From de37bfb02dcc41c2e932a788ba10a05e5a539870 Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Mon, 1 May 2023 15:38:29 -0700 Subject: [PATCH v6 1/5] Introduce collation provider "none". Provides locale-unaware semantics that are implemented as fast byte operations in Postgres, independent of the operating system or any provider libraries. Equivalent (in semantics and implementation) to the libc provider with locale "C", except that LC_COLLATE and LC_CTYPE can be set independently. Use provider "none" for built-in collation "ucs_basic" instead of libc. --- doc/src/sgml/charset.sgml | 87 +++++++++++++++++++++----- doc/src/sgml/ref/create_collation.sgml | 2 +- doc/src/sgml/ref/create_database.sgml | 2 +- doc/src/sgml/ref/createdb.sgml | 2 +- doc/src/sgml/ref/initdb.sgml | 2 +- src/backend/catalog/pg_collation.c | 7 ++- src/backend/commands/collationcmds.c | 84 +++++++++++++++++++++---- src/backend/commands/dbcommands.c | 69 +++++++++++++++++--- src/backend/utils/adt/pg_locale.c | 27 +++++++- src/backend/utils/init/postinit.c | 10 ++- src/bin/initdb/initdb.c | 33 +++++++++- src/bin/initdb/t/001_initdb.pl | 29 +++++++++ src/bin/pg_dump/pg_dump.c | 8 ++- src/bin/pg_upgrade/t/002_pg_upgrade.pl | 18 +++++- src/bin/psql/describe.c | 2 +- src/bin/scripts/createdb.c | 2 +- src/bin/scripts/t/020_createdb.pl | 29 +++++++++ src/include/catalog/pg_collation.dat | 3 +- src/include/catalog/pg_collation.h | 3 + src/test/regress/expected/collate.out | 10 ++- src/test/regress/sql/collate.sql | 6 ++ 21 files changed, 373 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml index 9db14649aa..7a791a2b7c 100644 --- a/doc/src/sgml/charset.sgml +++ b/doc/src/sgml/charset.sgml @@ -342,22 +342,14 @@ initdb --locale=sv_SE Locale Providers - PostgreSQL supports multiple locale - providers. This specifies which library supplies the locale - data. One standard provider name is libc, which uses - the locales provided by the operating system C library. These are the - locales used by most tools provided by the operating system. Another - provider is icu, which uses the external - ICUICU library. ICU locales can - only be used if support for ICU was configured when PostgreSQL was built. + A locale provider specifies which library defines the locale behavior for + collations and character classifications. The commands and tools that select the locale settings, as described - above, each have an option to select the locale provider. The examples - shown earlier all use the libc provider, which is the - default. Here is an example to initialize a database cluster using the - ICU provider: + above, each have an option to select the locale provider. Here is an + example to initialize a database cluster using the ICU provider: initdb --locale-provider=icu --icu-locale=en @@ -370,12 +362,73 @@ initdb --locale-provider=icu --icu-locale=en - Which locale provider to use depends on individual requirements. For most - basic uses, either provider will give adequate results. For the libc - provider, it depends on what the operating system offers; some operating - systems are better than others. For advanced uses, ICU offers more locale - variants and customization options. + Regardless of the locale provider, the operating system is still used to + provide some locale-aware behavior, such as messages (see ). + + + The available locale providers are listed below. + + + + None + + The none provider uses simple built-in operations + which are not locale-aware. + + + The collation and character classification behavior is equivalent to + using the libc provider with locale + C, except that LC_COLLATE and + LC_CTYPE can be set independently. + + + + When using the none locale provider, behavior may + depend on the database encoding. + + + + + ICU + + The icu provider uses the external + ICUICU + library. PostgreSQL must have been configured + with support. + + + ICU