From f4b36a5fb83dd23500cd956e400342689b99d39b Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Wed, 12 Aug 2026 15:02:17 -0400 Subject: [PATCH v1] Consistently enforce tsvector/tsquery maximum lengths. 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. --- src/backend/tsearch/ts_parse.c | 4 ++-- src/backend/utils/adt/tsquery.c | 6 +++--- src/backend/utils/adt/tsvector.c | 4 ++-- src/backend/utils/adt/tsvector_op.c | 4 ++-- 4 files changed, 9 insertions(+), 9 deletions(-) diff --git a/src/backend/tsearch/ts_parse.c b/src/backend/tsearch/ts_parse.c index cb69e9899c5..93d46f1d642 100644 --- a/src/backend/tsearch/ts_parse.c +++ b/src/backend/tsearch/ts_parse.c @@ -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, diff --git a/src/backend/utils/adt/tsquery.c b/src/backend/utils/adt/tsquery.c index e411a21f07e..3247d5db082 100644 --- a/src/backend/utils/adt/tsquery.c +++ b/src/backend/utils/adt/tsquery.c @@ -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\"", diff --git a/src/backend/utils/adt/tsvector.c b/src/backend/utils/adt/tsvector.c index 40be82b890a..b99878d0ca2 100644 --- a/src/backend/utils/adt/tsvector.c +++ b/src/backend/utils/adt/tsvector.c @@ -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 (%d bytes, max %d bytes)", toklen, - MAXSTRLEN - 1))); + MAXSTRLEN))); if (cur - tmpbuf > MAXSTRPOS) ereturn(escontext, (Datum) 0, diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c index 782b91f701e..d5336774b22 100644 --- a/src/backend/utils/adt/tsvector_op.c +++ b/src/backend/utils/adt/tsvector_op.c @@ -776,12 +776,12 @@ 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. */ -- 2.52.0