Teach pattern_fixed_prefix() about collations.

tglsfdc · tglsfdc · commit 3c381a55b0fa · 2011-04-11T12:28:28.000-04:00
This is necessary, not optional, now that ILIKE and regexes are collation
aware --- else we might derive a wrong comparison constant for index
optimized pattern matches.
diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c
@@ -2446,6 +2446,7 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 	bool		isIndexable = false;
 	Node	   *rightop;
 	Oid			expr_op;
+	Oid			expr_coll;
 	Const	   *patt;
 	Const	   *prefix = NULL;
 	Const	   *rest = NULL;
@@ -2462,6 +2463,7 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 	/* we know these will succeed */
 	rightop = get_rightop(clause);
 	expr_op = ((OpExpr *) clause)->opno;
+	expr_coll = ((OpExpr *) clause)->inputcollid;
 
 	/* again, required for all current special ops: */
 	if (!IsA(rightop, Const) ||
@@ -2475,13 +2477,13 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 		case OID_BPCHAR_LIKE_OP:
 		case OID_NAME_LIKE_OP:
 			/* the right-hand const is type text for all of these */
-			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like,
+			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like, expr_coll,
 										   &prefix, &rest);
 			isIndexable = (pstatus != Pattern_Prefix_None);
 			break;
 
 		case OID_BYTEA_LIKE_OP:
-			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like,
+			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like, expr_coll,
 										   &prefix, &rest);
 			isIndexable = (pstatus != Pattern_Prefix_None);
 			break;
@@ -2490,7 +2492,7 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 		case OID_BPCHAR_ICLIKE_OP:
 		case OID_NAME_ICLIKE_OP:
 			/* the right-hand const is type text for all of these */
-			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like_IC,
+			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like_IC, expr_coll,
 										   &prefix, &rest);
 			isIndexable = (pstatus != Pattern_Prefix_None);
 			break;
@@ -2499,7 +2501,7 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 		case OID_BPCHAR_REGEXEQ_OP:
 		case OID_NAME_REGEXEQ_OP:
 			/* the right-hand const is type text for all of these */
-			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex,
+			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex, expr_coll,
 										   &prefix, &rest);
 			isIndexable = (pstatus != Pattern_Prefix_None);
 			break;
@@ -2508,7 +2510,7 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 		case OID_BPCHAR_ICREGEXEQ_OP:
 		case OID_NAME_ICREGEXEQ_OP:
 			/* the right-hand const is type text for all of these */
-			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex_IC,
+			pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex_IC, expr_coll,
 										   &prefix, &rest);
 			isIndexable = (pstatus != Pattern_Prefix_None);
 			break;
@@ -2544,10 +2546,9 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 	 *
 	 * The non-pattern opclasses will not sort the way we need in most non-C
 	 * locales.  We can use such an index anyway for an exact match (simple
-	 * equality), but not for prefix-match cases.  Note that we are looking at
-	 * the index's collation, not the expression's collation -- this test is
-	 * not dependent on the LIKE/regex operator's collation (which would only
-	 * affect case folding behavior of ILIKE, anyway).
+	 * equality), but not for prefix-match cases.  Note that here we are
+	 * looking at the index's collation, not the expression's collation --
+	 * this test is *not* dependent on the LIKE/regex operator's collation.
 	 */
 	switch (expr_op)
 	{
@@ -2558,7 +2559,8 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 			isIndexable =
 				(opfamily == TEXT_PATTERN_BTREE_FAM_OID) ||
 				(opfamily == TEXT_BTREE_FAM_OID &&
-				 (pstatus == Pattern_Prefix_Exact || lc_collate_is_c(idxcollation)));
+				 (pstatus == Pattern_Prefix_Exact ||
+				  lc_collate_is_c(idxcollation)));
 			break;
 
 		case OID_BPCHAR_LIKE_OP:
@@ -2568,7 +2570,8 @@ match_special_index_operator(Expr *clause, Oid opfamily, Oid idxcollation,
 			isIndexable =
 				(opfamily == BPCHAR_PATTERN_BTREE_FAM_OID) ||
 				(opfamily == BPCHAR_BTREE_FAM_OID &&
-				 (pstatus == Pattern_Prefix_Exact || lc_collate_is_c(idxcollation)));
+				 (pstatus == Pattern_Prefix_Exact ||
+				  lc_collate_is_c(idxcollation)));
 			break;
 