provides collation and character classification behavior that is + independent of the operating system and database encoding, which is + preferable if you expect to transition to other platforms without any + change in results. LC_COLLATE and + LC_CTYPE can be set independently of the ICU locale. + + + + For the ICU provider, results may depend on the version of the ICU + library used, as it is updated to reflect changes in natural language + over time. + + + + + libc + + The libc provider uses the operating system's C + library. The collation and character classification behavior is + controlled by the settings LC_COLLATE and + LC_CTYPE, so they cannot be set independently. + + + + The same locale name may have different behavior on different platforms + when using the libc provider. + + + + ICU Locales diff --git a/doc/src/sgml/ref/create_collation.sgml b/doc/src/sgml/ref/create_collation.sgml index f6353da5c1..5489ae7413 100644 --- a/doc/src/sgml/ref/create_collation.sgml +++ b/doc/src/sgml/ref/create_collation.sgml @@ -120,7 +120,7 @@ CREATE COLLATION [ IF NOT EXISTS ] name FROM Specifies the provider to use for locale services associated with this - collation. Possible values are + collation. Possible values are none, icuICU (if the server was built with ICU support) or libc. libc is the default. See name Specifies the provider to use for the default collation in this - database. Possible values are + database. Possible values are none, icuICU (if the server was built with ICU support) or libc. By default, the provider is the same as that of the - + Specifies the locale provider for the database's default collation. diff --git a/doc/src/sgml/ref/initdb.sgml b/doc/src/sgml/ref/initdb.sgml index 87945b4b62..e604ab48b7 100644 --- a/doc/src/sgml/ref/initdb.sgml +++ b/doc/src/sgml/ref/initdb.sgml @@ -323,7 +323,7 @@ PostgreSQL documentation - + This option sets the locale provider for databases created in the new diff --git a/src/backend/catalog/pg_collation.c b/src/backend/catalog/pg_collation.c index fd022e6fc2..86b6ba2375 100644 --- a/src/backend/catalog/pg_collation.c +++ b/src/backend/catalog/pg_collation.c @@ -68,7 +68,12 @@ CollationCreate(const char *collname, Oid collnamespace, Assert(collname); Assert(collnamespace); Assert(collowner); - Assert((collcollate && collctype) || colliculocale); + Assert((collprovider == COLLPROVIDER_NONE && + !collcollate && !collctype && !colliculocale) || + (collprovider == COLLPROVIDER_LIBC && + collcollate && collctype && !colliculocale) || + (collprovider == COLLPROVIDER_ICU && + !collcollate && !collctype && colliculocale)); /* * Make sure there is no existing collation of same name & encoding. diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c index c91fe66d9b..aeaf6c419e 100644 --- a/src/backend/commands/collationcmds.c +++ b/src/backend/commands/collationcmds.c @@ -215,7 +215,9 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e if (collproviderstr) { - if (pg_strcasecmp(collproviderstr, "icu") == 0) + if (pg_strcasecmp(collproviderstr, "none") == 0) + collprovider = COLLPROVIDER_NONE; + else if (pg_strcasecmp(collproviderstr, "icu") == 0) collprovider = COLLPROVIDER_ICU; else if (pg_strcasecmp(collproviderstr, "libc") == 0) collprovider = COLLPROVIDER_LIBC; @@ -228,6 +230,13 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e else collprovider = COLLPROVIDER_LIBC; + if (collprovider == COLLPROVIDER_NONE + && (localeEl || lccollateEl || lcctypeEl)) + { + ereport(ERROR, + (errmsg("collation provider \"none\" does not support LOCALE, LC_COLLATE, or LC_CTYPE"))); + } + if (localeEl) { if (collprovider == COLLPROVIDER_LIBC) @@ -302,6 +311,16 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("ICU rules cannot be specified unless locale provider is ICU"))); + if (collprovider == COLLPROVIDER_NONE) + { + /* + * Behavior may be different in different encodings, so