Use wrappers of PG_DETOAST_DATUM_PACKED() more.

This makes almost all core code follow the policy introduced in the
previous commit.  Specific decisions:

- Text search support functions with char* and length arguments, such as
  prsstart and lexize, may receive unaligned strings.  I doubt
  maintainers of non-core text search code will notice.

- Use plain VARDATA() on values detoasted or synthesized earlier in the
  same function.  Use VARDATA_ANY() on varlenas sourced outside the
  function, even if they happen to always have four-byte headers.  As an
  exception, retain the universal practice of using VARDATA() on return
  values of SendFunctionCall().

- Retain PG_GETARG_BYTEA_P() in pageinspect.  (Page images are too large
  for a one-byte header, so this misses no optimization.)  Sites that do
  not call get_page_from_raw() typically need the four-byte alignment.

- For now, do not change btree_gist.  Its use of four-byte headers in
  memory is partly entangled with storage of 4-byte headers inside
  GBT_VARKEY, on disk.

- For now, do not change gtrgm_consistent() or gtrgm_distance().  They
  incorporate the varlena header into a cache, and there are multiple
  credible implementation strategies to consider.

Author: nmisch

contrib/adminpack/adminpack.c

@@ -124,8 +124,8 @@ pg_file_write(PG_FUNCTION_ARGS)
 
 	requireSuperuser();
 
-	filename = convert_and_check_filename(PG_GETARG_TEXT_P(0), false);
-	data = PG_GETARG_TEXT_P(1);
+	filename = convert_and_check_filename(PG_GETARG_TEXT_PP(0), false);
+	data = PG_GETARG_TEXT_PP(1);
 
 	if (!PG_GETARG_BOOL(2))
 	{
@@ -147,8 +147,8 @@ pg_file_write(PG_FUNCTION_ARGS)
 				 errmsg("could not open file \"%s\" for writing: %m",
 						filename)));
 
-	count = fwrite(VARDATA(data), 1, VARSIZE(data) - VARHDRSZ, f);
-	if (count != VARSIZE(data) - VARHDRSZ || FreeFile(f))
+	count = fwrite(VARDATA_ANY(data), 1, VARSIZE_ANY_EXHDR(data), f);
+	if (count != VARSIZE_ANY_EXHDR(data) || FreeFile(f))
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write file \"%s\": %m", filename)));
@@ -170,12 +170,12 @@ pg_file_rename(PG_FUNCTION_ARGS)
 	if (PG_ARGISNULL(0) || PG_ARGISNULL(1))
 		PG_RETURN_NULL();
 
-	fn1 = convert_and_check_filename(PG_GETARG_TEXT_P(0), false);
-	fn2 = convert_and_check_filename(PG_GETARG_TEXT_P(1), false);
+	fn1 = convert_and_check_filename(PG_GETARG_TEXT_PP(0), false);
+	fn2 = convert_and_check_filename(PG_GETARG_TEXT_PP(1), false);
 	if (PG_ARGISNULL(2))
 		fn3 = 0;
 	else
-		fn3 = convert_and_check_filename(PG_GETARG_TEXT_P(2), false);
+		fn3 = convert_and_check_filename(PG_GETARG_TEXT_PP(2), false);
 
 	if (access(fn1, W_OK) < 0)
 	{
@@ -254,7 +254,7 @@ pg_file_unlink(PG_FUNCTION_ARGS)
 
 	requireSuperuser();
 
-	filename = convert_and_check_filename(PG_GETARG_TEXT_P(0), false);
+	filename = convert_and_check_filename(PG_GETARG_TEXT_PP(0), false);
 
 	if (access(filename, W_OK) < 0)
 	{

contrib/dblink/dblink.c

@@ -1502,7 +1502,7 @@ dblink_get_pkey(PG_FUNCTION_ARGS)
 		oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
 
 		/* open target relation */
-		rel = get_rel_from_relname(PG_GETARG_TEXT_P(0), AccessShareLock, ACL_SELECT);
+		rel = get_rel_from_relname(PG_GETARG_TEXT_PP(0), AccessShareLock, ACL_SELECT);
 
