LCOV - code coverage report
Current view: top level - src/backend/tsearch - ts_typanalyze.c (source / functions) Hit Total Coverage
Test: PostgreSQL 15devel Lines: 110 130 84.6 %
Date: 2021-12-09 04:09:06 Functions: 7 8 87.5 %
Legend: Lines: hit not hit

          Line data    Source code
       1             : /*-------------------------------------------------------------------------
       2             :  *
       3             :  * ts_typanalyze.c
       4             :  *    functions for gathering statistics from tsvector columns
       5             :  *
       6             :  * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
       7             :  *
       8             :  *
       9             :  * IDENTIFICATION
      10             :  *    src/backend/tsearch/ts_typanalyze.c
      11             :  *
      12             :  *-------------------------------------------------------------------------
      13             :  */
      14             : #include "postgres.h"
      15             : 
      16             : #include "catalog/pg_collation.h"
      17             : #include "catalog/pg_operator.h"
      18             : #include "commands/vacuum.h"
      19             : #include "common/hashfn.h"
      20             : #include "tsearch/ts_type.h"
      21             : #include "utils/builtins.h"
      22             : 
      23             : 
      24             : /* A hash key for lexemes */
      25             : typedef struct
      26             : {
      27             :     char       *lexeme;         /* lexeme (not NULL terminated!) */
      28             :     int         length;         /* its length in bytes */
      29             : } LexemeHashKey;
      30             : 
      31             : /* A hash table entry for the Lossy Counting algorithm */
      32             : typedef struct
      33             : {
      34             :     LexemeHashKey key;          /* This is 'e' from the LC algorithm. */
      35             :     int         frequency;      /* This is 'f'. */
      36             :     int         delta;          /* And this is 'delta'. */
      37             : } TrackItem;
      38             : 
      39             : static void compute_tsvector_stats(VacAttrStats *stats,
      40             :                                    AnalyzeAttrFetchFunc fetchfunc,
      41             :                                    int samplerows,
      42             :                                    double totalrows);
      43             : static void prune_lexemes_hashtable(HTAB *lexemes_tab, int b_current);
      44             : static uint32 lexeme_hash(const void *key, Size keysize);
      45             : static int  lexeme_match(const void *key1, const void *key2, Size keysize);
      46             : static int  lexeme_compare(const void *key1, const void *key2);
      47             : static int  trackitem_compare_frequencies_desc(const void *e1, const void *e2);
      48             : static int  trackitem_compare_lexemes(const void *e1, const void *e2);
      49             : 
      50             : 
      51             : /*
      52             :  *  ts_typanalyze -- a custom typanalyze function for tsvector columns
      53             :  */
      54             : Datum
      55           4 : ts_typanalyze(PG_FUNCTION_ARGS)
      56             : {
      57           4 :     VacAttrStats *stats = (VacAttrStats *) PG_GETARG_POINTER(0);
      58           4 :     Form_pg_attribute attr = stats->attr;
      59             : 
      60             :     /* If the attstattarget column is negative, use the default value */
      61             :     /* NB: it is okay to scribble on stats->attr since it's a copy */
      62           4 :     if (attr->attstattarget < 0)
      63           4 :         attr->attstattarget = default_statistics_target;
      64             : 
      65           4 :     stats->compute_stats = compute_tsvector_stats;
      66             :     /* see comment about the choice of minrows in commands/analyze.c */
      67           4 :     stats->minrows = 300 * attr->attstattarget;
      68             : 
      69           4 :     PG_RETURN_BOOL(true);
      70             : }
      71             : 
      72             : /*
      73             :  *  compute_tsvector_stats() -- compute statistics for a tsvector column
      74             :  *
      75             :  *  This functions computes statistics that are useful for determining @@
      76             :  *  operations' selectivity, along with the fraction of non-null rows and
      77             :  *  average width.
      78             :  *
      79             :  *  Instead of finding the most common values, as we do for most datatypes,
      80             :  *  we're looking for the most common lexemes. This is more useful, because
      81             :  *  there most probably won't be any two rows with the same tsvector and thus
      82             :  *  the notion of a MCV is a bit bogus with this datatype. With a list of the
      83             :  *  most common lexemes we can do a better job at figuring out @@ selectivity.
      84             :  *
      85             :  *  For the same reasons we assume that tsvector columns are unique when
      86             :  *  determining the number of distinct values.
