Hi Aleksandr,
I agree with Aleksander about silencing all errors in
websearch_to_tsquery().
In the attachment is a revised patch with the attempt to introduce an
ability to ignore syntax errors in gettoken_tsvector().
Thanks for the further improvements! Yes, you're both right, the API has
to be consistent. Unfortunately, I had to make some adjustments
according to Oleg Bartunov's review. Here's a change log:
1. &, | and (), <-> are no longer considered operators in web search
mode.
2. I've stumbled upon a bug: web search used to transform "pg_class"
into 'pg <-> class', which is no longer the case.
3. I changed the behavior of gettoken_tsvector() as soon as I had heard
from Aleksander Alekseev, so I decided to use my implementation in this
revision of the patch. This is a good subject for discussion, though.
Feel free to share your opinion.
4. As suggested by Theodor, I've replaced some bool args with bit flags.
The name of enum ts_parsestate looks more like a name of the function
than a name of a type.
In my version, it renamed to QueryParserState, but you can fix it if
I'm wrong.
True, but gettoken_query() returns ts_tokentype, so I decided to use
this naming scheme.
--
Dmitry Ivanov
Postgres Professional: http://www.postgrespro.com
The Russian Postgres Company
diff --git a/src/backend/tsearch/to_tsany.c b/src/backend/tsearch/to_tsany.c
index ea5947a3a8..6055fb6b4e 100644
--- a/src/backend/tsearch/to_tsany.c
+++ b/src/backend/tsearch/to_tsany.c
@@ -490,7 +490,7 @@ to_tsquery_byid(PG_FUNCTION_ARGS)
query = parse_tsquery(text_to_cstring(in),
pushval_morph,
PointerGetDatum(&data),
- false);
+ 0);
PG_RETURN_TSQUERY(query);
}
@@ -520,7 +520,7 @@ plainto_tsquery_byid(PG_FUNCTION_ARGS)
query = parse_tsquery(text_to_cstring(in),
pushval_morph,
PointerGetDatum(&data),
- true);
+ P_TSQ_PLAIN);
PG_RETURN_POINTER(query);
}
@@ -551,7 +551,7 @@ phraseto_tsquery_byid(PG_FUNCTION_ARGS)
query = parse_tsquery(text_to_cstring(in),
pushval_morph,
PointerGetDatum(&data),
- true);
+ P_TSQ_PLAIN);
PG_RETURN_TSQUERY(query);
}
@@ -567,3 +567,35 @@ phraseto_tsquery(PG_FUNCTION_ARGS)
ObjectIdGetDatum(cfgId),
PointerGetDatum(in)));
}
+
+Datum
+websearch_to_tsquery_byid(PG_FUNCTION_ARGS)
+{
+ text *in = PG_GETARG_TEXT_PP(1);
+ MorphOpaque data;
+ TSQuery query = NULL;
+
+ data.cfg_id = PG_GETARG_OID(0);
+
+ data.qoperator = OP_AND;
+
+ query = parse_tsquery(text_to_cstring(in),
+ pushval_morph,
+ PointerGetDatum(&data),
+ P_TSQ_WEB);
+
+ PG_RETURN_TSQUERY(query);
+}
+
+Datum
+websearch_to_tsquery(PG_FUNCTION_ARGS)
+{
+ text *in = PG_GETARG_TEXT_PP(0);
+ Oid cfgId;
+
+ cfgId = getTSCurrentConfig(true);
+ PG_RETURN_DATUM(DirectFunctionCall2(websearch_to_tsquery_byid,
+ ObjectIdGetDatum(cfgId),
+ PointerGetDatum(in)));
+
+}
diff --git a/src/backend/utils/adt/tsquery.c b/src/backend/utils/adt/tsquery.c
index 1ccbf79030..695bdb89e9 100644
--- a/src/backend/utils/adt/tsquery.c
+++ b/src/backend/utils/adt/tsquery.c
@@ -32,14 +32,27 @@ const int tsearch_op_priority[OP_COUNT] =
3 /* OP_PHRASE */
};
+/*
+ * parser's states
+ */
+typedef enum
+{
+ WAITOPERAND = 1,
+ WAITOPERATOR = 2,
+ WAITFIRSTOPERAND = 3,
+ WAITSINGLEOPERAND = 4
+} ts_parserstate;
+
struct TSQueryParserStateData
{
/* State for gettoken_query */
char *buffer; /* entire string we are scanning */
char *buf; /* current scan point */
- int state;
int count; /* nesting count, incremented by (,
* decremented by ) */
+ bool in_quotes; /* phrase in quotes "" */
+ bool is_web; /* is it a web search? */
+ ts_parserstate state;
/* polish (prefix) notation in list, filled in by push* functions */
List *polstr;
@@ -57,12 +70,6 @@ struct TSQueryParserStateData
TSVectorParseState valstate;
};
-/* parser's states */
-#define WAITOPERAND 1
-#define WAITOPERATOR 2
-#define WAITFIRSTOPERAND 3
-#define WAITSINGLEOPERAND 4
-
/*
* subroutine to parse the modifiers (weight and prefix flag currently)
* part, like ':AB*' of a query.
