pg_query 6.0.0 → 6.1.0

data/ext/pg_query/src_backend_parser_gram.c

@@ -34303,7 +34303,7 @@ yyreduce:
 					n->def = (Node *) c;
 					c->contype = CONSTR_FOREIGN; /* others not supported, yet */
 					c->conname = (yyvsp[(3) - (4)].str);
-					processCASbits((yyvsp[(4) - (4)].ival), (yylsp[(4) - (4)]), "ALTER CONSTRAINT statement",
+					processCASbits((yyvsp[(4) - (4)].ival), (yylsp[(4) - (4)]), "FOREIGN KEY",
 									&c->deferrable,
 									&c->initdeferred,
 									NULL, NULL, yyscanner);

data/ext/pg_query/src_common_wchar.c

@@ -98,6 +98,25 @@
 #include "utils/ascii.h"
 
 
+/*
+ * In today's multibyte encodings other than UTF8, this two-byte sequence
+ * ensures pg_encoding_mblen() == 2 && pg_encoding_verifymbstr() == 0.
+ *
+ * For historical reasons, several verifychar implementations opt to reject
+ * this pair specifically.  Byte pair range constraints, in encoding
+ * originator documentation, always excluded this pair.  No core conversion
+ * could translate it.  However, longstanding verifychar implementations
+ * accepted any non-NUL byte.  big5_to_euc_tw and big5_to_mic even translate
+ * pairs not valid per encoding originator documentation.  To avoid tightening
+ * core or non-core conversions in a security patch, we sought this one pair.
+ *
+ * PQescapeString() historically used spaces for BYTE1; many other values
+ * could suffice for BYTE1.
+ */
+#define NONUTF8_INVALID_BYTE0 (0x8d)
+#define NONUTF8_INVALID_BYTE1 (' ')
+
+
 /*
  * Operations on multi-byte encodings are driven by a table of helper
  * functions.
@@ -1547,6 +1566,11 @@ pg_big5_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -1596,6 +1620,11 @@ pg_gbk_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -1645,6 +1674,11 @@ pg_uhc_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -2089,6 +2123,12 @@ pg_utf8_islegal(const unsigned char *source, int length)
 }
 
 
+/*
+ * Fills the provided buffer with two bytes such that:
+ *   pg_encoding_mblen(dst) == 2 && pg_encoding_verifymbstr(dst) == 0
+ */
+
+
 /*
  *-------------------------------------------------------------------
  * encoding info table
@@ -2188,5 +2228,11 @@ pg_encoding_max_length(int encoding)
 {
 	Assert(PG_VALID_ENCODING(encoding));
 
-	return pg_wchar_table[encoding].maxmblen;
+	/*
+	 * Check for the encoding despite the assert, due to some mingw versions
+	 * otherwise issuing bogus warnings.
+	 */
+	return PG_VALID_ENCODING(encoding) ?
+		pg_wchar_table[encoding].maxmblen :
+		pg_wchar_table[PG_SQL_ASCII].maxmblen;
 }

data/ext/pg_query/src_port_snprintf.c

@@ -3,7 +3,7 @@
  * - pg_vsnprintf
  * - dopr
  * - pg_snprintf
- * - strchrnul
+ * - pg_strchrnul
  * - dostr
  * - flushbuffer
  * - find_arguments
@@ -362,13 +362,22 @@ static void leading_pad(int zpad, int signvalue, int *padlen,
 static void trailing_pad(int padlen, PrintfTarget *target);
 
 /*
- * If strchrnul exists (it's a glibc-ism), it's a good bit faster than the
- * equivalent manual loop.  If it doesn't exist, provide a replacement.
+ * If strchrnul exists (it's a glibc-ism, but since adopted by some other
+ * platforms), it's a good bit faster than the equivalent manual loop.
+ * Use it if possible, and if it doesn't exist, use this replacement.
  *
  * Note: glibc declares this as returning "char *", but that would require
  * casting away const internally, so we don't follow that detail.
+ *
+ * Note: macOS has this too as of Sequoia 15.4, but it's hidden behind
+ * a deployment-target check that causes compile errors if the deployment
+ * target isn't high enough.  So !HAVE_DECL_STRCHRNUL may mean "yes it's
+ * declared, but it doesn't compile".  To avoid failing in that scenario,
+ * use a macro to avoid matching <string.h>'s name.
  */
-#ifndef HAVE_STRCHRNUL
+#if !HAVE_DECL_STRCHRNUL
+
+#define strchrnul pg_strchrnul
 
 static inline const char *
 strchrnul(const char *s, int c)
@@ -378,19 +387,7 @@ strchrnul(const char *s, int c)
 	return s;
 }
 
