|
|
|
|
@ -131,24 +131,24 @@ ORDER BY |
|
|
|
|
</sect2> |
|
|
|
|
|
|
|
|
|
<sect2> |
|
|
|
|
<title>Tsearch2 Integration</title> |
|
|
|
|
<title>Text Search Integration</title> |
|
|
|
|
<para> |
|
|
|
|
Trigram matching is a very useful tool when used in conjunction |
|
|
|
|
with a text index created by the Tsearch2 contrib module. (See |
|
|
|
|
contrib/tsearch2) |
|
|
|
|
with a full text index. |
|
|
|
|
</para> |
|
|
|
|
<para> |
|
|
|
|
The first step is to generate an auxiliary table containing all |
|
|
|
|
the unique words in the Tsearch2 index: |
|
|
|
|
the unique words in the documents: |
|
|
|
|
</para> |
|
|
|
|
<programlisting> |
|
|
|
|
CREATE TABLE words AS SELECT word FROM |
|
|
|
|
stat('SELECT to_tsvector(''simple'', bodytext) FROM documents'); |
|
|
|
|
</programlisting> |
|
|
|
|
<para> |
|
|
|
|
Where 'documents' is a table that has a text field 'bodytext' |
|
|
|
|
that TSearch2 is used to search. The use of the 'simple' dictionary |
|
|
|
|
with the to_tsvector function, instead of just using the already |
|
|
|
|
where <structname>documents</> is a table that has a text field |
|
|
|
|
<structfield>bodytext</> that we wish to search. The use of the |
|
|
|
|
<literal>simple</> configuration with the <function>to_tsvector</> |
|
|
|
|
function, instead of just using the already |
|
|
|
|
existing vector is to avoid creating a list of already stemmed |
|
|
|
|
words. This way, only the original, unstemmed words are added |
|
|
|
|
to the word list. |
|
|
|
|
@ -174,9 +174,9 @@ CREATE INDEX words_idx ON words USING gin(word gist_trgm_ops); |
|
|
|
|
<para> |
|
|
|
|
<note> |
|
|
|
|
<para> |
|
|
|
|
Since the 'words' table has been generated as a separate, |
|
|
|
|
Since the <structname>words</> table has been generated as a separate, |
|
|
|
|
static table, it will need to be periodically regenerated so that |
|
|
|
|
it remains up to date with the word list in the Tsearch2 index. |
|
|
|
|
it remains up to date with the document collection. |
|
|
|
|
</para> |
|
|
|
|
</note> |
|
|
|
|
</para> |
|
|
|
|
@ -184,14 +184,14 @@ CREATE INDEX words_idx ON words USING gin(word gist_trgm_ops); |
|
|
|
|
|
|
|
|
|
<sect2> |
|
|
|
|
<title>References</title> |
|
|
|
|
<para> |
|
|
|
|
Tsearch2 Development Site |
|
|
|
|
<ulink url="http://www.sai.msu.su/~megera/postgres/gist/tsearch/V2/"></ulink> |
|
|
|
|
</para> |
|
|
|
|
<para> |
|
|
|
|
GiST Development Site |
|
|
|
|
<ulink url="http://www.sai.msu.su/~megera/postgres/gist/"></ulink> |
|
|
|
|
</para> |
|
|
|
|
<para> |
|
|
|
|
Tsearch2 Development Site |
|
|
|
|
<ulink url="http://www.sai.msu.su/~megera/postgres/gist/tsearch/V2/"></ulink> |
|
|
|
|
</para> |
|
|
|
|
</sect2> |
|
|
|
|
|
|
|
|
|
<sect2> |
|
|
|
|
|
Tom Lane
18 years ago