New header varatt.h split off from postgres.h

This new header contains all the variable-length data types support
(TOAST support) from postgres.h, which isn't needed by large parts of
the backend code.

Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://www.postgresql.org/message-id/flat/ddcce239-0f29-6e62-4b47-1f8ca742addf%40enterprisedb.com

contrib/citext/citext.c

@@ -8,6 +8,7 @@
 #include "utils/builtins.h"
 #include "utils/formatting.h"
 #include "utils/varlena.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

contrib/cube/cubeparse.y

@@ -9,6 +9,7 @@
 #include "cubedata.h"
 #include "nodes/miscnodes.h"
 #include "utils/float.h"
+#include "varatt.h"
 
 /* All grammar constructs return strings */
 #define YYSTYPE char *

contrib/fuzzystrmatch/fuzzystrmatch.c

@@ -43,6 +43,7 @@
 #include "mb/pg_wchar.h"
 #include "utils/builtins.h"
 #include "utils/varlena.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

contrib/ltree/ltree_io.c

@@ -11,6 +11,7 @@
 #include "libpq/pqformat.h"
 #include "ltree.h"
 #include "utils/memutils.h"
+#include "varatt.h"
 
 
 typedef struct

contrib/ltree/ltxtquery_io.c

@@ -12,6 +12,7 @@
 #include "ltree.h"
 #include "miscadmin.h"
 #include "nodes/miscnodes.h"
+#include "varatt.h"
 
 
 /* parser's states */

contrib/pg_trgm/trgm_gin.c

@@ -7,6 +7,7 @@
 #include "access/stratnum.h"
 #include "fmgr.h"
 #include "trgm.h"
+#include "varatt.h"
 
 PG_FUNCTION_INFO_V1(gin_extract_trgm);
 PG_FUNCTION_INFO_V1(gin_extract_value_trgm);

contrib/pg_trgm/trgm_gist.c

@@ -8,6 +8,7 @@
 #include "fmgr.h"
 #include "port/pg_bitutils.h"
 #include "trgm.h"
+#include "varatt.h"
 
 /* gist_trgm_ops opclass options */
 typedef struct

contrib/pg_trgm/trgm_regexp.c

@@ -196,6 +196,7 @@
 #include "tsearch/ts_locale.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "varatt.h"
 
 /*
  * Uncomment (or use -DTRGM_REGEXP_DEBUG) to print debug info,

contrib/pgcrypto/pgcrypto.c

@@ -39,6 +39,7 @@
 #include "px.h"
 #include "utils/builtins.h"
 #include "utils/uuid.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

contrib/uuid-ossp/uuid-ossp.c

@@ -19,6 +19,7 @@
 #include "port/pg_bswap.h"
 #include "utils/builtins.h"
 #include "utils/uuid.h"
+#include "varatt.h"
 
 /*
  * It's possible that there's more than one uuid.h header file present.

doc/src/sgml/xfunc.sgml

@@ -2390,6 +2390,7 @@ PG_FUNCTION_INFO_V1(funcname);
 #include <string.h>
 #include "fmgr.h"
 #include "utils/geo_decls.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

src/backend/access/common/toast_compression.c

@@ -22,6 +22,7 @@
 #include "common/pg_lzcompress.h"
 #include "fmgr.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 /* GUC */
 int			default_toast_compression = TOAST_PGLZ_COMPRESSION;

src/backend/access/hash/hashfunc.c

@@ -32,6 +32,7 @@
 #include "utils/builtins.h"
 #include "utils/float.h"
 #include "utils/pg_locale.h"
+#include "varatt.h"
 
 /*
  * Datatype-specific hash functions.

src/backend/access/spgist/spgtextproc.c

@@ -46,6 +46,7 @@
 #include "utils/datum.h"
 #include "utils/pg_locale.h"
 #include "utils/varlena.h"
+#include "varatt.h"
 
 
 /*

src/backend/access/table/toast_helper.c

@@ -19,6 +19,7 @@
 #include "access/toast_helper.h"
 #include "access/toast_internals.h"
 #include "catalog/pg_type_d.h"
+#include "varatt.h"
 
 
 /*

src/backend/libpq/be-fsstubs.c

@@ -53,6 +53,7 @@
 #include "utils/builtins.h"
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
+#include "varatt.h"
 
 /* define this to enable debug logging */
 /* #define FSDB 1 */

src/backend/libpq/pqformat.c

@@ -77,6 +77,7 @@
 #include "libpq/pqformat.h"
 #include "mb/pg_wchar.h"
 #include "port/pg_bswap.h"
+#include "varatt.h"
 
 
 /* --------------------------------

src/backend/tsearch/ts_parse.c

@@ -16,6 +16,7 @@
 
 #include "tsearch/ts_cache.h"
 #include "tsearch/ts_utils.h"
+#include "varatt.h"
 
 #define IGNORE_LONGLEXEME	1
 

src/backend/tsearch/ts_typanalyze.c

@@ -19,6 +19,7 @@
 #include "common/hashfn.h"
 #include "tsearch/ts_type.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 
 /* A hash key for lexemes */

src/backend/utils/adt/ascii.c

@@ -14,6 +14,7 @@
 #include "mb/pg_wchar.h"
 #include "utils/ascii.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 static void pg_to_ascii(unsigned char *src, unsigned char *src_end,
 						unsigned char *dest, int enc);

src/backend/utils/adt/char.c

@@ -19,6 +19,7 @@
 
 #include "libpq/pqformat.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 #define ISOCTAL(c)   (((c) >= '0') && ((c) <= '7'))
 #define TOOCTAL(c)   ((c) + '0')

src/backend/utils/adt/cryptohashfuncs.c

@@ -17,6 +17,7 @@
 #include "common/md5.h"
 #include "common/sha2.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 
 /*

src/backend/utils/adt/encode.c

@@ -18,6 +18,7 @@
 #include "mb/pg_wchar.h"
 #include "utils/builtins.h"
 #include "utils/memutils.h"
+#include "varatt.h"
 
