Replace TS_execute's TS_EXEC_CALC_NOT flag with TS_EXEC_SKIP_NOT.

tglsfdc · tglsfdc · commit 79d6d1a277ee · 2020-07-24T15:43:56.000-04:00
It's fairly silly that ignoring NOT subexpressions is TS_execute's default behavior. It's wrong on its face and it encourages errors of omission. Moreover, the only two remaining callers that aren't specifying CALC_NOT are in ts_headline calculations, and it's very arguable that those are bugs: if you've specified "!foo" in your query, why would you want to get a headline that includes "foo"? Hence, rip that out and change the default behavior to be to calculate NOT accurately. As a concession to the slim chance that there is still somebody somewhere who needs the incorrect behavior, provide a new SKIP_NOT flag to explicitly request that. Back-patch into v13, mainly because it seems better to change this at the same time as the previous commit's rejiggering of TS_execute related APIs. Any outside callers affected by this change are probably also affected by that one. Discussion: https://postgr.es/m/CALT9ZEE-aLotzBg-pOp2GFTesGWVYzXA3=mZKzRDa_OKnLF7Mg@mail.gmail.com
diff --git a/src/backend/utils/adt/tsginidx.c b/src/backend/utils/adt/tsginidx.c
@@ -248,7 +248,7 @@ gin_tsquery_consistent(PG_FUNCTION_ARGS)
 
 		res = TS_execute(GETQUERY(query),
 						 &gcv,
-						 TS_EXEC_CALC_NOT | TS_EXEC_PHRASE_NO_POS,
+						 TS_EXEC_PHRASE_NO_POS,
 						 checkcondition_gin);
 	}
 
@@ -286,7 +286,7 @@ gin_tsquery_triconsistent(PG_FUNCTION_ARGS)
 
 		if (TS_execute(GETQUERY(query),
 					   &gcv,
-					   TS_EXEC_CALC_NOT | TS_EXEC_PHRASE_NO_POS,
+					   TS_EXEC_PHRASE_NO_POS,
 					   checkcondition_gin))
 			res = recheck ? GIN_MAYBE : GIN_TRUE;
 	}
diff --git a/src/backend/utils/adt/tsgistidx.c b/src/backend/utils/adt/tsgistidx.c
@@ -348,7 +348,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)
 
 		PG_RETURN_BOOL(TS_execute(GETQUERY(query),
 								  key,
-								  TS_EXEC_PHRASE_NO_POS | TS_EXEC_CALC_NOT,
+								  TS_EXEC_PHRASE_NO_POS,
 								  checkcondition_bit));
 	}
 	else
@@ -359,7 +359,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)
 		chkval.arre = chkval.arrb + ARRNELEM(key);
 		PG_RETURN_BOOL(TS_execute(GETQUERY(query),
 								  (void *) &chkval,
-								  TS_EXEC_PHRASE_NO_POS | TS_EXEC_CALC_NOT,
+								  TS_EXEC_PHRASE_NO_POS,
 								  checkcondition_arr));
 	}
 }
diff --git a/src/backend/utils/adt/tsrank.c b/src/backend/utils/adt/tsrank.c
@@ -697,7 +697,7 @@ Cover(DocRepresentation *doc, int len, QueryRepresentation *qr, CoverExt *ext)
 		fillQueryRepresentationData(qr, ptr);
 
 		if (TS_execute(GETQUERY(qr->query), (void *) qr,
-					   TS_EXEC_CALC_NOT, checkcondition_QueryOperand))
+					   TS_EXEC_EMPTY, checkcondition_QueryOperand))
 		{
 			if (WEP_GETPOS(ptr->pos) < ext->p)
 			{
diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c
@@ -1627,9 +1627,9 @@ TS_phrase_execute(QueryItem *curitem, void *arg, uint32 flags,
 			 * We need not touch data->width, since a NOT operation does not
 			 * change the match width.
 			 */
-			if (!(flags & TS_EXEC_CALC_NOT))
+			if (flags & TS_EXEC_SKIP_NOT)
 			{
-				/* without CALC_NOT, report NOT as "match everywhere" */
+				/* with SKIP_NOT, report NOT as "match everywhere" */
 				Assert(data->npos == 0 && !data->negate);
 				data->negate = true;
 				return TS_YES;
@@ -1875,7 +1875,7 @@ TS_execute_recurse(QueryItem *curitem, void *arg, uint32 flags,
 	switch (curitem->qoperator.oper)
 	{
 		case OP_NOT:
-			if (!(flags & TS_EXEC_CALC_NOT))
+			if (flags & TS_EXEC_SKIP_NOT)
 				return TS_YES;
 			switch (TS_execute_recurse(curitem + 1, arg, flags, chkcond))
 			{
@@ -2038,7 +2038,7 @@ ts_match_vq(PG_FUNCTION_ARGS)
 	chkval.operand = GETOPERAND(query);
 	result = TS_execute(GETQUERY(query),
 						&chkval,
-						TS_EXEC_CALC_NOT,
+						TS_EXEC_EMPTY,
 						checkcondition_str);
 