@@ -197,6 +204,26 @@ err:
return buf;
}
+/*
+ * Parse OR operator used in websearch_to_tsquery().
+ */
+static bool
+parse_or_operator(TSQueryParserState state)
+{
+ char *buf = state->buf;
+
+ if (state->in_quotes)
+ return false;
+
+ return (t_iseq(&buf[0], 'o') || t_iseq(&buf[0], 'O')) &&
+ (t_iseq(&buf[1], 'r') || t_iseq(&buf[1], 'R')) &&
+ (buf[2] != '\0' &&
+ !t_iseq(&buf[2], '-') &&
+ !t_iseq(&buf[2], '_') &&
+ !t_isalpha(&buf[2]) &&
+ !t_isdigit(&buf[2]));
+}
+
/*
* token types for parsing
*/
@@ -219,10 +246,12 @@ typedef enum
*
*/
static ts_tokentype
-gettoken_query(TSQueryParserState state,
- int8 *operator,
- int *lenval, char **strval, int16 *weight, bool *prefix)
+gettoken_query(TSQueryParserState state, int8 *operator,
+ int *lenval, char **strval,
+ int16 *weight, bool *prefix)
{
+ bool is_web = state->is_web;
+
*weight = 0;
*prefix = false;
@@ -232,28 +261,63 @@ gettoken_query(TSQueryParserState state,
{
case WAITFIRSTOPERAND:
case WAITOPERAND:
- if (t_iseq(state->buf, '!'))
+ if ((! is_web && t_iseq(state->buf, '!')) ||
+ (is_web && t_iseq(state->buf, '-')))
{
- (state->buf)++; /* can safely ++, t_iseq guarantee that
- * pg_mblen()==1 */
+ state->buf++;
+
+ if (state->in_quotes)
+ continue;
+
*operator = OP_NOT;
state->state = WAITOPERAND;
return PT_OPR;
}
else if (t_iseq(state->buf, '('))
{
+ state->buf++;
+
+ if (is_web)
+ continue;
+
state->count++;
- (state->buf)++;
state->state = WAITOPERAND;
return PT_OPEN;
}
else if (t_iseq(state->buf, ':'))
{
+ state->buf++;
+
+ if (is_web)
+ continue;
+
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error in tsquery: \"%s\"",
state->buffer)));
}
+ else if (is_web && t_iseq(state->buf, '"'))
+ {
+ state->buf++;
+
+ /* web search tolerates missing quotes */
+ if (!state->in_quotes && strchr(state->buf, '"'))
+ {
+ /* quoted text should be ordered <-> */
+ state->in_quotes = true;
+ state->state = WAITOPERAND;
+ }
+ else
+ state->in_quotes = false;
+
+ continue;
+ }
+ else if (is_web && ISOPERATOR(state->buf))
+ {
+ /* or else gettoken_tsvector() will raise an error */
+ state->buf++;
+ continue;
+ }
else if (!t_isspace(state->buf))
{
/*
@@ -263,12 +327,22 @@ gettoken_query(TSQueryParserState state,
reset_tsvector_parser(state->valstate, state->buf);
if (gettoken_tsvector(state->valstate, strval, lenval, NULL, NULL, &state->buf))
{
- state->buf = get_modifiers(state->buf, weight, prefix);
+ if (!is_web)
+ {
+ /* web search does not support weights */
+ state->buf = get_modifiers(state->buf, weight, prefix);
+ }
state->state = WAITOPERATOR;
return PT_VAL;
}
else if (state->state == WAITFIRSTOPERAND)
return PT_END;
+ else if (is_web)
+ {
+ /* finally, we have to provide an operand */
+ pushStop(state);
+ return PT_END;
+ }
else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
@@ -277,40 +351,95 @@ gettoken_query(TSQueryParserState state,
}
break;
case WAITOPERATOR:
- if (t_iseq(state->buf, '&'))
+ if (! is_web && t_iseq(state->buf, '&'))
{
+ state->buf++;
state->state = WAITOPERAND;
*operator = OP_AND;
- (state->buf)++;
return PT_OPR;
}
- else if (t_iseq(state->buf, '|'))
+ else if (! is_web && t_iseq(state->buf, '|'))
{
+ state->buf++;
state->state = WAITOPERAND;
*operator = OP_OR;
- (state->buf)++;
return PT_OPR;
}
- else if (t_iseq(state->buf, '<'))
+ else if (! is_web && t_iseq(state->buf, '<'))
{
- state->state = WAITOPERAND;
- *operator = OP_PHRASE;
/* weight var is used as storage for distance */
state->buf = parse_phrase_operator(state->buf, weight);
