From 68b05c20a68098613fbe6657ddb2b07c5ffd3d0b Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Mon, 24 Nov 2025 14:00:52 -0800 Subject: [PATCH v12 8/8] Control LC_COLLATE with GUC. Now that the global LC_COLLATE setting is not used for any in-core purpose at all (see commit 5e6e42e44f), allow it to be set with a GUC. This may be useful for extensions or procedural languages that still depend on the global LC_COLLATE setting. TODO: needs discussion Discussion: https://postgr.es/m/450ceb6260cad30d7afdf155d991a9caafee7c0d.camel@j-davis.com --- src/backend/utils/adt/pg_locale.c | 59 +++++++++++++++++++ src/backend/utils/init/postinit.c | 2 + src/backend/utils/misc/guc_parameters.dat | 9 +++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/bin/initdb/initdb.c | 3 + src/include/utils/guc_hooks.h | 2 + src/include/utils/pg_locale.h | 1 + 7 files changed, 78 insertions(+) diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index ee08ac045b7..6dfbe8af47b 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -81,6 +81,7 @@ extern pg_locale_t create_pg_locale_libc(Oid collid, MemoryContext context); extern char *get_collation_actual_version_libc(const char *collcollate); /* GUC settings */ +char *locale_collate; char *locale_messages; char *locale_monetary; char *locale_numeric; @@ -369,6 +370,64 @@ assign_locale_time(const char *newval, void *extra) CurrentLCTimeValid = false; } +/* + * We allow LC_COLLATE to actually be set globally. + * + * Note: we normally disallow value = "" because it wouldn't have consistent + * semantics (it'd effectively just use the previous value). However, this + * is the value passed for PGC_S_DEFAULT, so don't complain in that case, + * not even if the attempted setting fails due to invalid environment value. + * The idea there is just to accept the environment setting *if possible* + * during startup, until we can read the proper value from postgresql.conf. + */ +bool +check_locale_collate(char **newval, void **extra, GucSource source) +{ + int locale_enc; + int db_enc; + + if (**newval == '\0') + { + if (source == PGC_S_DEFAULT) + return true; + else + return false; + } + + locale_enc = pg_get_encoding_from_locale(*newval, true); + db_enc = GetDatabaseEncoding(); + + if (!(locale_enc == db_enc || + locale_enc == PG_SQL_ASCII || + db_enc == PG_SQL_ASCII || + locale_enc == -1)) + { + if (source == PGC_S_FILE) + { + guc_free(*newval); + *newval = guc_strdup(LOG, "C"); + if (!*newval) + return false; + } + else if (source != PGC_S_TEST) + { + ereport(WARNING, + (errmsg("encoding mismatch"), + errdetail("Locale \"%s\" uses encoding \"%s\", which does not match database encoding \"%s\".", + *newval, pg_encoding_to_char(locale_enc), pg_encoding_to_char(db_enc)))); + return false; + } + } + + return check_locale(LC_COLLATE, *newval, NULL); +} + +void +assign_locale_collate(const char *newval, void *extra) +{ + (void) pg_perm_setlocale(LC_COLLATE, newval); +} + /* * We allow LC_MESSAGES to actually be set globally. * diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c index 4ed69ac7ba2..8586832acaa 100644 --- a/src/backend/utils/init/postinit.c +++ b/src/backend/utils/init/postinit.c @@ -404,6 +404,8 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect * the pg_database tuple. */ SetDatabaseEncoding(dbform->encoding); + /* Reset lc_collate to check encoding, and fall back to C if necessary */ + SetConfigOption("lc_collate", locale_collate, PGC_POSTMASTER, PGC_S_FILE); /* Record it as a GUC internal option, too */ SetConfigOption("server_encoding", GetDatabaseEncodingName(), PGC_INTERNAL, PGC_S_DYNAMIC_DEFAULT); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index 3b9d8349078..a36c680719f 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -1457,6 +1457,15 @@ boot_val => 'PG_KRB_SRVTAB', }, +{ name => 'lc_collate', type => 'string', context => 'PGC_SUSET', group => 'CLIENT_CONN_LOCALE', + short_desc => 'Sets the locale for text ordering in extensions.', + long_desc => 'An empty string means use the operating system setting.', + variable => 'locale_collate', + boot_val => '""', + check_hook => 'check_locale_collate', + assign_hook => 'assign_locale_collate', +}, + { name => 'lc_messages', type => 'string', context => 'PGC_SUSET', group => 'CLIENT_CONN_LOCALE', short_desc => 'Sets the language in which messages are displayed.', long_desc => 'An empty string means use the operating system setting.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index dc9e2255f8a..19332e39e82 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -798,6 +798,8 @@ # encoding # These settings are initialized by initdb, but they can be changed. +#lc_collate = '' # locale for text ordering (only affects + # extensions) #lc_messages = '' # locale for system error message # strings #lc_monetary = 'C' # locale for monetary formatting diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 92fe2f531f7..8b2e7bfab6f 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -1312,6 +1312,9 @@ setup_config(void) conflines = replace_guc_value(conflines, "shared_buffers", repltok, false); + conflines = replace_guc_value(conflines, "lc_collate", + lc_collate, false); + conflines = replace_guc_value(conflines, "lc_messages", lc_messages, false); diff --git a/src/include/utils/guc_hooks.h b/src/include/utils/guc_hooks.h index 82ac8646a8d..8a20f76eec8 100644 --- a/src/include/utils/guc_hooks.h +++ b/src/include/utils/guc_hooks.h @@ -65,6 +65,8 @@ extern bool check_huge_page_size(int *newval, void **extra, GucSource source); extern void assign_io_method(int newval, void *extra); extern bool check_io_max_concurrency(int *newval, void **extra, GucSource source); extern const char *show_in_hot_standby(void); +extern bool check_locale_collate(char **newval, void **extra, GucSource source); +extern void assign_locale_collate(const char *newval, void *extra); extern bool check_locale_messages(char **newval, void **extra, GucSource source); extern void assign_locale_messages(const char *newval, void *extra); extern bool check_locale_monetary(char **newval, void **extra, GucSource source); diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h index 8ad8900cf93..e29497dc7d2 100644 --- a/src/include/utils/pg_locale.h +++ b/src/include/utils/pg_locale.h @@ -41,6 +41,7 @@ #define UNICODE_CASEMAP_BUFSZ (UNICODE_CASEMAP_LEN * sizeof(char32_t)) /* GUC settings */ +extern PGDLLIMPORT char *locale_collate; extern PGDLLIMPORT char *locale_messages; extern PGDLLIMPORT char *locale_monetary; extern PGDLLIMPORT char *locale_numeric; -- 2.43.0