Text parser rewritten:

- supports multibyte encodings
        - more strict rules for lexemes
        - flex isn't used
Add:
        - tsquery plainto_tsquery(text)
          Function makes tsquery from plain text.
        - &&, ||, !! operation for tsquery for combining
          tsquery from it's parts:  'foo & bar' || 'asd' => 'foo & bar | asd'
This commit is contained in:
Teodor Sigaev 2005-11-21 12:27:57 +00:00
parent b91e6ed93e
commit c52795d18a
15 changed files with 1613 additions and 424 deletions

View File

@ -1,4 +1,4 @@
# $PostgreSQL: pgsql/contrib/tsearch2/Makefile,v 1.11 2005/11/08 17:08:46 teodor Exp $
# $PostgreSQL: pgsql/contrib/tsearch2/Makefile,v 1.12 2005/11/21 12:27:57 teodor Exp $
MODULE_big = tsearch2
OBJS = dict_ex.o dict.o snmap.o stopword.o common.o prs_dcfg.o \
@ -6,7 +6,8 @@ OBJS = dict_ex.o dict.o snmap.o stopword.o common.o prs_dcfg.o \
wparser.o wparser_def.o \
ts_cfg.o tsvector.o query_cleanup.o crc32.o query.o gistidx.o \
tsvector_op.o rank.o ts_stat.o \
query_util.o query_support.o query_rewrite.o query_gist.o
query_util.o query_support.o query_rewrite.o query_gist.o \
ts_locale.o
SUBDIRS := snowball ispell wordparser
SUBDIROBJS := $(SUBDIRS:%=%/SUBSYS.o)