+ state->state = WAITOPERAND;
+ *operator = OP_PHRASE;
if (*weight < 0)
return PT_ERR;
return PT_OPR;
}
- else if (t_iseq(state->buf, ')'))
+ else if (! is_web && t_iseq(state->buf, ')'))
{
- (state->buf)++;
+ state->buf++;
state->count--;
return (state->count < 0) ? PT_ERR : PT_CLOSE;
}
+ else if (is_web && t_iseq(state->buf, '"'))
+ {
+ state->buf++;
+
+ /* web search tolerates missing quotes */
+ if (!state->in_quotes && strchr(state->buf, '"'))
+ {
+ /* quoted text should be ordered <-> */
+ state->in_quotes = true;
+ state->state = WAITOPERAND;
+
+ /* put implicit AND after an operand */
+ *operator = OP_AND;
+ return PT_OPR;
+ }
+ else
+ state->in_quotes = false;
+
+ continue;
+ }
+ else if (is_web && parse_or_operator(state))
+ {
+ state->buf += 2; /* strlen("OR") */
+ state->state = WAITOPERAND;
+ *operator = OP_OR;
+ return PT_OPR;
+ }
+ else if (is_web && ISOPERATOR(state->buf))
+ {
+ /* just skip disabled operators */
+ state->buf++;
+ continue;
+ }
else if (*(state->buf) == '\0')
- return (state->count) ? PT_ERR : PT_END;
+ {
+ /* web search tolerates unexpected end of line */
+ return (!is_web && state->count) ? PT_ERR : PT_END;
+ }
else if (!t_isspace(state->buf))
+ {
+ if (is_web)
+ {
+ if (state->in_quotes)
+ {
+ /* put implicit <-> after an operand */
+ *operator = OP_PHRASE;
+ *weight = 1;
+ }
+ else
+ {
+ /* put implicit AND after an operand */
+ *operator = OP_AND;
+ }
+
+ state->state = WAITOPERAND;
+ return PT_OPR;
+ }
return PT_ERR;
+ }
break;
case WAITSINGLEOPERAND:
if (*(state->buf) == '\0')
@@ -320,9 +449,6 @@ gettoken_query(TSQueryParserState state,
state->buf += strlen(state->buf);
state->count++;
return PT_VAL;
- default:
- return PT_ERR;
- break;
}
state->buf += pg_mblen(state->buf);
}
@@ -605,7 +731,7 @@ TSQuery
parse_tsquery(char *buf,
PushFunction pushval,
Datum opaque,
- bool isplain)
+ int flags)
{
struct TSQueryParserStateData state;
int i;
@@ -613,17 +739,28 @@ parse_tsquery(char *buf,
int commonlen;
QueryItem *ptr;
ListCell *cell;
- bool needcleanup;
+ bool needcleanup,
+ is_plain,
+ is_web;
+ int tsv_flags = P_TSV_OPR_IS_DELIM | P_TSV_IS_TSQUERY;
+
+ is_plain = (flags & P_TSQ_PLAIN) != 0;
+ is_web = (flags & P_TSQ_WEB) != 0;
+
+ if (is_web)
+ tsv_flags |= P_TSV_IS_WEB;
/* init state */
state.buffer = buf;
state.buf = buf;
- state.state = (isplain) ? WAITSINGLEOPERAND : WAITFIRSTOPERAND;
state.count = 0;
+ state.in_quotes = false;
+ state.is_web = is_web;
+ state.state = is_plain ? WAITSINGLEOPERAND : WAITFIRSTOPERAND;
state.polstr = NIL;
/* init value parser's state */
- state.valstate = init_tsvector_parser(state.buffer, true, true);
+ state.valstate = init_tsvector_parser(state.buffer, tsv_flags);
/* init list of operand */
state.sumlen = 0;
@@ -716,7 +853,7 @@ tsqueryin(PG_FUNCTION_ARGS)
{
char *in = PG_GETARG_CSTRING(0);
- PG_RETURN_TSQUERY(parse_tsquery(in, pushval_asis, PointerGetDatum(NULL), false));
+ PG_RETURN_TSQUERY(parse_tsquery(in, pushval_asis, PointerGetDatum(NULL), 0));
}
/*
diff --git a/src/backend/utils/adt/tsvector.c b/src/backend/utils/adt/tsvector.c
index 64e02ef434..7a27bd12a3 100644
--- a/src/backend/utils/adt/tsvector.c
+++ b/src/backend/utils/adt/tsvector.c
@@ -200,7 +200,7 @@ tsvectorin(PG_FUNCTION_ARGS)
char *cur;
int buflen = 256; /* allocated size of tmpbuf */
- state = init_tsvector_parser(buf, false, false);
+ state = init_tsvector_parser(buf, 0);
arrlen = 64;
arr = (WordEntryIN *) palloc(sizeof(WordEntryIN) * arrlen);