 
 /*

src/backend/utils/adt/formatting.c

@@ -88,6 +88,7 @@
 #include "utils/memutils.h"
 #include "utils/numeric.h"
 #include "utils/pg_locale.h"
+#include "varatt.h"
 
 
 /* ----------

src/backend/utils/adt/geo_ops.c

@@ -35,6 +35,7 @@
 #include "utils/float.h"
 #include "utils/fmgrprotos.h"
 #include "utils/geo_decls.h"
+#include "varatt.h"
 
 /*
  * * Type constructors have this form:

src/backend/utils/adt/like.c

@@ -24,6 +24,7 @@
 #include "miscadmin.h"
 #include "utils/builtins.h"
 #include "utils/pg_locale.h"
+#include "varatt.h"
 
 
 #define LIKE_TRUE						1

src/backend/utils/adt/network_gist.c

@@ -51,6 +51,7 @@
 #include "access/stratnum.h"
 #include "utils/builtins.h"
 #include "utils/inet.h"
+#include "varatt.h"
 
 /*
  * Operator strategy numbers used in the GiST inet_ops opclass

src/backend/utils/adt/network_spgist.c

@@ -37,6 +37,7 @@
 #include "catalog/pg_type.h"
 #include "utils/builtins.h"
 #include "utils/inet.h"
+#include "varatt.h"
 
 
 static int	inet_spg_node_number(const inet *val, int commonbits);

src/backend/utils/adt/oracle_compat.c

@@ -21,6 +21,7 @@
 #include "utils/builtins.h"
 #include "utils/formatting.h"
 #include "utils/memutils.h"
+#include "varatt.h"
 
 
 static text *dotrim(const char *string, int stringlen,

src/backend/utils/adt/quote.c

@@ -14,6 +14,7 @@
 #include "postgres.h"
 
 #include "utils/builtins.h"
+#include "varatt.h"
 
 
 /*

src/backend/utils/adt/rangetypes.c

@@ -42,6 +42,7 @@
 #include "utils/lsyscache.h"
 #include "utils/rangetypes.h"
 #include "utils/timestamp.h"
+#include "varatt.h"
 
 
 /* fn_extra cache entry for one of the range I/O functions */

src/backend/utils/adt/rangetypes_typanalyze.c

@@ -31,6 +31,7 @@
 #include "utils/lsyscache.h"
 #include "utils/rangetypes.h"
 #include "utils/multirangetypes.h"
+#include "varatt.h"
 
 static int	float8_qsort_cmp(const void *a1, const void *a2, void *arg);
 static int	range_bound_qsort_cmp(const void *a1, const void *a2, void *arg);

src/backend/utils/adt/tsginidx.c

@@ -19,6 +19,7 @@
 #include "tsearch/ts_type.h"
 #include "tsearch/ts_utils.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 
 Datum

src/backend/utils/adt/tsquery.c

@@ -23,6 +23,7 @@
 #include "utils/builtins.h"
 #include "utils/memutils.h"
 #include "utils/pg_crc.h"
+#include "varatt.h"
 
 /* FTS operator priorities, see ts_type.h */
 const int	tsearch_op_priority[OP_COUNT] =

src/backend/utils/adt/tsquery_cleanup.c

@@ -17,6 +17,7 @@
 
 #include "miscadmin.h"
 #include "tsearch/ts_utils.h"
+#include "varatt.h"
 
 typedef struct NODE
 {

src/backend/utils/adt/tsquery_op.c

@@ -17,6 +17,7 @@
 #include "lib/qunique.h"
 #include "tsearch/ts_utils.h"
 #include "utils/builtins.h"
+#include "varatt.h"
 
 Datum
 tsquery_numnode(PG_FUNCTION_ARGS)

src/backend/utils/adt/tsquery_util.c

@@ -16,6 +16,7 @@
 
 #include "miscadmin.h"
 #include "tsearch/ts_utils.h"
+#include "varatt.h"
 
 /*
  * Build QTNode tree for a tsquery given in QueryItem array format.

src/backend/utils/adt/tsvector.c

@@ -20,6 +20,7 @@
 #include "tsearch/ts_utils.h"
 #include "utils/builtins.h"
 #include "utils/memutils.h"
+#include "varatt.h"
 
 typedef struct
 {

src/backend/utils/cache/attoptcache.c

@@ -22,6 +22,7 @@
 #include "utils/hsearch.h"
 #include "utils/inval.h"
 #include "utils/syscache.h"
+#include "varatt.h"
 
 
 /* Hash table for information about each attribute's options */

src/backend/utils/cache/spccache.c

@@ -29,6 +29,7 @@
 #include "utils/inval.h"
 #include "utils/spccache.h"
 #include "utils/syscache.h"
+#include "varatt.h"
 
 
 /* Hash table for information about each tablespace */

src/backend/utils/mb/mbutils.c

@@ -40,6 +40,7 @@
 #include "utils/builtins.h"
 #include "utils/memutils.h"
 #include "utils/syscache.h"
+#include "varatt.h"
 
 /*
  * We maintain a simple linked list caching the fmgr lookup info for the

src/include/access/htup_details.h

@@ -19,6 +19,7 @@
 #include "access/tupdesc.h"
 #include "access/tupmacs.h"
 #include "storage/bufpage.h"
+#include "varatt.h"
 
 /*
  * MaxTupleAttributeNumber limits the number of (user) columns in a tuple.