      87             :  *
      88             :  *  The algorithm used is Lossy Counting, as proposed in the paper "Approximate
      89             :  *  frequency counts over data streams" by G. S. Manku and R. Motwani, in
      90             :  *  Proceedings of the 28th International Conference on Very Large Data Bases,
      91             :  *  Hong Kong, China, August 2002, section 4.2. The paper is available at
      92             :  *  http://www.vldb.org/conf/2002/S10P03.pdf
      93             :  *
      94             :  *  The Lossy Counting (aka LC) algorithm goes like this:
      95             :  *  Let s be the threshold frequency for an item (the minimum frequency we
      96             :  *  are interested in) and epsilon the error margin for the frequency. Let D
      97             :  *  be a set of triples (e, f, delta), where e is an element value, f is that
      98             :  *  element's frequency (actually, its current occurrence count) and delta is
      99             :  *  the maximum error in f. We start with D empty and process the elements in
     100             :  *  batches of size w. (The batch size is also known as "bucket size" and is
     101             :  *  equal to 1/epsilon.) Let the current batch number be b_current, starting
     102             :  *  with 1. For each element e we either increment its f count, if it's
     103             :  *  already in D, or insert a new triple into D with values (e, 1, b_current
     104             :  *  - 1). After processing each batch we prune D, by removing from it all
     105             :  *  elements with f + delta <= b_current.  After the algorithm finishes we
     106             :  *  suppress all elements from D that do not satisfy f >= (s - epsilon) * N,
     107             :  *  where N is the total number of elements in the input.  We emit the
     108             :  *  remaining elements with estimated frequency f/N.  The LC paper proves
     109             :  *  that this algorithm finds all elements with true frequency at least s,
     110             :  *  and that no frequency is overestimated or is underestimated by more than
     111             :  *  epsilon.  Furthermore, given reasonable assumptions about the input
     112             :  *  distribution, the required table size is no more than about 7 times w.
     113             :  *
     114             :  *  We set s to be the estimated frequency of the K'th word in a natural
     115             :  *  language's frequency table, where K is the target number of entries in
     116             :  *  the MCELEM array plus an arbitrary constant, meant to reflect the fact
     117             :  *  that the most common words in any language would usually be stopwords
     118             :  *  so we will not actually see them in the input.  We assume that the
     119             :  *  distribution of word frequencies (including the stopwords) follows Zipf's
     120             :  *  law with an exponent of 1.
     121             :  *
     122             :  *  Assuming Zipfian distribution, the frequency of the K'th word is equal
     123             :  *  to 1/(K * H(W)) where H(n) is 1/2 + 1/3 + ... + 1/n and W is the number of
     124             :  *  words in the language.  Putting W as one million, we get roughly 0.07/K.
     125             :  *  Assuming top 10 words are stopwords gives s = 0.07/(K + 10).  We set
     126             :  *  epsilon = s/10, which gives bucket width w = (K + 10)/0.007 and
     127             :  *  maximum expected hashtable size of about 1000 * (K + 10).
     128             :  *
     129             :  *  Note: in the above discussion, s, epsilon, and f/N are in terms of a
     130             :  *  lexeme's frequency as a fraction of all lexemes seen in the input.
     131             :  *  However, what we actually want to store in the finished pg_statistic
     132             :  *  entry is each lexeme's frequency as a fraction of all rows that it occurs
     133             :  *  in.  Assuming that the input tsvectors are correctly constructed, no
     134             :  *  lexeme occurs more than once per tsvector, so the final count f is a
     135             :  *  correct estimate of the number of input tsvectors it occurs in, and we
     136             :  *  need only change the divisor from N to nonnull_cnt to get the number we
     137             :  *  want.
     138             :  */
     139             : static void
     140           4 : compute_tsvector_stats(VacAttrStats *stats,
     141             :                        AnalyzeAttrFetchFunc fetchfunc,
     142             :                        int samplerows,
     143             :                        double totalrows)
     144             : {
     145             :     int         num_mcelem;
     146           4 :     int         null_cnt = 0;
     147           4 :     double      total_width = 0;
     148             : 
     149             :     /* This is D from the LC algorithm. */
     150             :     HTAB       *lexemes_tab;
     151             :     HASHCTL     hash_ctl;
     152             :     HASH_SEQ_STATUS scan_status;
     153             : 
     154             :     /* This is the current bucket number from the LC algorithm */
     155             :     int         b_current;
     156             : 
     157             :     /* This is 'w' from the LC algorithm */
     158             :     int         bucket_width;
     159             :     int         vector_no,
     160             :                 lexeme_no;
     161             :     LexemeHashKey hash_key;
     162             :     TrackItem  *item;
     163             : 
     164             :     /*
     165             :      * We want statistics_target * 10 lexemes in the MCELEM array.  This
     166             :      * multiplier is pretty arbitrary, but is meant to reflect the fact that
     167             :      * the number of individual lexeme values tracked in pg_statistic ought to
     168             :      * be more than the number of values for a simple scalar column.
