Fix bug in the tsvector stats collection function, which caused a crash if

the sample contains just a one tsvector, containing only one lexeme.

diff --git a/src/backend/tsearch/ts_typanalyze.c b/src/backend/tsearch/ts_typanalyze.c
index a284360a922bff19c860dc14e80718038feeb3f6..199432097bc969b53e327357a841d316253b26ea 100644 (file)
--- a/src/backend/tsearch/ts_typanalyze.c
+++ b/src/backend/tsearch/ts_typanalyze.c
@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.2 2008/09/19 19:03:40 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.3 2008/11/27 21:17:39 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -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);