diff --git a/src/backend/utils/adt/tsvector_parser.c b/src/backend/utils/adt/tsvector_parser.c
index 7367ba6a40..fed411a842 100644
--- a/src/backend/utils/adt/tsvector_parser.c
+++ b/src/backend/utils/adt/tsvector_parser.c
@@ -33,6 +33,7 @@ struct TSVectorParseStateData
int eml; /* max bytes per character */
bool oprisdelim; /* treat ! | * ( ) as delimiters? */
bool is_tsquery; /* say "tsquery" not "tsvector" in errors? */
+ bool is_web; /* we're in websearch_to_tsquery() */
};
@@ -42,7 +43,7 @@ struct TSVectorParseStateData
* ! | & ( )
*/
TSVectorParseState
-init_tsvector_parser(char *input, bool oprisdelim, bool is_tsquery)
+init_tsvector_parser(char *input, int flags)
{
TSVectorParseState state;
@@ -52,8 +53,9 @@ init_tsvector_parser(char *input, bool oprisdelim, bool is_tsquery)
state->len = 32;
state->word = (char *) palloc(state->len);
state->eml = pg_database_encoding_max_length();
- state->oprisdelim = oprisdelim;
- state->is_tsquery = is_tsquery;
+ state->oprisdelim = (flags & P_TSV_OPR_IS_DELIM) != 0;
+ state->is_tsquery = (flags & P_TSV_IS_TSQUERY) != 0;
+ state->is_web = (flags & P_TSV_IS_WEB) != 0;
return state;
}
@@ -89,16 +91,6 @@ do { \
} \
} while (0)
-/* phrase operator begins with '<' */
-#define ISOPERATOR(x) \
- ( pg_mblen(x) == 1 && ( *(x) == '!' || \
- *(x) == '&' || \
- *(x) == '|' || \
- *(x) == '(' || \
- *(x) == ')' || \
- *(x) == '<' \
- ) )
-
/* Fills gettoken_tsvector's output parameters, and returns true */
#define RETURN_TOKEN \
do { \
@@ -183,14 +175,15 @@ gettoken_tsvector(TSVectorParseState state,
{
if (*(state->prsbuf) == '\0')
return false;
- else if (t_iseq(state->prsbuf, '\''))
+ else if (!state->is_web && t_iseq(state->prsbuf, '\''))
statecode = WAITENDCMPLX;
- else if (t_iseq(state->prsbuf, '\\'))
+ else if (!state->is_web && t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
- else if (state->oprisdelim && ISOPERATOR(state->prsbuf))
+ else if ((state->oprisdelim && ISOPERATOR(state->prsbuf)) ||
+ (state->is_web && t_iseq(state->prsbuf, '"')))
PRSSYNTAXERROR;
else if (!t_isspace(state->prsbuf))
{
@@ -217,13 +210,14 @@ gettoken_tsvector(TSVectorParseState state,
}
else if (statecode == WAITENDWORD)
{
- if (t_iseq(state->prsbuf, '\\'))
+ if (!state->is_web && t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
else if (t_isspace(state->prsbuf) || *(state->prsbuf) == '\0' ||
- (state->oprisdelim && ISOPERATOR(state->prsbuf)))
+ (state->oprisdelim && ISOPERATOR(state->prsbuf)) ||
+ (state->is_web && t_iseq(state->prsbuf, '"')))
{
RESIZEPRSBUF;
if (curpos == state->word)
@@ -250,11 +244,11 @@ gettoken_tsvector(TSVectorParseState state,
}
else if (statecode == WAITENDCMPLX)
{
- if (t_iseq(state->prsbuf, '\''))
+ if (!state->is_web && t_iseq(state->prsbuf, '\''))
{
statecode = WAITCHARCMPLX;
}
- else if (t_iseq(state->prsbuf, '\\'))
+ else if (!state->is_web && t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDCMPLX;
@@ -270,7 +264,7 @@ gettoken_tsvector(TSVectorParseState state,
}
else if (statecode == WAITCHARCMPLX)
{
- if (t_iseq(state->prsbuf, '\''))
+ if (!state->is_web && t_iseq(state->prsbuf, '\''))
{
RESIZEPRSBUF;
COPYCHAR(curpos, state->prsbuf);
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index bfc90098f8..00f1a85ae7 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -4950,6 +4950,8 @@ DATA(insert OID = 3747 ( plainto_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f i s
DESCR("transform to tsquery");
