From cbe25dcff73a297adbada9dc1d6cad3df18014e9 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Sat, 6 Nov 2021 13:28:53 -0400 Subject: Disallow making an empty lexeme via array_to_tsvector(). The tsvector data type has always forbidden lexemes to be empty. However, array_to_tsvector() didn't get that memo, and would allow an empty-string array element to become an empty lexeme. This could result in dump/restore failures later, not to mention whatever semantic issues might be behind the original prohibition. However, other functions that take a plain text input directly as a lexeme value do not need a similar restriction, because they only match the string against existing tsvector entries. In particular it'd be a bad idea to make ts_delete() reject empty strings, since that is the most convenient way to clean up any bad data that might have gotten into a tsvector column via this bug. Reflecting on that, let's also remove the prohibition against NULL array elements in tsvector_delete_arr and tsvector_setweight_by_filter. It seems more consistent to ignore them, as an empty-string element would be ignored. There's a case for back-patching this, since it's clearly a bug fix. On balance though, it doesn't seem like something to change in a minor release. Jean-Christophe Arnu Discussion: https://postgr.es/m/CAHZmTm1YVndPgUVRoag2WL0w900XcoiivDDj-gTTYBsG25c65A@mail.gmail.com --- src/backend/utils/adt/tsvector_op.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'src/backend/utils/adt/tsvector_op.c') diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c index 9236ebcc8fe..11ccb5297c9 100644 --- a/src/backend/utils/adt/tsvector_op.c +++ b/src/backend/utils/adt/tsvector_op.c @@ -322,10 +322,9 @@ tsvector_setweight_by_filter(PG_FUNCTION_ARGS) int lex_len, lex_pos; + /* Ignore null array elements, they surely don't match */ if (nulls[i]) - ereport(ERROR, - (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), - errmsg("lexeme array may not contain nulls"))); + continue; lex = VARDATA(dlexemes[i]); lex_len = VARSIZE(dlexemes[i]) - VARHDRSZ; @@ -602,10 +601,9 @@ tsvector_delete_arr(PG_FUNCTION_ARGS) int lex_len, lex_pos; + /* Ignore null array elements, they surely don't match */ if (nulls[i]) - ereport(ERROR, - (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), - errmsg("lexeme array may not contain nulls"))); + continue; lex = VARDATA(dlexemes[i]); lex_len = VARSIZE(dlexemes[i]) - VARHDRSZ; @@ -761,13 +759,21 @@ array_to_tsvector(PG_FUNCTION_ARGS) deconstruct_array(v, TEXTOID, -1, false, TYPALIGN_INT, &dlexemes, &nulls, &nitems); - /* Reject nulls (maybe we should just ignore them, instead?) */ + /* + * Reject nulls and zero length strings (maybe we should just ignore them, + * instead?) + */ for (i = 0; i < nitems; i++) { if (nulls[i]) ereport(ERROR, (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), errmsg("lexeme array may not contain nulls"))); + + if (VARSIZE(dlexemes[i]) - VARHDRSZ == 0) + ereport(ERROR, + (errcode(ERRCODE_ZERO_LENGTH_CHARACTER_STRING), + errmsg("lexeme array may not contain empty strings"))); } /* Sort and de-dup, because this is required for a valid tsvector. */ -- cgit v1.2.3