From 0c1951c36fdc6558b334ad4c14121952a530fe00 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Thu, 27 Nov 2008 21:17:39 +0000 Subject: [PATCH] Fix bug in the tsvector stats collection function, which caused a crash if the sample contains just a one tsvector, containing only one lexeme. --- src/backend/tsearch/ts_typanalyze.c | 41 +++++++++++++++-------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/src/backend/tsearch/ts_typanalyze.c b/src/backend/tsearch/ts_typanalyze.c index 3d35f47c66..d56e6b45b3 100644 --- a/src/backend/tsearch/ts_typanalyze.c +++ b/src/backend/tsearch/ts_typanalyze.c @@ -290,26 +290,6 @@ compute_tsvector_stats(VacAttrStats *stats, if (num_mcelem > track_len) num_mcelem = track_len; - /* Grab the minimal and maximal frequencies that will get stored */ - minfreq = sort_table[num_mcelem - 1]->frequency; - maxfreq = sort_table[0]->frequency; - - /* - * We want to store statistics sorted on the lexeme value using first - * length, then byte-for-byte comparison. The reason for doing length - * comparison first is that we don't care about the ordering so long - * as it's consistent, and comparing lengths first gives us a chance - * to avoid a strncmp() call. - * - * This is different from what we do with scalar statistics -- they get - * sorted on frequencies. The rationale is that we usually search - * through most common elements looking for a specific value, so we can - * grab its frequency. When values are presorted we can employ binary - * search for that. See ts_selfuncs.c for a real usage scenario. - */ - qsort(sort_table, num_mcelem, sizeof(TrackItem *), - trackitem_compare_lexemes); - /* Generate MCELEM slot entry */ if (num_mcelem > 0) { @@ -317,6 +297,27 @@ compute_tsvector_stats(VacAttrStats *stats, Datum *mcelem_values; float4 *mcelem_freqs; + /* Grab the minimal and maximal frequencies that will get stored */ + minfreq = sort_table[num_mcelem - 1]->frequency; + maxfreq = sort_table[0]->frequency; + + /* + * We want to store statistics sorted on the lexeme value using + * first length, then byte-for-byte comparison. The reason for + * doing length comparison first is that we don't care about the + * ordering so long as it's consistent, and comparing lengths first + * gives us a chance to avoid a strncmp() call. + * + * This is different from what we do with scalar statistics -- they + * get sorted on frequencies. The rationale is that we usually + * search through most common elements looking for a specific + * value, so we can grab its frequency. When values are presorted + * we can employ binary search for that. See ts_selfuncs.c for a + * real usage scenario. + */ + qsort(sort_table, num_mcelem, sizeof(TrackItem *), + trackitem_compare_lexemes); + /* Must copy the target values into anl_context */ old_context = MemoryContextSwitchTo(stats->anl_context); -- 2.39.5