src/include/meson.build

@@ -113,6 +113,7 @@ install_headers(
   'postgres.h',
   'postgres_ext.h',
   'postgres_fe.h',
+  'varatt.h',
   'windowapi.h',
   pg_config_ext,
   pg_config_os,

src/include/postgres.h

@@ -23,9 +23,8 @@
  *
  *	  section	description
  *	  -------	------------------------------------------------
- *		1)		variable-length datatypes (TOAST support)
+ *		1)		Datum type + support functions
- *		2)		Datum type + support functions
+ *		2)		miscellaneous
- *		3)		miscellaneous
  *
  *	 NOTES
  *
@@ -36,8 +35,7 @@
  *	postgres_fe.h.  We do that since those type definitions are needed by
  *	frontend modules that want to deal with binary data transmission to or
  *	from the backend.  Type definitions in this file should be for
- *	representations that never escape the backend, such as Datum or
+ *	representations that never escape the backend, such as Datum.
- *	TOASTed varlena objects.
  *
  *----------------------------------------------------------------
  */
@@ -49,353 +47,7 @@
 #include "utils/palloc.h"
 
 /* ----------------------------------------------------------------
- *				Section 1:	variable-length datatypes (TOAST support)
+ *				Section 1:	Datum type + support functions
- * ----------------------------------------------------------------
- */
-
-/*
- * struct varatt_external is a traditional "TOAST pointer", that is, the
- * information needed to fetch a Datum stored out-of-line in a TOAST table.
- * The data is compressed if and only if the external size stored in
- * va_extinfo is less than va_rawsize - VARHDRSZ.
- *
- * This struct must not contain any padding, because we sometimes compare
- * these pointers using memcmp.
- *
- * Note that this information is stored unaligned within actual tuples, so
- * you need to memcpy from the tuple into a local struct variable before
- * you can look at these fields!  (The reason we use memcmp is to avoid
- * having to do that just to detect equality of two TOAST pointers...)
- */
-typedef struct varatt_external
-{
-	int32		va_rawsize;		/* Original data size (includes header) */
-	uint32		va_extinfo;		/* External saved size (without header) and
-								 * compression method */
-	Oid			va_valueid;		/* Unique ID of value within TOAST table */
-	Oid			va_toastrelid;	/* RelID of TOAST table containing it */
-}			varatt_external;
-
-/*
- * These macros define the "saved size" portion of va_extinfo.  Its remaining
- * two high-order bits identify the compression method.
- */
-#define VARLENA_EXTSIZE_BITS	30
-#define VARLENA_EXTSIZE_MASK	((1U << VARLENA_EXTSIZE_BITS) - 1)
-
-/*
- * struct varatt_indirect is a "TOAST pointer" representing an out-of-line
- * Datum that's stored in memory, not in an external toast relation.
- * The creator of such a Datum is entirely responsible that the referenced
- * storage survives for as long as referencing pointer Datums can exist.
- *
- * Note that just as for struct varatt_external, this struct is stored
- * unaligned within any containing tuple.
- */
-typedef struct varatt_indirect
-{
-	struct varlena *pointer;	/* Pointer to in-memory varlena */
-}			varatt_indirect;
-
-/*
- * struct varatt_expanded is a "TOAST pointer" representing an out-of-line
- * Datum that is stored in memory, in some type-specific, not necessarily
- * physically contiguous format that is convenient for computation not
- * storage.  APIs for this, in particular the definition of struct
- * ExpandedObjectHeader, are in src/include/utils/expandeddatum.h.
- *
- * Note that just as for struct varatt_external, this struct is stored
- * unaligned within any containing tuple.
- */
-typedef struct ExpandedObjectHeader ExpandedObjectHeader;
-
-typedef struct varatt_expanded
-{
-	ExpandedObjectHeader *eohptr;
-} varatt_expanded;
-
-/*
- * Type tag for the various sorts of "TOAST pointer" datums.  The peculiar
- * value for VARTAG_ONDISK comes from a requirement for on-disk compatibility
- * with a previous notion that the tag field was the pointer datum's length.
- */
-typedef enum vartag_external
-{
-	VARTAG_INDIRECT = 1,
-	VARTAG_EXPANDED_RO = 2,
-	VARTAG_EXPANDED_RW = 3,
-	VARTAG_ONDISK = 18
-} vartag_external;
-
-/* this test relies on the specific tag values above */
-#define VARTAG_IS_EXPANDED(tag) \
-	(((tag) & ~1) == VARTAG_EXPANDED_RO)
-
-#define VARTAG_SIZE(tag) \
-	((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) : \
-	 VARTAG_IS_EXPANDED(tag) ? sizeof(varatt_expanded) : \
-	 (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \
-	 (AssertMacro(false), 0))
-
-/*
- * These structs describe the header of a varlena object that may have been
- * TOASTed.  Generally, don't reference these structs directly, but use the
- * macros below.
- *
- * We use separate structs for the aligned and unaligned cases because the
- * compiler might otherwise think it could generate code that assumes
- * alignment while touching fields of a 1-byte-header varlena.
- */
-typedef union
-{
-	struct						/* Normal varlena (4-byte length) */
-	{
-		uint32		va_header;
-		char		va_data[FLEXIBLE_ARRAY_MEMBER];
-	}			va_4byte;
-	struct						/* Compressed-in-line format */
-	{
