From 5a0c410452f54b22a7a4361c90d7bb4a93c83d01 Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Sat, 30 Nov 2024 20:00:19 +1300 Subject: [PATCH v2] Formalize the encoding of the shared catalogs. The encoding of shared catalogs was previously undefined. Each database just naively used its own encoding, and early connection phases worked with raw bytes and hoped for the best. Database names, role names, and more could be corrupted in various multi-encoding scenarios. This commit introduces a new setting CLUSTER CATALOG ENCODING to define and enforce the encoding. It can be specified at initdb time, and changed later with ALTER SYSTEM if the conditions for the new setting are met. Three settings are available: DATABASE: The shared catalogs use the same encoding as all databases, and all databases must use the same encoding. Database names and role names are free to include non-ASCII characters. This is the default. ASCII: The shared catalogs are restricted to 7-bit ASCII. Databases with different encodings are allowed to co-exist, because ASCII is a subset of all supported encodings. UNDEFINED: The old behavior. Not recommended, and perhaps one day we'll consider removing it. Work in progress! Discussion: https://postgr.es/m/CA%2BhUKGKKNAc599Vp7kFAnLE1%3DV%3DceYujz_YQoSNrvNFGaJ6i7w%40mail.gmail.com --- doc/src/sgml/catalogs.sgml | 2 + doc/src/sgml/charset.sgml | 66 ++- doc/src/sgml/ref/alter_system.sgml | 19 +- doc/src/sgml/ref/initdb.sgml | 21 + src/backend/access/rmgrdesc/xlogdesc.c | 10 + src/backend/access/transam/xlog.c | 42 +- src/backend/bootstrap/bootstrap.c | 9 +- src/backend/catalog/Makefile | 1 + src/backend/catalog/encoding.c | 432 ++++++++++++++++++ src/backend/catalog/meson.build | 1 + src/backend/catalog/pg_db_role_setting.c | 5 + src/backend/commands/alter.c | 18 + src/backend/commands/comment.c | 3 + src/backend/commands/dbcommands.c | 28 ++ src/backend/commands/seclabel.c | 3 + src/backend/commands/subscriptioncmds.c | 6 + src/backend/commands/tablespace.c | 4 + src/backend/commands/user.c | 4 + src/backend/parser/gram.y | 14 + src/backend/replication/logical/origin.c | 2 + src/backend/tcop/utility.c | 11 +- src/backend/utils/misc/guc_tables.c | 12 + src/bin/initdb/initdb.c | 22 +- src/bin/pg_controldata/pg_controldata.c | 3 + src/bin/pg_resetwal/pg_resetwal.c | 2 + src/bin/pg_upgrade/controldata.c | 16 + src/bin/pg_upgrade/pg_upgrade.c | 17 + src/bin/pg_upgrade/pg_upgrade.h | 1 + src/bin/psql/tab-complete.in.c | 12 +- src/bin/scripts/t/020_createdb.pl | 4 +- src/include/access/xlog.h | 5 +- src/include/access/xlog_internal.h | 6 + src/include/catalog/catalog.h | 3 + src/include/catalog/pg_control.h | 5 +- src/include/commands/alter.h | 2 + src/include/nodes/parsenodes.h | 1 + src/test/modules/Makefile | 1 + src/test/modules/encoding/Makefile | 17 + .../expected/cluster_catalog_encoding.out | 208 +++++++++ src/test/modules/encoding/meson.build | 14 + .../encoding/sql/cluster_catalog_encoding.sql | 137 ++++++ src/test/modules/meson.build | 1 + src/test/regress/expected/database.out | 16 +- src/test/regress/pg_regress.c | 2 + src/test/regress/sql/database.sql | 16 +- src/tools/pgindent/typedefs.list | 1 + 46 files changed, 1197 insertions(+), 28 deletions(-) create mode 100644 src/backend/catalog/encoding.c create mode 100644 src/test/modules/encoding/Makefile create mode 100644 src/test/modules/encoding/expected/cluster_catalog_encoding.out create mode 100644 src/test/modules/encoding/meson.build create mode 100644 src/test/modules/encoding/sql/cluster_catalog_encoding.sql diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml index bf3cee08a93..1a7c0b9565e 100644 --- a/doc/src/sgml/catalogs.sgml +++ b/doc/src/sgml/catalogs.sgml @@ -36,6 +36,8 @@ database creation and are thereafter database-specific. A few catalogs are physically shared across all databases in a cluster; these are noted in the descriptions of the individual catalogs. + This has implications for their character set; see + for details. diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml index 00e1986849a..bbfba46eb0c 100644 --- a/doc/src/sgml/charset.sgml +++ b/doc/src/sgml/charset.sgml @@ -2222,7 +2222,10 @@ initdb -E EUC_JP You can specify a non-default encoding at database creation time, - provided that the encoding is compatible with the selected locale: + provided that the encoding is compatible with the selected locale, + and CLUSTER CATALOG ENCODING is set to + ASCII (or UNDEFINED, not + recommended). createdb -E EUC_KR -T template0 --lc-collate=ko_KR.euckr --lc-ctype=ko_KR.euckr korean @@ -2401,6 +2404,67 @@ RESET client_encoding; + + Character Sets and Catalogs Shared by the Whole Cluster + + The names of databases, roles and a small number of other object type + are + stored in shared catalogs, + and are visible from all the databases in a cluster. + Since databases can use different encodings, a trade-off is required to + make sure that they use compatible character sets. + Two main configurations are available, controlled by the system setting + CLUSTER CATALOG ENCODING: + + + + + DATABASE: To allow non-ASCII characters to be used in + database and role names, all databases must use the same encoding. + This is the default setting used by initdb. + + + + + ASCII: To allow databases with different + encodings to co-exist, the shared catalogs must use only ASCII + characters. It is a subset of all supported server encodings, so + conforming strings are also valid in every database's encoding without + conversion (or risk of conversion failure). + + + + + + A third setting UNDEFINED allows + databases with different encodings to co-exist while also allowing + non-ASCII characters in database and role names. + Corruption can occcur when in this mode. It is provided to + support upgrading from older PostgreSQL releases, but is not + recommended for new deployments. + + + CLUSTER CATALOG ENCODING can be set with the + option to initdb, or + changed later using the + command. To change to + ASCII, shared catalogs must have no existing non-ASCII + characters. + To change to DATABASE encoding, all existing databases must be using + that encoding. + It is always possible to change to UNDEFINED without restriction, + but not recommended. + + + Note that when CLUSTER CATALOG ENCODING is set to + ASCII, + it only restricts the names and properties of a small number of kinds of database + objects that have cluster-wide visibility. Most objects such as tables, + indexes and functions are stored in per-database catalogs and can always + use the full character set of the database's encoding. + + + Available Character Set Conversions diff --git a/doc/src/sgml/ref/alter_system.sgml b/doc/src/sgml/ref/alter_system.sgml index 1bde66d6ad2..52b7100a52e 100644 --- a/doc/src/sgml/ref/alter_system.sgml +++ b/doc/src/sgml/ref/alter_system.sgml @@ -25,6 +25,8 @@ ALTER SYSTEM SET configuration_parameterconfiguration_parameter ALTER SYSTEM RESET ALL + +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO { DATABASE | ASCII | UNKNOWN } @@ -32,7 +34,7 @@ ALTER SYSTEM RESET ALL Description - ALTER SYSTEM is used for changing server configuration + ALTER SYSTEM { SET | RESET } is used for changing server configuration parameters across the entire database cluster. It can be more convenient than the traditional method of manually editing the postgresql.conf file. @@ -54,6 +56,20 @@ ALTER SYSTEM RESET ALL or sending a SIGHUP signal to the main server process. + + ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO selects the + character set used for role names, database names and the properties of + certain other database objects that are shared + by all databases in the cluster. DATABASE means that database + encoding is used, and all databases are required to use the same encoding. + ASCII means that only the ASCII character set can used, + but databases can use any encoding. + UNDEFINED disables enforcement of character set restrictions and is + not recommended. See for details. + Unlike other ALTER SYSTEM SET commands, this change takes + effect immediately, if the required conditions required are met. + + Only superusers and users granted ALTER SYSTEM privilege on a parameter can change it using ALTER SYSTEM. Also, since @@ -96,6 +112,7 @@ ALTER SYSTEM RESET ALL + diff --git a/doc/src/sgml/ref/initdb.sgml b/doc/src/sgml/ref/initdb.sgml index 0c32114cf70..d3bead500ba 100644 --- a/doc/src/sgml/ref/initdb.sgml +++ b/doc/src/sgml/ref/initdb.sgml @@ -132,6 +132,10 @@ PostgreSQL documentation To alter the default encoding, use the . + To specify a different encoding for the shared catalogs with + ; this affects the character + set available for database and role names, and the ability to create + databases with different encodings. More details can be found in . @@ -227,6 +231,23 @@ PostgreSQL documentation + + + + + + Specifies the initial CLUSTER CATALOG ENCODING setting. + + + By default, shared catalog encoding is set to DATABASE. + Valid options are DATABASE, ASCII + and UNDEFINED. The value can be changed later with + the ALTER SYSTEM command. + See for details. + + + + diff --git a/src/backend/access/rmgrdesc/xlogdesc.c b/src/backend/access/rmgrdesc/xlogdesc.c index 363294d6234..c65bd741dae 100644 --- a/src/backend/access/rmgrdesc/xlogdesc.c +++ b/src/backend/access/rmgrdesc/xlogdesc.c @@ -134,6 +134,13 @@ xlog_desc(StringInfo buf, XLogReaderState *record) xlrec.wal_log_hints ? "on" : "off", xlrec.track_commit_timestamp ? "on" : "off"); } + else if (info == XLOG_CLUSTER_CATALOG_ENCODING_CHANGE) + { + xl_cluster_catalog_encoding_change xlrec; + + memcpy(&xlrec, rec, sizeof(xl_cluster_catalog_encoding_change)); + appendStringInfo(buf, "encoding=%d", xlrec.encoding); + } else if (info == XLOG_FPW_CHANGE) { bool fpw; @@ -197,6 +204,9 @@ xlog_identify(uint8 info) case XLOG_PARAMETER_CHANGE: id = "PARAMETER_CHANGE"; break; + case XLOG_CLUSTER_CATALOG_ENCODING_CHANGE: + id = "CLUSTER_CATALOG_ENCODING_CHANGE"; + break; case XLOG_RESTORE_POINT: id = "RESTORE_POINT"; break; diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 6f58412bcab..52c675dbe8a 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -70,6 +70,7 @@ #include "common/file_utils.h" #include "executor/instrument.h" #include "miscadmin.h" +#include "mb/pg_wchar.h" #include "pg_trace.h" #include "pgstat.h" #include "port/atomics.h" @@ -5030,7 +5031,8 @@ XLOGShmemInit(void) * and the initial XLOG segment. */ void -BootStrapXLOG(uint32 data_checksum_version) +BootStrapXLOG(int cluster_catalog_encoding, + uint32 data_checksum_version) { CheckPoint checkPoint; char *buffer; @@ -5173,6 +5175,7 @@ BootStrapXLOG(uint32 data_checksum_version) /* Now create pg_control */ InitControlFile(sysidentifier, data_checksum_version); + ControlFile->cluster_catalog_encoding = cluster_catalog_encoding; ControlFile->time = checkPoint.time; ControlFile->checkPoint = checkPoint.redo; ControlFile->checkPointCopy = checkPoint; @@ -8557,6 +8560,13 @@ xlog_redo(XLogReaderState *record) /* Check to see if any parameter change gives a problem on recovery */ CheckRequiredParameterValues(); } + else if (info == XLOG_CLUSTER_CATALOG_ENCODING_CHANGE) + { + xl_cluster_catalog_encoding_change xlrec; + + memcpy(&xlrec, XLogRecGetData(record), sizeof(xlrec)); + ControlFile->cluster_catalog_encoding = xlrec.encoding; + } else if (info == XLOG_FPW_CHANGE) { bool fpw; @@ -9510,3 +9520,33 @@ SetWalWriterSleeping(bool sleeping) XLogCtl->WalWriterSleeping = sleeping; SpinLockRelease(&XLogCtl->info_lck); } + +/* + * Get the shared catalog encoding. This should only be called when a lock is + * held on one of the shared catalog tables. + */ +int +GetClusterCatalogEncoding(void) +{ + return ControlFile->cluster_catalog_encoding; +} + +/* + * Set CLUSTER CATALOG ENCODING. This should only be called with + * AccessExclusiveLock held on *all* shared catalog tables that contain text. + */ +void +SetClusterCatalogEncoding(int encoding) +{ + xl_cluster_catalog_encoding_change xlrec; + + START_CRIT_SECTION(); + MyProc->delayChkptFlags |= DELAY_CHKPT_START; + xlrec.encoding = encoding; + XLogBeginInsert(); + XLogRegisterData((char *) &xlrec, sizeof(xlrec)); + XLogFlush(XLogInsert(RM_XLOG_ID, XLOG_CLUSTER_CATALOG_ENCODING_CHANGE)); + ControlFile->cluster_catalog_encoding = encoding; + MyProc->delayChkptFlags &= ~DELAY_CHKPT_START; + END_CRIT_SECTION(); +} diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index d31a67599c9..cc1bfd2ce04 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -202,6 +202,7 @@ BootstrapModeMain(int argc, char *argv[], bool check_only) int flag; char *userDoption = NULL; uint32 bootstrap_data_checksum_version = 0; /* No checksum */ + int cluster_catalog_encoding = -1; Assert(!IsUnderPostmaster); @@ -217,7 +218,7 @@ BootstrapModeMain(int argc, char *argv[], bool check_only) argv++; argc--; - while ((flag = getopt(argc, argv, "B:c:d:D:Fkr:X:-:")) != -1) + while ((flag = getopt(argc, argv, "B:c:C:d:D:Fkr:X:-:")) != -1) { switch (flag) { @@ -266,6 +267,9 @@ BootstrapModeMain(int argc, char *argv[], bool check_only) pfree(debugstr); } break; + case 'C': + cluster_catalog_encoding = atoi(optarg); + break; case 'F': SetConfigOption("fsync", "false", PGC_POSTMASTER, PGC_S_ARGV); break; @@ -341,7 +345,8 @@ BootstrapModeMain(int argc, char *argv[], bool check_only) BaseInit(); bootstrap_signals(); - BootStrapXLOG(bootstrap_data_checksum_version); + BootStrapXLOG(cluster_catalog_encoding, + bootstrap_data_checksum_version); /* * To ensure that src/common/link-canary.c is linked into the backend, we diff --git a/src/backend/catalog/Makefile b/src/backend/catalog/Makefile index 1589a75fd53..ed460a95e62 100644 --- a/src/backend/catalog/Makefile +++ b/src/backend/catalog/Makefile @@ -17,6 +17,7 @@ OBJS = \ aclchk.o \ catalog.o \ dependency.o \ + encoding.o \ heap.o \ index.o \ indexing.o \ diff --git a/src/backend/catalog/encoding.c b/src/backend/catalog/encoding.c new file mode 100644 index 00000000000..8f1d69a39de --- /dev/null +++ b/src/backend/catalog/encoding.c @@ -0,0 +1,432 @@ +/*------------------------------------------------------------------------- + * + * encoding.c + * Shared catalog encoding management. + * + * + * Portions Copyright (c) 2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/catalog/encoding.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "access/genam.h" +#include "access/table.h" +#include "access/xlog.h" +#include "catalog/catalog.h" +#include "catalog/pg_authid.h" +#include "catalog/pg_database.h" +#include "catalog/pg_db_role_setting.h" +#include "catalog/pg_namespace.h" +#include "catalog/pg_parameter_acl.h" +#include "catalog/pg_replication_origin.h" +#include "catalog/pg_shdescription.h" +#include "catalog/pg_shseclabel.h" +#include "catalog/pg_subscription.h" +#include "catalog/pg_tablespace.h" +#include "commands/dbcommands.h" +#include "common/string.h" +#include "mb/pg_wchar.h" +#include "miscadmin.h" +#include "storage/lmgr.h" +#include "utils/builtins.h" + +/* + * Check if a NULL-terminated string can be inserted into a shared catalog. + * The caller must hold a lock on the shared catalog table, to block + * AlterSystemSetClusterCatalogEncoding(). + */ +void +ValidateClusterCatalogString(Relation rel, const char *s) +{ + /* + * The main reason for taking the rel argument is to make sure that caller + * remembered to lock the catalog before validating strings to be + * inserted. But we might as well check it's a shared relation since we + * have it. + */ + Assert(rel->rd_rel->relisshared); + + /* + * If using SQL_ASCII, then we have to make sure this string is clean + * 7-bit ASCII, so that it is valid in every supported encoding. + */ + if (GetClusterCatalogEncoding() != PG_SQL_ASCII) + { + /* + * Otherwise, either we're in UNKNOWN mode where anything goes, or all + * databases are using the same encoding and matches the shared + * catalog encoding. We don't have to validate anything. + */ + Assert(GetClusterCatalogEncoding() == -1 || + GetClusterCatalogEncoding() == GetDatabaseEncoding()); + return; + } + + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("the string \"%s\" contains invalid characters", s), + errdetail("CLUSTER CATALOG ENCODING is set to ASCII."), + errhint("Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE."))); +} + +/* + * Try to change the cluster catalog encoding, if all the conditions are met. + */ +void +AlterSystemSetClusterCatalogEncoding(const char *encoding_name) +{ + Relation rel; + SysScanDesc scan; + HeapTuple tup; + int encoding; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("permission denied"))); + + /* Decode the name. */ + if (pg_strcasecmp(encoding_name, "DATABASE") == 0) + encoding = GetDatabaseEncoding(); + else if (pg_strcasecmp(encoding_name, "ASCII") == 0) + encoding = PG_SQL_ASCII; + else if (pg_strcasecmp(encoding_name, "UNDEFINED") == 0) + encoding = -1; + else + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid shared catalog encoding: %s", + encoding_name))); + + /* + * Lock all of the shared catalog tables containing name or text values, + * to prevent concurrent updates. This is the set of shared catalogs that + * contain text. If new shared catalogs are invented that hold text they + * will need to be handled here too. For every validation that we perform + * below, there must also be corresponding calls to + * ValidateClusterCatalogString() in the commands that CREATE or ALTER + * these database objects. + */ + LockRelationOid(AuthIdRelationId, AccessExclusiveLock); + LockRelationOid(DatabaseRelationId, AccessExclusiveLock); + LockRelationOid(DbRoleSettingRelationId, AccessExclusiveLock); + LockRelationOid(ParameterAclRelationId, AccessExclusiveLock); + LockRelationOid(ReplicationOriginRelationId, AccessExclusiveLock); + LockRelationOid(SharedDescriptionRelationId, AccessExclusiveLock); + LockRelationOid(SharedSecLabelRelationId, AccessExclusiveLock); + LockRelationOid(SubscriptionRelationId, AccessExclusiveLock); + LockRelationOid(TableSpaceRelationId, AccessExclusiveLock); + + /* No change? */ + if (GetClusterCatalogEncoding() == encoding) + return; + + if (encoding == -1) + { + /* There are no encoding restrictions for UNDEFINED. Good luck. */ + } + else if (encoding == PG_SQL_ASCII) + { + /* Make sure all shared catalogs contain only pure 7-bit ASCII. */ + + /* pg_authid */ + rel = table_open(AuthIdRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + Form_pg_authid authid = (Form_pg_authid) GETSTRUCT(tup); + + if (!pg_is_ascii(NameStr(authid->rolname))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing role name \"%s\" contains invalid characters", + NameStr(authid->rolname)), + errhint("Consider ALTER ROLE ... RENAME TO ... using ASCII characters."))); + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_database */ + rel = table_open(DatabaseRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + Form_pg_database db = (Form_pg_database) GETSTRUCT(tup); + + if (!pg_is_ascii(NameStr(db->datname))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing database name \"%s\" contains invalid characters", + NameStr(db->datname)), + errhint("Consider ALTER DATABASE ... RENAME TO ... using ASCII characters."))); + + /* + * Locale-related text fields requiring heap tuple deforming + * should already have been validated as pure ASCII, so we don't + * have to work harder here. + * + * XXX That's only true for the LC_ stuff; what about ICU, should + * it get the same treatment, or be checked here? + */ + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_db_role_setting */ + rel = table_open(DbRoleSettingRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + Datum setconfig; + + setconfig = heap_getattr(tup, Anum_pg_db_role_setting_setconfig, + RelationGetDescr(rel), &isnull); + if (!isnull) + { + List *gucNames; + List *gucValues; + ListCell *lc1; + ListCell *lc2; + + TransformGUCArray(DatumGetArrayTypeP(setconfig), &gucNames, &gucValues); + forboth(lc1, gucNames, lc2, gucValues) + { + char *name = lfirst(lc1); + char *value = lfirst(lc2); + + if (!pg_is_ascii(name) || !pg_is_ascii(value)) + { + Datum db_id; + Datum role_id; + + db_id = heap_getattr(tup, Anum_pg_db_role_setting_setdatabase, + RelationGetDescr(rel), &isnull); + role_id = heap_getattr(tup, Anum_pg_db_role_setting_setrole, + RelationGetDescr(rel), &isnull); + + if (DatumGetObjectId(db_id) == InvalidOid) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("role \"%s\" has setting \"%s\" with value \"%s\" that contains invalid characters", + GetUserNameFromId(DatumGetObjectId(role_id), false), + name, + value), + errhint("Consider ALTER ROLE ... SET ... TO ... using ASCII characters."))); + else + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("role \"%s\" has setting \"%s\" with value \"%s\" in database \"%s\" that contains invalid characters", + GetUserNameFromId(DatumGetObjectId(role_id), false), + name, + value, + get_database_name(DatumGetObjectId(db_id))), + errhint("Consider ALTER ROLE ... IN DATABASE ... SET ... TO ... using ASCII characters."))); + } + pfree(name); + pfree(value); + } + list_free(gucNames); + list_free(gucValues); + } + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_parameter_acl */ + rel = table_open(ParameterAclRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + char *parname; + + parname = TextDatumGetCString(heap_getattr(tup, Anum_pg_parameter_acl_parname, + RelationGetDescr(rel), &isnull)); + + /* + * This probably shouldn't happen as they are GUC names, so it's + * hard to suggest a useful hint. + */ + if (!pg_is_ascii(parname)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing ACL parameter name name \"%s\" contains invalid characters", + parname))); + pfree(parname); + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_replication_origin */ + rel = table_open(ReplicationOriginRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + char *s; + + s = TextDatumGetCString(heap_getattr(tup, Anum_pg_replication_origin_roname, + RelationGetDescr(rel), &isnull)); + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("replication origin \"%s\" contains invalid characters", + s), + errhint("Consider recreating the replication origin using ASCII characters."))); + pfree(s); + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_shdescription */ + rel = table_open(SharedDescriptionRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + char *s; + + s = TextDatumGetCString(heap_getattr(tup, Anum_pg_shdescription_description, + RelationGetDescr(rel), &isnull)); + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("comment \"%s\" on a shared database object contains invalid characters", + s), + errhint("Consider COMMENT ON ... IS ... using ASCII characters."))); + pfree(s); + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_shseclabel */ + rel = table_open(SharedSecLabelRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + char *s; + + s = TextDatumGetCString(heap_getattr(tup, Anum_pg_shseclabel_provider, + RelationGetDescr(rel), &isnull)); + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("security label provider name \"%s\" contains invalid characters", + s), + errhint("This security label provider cannot be used with CATALOG ENCODING set to ASCII."))); + pfree(s); + + s = TextDatumGetCString(heap_getattr(tup, Anum_pg_shseclabel_label, + RelationGetDescr(rel), &isnull)); + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("a security label on a shared database object contains invalid characters"), + errhint("Security labels applied to shared database objects must be representable in the CATALOG ENCODING."))); + pfree(s); + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_subscription */ + rel = table_open(SubscriptionRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + bool isnull; + char *name; + char *s; + + name = NameStr(*DatumGetName(heap_getattr(tup, Anum_pg_subscription_subname, + RelationGetDescr(rel), &isnull))); + if (!pg_is_ascii(name)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing subscription name \"%s\" contains invalid characters", + name), + errhint("Consider ALTER SUBSCRIPTION ... RENAME TO ... using ASCII characters."))); + + s = TextDatumGetCString(heap_getattr(tup, Anum_pg_subscription_subconninfo, + RelationGetDescr(rel), &isnull)); + if (!pg_is_ascii(s)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing subscription \"%s\" has connection string \"%s\" containing invalid characters", + name, s), + errhint("Consider ALTER SUBSCRIPTION ... CONNECTION ... using ASCII characters."))); + pfree(s); + + /* + * subsynccommit, subslotname and suborigin have their own + * validation that requires ASCII, so no check for now. + */ + + /* XXX TODO check subpublications, a text[] */ + } + systable_endscan(scan); + table_close(rel, NoLock); + + /* pg_tablespace */ + rel = table_open(TableSpaceRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + Form_pg_tablespace ts = (Form_pg_tablespace) GETSTRUCT(tup); + + if (!pg_is_ascii(NameStr(ts->spcname))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("existing tablespace name \"%s\" contains invalid characters", + NameStr(ts->spcname)), + errhint("Consider ALTER TABLESPACE ... RENAME TO ... using ASCII characters."))); + } + systable_endscan(scan); + table_close(rel, NoLock); + } + else + { + /* Make sure all databases