Allow tailoring of ICU locales with custom rules

This exposes the ICU facility to add custom collation rules to a
standard collation.

New options are added to CREATE COLLATION, CREATE DATABASE, createdb,
and initdb to set the rules.

Reviewed-by: Laurenz Albe <laurenz.albe@cybertec.at>
Reviewed-by: Daniel Verite <daniel@manitou-mail.org>
Discussion: https://www.postgresql.org/message-id/flat/821c71a4-6ef0-d366-9acf-bb8e367f739f@enterprisedb.com

doc/src/sgml/catalogs.sgml

@@ -2428,6 +2428,15 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>collicurules</structfield> <type>text</type>
+      </para>
+      <para>
+       ICU collation rules for this collation object
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>collversion</structfield> <type>text</type>
@@ -3106,6 +3115,15 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>daticurules</structfield> <type>text</type>
+      </para>
+      <para>
+       ICU collation rules for this database
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>datcollversion</structfield> <type>text</type>

doc/src/sgml/ref/create_collation.sgml

@@ -27,6 +27,7 @@ CREATE COLLATION [ IF NOT EXISTS ] <replaceable>name</replaceable> (
     [ LC_CTYPE = <replaceable>lc_ctype</replaceable>, ]
     [ PROVIDER = <replaceable>provider</replaceable>, ]
     [ DETERMINISTIC = <replaceable>boolean</replaceable>, ]
+    [ RULES = <replaceable>rules</replaceable>, ]
     [ VERSION = <replaceable>version</replaceable> ]
 )
 CREATE COLLATION [ IF NOT EXISTS ] <replaceable>name</replaceable> FROM <replaceable>existing_collation</replaceable>
@@ -149,6 +150,19 @@ CREATE COLLATION [ IF NOT EXISTS ] <replaceable>name</replaceable> FROM <replace
      </listitem>
     </varlistentry>
 
+    <varlistentry>
+     <term><replaceable>rules</replaceable></term>
+
+     <listitem>
+      <para>
+       Specifies additional collation rules to customize the behavior of the
+       collation.  This is supported for ICU only.  See <ulink
+       url="https://unicode-org.github.io/icu/userguide/collation/customization/"/>
+       for details on the syntax.
+      </para>
+     </listitem>
+    </varlistentry>
+
     <varlistentry>
      <term><replaceable>version</replaceable></term>
 
@@ -228,6 +242,14 @@ CREATE COLLATION german_phonebook (provider = icu, locale = 'de-u-co-phonebk');
 </programlisting>
   </para>
 
+  <para>
+   To create a collation using the ICU provider, based on the English ICU
+   locale, with custom rules:
+<programlisting>
+<![CDATA[CREATE COLLATION en_custom (provider = icu, locale = 'en', rules = '&a < g');]]>
+</programlisting>
+  </para>
+
   <para>
    To create a collation from an existing collation:
 <programlisting>

doc/src/sgml/ref/create_database.sgml

@@ -30,6 +30,7 @@ CREATE DATABASE <replaceable class="parameter">name</replaceable>
            [ LC_COLLATE [=] <replaceable class="parameter">lc_collate</replaceable> ]
            [ LC_CTYPE [=] <replaceable class="parameter">lc_ctype</replaceable> ]
            [ ICU_LOCALE [=] <replaceable class="parameter">icu_locale</replaceable> ]
+           [ ICU_RULES [=] <replaceable class="parameter">icu_rules</replaceable> ]
            [ LOCALE_PROVIDER [=] <replaceable class="parameter">locale_provider</replaceable> ]
            [ COLLATION_VERSION = <replaceable>collation_version</replaceable> ]
            [ TABLESPACE [=] <replaceable class="parameter">tablespace_name</replaceable> ]
@@ -192,6 +193,19 @@ CREATE DATABASE <replaceable class="parameter">name</replaceable>
       </listitem>
      </varlistentry>
 
+     <varlistentry id="create-database-icu-rules">
+      <term><replaceable class="parameter">icu_rules</replaceable></term>
+      <listitem>
+       <para>
+        Specifies additional collation rules to customize the behavior of the
+        default collation of this database.  This is supported for ICU only.
+        See <ulink
+        url="https://unicode-org.github.io/icu/userguide/collation/customization/"/>
+        for details on the syntax.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="create-database-locale-provider">
       <term><replaceable>locale_provider</replaceable></term>
 

doc/src/sgml/ref/createdb.sgml

@@ -157,6 +157,16 @@ PostgreSQL documentation
       </listitem>
      </varlistentry>
 
+     <varlistentry>
+      <term><option>--icu-rules=<replaceable class="parameter">rules</replaceable></option></term>
+      <listitem>
+       <para>
+        Specifies additional collation rules to customize the behavior of the
+        default collation of this database.  This is supported for ICU only.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry>
       <term><option>--locale-provider={<literal>libc</literal>|<literal>icu</literal>}</option></term>
       <listitem>

doc/src/sgml/ref/initdb.sgml

@@ -239,6 +239,16 @@ PostgreSQL documentation
       </listitem>
      </varlistentry>
 