-		uint32		va_header;
-		uint32		va_tcinfo;	/* Original data size (excludes header) and
-								 * compression method; see va_extinfo */
-		char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */
-	}			va_compressed;
-} varattrib_4b;
-
-typedef struct
-{
-	uint8		va_header;
-	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Data begins here */
-} varattrib_1b;
-
-/* TOAST pointers are a subset of varattrib_1b with an identifying tag byte */
-typedef struct
-{
-	uint8		va_header;		/* Always 0x80 or 0x01 */
-	uint8		va_tag;			/* Type of datum */
-	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Type-specific data */
-} varattrib_1b_e;
-
-/*
- * Bit layouts for varlena headers on big-endian machines:
- *
- * 00xxxxxx 4-byte length word, aligned, uncompressed data (up to 1G)
- * 01xxxxxx 4-byte length word, aligned, *compressed* data (up to 1G)
- * 10000000 1-byte length word, unaligned, TOAST pointer
- * 1xxxxxxx 1-byte length word, unaligned, uncompressed data (up to 126b)
- *
- * Bit layouts for varlena headers on little-endian machines:
- *
- * xxxxxx00 4-byte length word, aligned, uncompressed data (up to 1G)
- * xxxxxx10 4-byte length word, aligned, *compressed* data (up to 1G)
- * 00000001 1-byte length word, unaligned, TOAST pointer
- * xxxxxxx1 1-byte length word, unaligned, uncompressed data (up to 126b)
- *
- * The "xxx" bits are the length field (which includes itself in all cases).
- * In the big-endian case we mask to extract the length, in the little-endian
- * case we shift.  Note that in both cases the flag bits are in the physically
- * first byte.  Also, it is not possible for a 1-byte length word to be zero;
- * this lets us disambiguate alignment padding bytes from the start of an
- * unaligned datum.  (We now *require* pad bytes to be filled with zero!)
- *
- * In TOAST pointers the va_tag field (see varattrib_1b_e) is used to discern
- * the specific type and length of the pointer datum.
- */
-
-/*
- * Endian-dependent macros.  These are considered internal --- use the
- * external macros below instead of using these directly.
- *
- * Note: IS_1B is true for external toast records but VARSIZE_1B will return 0
- * for such records. Hence you should usually check for IS_EXTERNAL before
- * checking for IS_1B.
- */
-
-#ifdef WORDS_BIGENDIAN
-
-#define VARATT_IS_4B(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x80) == 0x00)
-#define VARATT_IS_4B_U(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0xC0) == 0x00)
-#define VARATT_IS_4B_C(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0xC0) == 0x40)
-#define VARATT_IS_1B(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x80) == 0x80)
-#define VARATT_IS_1B_E(PTR) \
-	((((varattrib_1b *) (PTR))->va_header) == 0x80)
-#define VARATT_NOT_PAD_BYTE(PTR) \
-	(*((uint8 *) (PTR)) != 0)
-
-/* VARSIZE_4B() should only be used on known-aligned data */
-#define VARSIZE_4B(PTR) \
-	(((varattrib_4b *) (PTR))->va_4byte.va_header & 0x3FFFFFFF)
-#define VARSIZE_1B(PTR) \
-	(((varattrib_1b *) (PTR))->va_header & 0x7F)
-#define VARTAG_1B_E(PTR) \
-	(((varattrib_1b_e *) (PTR))->va_tag)
-
-#define SET_VARSIZE_4B(PTR,len) \
-	(((varattrib_4b *) (PTR))->va_4byte.va_header = (len) & 0x3FFFFFFF)
-#define SET_VARSIZE_4B_C(PTR,len) \
-	(((varattrib_4b *) (PTR))->va_4byte.va_header = ((len) & 0x3FFFFFFF) | 0x40000000)
-#define SET_VARSIZE_1B(PTR,len) \
-	(((varattrib_1b *) (PTR))->va_header = (len) | 0x80)
-#define SET_VARTAG_1B_E(PTR,tag) \
-	(((varattrib_1b_e *) (PTR))->va_header = 0x80, \
-	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
-
-#else							/* !WORDS_BIGENDIAN */
-
-#define VARATT_IS_4B(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x00)
-#define VARATT_IS_4B_U(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x00)
-#define VARATT_IS_4B_C(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x02)
-#define VARATT_IS_1B(PTR) \
-	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x01)
-#define VARATT_IS_1B_E(PTR) \
-	((((varattrib_1b *) (PTR))->va_header) == 0x01)
-#define VARATT_NOT_PAD_BYTE(PTR) \
-	(*((uint8 *) (PTR)) != 0)
-
-/* VARSIZE_4B() should only be used on known-aligned data */
-#define VARSIZE_4B(PTR) \
-	((((varattrib_4b *) (PTR))->va_4byte.va_header >> 2) & 0x3FFFFFFF)
-#define VARSIZE_1B(PTR) \
-	((((varattrib_1b *) (PTR))->va_header >> 1) & 0x7F)
-#define VARTAG_1B_E(PTR) \
-	(((varattrib_1b_e *) (PTR))->va_tag)
-
-#define SET_VARSIZE_4B(PTR,len) \
-	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2))
-#define SET_VARSIZE_4B_C(PTR,len) \
-	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2) | 0x02)
-#define SET_VARSIZE_1B(PTR,len) \
-	(((varattrib_1b *) (PTR))->va_header = (((uint8) (len)) << 1) | 0x01)
-#define SET_VARTAG_1B_E(PTR,tag) \
-	(((varattrib_1b_e *) (PTR))->va_header = 0x01, \
-	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
-
-#endif							/* WORDS_BIGENDIAN */
-
-#define VARDATA_4B(PTR)		(((varattrib_4b *) (PTR))->va_4byte.va_data)
-#define VARDATA_4B_C(PTR)	(((varattrib_4b *) (PTR))->va_compressed.va_data)
-#define VARDATA_1B(PTR)		(((varattrib_1b *) (PTR))->va_data)
-#define VARDATA_1B_E(PTR)	(((varattrib_1b_e *) (PTR))->va_data)