 		/* get the array of attnums */
 		results = get_pkey_attnames(rel, &numatts);
@@ -1603,7 +1603,7 @@ PG_FUNCTION_INFO_V1(dblink_build_sql_insert);
 Datum
 dblink_build_sql_insert(PG_FUNCTION_ARGS)
 {
-	text	   *relname_text = PG_GETARG_TEXT_P(0);
+	text	   *relname_text = PG_GETARG_TEXT_PP(0);
 	int2vector *pkattnums_arg = (int2vector *) PG_GETARG_POINTER(1);
 	int32		pknumatts_arg = PG_GETARG_INT32(2);
 	ArrayType  *src_pkattvals_arry = PG_GETARG_ARRAYTYPE_P(3);
@@ -1694,7 +1694,7 @@ PG_FUNCTION_INFO_V1(dblink_build_sql_delete);
 Datum
 dblink_build_sql_delete(PG_FUNCTION_ARGS)
 {
-	text	   *relname_text = PG_GETARG_TEXT_P(0);
+	text	   *relname_text = PG_GETARG_TEXT_PP(0);
 	int2vector *pkattnums_arg = (int2vector *) PG_GETARG_POINTER(1);
 	int32		pknumatts_arg = PG_GETARG_INT32(2);
 	ArrayType  *tgt_pkattvals_arry = PG_GETARG_ARRAYTYPE_P(3);
@@ -1771,7 +1771,7 @@ PG_FUNCTION_INFO_V1(dblink_build_sql_update);
 Datum
 dblink_build_sql_update(PG_FUNCTION_ARGS)
 {
-	text	   *relname_text = PG_GETARG_TEXT_P(0);
+	text	   *relname_text = PG_GETARG_TEXT_PP(0);
 	int2vector *pkattnums_arg = (int2vector *) PG_GETARG_POINTER(1);
 	int32		pknumatts_arg = PG_GETARG_INT32(2);
 	ArrayType  *src_pkattvals_arry = PG_GETARG_ARRAYTYPE_P(3);
@@ -2338,7 +2338,7 @@ quote_ident_cstr(char *rawstr)
 	char	   *result;
 
 	rawstr_text = cstring_to_text(rawstr);
-	result_text = DatumGetTextP(DirectFunctionCall1(quote_ident,
+	result_text = DatumGetTextPP(DirectFunctionCall1(quote_ident,
 											  PointerGetDatum(rawstr_text)));
 	result = text_to_cstring(result_text);
 

contrib/fuzzystrmatch/dmetaphone.c

@@ -139,7 +139,7 @@ dmetaphone(PG_FUNCTION_ARGS)
 	if (PG_ARGISNULL(0))
 		PG_RETURN_NULL();
 #endif
-	arg = PG_GETARG_TEXT_P(0);
+	arg = PG_GETARG_TEXT_PP(0);
 	aptr = text_to_cstring(arg);
 
 	DoubleMetaphone(aptr, codes);
@@ -168,7 +168,7 @@ dmetaphone_alt(PG_FUNCTION_ARGS)
 	if (PG_ARGISNULL(0))
 		PG_RETURN_NULL();
 #endif
-	arg = PG_GETARG_TEXT_P(0);
+	arg = PG_GETARG_TEXT_PP(0);
 	aptr = text_to_cstring(arg);
 
 	DoubleMetaphone(aptr, codes);

contrib/fuzzystrmatch/fuzzystrmatch.c

@@ -736,7 +736,7 @@ soundex(PG_FUNCTION_ARGS)
 	char		outstr[SOUNDEX_LEN + 1];
 	char	   *arg;
 
-	arg = text_to_cstring(PG_GETARG_TEXT_P(0));
+	arg = text_to_cstring(PG_GETARG_TEXT_PP(0));
 
 	_soundex(arg, outstr);
 
@@ -802,8 +802,8 @@ difference(PG_FUNCTION_ARGS)
 	int			i,
 				result;
 