View File

@ -13,12 +13,12 @@ psql:tsearch2.sql:342: NOTICE: argument type tsvector is only a shell
psql:tsearch2.sql:396: NOTICE: type "tsquery" is not yet defined
DETAIL: Creating a shell type definition.
psql:tsearch2.sql:401: NOTICE: argument type tsquery is only a shell
psql:tsearch2.sql:544: NOTICE: type "gtsvector" is not yet defined
psql:tsearch2.sql:559: NOTICE: type "gtsvector" is not yet defined
DETAIL: Creating a shell type definition.
psql:tsearch2.sql:549: NOTICE: argument type gtsvector is only a shell
psql:tsearch2.sql:998: NOTICE: type "gtsq" is not yet defined
psql:tsearch2.sql:564: NOTICE: argument type gtsvector is only a shell
psql:tsearch2.sql:1054: NOTICE: type "gtsq" is not yet defined
DETAIL: Creating a shell type definition.
psql:tsearch2.sql:1003: NOTICE: argument type gtsq is only a shell
psql:tsearch2.sql:1059: NOTICE: argument type gtsq is only a shell
--tsvector
SELECT '1'::tsvector;
tsvector
@ -653,7 +653,7 @@ select * from token_type('default');
11 | lpart_hword | Latin part of hyphenated word
12 | blank | Space symbols
13 | tag | HTML Tag
14 | http | HTTP head
14 | protocol | Protocol head
15 | hword | Hyphenated word
16 | lhword | Latin hyphenated word
17 | nlhword | Non-latin hyphenated word
@ -672,14 +672,13 @@ select * from parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc
-------+--------------------------------------
22 | 345
12 |
4 | qwe@efd.r
12 |
1 | qwe
12 | @
19 | efd.r
12 | '
12 |
14 | http://
6 | www.com
12 | /
12 |
14 | http://
5 | aew.werc.ewr/?ad=qwe&dw
6 | aew.werc.ewr
@ -700,10 +699,8 @@ select * from parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc
6 | 4aew.werc.ewr
12 |
14 | http://
5 | 5aew.werc.ewr:8100/?
6 | 5aew.werc.ewr
18 | :8100/?
12 |
6 | 5aew.werc.ewr:8100
12 | /?
1 | ad
12 | =
1 | qwe
@ -711,12 +708,12 @@ select * from parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc
1 | dw
12 |
5 | 6aew.werc.ewr:8100/?ad=qwe&dw
6 | 6aew.werc.ewr
18 | :8100/?ad=qwe&dw
6 | 6aew.werc.ewr:8100
18 | /?ad=qwe&dw
12 |
5 | 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32
6 | 7aew.werc.ewr
18 | :8100/?ad=qwe&dw=%20%32
6 | 7aew.werc.ewr:8100
18 | /?ad=qwe&dw=%20%32
12 |
7 | +4.0e-10
12 |
@ -747,11 +744,15 @@ select * from parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc
1 | jf
12 |
1 | sdjk
13 | <we hjwer <werrwe>
12 | <
1 | we
12 |
1 | hjwer
12 |
13 | <werrwe>
12 |
3 | ewr1
12 | >
12 |
3 | ewri2
12 |
13 | <a href="qwe<qwe>">
@ -767,57 +768,53 @@ select * from parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc
12 |
19 | /wqe-324/ewr
12 |
6 | gist.h
19 | gist.h
12 |
6 | gist.h.c
19 | gist.h.c
12 |
6 | gist.c
19 | gist.c
12 | .
12 |
1 | readline
12 |
20 | 4.2
12 |
20 | 4.2
12 | .
12 |
20 | 4.2
12 | ,
12 |
15 | readline-4
15 | readline-4.2
11 | readline
12 | -
20 | 4.2
12 |
15 | readline-4
15 | readline-4.2
11 | readline
12 | -
20 | 4.2
12 | .
12 |
22 | 234
12 |
13 | <i <b>
12 | <
1 | i
12 |
13 | <b>
12 |
1 | wow
12 |
12 | <
12 |
1 | jqw
12 |
12 | <
12 | >
12 |
12 | <>
1 | qwerty
(138 rows)
(135 rows)
SELECT to_tsvector('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 teodor@stack.net qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
/usr/local/fff /awdf/dwqe/4325 rewt/ewr wefjn /wqe-324/ewr gist.h gist.h.c gist.c. readline 4.2 4.2. 4.2, readline-4.2 readline-4.2. 234
<i <b> wow < jqw <> qwerty');
to_tsvector
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
'ad':18 'dw':20 'jf':40 '234':62 '345':1 '4.2':53,54,55,58,61 '455':32 'jqw':64 'qwe':19,28,29,36 'wer':37 'wow':63 'asdf':38 'ewr1':42 'qwer':39 'sdjk':41 '5.005':33 'ewri2':43 'qwqwe':30 'wefjn':47 'gist.c':51 'gist.h':49 'qwerti':65 '234.435':31 ':8100/?':17 'qwe-wer':35 'readlin':52,57,60 'www.com':3 '+4.0e-10':27 'gist.h.c':50 'rewt/ewr':46 'qwe@efd.r':2 'readline-4':56,59 '/?ad=qwe&dw':6,9,13 '/wqe-324/ewr':48 'aew.werc.ewr':5 '1aew.werc.ewr':8 '2aew.werc.ewr':10 '3aew.werc.ewr':12 '4aew.werc.ewr':14 '5aew.werc.ewr':16 '6aew.werc.ewr':22 '7aew.werc.ewr':25 '/usr/local/fff':44 '/awdf/dwqe/4325':45 ':8100/?ad=qwe&dw':23 'teodor@stack.net':34 '5aew.werc.ewr:8100/?':15 ':8100/?ad=qwe&dw=%20%32':26 'aew.werc.ewr/?ad=qwe&dw':4 '1aew.werc.ewr/?ad=qwe&dw':7 '3aew.werc.ewr/?ad=qwe&dw':11 '6aew.werc.ewr:8100/?ad=qwe&dw':21 '7aew.werc.ewr:8100/?ad=qwe&dw=%20%32':24
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
'ad':17 'dw':19 'jf':39 '234':63 '345':1 '4.2':54,55,56,59,62 '455':31 'jqw':66 'qwe':2,18,27,28,35 'wer':36 'wow':65 'asdf':37 'ewr1':43 'qwer':38 'sdjk':40 '5.005':32 'efd.r':3 'ewri2':44 'hjwer':42 'qwqwe':29 'wefjn':48 'gist.c':52 'gist.h':50 'qwerti':67 '234.435':30 'qwe-wer':34 'readlin':53,58,61 'www.com':4 '+4.0e-10':26 'gist.h.c':51 'rewt/ewr':47 '/?ad=qwe&dw':7,10,14,22 '/wqe-324/ewr':49 'aew.werc.ewr':6 'readline-4.2':57,60 '1aew.werc.ewr':9 '2aew.werc.ewr':11 '3aew.werc.ewr':13 '4aew.werc.ewr':15 '/usr/local/fff':45 '/awdf/dwqe/4325':46 'teodor@stack.net':33 '/?ad=qwe&dw=%20%32':25 '5aew.werc.ewr:8100':16 '6aew.werc.ewr:8100':21 '7aew.werc.ewr:8100':24 'aew.werc.ewr/?ad=qwe&dw':5 '1aew.werc.ewr/?ad=qwe&dw':8 '3aew.werc.ewr/?ad=qwe&dw':12 '6aew.werc.ewr:8100/?ad=qwe&dw':20 '7aew.werc.ewr:8100/?ad=qwe&dw=%20%32':23
(1 row)
SELECT length(to_tsvector('default', '345 qw'));
@ -831,7 +828,7 @@ SELECT length(to_tsvector('default', '345 qwe@efd.r '' http://www.com/ http://ae
<i <b> wow < jqw <> qwerty'));
length
--------
53
51
(1 row)
select to_tsquery('default', 'qwe & sKies ');
@ -876,6 +873,36 @@ select to_tsquery('default', '(the|and&(i&1))&fghj');
'1' & 'fghj'
(1 row)
select plainto_tsquery('default', 'the and z 1))& fghj');
plainto_tsquery
--------------------
'z' & '1' & 'fghj'
(1 row)
select plainto_tsquery('default', 'foo bar') && plainto_tsquery('default', 'asd');
?column?
-----------------------
'foo' & 'bar' & 'asd'
(1 row)
select plainto_tsquery('default', 'foo bar') || plainto_tsquery('default', 'asd fg');
?column?
------------------------------
'foo' & 'bar' | 'asd' & 'fg'
(1 row)
select plainto_tsquery('default', 'foo bar') || !!plainto_tsquery('default', 'asd fg');
?column?
-----------------------------------
'foo' & 'bar' | !( 'asd' & 'fg' )
(1 row)
select plainto_tsquery('default', 'foo bar') && 'asd | fg';
?column?
----------------------------------
'foo' & 'bar' & ( 'asd' | 'fg' )
(1 row)
select 'a b:89 ca:23A,64b d:34c'::tsvector @@ 'd:AC & ca';
?column?
----------