     169             :      */
     170           4 :     num_mcelem = stats->attr->attstattarget * 10;
     171             : 
     172             :     /*
     173             :      * We set bucket width equal to (num_mcelem + 10) / 0.007 as per the
     174             :      * comment above.
     175             :      */
     176           4 :     bucket_width = (num_mcelem + 10) * 1000 / 7;
     177             : 
     178             :     /*
     179             :      * Create the hashtable. It will be in local memory, so we don't need to
     180             :      * worry about overflowing the initial size. Also we don't need to pay any
     181             :      * attention to locking and memory management.
     182             :      */
     183           4 :     hash_ctl.keysize = sizeof(LexemeHashKey);
     184           4 :     hash_ctl.entrysize = sizeof(TrackItem);
     185           4 :     hash_ctl.hash = lexeme_hash;
     186           4 :     hash_ctl.match = lexeme_match;
     187           4 :     hash_ctl.hcxt = CurrentMemoryContext;
     188           4 :     lexemes_tab = hash_create("Analyzed lexemes table",
     189             :                               num_mcelem,
     190             :                               &hash_ctl,
     191             :                               HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
     192             : 
     193             :     /* Initialize counters. */
     194           4 :     b_current = 1;
     195           4 :     lexeme_no = 0;
     196             : 
     197             :     /* Loop over the tsvectors. */
     198        2036 :     for (vector_no = 0; vector_no < samplerows; vector_no++)
     199             :     {
     200             :         Datum       value;
     201             :         bool        isnull;
     202             :         TSVector    vector;
     203             :         WordEntry  *curentryptr;
     204             :         char       *lexemesptr;
     205             :         int         j;
     206             : 
     207        2032 :         vacuum_delay_point();
     208             : 
     209        2032 :         value = fetchfunc(stats, vector_no, &isnull);
     210             : 
     211             :         /*
     212             :          * Check for null/nonnull.
     213             :          */
     214        2032 :         if (isnull)
     215             :         {
     216           0 :             null_cnt++;
     217           0 :             continue;
     218             :         }
     219             : 
     220             :         /*
     221             :          * Add up widths for average-width calculation.  Since it's a
     222             :          * tsvector, we know it's varlena.  As in the regular
     223             :          * compute_minimal_stats function, we use the toasted width for this
     224             :          * calculation.
     225             :          */
     226        2032 :         total_width += VARSIZE_ANY(DatumGetPointer(value));
     227             : 
     228             :         /*
     229             :          * Now detoast the tsvector if needed.
     230             :          */
     231        2032 :         vector = DatumGetTSVector(value);
     232             : 
     233             :         /*
     234             :          * We loop through the lexemes in the tsvector and add them to our
     235             :          * tracking hashtable.
     236             :          */
     237        2032 :         lexemesptr = STRPTR(vector);
     238        2032 :         curentryptr = ARRPTR(vector);
     239      117232 :         for (j = 0; j < vector->size; j++)
     240             :         {
     241             :             bool        found;
     242             : 
     243             :             /*
     244             :              * Construct a hash key.  The key points into the (detoasted)
     245             :              * tsvector value at this point, but if a new entry is created, we
     246             :              * make a copy of it.  This way we can free the tsvector value
     247             :              * once we've processed all its lexemes.