+     <varlistentry id="app-initdb-icu-rules">
+      <term><option>--icu-rules=<replaceable>rules</replaceable></option></term>
+      <listitem>
+       <para>
+        Specifies additional collation rules to customize the behavior of the
+        default collation.  This is supported for ICU only.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="app-initdb-data-checksums" xreflabel="data checksums">
       <term><option>-k</option></term>
       <term><option>--data-checksums</option></term>

src/backend/catalog/pg_collation.c

@@ -50,6 +50,7 @@ CollationCreate(const char *collname, Oid collnamespace,
 				int32 collencoding,
 				const char *collcollate, const char *collctype,
 				const char *colliculocale,
+				const char *collicurules,
 				const char *collversion,
 				bool if_not_exists,
 				bool quiet)
@@ -194,6 +195,10 @@ CollationCreate(const char *collname, Oid collnamespace,
 		values[Anum_pg_collation_colliculocale - 1] = CStringGetTextDatum(colliculocale);
 	else
 		nulls[Anum_pg_collation_colliculocale - 1] = true;
+	if (collicurules)
+		values[Anum_pg_collation_collicurules - 1] = CStringGetTextDatum(collicurules);
+	else
+		nulls[Anum_pg_collation_collicurules - 1] = true;
 	if (collversion)
 		values[Anum_pg_collation_collversion - 1] = CStringGetTextDatum(collversion);
 	else

src/backend/commands/collationcmds.c

@@ -64,10 +64,12 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 	DefElem    *lcctypeEl = NULL;
 	DefElem    *providerEl = NULL;
 	DefElem    *deterministicEl = NULL;
+	DefElem    *rulesEl = NULL;
 	DefElem    *versionEl = NULL;
 	char	   *collcollate;
 	char	   *collctype;
 	char	   *colliculocale;
+	char	   *collicurules;
 	bool		collisdeterministic;
 	int			collencoding;
 	char		collprovider;
@@ -99,6 +101,8 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 			defelp = &providerEl;
 		else if (strcmp(defel->defname, "deterministic") == 0)
 			defelp = &deterministicEl;
+		else if (strcmp(defel->defname, "rules") == 0)
+			defelp = &rulesEl;
 		else if (strcmp(defel->defname, "version") == 0)
 			defelp = &versionEl;
 		else
@@ -161,6 +165,12 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 		else
 			colliculocale = NULL;
 
+		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collicurules, &isnull);
+		if (!isnull)
+			collicurules = TextDatumGetCString(datum);
+		else
+			collicurules = NULL;
+
 		ReleaseSysCache(tp);
 
 		/*
@@ -182,6 +192,7 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 		collcollate = NULL;
 		collctype = NULL;
 		colliculocale = NULL;
+		collicurules = NULL;
 
 		if (providerEl)
 			collproviderstr = defGetString(providerEl);
@@ -191,6 +202,9 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 		else
 			collisdeterministic = true;
 
+		if (rulesEl)
+			collicurules = defGetString(rulesEl);
+
 		if (versionEl)
 			collversion = defGetString(versionEl);
 
@@ -297,6 +311,7 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 							 collcollate,
 							 collctype,
 							 colliculocale,
+							 collicurules,
 							 collversion,
 							 if_not_exists,
 							 false);	/* not quiet */
@@ -680,7 +695,7 @@ create_collation_from_locale(const char *locale, int nspid,
 	 */
 	collid = CollationCreate(locale, nspid, GetUserId(),
 							 COLLPROVIDER_LIBC, true, enc,
-							 locale, locale, NULL,
+							 locale, locale, NULL, NULL,
 							 get_collation_actual_version(COLLPROVIDER_LIBC, locale),
 							 true, true);
 	if (OidIsValid(collid))
@@ -755,7 +770,7 @@ win32_read_locale(LPWSTR pStr, DWORD dwFlags, LPARAM lparam)
 
 		collid = CollationCreate(alias, param->nspid, GetUserId(),
 								 COLLPROVIDER_LIBC, true, enc,
-								 localebuf, localebuf, NULL,
+								 localebuf, localebuf, NULL, NULL,
 								 get_collation_actual_version(COLLPROVIDER_LIBC, localebuf),
 								 true, true);
 		if (OidIsValid(collid))
@@ -889,7 +904,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 
 			collid = CollationCreate(alias, nspid, GetUserId(),
 									 COLLPROVIDER_LIBC, true, enc,
-									 locale, locale, NULL,
+									 locale, locale, NULL, NULL,
 									 get_collation_actual_version(COLLPROVIDER_LIBC, locale),
 									 true, true);
 			if (OidIsValid(collid))
@@ -951,7 +966,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 			collid = CollationCreate(psprintf("%s-x-icu", langtag),
 									 nspid, GetUserId(),
 									 COLLPROVIDER_ICU, true, -1,
-									 NULL, NULL, iculocstr,
+									 NULL, NULL, iculocstr, NULL,
 									 get_collation_actual_version(COLLPROVIDER_ICU, iculocstr),
 									 true, true);
 			if (OidIsValid(collid))

