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.

3 files changed, 23 insertions, 21 deletions

diff --git a/contrib/pg_trgm/trgm_gin.c b/contrib/pg_trgm/trgm_gin.c
index ead33ef5447..e4b3daea446 100644
--- a/contrib/pg_trgm/trgm_gin.c
+++ b/contrib/pg_trgm/trgm_gin.c
@@ -35,7 +35,7 @@ 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;
@@ -43,7 +43,7 @@ gin_extract_value_trgm(PG_FUNCTION_ARGS)
 
 	*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;
diff --git a/contrib/pg_trgm/trgm_gist.c b/contrib/pg_trgm/trgm_gist.c
index f52867df324..ed02af875ca 100644
--- a/contrib/pg_trgm/trgm_gist.c
+++ b/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 ||
diff --git a/contrib/pg_trgm/trgm_op.c b/contrib/pg_trgm/trgm_op.c
index 368e7c8941d..e9a713113ed 100644
--- a/contrib/pg_trgm/trgm_op.c
+++ b/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);