v2-0001-Add-tests-for-low-level-PGLZ-compression.patch

From ad27ede8a798c264de961b8bc37205a2635e43c5 Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Tue, 14 Apr 2026 02:01:26 +0900
Subject: [PATCH v2] Add tests for low-level PGLZ compression

The goal of this module is to provide an entry point for the coverage of
for low-level APIs of compression and decompression of PGLZ.

This includes tests for the cases detected by fuzzing related to
corrupted data, as fixed in 2b5ba2a0a141:
- Control byte with match tag bit set, where no data follows.
- Control byte with match tag bit set, where 1 byte follows.
- Extension byte needed (len=18), where no data follows.

As bonus points, tests are added for compress/decompress roundtrips, and
for check_complete=false/true.

Backpatch-through: 14
---
 .../regress/expected/compression_pglz.out     | 62 +++++++++++++++++
 src/test/regress/parallel_schedule            |  2 +-
 src/test/regress/regress.c                    | 66 +++++++++++++++++++
 src/test/regress/sql/compression_pglz.sql     | 49 ++++++++++++++
 4 files changed, 178 insertions(+), 1 deletion(-)
 create mode 100644 src/test/regress/expected/compression_pglz.out
 create mode 100644 src/test/regress/sql/compression_pglz.sql

diff --git a/src/test/regress/expected/compression_pglz.out b/src/test/regress/expected/compression_pglz.out
new file mode 100644
index 000000000000..daf457f4ac0a
--- /dev/null
+++ b/src/test/regress/expected/compression_pglz.out
@@ -0,0 +1,62 @@
+--
+-- Tests for PGLZ compression
+--
+-- directory paths and dlsuffix are passed to us in environment variables
+\getenv libdir PG_LIBDIR
+\getenv dlsuffix PG_DLSUFFIX
+\set regresslib :libdir '/regress' :dlsuffix
+CREATE FUNCTION test_pglz_compress(bytea)
+  RETURNS bytea
+  AS :'regresslib' LANGUAGE C STRICT;
+CREATE FUNCTION test_pglz_decompress(bytea, int4, bool)
+  RETURNS bytea
+  AS :'regresslib' LANGUAGE C STRICT;
+-- Round-trip with pglz: compress then decompress.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, false) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+ roundtrip_ok 
+--------------
+ t
+(1 row)
+
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, true) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+ roundtrip_ok 
+--------------
+ t
+(1 row)
+
+-- Decompression with rawsize too large, fails to fill the destination
+-- buffer.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 500, true);
+ERROR:  pglz_decompress failed
+-- Decompression with rawsize too small, fails with source not fully
+-- consumed.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 100, true);
+ERROR:  pglz_decompress failed
+-- Corrupted compressed data.  The control byte is set with match tag bit,
+-- but only 1 byte follows.
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, false);
+ERROR:  pglz_decompress failed
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, true);
+ERROR:  pglz_decompress failed
+-- Corrupted compressed data.  Control byte with match tag bit set, where
+-- no data follows.
+SELECT length(test_pglz_decompress('\x01'::bytea, 1024, false)) AS ctrl_only_len;
+ ctrl_only_len 
+---------------
+             0
+(1 row)
+
+SELECT test_pglz_decompress('\x01'::bytea, 1024, true);
+ERROR:  pglz_decompress failed
+-- Corrupted compressed data.  The match tag encodes len=18 (aka the
+-- extension byte is needed) but there is no data.
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, false);
+ERROR:  pglz_decompress failed
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, true);
+ERROR:  pglz_decompress failed
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index cc365393bb7d..3b059906161f 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -128,7 +128,7 @@ test: partition_merge partition_split partition_join partition_prune reloptions
 # event_trigger depends on create_am and cannot run concurrently with
 # any test that runs DDL
 # oidjoins is read-only, though, and should run late for best coverage
-test: oidjoins event_trigger
+test: oidjoins event_trigger compression_pglz
 
 test: role_ddl tablespace_ddl database_ddl
 
diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c
index 5c19f70b6e8e..2bcb5559a452 100644
--- a/src/test/regress/regress.c
+++ b/src/test/regress/regress.c
@@ -27,6 +27,7 @@
 #include "catalog/pg_type.h"
 #include "commands/sequence.h"
 #include "commands/trigger.h"
+#include "common/pg_lzcompress.h"
 #include "executor/executor.h"
 #include "executor/functions.h"
 #include "executor/spi.h"
@@ -1422,3 +1423,68 @@ test_instr_time(PG_FUNCTION_ARGS)
 
