mirror/postgresql
2
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2024-11-21 03:13:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Adjust ts_debug's output as per my proposal of yesterday: show the

Browse Source 
active dictionary and its output lexemes as separate columns, instead
of smashing them into one text column, and lowercase the column names.
Also, define the output rowtype using OUT parameters instead of a
composite type, to be consistent with the other built-in functions.
This commit is contained in:
Tom Lane 2007-10-22 20:13:37 +00:00
parent 7ec280e117
commit 3e17ef1cfa
4 changed files with 153 additions and 123 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
doc/src/sgml/func.sgml
View File

@ -1,4 +1,4 @@
<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.402 2007/10/21 20:04:37 tgl Exp $ -->
<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.403 2007/10/22 20:13:37 tgl Exp $ -->
<chapter id="functions">
<title>Functions and Operators</title>
@ -7857,11 +7857,11 @@ CREATE TYPE rainbow AS ENUM ('red', 'orange', 'yellow', 'green', 'blue', 'purple
</thead>
<tbody>
<row>
<entry><literal><function>ts_debug</function>(<optional> <replaceable class="PARAMETER">config</replaceable> <type>regconfig</>, </optional> <replaceable class="PARAMETER">document</replaceable> <type>text</>)</literal></entry>
<entry><type>setof ts_debug</type></entry>
<entry><literal><function>ts_debug</function>(<optional> <replaceable class="PARAMETER">config</replaceable> <type>regconfig</>, </optional> <replaceable class="PARAMETER">document</replaceable> <type>text</>, OUT <replaceable class="PARAMETER">alias</> <type>text</>, OUT <replaceable class="PARAMETER">description</> <type>text</>, OUT <replaceable class="PARAMETER">token</> <type>text</>, OUT <replaceable class="PARAMETER">dictionaries</> <type>regdictionary[]</>, OUT <replaceable class="PARAMETER">dictionary</> <type>regdictionary</>, OUT <replaceable class="PARAMETER">lexemes</> <type>text[]</>)</literal></entry>
<entry><type>setof record</type></entry>
<entry>test a configuration</entry>
<entry><literal>ts_debug('english', 'The Brightest supernovaes')</literal></entry>
<entry><literal>(lword,"Latin word",The,{english_stem},"english_stem: {}") ...</literal></entry>
<entry><literal>(lword,"Latin word",The,{english_stem},english_stem,{}) ...</literal></entry>
</row>
<row>
<entry><literal><function>ts_lexize</function>(<replaceable class="PARAMETER">dict</replaceable> <type>regdictionary</>, <replaceable class="PARAMETER">token</replaceable> <type>text</>)</literal></entry>

200
doc/src/sgml/textsearch.sgml
View File

@ -1,4 +1,4 @@
<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.22 2007/10/22 03:37:04 tgl Exp $ -->
<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.23 2007/10/22 20:13:37 tgl Exp $ -->
<chapter id="textsearch">
<title id="textsearch-title">Full Text Search</title>
@ -1699,18 +1699,18 @@ ON messages FOR EACH ROW EXECUTE PROCEDURE messages_trigger();
<itemizedlist spacing="compact" mark="bullet">
<listitem>
<para>
<structname>word</> <type>text</> &mdash; the value of a lexeme
<replaceable>word</> <type>text</> &mdash; the value of a lexeme
</para>
</listitem>
<listitem>
<para>
<structname>ndoc</> <type>integer</> &mdash; number of documents
<replaceable>ndoc</> <type>integer</> &mdash; number of documents
(<type>tsvector</>s) the word occurred in
</para>
</listitem>
<listitem>
<para>
<structname>nentry</> <type>integer</> &mdash; total number of
<replaceable>nentry</> <type>integer</> &mdash; total number of
occurrences of the word
</para>
</listitem>
@ -1901,8 +1901,8 @@ LIMIT 10;
as the entire word and as each component:
<programlisting>
SELECT "Alias", "Description", "Token" FROM ts_debug('foo-bar-beta1');
Alias | Description | Token
SELECT alias, description, token FROM ts_debug('foo-bar-beta1');
alias | description | token
-------------+-------------------------------+---------------
hword | Hyphenated word | foo-bar-beta1
lpart_hword | Latin part of hyphenated word | foo
@ -1917,8 +1917,8 @@ SELECT "Alias", "Description", "Token" FROM ts_debug('foo-bar-beta1');
instructive example:
<programlisting>
SELECT "Alias", "Description", "Token" FROM ts_debug('http://foo.com/stuff/index.html');
Alias | Description | Token
SELECT alias, description, token FROM ts_debug('http://foo.com/stuff/index.html');
alias | description | token
----------+---------------+--------------------------
protocol | Protocol head | http://
url | URL | foo.com/stuff/index.html
@ -2186,25 +2186,23 @@ SELECT ts_lexize('public.simple_dict','The');
synonym dictionary and put it before the <literal>english_stem</> dictionary:
<programlisting>
SELECT * FROM ts_debug('english','Paris');
Alias | Description | Token | Dictionaries | Lexized token
-------+-------------+-------+----------------+----------------------
lword | Latin word | Paris | {english_stem} | english_stem: {pari}
(1 row)
SELECT * FROM ts_debug('english', 'Paris');
alias | description | token | dictionaries | dictionary | lexemes
-------+-------------+-------+----------------+--------------+---------
lword | Latin word | Paris | {english_stem} | english_stem | {pari}
CREATE TEXT SEARCH DICTIONARY synonym (
CREATE TEXT SEARCH DICTIONARY my_synonym (
TEMPLATE = synonym,
SYNONYMS = my_synonyms
);
ALTER TEXT SEARCH CONFIGURATION english
ALTER MAPPING FOR lword WITH synonym, english_stem;
ALTER MAPPING FOR lword WITH my_synonym, english_stem;
SELECT * FROM ts_debug('english','Paris');
Alias | Description | Token | Dictionaries | Lexized token
-------+-------------+-------+------------------------+------------------
lword | Latin word | Paris | {synonym,english_stem} | synonym: {paris}
(1 row)
SELECT * FROM ts_debug('english', 'Paris');
alias | description | token | dictionaries | dictionary | lexemes
-------+-------------+-------+---------------------------+------------+---------
lword | Latin word | Paris | {my_synonym,english_stem} | my_synonym | {paris}
</programlisting>
</para>
@ -2711,7 +2709,14 @@ SHOW default_text_search_config;
</indexterm>
<synopsis>
ts_debug(<optional> <replaceable class="PARAMETER">config</replaceable> <type>regconfig</>, </optional> <replaceable class="PARAMETER">document</replaceable> <type>text</>) returns <type>setof ts_debug</>
ts_debug(<optional> <replaceable class="PARAMETER">config</replaceable> <type>regconfig</>, </optional> <replaceable class="PARAMETER">document</replaceable> <type>text</>,
OUT <replaceable class="PARAMETER">alias</> <type>text</>,
OUT <replaceable class="PARAMETER">description</> <type>text</>,
OUT <replaceable class="PARAMETER">token</> <type>text</>,
OUT <replaceable class="PARAMETER">dictionaries</> <type>regdictionary[]</>,
OUT <replaceable class="PARAMETER">dictionary</> <type>regdictionary</>,
OUT <replaceable class="PARAMETER">lexemes</> <type>text[]</>)
returns setof record
</synopsis>
<para>
@ -2725,23 +2730,47 @@ SHOW default_text_search_config;
</para>
<para>
<function>ts_debug</>'s result row type is defined as:
<function>ts_debug</> returns one row for each token identified in the text
by the parser. The columns returned are
<programlisting>
CREATE TYPE ts_debug AS (
"Alias" text,
"Description" text,
"Token" text,
"Dictionaries" regdictionary[],
"Lexized token" text
);
</programlisting>
One row is produced for each token identified by the parser.