 	PG_FREE_IF_COPY(val, 0);
diff --git a/src/include/tsearch/ts_utils.h b/src/include/tsearch/ts_utils.h
@@ -183,10 +183,12 @@ typedef TSTernaryValue (*TSExecuteCallback) (void *arg, QueryOperand *val,
  */
 #define TS_EXEC_EMPTY			(0x00)
 /*
- * If TS_EXEC_CALC_NOT is not set, then NOT expressions are automatically
- * evaluated to be true.  Useful in cases where NOT isn't important (ranking).
+ * If TS_EXEC_SKIP_NOT is set, then NOT sub-expressions are automatically
+ * evaluated to be true.  This was formerly the default behavior.  It's now
+ * deprecated because it tends to give silly answers, but some applications
+ * might still have a use for it.
  */
-#define TS_EXEC_CALC_NOT		(0x01)
+#define TS_EXEC_SKIP_NOT		(0x01)
 /*
  * If TS_EXEC_PHRASE_NO_POS is set, allow OP_PHRASE to be executed lossily
  * in the absence of position information: a true result indicates that the

Original file line number	Diff line number	Diff line change
`@@ -248,7 +248,7 @@ gin_tsquery_consistent(PG_FUNCTION_ARGS)`
`248`	`248`
`249`	`249`	`res = TS_execute(GETQUERY(query),`
`250`	`250`	`&gcv,`
`251`		`- TS_EXEC_CALC_NOT \| TS_EXEC_PHRASE_NO_POS,`
	`251`	`+ TS_EXEC_PHRASE_NO_POS,`
`252`	`252`	`checkcondition_gin);`
`253`	`253`	`}`
`254`	`254`
`@@ -286,7 +286,7 @@ gin_tsquery_triconsistent(PG_FUNCTION_ARGS)`
`286`	`286`
`287`	`287`	`if (TS_execute(GETQUERY(query),`
`288`	`288`	`&gcv,`
`289`		`- TS_EXEC_CALC_NOT \| TS_EXEC_PHRASE_NO_POS,`
	`289`	`+ TS_EXEC_PHRASE_NO_POS,`
`290`	`290`	`checkcondition_gin))`
`291`	`291`	`res = recheck ? GIN_MAYBE : GIN_TRUE;`
`292`	`292`	`}`
Original file line number	Diff line number	Diff line change
`@@ -348,7 +348,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)`
`348`	`348`
`349`	`349`	`PG_RETURN_BOOL(TS_execute(GETQUERY(query),`
`350`	`350`	`key,`
`351`		`- TS_EXEC_PHRASE_NO_POS \| TS_EXEC_CALC_NOT,`
	`351`	`+ TS_EXEC_PHRASE_NO_POS,`
`352`	`352`	`checkcondition_bit));`
`353`	`353`	`}`
`354`	`354`	`else`
`@@ -359,7 +359,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)`
`359`	`359`	`chkval.arre = chkval.arrb + ARRNELEM(key);`
`360`	`360`	`PG_RETURN_BOOL(TS_execute(GETQUERY(query),`
`361`	`361`	`(void *) &chkval,`
`362`		`- TS_EXEC_PHRASE_NO_POS \| TS_EXEC_CALC_NOT,`
	`362`	`+ TS_EXEC_PHRASE_NO_POS,`
`363`	`363`	`checkcondition_arr));`
`364`	`364`	`}`
`365`	`365`	`}`
Original file line number	Diff line number	Diff line change
`@@ -697,7 +697,7 @@ Cover(DocRepresentation doc, int len, QueryRepresentation qr, CoverExt *ext)`
`697`	`697`	`fillQueryRepresentationData(qr, ptr);`
`698`	`698`
`699`	`699`	`if (TS_execute(GETQUERY(qr->query), (void *) qr,`
`700`		`- TS_EXEC_CALC_NOT, checkcondition_QueryOperand))`
	`700`	`+ TS_EXEC_EMPTY, checkcondition_QueryOperand))`
`701`	`701`	`{`
`702`	`702`	`if (WEP_GETPOS(ptr->pos) < ext->p)`
`703`	`703`	`{`