DATA(insert OID = 5006 ( phraseto_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f i s 2 0 3615 "3734 25" _null_ _null_ _null_ _null_ _null_ phraseto_tsquery_byid _null_ _null_ _null_ ));
DESCR("transform to tsquery");
+DATA(insert OID = 8889 ( websearch_to_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f i s 2 0 3615 "3734 25" _null_ _null_ _null_ _null_ _null_ websearch_to_tsquery_byid _null_ _null_ _null_ ));
+DESCR("transform to tsquery");
DATA(insert OID = 3749 ( to_tsvector PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3614 "25" _null_ _null_ _null_ _null_ _null_ to_tsvector _null_ _null_ _null_ ));
DESCR("transform to tsvector");
DATA(insert OID = 3750 ( to_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3615 "25" _null_ _null_ _null_ _null_ _null_ to_tsquery _null_ _null_ _null_ ));
@@ -4958,6 +4960,8 @@ DATA(insert OID = 3751 ( plainto_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f s s
DESCR("transform to tsquery");
DATA(insert OID = 5001 ( phraseto_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3615 "25" _null_ _null_ _null_ _null_ _null_ phraseto_tsquery _null_ _null_ _null_ ));
DESCR("transform to tsquery");
+DATA(insert OID = 8890 ( websearch_to_tsquery PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3615 "25" _null_ _null_ _null_ _null_ _null_ websearch_to_tsquery _null_ _null_ _null_ ));
+DESCR("transform to tsquery");
DATA(insert OID = 4209 ( to_tsvector PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3614 "3802" _null_ _null_ _null_ _null_ _null_ jsonb_to_tsvector _null_ _null_ _null_ ));
DESCR("transform jsonb to tsvector");
DATA(insert OID = 4210 ( to_tsvector PGNSP PGUID 12 100 0 0 0 f f f t f s s 1 0 3614 "114" _null_ _null_ _null_ _null_ _null_ json_to_tsvector _null_ _null_ _null_ ));
diff --git a/src/include/tsearch/ts_utils.h b/src/include/tsearch/ts_utils.h
index f8ddce5ecb..73e969fe9c 100644
--- a/src/include/tsearch/ts_utils.h
+++ b/src/include/tsearch/ts_utils.h
@@ -25,9 +25,11 @@
struct TSVectorParseStateData; /* opaque struct in tsvector_parser.c */
typedef struct TSVectorParseStateData *TSVectorParseState;
-extern TSVectorParseState init_tsvector_parser(char *input,
- bool oprisdelim,
- bool is_tsquery);
+#define P_TSV_OPR_IS_DELIM (1 << 0)
+#define P_TSV_IS_TSQUERY (1 << 1)
+#define P_TSV_IS_WEB (1 << 2)
+
+extern TSVectorParseState init_tsvector_parser(char *input, int flags);
extern void reset_tsvector_parser(TSVectorParseState state, char *input);
extern bool gettoken_tsvector(TSVectorParseState state,
char **token, int *len,
@@ -35,6 +37,16 @@ extern bool gettoken_tsvector(TSVectorParseState state,
char **endptr);
extern void close_tsvector_parser(TSVectorParseState state);
+/* phrase operator begins with '<' */
+#define ISOPERATOR(x) \
+ ( pg_mblen(x) == 1 && ( *(x) == '!' || \
+ *(x) == '&' || \
+ *(x) == '|' || \
+ *(x) == '(' || \
+ *(x) == ')' || \
+ *(x) == '<' \
+ ) )
+
/* parse_tsquery */
struct TSQueryParserStateData; /* private in backend/utils/adt/tsquery.c */
@@ -46,9 +58,13 @@ typedef void (*PushFunction) (Datum opaque, TSQueryParserState state,
* QueryOperand struct */
bool prefix);
+#define P_TSQ_PLAIN (1 << 0)
+#define P_TSQ_WEB (1 << 1)
+
extern TSQuery parse_tsquery(char *buf,
- PushFunction pushval,
- Datum opaque, bool isplain);
+ PushFunction pushval,
+ Datum opaque,
+ int flags);
/* Functions for use by PushFunction implementations */
extern void pushValue(TSQueryParserState state,
diff --git a/src/test/regress/expected/tsearch.out b/src/test/regress/expected/tsearch.out
index d63fb12f1d..2b1da308df 100644
