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 
Reviewed-by: Daniel Verite 
Discussion: https://www.postgresql.org/message-id/flat/[email protected]

Author: petere

doc/src/sgml/catalogs.sgml

@@ -2428,6 +2428,15 @@ SCRAM-SHA-256$<iteration count>:&l
       
      
 
+     
+      
+       collicurules text
+      
+      
+       ICU collation rules for this collation object
+      
+     
+
      
       
        collversion text
@@ -3106,6 +3115,15 @@ SCRAM-SHA-256$<iteration count>:&l
       
      
 
+     
+      
+       daticurules text
+      
+      
+       ICU collation rules for this database
+      
+     
+
      
       
        datcollversion text

doc/src/sgml/ref/create_collation.sgml

@@ -27,6 +27,7 @@ CREATE COLLATION [ IF NOT EXISTS ] name (
     [ LC_CTYPE = lc_ctype, ]
     [ PROVIDER = provider, ]
     [ DETERMINISTIC = boolean, ]
+    [ RULES = rules, ]
     [ VERSION = version ]
 )
 CREATE COLLATION [ IF NOT EXISTS ] name FROM existing_collation
      
     
 
+    
+     rules
+
+     
+      
+       Specifies additional collation rules to customize the behavior of the
+
+       url="https://unicode-org.github.io/icu/userguide/collation/customization/"/>
+       for details on the syntax.
+      
+     
+    
+
     
      version
 
@@ -228,6 +242,14 @@ CREATE COLLATION german_phonebook (provider = icu, locale = 'de-u-co-phonebk');
 
   
 
+  
+   To create a collation using the ICU provider, based on the English ICU
+   locale, with custom rules:
+
+
+
+  
+
   
    To create a collation from an existing collation:
 

doc/src/sgml/ref/create_database.sgml

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

doc/src/sgml/ref/createdb.sgml

@@ -157,6 +157,16 @@ PostgreSQL documentation
       
      
 
+     
+      --icu-rules=rules
+      
+       
+        Specifies additional collation rules to customize the behavior of the
+        default collation of this database.  This is supported for ICU only.
+       
+      
+     
+
      
       --locale-provider={libc|icu}
       

doc/src/sgml/ref/initdb.sgml

@@ -239,6 +239,16 @@ PostgreSQL documentation
       
      
 
+     
+      --icu-rules=rules
+      
+       
+        Specifies additional collation rules to customize the behavior of the
+        default collation.  This is supported for ICU only.
+       
+      
+     
+
      
       -k
       --data-checksums

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))