View File

@ -51,10 +51,20 @@ Datum to_tsquery_name(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(to_tsquery_current);
Datum to_tsquery_current(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(plainto_tsquery);
Datum plainto_tsquery(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(plainto_tsquery_name);
Datum plainto_tsquery_name(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(plainto_tsquery_current);
Datum plainto_tsquery_current(PG_FUNCTION_ARGS);
/* parser's states */
#define WAITOPERAND 1
#define WAITOPERATOR 2
#define WAITFIRSTOPERAND 3
#define WAITSINGLEOPERAND 4
/*
* node of query tree, also used
@ -195,6 +205,14 @@ gettoken_query(QPRS_STATE * state, int4 *val, int4 *lenval, char **strval, int2
else if (*(state->buf) != ' ')
return ERR;
break;
case WAITSINGLEOPERAND:
if ( *(state->buf) == '\0' )
return END;
*strval = state->buf;
*lenval = strlen( state->buf );
state->buf += strlen( state->buf );
state->count++;
return VAL;
default:
return ERR;
break;
@ -582,7 +600,7 @@ findoprnd(ITEM * ptr, int4 *pos)
* input
*/
static QUERYTYPE *
queryin(char *buf, void (*pushval) (QPRS_STATE *, int, char *, int, int2), int cfg_id)
queryin(char *buf, void (*pushval) (QPRS_STATE *, int, char *, int, int2), int cfg_id, bool isplain)
{
QPRS_STATE state;
int4 i;
@ -599,7 +617,7 @@ static QUERYTYPE *
/* init state */
state.buf = buf;
state.state = WAITFIRSTOPERAND;
state.state = (isplain) ? WAITSINGLEOPERAND : WAITFIRSTOPERAND;
state.count = 0;
state.num = 0;
state.str = NULL;
@ -679,7 +697,7 @@ Datum
tsquery_in(PG_FUNCTION_ARGS)
{
SET_FUNCOID();
PG_RETURN_POINTER(queryin((char *) PG_GETARG_POINTER(0), pushval_asis, 0));
PG_RETURN_POINTER(queryin((char *) PG_GETARG_POINTER(0), pushval_asis, 0, false));
}
/*
@ -910,7 +928,7 @@ to_tsquery(PG_FUNCTION_ARGS)
str = text2char(in);
PG_FREE_IF_COPY(in, 1);
query = queryin(str, pushval_morph, PG_GETARG_INT32(0));
query = queryin(str, pushval_morph, PG_GETARG_INT32(0),false);
if ( query->size == 0 )
PG_RETURN_POINTER(query);
@ -950,3 +968,59 @@ to_tsquery_current(PG_FUNCTION_ARGS)
Int32GetDatum(get_currcfg()),
PG_GETARG_DATUM(0)));
}
Datum
plainto_tsquery(PG_FUNCTION_ARGS)
{
text *in = PG_GETARG_TEXT_P(1);
char *str;
QUERYTYPE *query;
ITEM *res;
int4 len;
SET_FUNCOID();
str = text2char(in);
PG_FREE_IF_COPY(in, 1);
query = queryin(str, pushval_morph, PG_GETARG_INT32(0), true);
if ( query->size == 0 )
PG_RETURN_POINTER(query);
res = clean_fakeval_v2(GETQUERY(query), &len);
if (!res)
{
query->len = HDRSIZEQT;
query->size = 0;
PG_RETURN_POINTER(query);
}
memcpy((void *) GETQUERY(query), (void *) res, len * sizeof(ITEM));
pfree(res);
PG_RETURN_POINTER(query);
}
Datum
plainto_tsquery_name(PG_FUNCTION_ARGS)
{
text *name = PG_GETARG_TEXT_P(0);
Datum res;
SET_FUNCOID();
res = DirectFunctionCall2(plainto_tsquery,
Int32GetDatum(name2id_cfg(name)),
PG_GETARG_DATUM(1));
PG_FREE_IF_COPY(name, 0);
PG_RETURN_DATUM(res);
}
Datum
plainto_tsquery_current(PG_FUNCTION_ARGS)
{
SET_FUNCOID();
PG_RETURN_DATUM(DirectFunctionCall2(plainto_tsquery,
Int32GetDatum(get_currcfg()),
PG_GETARG_DATUM(0)));
}