The first three columns describe the token, and the fourth lists
the dictionaries selected by the configuration for that token's type.
The last column shows the result of dictionary processing: which
dictionary (if any) recognized the token, and what it produced.
<itemizedlist spacing="compact" mark="bullet">
<listitem>
<para>
<replaceable>alias</> <type>text</> &mdash; short name of the token type
</para>
</listitem>
<listitem>
<para>
<replaceable>description</> <type>text</> &mdash; description of the
token type
</para>
</listitem>
<listitem>
<para>
<replaceable>token</> <type>text</> &mdash; text of the token
</para>
</listitem>
<listitem>
<para>
<replaceable>dictionaries</> <type>regdictionary[]</> &mdash; the
dictionaries selected by the configuration for this token type
</para>
</listitem>
<listitem>
<para>
<replaceable>dictionary</> <type>regdictionary</> &mdash; the dictionary
that recognized the token, or <literal>NULL</> if none did
</para>
</listitem>
<listitem>
<para>
<replaceable>lexemes</> <type>text[]</> &mdash; the lexeme(s) produced
by the dictionary that recognized the token, or <literal>NULL</> if
none did; an empty array (<literal>{}</>) means it was recognized as a
stop word
</para>
</listitem>
</itemizedlist>
</para>
<para>
@ -2749,33 +2778,32 @@ CREATE TYPE ts_debug AS (
<programlisting>
SELECT * FROM ts_debug('english','a fat cat sat on a mat - it ate a fat rats');
Alias | Description | Token | Dictionaries | Lexized token
-------+---------------+-------+--------------+----------------
lword | Latin word | a | {english} | english: {}
blank | Space symbols | | |
lword | Latin word | fat | {english} | english: {fat}
blank | Space symbols | | |
lword | Latin word | cat | {english} | english: {cat}
blank | Space symbols | | |
lword | Latin word | sat | {english} | english: {sat}
blank | Space symbols | | |
lword | Latin word | on | {english} | english: {}
blank | Space symbols | | |
lword | Latin word | a | {english} | english: {}
blank | Space symbols | | |
lword | Latin word | mat | {english} | english: {mat}
blank | Space symbols | | |
blank | Space symbols | - | |
lword | Latin word | it | {english} | english: {}
blank | Space symbols | | |
lword | Latin word | ate | {english} | english: {ate}
blank | Space symbols | | |
lword | Latin word | a | {english} | english: {}
blank | Space symbols | | |
lword | Latin word | fat | {english} | english: {fat}
blank | Space symbols | | |
lword | Latin word | rats | {english} | english: {rat}
(24 rows)
alias | description | token | dictionaries | dictionary | lexemes
-------+---------------+-------+----------------+--------------+---------
lword | Latin word | a | {english_stem} | english_stem | {}
blank | Space symbols | | {} | |
lword | Latin word | fat | {english_stem} | english_stem | {fat}
blank | Space symbols | | {} | |
lword | Latin word | cat | {english_stem} | english_stem | {cat}
blank | Space symbols | | {} | |
lword | Latin word | sat | {english_stem} | english_stem | {sat}
blank | Space symbols | | {} | |
lword | Latin word | on | {english_stem} | english_stem | {}
blank | Space symbols | | {} | |
lword | Latin word | a | {english_stem} | english_stem | {}
blank | Space symbols | | {} | |
lword | Latin word | mat | {english_stem} | english_stem | {mat}
blank | Space symbols | | {} | |
blank | Space symbols | - | {} | |
lword | Latin word | it | {english_stem} | english_stem | {}
blank | Space symbols | | {} | |
lword | Latin word | ate | {english_stem} | english_stem | {ate}
blank | Space symbols | | {} | |