src/backend/commands/dbcommands.c

@@ -119,6 +119,7 @@ static bool get_db_info(const char *name, LOCKMODE lockmode,
 						int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP,
 						TransactionId *dbFrozenXidP, MultiXactId *dbMinMultiP,
 						Oid *dbTablespace, char **dbCollate, char **dbCtype, char **dbIculocale,
+						char **dbIcurules,
 						char *dbLocProvider,
 						char **dbCollversion);
 static void remove_dbtablespaces(Oid db_id);
@@ -675,6 +676,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	char	   *src_collate = NULL;
 	char	   *src_ctype = NULL;
 	char	   *src_iculocale = NULL;
+	char	   *src_icurules = NULL;
 	char		src_locprovider = '\0';
 	char	   *src_collversion = NULL;
 	bool		src_istemplate;
@@ -698,6 +700,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	DefElem    *dcollate = NULL;
 	DefElem    *dctype = NULL;
 	DefElem    *diculocale = NULL;
+	DefElem    *dicurules = NULL;
 	DefElem    *dlocprovider = NULL;
 	DefElem    *distemplate = NULL;
 	DefElem    *dallowconnections = NULL;
@@ -710,6 +713,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	char	   *dbcollate = NULL;
 	char	   *dbctype = NULL;
 	char	   *dbiculocale = NULL;
+	char	   *dbicurules = NULL;
 	char		dblocprovider = '\0';
 	char	   *canonname;
 	int			encoding = -1;
@@ -775,6 +779,12 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 				errorConflictingDefElem(defel, pstate);
 			diculocale = defel;
 		}
+		else if (strcmp(defel->defname, "icu_rules") == 0)
+		{
+			if (dicurules)
+				errorConflictingDefElem(defel, pstate);
+			dicurules = defel;
+		}
 		else if (strcmp(defel->defname, "locale_provider") == 0)
 		{
 			if (dlocprovider)
@@ -893,6 +903,8 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 		dbctype = defGetString(dctype);
 	if (diculocale && diculocale->arg)
 		dbiculocale = defGetString(diculocale);
+	if (dicurules && dicurules->arg)
+		dbicurules = defGetString(dicurules);
 	if (dlocprovider && dlocprovider->arg)
 	{
 		char	   *locproviderstr = defGetString(dlocprovider);
@@ -958,7 +970,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 					 &src_dboid, &src_owner, &src_encoding,
 					 &src_istemplate, &src_allowconn,
 					 &src_frozenxid, &src_minmxid, &src_deftablespace,
-					 &src_collate, &src_ctype, &src_iculocale, &src_locprovider,
+					 &src_collate, &src_ctype, &src_iculocale, &src_icurules, &src_locprovider,
 					 &src_collversion))
 		ereport(ERROR,
 				(errcode(ERRCODE_UNDEFINED_DATABASE),
@@ -1006,6 +1018,8 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 		dblocprovider = src_locprovider;
 	if (dbiculocale == NULL && dblocprovider == COLLPROVIDER_ICU)
 		dbiculocale = src_iculocale;
+	if (dbicurules == NULL && dblocprovider == COLLPROVIDER_ICU)
+		dbicurules = src_icurules;
 
 	/* Some encodings are client only */
 	if (!PG_VALID_BE_ENCODING(encoding))
@@ -1097,6 +1111,9 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 
 		if (dblocprovider == COLLPROVIDER_ICU)
 		{
+			char	   *val1;
+			char	   *val2;
+
 			Assert(dbiculocale);
 			Assert(src_iculocale);
 			if (strcmp(dbiculocale, src_iculocale) != 0)
@@ -1105,6 +1122,19 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 						 errmsg("new ICU locale (%s) is incompatible with the ICU locale of the template database (%s)",
 								dbiculocale, src_iculocale),
 						 errhint("Use the same ICU locale as in the template database, or use template0 as template.")));
+
+			val1 = dbicurules;
+			if (!val1)
+				val1 = "";
+			val2 = src_icurules;
+			if (!val2)
+				val2 = "";
+			if (strcmp(val1, val2) != 0)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("new ICU collation rules (%s) are incompatible with the ICU collation rules of the template database (%s)",
+								val1, val2),
+						 errhint("Use the same ICU collation rules as in the template database, or use template0 as template.")));
 		}
 	}
 
@@ -1313,6 +1343,10 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 		new_record[Anum_pg_database_daticulocale - 1] = CStringGetTextDatum(dbiculocale);
 	else
 		new_record_nulls[Anum_pg_database_daticulocale - 1] = true;
+	if (dbicurules)
+		new_record[Anum_pg_database_daticurules - 1] = CStringGetTextDatum(dbicurules);
+	else
+		new_record_nulls[Anum_pg_database_daticurules - 1] = true;
 	if (dbcollversion)
 		new_record[Anum_pg_database_datcollversion - 1] = CStringGetTextDatum(dbcollversion);
 	else
@@ -1526,7 +1560,7 @@ dropdb(const char *dbname, bool missing_ok, bool force)
 	pgdbrel = table_open(DatabaseRelationId, RowExclusiveLock);
 
 	if (!get_db_info(dbname, AccessExclusiveLock, &db_id, NULL, NULL,
-					 &db_istemplate, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL))
+					 &db_istemplate, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL))
 	{
 		if (!missing_ok)
 		{
@@ -1726,7 +1760,7 @@ RenameDatabase(const char *oldname, const char *newname)
 	rel = table_open(DatabaseRelationId, RowExclusiveLock);
 
 	if (!get_db_info(oldname, AccessExclusiveLock, &db_id, NULL, NULL,
-					 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL))
+					 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL))
 		ereport(ERROR,
 				(errcode(ERRCODE_UNDEFINED_DATABASE),
 				 errmsg("database \"%s\" does not exist", oldname)));
@@ -1836,7 +1870,7 @@ movedb(const char *dbname, const char *tblspcname)
 	pgdbrel = table_open(DatabaseRelationId, RowExclusiveLock);
 
