<!-- $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>

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

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>

generateHeadline(HeadlineParsedText*prs)

{

text*out;

intlen=128;

char*ptr;

intlen=128;

intnumfragments=0;

int2infrag=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)

{

intdist=ptr- ((char*)out);

if (wrd->in&& !wrd->repeated)

{

if (!infrag)

{

infrag=1;

numfragments++;

if (numfragments>1)

{

memcpy(ptr,prs->fragdelim,prs->fragdelimlen);

ptr+=prs->fragdelimlen;

}

}

if (wrd->replace)

{

*ptr=' ';

}

}

elseif (!wrd->repeated)

{

if (infrag)

infrag=0;

pfree(wrd->word);

}

wrd++;

}