Fix ts_headline() edge cases for empty query and empty search text.

tglsfdc · tglsfdc · commit f976a77787eb · 2023-04-06T15:52:37.000-04:00
tsquery's GETQUERY() macro is only safe to apply to a tsquery that is known non-empty; otherwise it gives a pointer to garbage. Before commit 5a617d7, ts_headline() avoided this pitfall, but only in a very indirect, nonobvious way. (hlCover could not reach its TS_execute call, because if the query contains no lexemes then hlFirstIndex would surely return -1.) After that commit, it fell into the trap, resulting in weird errors such as "unrecognized operator" and/or valgrind complaints. In HEAD, fix this by not calling TS_execute_locations() at all for an empty query. In the back branches, add a defensive check to hlCover() --- that's not fixing any live bug, but I judge the code a bit too fragile as-is. Also, both mark_hl_fragments() and mark_hl_words() were careless about the possibility of empty search text: in the cases where no match has been found, they'd end up telling mark_fragment() to mark from word indexes 0 to 0 inclusive, even when there is no word 0. This is harmless since we over-allocated the prs->words array, but it does annoy valgrind. Fix so that the end index is -1 and thus mark_fragment() will do nothing in such cases. Bottom line is that this fixes a live bug in HEAD, but in the back branches it's only getting rid of a valgrind nitpick. Back-patch anyway. Per report from Alexander Lakhin. Discussion: https://postgr.es/m/c27f642d-020b-01ff-ae61-086af287c4fd@gmail.com
diff --git a/src/backend/tsearch/wparser_def.c b/src/backend/tsearch/wparser_def.c
@@ -2038,6 +2038,9 @@ hlCover(HeadlineParsedText *prs, TSQuery query, int max_cover,
 				nextpmax;
 	hlCheck		ch;
 
+	if (query->size <= 0)
+		return false;			/* empty query matches nothing */
+
 	/*
 	 * We look for the earliest, shortest substring of prs->words that
 	 * satisfies the query.  Both the pmin and pmax indices must be words
@@ -2342,7 +2345,8 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, bool highlightall,
 	/* show the first min_words words if we have not marked anything */
 	if (num_f <= 0)
 	{
-		startpos = endpos = curlen = 0;
+		startpos = curlen = 0;
+		endpos = -1;
 		for (i = 0; i < prs->curwords && curlen < min_words; i++)
 		{
 			if (!NONWORDTOKEN(prs->words[i].type))
@@ -2497,7 +2501,7 @@ mark_hl_words(HeadlineParsedText *prs, TSQuery query, bool highlightall,
 		if (bestlen < 0)
 		{
 			curlen = 0;
-			pose = 0;
+			pose = -1;
 			for (i = 0; i < prs->curwords && curlen < min_words; i++)
 			{
 				if (!NONWORDTOKEN(prs->words[i].type))
diff --git a/src/test/regress/expected/tsearch.out b/src/test/regress/expected/tsearch.out
@@ -2000,6 +2000,27 @@ to_tsquery('english','Lorem') && phraseto_tsquery('english','ullamcorper urna'),
  <b>Lorem</b> ipsum <b>urna</b>.  Nullam nullam <b>ullamcorper</b> <b>urna</b>
 (1 row)
 
+-- Edge cases with empty query
+SELECT ts_headline('english',
+'', ''::tsquery);
+NOTICE:  text-search query doesn't contain lexemes: ""
+LINE 2: '', ''::tsquery);
+            ^
+ ts_headline 
+-------------
+ 
+(1 row)
+
+SELECT ts_headline('english',
+'foo bar', ''::tsquery);
+NOTICE:  text-search query doesn't contain lexemes: ""
+LINE 2: 'foo bar', ''::tsquery);
+                   ^
+ ts_headline 
+-------------
+ foo bar
+(1 row)
+
 --Rewrite sub system
 CREATE TABLE test_tsquery (txtkeyword TEXT, txtsample TEXT);
 \set ECHO none
diff --git a/src/test/regress/sql/tsearch.sql b/src/test/regress/sql/tsearch.sql
@@ -563,6 +563,12 @@ SELECT ts_headline('english',
 to_tsquery('english','Lorem') && phraseto_tsquery('english','ullamcorper urna'),
 'MaxFragments=100, MaxWords=100, MinWords=1');
 
+-- Edge cases with empty query
+SELECT ts_headline('english',
+'', ''::tsquery);
+SELECT ts_headline('english',
+'foo bar', ''::tsquery);
+
 --Rewrite sub system
 
 CREATE TABLE test_tsquery (txtkeyword TEXT, txtsample TEXT);