 	if (!get_db_info(dbname, AccessExclusiveLock, &db_id, NULL, NULL,
-					 NULL, NULL, NULL, NULL, &src_tblspcoid, NULL, NULL, NULL, NULL, NULL))
+					 NULL, NULL, NULL, NULL, &src_tblspcoid, NULL, NULL, NULL, NULL, NULL, NULL))
 		ereport(ERROR,
 				(errcode(ERRCODE_UNDEFINED_DATABASE),
 				 errmsg("database \"%s\" does not exist", dbname)));
@@ -2599,6 +2633,7 @@ get_db_info(const char *name, LOCKMODE lockmode,
 			int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP,
 			TransactionId *dbFrozenXidP, MultiXactId *dbMinMultiP,
 			Oid *dbTablespace, char **dbCollate, char **dbCtype, char **dbIculocale,
+			char **dbIcurules,
 			char *dbLocProvider,
 			char **dbCollversion)
 {
@@ -2715,6 +2750,14 @@ get_db_info(const char *name, LOCKMODE lockmode,
 					else
 						*dbIculocale = TextDatumGetCString(datum);
 				}
+				if (dbIcurules)
+				{
+					datum = SysCacheGetAttr(DATABASEOID, tuple, Anum_pg_database_daticurules, &isnull);
+					if (isnull)
+						*dbIcurules = NULL;
+					else
+						*dbIcurules = TextDatumGetCString(datum);
+				}
 				if (dbCollversion)
 				{
 					datum = SysCacheGetAttr(DATABASEOID, tuple, Anum_pg_database_datcollversion, &isnull);

src/backend/utils/adt/pg_locale.c

@@ -69,6 +69,7 @@
 
 #ifdef USE_ICU
 #include <unicode/ucnv.h>
+#include <unicode/ustring.h>
 #endif
 
 #ifdef __GLIBC__
@@ -1421,6 +1422,7 @@ struct pg_locale_struct default_locale;
 
 void
 make_icu_collator(const char *iculocstr,
+				  const char *icurules,
 				  struct pg_locale_struct *resultp)
 {
 #ifdef USE_ICU
@@ -1437,6 +1439,35 @@ make_icu_collator(const char *iculocstr,
 	if (U_ICU_VERSION_MAJOR_NUM < 54)
 		icu_set_collation_attributes(collator, iculocstr);
 
+	/*
+	 * If rules are specified, we extract the rules of the standard collation,
+	 * add our own rules, and make a new collator with the combined rules.
+	 */
+	if (icurules)
+	{
+		const UChar *default_rules;
+		UChar	   *agg_rules;
+		UChar	   *my_rules;
+		int32_t		length;
+
+		default_rules = ucol_getRules(collator, &length);
+		icu_to_uchar(&my_rules, icurules, strlen(icurules));
+
+		agg_rules = palloc_array(UChar, u_strlen(default_rules) + u_strlen(my_rules) + 1);
+		u_strcpy(agg_rules, default_rules);
+		u_strcat(agg_rules, my_rules);
+
+		ucol_close(collator);
+
+		status = U_ZERO_ERROR;
+		collator = ucol_openRules(agg_rules, u_strlen(agg_rules),
+								  UCOL_DEFAULT, UCOL_DEFAULT_STRENGTH, NULL, &status);
+		if (U_FAILURE(status))
+			ereport(ERROR,
+					(errmsg("could not open collator for locale \"%s\" with rules \"%s\": %s",
+							iculocstr, icurules, u_errorName(status))));
+	}
+
 	/* We will leak this string if the caller errors later :-( */
 	resultp->info.icu.locale = MemoryContextStrdup(TopMemoryContext, iculocstr);
 	resultp->info.icu.ucol = collator;
@@ -1608,11 +1639,19 @@ pg_newlocale_from_collation(Oid collid)
 		else if (collform->collprovider == COLLPROVIDER_ICU)
 		{
 			const char *iculocstr;
+			const char *icurules;
 
 			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_colliculocale, &isnull);
 			Assert(!isnull);
 			iculocstr = TextDatumGetCString(datum);
-			make_icu_collator(iculocstr, &result);
+
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collicurules, &isnull);
+			if (!isnull)
+				icurules = TextDatumGetCString(datum);
+			else
+				icurules = NULL;
+
+			make_icu_collator(iculocstr, icurules, &result);
 		}
 
 		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion,

src/backend/utils/init/postinit.c

@@ -421,10 +421,19 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 
 	if (dbform->datlocprovider == COLLPROVIDER_ICU)
 	{
+		char	   *icurules;
+
 		datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_daticulocale, &isnull);
 		Assert(!isnull);
 		iculocale = TextDatumGetCString(datum);
-		make_icu_collator(iculocale, &default_locale);
+
+		datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_daticurules, &isnull);
+		if (!isnull)
+			icurules = TextDatumGetCString(datum);
+		else
+			icurules = NULL;
+
+		make_icu_collator(iculocale, icurules, &default_locale);
 	}
 	else
 		iculocale = NULL;

src/bin/initdb/initdb.c

@@ -135,6 +135,7 @@ static char *lc_time = NULL;
 static char *lc_messages = NULL;
 static char locale_provider = COLLPROVIDER_LIBC;
 static char *icu_locale = NULL;
+static char *icu_rules = NULL;
 static const char *default_text_search_config = NULL;
 static char *username = NULL;
 static bool pwprompt = false;
@@ -1312,7 +1313,10 @@ bootstrap_template1(void)
 							  escape_quotes_bki(lc_ctype));
 
 	bki_lines = replace_token(bki_lines, "ICU_LOCALE",
-							  locale_provider == COLLPROVIDER_ICU ? escape_quotes_bki(icu_locale) : "_null_");
+							  icu_locale ? escape_quotes_bki(icu_locale) : "_null_");
+
+	bki_lines = replace_token(bki_lines, "ICU_RULES",
+							  icu_rules ? escape_quotes_bki(icu_rules) : "_null_");
 