-	_soundex(text_to_cstring(PG_GETARG_TEXT_P(0)), sndx1);
-	_soundex(text_to_cstring(PG_GETARG_TEXT_P(1)), sndx2);
+	_soundex(text_to_cstring(PG_GETARG_TEXT_PP(0)), sndx1);
+	_soundex(text_to_cstring(PG_GETARG_TEXT_PP(1)), sndx2);
 
 	result = 0;
 	for (i = 0; i < SOUNDEX_LEN; i++)

contrib/intarray/_int_op.c

@@ -200,9 +200,9 @@ Datum
 sort(PG_FUNCTION_ARGS)
 {
 	ArrayType  *a = PG_GETARG_ARRAYTYPE_P_COPY(0);
-	text	   *dirstr = (fcinfo->nargs == 2) ? PG_GETARG_TEXT_P(1) : NULL;
-	int32		dc = (dirstr) ? VARSIZE(dirstr) - VARHDRSZ : 0;
-	char	   *d = (dirstr) ? VARDATA(dirstr) : NULL;
+	text	   *dirstr = (fcinfo->nargs == 2) ? PG_GETARG_TEXT_PP(1) : NULL;
+	int32		dc = (dirstr) ? VARSIZE_ANY_EXHDR(dirstr) : 0;
+	char	   *d = (dirstr) ? VARDATA_ANY(dirstr) : NULL;
 	int			dir = -1;
 
 	CHECKARRVALID(a);

contrib/pageinspect/btreefuncs.c

@@ -159,7 +159,7 @@ GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat)
 Datum
 bt_page_stats(PG_FUNCTION_ARGS)
 {
-	text	   *relname = PG_GETARG_TEXT_P(0);
+	text	   *relname = PG_GETARG_TEXT_PP(0);
 	uint32		blkno = PG_GETARG_UINT32(1);
 	Buffer		buffer;
 	Relation	rel;
@@ -256,7 +256,7 @@ struct user_args
 Datum
 bt_page_items(PG_FUNCTION_ARGS)
 {
-	text	   *relname = PG_GETARG_TEXT_P(0);
+	text	   *relname = PG_GETARG_TEXT_PP(0);
 	uint32		blkno = PG_GETARG_UINT32(1);
 	Datum		result;
 	char	   *values[6];
@@ -408,7 +408,7 @@ bt_page_items(PG_FUNCTION_ARGS)
 Datum
 bt_metap(PG_FUNCTION_ARGS)
 {
-	text	   *relname = PG_GETARG_TEXT_P(0);
+	text	   *relname = PG_GETARG_TEXT_PP(0);
 	Datum		result;
 	Relation	rel;
 	RangeVar   *relrv;

contrib/pageinspect/rawpage.c

@@ -45,7 +45,7 @@ PG_FUNCTION_INFO_V1(get_raw_page);
 Datum
 get_raw_page(PG_FUNCTION_ARGS)
 {
-	text	   *relname = PG_GETARG_TEXT_P(0);
+	text	   *relname = PG_GETARG_TEXT_PP(0);
 	uint32		blkno = PG_GETARG_UINT32(1);
 	bytea	   *raw_page;
 
@@ -74,8 +74,8 @@ PG_FUNCTION_INFO_V1(get_raw_page_fork);
 Datum
 get_raw_page_fork(PG_FUNCTION_ARGS)
 {
-	text	   *relname = PG_GETARG_TEXT_P(0);
-	text	   *forkname = PG_GETARG_TEXT_P(1);
+	text	   *relname = PG_GETARG_TEXT_PP(0);
+	text	   *forkname = PG_GETARG_TEXT_PP(1);
 	uint32		blkno = PG_GETARG_UINT32(2);
 	bytea	   *raw_page;
 	ForkNumber	forknum;
@@ -184,7 +184,7 @@ get_page_from_raw(bytea *raw_page)
 	Page		page;
 	int			raw_page_size;
 
-	raw_page_size = VARSIZE(raw_page) - VARHDRSZ;
+	raw_page_size = VARSIZE_ANY_EXHDR(raw_page);
 
 	if (raw_page_size != BLCKSZ)
 		ereport(ERROR,
@@ -195,7 +195,7 @@ get_page_from_raw(bytea *raw_page)
 
 	page = palloc(raw_page_size);
 
