations in typical cases. This should be large enough that most strings @@ -43,13 +83,6 @@ extern pg_locale_t create_pg_locale_libc(Oid collid, MemoryContext context); -extern size_t strlower_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strtitle_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); -extern size_t strupper_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale); - static int strncoll_libc(const char *arg1, ssize_t len1, const char *arg2, ssize_t len2, pg_locale_t locale); @@ -85,6 +118,251 @@ static size_t strupper_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); +static bool +wc_isdigit_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isdigit_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isalpha_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isalpha_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isalnum_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isalnum_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isupper_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isupper_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_islower_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return islower_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isgraph_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isgraph_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isprint_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isprint_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_ispunct_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return ispunct_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isspace_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + return isspace_l((unsigned char) wc, locale->info.lt); +} + +static bool +wc_isdigit_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswdigit_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isalpha_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswalpha_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isalnum_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswalnum_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isupper_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswupper_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_islower_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswlower_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isgraph_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswgraph_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isprint_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswprint_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_ispunct_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswpunct_l((wint_t) wc, locale->info.lt); +} + +static bool +wc_isspace_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + return iswspace_l((wint_t) wc, locale->info.lt); +} + +static char +char_tolower_libc(unsigned char ch, pg_locale_t locale) +{ + Assert(pg_database_encoding_max_length() == 1); + return tolower_l(ch, locale->info.lt); +} + +static bool +char_is_cased_libc(char ch, pg_locale_t locale) +{ + bool is_multibyte = pg_database_encoding_max_length() > 1; + + if (is_multibyte && IS_HIGHBIT_SET(ch)) + return true; + else + return isalpha_l((unsigned char) ch, locale->info.lt); +} + +static pg_wchar +toupper_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + Assert(GetDatabaseEncoding() != PG_UTF8); + + /* force C behavior for ASCII characters, per comments above */ + if (locale->is_default && wc <= (pg_wchar) 127) + return pg_ascii_toupper((unsigned char) wc); + if (wc <= (pg_wchar) UCHAR_MAX) + return toupper_l((unsigned char) wc, locale->info.lt); + else + return wc; +} + +static pg_wchar +toupper_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + Assert(GetDatabaseEncoding() == PG_UTF8); + + /* force C behavior for ASCII characters, per comments above */ + if (locale->is_default && wc <= (pg_wchar) 127) + return pg_ascii_toupper((unsigned char) wc); + if (sizeof(wchar_t) >= 4 || wc <= (pg_wchar) 0xFFFF) + return towupper_l((wint_t) wc, locale->info.lt); + else + return wc; +} + +static pg_wchar +tolower_libc_sb(pg_wchar wc, pg_locale_t locale) +{ + Assert(GetDatabaseEncoding() != PG_UTF8); + + /* force C behavior for ASCII characters, per comments above */ + if (locale->is_default && wc <= (pg_wchar) 127) + return pg_ascii_tolower((unsigned char) wc); + if (wc <= (pg_wchar) UCHAR_MAX) + return tolower_l((unsigned char) wc, locale->info.lt); + else + return wc; +} + +static pg_wchar +tolower_libc_mb(pg_wchar wc, pg_locale_t locale) +{ + Assert(GetDatabaseEncoding() == PG_UTF8); + + /* force C behavior for ASCII characters, per comments above */ + if (locale->is_default && wc <= (pg_wchar) 127) + return pg_ascii_tolower((unsigned char) wc); + if (sizeof(wchar_t) >= 4 || wc <= (pg_wchar) 0xFFFF) + return towlower_l((wint_t) wc, locale->info.lt); + else + return wc; +} + +static const struct ctype_methods ctype_methods_libc_sb = { + .strlower = strlower_libc_sb, + .strtitle = strtitle_libc_sb, + .strupper = strupper_libc_sb, + .wc_isdigit = wc_isdigit_libc_sb, + .wc_isalpha = wc_isalpha_libc_sb, + .wc_isalnum = wc_isalnum_libc_sb, + .wc_isupper = wc_isupper_libc_sb, + .wc_islower = wc_islower_libc_sb, + .wc_isgraph = wc_isgraph_libc_sb, + .wc_isprint = wc_isprint_libc_sb, + .wc_ispunct = wc_ispunct_libc_sb, + .wc_isspace = wc_isspace_libc_sb, + .char_is_cased = char_is_cased_libc, + .char_tolower = char_tolower_libc, + .wc_toupper = toupper_libc_sb, + .wc_tolower = tolower_libc_sb, + .max_chr = UCHAR_MAX, +}; + +/* + * Non-UTF8 multibyte encodings use multibyte semantics for case mapping, but + * single-byte semantics for pattern matching. + */ +static const struct ctype_methods