 	sprintf(buf, "%c", locale_provider);
 	bki_lines = replace_token(bki_lines, "LOCALE_PROVIDER", buf);
@@ -2107,6 +2111,7 @@ usage(const char *progname)
 	printf(_("  -E, --encoding=ENCODING   set default encoding for new databases\n"));
 	printf(_("  -g, --allow-group-access  allow group read/execute on data directory\n"));
 	printf(_("      --icu-locale=LOCALE   set ICU locale ID for new databases\n"));
+	printf(_("      --icu-rules=RULES     set additional ICU collation rules for new databases\n"));
 	printf(_("  -k, --data-checksums      use data page checksums\n"));
 	printf(_("      --locale=LOCALE       set default locale for new databases\n"));
 	printf(_("      --lc-collate=, --lc-ctype=, --lc-messages=LOCALE\n"
@@ -2767,6 +2772,7 @@ main(int argc, char *argv[])
 		{"discard-caches", no_argument, NULL, 14},
 		{"locale-provider", required_argument, NULL, 15},
 		{"icu-locale", required_argument, NULL, 16},
+		{"icu-rules", required_argument, NULL, 17},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -2924,6 +2930,9 @@ main(int argc, char *argv[])
 			case 16:
 				icu_locale = pg_strdup(optarg);
 				break;
+			case 17:
+				icu_rules = pg_strdup(optarg);
+				break;
 			default:
 				/* getopt_long already emitted a complaint */
 				pg_log_error_hint("Try \"%s --help\" for more information.", progname);
@@ -2954,6 +2963,10 @@ main(int argc, char *argv[])
 		pg_fatal("%s cannot be specified unless locale provider \"%s\" is chosen",
 				 "--icu-locale", "icu");
 
+	if (icu_rules && locale_provider != COLLPROVIDER_ICU)
+		pg_fatal("%s cannot be specified unless locale provider \"%s\" is chosen",
+				 "--icu-rules", "icu");
+
 	atexit(cleanup_directories_atexit);
 
 	/* If we only need to fsync, just do it and exit */

src/bin/pg_dump/pg_dump.c

@@ -2843,6 +2843,7 @@ dumpDatabase(Archive *fout)
 				i_collate,
 				i_ctype,
 				i_daticulocale,
+				i_daticurules,
 				i_frozenxid,
 				i_minmxid,
 				i_datacl,
@@ -2861,6 +2862,7 @@ dumpDatabase(Archive *fout)
 			   *collate,
 			   *ctype,
 			   *iculocale,
+			   *icurules,
 			   *datistemplate,
 			   *datconnlimit,
 			   *tablespace;
@@ -2887,6 +2889,10 @@ dumpDatabase(Archive *fout)
 		appendPQExpBufferStr(dbQry, "datlocprovider, daticulocale, datcollversion, ");
 	else
 		appendPQExpBufferStr(dbQry, "'c' AS datlocprovider, NULL AS daticulocale, NULL AS datcollversion, ");
+	if (fout->remoteVersion >= 160000)
+		appendPQExpBufferStr(dbQry, "daticurules, ");
+	else
+		appendPQExpBufferStr(dbQry, "NULL AS daticurules, ");
 	appendPQExpBufferStr(dbQry,
 						 "(SELECT spcname FROM pg_tablespace t WHERE t.oid = dattablespace) AS tablespace, "
 						 "shobj_description(oid, 'pg_database') AS description "
@@ -2904,6 +2910,7 @@ dumpDatabase(Archive *fout)
 	i_collate = PQfnumber(res, "datcollate");
 	i_ctype = PQfnumber(res, "datctype");
 	i_daticulocale = PQfnumber(res, "daticulocale");
+	i_daticurules = PQfnumber(res, "daticurules");
 	i_frozenxid = PQfnumber(res, "datfrozenxid");
 	i_minmxid = PQfnumber(res, "datminmxid");
 	i_datacl = PQfnumber(res, "datacl");
@@ -2925,6 +2932,10 @@ dumpDatabase(Archive *fout)
 		iculocale = PQgetvalue(res, 0, i_daticulocale);
 	else
 		iculocale = NULL;
+	if (!PQgetisnull(res, 0, i_daticurules))
+		icurules = PQgetvalue(res, 0, i_daticurules);
+	else
+		icurules = NULL;
 	frozenxid = atooid(PQgetvalue(res, 0, i_frozenxid));
 	minmxid = atooid(PQgetvalue(res, 0, i_minmxid));
 	dbdacl.acl = PQgetvalue(res, 0, i_datacl);
@@ -2990,6 +3001,11 @@ dumpDatabase(Archive *fout)
 		appendPQExpBufferStr(creaQry, " ICU_LOCALE = ");
 		appendStringLiteralAH(creaQry, iculocale, fout);
 	}
+	if (icurules)
+	{
+		appendPQExpBufferStr(creaQry, " ICU_RULES = ");
+		appendStringLiteralAH(creaQry, icurules, fout);
+	}
 
 	/*
 	 * For binary upgrade, carry over the collation version.  For normal
@@ -13153,10 +13169,12 @@ dumpCollation(Archive *fout, const CollInfo *collinfo)
 	int			i_collcollate;
 	int			i_collctype;
 	int			i_colliculocale;
+	int			i_collicurules;
 	const char *collprovider;
 	const char *collcollate;
 	const char *collctype;
 	const char *colliculocale;
+	const char *collicurules;
 
 	/* Do nothing in data-only dump */
 	if (dopt->dataOnly)
@@ -13194,6 +13212,13 @@ dumpCollation(Archive *fout, const CollInfo *collinfo)
 		appendPQExpBufferStr(query,
 							 "NULL AS colliculocale, ");
 