--- a/src/test/regress/expected/tsearch.out
+++ b/src/test/regress/expected/tsearch.out
@@ -1672,3 +1672,325 @@ select * from phrase_index_test where fts @@ phraseto_tsquery('english', 'fat ca
(1 row)
set enable_seqscan = on;
+-- test websearch_to_tsquery function
+select websearch_to_tsquery('simple', 'I have a fat:*ABCD cat');
+ websearch_to_tsquery
+---------------------------------------------
+ 'i' & 'have' & 'a' & 'fat' & 'abcd' & 'cat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'orange:**AABBCCDD');
+ websearch_to_tsquery
+-----------------------
+ 'orange' & 'aabbccdd'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat:A!cat:B|rat:C<');
+ websearch_to_tsquery
+-----------------------------------------
+ 'fat' & 'a' & 'cat' & 'b' & 'rat' & 'c'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat:A : cat:B');
+ websearch_to_tsquery
+---------------------------
+ 'fat' & 'a' & 'cat' & 'b'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc : def');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'def'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc:def');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'def'
+(1 row)
+
+select websearch_to_tsquery('simple', 'a:::b');
+ websearch_to_tsquery
+----------------------
+ 'a' & 'b'
+(1 row)
+
+select websearch_to_tsquery('simple', ':');
+NOTICE: text-search query doesn't contain lexemes: ":"
+ websearch_to_tsquery
+----------------------
+
+(1 row)
+
+select websearch_to_tsquery('english', 'My brand new smartphone');
+ websearch_to_tsquery
+-------------------------------
+ 'brand' & 'new' & 'smartphon'
+(1 row)
+
+select websearch_to_tsquery('english', 'My brand "new smartphone"');
+ websearch_to_tsquery
+---------------------------------
+ 'brand' & 'new' <-> 'smartphon'
+(1 row)
+
+select websearch_to_tsquery('english', 'My brand "new -smartphone"');
+ websearch_to_tsquery
+---------------------------------
+ 'brand' & 'new' <-> 'smartphon'
+(1 row)
+
+select websearch_to_tsquery('english', 'My brand:B "new -smartphone"');
+ websearch_to_tsquery
+---------------------------------------
+ 'brand' & 'b' & 'new' <-> 'smartphon'
+(1 row)
+
+select websearch_to_tsquery('simple', 'cat or rat');
+ websearch_to_tsquery
+----------------------
+ 'cat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'cat OR rat');
+ websearch_to_tsquery
+----------------------
+ 'cat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'cat "OR" rat');
+ websearch_to_tsquery
+----------------------
+ 'cat' & 'or' & 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'cat OR');
+ websearch_to_tsquery
+----------------------
+ 'cat' & 'or'
+(1 row)
+
+select websearch_to_tsquery('simple', 'OR rat');
+ websearch_to_tsquery
+----------------------
+ 'or' & 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', '"fat cat OR rat"');
+ websearch_to_tsquery
+------------------------------------
+ 'fat' <-> 'cat' <-> 'or' <-> 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat (cat OR rat');
+ websearch_to_tsquery
+-----------------------
+ 'fat' & 'cat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat*rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' & 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat-rat');
+ websearch_to_tsquery
+---------------------------
+ 'fat-rat' & 'fat' & 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat_rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' & 'rat'
+(1 row)
+
+-- OR is an operator here ...