lword | Latin word | a | {english_stem} | english_stem | {}
blank | Space symbols | | {} | |
lword | Latin word | fat | {english_stem} | english_stem | {fat}
blank | Space symbols | | {} | |
lword | Latin word | rats | {english_stem} | english_stem | {rat}
</programlisting>
</para>
@ -2801,34 +2829,33 @@ ALTER TEXT SEARCH CONFIGURATION public.english
<programlisting>
SELECT * FROM ts_debug('public.english','The Brightest supernovaes');
Alias | Description | Token | Dictionaries | Lexized token
-------+---------------+-------------+-------------------------------------------------+-------------------------------------
lword | Latin word | The | {public.english_ispell,pg_catalog.english_stem} | public.english_ispell: {}
blank | Space symbols | | |
lword | Latin word | Brightest | {public.english_ispell,pg_catalog.english_stem} | public.english_ispell: {bright}
blank | Space symbols | | |
lword | Latin word | supernovaes | {public.english_ispell,pg_catalog.english_stem} | pg_catalog.english_stem: {supernova}
(5 rows)
alias | description | token | dictionaries | dictionary | lexemes
-------+---------------+-------------+-------------------------------+----------------+-------------
lword | Latin word | The | {english_ispell,english_stem} | english_ispell | {}
blank | Space symbols | | {} | |
lword | Latin word | Brightest | {english_ispell,english_stem} | english_ispell | {bright}
blank | Space symbols | | {} | |
lword | Latin word | supernovaes | {english_ispell,english_stem} | english_stem | {supernova}
</programlisting>
<para>
In this example, the word <literal>Brightest</> was recognized by the
parser as a <literal>Latin word</literal> (alias <literal>lword</literal>).
For this token type the dictionary list is
<literal>public.english_ispell</> and
<literal>pg_catalog.english_stem</literal>. The word was recognized by
<literal>public.english_ispell</literal>, which reduced it to the noun
<literal>english_ispell</> and
<literal>english_stem</literal>. The word was recognized by
<literal>english_ispell</literal>, which reduced it to the noun
<literal>bright</literal>. The word <literal>supernovaes</literal> is
unknown to the <literal>public.english_ispell</literal> dictionary so it
unknown to the <literal>english_ispell</literal> dictionary so it
was passed to the next dictionary, and, fortunately, was recognized (in
fact, <literal>public.english_stem</literal> is a Snowball dictionary which
fact, <literal>english_stem</literal> is a Snowball dictionary which
recognizes everything; that is why it was placed at the end of the
dictionary list).
</para>
<para>
The word <literal>The</literal> was recognized by the
<literal>public.english_ispell</literal> dictionary as a stop word (<xref
<literal>english_ispell</literal> dictionary as a stop word (<xref
linkend="textsearch-stopwords">) and will not be indexed.
The spaces are discarded too, since the configuration provides no
dictionaries at all for them.
@ -2839,16 +2866,15 @@ SELECT * FROM ts_debug('public.english','The Brightest supernovaes');
you want to see:
<programlisting>
SELECT "Alias", "Token", "Lexized token"
SELECT alias, token, dictionary, lexemes
FROM ts_debug('public.english','The Brightest supernovaes');
Alias | Token | Lexized token
-------+-------------+--------------------------------------
lword | The | public.english_ispell: {}
blank | |
lword | Brightest | public.english_ispell: {bright}
blank | |
lword | supernovaes | pg_catalog.english_stem: {supernova}
(5 rows)
alias | token | dictionary | lexemes