 	PG_RETURN_BOOL(true);
 }
+
+/*
+ * test_pglz_compress
+ *
+ * Compress the input using pglz_compress().  Only the "always" strategy is
+ * currently supported.
+ *
+ * Returns the compressed data, or NULL if compression fails.
+ */
+PG_FUNCTION_INFO_V1(test_pglz_compress);
+Datum
+test_pglz_compress(PG_FUNCTION_ARGS)
+{
+	bytea	   *input = PG_GETARG_BYTEA_PP(0);
+	char	   *source = VARDATA_ANY(input);
+	int32		slen = VARSIZE_ANY_EXHDR(input);
+	int32		maxout = PGLZ_MAX_OUTPUT(slen);
+	bytea	   *result;
+	int32		clen;
+
+	result = (bytea *) palloc(maxout + VARHDRSZ);
+	clen = pglz_compress(source, slen, VARDATA(result),
+						 PGLZ_strategy_always);
+	if (clen < 0)
+		PG_RETURN_NULL();
+
+	SET_VARSIZE(result, clen + VARHDRSZ);
+	PG_RETURN_BYTEA_P(result);
+}
+
+/*
+ * test_pglz_decompress
+ *
+ * Decompress the input using pglz_decompress().
+ *
+ * The second argument is the expected uncompressed data size.  The third
+ * argument is here for the check_complete flag.
+ *
+ * Returns the decompressed data, or raises an error if decompression fails.
+ */
+PG_FUNCTION_INFO_V1(test_pglz_decompress);
+Datum
+test_pglz_decompress(PG_FUNCTION_ARGS)
+{
+	bytea	   *input = PG_GETARG_BYTEA_PP(0);
+	int32		rawsize = PG_GETARG_INT32(1);
+	bool		check_complete = PG_GETARG_BOOL(2);
+	char	   *source = VARDATA_ANY(input);
+	int32		slen = VARSIZE_ANY_EXHDR(input);
+	bytea	   *result;
+	int32		dlen;
+
+	if (rawsize < 0)
+		elog(ERROR, "rawsize must not be negative");
+
+	result = (bytea *) palloc(rawsize + VARHDRSZ);
+
+	dlen = pglz_decompress(source, slen, VARDATA(result),
+						   rawsize, check_complete);
+	if (dlen < 0)
+		elog(ERROR, "pglz_decompress failed");
+
+	SET_VARSIZE(result, dlen + VARHDRSZ);
+	PG_RETURN_BYTEA_P(result);
+}
diff --git a/src/test/regress/sql/compression_pglz.sql b/src/test/regress/sql/compression_pglz.sql
new file mode 100644
index 000000000000..115f1300d748
--- /dev/null
+++ b/src/test/regress/sql/compression_pglz.sql
@@ -0,0 +1,49 @@
+--
+-- Tests for PGLZ compression
+--
+
+-- directory paths and dlsuffix are passed to us in environment variables
+\getenv libdir PG_LIBDIR
+\getenv dlsuffix PG_DLSUFFIX
+
+\set regresslib :libdir '/regress' :dlsuffix
+
+CREATE FUNCTION test_pglz_compress(bytea)
+  RETURNS bytea
+  AS :'regresslib' LANGUAGE C STRICT;
+CREATE FUNCTION test_pglz_decompress(bytea, int4, bool)
+  RETURNS bytea
+  AS :'regresslib' LANGUAGE C STRICT;
+
+-- Round-trip with pglz: compress then decompress.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, false) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 400, true) =
+    decode(repeat('abcd', 100), 'escape') AS roundtrip_ok;
+
+-- Decompression with rawsize too large, fails to fill the destination
+-- buffer.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 500, true);
+
+-- Decompression with rawsize too small, fails with source not fully
+-- consumed.
+SELECT test_pglz_decompress(test_pglz_compress(
+    decode(repeat('abcd', 100), 'escape')), 100, true);
+
+-- Corrupted compressed data.  The control byte is set with match tag bit,
+-- but only 1 byte follows.
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, false);
+SELECT test_pglz_decompress('\x01ff'::bytea, 1024, true);
+
+-- Corrupted compressed data.  Control byte with match tag bit set, where
+-- no data follows.
+SELECT length(test_pglz_decompress('\x01'::bytea, 1024, false)) AS ctrl_only_len;
+SELECT test_pglz_decompress('\x01'::bytea, 1024, true);
+
+-- Corrupted compressed data.  The match tag encodes len=18 (aka the
+-- extension byte is needed) but there is no data.
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, false);
+SELECT test_pglz_decompress('\x010f01'::bytea, 1024, true);
-- 
2.53.0