-
-/*
- * Externally visible TOAST macros begin here.
- */
-
-#define VARHDRSZ_EXTERNAL		offsetof(varattrib_1b_e, va_data)
-#define VARHDRSZ_COMPRESSED		offsetof(varattrib_4b, va_compressed.va_data)
-#define VARHDRSZ_SHORT			offsetof(varattrib_1b, va_data)
-
-#define VARATT_SHORT_MAX		0x7F
-#define VARATT_CAN_MAKE_SHORT(PTR) \
-	(VARATT_IS_4B_U(PTR) && \
-	 (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) <= VARATT_SHORT_MAX)
-#define VARATT_CONVERTED_SHORT_SIZE(PTR) \
-	(VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT)
-
-/*
- * In consumers oblivious to data alignment, call PG_DETOAST_DATUM_PACKED(),
- * VARDATA_ANY(), VARSIZE_ANY() and VARSIZE_ANY_EXHDR().  Elsewhere, call
- * PG_DETOAST_DATUM(), VARDATA() and VARSIZE().  Directly fetching an int16,
- * int32 or wider field in the struct representing the datum layout requires
- * aligned data.  memcpy() is alignment-oblivious, as are most operations on
- * datatypes, such as text, whose layout struct contains only char fields.
- *
- * Code assembling a new datum should call VARDATA() and SET_VARSIZE().
- * (Datums begin life untoasted.)
- *
- * Other macros here should usually be used only by tuple assembly/disassembly
- * code and code that specifically wants to work with still-toasted Datums.
- */
-#define VARDATA(PTR)						VARDATA_4B(PTR)
-#define VARSIZE(PTR)						VARSIZE_4B(PTR)
-
-#define VARSIZE_SHORT(PTR)					VARSIZE_1B(PTR)
-#define VARDATA_SHORT(PTR)					VARDATA_1B(PTR)
-
-#define VARTAG_EXTERNAL(PTR)				VARTAG_1B_E(PTR)
-#define VARSIZE_EXTERNAL(PTR)				(VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR)))
-#define VARDATA_EXTERNAL(PTR)				VARDATA_1B_E(PTR)
-
-#define VARATT_IS_COMPRESSED(PTR)			VARATT_IS_4B_C(PTR)
-#define VARATT_IS_EXTERNAL(PTR)				VARATT_IS_1B_E(PTR)
-#define VARATT_IS_EXTERNAL_ONDISK(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK)
-#define VARATT_IS_EXTERNAL_INDIRECT(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT)
-#define VARATT_IS_EXTERNAL_EXPANDED_RO(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RO)
-#define VARATT_IS_EXTERNAL_EXPANDED_RW(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RW)
-#define VARATT_IS_EXTERNAL_EXPANDED(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)))
-#define VARATT_IS_EXTERNAL_NON_EXPANDED(PTR) \
-	(VARATT_IS_EXTERNAL(PTR) && !VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)))
-#define VARATT_IS_SHORT(PTR)				VARATT_IS_1B(PTR)
-#define VARATT_IS_EXTENDED(PTR)				(!VARATT_IS_4B_U(PTR))
-
-#define SET_VARSIZE(PTR, len)				SET_VARSIZE_4B(PTR, len)
-#define SET_VARSIZE_SHORT(PTR, len)			SET_VARSIZE_1B(PTR, len)
-#define SET_VARSIZE_COMPRESSED(PTR, len)	SET_VARSIZE_4B_C(PTR, len)
-
-#define SET_VARTAG_EXTERNAL(PTR, tag)		SET_VARTAG_1B_E(PTR, tag)
-
-#define VARSIZE_ANY(PTR) \
-	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR) : \
-	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR) : \
-	  VARSIZE_4B(PTR)))
-
-/* Size of a varlena data, excluding header */
-#define VARSIZE_ANY_EXHDR(PTR) \
-	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR)-VARHDRSZ_EXTERNAL : \
-	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR)-VARHDRSZ_SHORT : \
-	  VARSIZE_4B(PTR)-VARHDRSZ))
-
-/* caution: this will not work on an external or compressed-in-line Datum */
-/* caution: this will return a possibly unaligned pointer */
-#define VARDATA_ANY(PTR) \
-	 (VARATT_IS_1B(PTR) ? VARDATA_1B(PTR) : VARDATA_4B(PTR))
-
-/* Decompressed size and compression method of a compressed-in-line Datum */
-#define VARDATA_COMPRESSED_GET_EXTSIZE(PTR) \
-	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK)
-#define VARDATA_COMPRESSED_GET_COMPRESS_METHOD(PTR) \
-	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS)
-
-/* Same for external Datums; but note argument is a struct varatt_external */
-#define VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) \
-	((toast_pointer).va_extinfo & VARLENA_EXTSIZE_MASK)
-#define VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer) \
-	((toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS)
-
-#define VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, len, cm) \
-	do { \
-		Assert((cm) == TOAST_PGLZ_COMPRESSION_ID || \
-			   (cm) == TOAST_LZ4_COMPRESSION_ID); \
-		((toast_pointer).va_extinfo = \
-			(len) | ((uint32) (cm) << VARLENA_EXTSIZE_BITS)); \
-	} while (0)
-
-/*
- * Testing whether an externally-stored value is compressed now requires
- * comparing size stored in va_extinfo (the actual length of the external data)
- * to rawsize (the original uncompressed datum's size).  The latter includes
- * VARHDRSZ overhead, the former doesn't.  We never use compression unless it
- * actually saves space, so we expect either equality or less-than.
- */
-#define VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer) \
-	(VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) < \
-	 (toast_pointer).va_rawsize - VARHDRSZ)
-
-
-/* ----------------------------------------------------------------
- *				Section 2:	Datum type + support functions
  * ----------------------------------------------------------------
  */
 