View File

@ -14,6 +14,117 @@ tsquery_numnode(PG_FUNCTION_ARGS) {
PG_RETURN_INT32(nnode);
}
static QTNode*
join_tsqueries(QUERYTYPE *a, QUERYTYPE *b) {
QTNode *res=(QTNode*)palloc0( sizeof(QTNode) );
res->flags |= QTN_NEEDFREE;
res->valnode = (ITEM*)palloc0( sizeof(ITEM) );
res->valnode->type = OPR;
res->child = (QTNode**)palloc0( sizeof(QTNode*)*2 );
res->child[0] = QT2QTN( GETQUERY(b), GETOPERAND(b) );
res->child[1] = QT2QTN( GETQUERY(a), GETOPERAND(a) );
res->nchild = 2;
return res;
}
PG_FUNCTION_INFO_V1(tsquery_and);
Datum tsquery_and(PG_FUNCTION_ARGS);
Datum
tsquery_and(PG_FUNCTION_ARGS) {
QUERYTYPE *a = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM_COPY(PG_GETARG_DATUM(0)));
QUERYTYPE *b = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM_COPY(PG_GETARG_DATUM(1)));
QTNode *res;
QUERYTYPE *query;
if ( a->size == 0 ) {
PG_FREE_IF_COPY(a,1);
PG_RETURN_POINTER(b);
} else if ( b->size == 0 ) {
PG_FREE_IF_COPY(b,1);
PG_RETURN_POINTER(a);
}
res = join_tsqueries(a, b);
res->valnode->val = '&';
query = QTN2QT( res, PlainMemory );
QTNFree(res);
PG_FREE_IF_COPY(a,0);
PG_FREE_IF_COPY(b,1);
PG_RETURN_POINTER(query);
}
PG_FUNCTION_INFO_V1(tsquery_or);
Datum tsquery_or(PG_FUNCTION_ARGS);
Datum
tsquery_or(PG_FUNCTION_ARGS) {
QUERYTYPE *a = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM_COPY(PG_GETARG_DATUM(0)));
QUERYTYPE *b = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM_COPY(PG_GETARG_DATUM(1)));
QTNode *res;
QUERYTYPE *query;
if ( a->size == 0 ) {
PG_FREE_IF_COPY(a,1);
PG_RETURN_POINTER(b);
} else if ( b->size == 0 ) {
PG_FREE_IF_COPY(b,1);
PG_RETURN_POINTER(a);
}
res = join_tsqueries(a, b);
res->valnode->val = '|';
query = QTN2QT( res, PlainMemory );
QTNFree(res);
PG_FREE_IF_COPY(a,0);
PG_FREE_IF_COPY(b,1);
PG_RETURN_POINTER(query);
}
PG_FUNCTION_INFO_V1(tsquery_not);
Datum tsquery_not(PG_FUNCTION_ARGS);
Datum
tsquery_not(PG_FUNCTION_ARGS) {
QUERYTYPE *a = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM_COPY(PG_GETARG_DATUM(0)));
QTNode *res;
QUERYTYPE *query;
if ( a->size == 0 )
PG_RETURN_POINTER(a);
res=(QTNode*)palloc0( sizeof(QTNode) );
res->flags |= QTN_NEEDFREE;
res->valnode = (ITEM*)palloc0( sizeof(ITEM) );
res->valnode->type = OPR;
res->valnode->val = '!';
res->child = (QTNode**)palloc0( sizeof(QTNode*) );
res->child[0] = QT2QTN( GETQUERY(a), GETOPERAND(a) );
res->nchild = 1;
query = QTN2QT( res, PlainMemory );
QTNFree(res);
PG_FREE_IF_COPY(a,0);
PG_RETURN_POINTER(query);
}
static int
CompareTSQ( QUERYTYPE *a, QUERYTYPE *b ) {
if ( a->size != b->size ) {

View File

@ -173,6 +173,13 @@ select to_tsquery('default', 'asd&(and|fghj)');
select to_tsquery('default', '(asd&and)|fghj');
select to_tsquery('default', '(asd&!and)|fghj');
select to_tsquery('default', '(the|and&(i&1))&fghj');
select plainto_tsquery('default', 'the and z 1))& fghj');
select plainto_tsquery('default', 'foo bar') && plainto_tsquery('default', 'asd');
select plainto_tsquery('default', 'foo bar') || plainto_tsquery('default', 'asd fg');
select plainto_tsquery('default', 'foo bar') || !!plainto_tsquery('default', 'asd fg');
select plainto_tsquery('default', 'foo bar') && 'asd | fg';
select 'a b:89 ca:23A,64b d:34c'::tsvector @@ 'd:AC & ca';
select 'a b:89 ca:23A,64b d:34c'::tsvector @@ 'd:AC & ca:B';
select 'a b:89 ca:23A,64b d:34c'::tsvector @@ 'd:AC & ca:A';

