database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2026-10-23 13:29:09 +03:00
Code Activity

Consistently enforce tsvector/tsquery maximum lengths.

Browse Source 
Some places rejected individual tokens longer than MAXSTRLEN, while
others rejected ones longer than MAXSTRLEN-1.  The data structure is
perfectly capable of handling MAXSTRLEN, so there's nothing wrong
with using the looser bound.  Moreover, as things stand there is a
dump/reload hazard: some code paths permit construction of a tsvector
or tsquery that would later be rejected by tsvectorin or tsqueryin.
So standardize on using MAXSTRLEN.

Identical remarks apply to MAXSTRPOS (the total data length),
so fix that too.

Back-patch, in hopes of avoiding cases where a value acceptable to
one supported release is not acceptable to another.

Author: Tom Lane <tgl@sss.pgh.pa.us>
Reviewed-by: Zsolt Parragi <zsolt.parragi@percona.com>
Discussion: https://postgr.es/m/CAN4CZFNYQo4zfbRR435uD0vSfuy5y7dnFOXDfKr9zYoL1JnAxA@mail.gmail.com
Backpatch-through: 14
This commit is contained in:
Tom Lane
2026-08-13 11:20:27 -04:00
parent 864ef0fb1c
commit a68beda425
4 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/backend/tsearch/ts_parse.c
View File

@@ -379,7 +379,7 @@ parsetext(Oid cfgId, ParsedText *prs, char *buf, int buflen)
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
if (type > 0 && lenlemm > MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,
@@ -582,7 +582,7 @@ hlparsetext(Oid cfgId, HeadlineParsedText *prs, TSQuery query, char *buf, int bu
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
if (type > 0 && lenlemm > MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,

6
src/backend/utils/adt/tsquery.c
View File

@@ -548,12 +548,12 @@ pushValue_internal(TSQueryParserState state, pg_crc32 valcrc, int distance, int
{
QueryOperand *tmp;
if (distance >= MAXSTRPOS)
if (distance > MAXSTRPOS)
ereturn(state->escontext,,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("value is too big in tsquery: \"%s\"",
state->buffer)));
if (lenval >= MAXSTRLEN)
if (lenval > MAXSTRLEN)
ereturn(state->escontext,,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("operand is too long in tsquery: \"%s\"",
@@ -581,7 +581,7 @@ pushValue(TSQueryParserState state, char *strval, int lenval, int16 weight, bool
{
pg_crc32 valcrc;
if (lenval >= MAXSTRLEN)
if (lenval > MAXSTRLEN)
ereturn(state->escontext,,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long in tsquery: \"%s\"",

4
src/backend/utils/adt/tsvector.c
View File

@@ -207,12 +207,12 @@ tsvectorin(PG_FUNCTION_ARGS)
while (gettoken_tsvector(state, &token, &toklen, &pos, &poslen, NULL))
{
if (toklen >= MAXSTRLEN)
if (toklen > MAXSTRLEN)
ereturn(escontext, (Datum) 0,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long (%ld bytes, max %ld bytes)",
(long) toklen,
(long) (MAXSTRLEN - 1))));
(long) MAXSTRLEN)));
if (cur - tmpbuf > MAXSTRPOS)
ereturn(escontext, (Datum) 0,

4
src/backend/utils/adt/tsvector_op.c
View File

@@ -775,12 +775,12 @@ array_to_tsvector(PG_FUNCTION_ARGS)
ereport(ERROR,
(errcode(ERRCODE_ZERO_LENGTH_CHARACTER_STRING),
errmsg("lexeme array may not contain empty strings")));
if (toklen >= MAXSTRLEN)
if (toklen > MAXSTRLEN)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long (%d bytes, max %d bytes)",
toklen,
MAXSTRLEN - 1)));
MAXSTRLEN)));
}
/* Sort and de-dup, because this is required for a valid tsvector. */