 		case OID_NAME_LIKE_OP:
@@ -2770,6 +2773,7 @@ expand_indexqual_opclause(RestrictInfo *rinfo, Oid opfamily, Oid idxcollation)
 	Node	   *leftop = get_leftop(clause);
 	Node	   *rightop = get_rightop(clause);
 	Oid			expr_op = ((OpExpr *) clause)->opno;
+	Oid			expr_coll = ((OpExpr *) clause)->inputcollid;
 	Const	   *patt = (Const *) rightop;
 	Const	   *prefix = NULL;
 	Const	   *rest = NULL;
@@ -2791,7 +2795,7 @@ expand_indexqual_opclause(RestrictInfo *rinfo, Oid opfamily, Oid idxcollation)
 		case OID_BYTEA_LIKE_OP:
 			if (!op_in_opfamily(expr_op, opfamily))
 			{
-				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like,
+				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like, expr_coll,
 											   &prefix, &rest);
 				return prefix_quals(leftop, opfamily, idxcollation, prefix, pstatus);
 			}
@@ -2803,7 +2807,7 @@ expand_indexqual_opclause(RestrictInfo *rinfo, Oid opfamily, Oid idxcollation)
 			if (!op_in_opfamily(expr_op, opfamily))
 			{
 				/* the right-hand const is type text for all of these */
-				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like_IC,
+				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Like_IC, expr_coll,
 											   &prefix, &rest);
 				return prefix_quals(leftop, opfamily, idxcollation, prefix, pstatus);
 			}
@@ -2815,7 +2819,7 @@ expand_indexqual_opclause(RestrictInfo *rinfo, Oid opfamily, Oid idxcollation)
 			if (!op_in_opfamily(expr_op, opfamily))
 			{
 				/* the right-hand const is type text for all of these */
-				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex,
+				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex, expr_coll,
 											   &prefix, &rest);
 				return prefix_quals(leftop, opfamily, idxcollation, prefix, pstatus);
 			}
@@ -2827,7 +2831,7 @@ expand_indexqual_opclause(RestrictInfo *rinfo, Oid opfamily, Oid idxcollation)
 			if (!op_in_opfamily(expr_op, opfamily))
 			{
 				/* the right-hand const is type text for all of these */
-				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex_IC,
+				pstatus = pattern_fixed_prefix(patt, Pattern_Type_Regex_IC, expr_coll,
 											   &prefix, &rest);
 				return prefix_quals(leftop, opfamily, idxcollation, prefix, pstatus);
 			}
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -1181,9 +1181,14 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype, bool negate)
 			return result;
 	}
 
-	/* divide pattern into fixed prefix and remainder */
+	/*
+	 * Divide pattern into fixed prefix and remainder.  XXX we have to assume
+	 * default collation here, because we don't have access to the actual
+	 * input collation for the operator.  FIXME ...
+	 */
 	patt = (Const *) other;
-	pstatus = pattern_fixed_prefix(patt, ptype, &prefix, &rest);
+	pstatus = pattern_fixed_prefix(patt, ptype, DEFAULT_COLLATION_OID,
+								   &prefix, &rest);
 
 	/*
 	 * If necessary, coerce the prefix constant to the right type. (The "rest"
@@ -4755,6 +4760,29 @@ get_actual_variable_range(PlannerInfo *root, VariableStatData *vardata,
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Check whether char is a letter (and, hence, subject to case-folding)
+ *
+ * In multibyte character sets, we can't use isalpha, and it does not seem
+ * worth trying to convert to wchar_t to use iswalpha.  Instead, just assume
+ * any multibyte char is potentially case-varying.
+ */
+static int
+pattern_char_isalpha(char c, bool is_multibyte,
+					 pg_locale_t locale, bool locale_is_c)
+{
+	if (locale_is_c)
+		return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
+	else if (is_multibyte && IS_HIGHBIT_SET(c))
+		return true;
+#ifdef HAVE_LOCALE_T
+	else if (locale)
+		return isalpha_l((unsigned char) c, locale);
+#endif
+	else
+		return isalpha((unsigned char) c);
+}
+
 /*
  * Extract the fixed prefix, if any, for a pattern.
  *
@@ -4769,7 +4797,7 @@ get_actual_variable_range(PlannerInfo *root, VariableStatData *vardata,
  */
 
 static Pattern_Prefix_Status
-like_fixed_prefix(Const *patt_const, bool case_insensitive,
+like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation,
 				  Const **prefix_const, Const **rest_const)
 {
 	char	   *match;
@@ -4780,15 +4808,39 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive,
 	int			pos,
 				match_pos;
 	bool		is_multibyte = (pg_database_encoding_max_length() > 1);
+	pg_locale_t	locale = 0;
+	bool		locale_is_c = false;
 
 	/* the right-hand const is type text or bytea */
 	Assert(typeid == BYTEAOID || typeid == TEXTOID);
 
-	if (typeid == BYTEAOID && case_insensitive)
-		ereport(ERROR,
-				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+	if (case_insensitive)
+	{
+		if (typeid == BYTEAOID)
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 		   errmsg("case insensitive matching not supported on type bytea")));
 
+		/* If case-insensitive, we need locale info */
+		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);
+		}
+	}
+
 	if (typeid != BYTEAOID)
 	{
 		patt = TextDatumGetCString(patt_const->constvalue);
@@ -4822,23 +4874,11 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive,
 				break;
 		}
 