View File

@ -0,0 +1,61 @@
#include "ts_locale.h"
#include "utils/builtins.h"
#include "utils/pg_locale.h"
#include "mb/pg_wchar.h"
#if defined(TS_USE_WIDE) && defined(WIN32)
size_t
wchar2char( const char *to, const wchar_t *from, size_t len ) {
if (GetDatabaseEncoding() == PG_UTF8) {
int r;
if (len==0)
return 0;
r = WideCharToMultiByte(CP_UTF8, 0, from, len, to, nbytes,
NULL, NULL);
if ( r==0 )
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("UTF-16 to UTF-8 translation failed: %lu",
GetLastError())));
return r;
}
return wcstombs(to, from, len);
}
size_t
char2wchar( const wchar_t *to, const char *from, size_t len ) {
if (GetDatabaseEncoding() == PG_UTF8) {
int r;
if (len==0)
return 0;
r = MultiByteToWideChar(CP_UTF8, 0, from, len,
to, len);
if (!r) {
pg_verifymbstr(from, len, false);
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("invalid multibyte character for locale"),
errhint("The server's LC_CTYPE locale is probably incompatible with the database encoding.")));
}
Assert(r <= nbytes);
return r;
}
return mbstowcs(to, from, len);
}
#endif

View File

@ -0,0 +1,38 @@
#ifndef __TSLOCALE_H__
#define __TSLOCALE_H__
#include "postgres.h"
#include <ctype.h>
#include <limits.h>
/*
* towlower() and friends should be in <wctype.h>, but some pre-C99 systems
* declare them in <wchar.h>.
*/
#ifdef HAVE_WCHAR_H
#include <wchar.h>
#endif
#ifdef HAVE_WCTYPE_H
#include <wctype.h>
#endif
#if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
#define TS_USE_WIDE
#ifdef WIN32
size_t wchar2char( const char *to, const wchar_t *from, size_t len );
size_t char2wchar( const wchar_t *to, const char *from, size_t len );
#else /* WIN32 */
/* correct mbstowcs */
#define char2wchar mbstowcs
#define wchar2char wcstombs
#endif /* WIN32 */
#endif /* defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER) */
#endif /* __TSLOCALE_H__ */

View File

@ -427,6 +427,21 @@ RETURNS tsquery
AS 'MODULE_PATHNAME','to_tsquery_current'
LANGUAGE 'c' with (isstrict,iscachable);
CREATE FUNCTION plainto_tsquery(oid, text)
RETURNS tsquery
AS 'MODULE_PATHNAME'
LANGUAGE 'c' with (isstrict,iscachable);
CREATE FUNCTION plainto_tsquery(text, text)
RETURNS tsquery
AS 'MODULE_PATHNAME','plainto_tsquery_name'
LANGUAGE 'c' with (isstrict,iscachable);
CREATE FUNCTION plainto_tsquery(text)
RETURNS tsquery
AS 'MODULE_PATHNAME','plainto_tsquery_current'
LANGUAGE 'c' with (isstrict,iscachable);
--operations
CREATE FUNCTION exectsq(tsvector, tsquery)
RETURNS bool
@ -929,6 +944,47 @@ CREATE OR REPLACE FUNCTION numnode(tsquery)
language 'C'
with (isstrict,iscachable);
CREATE OR REPLACE FUNCTION tsquery_and(tsquery,tsquery)
returns tsquery
as 'MODULE_PATHNAME', 'tsquery_and'
language 'C'
with (isstrict,iscachable);
CREATE OPERATOR && (
LEFTARG = tsquery,
RIGHTARG = tsquery,
PROCEDURE = tsquery_and,
COMMUTATOR = '&&',
RESTRICT = contsel,
JOIN = contjoinsel
);
CREATE OR REPLACE FUNCTION tsquery_or(tsquery,tsquery)
returns tsquery
as 'MODULE_PATHNAME', 'tsquery_or'
language 'C'
with (isstrict,iscachable);
CREATE OPERATOR || (
LEFTARG = tsquery,
RIGHTARG = tsquery,
PROCEDURE = tsquery_or,
COMMUTATOR = '||',
RESTRICT = contsel,
JOIN = contjoinsel
);
CREATE OR REPLACE FUNCTION tsquery_not(tsquery)
returns tsquery
as 'MODULE_PATHNAME', 'tsquery_not'
language 'C'
with (isstrict,iscachable);
CREATE OPERATOR !! (
RIGHTARG = tsquery,
PROCEDURE = tsquery_not
);
--------------rewrite subsystem
CREATE OR REPLACE FUNCTION rewrite(tsquery, text)