set + * collencoding to the current database encoding. No validation is + * required, because the "none" provider is compatible with any + * encoding. + */ + collencoding = GetDatabaseEncoding(); + } if (collprovider == COLLPROVIDER_ICU) { #ifdef USE_ICU @@ -331,7 +350,18 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e } if (!collversion) - collversion = get_collation_actual_version(collprovider, collprovider == COLLPROVIDER_ICU ? colliculocale : collcollate); + { + char *locale; + + if (collprovider == COLLPROVIDER_ICU) + locale = colliculocale; + else if (collprovider == COLLPROVIDER_LIBC) + locale = collcollate; + else + locale = NULL; /* COLLPROVIDER_NONE */ + + collversion = get_collation_actual_version(collprovider, locale); + } newoid = CollationCreate(collName, collNamespace, @@ -406,6 +436,7 @@ AlterCollation(AlterCollationStmt *stmt) Form_pg_collation collForm; Datum datum; bool isnull; + char *locale; char *oldversion; char *newversion; ObjectAddress address; @@ -430,8 +461,20 @@ AlterCollation(AlterCollationStmt *stmt) datum = SysCacheGetAttr(COLLOID, tup, Anum_pg_collation_collversion, &isnull); oldversion = isnull ? NULL : TextDatumGetCString(datum); - datum = SysCacheGetAttrNotNull(COLLOID, tup, collForm->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colliculocale : Anum_pg_collation_collcollate); - newversion = get_collation_actual_version(collForm->collprovider, TextDatumGetCString(datum)); + if (collForm->collprovider == COLLPROVIDER_ICU) + { + datum = SysCacheGetAttrNotNull(COLLOID, tup, Anum_pg_collation_colliculocale); + locale = TextDatumGetCString(datum); + } + else if (collForm->collprovider == COLLPROVIDER_LIBC) + { + datum = SysCacheGetAttrNotNull(COLLOID, tup, Anum_pg_collation_collcollate); + locale = TextDatumGetCString(datum); + } + else + locale = NULL; /* COLLPROVIDER_NONE */ + + newversion = get_collation_actual_version(collForm->collprovider, locale); /* cannot change from NULL to non-NULL or vice versa */ if ((!oldversion && newversion) || (oldversion && !newversion)) @@ -494,11 +537,18 @@ pg_collation_actual_version(PG_FUNCTION_ARGS) provider = ((Form_pg_database) GETSTRUCT(dbtup))->datlocprovider; - datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup, - provider == COLLPROVIDER_ICU ? - Anum_pg_database_daticulocale : Anum_pg_database_datcollate); - - locale = TextDatumGetCString(datum); + if (provider == COLLPROVIDER_ICU) + { + datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup, Anum_pg_database_daticulocale); + locale = TextDatumGetCString(datum); + } + else if (provider == COLLPROVIDER_LIBC) + { + datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup, Anum_pg_database_datcollate); + locale = TextDatumGetCString(datum); + } + else + locale = NULL; /* COLLPROVIDER_NONE */ ReleaseSysCache(dbtup); } @@ -514,11 +564,19 @@ pg_collation_actual_version(PG_FUNCTION_ARGS) provider = ((Form_pg_collation) GETSTRUCT(colltp))->collprovider; Assert(provider != COLLPROVIDER_DEFAULT); - datum = SysCacheGetAttrNotNull(COLLOID, colltp, - provider == COLLPROVIDER_ICU ? - Anum_pg_collation_colliculocale : Anum_pg_collation_collcollate); - locale = TextDatumGetCString(datum); + if (provider == COLLPROVIDER_ICU) + { + datum = SysCacheGetAttrNotNull(COLLOID, colltp, Anum_pg_collation_colliculocale); + locale = TextDatumGetCString(datum); + } + else if (provider == COLLPROVIDER_LIBC) + { + datum = SysCacheGetAttrNotNull(COLLOID, colltp, Anum_pg_collation_collcollate); + locale = TextDatumGetCString(datum); + } + else + locale = NULL; /* COLLPROVIDER_NONE */ ReleaseSysCache(colltp); } diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index 2e242eeff2..9e73f54803 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -909,7 +909,9 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt) { char *locproviderstr = defGetString(dlocprovider); - if (pg_strcasecmp(locproviderstr, "icu") == 