@@ -907,7 +559,7 @@ extern Datum Float8GetDatum(float8 X);
 
 
 /* ----------------------------------------------------------------
- *				Section 3:	miscellaneous
+ *				Section 2:	miscellaneous
  * ----------------------------------------------------------------
  */
 

src/include/utils/expandeddatum.h

@@ -44,6 +44,8 @@
 #ifndef EXPANDEDDATUM_H
 #define EXPANDEDDATUM_H
 
+#include "varatt.h"
+
 /* Size of an EXTERNAL datum that contains a pointer to an expanded object */
 #define EXPANDED_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(varatt_expanded))
 

src/include/varatt.h

@@ -0,0 +1,358 @@
+/*-------------------------------------------------------------------------
+ *
+ * varatt.h
+ *	  variable-length datatypes (TOAST support)
+ *
+ *
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1995, Regents of the University of California
+ *
+ * src/include/varatt.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef VARATT_H
+#define VARATT_H
+
+/*
+ * struct varatt_external is a traditional "TOAST pointer", that is, the
+ * information needed to fetch a Datum stored out-of-line in a TOAST table.
+ * The data is compressed if and only if the external size stored in
+ * va_extinfo is less than va_rawsize - VARHDRSZ.
+ *
+ * This struct must not contain any padding, because we sometimes compare
+ * these pointers using memcmp.
+ *
+ * Note that this information is stored unaligned within actual tuples, so
+ * you need to memcpy from the tuple into a local struct variable before
+ * you can look at these fields!  (The reason we use memcmp is to avoid
+ * having to do that just to detect equality of two TOAST pointers...)
+ */
+typedef struct varatt_external
+{
+	int32		va_rawsize;		/* Original data size (includes header) */
+	uint32		va_extinfo;		/* External saved size (without header) and
+								 * compression method */
+	Oid			va_valueid;		/* Unique ID of value within TOAST table */
+	Oid			va_toastrelid;	/* RelID of TOAST table containing it */
+}			varatt_external;
+
+/*
+ * These macros define the "saved size" portion of va_extinfo.  Its remaining
+ * two high-order bits identify the compression method.
+ */
+#define VARLENA_EXTSIZE_BITS	30
+#define VARLENA_EXTSIZE_MASK	((1U << VARLENA_EXTSIZE_BITS) - 1)
+
+/*
+ * struct varatt_indirect is a "TOAST pointer" representing an out-of-line
+ * Datum that's stored in memory, not in an external toast relation.
+ * The creator of such a Datum is entirely responsible that the referenced
+ * storage survives for as long as referencing pointer Datums can exist.
+ *
+ * Note that just as for struct varatt_external, this struct is stored
+ * unaligned within any containing tuple.
+ */
+typedef struct varatt_indirect
+{
+	struct varlena *pointer;	/* Pointer to in-memory varlena */
+}			varatt_indirect;
+
+/*
+ * struct varatt_expanded is a "TOAST pointer" representing an out-of-line
+ * Datum that is stored in memory, in some type-specific, not necessarily
+ * physically contiguous format that is convenient for computation not
+ * storage.  APIs for this, in particular the definition of struct
+ * ExpandedObjectHeader, are in src/include/utils/expandeddatum.h.
+ *
+ * Note that just as for struct varatt_external, this struct is stored
+ * unaligned within any containing tuple.
+ */
+typedef struct ExpandedObjectHeader ExpandedObjectHeader;
+
+typedef struct varatt_expanded
+{
+	ExpandedObjectHeader *eohptr;
+} varatt_expanded;
+
+/*
+ * Type tag for the various sorts of "TOAST pointer" datums.  The peculiar
+ * value for VARTAG_ONDISK comes from a requirement for on-disk compatibility
+ * with a previous notion that the tag field was the pointer datum's length.
+ */
+typedef enum vartag_external
+{
+	VARTAG_INDIRECT = 1,
+	VARTAG_EXPANDED_RO = 2,
+	VARTAG_EXPANDED_RW = 3,
+	VARTAG_ONDISK = 18
+} vartag_external;
+
+/* this test relies on the specific tag values above */
+#define VARTAG_IS_EXPANDED(tag) \
+	(((tag) & ~1) == VARTAG_EXPANDED_RO)
+
+#define VARTAG_SIZE(tag) \
+	((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) : \
+	 VARTAG_IS_EXPANDED(tag) ? sizeof(varatt_expanded) : \
+	 (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \
+	 (AssertMacro(false), 0))
+
+/*
+ * These structs describe the header of a varlena object that may have been
+ * TOASTed.  Generally, don't reference these structs directly, but use the
+ * macros below.
+ *
+ * We use separate structs for the aligned and unaligned cases because the
+ * compiler might otherwise think it could generate code that assumes
+ * alignment while touching fields of a 1-byte-header varlena.
+ */
+typedef union
+{
+	struct						/* Normal varlena (4-byte length) */
+	{
+		uint32		va_header;
+		char		va_data[FLEXIBLE_ARRAY_MEMBER];
+	}			va_4byte;
+	struct						/* Compressed-in-line format */
+	{
+		uint32		va_header;
+		uint32		va_tcinfo;	/* Original data size (excludes header) and
+								 * compression method; see va_extinfo */
+		char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */
+	}			va_compressed;
+} varattrib_4b;
+
+typedef struct
+{
+	uint8		va_header;
+	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Data begins here */
+} varattrib_1b;
+
+/* TOAST pointers are a subset of varattrib_1b with an identifying tag byte */