View File

@ -1,8 +1,8 @@
# $PostgreSQL: pgsql/contrib/tsearch2/wordparser/Makefile,v 1.8 2005/10/18 01:30:49 tgl Exp $
# $PostgreSQL: pgsql/contrib/tsearch2/wordparser/Makefile,v 1.9 2005/11/21 12:27:57 teodor Exp $
SUBOBJS = parser.o deflex.o
EXTRA_CLEAN = SUBSYS.o $(SUBOBJS) parser.c
EXTRA_CLEAN = SUBSYS.o $(SUBOBJS)
PG_CPPFLAGS = -I$(srcdir)/..
@ -20,13 +20,6 @@ override CFLAGS += $(CFLAGS_SL)
all: SUBSYS.o
parser.c: parser.l
ifdef FLEX
$(FLEX) $(FLEXFLAGS) -8 -Ptsearch2_yy -o'$@' $<
else
@$(missing) flex $< $@
endif
SUBSYS.o: $(SUBOBJS)
$(LD) $(LDREL) $(LDOUT) $@ $^

View File

@ -15,7 +15,7 @@ const char *lex_descr[] = {
"Latin part of hyphenated word",
"Space symbols",
"HTML Tag",
"HTTP head",
"Protocol head",
"Hyphenated word",
"Latin hyphenated word",
"Non-latin hyphenated word",
@ -42,7 +42,7 @@ const char *tok_alias[] = {
"lpart_hword",
"blank",
"tag",
"http",
"protocol",
"hword",
"lhword",
"nlhword",

View File

@ -17,7 +17,7 @@
#define LATPARTHYPHENWORD 11
#define SPACE 12
#define TAG 13
#define HTTP 14
#define PROTOCOL 14
#define HYPHENWORD 15
#define LATHYPHENWORD 16
#define CYRHYPHENWORD 17

File diff suppressed because it is too large Load Diff

View File

@ -1,10 +1,147 @@
#ifndef __PARSER_H__
#define __PARSER_H__
extern char *token;
extern int tokenlen;
int tsearch2_yylex(void);
void tsearch2_start_parse_str(char *, int);
void tsearch2_end_parse(void);
#include <ctype.h>
#include <limits.h>
#include "ts_locale.h"
typedef enum {
TPS_Base = 0,
TPS_InUWord,
TPS_InLatWord,
TPS_InCyrWord,
TPS_InUnsignedInt,
TPS_InSignedIntFirst,
TPS_InSignedInt,
TPS_InSpace,
TPS_InUDecimalFirst,
TPS_InUDecimal,
TPS_InDecimalFirst,
TPS_InDecimal,
TPS_InVersionFirst,
TPS_InVersion,
TPS_InMantissaFirst,
TPS_InMantissaSign,
TPS_InMantissa,
TPS_InHTMLEntityFirst,
TPS_InHTMLEntity,
TPS_InHTMLEntityNumFirst,
TPS_InHTMLEntityNum,
TPS_InHTMLEntityEnd,
TPS_InTagFirst,
TPS_InTagCloseFirst,
TPS_InTag,
TPS_InTagEscapeK,
TPS_InTagEscapeKK,
TPS_InTagBackSleshed,
TPS_InTagEnd,
TPS_InCommentFirst,
TPS_InCommentLast,
TPS_InComment,
TPS_InCloseCommentFirst,
TPS_InCloseCommentLast,
TPS_InCommentEnd,
TPS_InHostFirstDomen,
TPS_InHostDomenSecond,
TPS_InHostDomen,
TPS_InPortFirst,
TPS_InPort,
TPS_InHostFirstAN,
TPS_InHost,
TPS_InEmail,
TPS_InFileFirst,
TPS_InFile,
TPS_InFileNext,
TPS_InURIFirst,
TPS_InURIStart,
TPS_InURI,
TPS_InFURL,
TPS_InProtocolFirst,
TPS_InProtocolSecond,
TPS_InProtocolEnd,
TPS_InHyphenLatWordFirst,
TPS_InHyphenLatWord,
TPS_InHyphenCyrWordFirst,
TPS_InHyphenCyrWord,
TPS_InHyphenUWordFirst,
TPS_InHyphenUWord,
TPS_InHyphenValueFirst,
TPS_InHyphenValue,
TPS_InHyphenValueExact,
TPS_InParseHyphen,
TPS_InParseHyphenHyphen,
TPS_InHyphenCyrWordPart,
TPS_InHyphenLatWordPart,
TPS_InHyphenUWordPart,
TPS_InHyphenUnsignedInt,
TPS_InHDecimalPartFirst,
TPS_InHDecimalPart,
TPS_InHVersionPartFirst,
TPS_InHVersionPart,
TPS_Null /* last state (fake value) */
} TParserState;
/* forward declaration */
struct TParser;
typedef int (*TParserCharTest)(struct TParser*); /* any p_is* functions except p_iseq */
typedef void (*TParserSpecial)(struct TParser*); /* special handler for special cases... */
typedef struct {
TParserCharTest isclass;
char c;
uint16 flags;
TParserState tostate;
int type;
TParserSpecial special;
} TParserStateActionItem;
typedef struct {
TParserState state;
TParserStateActionItem *action;
} TParserStateAction;
typedef struct TParserPosition {
int posbyte; /* position of parser in bytes */
int poschar; /* osition of parser in characters */
int charlen; /* length of current char */
int lenbytelexeme;
int lencharlexeme;
TParserState state;
struct TParserPosition *prev;
int flags;
TParserStateActionItem *pushedAtAction;
} TParserPosition;
typedef struct TParser {
/* string and position information */
char *str; /* multibyte string */
int lenstr; /* length of mbstring */
wchar_t *wstr; /* wide character string */
int lenwstr; /* length of wsting */
/* State of parse */
int charmaxlen;
bool usewide;
TParserPosition *state;
bool ignore;
bool wanthost;
/* silly char */
char c;
/* out */
char *lexeme;
int lenbytelexeme;
int lencharlexeme;
int type;
} TParser;
TParser* TParserInit( char *, int );
bool TParserGet( TParser* );
void TParserClose( TParser* );
#endif