0) + if (pg_strcasecmp(locproviderstr, "none") == 0) + dblocprovider = COLLPROVIDER_NONE; + else if (pg_strcasecmp(locproviderstr, "icu") == 0) dblocprovider = COLLPROVIDER_ICU; else if (pg_strcasecmp(locproviderstr, "libc") == 0) dblocprovider = COLLPROVIDER_LIBC; @@ -1177,9 +1179,17 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt) */ if (src_collversion && !dcollversion) { - char *actual_versionstr; + char *actual_versionstr; + char *locale; - actual_versionstr = get_collation_actual_version(dblocprovider, dblocprovider == COLLPROVIDER_ICU ? dbiculocale : dbcollate); + if (dblocprovider == COLLPROVIDER_ICU) + locale = dbiculocale; + else if (dblocprovider == COLLPROVIDER_LIBC) + locale = dbcollate; + else + locale = NULL; /* COLLPROVIDER_NONE */ + + actual_versionstr = get_collation_actual_version(dblocprovider, locale); if (!actual_versionstr) ereport(ERROR, (errmsg("template database \"%s\" has a collation version, but no actual collation version could be determined", @@ -1207,7 +1217,18 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt) * collation version, which is normally only the case for template0. */ if (dbcollversion == NULL) - dbcollversion = get_collation_actual_version(dblocprovider, dblocprovider == COLLPROVIDER_ICU ? dbiculocale : dbcollate); + { + char *locale; + + if (dblocprovider == COLLPROVIDER_ICU) + locale = dbiculocale; + else if (dblocprovider == COLLPROVIDER_LIBC) + locale = dbcollate; + else + locale = NULL; /* COLLPROVIDER_NONE */ + + dbcollversion = get_collation_actual_version(dblocprovider, locale); + } /* Resolve default tablespace for new database */ if (dtablespacename && dtablespacename->arg) @@ -2403,6 +2424,7 @@ AlterDatabaseRefreshColl(AlterDatabaseRefreshCollStmt *stmt) ObjectAddress address; Datum datum; bool isnull; + char *locale; char *oldversion; char *newversion; @@ -2429,10 +2451,24 @@ AlterDatabaseRefreshColl(AlterDatabaseRefreshCollStmt *stmt) datum = heap_getattr(tuple, Anum_pg_database_datcollversion, RelationGetDescr(rel), &isnull); oldversion = isnull ? NULL : TextDatumGetCString(datum); - datum = heap_getattr(tuple, datForm->datlocprovider == COLLPROVIDER_ICU ? Anum_pg_database_daticulocale : Anum_pg_database_datcollate, RelationGetDescr(rel), &isnull); - if (isnull) - elog(ERROR, "unexpected null in pg_database"); - newversion = get_collation_actual_version(datForm->datlocprovider, TextDatumGetCString(datum)); + if (datForm->datlocprovider == COLLPROVIDER_ICU) + { + datum = heap_getattr(tuple, Anum_pg_database_daticulocale, RelationGetDescr(rel), &isnull); + if (isnull) + elog(ERROR, "unexpected null in pg_database"); + locale = TextDatumGetCString(datum); + } + else if (datForm->datlocprovider == COLLPROVIDER_LIBC) + { + datum = heap_getattr(tuple, Anum_pg_database_datcollate, RelationGetDescr(rel), &isnull); + if (isnull) + elog(ERROR, "unexpected null in pg_database"); + locale = TextDatumGetCString(datum); + } + else + locale = NULL; /* COLLPROVIDER_NONE */ + + newversion = get_collation_actual_version(datForm->datlocprovider, locale); /* cannot change from NULL to non-NULL or vice versa */ if ((!oldversion && newversion) || (oldversion && !newversion)) @@ -2617,6 +2653,7 @@ pg_database_collation_actual_version(PG_FUNCTION_ARGS) HeapTuple tp; char datlocprovider; Datum datum; + char *locale; char *version; tp = SearchSysCache1(DATABASEOID, ObjectIdGetDatum(dbid)); @@ -2627,8 +2664,20 @@ pg_database_collation_actual_version(PG_FUNCTION_ARGS) datlocprovider = ((Form_pg_database) GETSTRUCT(tp))->datlocprovider; - datum = SysCacheGetAttrNotNull(DATABASEOID, tp, datlocprovider == COLLPROVIDER_ICU ? Anum_pg_database_daticulocale : Anum_pg_database_datcollate); - version = get_collation_actual_version(datlocprovider, TextDatumGetCString(datum)); + if (datlocprovider == COLLPROVIDER_ICU) + { + datum = SysCacheGetAttrNotNull(DATABASEOID, tp, Anum_pg_database_daticulocale); + locale = TextDatumGetCString(datum); + } + else if (datlocprovider == COLLPROVIDER_LIBC) + { + datum = SysCacheGetAttrNotNull(DATABASEOID, tp, Anum_pg_database_datcollate); + locale = TextDatumGetCString(datum); + } + else + locale = NULL; /* COLLPROVIDER_NONE */ + + version = get_collation_actual_version(datlocprovider, locale); ReleaseSysCache(tp); diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index eea1d1ae0f..95eb5cf464 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -1228,7 +1228,12 @@ lookup_collation_cache(Oid collation, bool set_flags) elog(ERROR, "cache lookup failed for collation %u", collation); collform = (Form_pg_collation) GETSTRUCT(tp); - if (collform->collprovider == COLLPROVIDER_LIBC) + if (collform->collprovider == COLLPROVIDER_NONE) + { + cache_entry->collate_is_c = true; + cache_entry->ctype_is_c = true; + } + else if (collform->collprovider == COLLPROVIDER_LIBC) { Datum datum; const char *collcollate; @@ -1281,6 +1286,9 @@ lc_collate_is_c(Oid collation) static int result = -1; char *localeptr; + if (default_locale.provider == COLLPROVIDER_NONE) + return true; + if (default_locale.provider == COLLPROVIDER_ICU) return false; @@ -1334,6 +1342,9 @@ lc_ctype_is_c(Oid collation) static int result = -1; char *localeptr; + if (default_locale.provider == COLLPROVIDER_NONE) + return true; + if (default_locale.provider == COLLPROVIDER_ICU) return false; @@ -1487,8 +1498,10 @@ pg_newlocale_from_collation(Oid collid) { if (default_locale.provider == COLLPROVIDER_ICU) return &default_locale; - else + else if (default_locale.provider == COLLPROVIDER_LIBC) return (pg_locale_t) 0; + else + elog(ERROR, "cannot open collation with provider \"none\""); } cache_entry = lookup_collation_cache(collid, false); @@ -1513,7 +1526,11 @@ pg_newlocale_from_collation(Oid collid) result.provider = collform->collprovider; result.deterministic = collform->collisdeterministic; - if (collform->collprovider == COLLPROVIDER_LIBC) + if (collform->collprovider == COLLPROVIDER_NONE) + { + elog(ERROR, "cannot open collation with provider \"none\""); + } + else if (collform->collprovider == COLLPROVIDER_LIBC) { #ifdef HAVE_LOCALE_T const char *collcollate; @@ -1599,6 +1616,7 @@ pg_newlocale_from_collation(Oid collid) collversionstr = TextDatumGetCString(datum); + Assert(collform->collprovider != COLLPROVIDER_NONE); datum = SysCacheGetAttrNotNull(COLLOID, tp, collform->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colliculocale : Anum_pg_collation_collcollate); actual_versionstr = get_collation_actual_version(collform->collprovider, @@ -1650,6 +1668,9 @@ get_collation_actual_version(char collprovider, const char *collcollate) { char *collversion = NULL; + if (collprovider == COLLPROVIDER_NONE) + return NULL; + #ifdef USE_ICU if (collprovider == COLLPROVIDER_ICU) { diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c index 53420f4974..8053642fd3 100644 --- a/src/backend/utils/init/postinit.c +++ b/src/backend/utils/init/postinit.c @@ -461,10 +461,18 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect { char *actual_versionstr; char *collversionstr; + char *locale; collversionstr = TextDatumGetCString(datum); - actual_versionstr = get_collation_actual_version(dbform->datlocprovider, dbform->datlocprovider == COLLPROVIDER_ICU ? iculocale : collate); + if (dbform->datlocprovider == COLLPROVIDER_ICU) + locale = iculocale; + else if (dbform->datlocprovider == COLLPROVIDER_LIBC) + locale = collate; + else + locale = NULL; /* COLLPROVIDER_NONE */ + + actual_versionstr = get_collation_actual_version(dbform->datlocprovider, locale); if (!actual_versionstr) /* should not happen */ elog(WARNING, diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 30b576932f..4a6cad3cb9 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -2408,6 +2408,22 @@ setlocales(void) /* set empty lc_* values to