From 3b208a189ecc0d6942c357f8b616ad0aa9ee5848 Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Wed, 5 Jun 2024 15:22:04 -0700 Subject: [PATCH v2 5/7] Avoid setlocale() in lc_collate_is_c() and lc_ctype_is_c(). Store the collate and ctype strings in the pg_locale_t structure, which requires some minor refactoring. --- src/backend/regex/regc_pg_locale.c | 44 ++++++++++++++-------------- src/backend/utils/adt/formatting.c | 20 ++++++------- src/backend/utils/adt/like.c | 2 +- src/backend/utils/adt/like_support.c | 2 +- src/backend/utils/adt/pg_locale.c | 30 +++++++++++-------- src/include/utils/pg_locale.h | 7 ++++- 6 files changed, 57 insertions(+), 48 deletions(-) diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c index 85f3238eb0..1e180b844f 100644 --- a/src/backend/regex/regc_pg_locale.c +++ b/src/backend/regex/regc_pg_locale.c @@ -309,11 +309,11 @@ pg_wc_isdigit(pg_wchar c) isdigit((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswdigit_l((wint_t) c, pg_regex_locale->info.lt); + return iswdigit_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isdigit_l((unsigned char) c, pg_regex_locale->info.lt)); + isdigit_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -343,11 +343,11 @@ pg_wc_isalpha(pg_wchar c) isalpha((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswalpha_l((wint_t) c, pg_regex_locale->info.lt); + return iswalpha_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isalpha_l((unsigned char) c, pg_regex_locale->info.lt)); + isalpha_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -377,11 +377,11 @@ pg_wc_isalnum(pg_wchar c) isalnum((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswalnum_l((wint_t) c, pg_regex_locale->info.lt); + return iswalnum_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isalnum_l((unsigned char) c, pg_regex_locale->info.lt)); + isalnum_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -420,11 +420,11 @@ pg_wc_isupper(pg_wchar c) isupper((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswupper_l((wint_t) c, pg_regex_locale->info.lt); + return iswupper_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isupper_l((unsigned char) c, pg_regex_locale->info.lt)); + isupper_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -454,11 +454,11 @@ pg_wc_islower(pg_wchar c) islower((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswlower_l((wint_t) c, pg_regex_locale->info.lt); + return iswlower_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - islower_l((unsigned char) c, pg_regex_locale->info.lt)); + islower_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -488,11 +488,11 @@ pg_wc_isgraph(pg_wchar c) isgraph((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswgraph_l((wint_t) c, pg_regex_locale->info.lt); + return iswgraph_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isgraph_l((unsigned char) c, pg_regex_locale->info.lt)); + isgraph_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -522,11 +522,11 @@ pg_wc_isprint(pg_wchar c) isprint((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswprint_l((wint_t) c, pg_regex_locale->info.lt); + return iswprint_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isprint_l((unsigned char) c, pg_regex_locale->info.lt)); + isprint_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -556,11 +556,11 @@ pg_wc_ispunct(pg_wchar c) ispunct((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswpunct_l((wint_t) c, pg_regex_locale->info.lt); + return iswpunct_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - ispunct_l((unsigned char) c, pg_regex_locale->info.lt)); + ispunct_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -590,11 +590,11 @@ pg_wc_isspace(pg_wchar c) isspace((unsigned char) c)); case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return iswspace_l((wint_t) c, pg_regex_locale->info.lt); + return iswspace_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: return (c <= (pg_wchar) UCHAR_MAX && - isspace_l((unsigned