Fix parsing of ignored operators in websearch_to_tsquery().

tglsfdc · tglsfdc · commit 56a8296212b6 · 2024-06-13T20:35:02.000-04:00
The manual says clearly that punctuation in the input of websearch_to_tsquery() is ignored, except for the special cases of dashes and quotes. However, this failed for cases like "(foo bar) or something", or in general an ISOPERATOR character in front of the "or". We'd switch back to WAITOPERAND state, then ignore the operator character while remaining in that state, and then reach the "or" in WAITOPERAND state which (intentionally) makes us treat it as data. The fix is simple enough: if we see an ISOPERATOR character while in WAITOPERATOR state, we have to skip it while staying in that state. (We don't need to worry about other punctuation characters: those will be consumed as though they were words, but then rejected by lexizing.) In v14 and up (since commit eb08605) we can simplify the code a bit more too, because there is no longer a reason for the WAITOPERAND state to distinguish between quoted and unquoted operands. Per bug #18479 from Manos Emmanouilidis. Back-patch to all supported branches. Discussion: https://postgr.es/m/18479-d9b46e2fc242c33e@postgresql.org
diff --git a/src/backend/utils/adt/tsquery.c b/src/backend/utils/adt/tsquery.c
@@ -439,7 +439,7 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,
 				}
 				else if (ISOPERATOR(state->buf))
 				{
-					/* or else gettoken_tsvector() will raise an error */
+					/* ignore, else gettoken_tsvector() will raise an error */
 					state->buf++;
 					state->state = WAITOPERAND;
 					continue;
@@ -476,31 +476,27 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,
 				break;
 
 			case WAITOPERATOR:
-				if (t_iseq(state->buf, '"'))
+				if (*state->buf == '\0')
 				{
-					/*
-					 * put implicit AND after an operand and handle this quote
-					 * in WAITOPERAND
-					 */
-					state->state = WAITOPERAND;
-					*operator = OP_AND;
-					return PT_OPR;
+					return PT_END;
 				}
 				else if (parse_or_operator(state))
 				{
 					state->state = WAITOPERAND;
 					*operator = OP_OR;
 					return PT_OPR;
 				}
-				else if (*state->buf == '\0')
+				else if (ISOPERATOR(state->buf))
 				{
-					return PT_END;
+					/* ignore other operators in this state too */
+					state->buf++;
+					continue;
 				}
 				else if (!t_isspace(state->buf))
 				{
-					/* put implicit AND after an operand */
-					*operator = OP_AND;
+					/* insert implicit AND between operands */
 					state->state = WAITOPERAND;
+					*operator = OP_AND;
 					return PT_OPR;
 				}
 				break;
diff --git a/src/test/regress/expected/tsearch.out b/src/test/regress/expected/tsearch.out
@@ -2676,12 +2676,19 @@ select websearch_to_tsquery('simple', 'abc <-> def');
  'abc' & 'def'
 (1 row)
 
+-- parens are ignored, too
 select websearch_to_tsquery('simple', 'abc (pg or class)');
   websearch_to_tsquery  
 ------------------------
  'abc' & 'pg' | 'class'
 (1 row)
 
+select websearch_to_tsquery('simple', '(foo bar) or (ding dong)');
+      websearch_to_tsquery       
+---------------------------------
+ 'foo' & 'bar' | 'ding' & 'dong'
+(1 row)
+
 -- NOT is ignored in quotes
 select websearch_to_tsquery('english', 'My brand new smartphone');
      websearch_to_tsquery      
diff --git a/src/test/regress/sql/tsearch.sql b/src/test/regress/sql/tsearch.sql
@@ -818,7 +818,10 @@ select websearch_to_tsquery('simple', ':');
 select websearch_to_tsquery('simple', 'abc & def');
 select websearch_to_tsquery('simple', 'abc | def');
 select websearch_to_tsquery('simple', 'abc <-> def');
+
+-- parens are ignored, too
 select websearch_to_tsquery('simple', 'abc (pg or class)');
+select websearch_to_tsquery('simple', '(foo bar) or (ding dong)');
 
 -- NOT is ignored in quotes
 select websearch_to_tsquery('english', 'My brand new smartphone');

Original file line number	Diff line number	Diff line change
`@@ -439,7 +439,7 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,`
`439`	`439`	`}`
`440`	`440`	`else if (ISOPERATOR(state->buf))`
`441`	`441`	`{`
`442`		`- /* or else gettoken_tsvector() will raise an error */`
	`442`	`+ /* ignore, else gettoken_tsvector() will raise an error */`
`443`	`443`	`state->buf++;`
`444`	`444`	`state->state = WAITOPERAND;`
`445`	`445`	`continue;`
`@@ -476,31 +476,27 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,`
`476`	`476`	`break;`
`477`	`477`
`478`	`478`	`case WAITOPERATOR:`
`479`		`- if (t_iseq(state->buf, '"'))`
	`479`	`+ if (*state->buf == '\0')`
`480`	`480`	`{`
`481`		`- /*`
`482`		`- * put implicit AND after an operand and handle this quote`
`483`		`- * in WAITOPERAND`
`484`		`- */`
`485`		`- state->state = WAITOPERAND;`
`486`		`- *operator = OP_AND;`
`487`		`- return PT_OPR;`
	`481`	`+ return PT_END;`
`488`	`482`	`}`
`489`	`483`	`else if (parse_or_operator(state))`
`490`	`484`	`{`
`491`	`485`	`state->state = WAITOPERAND;`
`492`	`486`	`*operator = OP_OR;`
`493`	`487`	`return PT_OPR;`
`494`	`488`	`}`
`495`		`- else if (*state->buf == '\0')`
	`489`	`+ else if (ISOPERATOR(state->buf))`
`496`	`490`	`{`
`497`		`- return PT_END;`
	`491`	`+ /* ignore other operators in this state too */`
	`492`	`+ state->buf++;`
	`493`	`+ continue;`
`498`	`494`	`}`
`499`	`495`	`else if (!t_isspace(state->buf))`
`500`	`496`	`{`
`501`		`- /* put implicit AND after an operand */`
`502`		`- *operator = OP_AND;`
	`497`	`+ /* insert implicit AND between operands */`
`503`	`498`	`state->state = WAITOPERAND;`
	`499`	`+ *operator = OP_AND;`
`504`	`500`	`return PT_OPR;`
`505`	`501`	`}`
`506`	`502`	`break;`