1 Eliminate duplicate field HLWORD->skip

2 Rework support for html tags in parser
3 add HighlightAll to headline function for generating highlighted
  whole text with saved html tags

1 files changed, 105 insertions, 85 deletions

diff --git a/contrib/tsearch2/wparser_def.c b/contrib/tsearch2/wparser_def.c
index a3d6112628..035e5f2495 100644
--- a/contrib/tsearch2/wparser_def.c
+++ b/contrib/tsearch2/wparser_def.c
@@ -78,6 +78,7 @@ prsd_end(PG_FUNCTION_ARGS)
 
 #define IDIGNORE(x) ( (x)==13 || (x)==14 || (x)==12 || (x)==23 )
 #define HLIDIGNORE(x) ( (x)==5 || (x)==13 || (x)==15 || (x)==16 || (x)==17 )
+#define HTMLHLIDIGNORE(x) ( (x)==5 || (x)==15 || (x)==16 || (x)==17 )
 #define NONWORDTOKEN(x) ( (x)==12 || HLIDIGNORE(x) )
 #define NOENDTOKEN(x)	( NONWORDTOKEN(x) || (x)==7 || (x)==8 || (x)==20 || (x)==21 || (x)==22 || IDIGNORE(x) )
 
@@ -196,6 +197,7 @@ prsd_headline(PG_FUNCTION_ARGS)
 				curlen;
 
 	int			i;
+	int 			highlight=0;
 
 	/* config */
 	prs->startsel = NULL;
@@ -220,6 +222,15 @@ prsd_headline(PG_FUNCTION_ARGS)
 				prs->startsel = pstrdup(mptr->value);
 			else if (pg_strcasecmp(mptr->key, "StopSel") == 0)
 				prs->stopsel = pstrdup(mptr->value);
+			else if (pg_strcasecmp(mptr->key, "HighlightAll") == 0)
+				highlight = (
+					pg_strcasecmp(mptr->value, "1")==0 || 
+					pg_strcasecmp(mptr->value, "on")==0 || 
+					pg_strcasecmp(mptr->value, "true")==0 || 
+					pg_strcasecmp(mptr->value, "t")==0 || 
+					pg_strcasecmp(mptr->value, "y")==0 || 
+					pg_strcasecmp(mptr->value, "yes")==0 ) ?
+				1 : 0;
 
 			pfree(mptr->key);
 			pfree(mptr->value);
@@ -228,124 +239,133 @@ prsd_headline(PG_FUNCTION_ARGS)
 		}
 		pfree(map);
 
-		if (min_words >= max_words)
-			ereport(ERROR,
+		if (highlight==0) {
+			if (min_words >= max_words)
+				ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("MinWords should be less than MaxWords")));
-		if (min_words <= 0)
-			ereport(ERROR,
+			if (min_words <= 0)
+				ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("MinWords should be positive")));
-		if (shortword < 0)
-			ereport(ERROR,
+			if (shortword < 0)
+				ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("ShortWord should be >= 0")));
-	}
-
-	while (hlCover(prs, query, &p, &q))
-	{
-		/* find cover len in words */
-		curlen = 0;
-		poslen = 0;
-		for (i = p; i <= q && curlen < max_words; i++)
-		{
-			if (!NONWORDTOKEN(prs->words[i].type))
-				curlen++;
-			if (prs->words[i].item && !prs->words[i].repeated)
-				poslen++;
-			pose = i;
 		}
+	}
 