+	if (fout->remoteVersion >= 160000)
+		appendPQExpBufferStr(query,
+							 "collicurules, ");
+	else
+		appendPQExpBufferStr(query,
+							 "NULL AS collicurules, ");
+
 	appendPQExpBuffer(query,
 					  "collcollate, "
 					  "collctype "
@@ -13208,6 +13233,7 @@ dumpCollation(Archive *fout, const CollInfo *collinfo)
 	i_collcollate = PQfnumber(res, "collcollate");
 	i_collctype = PQfnumber(res, "collctype");
 	i_colliculocale = PQfnumber(res, "colliculocale");
+	i_collicurules = PQfnumber(res, "collicurules");
 
 	collprovider = PQgetvalue(res, 0, i_collprovider);
 
@@ -13226,6 +13252,11 @@ dumpCollation(Archive *fout, const CollInfo *collinfo)
 	else
 		colliculocale = NULL;
 
+	if (!PQgetisnull(res, 0, i_collicurules))
+		collicurules = PQgetvalue(res, 0, i_collicurules);
+	else
+		collicurules = NULL;
+
 	appendPQExpBuffer(delq, "DROP COLLATION %s;\n",
 					  fmtQualifiedDumpable(collinfo));
 
@@ -13271,6 +13302,12 @@ dumpCollation(Archive *fout, const CollInfo *collinfo)
 		}
 	}
 
+	if (collicurules)
+	{
+		appendPQExpBufferStr(q, ", rules = ");
+		appendStringLiteralAH(q, collicurules, fout);
+	}
+
 	/*
 	 * For binary upgrade, carry over the collation version.  For normal
 	 * dump/restore, omit the version, so that it is computed upon restore.

src/bin/psql/describe.c

@@ -923,28 +923,42 @@ listAllDbs(const char *pattern, bool verbose)
 	initPQExpBuffer(&buf);
 
 	printfPQExpBuffer(&buf,
-					  "SELECT d.datname as \"%s\",\n"
+					  "SELECT\n"
+					  "  d.datname as \"%s\",\n"
 					  "  pg_catalog.pg_get_userbyid(d.datdba) as \"%s\",\n"
-					  "       pg_catalog.pg_encoding_to_char(d.encoding) as \"%s\",\n"
+					  "  pg_catalog.pg_encoding_to_char(d.encoding) as \"%s\",\n",
-					  "       d.datcollate as \"%s\",\n"
-					  "       d.datctype as \"%s\",\n",
 					  gettext_noop("Name"),
 					  gettext_noop("Owner"),
-					  gettext_noop("Encoding"),
+					  gettext_noop("Encoding"));
+	if (pset.sversion >= 150000)
+		appendPQExpBuffer(&buf,
+						  "  CASE d.datlocprovider WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\",\n",
+						  gettext_noop("Locale Provider"));
+	else
+		appendPQExpBuffer(&buf,
+						  "  'libc' AS \"%s\",\n",
+						  gettext_noop("Locale Provider"));
+	appendPQExpBuffer(&buf,
+					  "  d.datcollate as \"%s\",\n"
+					  "  d.datctype as \"%s\",\n",
 					  gettext_noop("Collate"),
 					  gettext_noop("Ctype"));
 	if (pset.sversion >= 150000)
 		appendPQExpBuffer(&buf,
-						  "       d.daticulocale as \"%s\",\n"
+						  "  d.daticulocale as \"%s\",\n",
-						  "       CASE d.datlocprovider WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\",\n",
+						  gettext_noop("ICU Locale"));
-						  gettext_noop("ICU Locale"),
-						  gettext_noop("Locale Provider"));
 	else
 		appendPQExpBuffer(&buf,
-						  "       NULL as \"%s\",\n"
+						  "  NULL as \"%s\",\n",
-						  "       'libc' AS \"%s\",\n",
+						  gettext_noop("ICU Locale"));
-						  gettext_noop("ICU Locale"),
+	if (pset.sversion >= 160000)
-						  gettext_noop("Locale Provider"));
+		appendPQExpBuffer(&buf,
+						  "  d.daticurules as \"%s\",\n",
+						  gettext_noop("ICU Rules"));
+	else
+		appendPQExpBuffer(&buf,
+						  "  NULL as \"%s\",\n",
+						  gettext_noop("ICU Rules"));
 	appendPQExpBufferStr(&buf, "  ");
 	printACLColumn(&buf, "d.datacl");
 	if (verbose)
@@ -4849,46 +4863,58 @@ listCollations(const char *pattern, bool verbose, bool showSystem)
 	PQExpBufferData buf;
 	PGresult   *res;
 	printQueryOpt myopt = pset.popt;
-	static const bool translate_columns[] = {false, false, false, false, false, false, true, false};
+	static const bool translate_columns[] = {false, false, false, false, false, false, false, true, false};
 
 	initPQExpBuffer(&buf);
 
 	printfPQExpBuffer(&buf,
-					  "SELECT n.nspname AS \"%s\",\n"
+					  "SELECT\n"
-					  "       c.collname AS \"%s\",\n"
+					  "  n.nspname AS \"%s\",\n"
-					  "       c.collcollate AS \"%s\",\n"
+					  "  c.collname AS \"%s\",\n",
-					  "       c.collctype AS \"%s\"",
 					  gettext_noop("Schema"),
-					  gettext_noop("Name"),
+					  gettext_noop("Name"));
+
+	if (pset.sversion >= 100000)
+		appendPQExpBuffer(&buf,
+						  "  CASE c.collprovider WHEN 'd' THEN 'default' WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\",\n",
+						  gettext_noop("Provider"));
+	else
+		appendPQExpBuffer(&buf,
+						  "  'libc' AS \"%s\",\n",
+						  gettext_noop("Provider"));
+
+	appendPQExpBuffer(&buf,
+					  "  c.collcollate AS \"%s\",\n"
+					  "  c.collctype AS \"%s\",\n",
 					  gettext_noop("Collate"),
 					  gettext_noop("Ctype"));
 
