postgrespro
diff --git a/‎doc/src/sgml/textsearch.sgml
Lines changed: 25 additions & 2 deletions b/‎doc/src/sgml/textsearch.sgml
Lines changed: 25 additions & 2 deletions
diff --git a/‎src/backend/tsearch/ts_parse.c
Lines changed: 24 additions & 3 deletions b/‎src/backend/tsearch/ts_parse.c
Lines changed: 24 additions & 3 deletions
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.45 2008/09/23 09:20:34 heikki Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.46 2008/10/17 18:05:19 teodor Exp $ -->
 
 <chapter id="textsearch">
  <title id="textsearch-title">Full Text Search</title>
@@ -1098,6 +1098,29 @@ ORDER BY rank DESC LIMIT 10;
        value of three eliminates the English articles.
       </para>
      </listitem>
+     <listitem>
+      <para>
+       <literal>MaxFragments</literal>: maximum number of text excerpts 
+       or fragments that matches the query words. It also triggers a 
+       different headline generation function than the default one. This
+       function finds text fragments with as many query words as possible and 
+       stretches  those fragments around the query words. As a result 
+       query words are close to the middle of each fragment and have words on 
+       each side. Each fragment will be of at  most MaxWords and will not 
+       have words of size less than or equal to ShortWord at the start or 
+       end of a  fragment. If all query words are not found in the document, 
+       then  a single fragment of MinWords will be displayed.
+      </para>
+     </listitem>
+     <listitem>
+      <para>
+       <literal>FragmentDelimiter</literal>: When more than one fragments are 
+       displayed, then the fragments will be separated by this delimiter. This 
+       option is effective only if MaxFragments is greater than 1 and there are
+       more than one fragments to be diplayed. This option has no effect on the
+       default headline generation function.
+      </para>
+     </listitem>
      <listitem>
       <para>
        <literal>HighlightAll</literal>: Boolean flag;  if
@@ -1109,7 +1132,7 @@ ORDER BY rank DESC LIMIT 10;
     Any unspecified options receive these defaults:
 
 <programlisting>
-StartSel=&lt;b&gt;, StopSel=&lt;/b&gt;, MaxWords=35, MinWords=15, ShortWord=3, HighlightAll=FALSE
+StartSel=&lt;b&gt;, StopSel=&lt;/b&gt;, MaxFragments=0, FragmentDelimiter=" ... ", MaxWords=35, MinWords=15, ShortWord=3, HighlightAll=FALSE
 </programlisting>
    </para>
 
 
@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_parse.c,v 1.8 2008/05/16 16:31:01 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_parse.c,v 1.9 2008/10/17 18:05:19 teodor Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -583,16 +583,19 @@ text *
 generateHeadline(HeadlineParsedText *prs)
 {
 	text	   *out;
-	int			len = 128;
 	char	   *ptr;
+	int			len          = 128;
+	int	   		numfragments = 0;
+	int2	   		infrag       = 0;
+
 	HeadlineWordEntry *wrd = prs->words;
 
 	out = (text *) palloc(len);
 	ptr = ((char *) out) + VARHDRSZ;
 
 	while (wrd - prs->words < prs->curwords)
 	{
-		while (wrd->len + prs->stopsellen + prs->startsellen + (ptr - ((char *) out)) >= len)
+		while (wrd->len + prs->stopsellen + prs->startsellen + prs->fragdelimlen + (ptr - ((char *) out)) >= len)
 		{
 			int			dist = ptr - ((char *) out);
 
@@ -603,6 +606,20 @@ generateHeadline(HeadlineParsedText *prs)
 
 		if (wrd->in && !wrd->repeated)
 		{
+			if (!infrag)
+			{
+
+				/* start of a new fragment */
+				infrag = 1;
+				numfragments ++;
+				/* add a fragment delimitor if this is after the first one */ 
+				if (numfragments > 1)
+				{
+					memcpy(ptr, prs->fragdelim, prs->fragdelimlen);
+					ptr += prs->fragdelimlen;
+				}	
+
+			}	
 			if (wrd->replace)
 			{
 				*ptr = ' ';
@@ -625,7 +642,11 @@ generateHeadline(HeadlineParsedText *prs)
 			}
 		}
 		else if (!wrd->repeated)
+		{
+			if (infrag)
+				infrag = 0;
 			pfree(wrd->word);
+		}	
 
 		wrd++;
 	}
Original file line number	Diff line number	Diff line change
`@@ -7,7 +7,7 @@`
`7`	`7`	`*`
`8`	`8`	`*`
`9`	`9`	`* IDENTIFICATION`
`10`		`- * $PostgreSQL: pgsql/src/backend/tsearch/ts_parse.c,v 1.8 2008/05/16 16:31:01 tgl Exp $`
	`10`	`+ * $PostgreSQL: pgsql/src/backend/tsearch/ts_parse.c,v 1.9 2008/10/17 18:05:19 teodor Exp $`
`11`	`11`	`*`
`12`	`12`	`*-------------------------------------------------------------------------`
`13`	`13`	`*/`
`@@ -583,16 +583,19 @@ text *`
`583`	`583`	`generateHeadline(HeadlineParsedText *prs)`
`584`	`584`	`{`
`585`	`585`	`text *out;`
`586`		`- int len = 128;`
`587`	`586`	`char *ptr;`
	`587`	`+ int len = 128;`
	`588`	`+ int numfragments = 0;`
	`589`	`+ int2 infrag = 0;`
	`590`	`+`
`588`	`591`	`HeadlineWordEntry *wrd = prs->words;`
`589`	`592`
`590`	`593`	`out = (text *) palloc(len);`
`591`	`594`	`ptr = ((char *) out) + VARHDRSZ;`
`592`	`595`
`593`	`596`	`while (wrd - prs->words < prs->curwords)`
`594`	`597`	`{`
`595`		`- while (wrd->len + prs->stopsellen + prs->startsellen + (ptr - ((char *) out)) >= len)`
	`598`	`+ while (wrd->len + prs->stopsellen + prs->startsellen + prs->fragdelimlen + (ptr - ((char *) out)) >= len)`
`596`	`599`	`{`
`597`	`600`	`int dist = ptr - ((char *) out);`
`598`	`601`
`@@ -603,6 +606,20 @@ generateHeadline(HeadlineParsedText *prs)`
`603`	`606`
`604`	`607`	`if (wrd->in && !wrd->repeated)`
`605`	`608`	`{`
	`609`	`+ if (!infrag)`
	`610`	`+ {`
	`611`	`+`
	`612`	`+ /* start of a new fragment */`
	`613`	`+ infrag = 1;`
	`614`	`+ numfragments ++;`
	`615`	`+ /* add a fragment delimitor if this is after the first one */`
	`616`	`+ if (numfragments > 1)`
	`617`	`+ {`
	`618`	`+ memcpy(ptr, prs->fragdelim, prs->fragdelimlen);`
	`619`	`+ ptr += prs->fragdelimlen;`
	`620`	`+ }`
	`621`	`+`
	`622`	`+ }`
`606`	`623`	`if (wrd->replace)`
`607`	`624`	`{`
`608`	`625`	`*ptr = ' ';`
`@@ -625,7 +642,11 @@ generateHeadline(HeadlineParsedText *prs)`
`625`	`642`	`}`
`626`	`643`	`}`
`627`	`644`	`else if (!wrd->repeated)`
	`645`	`+ {`
	`646`	`+ if (infrag)`
	`647`	`+ infrag = 0;`
`628`	`648`	`pfree(wrd->word);`
	`649`	`+ }`
`629`	`650`
`630`	`651`	`wrd++;`
`631`	`652`	`}`