View File

@ -1,346 +0,0 @@
%{
#include "postgres.h"
#include "deflex.h"
#include "parser.h"
#include "common.h"
/* Avoid exit() on fatal scanner errors */
#undef fprintf
#define fprintf(file, fmt, msg) ts_error(ERROR, fmt, msg)
char *token = NULL; /* pointer to token */
int tokenlen;
static char *s = NULL; /* to return WHOLE hyphenated-word */
YY_BUFFER_STATE buf = NULL; /* buffer to parse; it need for parse from string */
typedef struct {
int tlen;
int clen;
char *str;
} TagStorage;
static TagStorage ts={0,0,NULL};
static void
addTag(void)
{
while( ts.clen+tsearch2_yyleng+1 > ts.tlen ) {
ts.tlen*=2;
ts.str=realloc(ts.str,ts.tlen);
if (!ts.str)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of memory")));
}
memcpy(ts.str+ts.clen,tsearch2_yytext,tsearch2_yyleng);
ts.clen+=tsearch2_yyleng;
ts.str[ts.clen]='\0';
}
static void
startTag(void)
{
if ( ts.str==NULL ) {
ts.tlen=tsearch2_yyleng+1;
ts.str=malloc(ts.tlen);
if (!ts.str)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of memory")));
}
ts.clen=0;
ts.str[0]='\0';
addTag();
}
%}
%option 8bit
%option never-interactive
%option nodefault
%option nounput
%option noyywrap
/* parser's state for parsing hyphenated-word */
%x DELIM
/* parser's state for parsing URL*/
%x URL
%x SERVER
/* parser's state for parsing TAGS */
%x INTAG
%x QINTAG
%x INCOMMENT
%x INSCRIPT
/* cyrillic koi8 char */
CYRALNUM [0-9\200-\377]
CYRALPHA [\200-\377]
ALPHA [a-zA-Z\200-\377]
ALNUM [0-9a-zA-Z\200-\377]
HOSTNAME ([-_[:alnum:]]+\.)+[[:alpha:]]+
URI [-_[:alnum:]/%,\.;=&?#]+
%%
"<"[Ss][Cc][Rr][Ii][Pp][Tt] { BEGIN INSCRIPT; startTag(); }
<INSCRIPT>"</"[Ss][Cc][Rr][Ii][Pp][Tt]">" {
BEGIN INITIAL;
addTag();
token = ts.str;
tokenlen = ts.clen;
return TAG;
}
"<!--" { BEGIN INCOMMENT; startTag(); }
<INCOMMENT>"-->" {
BEGIN INITIAL;
addTag();
token = ts.str;
tokenlen = ts.clen;
return TAG;
}
"<"[\![:alpha:]] { BEGIN INTAG; startTag(); }
"</"[[:alpha:]] { BEGIN INTAG; startTag(); }
<INTAG>"\"" { BEGIN QINTAG; addTag(); }
<QINTAG>"\\\"" { addTag(); }
<QINTAG>"\"" { BEGIN INTAG; addTag(); }
<INTAG>">" {
BEGIN INITIAL;
addTag();
token = ts.str;
tokenlen = ts.clen;
return TAG;
}
<QINTAG,INTAG,INCOMMENT,INSCRIPT>.|\n { addTag(); }
\&(quot|amp|nbsp|lt|gt)\; {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return HTMLENTITY;
}
\&\#[0-9][0-9]?[0-9]?\; {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return HTMLENTITY;
}
[-_\.[:alnum:]]+@{HOSTNAME} /* Emails */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return EMAIL;
}
[+-]?[0-9]+(\.[0-9]+)?[eEdD][+-]?[0-9]+ /* float */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return SCIENTIFIC;
}
[0-9]+\.[0-9]+\.[0-9\.]*[0-9] {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return VERSIONNUMBER;
}
[+-]?[0-9]+\.[0-9]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return DECIMAL;
}
[+-][0-9]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return SIGNEDINT;
}
<DELIM,INITIAL>[0-9]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return UNSIGNEDINT;
}
http"://" {
BEGIN URL;
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return HTTP;
}
ftp"://" {
BEGIN URL;
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return HTTP;
}
<URL,INITIAL>{HOSTNAME}[/:]{URI} {
BEGIN SERVER;
if (s) { free(s); s=NULL; }
s = strdup( tsearch2_yytext );
tokenlen = tsearch2_yyleng;
yyless( 0 );
token = s;
return FURL;
}
<SERVER,URL,INITIAL>{HOSTNAME} {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return HOST;
}
<SERVER>[/:]{URI} {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return URI;
}
[[:alnum:]\./_-]+"/"[[:alnum:]\./_-]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return FILEPATH;
}
({CYRALPHA}+-)+{CYRALPHA}+ /* composite-word */ {
BEGIN DELIM;
if (s) { free(s); s=NULL; }
s = strdup( tsearch2_yytext );
tokenlen = tsearch2_yyleng;
yyless( 0 );
token = s;
return CYRHYPHENWORD;
}
([[:alpha:]]+-)+[[:alpha:]]+ /* composite-word */ {
BEGIN DELIM;
if (s) { free(s); s=NULL; }
s = strdup( tsearch2_yytext );
tokenlen = tsearch2_yyleng;
yyless( 0 );
token = s;
return LATHYPHENWORD;
}
({ALNUM}+-)+{ALNUM}+ /* composite-word */ {
BEGIN DELIM;
if (s) { free(s); s=NULL; }
s = strdup( tsearch2_yytext );
tokenlen = tsearch2_yyleng;
yyless( 0 );
token = s;
return HYPHENWORD;
}
<DELIM>[0-9]+\.[0-9]+\.[0-9\.]*[0-9] {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return VERSIONNUMBER;
}
<DELIM>\+?[0-9]+\.[0-9]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return DECIMAL;
}
<DELIM>{CYRALPHA}+ /* one word in composite-word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return CYRPARTHYPHENWORD;
}
<DELIM>[[:alpha:]]+ /* one word in composite-word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return LATPARTHYPHENWORD;
}
<DELIM>{ALNUM}+ /* one word in composite-word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return PARTHYPHENWORD;
}
<DELIM>- {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return SPACE;
}
<DELIM,SERVER,URL>.|\n /* return in basic state */ {
BEGIN INITIAL;
yyless( 0 );
}
{CYRALPHA}+ /* normal word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return CYRWORD;
}
[[:alpha:]]+ /* normal word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return LATWORD;
}
{ALNUM}+ /* normal word */ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return UWORD;
}
[ \r\n\t]+ {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return SPACE;
}
. {
token = tsearch2_yytext;
tokenlen = tsearch2_yyleng;
return SPACE;
}
%%
/* clearing after parsing from string */
void
tsearch2_end_parse(void)
{
if (s)
{
free(s);
s = NULL;
}
tsearch2_yy_delete_buffer( buf );
buf = NULL;
}
/* start parse from string */
void
tsearch2_start_parse_str(char* str, int limit)
{
if (buf)
tsearch2_end_parse();
buf = tsearch2_yy_scan_bytes( str, limit );
tsearch2_yy_switch_to_buffer( buf );
BEGIN INITIAL;
}