are using this encoding. */ + rel = table_open(DatabaseRelationId, NoLock); + scan = systable_beginscan(rel, InvalidOid, false, NULL, 0, NULL); + while ((tup = systable_getnext(scan))) + { + Form_pg_database db = (Form_pg_database) GETSTRUCT(tup); + + if (db->encoding != encoding) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("database \"%s\" has incompatible encoding %s", + NameStr(db->datname), + pg_encoding_to_char(db->encoding)))); + } + systable_endscan(scan); + table_close(rel, NoLock); + } + + /* If we made it this far, we are allowed to change it. */ + SetClusterCatalogEncoding(encoding); +} + +const char * +show_cluster_catalog_encoding(void) +{ + int encoding; + + encoding = GetClusterCatalogEncoding(); + if (encoding == -1) + return "UNDEFINED"; + else if (encoding == PG_SQL_ASCII) + return "ASCII"; + else + return "DATABASE"; +} diff --git a/src/backend/catalog/meson.build b/src/backend/catalog/meson.build index 2f3ded8a0e7..ba7ac5ce35f 100644 --- a/src/backend/catalog/meson.build +++ b/src/backend/catalog/meson.build @@ -4,6 +4,7 @@ backend_sources += files( 'aclchk.c', 'catalog.c', 'dependency.c', + 'encoding.c', 'heap.c', 'index.c', 'indexing.c', diff --git a/src/backend/catalog/pg_db_role_setting.c b/src/backend/catalog/pg_db_role_setting.c index 8c20f519fc0..d45bd2053c7 100644 --- a/src/backend/catalog/pg_db_role_setting.c +++ b/src/backend/catalog/pg_db_role_setting.c @@ -46,6 +46,11 @@ AlterSetting(Oid databaseid, Oid roleid, VariableSetStmt *setstmt) NULL, 2, scankey); tuple = systable_getnext(scan); + if (setstmt->name) + ValidateClusterCatalogString(rel, setstmt->name); + if (valuestr) + ValidateClusterCatalogString(rel, valuestr); + /* * There are three cases: * diff --git a/src/backend/commands/alter.c b/src/backend/commands/alter.c index a45f3bb6b83..09cfc8775f7 100644 --- a/src/backend/commands/alter.c +++ b/src/backend/commands/alter.c @@ -1038,3 +1038,21 @@ AlterObjectOwner_internal(Oid classId, Oid objectId, Oid new_ownerId) table_close(rel, RowExclusiveLock); } + +/* + * Main entry point for ALTER SYSTEM command. + */ +void +AlterSystem(AlterSystemStmt *stmt) +{ + if (stmt->setstmt) + { + /* ALTER SYSTEM [RE]SET ... */ + AlterSystemSetConfigFile(stmt); + } + else if (stmt->encoding_name) + { + /* ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ... */ + AlterSystemSetClusterCatalogEncoding(stmt->encoding_name); + } +} diff --git a/src/backend/commands/comment.c b/src/backend/commands/comment.c index e9d50fc7d87..248208490d1 100644 --- a/src/backend/commands/comment.c +++ b/src/backend/commands/comment.c @@ -277,6 +277,9 @@ CreateSharedComments(Oid oid, Oid classoid, const char *comment) shdescription = table_open(SharedDescriptionRelationId, RowExclusiveLock); + if (comment) + ValidateClusterCatalogString(shdescription, comment); + sd = systable_beginscan(shdescription, SharedDescriptionObjIndexId, true, NULL, 2, skey); diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index aa91a396967..f24dbb64c25 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -1429,6 +1429,32 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt) Assert((dblocprovider != COLLPROVIDER_LIBC && dblocale) || (dblocprovider == COLLPROVIDER_LIBC && !dblocale)); + /* + * Check encoding of strings going into shared catalog. Locales have + * already been verified as ASCII by checklocale() so we skip those. + */ + ValidateClusterCatalogString(pg_database_rel, dbname); + if (dblocale) + ValidateClusterCatalogString(pg_database_rel, dblocale); + if (dbicurules) + ValidateClusterCatalogString(pg_database_rel, dbicurules); + if (dbcollversion) + ValidateClusterCatalogString(pg_database_rel, dbcollversion); + + /* + * Check encoding of the contents of the data, for compatibility with the + * shared catalogs. + */ + if (GetClusterCatalogEncoding() != -1 && + GetClusterCatalogEncoding() != PG_SQL_ASCII && + GetClusterCatalogEncoding() != encoding) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("encoding \"%s\" is not compatible with CLUSTER CATALOG ENCODING \"%s\"", + pg_encoding_to_char(encoding), + pg_encoding_to_char(GetClusterCatalogEncoding())), + errhint("Consider ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII."))); + /* Form tuple */ new_record[Anum_pg_database_oid - 1] = ObjectIdGetDatum(dboid); new_record[Anum_pg_database_datname - 1] = @@ -1889,6 +1915,8 @@ RenameDatabase(const char *oldname, const char *newname) */ rel = table_open(DatabaseRelationId, RowExclusiveLock); + ValidateClusterCatalogString(rel, newname); + if (!get_db_info(oldname, AccessExclusiveLock, &db_id, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)) ereport(ERROR, diff --git a/src/backend/commands/seclabel.c b/src/backend/commands/seclabel.c index 5607273bf9f..81856578806 100644 --- a/src/backend/commands/seclabel.c +++ b/src/backend/commands/seclabel.c @@ -363,6 +363,9 @@ SetSharedSecurityLabel(const ObjectAddress *object, pg_shseclabel = table_open(SharedSecLabelRelationId, RowExclusiveLock); + ValidateClusterCatalogString(pg_shseclabel, provider); + ValidateClusterCatalogString(pg_shseclabel, label); + scan = systable_beginscan(pg_shseclabel, SharedSecLabelObjectIndexId, true, NULL, 3, keys); diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index 03e97730e73..2012c73e233 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -552,6 +552,7 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt, bits32 supported_opts; SubOpts opts = {0}; AclResult aclresult; + ListCell *l; /* * Parse and check options. @@ -619,6 +620,11 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); + ValidateClusterCatalogString(rel, stmt->subname); + ValidateClusterCatalogString(rel, stmt->conninfo); + foreach(l, stmt->publication) + ValidateClusterCatalogString(rel, strVal(lfirst(l))); + /* Check if name is used */ subid = GetSysCacheOid2(SUBSCRIPTIONNAME, Anum_pg_subscription_oid, MyDatabaseId, CStringGetDatum(stmt->subname)); diff --git a/src/backend/commands/tablespace.c b/src/backend/commands/tablespace.c index 8ebbd935b0c..ef9856574f0 100644 --- a/src/backend/commands/tablespace.c +++ b/src/backend/commands/tablespace.c @@ -311,6 +311,8 @@ CreateTableSpace(CreateTableSpaceStmt *stmt) */ rel = table_open(TableSpaceRelationId, RowExclusiveLock); + ValidateClusterCatalogString(rel, stmt->tablespacename); + if (IsBinaryUpgrade) { /* Use binary-upgrade override for tablespace oid */ @@ -941,6 +943,8 @@ RenameTableSpace(const char *oldname, const char *newname) /* Search pg_tablespace */ rel = table_open(TableSpaceRelationId, RowExclusiveLock); + ValidateClusterCatalogString(rel, newname); + ScanKeyInit(&entry[0], Anum_pg_tablespace_spcname, BTEqualStrategyNumber, F_NAMEEQ, diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c index e7ade898a47..e91cf231625 100644 --- a/src/backend/commands/user.c +++ b/src/backend/commands/user.c @@ -371,6 +371,8 @@ CreateRole(ParseState *pstate, CreateRoleStmt *stmt) pg_authid_rel = table_open(AuthIdRelationId, RowExclusiveLock); pg_authid_dsc = RelationGetDescr(pg_authid_rel); + ValidateClusterCatalogString(pg_authid_rel, stmt->role); + if (OidIsValid(get_role_oid(stmt->role, true))) ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), @@ -1350,6 +1352,8 @@ RenameRole(const char *oldname, const char *newname) rel = table_open(AuthIdRelationId, RowExclusiveLock); dsc = RelationGetDescr(rel); + ValidateClusterCatalogString(rel, newname); + oldtuple = SearchSysCache1(AUTHNAME, CStringGetDatum(oldname)); if (!HeapTupleIsValid(oldtuple)) ereport(ERROR, diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index 67eb96396af..57495a10d24 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -1985,6 +1985,13 @@ VariableShowStmt: n->name = "session_authorization"; $$ = (Node *) n; } + | SHOW CLUSTER CATALOG_P ENCODING + { + VariableShowStmt *n = makeNode(VariableShowStmt); + + n->name = "cluster_catalog_encoding"; + $$ = (Node *) n; + } | SHOW ALL { VariableShowStmt *n = makeNode(VariableShowStmt); @@ -11540,6 +11547,13 @@ AlterSystemStmt: n->setstmt = $4; $$ = (Node *) n; } + | ALTER SYSTEM_P SET CLUSTER CATALOG_P ENCODING TO name + { + AlterSystemStmt *n = makeNode(AlterSystemStmt); + + n->encoding_name = $8; + $$ = (Node *) n; + } ; diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c index baf696d8e68..dc4866cff1b 100644 --- a/src/backend/replication/logical/origin.c +++ b/src/backend/replication/logical/origin.c @@ -286,6 +286,8 @@ replorigin_create(const