 	if (pset.sversion >= 150000)
 		appendPQExpBuffer(&buf,
-						  ",\n       c.colliculocale AS \"%s\"",
+						  "  c.colliculocale AS \"%s\",\n",
 						  gettext_noop("ICU Locale"));
 	else
 		appendPQExpBuffer(&buf,
-						  ",\n       c.collcollate AS \"%s\"",
+						  "  c.collcollate AS \"%s\",\n",
 						  gettext_noop("ICU Locale"));
 
-	if (pset.sversion >= 100000)
+	if (pset.sversion >= 160000)
 		appendPQExpBuffer(&buf,
-						  ",\n       CASE c.collprovider WHEN 'd' THEN 'default' WHEN 'c' THEN 'libc' WHEN 'i' THEN 'icu' END AS \"%s\"",
+						  "  c.collicurules AS \"%s\",\n",
-						  gettext_noop("Provider"));
+						  gettext_noop("ICU Rules"));
 	else
 		appendPQExpBuffer(&buf,
-						  ",\n       'libc' AS \"%s\"",
+						  "  NULL AS \"%s\",\n",
-						  gettext_noop("Provider"));
+						  gettext_noop("ICU Rules"));
 
 	if (pset.sversion >= 120000)
 		appendPQExpBuffer(&buf,
-						  ",\n       CASE WHEN c.collisdeterministic THEN '%s' ELSE '%s' END AS \"%s\"",
+						  "  CASE WHEN c.collisdeterministic THEN '%s' ELSE '%s' END AS \"%s\"",
 						  gettext_noop("yes"), gettext_noop("no"),
 						  gettext_noop("Deterministic?"));
 	else
 		appendPQExpBuffer(&buf,
-						  ",\n       '%s' AS \"%s\"",
+						  "  '%s' AS \"%s\"",
 						  gettext_noop("yes"),
 						  gettext_noop("Deterministic?"));
 

src/bin/scripts/createdb.c

@@ -41,6 +41,7 @@ main(int argc, char *argv[])
 		{"maintenance-db", required_argument, NULL, 3},
 		{"locale-provider", required_argument, NULL, 4},
 		{"icu-locale", required_argument, NULL, 5},
+		{"icu-rules", required_argument, NULL, 6},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -67,6 +68,7 @@ main(int argc, char *argv[])
 	char	   *locale = NULL;
 	char	   *locale_provider = NULL;
 	char	   *icu_locale = NULL;
+	char	   *icu_rules = NULL;
 
 	PQExpBufferData sql;
 
@@ -134,6 +136,9 @@ main(int argc, char *argv[])
 			case 5:
 				icu_locale = pg_strdup(optarg);
 				break;
+			case 6:
+				icu_rules = pg_strdup(optarg);
+				break;
 			default:
 				/* getopt_long already emitted a complaint */
 				pg_log_error_hint("Try \"%s --help\" for more information.", progname);
@@ -231,6 +236,11 @@ main(int argc, char *argv[])
 		appendPQExpBufferStr(&sql, " ICU_LOCALE ");
 		appendStringLiteralConn(&sql, icu_locale, conn);
 	}
+	if (icu_rules)
+	{
+		appendPQExpBufferStr(&sql, " ICU_RULES ");
+		appendStringLiteralConn(&sql, icu_rules, conn);
+	}
 
 	appendPQExpBufferChar(&sql, ';');
 
@@ -288,6 +298,7 @@ help(const char *progname)
 	printf(_("      --lc-collate=LOCALE      LC_COLLATE setting for the database\n"));
 	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"
 			 "                               locale provider for the database's default collation\n"));
 	printf(_("  -O, --owner=OWNER            database user to own the new database\n"));

src/include/catalog/catversion.h

@@ -57,6 +57,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202302221
+#define CATALOG_VERSION_NO	202303081
 
 #endif

src/include/catalog/pg_collation.h

@@ -43,6 +43,7 @@ CATALOG(pg_collation,3456,CollationRelationId)
 	text		collcollate BKI_DEFAULT(_null_);	/* LC_COLLATE setting */
 	text		collctype BKI_DEFAULT(_null_);	/* LC_CTYPE setting */
 	text		colliculocale BKI_DEFAULT(_null_);	/* ICU locale ID */
+	text		collicurules BKI_DEFAULT(_null_);	/* ICU collation rules */
 	text		collversion BKI_DEFAULT(_null_);	/* provider-dependent
 													 * version of collation
 													 * data */
@@ -91,6 +92,7 @@ extern Oid	CollationCreate(const char *collname, Oid collnamespace,
 							int32 collencoding,
 							const char *collcollate, const char *collctype,
 							const char *colliculocale,
+							const char *collicurules,
 							const char *collversion,
 							bool if_not_exists,
 							bool quiet);

src/include/catalog/pg_database.dat

@@ -18,6 +18,6 @@
   datlocprovider => 'LOCALE_PROVIDER', datistemplate => 't',
   datallowconn => 't', datconnlimit => '-1', datfrozenxid => '0',
   datminmxid => '1', dattablespace => 'pg_default', datcollate => 'LC_COLLATE',
-  datctype => 'LC_CTYPE', daticulocale => 'ICU_LOCALE', datacl => '_null_' },
+  datctype => 'LC_CTYPE', daticulocale => 'ICU_LOCALE', daticurules => 'ICU_RULES', datacl => '_null_' },
 