-		if (poslen < bestlen && !(NOENDTOKEN(prs->words[beste].type) || prs->words[beste].len <= shortword))
+	if (highlight==0) {
+		while (hlCover(prs, query, &p, &q))
 		{
-			/* best already finded, so try one more cover */
-			p++;
-			continue;
-		}
-
-		posb=p;
-		if (curlen < max_words)
-		{						/* find good end */
-			for (i = i - 1; i < prs->curwords && curlen < max_words; i++)
+			/* find cover len in words */
+			curlen = 0;
+			poslen = 0;
+			for (i = p; i <= q && curlen < max_words; i++)
 			{
-				if (i != q)
+				if (!NONWORDTOKEN(prs->words[i].type))
+					curlen++;
+				if (prs->words[i].item && !prs->words[i].repeated)
+					poslen++;
+				pose = i;
+			}
+	
+			if (poslen < bestlen && !(NOENDTOKEN(prs->words[beste].type) || prs->words[beste].len <= shortword))
+			{
+				/* best already finded, so try one more cover */
+				p++;
+				continue;
+			}
+	
+			posb=p;
+			if (curlen < max_words)
+			{						/* find good end */
+				for (i = i - 1; i < prs->curwords && curlen < max_words; i++)
 				{
-					if (!NONWORDTOKEN(prs->words[i].type))
-						curlen++;
-					if (prs->words[i].item && !prs->words[i].repeated)
-						poslen++;
+					if (i != q)
+					{
+						if (!NONWORDTOKEN(prs->words[i].type))
+							curlen++;
+						if (prs->words[i].item && !prs->words[i].repeated)
+							poslen++;
+					}
+					pose = i;
+					if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
+						continue;
+					if (curlen >= min_words)
+						break;
+				}
+				if ( curlen < min_words && i>=prs->curwords ) { /* got end of text and our cover is shoter than min_words */
+					for(i=p; i>= 0; i--) {
+						if (!NONWORDTOKEN(prs->words[i].type))
+							curlen++;
+						if (prs->words[i].item && !prs->words[i].repeated)
+							poslen++;
+						if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
+							continue;
+						if (curlen >= min_words)
+							break;
+					}
+					posb=(i>=0) ? i : 0;
 				}
-				pose = i;
-				if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
-					continue;
-				if (curlen >= min_words)
-					break;
 			}
-			if ( curlen < min_words && i>=prs->curwords ) { /* got end of text and our cover is shoter than min_words */
-				for(i=p; i>= 0; i--) {
+			else
+			{						/* shorter cover :((( */
+				for (; curlen > min_words; i--)
+				{
 					if (!NONWORDTOKEN(prs->words[i].type))
-						curlen++;
+						curlen--;
 					if (prs->words[i].item && !prs->words[i].repeated)
-						poslen++;
+						poslen--;
+					pose = i;
 					if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
 						continue;
-					if (curlen >= min_words)
-						break;
+					break;
 				}
-				posb=(i>=0) ? i : 0;
 			}
-		}
-		else
-		{						/* shorter cover :((( */
-			for (; curlen > min_words; i--)
+	
+			if (bestlen < 0 || (poslen > bestlen && !(NOENDTOKEN(prs->words[pose].type) || prs->words[pose].len <= shortword)) ||
+				(bestlen >= 0 && !(NOENDTOKEN(prs->words[pose].type) || prs->words[pose].len <= shortword) &&
+				 (NOENDTOKEN(prs->words[beste].type) || prs->words[beste].len <= shortword)))
 			{
-				if (!NONWORDTOKEN(prs->words[i].type))
-					curlen--;
-				if (prs->words[i].item && !prs->words[i].repeated)
-					poslen--;
-				pose = i;
-				if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
-					continue;
-				break;
+				bestb = posb;
+				beste = pose;
+				bestlen = poslen;
 			}
+	
+			p++;
 		}
 
-		if (bestlen < 0 || (poslen > bestlen && !(NOENDTOKEN(prs->words[pose].type) || prs->words[pose].len <= shortword)) ||
-			(bestlen >= 0 && !(NOENDTOKEN(prs->words[pose].type) || prs->words[pose].len <= shortword) &&
-			 (NOENDTOKEN(prs->words[beste].type) || prs->words[beste].len <= shortword)))
+		if (bestlen < 0)
 		{
-			bestb = posb;
+			curlen = 0;
+			for (i = 0; i < prs->curwords && curlen < min_words; i++)
+			{
+				if (!NONWORDTOKEN(prs->words[i].type))
+					curlen++;
+				pose = i;
+			}
+			bestb = 0;
 			beste = pose;
-			bestlen = poslen;
 		}
-
-		p++;
-	}
-
-	if (bestlen < 0)
-	{
-		curlen = 0;
-		poslen = 0;
-		for (i = 0; i < prs->curwords && curlen < min_words; i++)
-		{
-			if (!NONWORDTOKEN(prs->words[i].type))
-				curlen++;
-			pose = i;
-		}
-		bestb = 0;
-		beste = pose;
+	} else {
+		bestb=0;
+		beste=prs->curwords-1;
 	}
 
 	for (i = bestb; i <= beste; i++)
 	{
 		if (prs->words[i].item)
 			prs->words[i].selected = 1;
-		if (prs->words[i].repeated)
-			prs->words[i].skip = 1;
-		if (HLIDIGNORE(prs->words[i].type))
-			prs->words[i].replace = 1;
+		if ( highlight==0 ) { 
+			if (HLIDIGNORE(prs->words[i].type))
+				prs->words[i].replace = 1;
+		} else {
+			if (HTMLHLIDIGNORE(prs->words[i].type))
+				prs->words[i].replace = 1;
+		}
 
-		prs->words[i].in = 1;
+		prs->words[i].in = (prs->words[i].repeated) ? 0 : 1;
 	}
 
 	if (!prs->startsel)