char *roname) rel = table_open(ReplicationOriginRelationId, ExclusiveLock); + ValidateClusterCatalogString(rel, roname); + for (roident = InvalidOid + 1; roident < PG_UINT16_MAX; roident++) { bool nulls[Natts_pg_replication_origin]; diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c index f28bf371059..e6e6e6ab824 100644 --- a/src/backend/tcop/utility.c +++ b/src/backend/tcop/utility.c @@ -218,6 +218,8 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree) case T_AlterSystemStmt: { + AlterSystemStmt *stmt = (AlterSystemStmt *) parsetree; + /* * Surprisingly, ALTER SYSTEM meets all our definitions of * read-only: it changes nothing that affects the output of @@ -227,8 +229,13 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree) * * So, despite the fact that it writes to a file, it's read * only! + * + * XXX ^ that's about ALTER SYSTEM SET only */ - return COMMAND_IS_STRICTLY_READ_ONLY; + if (stmt->setstmt) + return COMMAND_IS_STRICTLY_READ_ONLY; + else + return COMMAND_IS_NOT_READ_ONLY; } case T_CallStmt: @@ -868,7 +875,7 @@ standard_ProcessUtility(PlannedStmt *pstmt, case T_AlterSystemStmt: PreventInTransactionBlock(isTopLevel, "ALTER SYSTEM"); - AlterSystemSetConfigFile((AlterSystemStmt *) parsetree); + AlterSystem((AlterSystemStmt *) parsetree); break; case T_VariableSetStmt: diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index 8cf1afbad20..31b012e2926 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -621,6 +621,7 @@ char *role_string; /* should be static, but guc.c needs to get at this */ bool in_hot_standby_guc; +static char *dummy = ""; /* * Displayable names for context types (enum GucContext) @@ -4813,6 +4814,17 @@ struct config_string ConfigureNamesString[] = check_restrict_nonsystem_relation_kind, assign_restrict_nonsystem_relation_kind, NULL }, + { + {"cluster_catalog_encoding", PGC_INTERNAL, PRESET_OPTIONS, + gettext_noop("The encoding of text in system catalogs that are shared by all databases in the cluster."), + NULL, + GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE | GUC_RUNTIME_COMPUTED + }, + &dummy, + "", + NULL, NULL, show_cluster_catalog_encoding + }, + /* End-of-list marker */ { {NULL, 0, 0, NULL, NULL}, NULL, NULL, NULL, NULL, NULL diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 9a91830783e..1e0e0342727 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -137,6 +137,7 @@ static char *share_path = NULL; /* values to be obtained from arguments */ static char *pg_data = NULL; static char *encoding = NULL; +static char *cluster_catalog_encoding = NULL; static char *locale = NULL; static char *lc_collate = NULL; static char *lc_ctype = NULL; @@ -173,6 +174,7 @@ static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ static const char *progname; static int encodingid; +static int cluster_catalog_encodingid; static char *bki_file; static char *hba_file; static char *ident_file; @@ -1593,6 +1595,7 @@ bootstrap_template1(void) printfPQExpBuffer(&cmd, "\"%s\" --boot %s %s", backend_exec, boot_options, extra_options); appendPQExpBuffer(&cmd, " -X %d", wal_segment_size_mb * (1024 * 1024)); + appendPQExpBuffer(&cmd, " -C %d", cluster_catalog_encodingid); if (data_checksums) appendPQExpBuffer(&cmd, " -k"); if (debug) @@ -2748,6 +2751,19 @@ setup_locale_encoding(void) else encodingid = get_encoding_id(encoding); + /* Choose initial value of CLUSTER CATALOG ENCODING. */ + if (cluster_catalog_encoding == NULL || + pg_strcasecmp(cluster_catalog_encoding, "DATABASE") == 0) + cluster_catalog_encodingid = encodingid; + else if (pg_strcasecmp(cluster_catalog_encoding, "ASCII") == 0) + cluster_catalog_encodingid = PG_SQL_ASCII; + else if (pg_strcasecmp(cluster_catalog_encoding, "UNDEFINED") == 0) + cluster_catalog_encodingid = -1; + printf(_("The initial cluster catalog encoding has been set to \"%s\".\n"), + cluster_catalog_encodingid == -1 ? "UNDEFINED" : + cluster_catalog_encodingid == PG_SQL_ASCII ? "ASCII" : + pg_encoding_to_char(cluster_catalog_encodingid)); + if (!check_locale_encoding(lc_ctype, encodingid) || !check_locale_encoding(lc_collate, encodingid)) exit(1); /* check_locale_encoding printed the error */ @@ -3146,6 +3162,7 @@ main(int argc, char *argv[]) static struct option long_options[] = { {"pgdata", required_argument, NULL, 'D'}, {"encoding", required_argument, NULL, 'E'}, + {"cluster-catalog-encoding", required_argument, NULL, 'C'}, {"locale", required_argument, NULL, 1}, {"lc-collate", required_argument, NULL, 2}, {"lc-ctype", required_argument, NULL, 3}, @@ -3224,7 +3241,7 @@ main(int argc, char *argv[]) /* process command-line options */ - while ((c = getopt_long(argc, argv, "A:c:dD:E:gkL:nNsST:U:WX:", + while ((c = getopt_long(argc, argv, "A:c:C:dD:E:gkL:nNsST:U:WX:", long_options, &option_index)) != -1) { switch (c) @@ -3272,6 +3289,9 @@ main(int argc, char *argv[]) case 'E': encoding = pg_strdup(optarg); break; + case 'C': + cluster_catalog_encoding = pg_strdup(optarg); + break; case 'W': pwprompt = true; break; diff --git a/src/bin/pg_controldata/pg_controldata.c b/src/bin/pg_controldata/pg_controldata.c index 93a05d80ca7..91ae8a920ce 100644 --- a/src/bin/pg_controldata/pg_controldata.c +++ b/src/bin/pg_controldata/pg_controldata.c @@ -27,6 +27,7 @@ #include "common/controldata_utils.h" #include "common/logging.h" #include "getopt_long.h" +#include "mb/pg_wchar.h" #include "pg_getopt.h" static void @@ -325,6 +326,8 @@ main(int argc, char *argv[]) (ControlFile->float8ByVal ? _("by value") : _("by reference"))); printf(_("Data page checksum version: %u\n"), ControlFile->data_checksum_version); + printf(_("Cluster catalog encoding: %d\n"), + ControlFile->cluster_catalog_encoding); printf(_("Mock authentication nonce: %s\n"), mock_auth_nonce_str); return 0; diff --git a/src/bin/pg_resetwal/pg_resetwal.c b/src/bin/pg_resetwal/pg_resetwal.c index e9dcb5a6d89..c7d02cdb37d 100644 --- a/src/bin/pg_resetwal/pg_resetwal.c +++ b/src/bin/pg_resetwal/pg_resetwal.c @@ -779,6 +779,8 @@ PrintControlValues(bool guessed) (ControlFile.float8ByVal ? _("by value") : _("by reference"))); printf(_("Data page checksum version: %u\n"), ControlFile.data_checksum_version); + printf(_("Cluster catalog encoding: %d\n"), + ControlFile.cluster_catalog_encoding); } diff --git a/src/bin/pg_upgrade/controldata.c b/src/bin/pg_upgrade/controldata.c index 854c6887a23..7b32848707d 100644 --- a/src/bin/pg_upgrade/controldata.c +++ b/src/bin/pg_upgrade/controldata.c @@ -61,6 +61,7 @@ get_control_data(ClusterInfo *cluster) bool got_large_object = false; bool got_date_is_int = false; bool got_data_checksum_version = false; + bool got_cluster_catalog_encoding = false; bool got_cluster_state = false; char *lc_collate = NULL; char *lc_ctype = NULL; @@ -501,6 +502,16 @@ get_control_data(ClusterInfo *cluster) cluster->controldata.data_checksum_version = str2uint(p); got_data_checksum_version = true; } + else if ((p = strstr(bufin, "Cluster catalog encoding")) != NULL) + { + p = strchr(p, ':'); + + if (p == NULL || strlen(p) <= 1) + pg_fatal("%d: controldata retrieval problem", __LINE__); + p++; + cluster->controldata.cluster_catalog_encoding = atoi(p); + got_cluster_catalog_encoding = true; + } } rc = pclose(output); @@ -561,6 +572,11 @@ get_control_data(ClusterInfo *cluster) } } + if (GET_MAJOR_VERSION(cluster->major_version) < 1800) + cluster->controldata.cluster_catalog_encoding = -1; /* UNDEFINED */ + else if (!got_cluster_catalog_encoding) + pg_fatal("Expected cluster catalog encoding from version 18+"); + /* verify that we got all the mandatory pg_control data */ if (!got_xid || !got_oid || !got_multi || !got_oldestxid || diff --git a/src/bin/pg_upgrade/pg_upgrade.c b/src/bin/pg_upgrade/pg_upgrade.c index 663235816f8..d79f7c83802 100644 --- a/src/bin/pg_upgrade/pg_upgrade.c +++ b/src/bin/pg_upgrade/pg_upgrade.c @@ -467,6 +467,23 @@ set_locale_and_encoding(void) PQfreemem(datctype_literal); PQfreemem(datlocale_literal); + /* + * Copy the CLUSTER CATALOG ENCODING. This will be UNDEFINED if the + * source database is from before v18. + */ + if (old_cluster.controldata.cluster_catalog_encoding == -1) + PQclear(executeQueryOrDie(conn_new_template1, + "ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO UNDEFINED")); + else if (old_cluster.controldata.cluster_catalog_encoding == 0) + PQclear(executeQueryOrDie(conn_new_template1, + "ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII")); + else if (old_cluster.controldata.cluster_catalog_encoding != locale->db_encoding) + pg_fatal("Source database has template0 encoding %d, but cluster_catalog_encoding %d", + locale->db_encoding, old_cluster.controldata.cluster_catalog_encoding); + else + PQclear(executeQueryOrDie(conn_new_template1, + "ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE")); + PQfinish(conn_new_template1); check_ok(); diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h index 53f693c2d4b..e5baf647051 100644 --- a/src/bin/pg_upgrade/pg_upgrade.h +++ b/src/bin/pg_upgrade/pg_upgrade.h @@ -245,6 +245,7 @@ typedef struct bool date_is_int; bool float8_pass_by_value; uint32 data_checksum_version; + int cluster_catalog_encoding; } ControlData; /* diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index bbd08770c3d..ad70f7f8340 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -2551,11 +2551,18 @@ match_previous_words(int pattern_id, /* ALTER SYSTEM SET, RESET, RESET ALL */ else if (Matches("ALTER", "SYSTEM")) COMPLETE_WITH("SET", "RESET"); - else if (Matches("ALTER", "SYSTEM", "SET|RESET")) + else if (Matches("ALTER", "SYSTEM", "SET")) + COMPLETE_WITH_QUERY_VERBATIM_PLUS(Query_for_list_of_alter_system_set_vars, + "CLUSTER CATALOG ENCODING TO"); + else if (Matches("ALTER", "SYSTEM", "RESET")) COMPLETE_WITH_QUERY_VERBATIM_PLUS(Query_for_list_of_alter_system_set_vars, "ALL"); + else if (Matches("ALTER", "SYSTEM", "SET", "CLUSTER")) + COMPLETE_WITH("TO", "CATALOG ENCODING TO"); else if (Matches("ALTER", "SYSTEM", "SET", MatchAny)) COMPLETE_WITH("TO"); + else if (Matches("ALTER", "SYSTEM", "SET", "CLUSTER", "CATALOG", "ENCODING", "TO")) + COMPLETE_WITH("DATABASE", "ASCII", "UNDEFINED"); /* ALTER VIEW */ else if (Matches("ALTER", "VIEW", MatchAny)) COMPLETE_WITH("ALTER COLUMN", "OWNER TO", "RENAME", "RESET", "SET"); @@ -4882,10 +4889,13 @@ match_previous_words(int pattern_id, "ALL"); else if (Matches("SHOW")) COMPLETE_WITH_QUERY_VERBATIM_PLUS(Query_for_list_of_show_vars, + "CLUSTER CATALOG ENCODING", "SESSION AUTHORIZATION", "ALL"); else if (Matches("SHOW", "SESSION")) COMPLETE_WITH("AUTHORIZATION"); + else if (Matches("SHOW", "CLUSTER")) + COMPLETE_WITH("CATALOG ENCODING"); /* Complete "SET TRANSACTION" */ else if (Matches("SET", "TRANSACTION")) COMPLETE_WITH("SNAPSHOT", "ISOLATION LEVEL", "READ", "DEFERRABLE", "NOT DEFERRABLE"); diff --git a/src/bin/scripts/t/020_createdb.pl b/src/bin/scripts/t/020_createdb.pl index 4a0e2c883a1..a2e0d0944f7 100644 --- a/src/bin/scripts/t/020_createdb.pl +++ b/src/bin/scripts/t/020_createdb.pl @@ -12,8 +12,10 @@ program_help_ok('createdb'); program_version_ok('createdb'); program_options_handling_ok('createdb'); +# Because we're using different encodings in the same cluster, we need shared +# catalog encoding set to ASCII for this test. my $node = PostgreSQL::Test::Cluster->new('main'); -$node->init; +$node->init(extra => [ '--cluster-catalog-encoding=ASCII' ]); $node->start; $node->issues_sql_like( diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 34ad46c067b..ef686479415 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -234,7 +234,8 @@ extern bool DataChecksumsEnabled(void); extern XLogRecPtr GetFakeLSNForUnloggedRel(void); extern Size XLOGShmemSize(void); extern void XLOGShmemInit(void); -extern void BootStrapXLOG(uint32 data_checksum_version); +extern void BootStrapXLOG(int cluster_catalog_encoding, + uint32 data_checksum_version); extern void InitializeWalConsistencyChecking(void); extern void LocalProcessControlFile(bool reset); extern WalLevel GetActiveWalLevelOnStandby(void); @@ -253,6 +254,8 @@ extern XLogRecPtr GetFlushRecPtr(TimeLineID *insertTLI); extern TimeLineID GetWALInsertionTimeLine(void); extern TimeLineID GetWALInsertionTimeLineIfSet(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern int GetClusterCatalogEncoding(void); +extern void SetClusterCatalogEncoding(int encoding); extern void SetWalWriterSleeping(bool sleeping); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index d9cf51a0f9f..6bef50c14ec 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -305,6 +305,12 @@ typedef struct xl_end_of_recovery int wal_level; } xl_end_of_recovery; +/* Change of CLUSTER CATALOG ENCODING. */ +typedef struct xl_cluster_catalog_encoding_change +{ + int encoding; +} xl_cluster_catalog_encoding_change; + /* * The functions in xloginsert.c construct a chain of XLogRecData structs * to represent the final WAL record. diff --git a/src/include/catalog/catalog.h b/src/include/catalog/catalog.h index a8dd304b1ad..5ebd62319c0 100644 --- a/src/include/catalog/catalog.h +++ b/src/include/catalog/catalog.h @@ -43,5 +43,8 @@ extern Oid GetNewOidWithIndex(Relation relation, Oid indexId, extern RelFileNumber GetNewRelFileNumber(Oid reltablespace, Relation pg_class, char relpersistence); +extern void ValidateClusterCatalogString(Relation rel, const char *s); +extern void AlterSystemSetClusterCatalogEncoding(const char *encoding_name); +extern const char *show_cluster_catalog_encoding(void); #endif /* CATALOG_H */ diff --git a/src/include/catalog/pg_control.h b/src/include/catalog/pg_control.h index e80ff8e4140..96ad1007a65 100644 --- a/src/include/catalog/pg_control.h +++ b/src/include/catalog/pg_control.h @@ -77,7 +77,7 @@ typedef struct CheckPoint #define XLOG_END_OF_RECOVERY 0x90 #define XLOG_FPI_FOR_HINT 0xA0 #define XLOG_FPI 0xB0 -/* 0xC0 is used in Postgres 9.5-11 */ +#define XLOG_CLUSTER_CATALOG_ENCODING_CHANGE 0xC0 #define XLOG_OVERWRITE_CONTRECORD 0xD0 #define XLOG_CHECKPOINT_REDO 0xE0 @@ -221,6 +221,9 @@ typedef struct ControlFileData /* Are data pages protected by checksums? Zero if no checksum version */ uint32 data_checksum_version; + /* A pg_enc value, or -1 for UNKNOWN. */ + int cluster_catalog_encoding; + /* * Random nonce, used in authentication requests that need to proceed * based on values that are cluster-unique, like a SASL exchange that diff --git a/src/include/commands/alter.h b/src/include/commands/alter.h index f00af75beff..295d6726ebc 100644 --- a/src/include/commands/alter.h +++ b/src/include/commands/alter.h @@ -31,4 +31,6 @@ extern ObjectAddress ExecAlterOwnerStmt(AlterOwnerStmt *stmt); extern void AlterObjectOwner_internal(Oid classId, Oid objectId, Oid new_ownerId); +extern void AlterSystem(AlterSystemStmt *stmt); + #endif /* ALTER_H */ diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index 0f9462493e3..5698783571f 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -3841,6 +3841,7 @@ typedef struct AlterSystemStmt { NodeTag type; VariableSetStmt *setstmt; /* SET subcommand */ + const char *encoding_name; /* CATALOG ENCODING subcommand */ } AlterSystemStmt; /* ---------------------- diff --git a/src/test/modules/Makefile b/src/test/modules/Makefile index c0d3cf0e14b..5e8cf098185 100644 --- a/src/test/modules/Makefile +++ b/src/test/modules/Makefile @@ -10,6 +10,7 @@ SUBDIRS = \ delay_execution \ dummy_index_am \ dummy_seclabel \ + encoding \ libpq_pipeline \ plsample \ spgist_name_ops \ diff --git a/src/test/modules/encoding/Makefile b/src/test/modules/encoding/Makefile new file mode 100644 index 00000000000..2e4d04a7bea --- /dev/null +++ b/src/test/modules/encoding/Makefile @@ -0,0 +1,17 @@ +# src/test/modules/encoding/Makefile + +REGRESS = encoding + +NO_INSTALLCHECK = 1 +ENCODING = UTF8 +NO_LOCALE = 1 + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/test/modules/encoding +top_builddir = ../../../.. +include $(top_builddir)/src/Makefile.global +endif diff --git a/src/test/modules/encoding/expected/cluster_catalog_encoding.out b/src/test/modules/encoding/expected/cluster_catalog_encoding.out new file mode 100644 index 00000000000..c575241c896 --- /dev/null +++ b/src/test/modules/encoding/expected/cluster_catalog_encoding.out @@ -0,0 +1,208 @@ +-- Exercise the ValidateClusterCatalogString() calls that should cover all +-- entry points (a few cases have ASCII-only validation of their own and give +-- slightly different error messages). +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +SHOW CLUSTER CATALOG ENCODING; + cluster_catalog_encoding +-------------------------- + ASCII +(1 row) + +-- pg_authid +CREATE USER regress_astérix; +ERROR: the string "regress_astérix" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE USER regress_fred; +ALTER USER regress_fred RENAME TO regress_astérix; +ERROR: the string "regress_astérix" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +DROP USER regress_fred; +-- pg_database +CREATE DATABASE regression_café; +ERROR: the string "regression_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +ALTER DATABASE template1 RENAME TO regression_café; +ERROR: the string "regression_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE DATABASE regression_ok TEMPLATE template0 LOCALE 'français'; +WARNING: locale name "français" contains non-ASCII characters +ERROR: invalid LC_COLLATE locale name: "français" +HINT: If the locale name is specific to ICU, use ICU_LOCALE. +-- pg_db_role_setting +CREATE USER regress_fred; +ALTER ROLE regress_fred SET application_name TO 'café'; +ERROR: the string "café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +DROP USER regress_fred; +-- pg_parameter_acl +-- XXX +-- pg_replication_origin +SELECT pg_replication_origin_create('regress_café'); +ERROR: the string "regress_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +-- pg_shdescription +COMMENT ON DATABASE template0 IS 'café'; +ERROR: the string "café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +-- non-shared objects are OK, because non-shared catalog +COMMENT ON TABLE pg_catalog.pg_class IS 'café'; +COMMENT ON TABLE pg_catalog.pg_class IS NULL; +-- pg_shseclabel +-- XXX +-- pg_subscription +CREATE SUBSCRIPTION regress_café CONNECTION 'dbname=crême' PUBLICATION brûlée; +ERROR: the string "regress_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=crême' PUBLICATION brûlée; +ERROR: the string "dbname=crême" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION brûlée; +ERROR: the string "brûlée" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (slot_name = 'café'); +ERROR: replication slot name "café" contains invalid character +HINT: Replication slot names may only contain lower case letters, numbers, and the underscore character. +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (synchronous_commit = 'café'); +ERROR: invalid value for parameter "synchronous_commit": "café" +HINT: Available values: local, remote_write, remote_apply, on, off. +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (origin = 'café'); +ERROR: unrecognized origin value: "café" +-- pg_tablespace +SET allow_in_place_tablespaces = 'on'; +CREATE TABLESPACE regress_café LOCATION ''; +ERROR: the string "regress_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +CREATE TABLESPACE regress_ok LOCATION ''; +ALTER TABLESPACE regress_ok RENAME TO regress_café; +ERROR: the string "regress_café" contains invalid characters +DETAIL: CLUSTER CATALOG ENCODING is set to ASCII. +HINT: Consider ALTER SYSTEM SET CATALOG ENCODING TO DATABASE. +DROP TABLESPACE regress_ok; +-- Check that we can create a new database with a different encoding, +-- while the shared catalog encoding is ASCII +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; +-- Check that we can't change the shared catalog encoding to UTF8, because that +-- LATIN1 database is in the way, then drop it so we can. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +ERROR: database "regression_latin1" has incompatible encoding LATIN1 +DROP DATABASE regression_latin1; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +-- Test that we can now do each of those things that failed before, and that +-- those things block us from going back to ASCII. +-- pg_authid +CREATE USER regress_astérix; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: existing role name "regress_astérix" contains invalid characters +HINT: Consider ALTER ROLE ... RENAME TO ... using ASCII characters. +DROP USER regress_astérix; +-- pg_database +CREATE DATABASE regression_café; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: existing database name "regression_café" contains invalid characters +HINT: Consider ALTER DATABASE ... RENAME TO ... using ASCII characters. +DROP DATABASE regression_café; +-- but we can't make a LATIN1 database while we have UTF8 catalogs +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; +ERROR: encoding "LATIN1" is not compatible with CLUSTER CATALOG ENCODING "UTF8" +HINT: Consider ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII. +-- pg_db_role_setting +CREATE USER regress_fred; +ALTER ROLE regress_fred SET application_name TO 'café'; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: role "regress_fred" has setting "application_name" with value "café" that contains invalid characters +HINT: Consider ALTER ROLE ... SET ... TO ... using ASCII characters. +DROP USER regress_fred; +-- pg_parameter_acl +-- XXX +-- pg_replication_origin +SELECT pg_replication_origin_create('regress_café'); + pg_replication_origin_create +------------------------------ + 1 +(1 row) + +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: replication origin "regress_café" contains invalid characters +HINT: Consider recreating the replication origin using ASCII characters. +SELECT pg_replication_origin_drop('regress_café'); + pg_replication_origin_drop +---------------------------- + +(1 row) + +-- pg_shdescription +COMMENT ON DATABASE template0 IS 'café'; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: comment "café" on a shared database object contains invalid characters +HINT: Consider COMMENT ON ... IS ... using ASCII characters. +COMMENT ON DATABASE template0 IS 'unmodifiable empty database'; +-- pg_shseclabel +-- XXX +-- pg_subscription +-- XXX +-- pg_tablespace +CREATE TABLESPACE regress_café LOCATION ''; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: existing tablespace name "regress_café" contains invalid characters +HINT: Consider ALTER TABLESPACE ... RENAME TO ... using ASCII characters. +DROP TABLESPACE regress_café; +-- We dropped everything that was in the way, so we should be able to go back +-- to ASCII now. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +-- Try out UNDEFINED mode, which is the only way to have a non-ASCII database +-- name and mutiple encodings at the same time +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO UNDEFINED; +SHOW CLUSTER CATALOG ENCODING; + cluster_catalog_encoding +-------------------------- + UNDEFINED +(1 row) + +CREATE DATABASE regression_café ENCODING UTF8; +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; +-- We can't switch to ASCII from this state +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: existing database name "regression_café" contains invalid characters +HINT: Consider ALTER DATABASE ... RENAME TO ... using ASCII characters. +SHOW CLUSTER CATALOG ENCODING; + cluster_catalog_encoding +-------------------------- + UNDEFINED +(1 row) + +-- We also can't switch to UTF8 from this state +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +ERROR: database "regression_latin1" has incompatible encoding LATIN1 +SHOW CLUSTER CATALOG ENCODING; + cluster_catalog_encoding +-------------------------- + UNDEFINED +(1 row) + +-- If we get rid of the LATIN1 database, we can go to UTF8 +DROP DATABASE regression_latin1; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +SHOW CLUSTER CATALOG ENCODING; + cluster_catalog_encoding +-------------------------- + DATABASE +(1 row) + +-- We still can't go back to ASCII unless we also get rid of the non-ASCII +-- database name. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +ERROR: existing database name "regression_café" contains invalid characters +HINT: Consider ALTER DATABASE ... RENAME TO ... using ASCII characters. +DROP DATABASE regression_café; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; diff --git a/src/test/modules/encoding/meson.build b/src/test/modules/encoding/meson.build new file mode 100644 index 00000000000..5f2254c87d8 --- /dev/null +++ b/src/test/modules/encoding/meson.build @@ -0,0 +1,14 @@ +# Copyright (c) 2024, PostgreSQL Global Development Group + +tests += { + 'name': 'encoding', + 'sd': meson.current_source_dir(), + 'bd': meson.current_build_dir(), + 'regress': { + 'sql': [ + 'cluster_catalog_encoding', + ], + 'regress_args': ['--no-locale', '--encoding=UTF8'], + 'runningcheck': false, + }, +} diff --git a/src/test/modules/encoding/sql/cluster_catalog_encoding.sql b/src/test/modules/encoding/sql/cluster_catalog_encoding.sql new file mode 100644 index 00000000000..983c2fdfd27 --- /dev/null +++ b/src/test/modules/encoding/sql/cluster_catalog_encoding.sql @@ -0,0 +1,137 @@ +-- Exercise the ValidateClusterCatalogString() calls that should cover all +-- entry points (a few cases have ASCII-only validation of their own and give +-- slightly different error messages). +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +SHOW