-		/*
-		 * XXX In multibyte character sets, we can't trust isalpha, so assume
-		 * any multibyte char is potentially case-varying.
-		 */
-		if (case_insensitive)
-		{
-			if (is_multibyte && (unsigned char) patt[pos] >= 0x80)
-				break;
-			if (isalpha((unsigned char) patt[pos]))
-				break;
-		}
+		/* Stop if case-varying character (it's sort of a wildcard) */
+		if (case_insensitive &&
+			pattern_char_isalpha(patt[pos], is_multibyte, locale, locale_is_c))
+			break;
 
-		/*
-		 * NOTE: this code used to think that %% meant a literal %, but
-		 * textlike() itself does not think that, and the SQL92 spec doesn't
-		 * say any such thing either.
-		 */
 		match[match_pos++] = patt[pos];
 	}
 
@@ -4870,7 +4910,7 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive,
 }
 
 static Pattern_Prefix_Status
-regex_fixed_prefix(Const *patt_const, bool case_insensitive,
+regex_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation,
 				   Const **prefix_const, Const **rest_const)
 {
 	char	   *match;
@@ -4883,6 +4923,8 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
 	char	   *rest;
 	Oid			typeid = patt_const->consttype;
 	bool		is_multibyte = (pg_database_encoding_max_length() > 1);
+	pg_locale_t	locale = 0;
+	bool		locale_is_c = false;
 
 	/*
 	 * Should be unnecessary, there are no bytea regex operators defined. As
@@ -4894,6 +4936,28 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 		 errmsg("regular-expression matching not supported on type bytea")));
 
+	if (case_insensitive)
+	{
+		/* If case-insensitive, we need locale info */
+		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 regular expression"),
+						 errhint("Use the COLLATE clause to set the collation explicitly.")));
+			}
+			locale = pg_newlocale_from_collation(collation);
+		}
+	}
+
 	/* the right-hand const is type text for all of these */
 	patt = TextDatumGetCString(patt_const->constvalue);
 
@@ -4969,17 +5033,10 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
 			patt[pos] == '$')
 			break;
 
-		/*
-		 * XXX In multibyte character sets, we can't trust isalpha, so assume
-		 * any multibyte char is potentially case-varying.
-		 */
-		if (case_insensitive)
-		{
-			if (is_multibyte && (unsigned char) patt[pos] >= 0x80)
-				break;
-			if (isalpha((unsigned char) patt[pos]))
-				break;
-		}
+		/* Stop if case-varying character (it's sort of a wildcard) */
+		if (case_insensitive &&
+			pattern_char_isalpha(patt[pos], is_multibyte, locale, locale_is_c))
+			break;
 
 		/*
 		 * Check for quantifiers.  Except for +, this means the preceding
@@ -5004,7 +5061,7 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
 		 * backslash followed by alphanumeric is an escape, not a quoted
 		 * character.  Must treat it as having multiple possible matches.
 		 * Note: since only ASCII alphanumerics are escapes, we don't have to
-		 * be paranoid about multibyte here.
+		 * be paranoid about multibyte or collations here.
 		 */
 		if (patt[pos] == '\\')
 		{
@@ -5056,24 +5113,24 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
 }
 
 Pattern_Prefix_Status
-pattern_fixed_prefix(Const *patt, Pattern_Type ptype,
+pattern_fixed_prefix(Const *patt, Pattern_Type ptype, Oid collation,
 					 Const **prefix, Const **rest)
 {
 	Pattern_Prefix_Status result;
 
 	switch (ptype)
 	{
 		case Pattern_Type_Like:
-			result = like_fixed_prefix(patt, false, prefix, rest);
+			result = like_fixed_prefix(patt, false, collation, prefix, rest);
 			break;
 		case Pattern_Type_Like_IC:
-			result = like_fixed_prefix(patt, true, prefix, rest);
+			result = like_fixed_prefix(patt, true, collation, prefix, rest);
 			break;
 		case Pattern_Type_Regex:
-			result = regex_fixed_prefix(patt, false, prefix, rest);
+			result = regex_fixed_prefix(patt, false, collation, prefix, rest);
 			break;
 		case Pattern_Type_Regex_IC:
-			result = regex_fixed_prefix(patt, true, prefix, rest);
+			result = regex_fixed_prefix(patt, true, collation, prefix, rest);
 			break;
 		default:
 			elog(ERROR, "unrecognized ptype: %d", (int) ptype);
diff --git a/src/include/utils/selfuncs.h b/src/include/utils/selfuncs.h
@@ -132,6 +132,7 @@ extern double histogram_selectivity(VariableStatData *vardata, FmgrInfo *opproc,
 
 extern Pattern_Prefix_Status pattern_fixed_prefix(Const *patt,
 					 Pattern_Type ptype,
+					 Oid collation,
 					 Const **prefix,
 					 Const **rest);
 extern Const *make_greater_string(const Const *str_const, FmgrInfo *ltproc);