char) c, pg_regex_locale->info.lt)); + isspace_l((unsigned char) c, pg_regex_locale->info.libc.lt)); break; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -632,11 +632,11 @@ pg_wc_toupper(pg_wchar c) return c; case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return towupper_l((wint_t) c, pg_regex_locale->info.lt); + return towupper_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: if (c <= (pg_wchar) UCHAR_MAX) - return toupper_l((unsigned char) c, pg_regex_locale->info.lt); + return toupper_l((unsigned char) c, pg_regex_locale->info.libc.lt); return c; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU @@ -674,11 +674,11 @@ pg_wc_tolower(pg_wchar c) return c; case PG_REGEX_LOCALE_WIDE_L: if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF) - return towlower_l((wint_t) c, pg_regex_locale->info.lt); + return towlower_l((wint_t) c, pg_regex_locale->info.libc.lt); /* FALL THRU */ case PG_REGEX_LOCALE_1BYTE_L: if (c <= (pg_wchar) UCHAR_MAX) - return tolower_l((unsigned char) c, pg_regex_locale->info.lt); + return tolower_l((unsigned char) c, pg_regex_locale->info.libc.lt); return c; case PG_REGEX_LOCALE_ICU: #ifdef USE_ICU diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c index 8736ada4be..2c3a28ca25 100644 --- a/src/backend/utils/adt/formatting.c +++ b/src/backend/utils/adt/formatting.c @@ -1732,7 +1732,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid) for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { if (mylocale) - workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.lt); + workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.libc.lt); else workspace[curr_char] = towlower(workspace[curr_char]); } @@ -1763,7 +1763,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid) for (p = result; *p; p++) { if (mylocale) - *p = tolower_l((unsigned char) *p, mylocale->info.lt); + *p = tolower_l((unsigned char) *p, mylocale->info.libc.lt); else *p = pg_tolower((unsigned char) *p); } @@ -1880,7 +1880,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid) for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { if (mylocale) - workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.lt); + workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.libc.lt); else workspace[curr_char] = towupper(workspace[curr_char]); } @@ -1911,7 +1911,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid) for (p = result; *p; p++) { if (mylocale) - *p = toupper_l((unsigned char) *p, mylocale->info.lt); + *p = toupper_l((unsigned char) *p, mylocale->info.libc.lt); else *p = pg_toupper((unsigned char) *p); } @@ -2084,10 +2084,10 @@ str_initcap(const char *buff, size_t nbytes, Oid collid) if (mylocale) { if (wasalnum) - workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.lt); + workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.libc.lt); else - workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.lt); - wasalnum = iswalnum_l(workspace[curr_char], mylocale->info.lt); + workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.libc.lt); + wasalnum = iswalnum_l(workspace[curr_char], mylocale->info.libc.lt); } else { @@ -2127,10 +2127,10 @@ str_initcap(const char *buff, size_t nbytes, Oid collid) if (mylocale) { if (wasalnum) - *p = tolower_l((unsigned char) *p, mylocale->info.lt); + *p = tolower_l((unsigned char) *p, mylocale->info.libc.lt); else - *p = toupper_l((unsigned char) *p, mylocale->info.lt); - wasalnum = isalnum_l((unsigned char) *p, mylocale->info.lt); + *p = toupper_l((unsigned char) *p, mylocale->info.libc.lt); + wasalnum = isalnum_l((unsigned char) *p, mylocale->info.libc.lt); } else { diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c index 0807b89b17..4d9a207816 100644 --- a/src/backend/utils/adt/like.c +++ b/src/backend/utils/adt/like.c @@ -96,7 +96,7 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c) if (locale_is_c) return pg_ascii_tolower(c); else if (locale) - return tolower_l(c, locale->info.lt); + return tolower_l(c, locale->info.libc.lt); else