+select websearch_to_tsquery('simple', '"fat cat"or"fat rat"');
+ websearch_to_tsquery
+-----------------------------------
+ 'fat' <-> 'cat' | 'fat' <-> 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or(rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or)rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or&rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or|rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or!rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or<rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or>rat');
+ websearch_to_tsquery
+----------------------
+ 'fat' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('simple', 'fat or ');
+ websearch_to_tsquery
+----------------------
+ 'fat'
+(1 row)
+
+-- ... but not here
+select websearch_to_tsquery('simple', 'abc orange');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'orange'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc orÑеÑÑ');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'orÑеÑÑ'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc OR1234');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'or1234'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc or-abc');
+ websearch_to_tsquery
+---------------------------------
+ 'abc' & 'or-abc' & 'or' & 'abc'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc OR_abc');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'or' & 'abc'
+(1 row)
+
+select websearch_to_tsquery('simple', 'abc or');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'or'
+(1 row)
+
+select websearch_to_tsquery('simple', 'or OR or');
+ websearch_to_tsquery
+----------------------
+ 'or' | 'or'
+(1 row)
+
+select websearch_to_tsquery('english', '"A fat cat" has just eaten a -rat.');
+ websearch_to_tsquery
+------------------------------------
+ 'fat' <-> 'cat' & 'eaten' & !'rat'
+(1 row)
+
+select websearch_to_tsquery('english', '"A fat cat" has just eaten OR !rat.');
+ websearch_to_tsquery
+-----------------------------------
+ 'fat' <-> 'cat' & 'eaten' | 'rat'
+(1 row)
+
+select websearch_to_tsquery('english', '"A fat cat" has just (+eaten OR -rat)');
+ websearch_to_tsquery
+------------------------------------
+ 'fat' <-> 'cat' & 'eaten' | !'rat'
+(1 row)
+
+select websearch_to_tsquery('english', 'this is ----fine');
+ websearch_to_tsquery
+----------------------
+ !!!!'fine'
+(1 row)
+
+select websearch_to_tsquery('english', '(()) )))) this ||| is && -fine, "dear friend" OR good');
+ websearch_to_tsquery
+----------------------------------------
+ !'fine' & 'dear' <-> 'friend' | 'good'
+(1 row)
+
+select websearch_to_tsquery('english', 'an old <-> cat " is fine &&& too');
+ websearch_to_tsquery
+------------------------
+ 'old' & 'cat' & 'fine'
+(1 row)
+
+select websearch_to_tsquery('english', '"A the" OR just on');
+NOTICE: text-search query contains only stop words or doesn't contain lexemes, ignored
+ websearch_to_tsquery
+----------------------
+
+(1 row)
+
+select websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+ websearch_to_tsquery
+--------------------------------------
+ 'ÑолÑÑ' <-> 'коÑк' & 'ÑÑел' & 'кÑÑÑ'
+(1 row)
+
+select to_tsvector('russian', 'ÑÑела ÑолÑÑÐ°Ñ ÐºÐ¾Ñка кÑÑÑÑ') @@
+websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+ ?column?
+----------
+ t
+(1 row)
+
+select to_tsvector('russian', 'ÑÑела ÑолÑÑÐ°Ñ ÑеÑÐ°Ñ ÐºÐ¾Ñка кÑÑÑÑ') @@
+websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+ ?column?