locale config if set */ + if (locale_provider == COLLPROVIDER_NONE) + { + if (!lc_ctype) + lc_ctype = "C"; + if (!lc_collate) + lc_collate = "C"; + if (!lc_numeric) + lc_numeric = "C"; + if (!lc_time) + lc_time = "C"; + if (!lc_monetary) + lc_monetary = "C"; + if (!lc_messages) + lc_messages = "C"; + } + if (locale) { if (!lc_ctype) @@ -2502,7 +2518,7 @@ usage(const char *progname) " set default locale in the respective category for\n" " new databases (default taken from environment)\n")); printf(_(" --no-locale equivalent to --locale=C\n")); - printf(_(" --locale-provider={libc|icu}\n" + printf(_(" --locale-provider={none|libc|icu}\n" " set default locale provider for new databases\n")); printf(_(" --pwfile=FILE read password for the new superuser from file\n")); printf(_(" -T, --text-search-config=CFG\n" @@ -2652,7 +2668,15 @@ setup_locale_encoding(void) { setlocales(); - if (locale_provider == COLLPROVIDER_LIBC && + if (locale_provider == COLLPROVIDER_NONE && + strcmp(lc_ctype, "C") == 0 && + strcmp(lc_collate, "C") == 0 && + strcmp(lc_time, "C") == 0 && + strcmp(lc_numeric, "C") == 0 && + strcmp(lc_monetary, "C") == 0 && + strcmp(lc_messages, "C") == 0) + printf(_("The database cluster will be initialized with no locale.\n")); + else if (locale_provider == COLLPROVIDER_LIBC && strcmp(lc_ctype, lc_collate) == 0 && strcmp(lc_ctype, lc_time) == 0 && strcmp(lc_ctype, lc_numeric) == 0 && @@ -3326,7 +3350,9 @@ main(int argc, char *argv[]) "-c debug_discard_caches=1"); break; case 15: - if (strcmp(optarg, "icu") == 0) + if (strcmp(optarg, "none") == 0) + locale_provider = COLLPROVIDER_NONE; + else if (strcmp(optarg, "icu") == 0) locale_provider = COLLPROVIDER_ICU; else if (strcmp(optarg, "libc") == 0) locale_provider = COLLPROVIDER_LIBC; @@ -3365,6 +3391,7 @@ main(int argc, char *argv[]) exit(1); } + if (icu_locale && locale_provider != COLLPROVIDER_ICU) pg_fatal("%s cannot be specified unless locale provider \"%s\" is chosen", "--icu-locale", "icu"); diff --git a/src/bin/initdb/t/001_initdb.pl b/src/bin/initdb/t/001_initdb.pl index 17a444d80c..fe6d224e5b 100644 --- a/src/bin/initdb/t/001_initdb.pl +++ b/src/bin/initdb/t/001_initdb.pl @@ -154,6 +154,35 @@ else 'locale provider ICU fails since no ICU support'); } +command_ok( + [ 'initdb', '--no-sync', '--locale-provider=none', "$tempdir/data6" ], + 'locale provider none'); + +command_ok( + [ 'initdb', '--no-sync', '--locale-provider=none', '--locale=C', + "$tempdir/data7" ], + 'locale provider none with --locale'); + +command_ok( + [ 'initdb', '--no-sync', '--locale-provider=none', '--lc-collate=C', + "$tempdir/data8" ], + 'locale provider none with --lc-collate'); + +command_ok( + [ 'initdb', '--no-sync', '--locale-provider=none', '--lc-ctype=C', + "$tempdir/data9" ], + 'locale provider none with --lc-ctype'); + +command_fails( + [ 'initdb', '--no-sync', '--locale-provider=none', '--icu-locale=en', + "$tempdir/dataX" ], + 'fails for locale provider none with ICU locale'); + +command_fails( + [ 'initdb', '--no-sync', '--locale-provider=none', '--icu-rules=""', + "$tempdir/dataX" ], + 'fails for locale provider none with ICU rules'); + command_fails( [ 'initdb', '--no-sync', '--locale-provider=xyz', "$tempdir/dataX" ], 'fails for invalid locale provider'); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index f9cbeb65ab..ddc8a5f71f 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -3070,7 +3070,9 @@ dumpDatabase(Archive *fout) } appendPQExpBufferStr(creaQry, " LOCALE_PROVIDER = "); - if (datlocprovider[0] == 'c') + if (datlocprovider[0] == 'n') + appendPQExpBufferStr(creaQry, "none"); + else if (datlocprovider[0] == 'c') appendPQExpBufferStr(creaQry, "libc"); else if (datlocprovider[0] == 'i') appendPQExpBufferStr(creaQry, "icu"); @@ -13429,7 +13431,9 @@ dumpCollation(Archive *fout, const CollInfo *collinfo) fmtQualifiedDumpable(collinfo)); appendPQExpBufferStr(q, "provider = "); - if (collprovider[0] == 'c') + if (collprovider[0] == 'n') + appendPQExpBufferStr(q, "none"); + else if (collprovider[0] == 'c') appendPQExpBufferStr(q, "libc"); else if (collprovider[0] == 'i') appendPQExpBufferStr(q, "icu"); diff --git a/src/bin/pg_upgrade/t/002_pg_upgrade.pl b/src/bin/pg_upgrade/t/002_pg_upgrade.pl index 4a7895a756..6d58f6103e 100644 --- a/src/bin/pg_upgrade/t/002_pg_upgrade.pl +++ b/src/bin/pg_upgrade/t/002_pg_upgrade.pl @@ -114,12 +114,20 @@ my $original_locale = "C"; my $original_iculocale = ""; my $provider_field = "'c' AS datlocprovider"; my $iculocale_field = "NULL AS daticulocale"; -if ($oldnode->pg_version >= 15 && $ENV{with_icu} eq 'yes') +if ($oldnode->pg_version >= 15) { $provider_field = "datlocprovider"; $iculocale_field = "daticulocale"; - $original_provider = "i"; - $original_iculocale = "fr-CA"; + + if ($ENV{with_icu} eq 'yes') + { + $original_provider = "i"; + $original_iculocale = "fr-CA"; + } + else + { + $original_provider = "n"; + } } my @initdb_params = @custom_opts; @@ -131,6 +139,10 @@ if ($original_provider eq "i") push @initdb_params, ('--locale-provider', 'icu'); push @initdb_params, ('--icu-locale', 'fr-CA'); } +elsif ($original_provider eq "n") +{ + push @initdb_params, ('--locale-provider', 'none'); +} $node_params{extra} = \@initdb_params; $oldnode->init(%node_params); diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c index ab4279ed58..c842a62ae9 100644 --- a/src/bin/psql/describe.c +++ b/src/bin/psql/describe.c @@ -932,7 +932,7 @@ listAllDbs(const char *pattern, bool verbose) gettext_noop("Encoding")); if (pset.sversion >= 150000) appendPQExpBuffer(&buf, - " CASE d.datlocprovider WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\",\n", + " CASE d.datlocprovider WHEN 'n' THEN 'none' WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\",\n", gettext_noop("Locale Provider")); else appendPQExpBuffer(&buf, diff --git a/src/bin/scripts/createdb.c b/src/bin/scripts/createdb.c index b4205c4fa5..79367d933b 100644 --- a/src/bin/scripts/createdb.c +++ b/src/bin/scripts/createdb.c @@ -299,7 +299,7 @@ help(const char *progname) printf(_(" --lc-ctype=LOCALE LC_CTYPE setting for the database\n")); printf(_(" --icu-locale=LOCALE ICU locale setting for the database\n")); printf(_(" --icu-rules=RULES ICU rules setting for the database\n")); - printf(_(" --locale-provider={libc|icu}\n" + printf(_(" --locale-provider={none|libc|icu}\n" " locale provider for the database's default collation\n")); printf(_(" -O, --owner=OWNER database user to own the new database\n")); printf(_(" -S, --strategy=STRATEGY database creation strategy wal_log or file_copy\n")); diff --git a/src/bin/scripts/t/020_createdb.pl b/src/bin/scripts/t/020_createdb.pl index af3b1492e3..5aa658b671 100644 --- a/src/bin/scripts/t/020_createdb.pl +++ b/src/bin/scripts/t/020_createdb.pl @@ -83,6 +83,35 @@ else 'create database with ICU fails since no ICU support'); } +$node->command_ok( + [ 'createdb', '-T', 'template0', '--locale-provider=none', 'testnone1' ], + 'create database with provider "none"'); + +$node->command_ok( + [ 'createdb', '-T', 'template0', '--locale-provider=none', '--locale=C', + 'testnone2' ], + 'create database with provider "none" and locale "C"'); + +$node->command_ok( + [ 'createdb', '-T', 'template0', '--locale-provider=none', '--lc-collate=C', + 'testnone3' ], + 'create database with provider "none" and LC_COLLATE=C'); + +$node->command_ok( + [ 'createdb', '-T', 'template0', '--locale-provider=none', '--lc-ctype=C', + 'testnone4' ], + 'create database with provider "none" and LC_CTYPE=C'); + +$node->command_fails( + [ 'createdb', '-T', 'template0', '--locale-provider=none', '--icu-locale=en', + 'testnone5' ], + 'create database with provider "none" and ICU_LOCALE="en"'); + +$node->command_fails( + [ 'createdb', '-T', 'template0', '--locale-provider=none', '--icu-rules=""', + 