-------+-------------+----------------+-------------
lword | The | english_ispell | {}
blank | | |
lword | Brightest | english_ispell | {bright}
blank | | |
lword | supernovaes | english_stem | {supernova}
</programlisting>
</para>

64
src/backend/catalog/system_views.sql
View File

@ -3,7 +3,7 @@
*
* Copyright (c) 1996-2007, PostgreSQL Global Development Group
*
* $PostgreSQL: pgsql/src/backend/catalog/system_views.sql,v 1.46 2007/09/25 20:03:37 tgl Exp $
* $PostgreSQL: pgsql/src/backend/catalog/system_views.sql,v 1.47 2007/10/22 20:13:37 tgl Exp $
*/
CREATE VIEW pg_roles AS
@ -386,41 +386,39 @@ CREATE VIEW pg_stat_bgwriter AS
pg_stat_get_buf_written_backend() AS buffers_backend,
pg_stat_get_buf_alloc() AS buffers_alloc;
-- Tsearch debug function. Defined here because it'd be pretty unwieldy
-- Tsearch debug function. Defined here because it'd be pretty unwieldy
-- to put it into pg_proc.h
CREATE TYPE ts_debug AS (
"Alias" text,
"Description" text,
"Token" text,
"Dictionaries" regdictionary[],
"Lexized token" text
);
COMMENT ON TYPE ts_debug IS 'type returned from ts_debug() function';
CREATE FUNCTION ts_debug(regconfig, text)
RETURNS SETOF ts_debug AS
CREATE FUNCTION ts_debug(IN config regconfig, IN document text,
OUT alias text,
OUT description text,
OUT token text,
OUT dictionaries regdictionary[],
OUT dictionary regdictionary,
OUT lexemes text[])
RETURNS SETOF record AS
$$
SELECT
tt.alias AS "Alias",
tt.description AS "Description",
parse.token AS "Token",
tt.alias AS alias,
tt.description AS description,
parse.token AS token,
ARRAY ( SELECT m.mapdict::pg_catalog.regdictionary
FROM pg_catalog.pg_ts_config_map AS m
WHERE m.mapcfg = $1 AND m.maptokentype = parse.tokid
ORDER BY m.mapseqno )
AS "Dictionaries",
(
SELECT
dl.mapdict::pg_catalog.regdictionary || ': ' || dl.lex::pg_catalog.text
FROM
( SELECT mapdict, pg_catalog.ts_lexize(mapdict, parse.token) AS lex
FROM pg_catalog.pg_ts_config_map AS m
WHERE m.mapcfg = $1 AND m.maptokentype = parse.tokid
ORDER BY pg_catalog.ts_lexize(mapdict, parse.token) IS NULL, m.mapseqno ) dl
LIMIT 1
) AS "Lexized token"
AS dictionaries,
( SELECT mapdict::pg_catalog.regdictionary
FROM pg_catalog.pg_ts_config_map AS m
WHERE m.mapcfg = $1 AND m.maptokentype = parse.tokid
ORDER BY pg_catalog.ts_lexize(mapdict, parse.token) IS NULL, m.mapseqno
LIMIT 1
) AS dictionary,
( SELECT pg_catalog.ts_lexize(mapdict, parse.token)
FROM pg_catalog.pg_ts_config_map AS m
WHERE m.mapcfg = $1 AND m.maptokentype = parse.tokid
ORDER BY pg_catalog.ts_lexize(mapdict, parse.token) IS NULL, m.mapseqno
LIMIT 1
) AS lexemes
FROM pg_catalog.ts_parse(
(SELECT cfgparser FROM pg_catalog.pg_ts_config WHERE oid = $1 ), $2
) AS parse,
@ -434,8 +432,14 @@ LANGUAGE SQL STRICT STABLE;
COMMENT ON FUNCTION ts_debug(regconfig,text) IS
'debug function for text search configuration';
CREATE FUNCTION ts_debug(text)
RETURNS SETOF ts_debug AS
CREATE FUNCTION ts_debug(IN document text,
OUT alias text,
OUT description text,
OUT token text,
OUT dictionaries regdictionary[],
OUT dictionary regdictionary,
OUT lexemes text[])
RETURNS SETOF record AS
$$
SELECT * FROM pg_catalog.ts_debug( pg_catalog.get_current_ts_config(), $1);
$$

4
src/include/catalog/catversion.h
View File

@ -37,7 +37,7 @@
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.434 2007/10/19 22:01:45 tgl Exp $
* $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.435 2007/10/22 20:13:37 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@ -53,6 +53,6 @@
*/
/* yyyymmddN */
#define CATALOG_VERSION_NO 200710192
#define CATALOG_VERSION_NO 200710221
#endif