+----------
+ f
+(1 row)
+
+-- cases handled by gettoken_tsvector()
+select websearch_to_tsquery('''');
+NOTICE: text-search query contains only stop words or doesn't contain lexemes, ignored
+ websearch_to_tsquery
+----------------------
+
+(1 row)
+
+select websearch_to_tsquery('''abc''''def''');
+ websearch_to_tsquery
+----------------------
+ 'abc' & 'def'
+(1 row)
+
+select websearch_to_tsquery('\abc');
+ websearch_to_tsquery
+----------------------
+ 'abc'
+(1 row)
+
+select websearch_to_tsquery('\');
+NOTICE: text-search query contains only stop words or doesn't contain lexemes, ignored
+ websearch_to_tsquery
+----------------------
+
+(1 row)
+
diff --git a/src/test/regress/sql/tsearch.sql b/src/test/regress/sql/tsearch.sql
index 1c8520b3e9..da8d089100 100644
--- a/src/test/regress/sql/tsearch.sql
+++ b/src/test/regress/sql/tsearch.sql
@@ -539,3 +539,75 @@ create index phrase_index_test_idx on phrase_index_test using gin(fts);
set enable_seqscan = off;
select * from phrase_index_test where fts @@ phraseto_tsquery('english', 'fat cat');
set enable_seqscan = on;
+
+-- test websearch_to_tsquery function
+select websearch_to_tsquery('simple', 'I have a fat:*ABCD cat');
+select websearch_to_tsquery('simple', 'orange:**AABBCCDD');
+select websearch_to_tsquery('simple', 'fat:A!cat:B|rat:C<');
+select websearch_to_tsquery('simple', 'fat:A : cat:B');
+
+select websearch_to_tsquery('simple', 'abc : def');
+select websearch_to_tsquery('simple', 'abc:def');
+select websearch_to_tsquery('simple', 'a:::b');
+select websearch_to_tsquery('simple', ':');
+
+select websearch_to_tsquery('english', 'My brand new smartphone');
+select websearch_to_tsquery('english', 'My brand "new smartphone"');
+select websearch_to_tsquery('english', 'My brand "new -smartphone"');
+select websearch_to_tsquery('english', 'My brand:B "new -smartphone"');
+
+select websearch_to_tsquery('simple', 'cat or rat');
+select websearch_to_tsquery('simple', 'cat OR rat');
+select websearch_to_tsquery('simple', 'cat "OR" rat');
+select websearch_to_tsquery('simple', 'cat OR');
+select websearch_to_tsquery('simple', 'OR rat');
+
+select websearch_to_tsquery('simple', '"fat cat OR rat"');
+select websearch_to_tsquery('simple', 'fat (cat OR rat');
+select websearch_to_tsquery('simple', 'fat*rat');
+select websearch_to_tsquery('simple', 'fat-rat');
+select websearch_to_tsquery('simple', 'fat_rat');
+
+-- OR is an operator here ...
+select websearch_to_tsquery('simple', '"fat cat"or"fat rat"');
+select websearch_to_tsquery('simple', 'fat or(rat');
+select websearch_to_tsquery('simple', 'fat or)rat');
+select websearch_to_tsquery('simple', 'fat or&rat');
+select websearch_to_tsquery('simple', 'fat or|rat');
+select websearch_to_tsquery('simple', 'fat or!rat');
+select websearch_to_tsquery('simple', 'fat or<rat');
+select websearch_to_tsquery('simple', 'fat or>rat');
+select websearch_to_tsquery('simple', 'fat or ');
+
+-- ... but not here
+select websearch_to_tsquery('simple', 'abc orange');
+select websearch_to_tsquery('simple', 'abc orÑеÑÑ');
+select websearch_to_tsquery('simple', 'abc OR1234');
+select websearch_to_tsquery('simple', 'abc or-abc');
+select websearch_to_tsquery('simple', 'abc OR_abc');
+select websearch_to_tsquery('simple', 'abc or');
+
+select websearch_to_tsquery('simple', 'or OR or');
+
+select websearch_to_tsquery('english', '"A fat cat" has just eaten a -rat.');
+select websearch_to_tsquery('english', '"A fat cat" has just eaten OR !rat.');
+select websearch_to_tsquery('english', '"A fat cat" has just (+eaten OR -rat)');
+
+select websearch_to_tsquery('english', 'this is ----fine');
+select websearch_to_tsquery('english', '(()) )))) this ||| is && -fine, "dear friend" OR good');
+select websearch_to_tsquery('english', 'an old <-> cat " is fine &&& too');
+
+select websearch_to_tsquery('english', '"A the" OR just on');
+select websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+
+select to_tsvector('russian', 'ÑÑела ÑолÑÑÐ°Ñ ÐºÐ¾Ñка кÑÑÑÑ') @@
+websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+
+select to_tsvector('russian', 'ÑÑела ÑолÑÑÐ°Ñ ÑеÑÐ°Ñ ÐºÐ¾Ñка кÑÑÑÑ') @@
+websearch_to_tsquery('russian', '"ÑолÑÑÐ°Ñ ÐºÐ¾Ñка" ÑÑела кÑÑÑÑ');
+
+-- cases handled by gettoken_tsvector()
+select websearch_to_tsquery('''');
+select websearch_to_tsquery('''abc''''def''');
+select websearch_to_tsquery('\abc');
+select websearch_to_tsquery('\');