+typedef struct
+{
+	uint8		va_header;		/* Always 0x80 or 0x01 */
+	uint8		va_tag;			/* Type of datum */
+	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Type-specific data */
+} varattrib_1b_e;
+
+/*
+ * Bit layouts for varlena headers on big-endian machines:
+ *
+ * 00xxxxxx 4-byte length word, aligned, uncompressed data (up to 1G)
+ * 01xxxxxx 4-byte length word, aligned, *compressed* data (up to 1G)
+ * 10000000 1-byte length word, unaligned, TOAST pointer
+ * 1xxxxxxx 1-byte length word, unaligned, uncompressed data (up to 126b)
+ *
+ * Bit layouts for varlena headers on little-endian machines:
+ *
+ * xxxxxx00 4-byte length word, aligned, uncompressed data (up to 1G)
+ * xxxxxx10 4-byte length word, aligned, *compressed* data (up to 1G)
+ * 00000001 1-byte length word, unaligned, TOAST pointer
+ * xxxxxxx1 1-byte length word, unaligned, uncompressed data (up to 126b)
+ *
+ * The "xxx" bits are the length field (which includes itself in all cases).
+ * In the big-endian case we mask to extract the length, in the little-endian
+ * case we shift.  Note that in both cases the flag bits are in the physically
+ * first byte.  Also, it is not possible for a 1-byte length word to be zero;
+ * this lets us disambiguate alignment padding bytes from the start of an
+ * unaligned datum.  (We now *require* pad bytes to be filled with zero!)
+ *
+ * In TOAST pointers the va_tag field (see varattrib_1b_e) is used to discern
+ * the specific type and length of the pointer datum.
+ */
+
+/*
+ * Endian-dependent macros.  These are considered internal --- use the
+ * external macros below instead of using these directly.
+ *
+ * Note: IS_1B is true for external toast records but VARSIZE_1B will return 0
+ * for such records. Hence you should usually check for IS_EXTERNAL before
+ * checking for IS_1B.
+ */
+
+#ifdef WORDS_BIGENDIAN
+
+#define VARATT_IS_4B(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x80) == 0x00)
+#define VARATT_IS_4B_U(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0xC0) == 0x00)
+#define VARATT_IS_4B_C(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0xC0) == 0x40)
+#define VARATT_IS_1B(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x80) == 0x80)
+#define VARATT_IS_1B_E(PTR) \
+	((((varattrib_1b *) (PTR))->va_header) == 0x80)
+#define VARATT_NOT_PAD_BYTE(PTR) \
+	(*((uint8 *) (PTR)) != 0)
+
+/* VARSIZE_4B() should only be used on known-aligned data */
+#define VARSIZE_4B(PTR) \
+	(((varattrib_4b *) (PTR))->va_4byte.va_header & 0x3FFFFFFF)
+#define VARSIZE_1B(PTR) \
+	(((varattrib_1b *) (PTR))->va_header & 0x7F)
+#define VARTAG_1B_E(PTR) \
+	(((varattrib_1b_e *) (PTR))->va_tag)
+
+#define SET_VARSIZE_4B(PTR,len) \
+	(((varattrib_4b *) (PTR))->va_4byte.va_header = (len) & 0x3FFFFFFF)
+#define SET_VARSIZE_4B_C(PTR,len) \
+	(((varattrib_4b *) (PTR))->va_4byte.va_header = ((len) & 0x3FFFFFFF) | 0x40000000)
+#define SET_VARSIZE_1B(PTR,len) \
+	(((varattrib_1b *) (PTR))->va_header = (len) | 0x80)
+#define SET_VARTAG_1B_E(PTR,tag) \
+	(((varattrib_1b_e *) (PTR))->va_header = 0x80, \
+	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
+
+#else							/* !WORDS_BIGENDIAN */
+
+#define VARATT_IS_4B(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x00)
+#define VARATT_IS_4B_U(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x00)
+#define VARATT_IS_4B_C(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x02)
+#define VARATT_IS_1B(PTR) \
+	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x01)
+#define VARATT_IS_1B_E(PTR) \
+	((((varattrib_1b *) (PTR))->va_header) == 0x01)
+#define VARATT_NOT_PAD_BYTE(PTR) \
+	(*((uint8 *) (PTR)) != 0)
+
+/* VARSIZE_4B() should only be used on known-aligned data */
+#define VARSIZE_4B(PTR) \
+	((((varattrib_4b *) (PTR))->va_4byte.va_header >> 2) & 0x3FFFFFFF)
+#define VARSIZE_1B(PTR) \
+	((((varattrib_1b *) (PTR))->va_header >> 1) & 0x7F)
+#define VARTAG_1B_E(PTR) \
+	(((varattrib_1b_e *) (PTR))->va_tag)
+
+#define SET_VARSIZE_4B(PTR,len) \
+	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2))
+#define SET_VARSIZE_4B_C(PTR,len) \
+	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2) | 0x02)
+#define SET_VARSIZE_1B(PTR,len) \
+	(((varattrib_1b *) (PTR))->va_header = (((uint8) (len)) << 1) | 0x01)
+#define SET_VARTAG_1B_E(PTR,tag) \
+	(((varattrib_1b_e *) (PTR))->va_header = 0x01, \
+	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
+
+#endif							/* WORDS_BIGENDIAN */
+
+#define VARDATA_4B(PTR)		(((varattrib_4b *) (PTR))->va_4byte.va_data)
+#define VARDATA_4B_C(PTR)	(((varattrib_4b *) (PTR))->va_compressed.va_data)
+#define VARDATA_1B(PTR)		(((varattrib_1b *) (PTR))->va_data)
+#define VARDATA_1B_E(PTR)	(((varattrib_1b_e *) (PTR))->va_data)
+
+/*
+ * Externally visible TOAST macros begin here.
+ */
+
+#define VARHDRSZ_EXTERNAL		offsetof(varattrib_1b_e, va_data)
+#define VARHDRSZ_COMPRESSED		offsetof(varattrib_4b, va_compressed.va_data)
+#define VARHDRSZ_SHORT			offsetof(varattrib_1b, va_data)
+
+#define VARATT_SHORT_MAX		0x7F
+#define VARATT_CAN_MAKE_SHORT(PTR) \
+	(VARATT_IS_4B_U(PTR) && \
+	 (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) <= VARATT_SHORT_MAX)
+#define VARATT_CONVERTED_SHORT_SIZE(PTR) \