-	memcpy(page, VARDATA(raw_page), raw_page_size);
+	memcpy(page, VARDATA_ANY(raw_page), raw_page_size);
 
 	return page;
 }

contrib/pg_prewarm/pg_prewarm.c

@@ -79,7 +79,7 @@ pg_prewarm(PG_FUNCTION_ARGS)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 				 (errmsg("prewarm type cannot be null"))));
-	type = PG_GETARG_TEXT_P(1);
+	type = PG_GETARG_TEXT_PP(1);
 	ttype = text_to_cstring(type);
 	if (strcmp(ttype, "prefetch") == 0)
 		ptype = PREWARM_PREFETCH;
@@ -99,7 +99,7 @@ pg_prewarm(PG_FUNCTION_ARGS)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 				 (errmsg("relation fork cannot be null"))));
-	forkName = PG_GETARG_TEXT_P(2);
+	forkName = PG_GETARG_TEXT_PP(2);
 	forkString = text_to_cstring(forkName);
 	forkNumber = forkname_to_number(forkString);
 

contrib/pg_trgm/trgm_gin.c

@@ -35,15 +35,15 @@ gin_extract_trgm(PG_FUNCTION_ARGS)
 Datum
 gin_extract_value_trgm(PG_FUNCTION_ARGS)
 {
-	text	   *val = (text *) PG_GETARG_TEXT_P(0);
+	text	   *val = (text *) PG_GETARG_TEXT_PP(0);
 	int32	   *nentries = (int32 *) PG_GETARG_POINTER(1);
 	Datum	   *entries = NULL;
 	TRGM	   *trg;
 	int32		trglen;
 
 	*nentries = 0;
 
-	trg = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+	trg = generate_trgm(VARDATA_ANY(val), VARSIZE_ANY_EXHDR(val));
 	trglen = ARRNELEM(trg);
 
 	if (trglen > 0)
@@ -70,7 +70,7 @@ gin_extract_value_trgm(PG_FUNCTION_ARGS)
 Datum
 gin_extract_query_trgm(PG_FUNCTION_ARGS)
 {
-	text	   *val = (text *) PG_GETARG_TEXT_P(0);
+	text	   *val = (text *) PG_GETARG_TEXT_PP(0);
 	int32	   *nentries = (int32 *) PG_GETARG_POINTER(1);
 	StrategyNumber strategy = PG_GETARG_UINT16(2);
 
@@ -90,7 +90,7 @@ gin_extract_query_trgm(PG_FUNCTION_ARGS)
 	{
 		case SimilarityStrategyNumber:
 		case WordSimilarityStrategyNumber:
-			trg = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+			trg = generate_trgm(VARDATA_ANY(val), VARSIZE_ANY_EXHDR(val));
 			break;
 		case ILikeStrategyNumber:
 #ifndef IGNORECASE
@@ -103,7 +103,8 @@ gin_extract_query_trgm(PG_FUNCTION_ARGS)
 			 * For wildcard search we extract all the trigrams that every
 			 * potentially-matching string must include.
 			 */
-			trg = generate_wildcard_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+			trg = generate_wildcard_trgm(VARDATA_ANY(val),
+										 VARSIZE_ANY_EXHDR(val));
 			break;
 		case RegExpICaseStrategyNumber:
 #ifndef IGNORECASE
@@ -170,7 +171,7 @@ gin_trgm_consistent(PG_FUNCTION_ARGS)
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	StrategyNumber strategy = PG_GETARG_UINT16(1);
 
-	/* text    *query = PG_GETARG_TEXT_P(2); */
+	/* text    *query = PG_GETARG_TEXT_PP(2); */
 	int32		nkeys = PG_GETARG_INT32(3);
 	Pointer    *extra_data = (Pointer *) PG_GETARG_POINTER(4);
 	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
@@ -268,7 +269,7 @@ gin_trgm_triconsistent(PG_FUNCTION_ARGS)
 	GinTernaryValue *check = (GinTernaryValue *) PG_GETARG_POINTER(0);
 	StrategyNumber strategy = PG_GETARG_UINT16(1);
 
