From 9d1c50e406099ebe82de8a8e03d9cb2f564d76eb Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Fri, 7 Nov 2025 12:11:34 -0800 Subject: [PATCH v10 04/11] Allow pg_locale_t APIs to work when ctype_is_c. Previously, the caller needed to check ctype_is_c first for some routines and not others. Now, the APIs consistently work, and the caller can just check ctype_is_c for optimization purposes. Discussion: https://postgr.es/m/450ceb6260cad30d7afdf155d991a9caafee7c0d.camel@j-davis.com Reviewed-by: Chao Li --- src/backend/utils/adt/like_support.c | 34 ++++------- src/backend/utils/adt/pg_locale.c | 78 ++++++++++++++++++++++++-- src/backend/utils/adt/pg_locale_libc.c | 6 ++ 3 files changed, 88 insertions(+), 30 deletions(-) diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c index 999f23f86d5..0debccfa67b 100644 --- a/src/backend/utils/adt/like_support.c +++ b/src/backend/utils/adt/like_support.c @@ -99,8 +99,6 @@ static Selectivity like_selectivity(const char *patt, int pattlen, static Selectivity regex_selectivity(const char *patt, int pattlen, bool case_insensitive, int fixed_prefix_len); -static int pattern_char_isalpha(char c, bool is_multibyte, - pg_locale_t locale); static Const *make_greater_string(const Const *str_const, FmgrInfo *ltproc, Oid collation); static Datum string_to_datum(const char *str, Oid datatype); @@ -995,7 +993,6 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation, Oid typeid = patt_const->consttype; int pos, match_pos; - bool is_multibyte = (pg_database_encoding_max_length() > 1); pg_locale_t locale = 0; /* the right-hand const is type text or bytea */ @@ -1055,9 +1052,16 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation, break; } - /* Stop if case-varying character (it's sort of a wildcard) */ - if (case_insensitive && - pattern_char_isalpha(patt[pos], is_multibyte, locale)) + /* + * Stop if case-varying character (it's sort of a wildcard). + * + * In multibyte character sets or with non-libc providers, we can't + * use isalpha, and it does not seem worth trying to convert to + * wchar_t or char32_t. Instead, just pass the single byte to the + * provider, which will assume any non-ASCII char is potentially + * case-varying. + */ + if (case_insensitive && char_is_cased(patt[pos], locale)) break; match[match_pos++] = patt[pos]; @@ -1481,24 +1485,6 @@ regex_selectivity(const char *patt, int pattlen, bool case_insensitive, return sel; } -/* - * Check whether char is a letter (and, hence, subject to case-folding) - * - * In multibyte character sets or with ICU, we can't use isalpha, and it does - * not seem worth trying to convert to wchar_t to use iswalpha or u_isalpha. - * Instead, just assume any non-ASCII char is potentially case-varying, and - * hard-wire knowledge of which ASCII chars are letters. - */ -static int -pattern_char_isalpha(char c, bool is_multibyte, - pg_locale_t locale) -{ - if (locale->ctype_is_c) - return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); - else - return char_is_cased(c, locale); -} - /* * For bytea, the increment function need only increment the current byte diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index b14c7837938..48f9d44a5f7 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -1257,35 +1257,99 @@ get_collation_actual_version(char collprovider, const char *collcollate) return collversion; } +/* lowercasing/casefolding in C locale */ +static size_t +strlower_c(char *dst, size_t dstsize, const char *src, ssize_t srclen) +{ + int i; + + srclen = (srclen >= 0) ? srclen : strlen(src); + for (i = 0; i < srclen && i < dstsize; i++) + dst[i] = pg_ascii_tolower(src[i]); + if (i < dstsize) + dst[i] = '\0'; + return srclen; +} + +/* titlecasing in C locale */ +static size_t +strtitle_c(char *dst, size_t dstsize, const char *src, ssize_t srclen) +{ + bool wasalnum = false; + int i; + + srclen = (srclen >= 0) ? srclen : strlen(src); + for (i = 0; i < srclen && i < dstsize; i++) + { + char c = src[i]; + + if (wasalnum) + dst[i] = pg_ascii_tolower(c); + else + dst[i] = pg_ascii_toupper(c); + + wasalnum = ((c >= '0' && c <= '9') || + (c >= 'A' && c <= 'Z') || + (c >= 'a' && c <= 'z')); + } + if (i < dstsize) + dst[i] = '\0'; + return srclen; +} + +/* uppercasing in C locale */ +static size_t +strupper_c(char *dst, size_t dstsize, const char *src, ssize_t srclen) +{ + int i; + + srclen = (srclen >= 0) ? srclen : strlen(src); + for (i = 0; i < srclen && i < dstsize; i++) + dst[i] = pg_ascii_toupper(src[i]); + if (i < dstsize) + dst[i] = '\0'; + return srclen; +} + size_t pg_strlower(char *dst, size_t dstsize, const char *src, ssize_t srclen, pg_locale_t locale) { - return locale->ctype->strlower(dst, dstsize, src, srclen, locale); + if (locale->ctype == NULL) + return strlower_c(dst, dstsize, src, srclen); + else + 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) { - return locale->ctype->strtitle(dst, dstsize, src, srclen, locale); + if (locale->ctype == NULL) + return strtitle_c(dst, dstsize, src, srclen); + else + 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) { - return locale->ctype->strupper(dst, dstsize, src, srclen, locale); + if (locale->ctype == NULL) + return strupper_c(dst, dstsize, src, srclen); + else + 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->ctype->strfold) - return locale->ctype->strfold(dst, dstsize, src, srclen, locale); + /* in the C locale, casefolding is the same as lowercasing */ + if (locale->ctype == NULL) + return strlower_c(dst, dstsize, src, srclen); else - return locale->ctype->strlower(dst, dstsize, src, srclen, locale); + return locale->ctype->strfold(dst, dstsize, src, srclen, locale); } /* @@ -1560,6 +1624,8 @@ pg_towlower(pg_wchar wc, pg_locale_t locale) bool char_is_cased(char ch, pg_locale_t locale) { + if (locale->ctype == NULL) + return (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z'); return locale->ctype->char_is_cased(ch, locale); } diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c index 716f005066a..26ba1be73f1 100644 --- a/src/backend/utils/adt/pg_locale_libc.c +++ b/src/backend/utils/adt/pg_locale_libc.c @@ -326,6 +326,8 @@ static const struct ctype_methods ctype_methods_libc_sb = { .strlower = strlower_libc_sb, .strtitle = strtitle_libc_sb, .strupper = strupper_libc_sb, + /* in libc, casefolding is the same as lowercasing */ + .strfold = strlower_libc_sb, .wc_isdigit = wc_isdigit_libc_sb, .wc_isalpha = wc_isalpha_libc_sb, .wc_isalnum = wc_isalnum_libc_sb, @@ -351,6 +353,8 @@ static const struct ctype_methods ctype_methods_libc_other_mb = { .strlower = strlower_libc_mb, .strtitle = strtitle_libc_mb, .strupper = strupper_libc_mb, + /* in libc, casefolding is the same as lowercasing */ + .strfold = strlower_libc_mb, .wc_isdigit = wc_isdigit_libc_sb, .wc_isalpha = wc_isalpha_libc_sb, .wc_isalnum = wc_isalnum_libc_sb, @@ -372,6 +376,8 @@ static const struct ctype_methods ctype_methods_libc_utf8 = { .strlower = strlower_libc_mb, .strtitle = strtitle_libc_mb, .strupper = strupper_libc_mb, + /* in libc, casefolding is the same as lowercasing */ + .strfold = strlower_libc_mb, .wc_isdigit = wc_isdigit_libc_mb, .wc_isalpha = wc_isalpha_libc_mb, .wc_isalnum = wc_isalnum_libc_mb, -- 2.43.0