     248             :              */
     249      115200 :             hash_key.lexeme = lexemesptr + curentryptr->pos;
     250      115200 :             hash_key.length = curentryptr->len;
     251             : 
     252             :             /* Lookup current lexeme in hashtable, adding it if new */
     253      115200 :             item = (TrackItem *) hash_search(lexemes_tab,
     254             :                                              (const void *) &hash_key,
     255             :                                              HASH_ENTER, &found);
     256             : 
     257      115200 :             if (found)
     258             :             {
     259             :                 /* The lexeme is already on the tracking list */
     260      110636 :                 item->frequency++;
     261             :             }
     262             :             else
     263             :             {
     264             :                 /* Initialize new tracking list element */
     265        4564 :                 item->frequency = 1;
     266        4564 :                 item->delta = b_current - 1;
     267             : 
     268        4564 :                 item->key.lexeme = palloc(hash_key.length);
     269        4564 :                 memcpy(item->key.lexeme, hash_key.lexeme, hash_key.length);
     270             :             }
     271             : 
     272             :             /* lexeme_no is the number of elements processed (ie N) */
     273      115200 :             lexeme_no++;
     274             : 
     275             :             /* We prune the D structure after processing each bucket */
     276      115200 :             if (lexeme_no % bucket_width == 0)
     277             :             {
     278           0 :                 prune_lexemes_hashtable(lexemes_tab, b_current);
     279           0 :                 b_current++;
     280             :             }
     281             : 
     282             :             /* Advance to the next WordEntry in the tsvector */
     283      115200 :             curentryptr++;
     284             :         }
     285             : 
     286             :         /* If the vector was toasted, free the detoasted copy. */
     287        2032 :         if (TSVectorGetDatum(vector) != value)
     288         256 :             pfree(vector);
     289             :     }
     290             : 
     291             :     /* We can only compute real stats if we found some non-null values. */
     292           4 :     if (null_cnt < samplerows)
     293             :     {
     294           4 :         int         nonnull_cnt = samplerows - null_cnt;
     295             :         int         i;
     296             :         TrackItem **sort_table;
     297             :         int         track_len;
     298             :         int         cutoff_freq;
     299             :         int         minfreq,
     300             :                     maxfreq;
     301             : 
     302           4 :         stats->stats_valid = true;
     303             :         /* Do the simple null-frac and average width stats */
     304           4 :         stats->stanullfrac = (double) null_cnt / (double) samplerows;
     305           4 :         stats->stawidth = total_width / (double) nonnull_cnt;
     306             : 
     307             :         /* Assume it's a unique column (see notes above) */
     308           4 :         stats->stadistinct = -1.0 * (1.0 - stats->stanullfrac);
     309             : 
     310             :         /*
     311             :          * Construct an array of the interesting hashtable items, that is,
     312             :          * those meeting the cutoff frequency (s - epsilon)*N.  Also identify
     313             :          * the minimum and maximum frequencies among these items.
     314             :          *
     315             :          * Since epsilon = s/10 and bucket_width = 1/epsilon, the cutoff
     316             :          * frequency is 9*N / bucket_width.
     317             :          */
     318           4 :         cutoff_freq = 9 * lexeme_no / bucket_width;
     319             : 
     320           4 :         i = hash_get_num_entries(lexemes_tab);  /* surely enough space */
     321           4 :         sort_table = (TrackItem **) palloc(sizeof(TrackItem *) * i);
     322             : 
     323           4 :         hash_seq_init(&scan_status, lexemes_tab);
     324           4 :         track_len = 0;
     325           4 :         minfreq = lexeme_no;
     326           4 :         maxfreq = 0;
     327        4568 :         while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
     328             :         {
     329        4564 :             if (item->frequency > cutoff_freq)
     330             :             {
     331        4212 :                 sort_table[track_len++] = item;
     332        4212 :                 minfreq = Min(minfreq, item->frequency);
     333        4212 :                 maxfreq = Max(maxfreq, item->frequency);
     334             :             }
     335             :         }
     336             :         Assert(track_len <= i);
     337             : 
     338             :         /* emit some statistics for debug purposes */
     339           4 :         elog(DEBUG3, "tsvector_stats: target # mces = %d, bucket width = %d, "
     340             :              "# lexemes = %d, hashtable size = %d, usable entries = %d",
     341             :              num_mcelem, bucket_width, lexeme_no, i, track_len);
     342             : 
     343             :         /*
     344             :          * If we obtained more lexemes than we really want, get rid of those
     345             :          * with least frequencies.  The easiest way is to qsort the array into
     346             :          * descending frequency order and truncate the array.
     347             :          */
     348           4 :         if (num_mcelem < track_len)
     349             :         {
     350           4 :             qsort(sort_table, track_len, sizeof(TrackItem *),
     351             :                   trackitem_compare_frequencies_desc);
     352             :             /* reset minfreq to the smallest frequency we're keeping */
     353           4 :             minfreq = sort_table[num_mcelem - 1]->frequency;
     354             :         }
     355             :         else
     356           0 :             num_mcelem = track_len;
     357             : 
     358             :         /* Generate MCELEM slot entry */
     359           4 :         if (num_mcelem > 0)
     360             :         {
     361             :             MemoryContext old_context;
     362             :             Datum      *mcelem_values;
     363             :             float4     *mcelem_freqs;
     364             : 
     365             :             /*
     366             :              * We want to store statistics sorted on the lexeme value using
     367             :              * first length, then byte-for-byte comparison. The reason for
     368             :              * doing length comparison first is that we don't care about the
     369             :              * ordering so long as it's consistent, and comparing lengths
     370             :              * first gives us a chance to avoid a strncmp() call.