View File

@ -39,8 +39,7 @@ Datum prsd_start(PG_FUNCTION_ARGS);
Datum
prsd_start(PG_FUNCTION_ARGS)
{
tsearch2_start_parse_str((char *) PG_GETARG_POINTER(0), PG_GETARG_INT32(1));
PG_RETURN_POINTER(NULL);
PG_RETURN_POINTER(TParserInit( (char *) PG_GETARG_POINTER(0), PG_GETARG_INT32(1)));
}
PG_FUNCTION_INFO_V1(prsd_getlexeme);
@ -48,14 +47,17 @@ Datum prsd_getlexeme(PG_FUNCTION_ARGS);
Datum
prsd_getlexeme(PG_FUNCTION_ARGS)
{
/* ParserState *p=(ParserState*)PG_GETARG_POINTER(0); */
TParser *p=(TParser*)PG_GETARG_POINTER(0);
char **t = (char **) PG_GETARG_POINTER(1);
int *tlen = (int *) PG_GETARG_POINTER(2);
int type = tsearch2_yylex();
*t = token;
*tlen = tokenlen;
PG_RETURN_INT32(type);
if ( !TParserGet(p) )
PG_RETURN_INT32(0);
*t = p->lexeme;
*tlen = p->lenbytelexeme;
PG_RETURN_INT32(p->type);
}
PG_FUNCTION_INFO_V1(prsd_end);
@ -63,8 +65,8 @@ Datum prsd_end(PG_FUNCTION_ARGS);
Datum
prsd_end(PG_FUNCTION_ARGS)
{
/* ParserState *p=(ParserState*)PG_GETARG_POINTER(0); */
tsearch2_end_parse();
TParser *p=(TParser*)PG_GETARG_POINTER(0);
TParserClose(p);
PG_RETURN_VOID();
}