From 3f2cca2d06b46b169d43a89a4ecc71c4dc2f07f9 Mon Sep 17 00:00:00 2001 From: Andreas Karlsson Date: Fri, 29 Nov 2024 04:44:09 +0100 Subject: [PATCH v9 03/11] Move code for collation version into provider specific files --- src/backend/utils/adt/pg_locale.c | 106 +++------------------- src/backend/utils/adt/pg_locale_builtin.c | 24 +++++ src/backend/utils/adt/pg_locale_icu.c | 17 ++++ src/backend/utils/adt/pg_locale_libc.c | 74 +++++++++++++++ 4 files changed, 126 insertions(+), 95 deletions(-) diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 5388057503c..ebad2d530fa 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -69,10 +69,6 @@ #include "utils/pg_locale.h" #include "utils/syscache.h" -#ifdef __GLIBC__ -#include -#endif - #ifdef WIN32 #include #endif @@ -91,6 +87,7 @@ /* pg_locale_builtin.c */ extern pg_locale_t create_pg_locale_builtin(Oid collid, MemoryContext context); +extern char *get_collation_actual_version_builtin(const char *collcollate); /* pg_locale_icu.c */ extern pg_locale_t create_pg_locale_icu(Oid collid, MemoryContext context); @@ -105,6 +102,7 @@ extern size_t strnxfrm_icu(char *dest, size_t destsize, extern size_t strnxfrm_prefix_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); +extern char *get_collation_actual_version_icu(const char *collcollate); #endif /* pg_locale_libc.c */ @@ -115,6 +113,7 @@ extern int strncoll_libc(const char *arg1, ssize_t len1, extern size_t strnxfrm_libc(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); +extern char *get_collation_actual_version_libc(const char *collcollate); /* GUC settings */ char *locale_messages; @@ -1367,100 +1366,17 @@ get_collation_actual_version(char collprovider, const char *collcollate) { char *collversion = NULL; - /* - * The only two supported locales (C and C.UTF-8) are both based on memcmp - * and are not expected to change, but track the version anyway. - * - * Note that the character semantics may change for some locales, but the - * collation version only tracks changes to sort order. - */ if (collprovider == COLLPROVIDER_BUILTIN) - { - if (strcmp(collcollate, "C") == 0) - return "1"; - else if (strcmp(collcollate, "C.UTF-8") == 0) - return "1"; - else - ereport(ERROR, - (errcode(ERRCODE_WRONG_OBJECT_TYPE), - errmsg("invalid locale name \"%s\" for builtin provider", - collcollate))); - } - + collversion = get_collation_actual_version_builtin(collcollate); #ifdef USE_ICU - if (collprovider == COLLPROVIDER_ICU) - { - UCollator *collator; - UVersionInfo versioninfo; - char buf[U_MAX_VERSION_STRING_LENGTH]; - - collator = pg_ucol_open(collcollate); - - ucol_getVersion(collator, versioninfo); - ucol_close(collator); - - u_versionToString(versioninfo, buf); - collversion = pstrdup(buf); - } - else -#endif - if (collprovider == COLLPROVIDER_LIBC && - pg_strcasecmp("C", collcollate) != 0 && - pg_strncasecmp("C.", collcollate, 2) != 0 && - pg_strcasecmp("POSIX", collcollate) != 0) - { -#if defined(__GLIBC__) - /* Use the glibc version because we don't have anything better. */ - collversion = pstrdup(gnu_get_libc_version()); -#elif defined(LC_VERSION_MASK) - locale_t loc; - - /* Look up FreeBSD collation version. */ - loc = newlocale(LC_COLLATE_MASK, collcollate, NULL); - if (loc) - { - collversion = - pstrdup(querylocale(LC_COLLATE_MASK | LC_VERSION_MASK, loc)); - freelocale(loc); - } - else - ereport(ERROR, - (errmsg("could not load locale \"%s\"", collcollate))); -#elif defined(WIN32) - /* - * If we are targeting Windows Vista and above, we can ask for a name - * given a collation name (earlier versions required a location code - * that we don't have). - */ - NLSVERSIONINFOEX version = {sizeof(NLSVERSIONINFOEX)}; - WCHAR wide_collcollate[LOCALE_NAME_MAX_LENGTH]; - - MultiByteToWideChar(CP_ACP, 0, collcollate, -1, wide_collcollate, - LOCALE_NAME_MAX_LENGTH); - if (!GetNLSVersionEx(COMPARE_STRING, wide_collcollate, &version)) - { - /* - * GetNLSVersionEx() wants a language tag such as "en-US", not a - * locale name like "English_United States.1252". Until those - * values can be prevented from entering the system, or 100% - * reliably converted to the more useful tag format, tolerate the - * resulting error and report that we have no version data. - */ - if (GetLastError() == ERROR_INVALID_PARAMETER) - return NULL; - - ereport(ERROR, - (errmsg("could not get collation version for locale \"%s\": error code %lu", - collcollate, - GetLastError()))); - } - collversion = psprintf("%lu.%lu,%lu.