return pg_tolower(c); } diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c index 2635050861..6a1c64176d 100644 --- a/src/backend/utils/adt/like_support.c +++ b/src/backend/utils/adt/like_support.c @@ -1509,7 +1509,7 @@ pattern_char_isalpha(char c, bool is_multibyte, return IS_HIGHBIT_SET(c) || (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); else if (locale && locale->provider == COLLPROVIDER_LIBC) - return isalpha_l((unsigned char) c, locale->info.lt); + return isalpha_l((unsigned char) c, locale->info.libc.lt); else return isalpha((unsigned char) c); } diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 2ffc551913..060dcbcb14 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -1350,9 +1350,7 @@ lc_collate_is_c(Oid collation) } else if (default_locale.provider == COLLPROVIDER_LIBC) { - localeptr = setlocale(LC_CTYPE, NULL); - if (!localeptr) - elog(ERROR, "invalid LC_CTYPE setting"); + localeptr = default_locale.info.libc.collate; } else elog(ERROR, "unexpected collation provider '%c'", @@ -1416,9 +1414,7 @@ lc_ctype_is_c(Oid collation) } else if (default_locale.provider == COLLPROVIDER_LIBC) { - localeptr = setlocale(LC_CTYPE, NULL); - if (!localeptr) - elog(ERROR, "invalid LC_CTYPE setting"); + localeptr = default_locale.info.libc.ctype; } else elog(ERROR, "unexpected collation provider '%c'", @@ -1629,7 +1625,11 @@ pg_init_database_collation() #endif } - default_locale.info.lt = loc; + default_locale.info.libc.collate = MemoryContextStrdup( + TopMemoryContext, datcollate); + default_locale.info.libc.ctype = MemoryContextStrdup( + TopMemoryContext, datctype); + default_locale.info.libc.lt = loc; } default_locale.provider = dbform->datlocprovider; @@ -1750,7 +1750,11 @@ pg_newlocale_from_collation(Oid collid) #endif } - result.info.lt = loc; + result.info.libc.collate = MemoryContextStrdup( + TopMemoryContext, collcollate); + result.info.libc.ctype = MemoryContextStrdup( + TopMemoryContext, collctype); + result.info.libc.lt = loc; } else if (collform->collprovider == COLLPROVIDER_ICU) { @@ -1990,7 +1994,7 @@ pg_strncoll_libc_win32_utf8(const char *arg1, size_t len1, const char *arg2, ((LPWSTR) a2p)[r] = 0; errno = 0; - result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.lt); + result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.libc.lt); if (result == 2147483647) /* _NLSCMPERROR; missing from mingw headers */ ereport(ERROR, (errmsg("could not compare Unicode strings: %m"))); @@ -2027,7 +2031,7 @@ pg_strcoll_libc(const char *arg1, const char *arg2, pg_locale_t locale) } else #endif /* WIN32 */ - result = strcoll_l(arg1, arg2, locale->info.lt); + result = strcoll_l(arg1, arg2, locale->info.libc.lt); return result; } @@ -2252,7 +2256,7 @@ pg_strxfrm_libc(char *dest, const char *src, size_t destsize, Assert(locale->provider == COLLPROVIDER_LIBC); #ifdef TRUST_STRXFRM - return strxfrm_l(dest, src, destsize, locale->info.lt); + return strxfrm_l(dest, src, destsize, locale->info.libc.lt); #else /* shouldn't happen */ PGLOCALE_SUPPORT_ERROR(locale->provider); @@ -3185,7 +3189,7 @@ wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale) else { /* Use wcstombs_l for nondefault locales */ - result = wcstombs_l(to, from, tolen, locale->info.lt); + result = wcstombs_l(to, from, tolen, locale->info.libc.lt); } return result; @@ -3247,7 +3251,7 @@ char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen, else { /* Use mbstowcs_l for nondefault locales */ - result = mbstowcs_l(to, str, tolen, locale->info.lt); + result = mbstowcs_l(to, str, tolen, locale->info.libc.lt); } pfree(str); diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h index 3a9026e7b7..63b724dc1d 100644 --- a/src/include/utils/pg_locale.h +++ b/src/include/utils/pg_locale.h @@ -80,7 +80,12 @@ struct pg_locale_struct { const char *locale; } builtin; - locale_t lt; + struct + { + const char *collate; + const char *ctype; + locale_t lt; + } libc; #ifdef USE_ICU struct { -- 2.34.1