-#else
-
-/*
- * glibc's <string.h> declares strchrnul only if _GNU_SOURCE is defined.
- * While we typically use that on glibc platforms, configure will set
- * HAVE_STRCHRNUL whether it's used or not.  Fill in the missing declaration
- * so that this file will compile cleanly with or without _GNU_SOURCE.
- */
-#ifndef _GNU_SOURCE
-extern char *strchrnul(const char *s, int c);
-#endif
-
-#endif							/* HAVE_STRCHRNUL */
+#endif							/* !HAVE_DECL_STRCHRNUL */
 
 
 /*

data/lib/pg_query/fingerprint.rb

@@ -61,7 +61,7 @@ module PgQuery
 
     def ignored_node_type?(node)
       [A_Const, Alias, ParamRef, SetToDefault, IntList, OidList].include?(node.class) ||
-        node.is_a?(TypeCast) && (node.arg.node == :a_const || node.arg.node == :param_ref)
+        (node.is_a?(TypeCast) && %i[a_const param_ref].include?(node.arg.node))
     end
 
     def node_protobuf_field_name_to_json_name(node_class, field)
@@ -112,12 +112,10 @@ module PgQuery
             fingerprint_value(val.gsub(/\d{2,}/, ''), hash, postgres_node_name, postgres_field_name, true)
             next
           end
-        when 'stmt_len'
-          next if node.is_a?(RawStmt)
-        when 'stmt_location'
+        when 'stmt_len', 'stmt_location'
           next if node.is_a?(RawStmt)
         when 'kind'
-          if node.is_a?(A_Expr) && (val == :AEXPR_OP_ANY || val == :AEXPR_IN)
+          if node.is_a?(A_Expr) && %i[AEXPR_OP_ANY AEXPR_IN].include?(val)
             fingerprint_value(:AEXPR_OP, hash, postgres_node_name, postgres_field_name, true)
             next
           end

data/lib/pg_query/param_refs.rb

@@ -7,7 +7,7 @@ module PgQuery
         case node
         when PgQuery::ParamRef
           # Ignore param refs inside type casts, as these are already handled
-          next if location[-3..-1] == %i[type_cast arg param_ref]
+          next if location[-3..] == %i[type_cast arg param_ref]
 
           results << { 'location' => node.location,
                        'length' => param_ref_length(node) }

data/lib/pg_query/parse.rb

@@ -24,9 +24,7 @@ module PgQuery
   end
 
   class ParserResult
-    attr_reader :query
-    attr_reader :tree
-    attr_reader :warnings
+    attr_reader :query, :tree, :warnings
 
     def initialize(query, tree, warnings = [])
       @query = query
@@ -176,7 +174,7 @@ module PgQuery
           # The following statement types are DDL (changing table structure)
           when :alter_table_stmt
             case statement.alter_table_stmt.objtype
-            when :OBJECT_INDEX # Index # rubocop:disable Lint/EmptyWhen
+            when :OBJECT_INDEX # Index
               # ignore `ALTER INDEX index_name`
             else
               from_clause_items << { item: PgQuery::Node.new(range_var: statement.alter_table_stmt.relation), type: :ddl }
@@ -230,11 +228,11 @@ module PgQuery
           when :grant_stmt
             objects = statement.grant_stmt.objects
             case statement.grant_stmt.objtype
-            when :OBJECT_COLUMN # Column # rubocop:disable Lint/EmptyWhen
+            when :OBJECT_COLUMN # Column
               # FIXME
             when :OBJECT_TABLE # Table
               from_clause_items += objects.map { |o| { item: o, type: :ddl } }
-            when :OBJECT_SEQUENCE # Sequence # rubocop:disable Lint/EmptyWhen
+            when :OBJECT_SEQUENCE # Sequence
               # FIXME
             end
           when :lock_stmt
@@ -339,7 +337,7 @@ module PgQuery
       @cte_names.uniq!
     end
 
-    def statements_and_cte_names_for_with_clause(with_clause) # FIXME
+    def statements_and_cte_names_for_with_clause(with_clause)
       statements = []
       cte_names = []
 

data/lib/pg_query/parse_error.rb

@@ -1,6 +1,7 @@
 module PgQuery
   class ParseError < ArgumentError
     attr_reader :location
+
     def initialize(message, source_file, source_line, location)
       super("#{message} (#{source_file}:#{source_line})")
       @location = location