'testnone6' ], + 'create database with provider "none" and ICU_RULES=""'); + $node->command_fails([ 'createdb', 'foobar1' ], 'fails if database already exists'); diff --git a/src/include/catalog/pg_collation.dat b/src/include/catalog/pg_collation.dat index b6a69d1d42..40d62416ea 100644 --- a/src/include/catalog/pg_collation.dat +++ b/src/include/catalog/pg_collation.dat @@ -24,8 +24,7 @@ collname => 'POSIX', collprovider => 'c', collencoding => '-1', collcollate => 'POSIX', collctype => 'POSIX' }, { oid => '962', descr => 'sorts by Unicode code point', - collname => 'ucs_basic', collprovider => 'c', collencoding => '6', - collcollate => 'C', collctype => 'C' }, + collname => 'ucs_basic', collprovider => 'n', collencoding => '6' }, { oid => '963', descr => 'sorts using the Unicode Collation Algorithm with default settings', collname => 'unicode', collprovider => 'i', collencoding => '-1', diff --git a/src/include/catalog/pg_collation.h b/src/include/catalog/pg_collation.h index bfa3568451..29be3f8d94 100644 --- a/src/include/catalog/pg_collation.h +++ b/src/include/catalog/pg_collation.h @@ -64,6 +64,7 @@ DECLARE_UNIQUE_INDEX_PKEY(pg_collation_oid_index, 3085, CollationOidIndexId, on #ifdef EXPOSE_TO_CLIENT_CODE +#define COLLPROVIDER_NONE 'n' #define COLLPROVIDER_DEFAULT 'd' #define COLLPROVIDER_ICU 'i' #define COLLPROVIDER_LIBC 'c' @@ -73,6 +74,8 @@ collprovider_name(char c) { switch (c) { + case COLLPROVIDER_NONE: + return "none"; case COLLPROVIDER_ICU: return "icu"; case COLLPROVIDER_LIBC: diff --git a/src/test/regress/expected/collate.out b/src/test/regress/expected/collate.out index 0649564485..b7603c9f6c 100644 --- a/src/test/regress/expected/collate.out +++ b/src/test/regress/expected/collate.out @@ -650,6 +650,13 @@ EXPLAIN (COSTS OFF) (3 rows) -- CREATE/DROP COLLATION +CREATE COLLATION none ( PROVIDER = none ); +CREATE COLLATION none2 ( PROVIDER = none, LOCALE="POSIX" ); -- fails +ERROR: collation provider "none" does not support LOCALE, LC_COLLATE, or LC_CTYPE +CREATE COLLATION none2 ( PROVIDER = none, LC_CTYPE="POSIX" ); -- fails +ERROR: collation provider "none" does not support LOCALE, LC_COLLATE, or LC_CTYPE +CREATE COLLATION none2 ( PROVIDER = none, LC_COLLATE="POSIX" ); -- fails +ERROR: collation provider "none" does not support LOCALE, LC_COLLATE, or LC_CTYPE CREATE COLLATION mycoll1 FROM "C"; CREATE COLLATION mycoll2 ( LC_COLLATE = "POSIX", LC_CTYPE = "POSIX" ); CREATE COLLATION mycoll3 FROM "default"; -- intentionally unsupported @@ -754,7 +761,7 @@ DETAIL: FROM cannot be specified together with any other options. -- must get rid of them. -- DROP SCHEMA collate_tests CASCADE; -NOTICE: drop cascades to 19 other objects +NOTICE: drop cascades to 20 other objects DETAIL: drop cascades to table collate_test1 drop cascades to table collate_test_like drop cascades to table collate_test2 @@ -771,6 +778,7 @@ drop cascades to function dup(anyelement) drop cascades to table collate_test20 drop cascades to table collate_test21 drop cascades to table collate_test22 +drop cascades to collation "none" drop cascades to collation mycoll2 drop cascades to table collate_test23 drop cascades to view collate_on_int diff --git a/src/test/regress/sql/collate.sql b/src/test/regress/sql/collate.sql index c3d40fc195..e2dceb8dff 100644 --- a/src/test/regress/sql/collate.sql +++ b/src/test/regress/sql/collate.sql @@ -244,6 +244,12 @@ EXPLAIN (COSTS OFF) -- CREATE/DROP COLLATION +CREATE COLLATION none ( PROVIDER = none ); + +CREATE COLLATION none2 ( PROVIDER = none, LOCALE="POSIX" ); -- fails +CREATE COLLATION none2 ( PROVIDER = none, LC_CTYPE="POSIX" ); -- fails +CREATE COLLATION none2 ( PROVIDER = none, LC_COLLATE="POSIX" ); -- fails + CREATE COLLATION mycoll1 FROM "C"; CREATE COLLATION mycoll2 ( LC_COLLATE = "POSIX", LC_CTYPE = "POSIX" ); CREATE COLLATION mycoll3 FROM "default"; -- intentionally unsupported -- 2.34.1