-	/* text    *query = PG_GETARG_TEXT_P(2); */
+	/* text    *query = PG_GETARG_TEXT_PP(2); */
 	int32		nkeys = PG_GETARG_INT32(3);
 	Pointer    *extra_data = (Pointer *) PG_GETARG_POINTER(4);
 	GinTernaryValue res = GIN_MAYBE;

contrib/pg_trgm/trgm_gist.c

@@ -100,9 +100,9 @@ gtrgm_compress(PG_FUNCTION_ARGS)
 	if (entry->leafkey)
 	{							/* trgm */
 		TRGM	   *res;
-		text	   *val = DatumGetTextP(entry->key);
+		text	   *val = DatumGetTextPP(entry->key);
 
-		res = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+		res = generate_trgm(VARDATA_ANY(val), VARSIZE_ANY_EXHDR(val));
 		retval = (GISTENTRY *) palloc(sizeof(GISTENTRY));
 		gistentryinit(*retval, PointerGetDatum(res),
 					  entry->rel, entry->page,
@@ -142,7 +142,7 @@ gtrgm_decompress(PG_FUNCTION_ARGS)
 	GISTENTRY  *retval;
 	text	   *key;
 
-	key = DatumGetTextP(entry->key);
+	key = DatumGetTextPP(entry->key);
 
 	if (key != (text *) DatumGetPointer(entry->key))
 	{
@@ -200,11 +200,12 @@ gtrgm_consistent(PG_FUNCTION_ARGS)
 	 * depends on strategy.
 	 *
 	 * The cached structure is a single palloc chunk containing the
-	 * gtrgm_consistent_cache header, then the input query (starting at a
-	 * MAXALIGN boundary), then the TRGM value (also starting at a MAXALIGN
-	 * boundary).  However we don't try to include the regex graph (if any) in
-	 * that struct.  (XXX currently, this approach can leak regex graphs
-	 * across index rescans.  Not clear if that's worth fixing.)
+	 * gtrgm_consistent_cache header, then the input query (4-byte length
+	 * word, uncompressed, starting at a MAXALIGN boundary), then the TRGM
+	 * value (also starting at a MAXALIGN boundary).  However we don't try to
+	 * include the regex graph (if any) in that struct.  (XXX currently, this
+	 * approach can leak regex graphs across index rescans.  Not clear if
+	 * that's worth fixing.)
 	 */
 	cache = (gtrgm_consistent_cache *) fcinfo->flinfo->fn_extra;
 	if (cache == NULL ||

contrib/pg_trgm/trgm_op.c

@@ -878,14 +878,14 @@ trgm2int(trgm *ptr)
 Datum
 show_trgm(PG_FUNCTION_ARGS)
 {
-	text	   *in = PG_GETARG_TEXT_P(0);
+	text	   *in = PG_GETARG_TEXT_PP(0);
 	TRGM	   *trg;
 	Datum	   *d;
 	ArrayType  *a;
 	trgm	   *ptr;
 	int			i;
 
-	trg = generate_trgm(VARDATA(in), VARSIZE(in) - VARHDRSZ);
+	trg = generate_trgm(VARDATA_ANY(in), VARSIZE_ANY_EXHDR(in));
 	d = (Datum *) palloc(sizeof(Datum) * (1 + ARRNELEM(trg)));
 
 	for (i = 0, ptr = GETARR(trg); i < ARRNELEM(trg); i++, ptr++)
@@ -1053,14 +1053,14 @@ trgm_presence_map(TRGM *query, TRGM *key)
 Datum
 similarity(PG_FUNCTION_ARGS)
 {
-	text	   *in1 = PG_GETARG_TEXT_P(0);
-	text	   *in2 = PG_GETARG_TEXT_P(1);
+	text	   *in1 = PG_GETARG_TEXT_PP(0);
+	text	   *in2 = PG_GETARG_TEXT_PP(1);
 	TRGM	   *trg1,
 			   *trg2;
 	float4		res;
 
-	trg1 = generate_trgm(VARDATA(in1), VARSIZE(in1) - VARHDRSZ);
-	trg2 = generate_trgm(VARDATA(in2), VARSIZE(in2) - VARHDRSZ);
+	trg1 = generate_trgm(VARDATA_ANY(in1), VARSIZE_ANY_EXHDR(in1));
+	trg2 = generate_trgm(VARDATA_ANY(in2), VARSIZE_ANY_EXHDR(in2));
 
 	res = cnt_sml(trg1, trg2, false);