ICU support

Add a column collprovider to pg_collation that determines which library
provides the collation data.  The existing choices are default and libc,
and this adds an icu choice, which uses the ICU4C library.

The pg_locale_t type is changed to a union that contains the
provider-specific locale handles.  Users of locale information are
changed to look into that struct for the appropriate handle to use.

Also add a collversion column that records the version of the collation
when it is created, and check at run time whether it is still the same.
This detects potentially incompatible library upgrades that can corrupt
indexes and other structures.  This is currently only supported by
ICU-provided collations.

initdb initializes the default collation set as before from the `locale
-a` output but also adds all available ICU locales with a "-x-icu"
appended.

Currently, ICU-provided collations can only be explicitly named
collations.  The global database locales are still always libc-provided.

ICU support is enabled by configure --with-icu.

Reviewed-by: Thomas Munro <thomas.munro@enterprisedb.com>
Reviewed-by: Andreas Karlsson <andreas@proxel.se>

1 files changed, 25 insertions, 28 deletions

diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c
index 8d9d285fb55..1f683ccd0f7 100644
--- a/src/backend/utils/adt/like.c
+++ b/src/backend/utils/adt/like.c
@@ -96,7 +96,7 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c)
 		return pg_ascii_tolower(c);
 #ifdef HAVE_LOCALE_T
 	else if (locale)
-		return tolower_l(c, locale);
+		return tolower_l(c, locale->info.lt);
 #endif
 	else
 		return pg_tolower(c);
@@ -165,14 +165,36 @@ Generic_Text_IC_like(text *str, text *pat, Oid collation)
 			   *p;
 	int			slen,
 				plen;
+	pg_locale_t locale = 0;
+	bool		locale_is_c = false;
+
+	if (lc_ctype_is_c(collation))
+		locale_is_c = true;
+	else if (collation != DEFAULT_COLLATION_OID)
+	{
+		if (!OidIsValid(collation))
+		{
+			/*
+			 * This typically means that the parser could not resolve a
+			 * conflict of implicit collations, so report it that way.
+			 */
+			ereport(ERROR,
+					(errcode(ERRCODE_INDETERMINATE_COLLATION),
+					 errmsg("could not determine which collation to use for ILIKE"),
+					 errhint("Use the COLLATE clause to set the collation explicitly.")));
+		}
+		locale = pg_newlocale_from_collation(collation);
+	}
 
 	/*
 	 * For efficiency reasons, in the single byte case we don't call lower()
 	 * on the pattern and text, but instead call SB_lower_char on each
-	 * character.  In the multi-byte case we don't have much choice :-(
+	 * character.  In the multi-byte case we don't have much choice :-(.
+	 * Also, ICU does not support single-character case folding, so we go the
+	 * long way.
 	 */
 
-	if (pg_database_encoding_max_length() > 1)
+	if (pg_database_encoding_max_length() > 1 || locale->provider == COLLPROVIDER_ICU)
 	{
 		/* lower's result is never packed, so OK to use old macros here */
 		pat = DatumGetTextPP(DirectFunctionCall1Coll(lower, collation,
@@ -190,31 +212,6 @@ Generic_Text_IC_like(text *str, text *pat, Oid collation)
 	}
 	else
 	{
-		/*
-		 * Here we need to prepare locale information for SB_lower_char. This
-		 * should match the methods used in str_tolower().
-		 */
-		pg_locale_t locale = 0;
-		bool		locale_is_c = false;
-
-		if (lc_ctype_is_c(collation))
-			locale_is_c = true;
-		else if (collation != DEFAULT_COLLATION_OID)
-		{
-			if (!OidIsValid(collation))
-			{
-				/*
-				 * This typically means that the parser could not resolve a
-				 * conflict of implicit collations, so report it that way.
-				 */
-				ereport(ERROR,
-						(errcode(ERRCODE_INDETERMINATE_COLLATION),
-						 errmsg("could not determine which collation to use for ILIKE"),
-						 errhint("Use the COLLATE clause to set the collation explicitly.")));
-			}
-			locale = pg_newlocale_from_collation(collation);
-		}
-
 		p = VARDATA_ANY(pat);
 		plen = VARSIZE_ANY_EXHDR(pat);
 		s = VARDATA_ANY(str);