ctype_methods_libc_other_mb = { + .strlower = strlower_libc_mb, + .strtitle = strtitle_libc_mb, + .strupper = strupper_libc_mb, + .wc_isdigit = wc_isdigit_libc_sb, + .wc_isalpha = wc_isalpha_libc_sb, + .wc_isalnum = wc_isalnum_libc_sb, + .wc_isupper = wc_isupper_libc_sb, + .wc_islower = wc_islower_libc_sb, + .wc_isgraph = wc_isgraph_libc_sb, + .wc_isprint = wc_isprint_libc_sb, + .wc_ispunct = wc_ispunct_libc_sb, + .wc_isspace = wc_isspace_libc_sb, + .char_is_cased = char_is_cased_libc, + .char_tolower = char_tolower_libc, + .wc_toupper = toupper_libc_sb, + .wc_tolower = tolower_libc_sb, + .max_chr = UCHAR_MAX, +}; + +static const struct ctype_methods ctype_methods_libc_utf8 = { + .strlower = strlower_libc_mb, + .strtitle = strtitle_libc_mb, + .strupper = strupper_libc_mb, + .wc_isdigit = wc_isdigit_libc_mb, + .wc_isalpha = wc_isalpha_libc_mb, + .wc_isalnum = wc_isalnum_libc_mb, + .wc_isupper = wc_isupper_libc_mb, + .wc_islower = wc_islower_libc_mb, + .wc_isgraph = wc_isgraph_libc_mb, + .wc_isprint = wc_isprint_libc_mb, + .wc_ispunct = wc_ispunct_libc_mb, + .wc_isspace = wc_isspace_libc_mb, + .char_is_cased = char_is_cased_libc, + .char_tolower = char_tolower_libc, + .wc_toupper = toupper_libc_mb, + .wc_tolower = tolower_libc_mb, +}; + static const struct collate_methods collate_methods_libc = { .strncoll = strncoll_libc, .strnxfrm = strnxfrm_libc, @@ -119,36 +397,6 @@ static const struct collate_methods collate_methods_libc_win32_utf8 = { }; #endif -size_t -strlower_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale) -{ - if (pg_database_encoding_max_length() > 1) - return strlower_libc_mb(dst, dstsize, src, srclen, locale); - else - return strlower_libc_sb(dst, dstsize, src, srclen, locale); -} - -size_t -strtitle_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale) -{ - if (pg_database_encoding_max_length() > 1) - return strtitle_libc_mb(dst, dstsize, src, srclen, locale); - else - return strtitle_libc_sb(dst, dstsize, src, srclen, locale); -} - -size_t -strupper_libc(char *dst, size_t dstsize, const char *src, - ssize_t srclen, pg_locale_t locale) -{ - if (pg_database_encoding_max_length() > 1) - return strupper_libc_mb(dst, dstsize, src, srclen, locale); - else - return strupper_libc_sb(dst, dstsize, src, srclen, locale); -} - static size_t strlower_libc_sb(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) @@ -481,6 +729,15 @@ create_pg_locale_libc(Oid collid, MemoryContext context) #endif result->collate = &collate_methods_libc; } + if (!result->ctype_is_c) + { + if (GetDatabaseEncoding() == PG_UTF8) + result->ctype = &ctype_methods_libc_utf8; + else if (pg_database_encoding_max_length() > 1) + result->ctype = &ctype_methods_libc_other_mb; + else + result->ctype = &ctype_methods_libc_sb; + } return result; } diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h index 7b8cbf58d2c..0f497fa8ce2 100644 --- a/src/include/utils/pg_locale.h +++ b/src/include/utils/pg_locale.h @@ -12,6 +12,8 @@ #ifndef _PG_LOCALE_ #define _PG_LOCALE_ +#include "mb/pg_wchar.h" + #ifdef USE_ICU #include #endif @@ -77,6 +79,52 @@ struct collate_methods bool strxfrm_is_safe; }; +struct ctype_methods +{ + /* case mapping: LOWER()/INITCAP()/UPPER() */ + size_t (*strlower) (char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + size_t (*strtitle) (char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + size_t (*strupper) (char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + size_t (*strfold) (char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + + /* required */ + bool (*wc_isdigit) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isalpha) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isalnum) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isupper) (pg_wchar wc, pg_locale_t locale); + bool (*wc_islower) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isgraph) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isprint) (pg_wchar wc, pg_locale_t locale); + bool (*wc_ispunct) (pg_wchar wc, pg_locale_t locale); + bool (*wc_isspace) (pg_wchar wc, pg_locale_t locale); + pg_wchar (*wc_toupper) (pg_wchar wc, pg_locale_t locale); + pg_wchar (*wc_tolower) (pg_wchar wc, pg_locale_t locale); + + /* required */ + bool (*char_is_cased) (char ch, pg_locale_t locale); + + /* + * Optional. If defined, will only be called for single-byte encodings. If + * not defined, or if the encoding is multibyte, will fall back to + * pg_strlower(). + */ + char (*char_tolower) (unsigned char ch, pg_locale_t locale); + + /* + * For regex and pattern matching efficiency, the maximum char value + * supported by the above methods. If zero, limit is set by regex code. + */ + pg_wchar max_chr; +}; + /* * We use a discriminated union to hold either a locale_t or an ICU collator. * pg_locale_t is occasionally checked for truth, so make it a pointer. @@ -102,6 +150,7 @@ struct pg_locale_struct bool is_default; const struct collate_methods *collate; /* NULL if collate_is_c */ + const struct ctype_methods *ctype; /* NULL if ctype_is_c */ union { @@ -125,6 +174,10 @@ extern void init_database_collation(void); extern pg_locale_t pg_newlocale_from_collation(Oid collid); extern char *get_collation_actual_version(char collprovider, const char *collcollate); + +extern bool char_is_cased(char ch, pg_locale_t locale); +extern bool char_tolower_enabled(pg_locale_t locale); +extern char char_tolower(unsigned char ch, pg_locale_t locale); extern size_t pg_strlower(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a8346cda633..eea8f1eee6b 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1872,7 +1872,6 @@ PGTargetServerType PGTernaryBool PGTransactionStatusType PGVerbosity -PG_Locale_Strategy PG_Lock_Status PG_init_t PGauthData -- 2.43.0