v5-0001-introduce-function-pg_column_toast_chunk_id.patch

From 8c518db9cefe5b1d3155c61d819116a405f099ff Mon Sep 17 00:00:00 2001
From: jian he <jian.universality@gmail.com>
Date: Tue, 30 Jan 2024 14:49:16 +0800
Subject: [PATCH v5 1/1] introduce function, pg_column_toast_chunk_id

This function returns the chunk_id of an on-disk TOASTed value, or
NULL if the value is un-TOASTed or not on disk. This enables users to
know which columns are actually TOASTed. This function is also useful
to identify a problematic row when an error like
  "ERROR:  unexpected chunk number ... (expected ...) for toast value"
---
 doc/src/sgml/func.sgml                       | 17 ++++++++
 src/backend/utils/adt/varlena.c              | 41 ++++++++++++++++++++
 src/include/catalog/pg_proc.dat              |  3 ++
 src/test/regress/expected/misc_functions.out | 21 ++++++++++
 src/test/regress/sql/misc_functions.sql      | 23 +++++++++++
 5 files changed, 105 insertions(+)

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 6788ba8e..4116aaff 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -28502,6 +28502,23 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_column_toast_chunk_id</primary>
+        </indexterm>
+        <function>pg_column_toast_chunk_id</function> ( <type>"any"</type> )
+        <returnvalue>oid</returnvalue>
+       </para>
+       <para>
+        Shows the <structfield>chunk_id</structfield> of an on-disk
+        <acronym>TOAST</acronym>ed value. Returns <literal>NULL</literal>
+        if the value is un-<acronym>TOAST</acronym>ed or not on-disk.
+        See <xref linkend="storage-toast-ondisk"/> for details about
+        <acronym>TOAST</acronym>.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 543afb66..84d36781 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -5105,6 +5105,47 @@ pg_column_compression(PG_FUNCTION_ARGS)
 	PG_RETURN_TEXT_P(cstring_to_text(result));
 }
 
+/*
+ * Return the chunk_id of the on-disk TOASTed value.
+ * Return NULL if the value is unTOASTed or not on disk.
+ */
+Datum
+pg_column_toast_chunk_id(PG_FUNCTION_ARGS)
+{
+	int			typlen;
+	struct varlena *attr;
+	struct varatt_external toast_pointer;
+
+	/* On first call, get the input type's typlen, and save at *fn_extra */
+	if (fcinfo->flinfo->fn_extra == NULL)
+	{
+		/* Lookup the datatype of the supplied argument */
+		Oid			argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
+
+		typlen = get_typlen(argtypeid);
+		if (typlen == 0)		/* should not happen */
+			elog(ERROR, "cache lookup failed for type %u", argtypeid);
+
+		fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
+													  sizeof(int));
+		*((int *) fcinfo->flinfo->fn_extra) = typlen;
+	}
+	else
+		typlen = *((int *) fcinfo->flinfo->fn_extra);
+
+	if (typlen != -1)
+		PG_RETURN_NULL();
+
+	attr = (struct varlena *) DatumGetPointer(PG_GETARG_DATUM(0));
+
+	if (!VARATT_IS_EXTERNAL_ONDISK(attr))
+		PG_RETURN_NULL();
+
+	VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
+
+	PG_RETURN_OID(toast_pointer.va_valueid);
+}
+
 /*
  * string_agg - Concatenates values and returns string.
  *
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 29af4ce6..9ab71646 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -7454,6 +7454,9 @@
 { oid => '2121', descr => 'compression method for the compressed datum',
   proname => 'pg_column_compression', provolatile => 's', prorettype => 'text',
   proargtypes => 'any', prosrc => 'pg_column_compression' },
+{ oid => '8393', descr => 'chunk ID of on-disk TOASTed value',
+  proname => 'pg_column_toast_chunk_id', provolatile => 's', prorettype => 'oid',
+  proargtypes => 'any', prosrc => 'pg_column_toast_chunk_id' },
 { oid => '2322',
   descr => 'total disk space usage for the specified tablespace',
   proname => 'pg_tablespace_size', provolatile => 'v', prorettype => 'int8',
diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out
index 7c154771..e80049a9 100644
--- a/src/test/regress/expected/misc_functions.out
+++ b/src/test/regress/expected/misc_functions.out
@@ -683,3 +683,24 @@ SELECT gist_stratnum_identity(18::smallint);
                      18
 (1 row)
 
+-- Test pg_column_toast_chunk_id:
+-- Check if the returned chunk_id exists in the TOAST table
+CREATE TABLE test_chunk_id (v1 text, v2 text);
+-- v1: small enough not to be TOASTed
+-- v2: large enough to be TOASTed
+INSERT INTO test_chunk_id(v1,v2)
+SELECT repeat('0123456789', 10),
+  (SELECT string_agg(chr((ascii('B') + round(random() * 25)) :: integer),'')
+    FROM generate_series(1,2500));
+DO $$
+  DECLARE result text default 'not_ok';
+  BEGIN
+  EXECUTE format(
+    'SELECT ''ok'' FROM test_chunk_id
+	   WHERE pg_column_toast_chunk_id(v1) IS NULL AND
+	         pg_column_toast_chunk_id(v2) IN (SELECT chunk_id FROM pg_toast.pg_toast_%s)',
+    regclass('test_chunk_id')::int::text) INTO result;
+  RAISE INFO '%', result;
+END; $$;
+INFO:  ok
+DROP TABLE test_chunk_id;
diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql
index 851dad90..3d6de868 100644
--- a/src/test/regress/sql/misc_functions.sql
+++ b/src/test/regress/sql/misc_functions.sql
@@ -254,3 +254,26 @@ FROM pg_walfile_name_offset('0/0'::pg_lsn + :segment_size - 1),
 -- test stratnum support functions
 SELECT gist_stratnum_identity(3::smallint);
 SELECT gist_stratnum_identity(18::smallint);
+
+-- Test pg_column_toast_chunk_id:
+-- Check if the returned chunk_id exists in the TOAST table
+CREATE TABLE test_chunk_id (v1 text, v2 text);
+
+-- v1: small enough not to be TOASTed
+-- v2: large enough to be TOASTed
+INSERT INTO test_chunk_id(v1,v2)
+SELECT repeat('0123456789', 10),
+  (SELECT string_agg(chr((ascii('B') + round(random() * 25)) :: integer),'')
+    FROM generate_series(1,2500));
+
+DO $$
+  DECLARE result text default 'not_ok';
+  BEGIN
+  EXECUTE format(
+    'SELECT ''ok'' FROM test_chunk_id
+	   WHERE pg_column_toast_chunk_id(v1) IS NULL AND
+	         pg_column_toast_chunk_id(v2) IN (SELECT chunk_id FROM pg_toast.pg_toast_%s)',
+    regclass('test_chunk_id')::int::text) INTO result;
+  RAISE INFO '%', result;
+END; $$;
+DROP TABLE test_chunk_id;
\ No newline at end of file
-- 
2.34.1