%lu", - (version.dwNLSVersion >> 8) & 0xFFFF, - version.dwNLSVersion & 0xFF, - (version.dwDefinedVersion >> 8) & 0xFFFF, - version.dwDefinedVersion & 0xFF); + else if (collprovider == COLLPROVIDER_ICU) + collversion = get_collation_actual_version_icu(collcollate); #endif - } + else if (collprovider == COLLPROVIDER_LIBC) + collversion = get_collation_actual_version_libc(collcollate); + else + /* shouldn't happen */ + PGLOCALE_SUPPORT_ERROR(collprovider); return collversion; } diff --git a/src/backend/utils/adt/pg_locale_builtin.c b/src/backend/utils/adt/pg_locale_builtin.c index 4246971a4d8..2e2d78758e1 100644 --- a/src/backend/utils/adt/pg_locale_builtin.c +++ b/src/backend/utils/adt/pg_locale_builtin.c @@ -22,6 +22,7 @@ extern pg_locale_t create_pg_locale_builtin(Oid collid, MemoryContext context); +extern char *get_collation_actual_version_builtin(const char *collcollate); pg_locale_t create_pg_locale_builtin(Oid collid, MemoryContext context) @@ -68,3 +69,26 @@ create_pg_locale_builtin(Oid collid, MemoryContext context) return result; } + +char * +get_collation_actual_version_builtin(const char *collcollate) +{ + /* + * The only two supported locales (C and C.UTF-8) are both based on memcmp + * and are not expected to change, but track the version anyway. + * + * Note that the character semantics may change for some locales, but the + * collation version only tracks changes to sort order. + */ + if (strcmp(collcollate, "C") == 0) + return "1"; + else if (strcmp(collcollate, "C.UTF-8") == 0) + return "1"; + else + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("invalid locale name \"%s\" for builtin provider", + collcollate))); + + return NULL; /* keep compiler quiet */ +} diff --git a/src/backend/utils/adt/pg_locale_icu.c b/src/backend/utils/adt/pg_locale_icu.c index 2c6b950ec18..158c00a8130 100644 --- a/src/backend/utils/adt/pg_locale_icu.c +++ b/src/backend/utils/adt/pg_locale_icu.c @@ -61,6 +61,7 @@ extern size_t strnxfrm_icu(char *dest, size_t destsize, extern size_t strnxfrm_prefix_icu(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); +extern char *get_collation_actual_version_icu(const char *collcollate); /* * Converter object for converting between ICU's UChar strings and C strings @@ -446,6 +447,22 @@ strnxfrm_prefix_icu(char *dest, size_t destsize, return result; } +char * +get_collation_actual_version_icu(const char *collcollate) +{ + UCollator *collator; + UVersionInfo versioninfo; + char buf[U_MAX_VERSION_STRING_LENGTH]; + + collator = pg_ucol_open(collcollate); + + ucol_getVersion(collator, versioninfo); + ucol_close(collator); + + u_versionToString(versioninfo, buf); + return pstrdup(buf); +} + /* * Convert a string in the database encoding into a string of UChars. * diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c index 374ac37ba0a..fdf5f784551 100644 --- a/src/backend/utils/adt/pg_locale_libc.c +++ b/src/backend/utils/adt/pg_locale_libc.c @@ -22,6 +22,14 @@ #include "utils/pg_locale.h" #include "utils/syscache.h" +#ifdef __GLIBC__ +#include +#endif + +#ifdef WIN32 +#include +#endif + /* * 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 @@ -38,6 +46,7 @@ extern int strncoll_libc(const char *arg1, ssize_t len1, extern size_t strnxfrm_libc(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale); +extern char *get_collation_actual_version_libc(const char *collcollate); static locale_t make_libc_collator(const char *collate, const char *ctype); static void report_newlocale_failure(const char *localename); @@ -283,6 +292,71 @@ strnxfrm_libc(char *dest, size_t destsize, const char *src, ssize_t srclen, return result; } +char * +get_collation_actual_version_libc(const char *collcollate) +{ + char *collversion = NULL; + + if (pg_strcasecmp("C", collcollate) != 0 && + pg_strncasecmp("C.", collcollate, 2) != 0 && + pg_strcasecmp("POSIX", collcollate) != 0) + { +#if defined(__GLIBC__) + /* Use the glibc version because we don't have anything better. */ + collversion = pstrdup(gnu_get_libc_version()); +#elif defined(LC_VERSION_MASK) + locale_t loc; + + /* Look up FreeBSD collation version. */ + loc = newlocale(LC_COLLATE_MASK, collcollate, NULL); + if (loc) + { + collversion = + pstrdup(querylocale(LC_COLLATE_MASK | LC_VERSION_MASK, loc)); + freelocale(loc); + } + else + ereport(ERROR, + (errmsg("could not load locale \"%s\"", collcollate))); +#elif defined(WIN32) + /* + * If we are targeting Windows Vista and above, we can ask for a name + * given a collation name (earlier versions required a location code + * that we don't have). + */ + NLSVERSIONINFOEX version = {sizeof(NLSVERSIONINFOEX)}; + WCHAR wide_collcollate[LOCALE_NAME_MAX_LENGTH]; + + MultiByteToWideChar(CP_ACP, 0, collcollate, -1, wide_collcollate, + LOCALE_NAME_MAX_LENGTH); + if (!GetNLSVersionEx(COMPARE_STRING, wide_collcollate, &version)) + { + /* + * GetNLSVersionEx() wants a language tag such as "en-US", not a + * locale name like "English_United States.1252". Until those + * values can be prevented from entering the system, or 100% + * reliably converted to the more useful tag format, tolerate the + * resulting error and report that we have no version data. + */ + if (GetLastError() == ERROR_INVALID_PARAMETER) + return NULL; + + ereport(ERROR, + (errmsg("could not get collation version for locale \"%s\": error code %lu", + collcollate, + GetLastError()))); + } + collversion = psprintf("%lu.%lu,%lu.%lu", + (version.dwNLSVersion >> 8) & 0xFFFF, + version.dwNLSVersion & 0xFF, + (version.dwDefinedVersion >> 8) & 0xFFFF, + version.dwDefinedVersion & 0xFF); +#endif + } + + return collversion; +} + /* * strncoll_libc_win32_utf8 * -- 2.45.2