+	(VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT)
+
+/*
+ * In consumers oblivious to data alignment, call PG_DETOAST_DATUM_PACKED(),
+ * VARDATA_ANY(), VARSIZE_ANY() and VARSIZE_ANY_EXHDR().  Elsewhere, call
+ * PG_DETOAST_DATUM(), VARDATA() and VARSIZE().  Directly fetching an int16,
+ * int32 or wider field in the struct representing the datum layout requires
+ * aligned data.  memcpy() is alignment-oblivious, as are most operations on
+ * datatypes, such as text, whose layout struct contains only char fields.
+ *
+ * Code assembling a new datum should call VARDATA() and SET_VARSIZE().
+ * (Datums begin life untoasted.)
+ *
+ * Other macros here should usually be used only by tuple assembly/disassembly
+ * code and code that specifically wants to work with still-toasted Datums.
+ */
+#define VARDATA(PTR)						VARDATA_4B(PTR)
+#define VARSIZE(PTR)						VARSIZE_4B(PTR)
+
+#define VARSIZE_SHORT(PTR)					VARSIZE_1B(PTR)
+#define VARDATA_SHORT(PTR)					VARDATA_1B(PTR)
+
+#define VARTAG_EXTERNAL(PTR)				VARTAG_1B_E(PTR)
+#define VARSIZE_EXTERNAL(PTR)				(VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR)))
+#define VARDATA_EXTERNAL(PTR)				VARDATA_1B_E(PTR)
+
+#define VARATT_IS_COMPRESSED(PTR)			VARATT_IS_4B_C(PTR)
+#define VARATT_IS_EXTERNAL(PTR)				VARATT_IS_1B_E(PTR)
+#define VARATT_IS_EXTERNAL_ONDISK(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK)
+#define VARATT_IS_EXTERNAL_INDIRECT(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT)
+#define VARATT_IS_EXTERNAL_EXPANDED_RO(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RO)
+#define VARATT_IS_EXTERNAL_EXPANDED_RW(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RW)
+#define VARATT_IS_EXTERNAL_EXPANDED(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)))
+#define VARATT_IS_EXTERNAL_NON_EXPANDED(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && !VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)))
+#define VARATT_IS_SHORT(PTR)				VARATT_IS_1B(PTR)
+#define VARATT_IS_EXTENDED(PTR)				(!VARATT_IS_4B_U(PTR))
+
+#define SET_VARSIZE(PTR, len)				SET_VARSIZE_4B(PTR, len)
+#define SET_VARSIZE_SHORT(PTR, len)			SET_VARSIZE_1B(PTR, len)
+#define SET_VARSIZE_COMPRESSED(PTR, len)	SET_VARSIZE_4B_C(PTR, len)
+
+#define SET_VARTAG_EXTERNAL(PTR, tag)		SET_VARTAG_1B_E(PTR, tag)
+
+#define VARSIZE_ANY(PTR) \
+	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR) : \
+	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR) : \
+	  VARSIZE_4B(PTR)))
+
+/* Size of a varlena data, excluding header */
+#define VARSIZE_ANY_EXHDR(PTR) \
+	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR)-VARHDRSZ_EXTERNAL : \
+	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR)-VARHDRSZ_SHORT : \
+	  VARSIZE_4B(PTR)-VARHDRSZ))
+
+/* caution: this will not work on an external or compressed-in-line Datum */
+/* caution: this will return a possibly unaligned pointer */
+#define VARDATA_ANY(PTR) \
+	 (VARATT_IS_1B(PTR) ? VARDATA_1B(PTR) : VARDATA_4B(PTR))
+
+/* Decompressed size and compression method of a compressed-in-line Datum */
+#define VARDATA_COMPRESSED_GET_EXTSIZE(PTR) \
+	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK)
+#define VARDATA_COMPRESSED_GET_COMPRESS_METHOD(PTR) \
+	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS)
+
+/* Same for external Datums; but note argument is a struct varatt_external */
+#define VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) \
+	((toast_pointer).va_extinfo & VARLENA_EXTSIZE_MASK)
+#define VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer) \
+	((toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS)
+
+#define VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, len, cm) \
+	do { \
+		Assert((cm) == TOAST_PGLZ_COMPRESSION_ID || \
+			   (cm) == TOAST_LZ4_COMPRESSION_ID); \
+		((toast_pointer).va_extinfo = \
+			(len) | ((uint32) (cm) << VARLENA_EXTSIZE_BITS)); \
+	} while (0)
+
+/*
+ * Testing whether an externally-stored value is compressed now requires
+ * comparing size stored in va_extinfo (the actual length of the external data)
+ * to rawsize (the original uncompressed datum's size).  The latter includes
+ * VARHDRSZ overhead, the former doesn't.  We never use compression unless it
+ * actually saves space, so we expect either equality or less-than.
+ */
+#define VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer) \
+	(VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) < \
+	 (toast_pointer).va_rawsize - VARHDRSZ)
+
+#endif

src/pl/plperl/Util.xs

@@ -16,6 +16,7 @@
 #include "fmgr.h"
 #include "utils/builtins.h"
 #include "utils/bytea.h"       /* for byteain & byteaout */
+#include "varatt.h"
 
 /* perl stuff */
 #define PG_NEED_PERL_XSUB_H

src/test/modules/spgist_name_ops/spgist_name_ops.c

@@ -24,6 +24,7 @@
 #include "access/spgist.h"
 #include "catalog/pg_type.h"
 #include "utils/datum.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

src/test/modules/test_custom_rmgrs/test_custom_rmgrs.c

@@ -22,6 +22,7 @@
 #include "access/xloginsert.h"
 #include "fmgr.h"
 #include "utils/pg_lsn.h"
+#include "varatt.h"
 
 PG_MODULE_MAGIC;
 

src/test/modules/test_shm_mq/test.c

@@ -16,6 +16,7 @@
 #include "fmgr.h"
 #include "miscadmin.h"
 #include "pgstat.h"
+#include "varatt.h"
 
 #include "test_shm_mq.h"