CLUSTER CATALOG ENCODING; + +-- pg_authid +CREATE USER regress_astérix; +CREATE USER regress_fred; +ALTER USER regress_fred RENAME TO regress_astérix; +DROP USER regress_fred; + +-- pg_database +CREATE DATABASE regression_café; +ALTER DATABASE template1 RENAME TO regression_café; +CREATE DATABASE regression_ok TEMPLATE template0 LOCALE 'français'; + +-- pg_db_role_setting +CREATE USER regress_fred; +ALTER ROLE regress_fred SET application_name TO 'café'; +DROP USER regress_fred; + +-- pg_parameter_acl +-- XXX + +-- pg_replication_origin +SELECT pg_replication_origin_create('regress_café'); + +-- pg_shdescription +COMMENT ON DATABASE template0 IS 'café'; +-- non-shared objects are OK, because non-shared catalog +COMMENT ON TABLE pg_catalog.pg_class IS 'café'; +COMMENT ON TABLE pg_catalog.pg_class IS NULL; + +-- pg_shseclabel +-- XXX + +-- pg_subscription +CREATE SUBSCRIPTION regress_café CONNECTION 'dbname=crême' PUBLICATION brûlée; +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=crême' PUBLICATION brûlée; +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION brûlée; +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (slot_name = 'café'); +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (synchronous_commit = 'café'); +CREATE SUBSCRIPTION regress_ok CONNECTION 'dbname=ok' PUBLICATION ok WITH (origin = 'café'); + +-- pg_tablespace +SET allow_in_place_tablespaces = 'on'; +CREATE TABLESPACE regress_café LOCATION ''; +CREATE TABLESPACE regress_ok LOCATION ''; +ALTER TABLESPACE regress_ok RENAME TO regress_café; +DROP TABLESPACE regress_ok; + +-- Check that we can create a new database with a different encoding, +-- while the shared catalog encoding is ASCII +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; + +-- Check that we can't change the shared catalog encoding to UTF8, because that +-- LATIN1 database is in the way, then drop it so we can. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +DROP DATABASE regression_latin1; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; + +-- Test that we can now do each of those things that failed before, and that +-- those things block us from going back to ASCII. + +-- pg_authid +CREATE USER regress_astérix; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +DROP USER regress_astérix; + +-- pg_database +CREATE DATABASE regression_café; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +DROP DATABASE regression_café; +-- but we can't make a LATIN1 database while we have UTF8 catalogs +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; + +-- pg_db_role_setting +CREATE USER regress_fred; +ALTER ROLE regress_fred SET application_name TO 'café'; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +DROP USER regress_fred; + +-- pg_parameter_acl +-- XXX + +-- pg_replication_origin +SELECT pg_replication_origin_create('regress_café'); +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +SELECT pg_replication_origin_drop('regress_café'); + +-- pg_shdescription +COMMENT ON DATABASE template0 IS 'café'; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +COMMENT ON DATABASE template0 IS 'unmodifiable empty database'; + +-- pg_shseclabel +-- XXX + +-- pg_subscription +-- XXX + +-- pg_tablespace +CREATE TABLESPACE regress_café LOCATION ''; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +DROP TABLESPACE regress_café; + +-- We dropped everything that was in the way, so we should be able to go back +-- to ASCII now. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; + +-- Try out UNDEFINED mode, which is the only way to have a non-ASCII database +-- name and mutiple encodings at the same time +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO UNDEFINED; +SHOW CLUSTER CATALOG ENCODING; +CREATE DATABASE regression_café ENCODING UTF8; +CREATE DATABASE regression_latin1 TEMPLATE template0 LOCALE 'C' ENCODING LATIN1; + +-- We can't switch to ASCII from this state +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +SHOW CLUSTER CATALOG ENCODING; + +-- We also can't switch to UTF8 from this state +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +SHOW CLUSTER CATALOG ENCODING; + +-- If we get rid of the LATIN1 database, we can go to UTF8 +DROP DATABASE regression_latin1; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO DATABASE; +SHOW CLUSTER CATALOG ENCODING; + +-- We still can't go back to ASCII unless we also get rid of the non-ASCII +-- database name. +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; +DROP DATABASE regression_café; +ALTER SYSTEM SET CLUSTER CATALOG ENCODING TO ASCII; + diff --git a/src/test/modules/meson.build b/src/test/modules/meson.build index c829b619530..1e4dc8b3bfd 100644 --- a/src/test/modules/meson.build +++ b/src/test/modules/meson.build @@ -5,6 +5,7 @@ subdir('commit_ts') subdir('delay_execution') subdir('dummy_index_am') subdir('dummy_seclabel') +subdir('encoding') subdir('gin') subdir('injection_points') subdir('ldap_password_func') diff --git a/src/test/regress/expected/database.out b/src/test/regress/expected/database.out index 454db91ec09..04279a2870c 100644 --- a/src/test/regress/expected/database.out +++ b/src/test/regress/expected/database.out @@ -1,15 +1,15 @@ CREATE DATABASE regression_tbd - ENCODING utf8 LC_COLLATE "C" LC_CTYPE "C" TEMPLATE template0; -ALTER DATABASE regression_tbd RENAME TO regression_utf8; -ALTER DATABASE regression_utf8 SET TABLESPACE regress_tblspace; -ALTER DATABASE regression_utf8 RESET TABLESPACE; -ALTER DATABASE regression_utf8 CONNECTION_LIMIT 123; + LC_COLLATE "C" LC_CTYPE "C" TEMPLATE template0; +ALTER DATABASE regression_tbd RENAME TO regression_xyz; +ALTER DATABASE regression_xyz SET TABLESPACE regress_tblspace; +ALTER DATABASE regression_xyz RESET TABLESPACE; +ALTER DATABASE regression_xyz CONNECTION_LIMIT 123; -- Test PgDatabaseToastTable. Doing this with GRANT would be slow. BEGIN; UPDATE pg_database SET datacl = array_fill(makeaclitem(10, 10, 'USAGE', false), ARRAY[5e5::int]) -WHERE datname = 'regression_utf8'; +WHERE datname = 'regression_xyz'; -- load catcache entry, if nothing else does -ALTER DATABASE regression_utf8 RESET TABLESPACE; +ALTER DATABASE regression_xyz RESET TABLESPACE; ROLLBACK; -DROP DATABASE regression_utf8; +DROP DATABASE regression_xyz; diff --git a/src/test/regress/pg_regress.c b/src/test/regress/pg_regress.c index 0e40ed32a21..8a405f27cbc 100644 --- a/src/test/regress/pg_regress.c +++ b/src/test/regress/pg_regress.c @@ -2341,6 +2341,8 @@ regression_main(int argc, char *argv[], appendStringInfoString(&cmd, " --debug"); if (nolocale) appendStringInfoString(&cmd, " --no-locale"); + if (encoding) + appendStringInfo(&cmd, " --encoding %s", encoding); if (initdb_extra_opts_env) appendStringInfo(&cmd, " %s", initdb_extra_opts_env); appendStringInfo(&cmd, " > \"%s/log/initdb.log\" 2>&1", outputdir); diff --git a/src/test/regress/sql/database.sql b/src/test/regress/sql/database.sql index 0367c0e37ab..dd84f866e4a 100644 --- a/src/test/regress/sql/database.sql +++ b/src/test/regress/sql/database.sql @@ -1,17 +1,17 @@ CREATE DATABASE regression_tbd - ENCODING utf8 LC_COLLATE "C" LC_CTYPE "C" TEMPLATE template0; -ALTER DATABASE regression_tbd RENAME TO regression_utf8; -ALTER DATABASE regression_utf8 SET TABLESPACE regress_tblspace; -ALTER DATABASE regression_utf8 RESET TABLESPACE; -ALTER DATABASE regression_utf8 CONNECTION_LIMIT 123; + LC_COLLATE "C" LC_CTYPE "C" TEMPLATE template0; +ALTER DATABASE regression_tbd RENAME TO regression_xyz; +ALTER DATABASE regression_xyz SET TABLESPACE regress_tblspace; +ALTER DATABASE regression_xyz RESET TABLESPACE; +ALTER DATABASE regression_xyz CONNECTION_LIMIT 123; -- Test PgDatabaseToastTable. Doing this with GRANT would be slow. BEGIN; UPDATE pg_database SET datacl = array_fill(makeaclitem(10, 10, 'USAGE', false), ARRAY[5e5::int]) -WHERE datname = 'regression_utf8'; +WHERE datname = 'regression_xyz'; -- load catcache entry, if nothing else does -ALTER DATABASE regression_utf8 RESET TABLESPACE; +ALTER DATABASE regression_xyz RESET TABLESPACE; ROLLBACK; -DROP DATABASE regression_utf8; +DROP DATABASE regression_xyz; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 2d4c870423a..f2984dcb876 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -4087,6 +4087,7 @@ xl_btree_unlink_page xl_btree_update xl_btree_vacuum xl_clog_truncate +xl_cluster_catalog_encoding_change xl_commit_ts_truncate xl_dbase_create_file_copy_rec xl_dbase_create_wal_log_rec -- 2.39.5 (Apple Git-154)