 ]

src/include/catalog/pg_database.h

@@ -71,6 +71,9 @@ CATALOG(pg_database,1262,DatabaseRelationId) BKI_SHARED_RELATION BKI_ROWTYPE_OID
 	/* ICU locale ID */
 	text		daticulocale;
 
+	/* ICU collation rules */
+	text		daticurules;
+
 	/* provider-dependent version of collation data */
 	text		datcollversion BKI_DEFAULT(_null_);
 

src/include/utils/pg_locale.h

@@ -95,6 +95,7 @@ typedef struct pg_locale_struct *pg_locale_t;
 extern PGDLLIMPORT struct pg_locale_struct default_locale;
 
 extern void make_icu_collator(const char *iculocstr,
+							  const char *icurules,
 							  struct pg_locale_struct *resultp);
 
 extern bool pg_locale_deterministic(pg_locale_t locale);

src/test/regress/expected/collate.icu.utf8.out

@@ -1190,6 +1190,36 @@ SELECT 'Goldmann' < 'Götz' COLLATE "de-x-icu", 'Goldmann' > 'Götz' COLLATE tes
  t        | t
 (1 row)
 
+-- rules
+CREATE COLLATION testcoll_rules1 (provider = icu, locale = '', rules = '&a < g');
+CREATE TABLE test7 (a text);
+-- example from https://unicode-org.github.io/icu/userguide/collation/customization/#syntax
+INSERT INTO test7 VALUES ('Abernathy'), ('apple'), ('bird'), ('Boston'), ('Graham'), ('green');
+SELECT * FROM test7 ORDER BY a COLLATE "en-x-icu";
+     a     
+-----------
+ Abernathy
+ apple
+ bird
+ Boston
+ Graham
+ green
+(6 rows)
+
+SELECT * FROM test7 ORDER BY a COLLATE testcoll_rules1;
+     a     
+-----------
+ Abernathy
+ apple
+ green
+ bird
+ Boston
+ Graham
+(6 rows)
+
+DROP TABLE test7;
+CREATE COLLATION testcoll_rulesx (provider = icu, locale = '', rules = '!!wrong!!');
+ERROR:  could not open collator for locale "" with rules "!!wrong!!": U_INVALID_FORMAT_ERROR
 -- nondeterministic collations
 CREATE COLLATION ctest_det (provider = icu, locale = '', deterministic = true);
 CREATE COLLATION ctest_nondet (provider = icu, locale = '', deterministic = false);

src/test/regress/expected/psql.out

@@ -6200,8 +6200,8 @@ List of schemas
 
 \dO "no.such.collation"
                                   List of collations
- Schema | Name | Collate | Ctype | ICU Locale | Provider | Deterministic? 
+ Schema | Name | Provider | Collate | Ctype | ICU Locale | ICU Rules | Deterministic? 
---------+------+---------+-------+------------+----------+----------------
+--------+------+----------+---------+-------+------------+-----------+----------------
 (0 rows)
 
 \dp "no.such.access.privilege"
@@ -6389,8 +6389,8 @@ cross-database references are not implemented: "no.such.schema"."no.such.languag
 
 \dO "no.such.schema"."no.such.collation"
                                   List of collations
- Schema | Name | Collate | Ctype | ICU Locale | Provider | Deterministic? 
+ Schema | Name | Provider | Collate | Ctype | ICU Locale | ICU Rules | Deterministic? 
---------+------+---------+-------+------------+----------+----------------
+--------+------+----------+---------+-------+------------+-----------+----------------
 (0 rows)
 
 \dp "no.such.schema"."no.such.access.privilege"
@@ -6532,8 +6532,8 @@ List of text search templates
 
 \dO regression."no.such.schema"."no.such.collation"
                                   List of collations
- Schema | Name | Collate | Ctype | ICU Locale | Provider | Deterministic? 
+ Schema | Name | Provider | Collate | Ctype | ICU Locale | ICU Rules | Deterministic? 
---------+------+---------+-------+------------+----------+----------------
+--------+------+----------+---------+-------+------------+-----------+----------------
 (0 rows)
 
 \dp regression."no.such.schema"."no.such.access.privilege"

src/test/regress/sql/collate.icu.utf8.sql

@@ -472,6 +472,19 @@ CREATE COLLATION testcoll_de_phonebook (provider = icu, locale = 'de@collation=p
 SELECT 'Goldmann' < 'Götz' COLLATE "de-x-icu", 'Goldmann' > 'Götz' COLLATE testcoll_de_phonebook;
 
 
+-- rules
+
+CREATE COLLATION testcoll_rules1 (provider = icu, locale = '', rules = '&a < g');
+CREATE TABLE test7 (a text);
+-- example from https://unicode-org.github.io/icu/userguide/collation/customization/#syntax
+INSERT INTO test7 VALUES ('Abernathy'), ('apple'), ('bird'), ('Boston'), ('Graham'), ('green');
+SELECT * FROM test7 ORDER BY a COLLATE "en-x-icu";
+SELECT * FROM test7 ORDER BY a COLLATE testcoll_rules1;
+DROP TABLE test7;
+
+CREATE COLLATION testcoll_rulesx (provider = icu, locale = '', rules = '!!wrong!!');
+
+
 -- nondeterministic collations
 
 CREATE COLLATION ctest_det (provider = icu, locale = '', deterministic = true);