Add pg_encoding_set_invalid()

There are cases where we cannot / do not want to error out for invalidly
encoded input. In such cases it can be useful to replace e.g. an incomplete
multi-byte characters with bytes that will trigger an error when getting
validated as part of a larger string.

Unfortunately, until now, for some encoding no such sequence existed. For
those encodings this commit removes one previously accepted input combination
- we consider that to be ok, as the chosen bytes are outside of the valid
ranges for the encodings, we just previously failed to detect that.

As we cannot add a new field to pg_wchar_table without breaking ABI, this is
implemented "in-line" in the newly added function.

Author: Noah Misch <noah@leadboat.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Backpatch-through: 13
Security: CVE-2025-1094

5 files changed, 65 insertions, 0 deletions

diff --git a/src/test/regress/expected/conversion.out b/src/test/regress/expected/conversion.out
index 62c10671685..f052783d84f 100644
--- a/src/test/regress/expected/conversion.out
+++ b/src/test/regress/expected/conversion.out
@@ -1,6 +1,10 @@
 --
 -- create user defined conversion
 --
+SELECT FROM test_enc_setup();
+--
+(1 row)
+
 CREATE USER regress_conversion_user WITH NOCREATEDB NOCREATEROLE;
 SET SESSION AUTHORIZATION regress_conversion_user;
 CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;
diff --git a/src/test/regress/input/create_function_1.source b/src/test/regress/input/create_function_1.source
index 412e339fcf2..b230a8a6a81 100644
--- a/src/test/regress/input/create_function_1.source
+++ b/src/test/regress/input/create_function_1.source
@@ -62,6 +62,10 @@ CREATE FUNCTION test_atomic_ops()
     AS '@libdir@/regress@DLSUFFIX@'
     LANGUAGE C;
 
+CREATE FUNCTION test_enc_setup() RETURNS void
+    AS '@libdir@/regress@DLSUFFIX@', 'test_enc_setup'
+    LANGUAGE C STRICT;
+
 -- Tests creating a FDW handler
 CREATE FUNCTION test_fdw_handler()
     RETURNS fdw_handler
diff --git a/src/test/regress/output/create_function_1.source b/src/test/regress/output/create_function_1.source
index 4d78fa12289..4e4db33612b 100644
--- a/src/test/regress/output/create_function_1.source
+++ b/src/test/regress/output/create_function_1.source
@@ -55,6 +55,9 @@ CREATE FUNCTION test_atomic_ops()
     RETURNS bool
     AS '@libdir@/regress@DLSUFFIX@'
     LANGUAGE C;
+CREATE FUNCTION test_enc_setup() RETURNS void
+    AS '@libdir@/regress@DLSUFFIX@', 'test_enc_setup'
+    LANGUAGE C STRICT;
 -- Tests creating a FDW handler
 CREATE FUNCTION test_fdw_handler()
     RETURNS fdw_handler
diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c
index aa9fef866fa..481588c9a44 100644
--- a/src/test/regress/regress.c
+++ b/src/test/regress/regress.c
@@ -29,6 +29,7 @@
 #include "commands/trigger.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "mb/pg_wchar.h"
 #include "miscadmin.h"
 #include "nodes/supportnodes.h"
 #include "optimizer/optimizer.h"
@@ -1088,3 +1089,53 @@ test_opclass_options_func(PG_FUNCTION_ARGS)
 {
 	PG_RETURN_NULL();
 }
+
+/* one-time tests for encoding infrastructure */
+PG_FUNCTION_INFO_V1(test_enc_setup);
+Datum
+test_enc_setup(PG_FUNCTION_ARGS)
+{
+	/* Test pg_encoding_set_invalid() */
+	for (int i = 0; i < _PG_LAST_ENCODING_; i++)
+	{
+		char		buf[2],
+					bigbuf[16];
+		int			len,
+					mblen,
+					valid;
+
+		if (pg_encoding_max_length(i) == 1)
+			continue;
+		pg_encoding_set_invalid(i, buf);
+		len = strnlen(buf, 2);
+		if (len != 2)
+			elog(WARNING,
+				 "official invalid string for encoding \"%s\" has length %d",
+				 pg_enc2name_tbl[i].name, len);
+		mblen = pg_encoding_mblen(i, buf);
+		if (mblen != 2)
+			elog(WARNING,
+				 "official invalid string for encoding \"%s\" has mblen %d",
+				 pg_enc2name_tbl[i].name, mblen);
+		valid = pg_encoding_verifymbstr(i, buf, len);
+		if (valid != 0)
+			elog(WARNING,
+				 "official invalid string for encoding \"%s\" has valid prefix of length %d",
+				 pg_enc2name_tbl[i].name, valid);
+		valid = pg_encoding_verifymbstr(i, buf, 1);
+		if (valid != 0)
+			elog(WARNING,
+				 "first byte of official invalid string for encoding \"%s\" has valid prefix of length %d",
+				 pg_enc2name_tbl[i].name, valid);
+		memset(bigbuf, ' ', sizeof(bigbuf));
+		bigbuf[0] = buf[0];
+		bigbuf[1] = buf[1];
+		valid = pg_encoding_verifymbstr(i, bigbuf, sizeof(bigbuf));
+		if (valid != 0)
+			elog(WARNING,
+				 "trailing data changed official invalid string for encoding \"%s\" to have valid prefix of length %d",
+				 pg_enc2name_tbl[i].name, valid);
+	}
+
+	PG_RETURN_VOID();
+}
diff --git a/src/test/regress/sql/conversion.sql b/src/test/regress/sql/conversion.sql
index 02cf39f1ce9..0f01190e9d9 100644
--- a/src/test/regress/sql/conversion.sql
+++ b/src/test/regress/sql/conversion.sql
@@ -1,6 +1,9 @@
 --
 -- create user defined conversion
 --
+
+SELECT FROM test_enc_setup();
+
 CREATE USER regress_conversion_user WITH NOCREATEDB NOCREATEROLE;
 SET SESSION AUTHORIZATION regress_conversion_user;
 CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;