     371             :              *
     372             :              * This is different from what we do with scalar statistics --
     373             :              * they get sorted on frequencies. The rationale is that we
     374             :              * usually search through most common elements looking for a
     375             :              * specific value, so we can grab its frequency.  When values are
     376             :              * presorted we can employ binary search for that.  See
     377             :              * ts_selfuncs.c for a real usage scenario.
     378             :              */
     379           4 :             qsort(sort_table, num_mcelem, sizeof(TrackItem *),
     380             :                   trackitem_compare_lexemes);
     381             : 
     382             :             /* Must copy the target values into anl_context */
     383           4 :             old_context = MemoryContextSwitchTo(stats->anl_context);
     384             : 
     385             :             /*
     386             :              * We sorted statistics on the lexeme value, but we want to be
     387             :              * able to find out the minimal and maximal frequency without
     388             :              * going through all the values.  We keep those two extra
     389             :              * frequencies in two extra cells in mcelem_freqs.
     390             :              *
     391             :              * (Note: the MCELEM statistics slot definition allows for a third
     392             :              * extra number containing the frequency of nulls, but we don't
     393             :              * create that for a tsvector column, since null elements aren't
     394             :              * possible.)
     395             :              */
     396           4 :             mcelem_values = (Datum *) palloc(num_mcelem * sizeof(Datum));
     397           4 :             mcelem_freqs = (float4 *) palloc((num_mcelem + 2) * sizeof(float4));
     398             : 
     399             :             /*
     400             :              * See comments above about use of nonnull_cnt as the divisor for
     401             :              * the final frequency estimates.
     402             :              */
     403        4004 :             for (i = 0; i < num_mcelem; i++)
     404             :             {
     405        4000 :                 TrackItem  *item = sort_table[i];
     406             : 
     407        4000 :                 mcelem_values[i] =
     408        4000 :                     PointerGetDatum(cstring_to_text_with_len(item->key.lexeme,
     409             :                                                              item->key.length));
     410        4000 :                 mcelem_freqs[i] = (double) item->frequency / (double) nonnull_cnt;
     411             :             }
     412           4 :             mcelem_freqs[i++] = (double) minfreq / (double) nonnull_cnt;
     413           4 :             mcelem_freqs[i] = (double) maxfreq / (double) nonnull_cnt;
     414           4 :             MemoryContextSwitchTo(old_context);
     415             : 
     416           4 :             stats->stakind[0] = STATISTIC_KIND_MCELEM;
     417           4 :             stats->staop[0] = TextEqualOperator;
     418           4 :             stats->stacoll[0] = DEFAULT_COLLATION_OID;
     419           4 :             stats->stanumbers[0] = mcelem_freqs;
     420             :             /* See above comment about two extra frequency fields */
     421           4 :             stats->numnumbers[0] = num_mcelem + 2;
     422           4 :             stats->stavalues[0] = mcelem_values;
     423           4 :             stats->numvalues[0] = num_mcelem;
     424             :             /* We are storing text values */
     425           4 :             stats->statypid[0] = TEXTOID;
     426           4 :             stats->statyplen[0] = -1;    /* typlen, -1 for varlena */
     427           4 :             stats->statypbyval[0] = false;
     428           4 :             stats->statypalign[0] = 'i';
     429             :         }
     430             :     }
     431             :     else
     432             :     {
     433             :         /* We found only nulls; assume the column is entirely null */
     434           0 :         stats->stats_valid = true;
     435           0 :         stats->stanullfrac = 1.0;
     436           0 :         stats->stawidth = 0; /* "unknown" */
     437           0 :         stats->stadistinct = 0.0;    /* "unknown" */
     438             :     }
     439             : 
     440             :     /*
     441             :      * We don't need to bother cleaning up any of our temporary palloc's. The
     442             :      * hashtable should also go away, as it used a child memory context.
     443             :      */
     444           4 : }
     445             : 
     446             : /*
     447             :  *  A function to prune the D structure from the Lossy Counting algorithm.
     448             :  *  Consult compute_tsvector_stats() for wider explanation.
     449             :  */
     450             : static void
     451           0 : prune_lexemes_hashtable(HTAB *lexemes_tab, int b_current)
     452             : {
     453             :     HASH_SEQ_STATUS scan_status;
     454             :     TrackItem  *item;
     455             : 
     456           0 :     hash_seq_init(&scan_status, lexemes_tab);
     457           0 :     while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
     458             :     {
     459           0 :         if (item->frequency + item->delta <= b_current)
     460             :         {
     461           0 :             char       *lexeme = item->key.lexeme;
     462             : 
     463           0 :             if (hash_search(lexemes_tab, (const void *) &item->key,
     464             :                             HASH_REMOVE, NULL) == NULL)
     465           0 :                 elog(ERROR, "hash table corrupted");
     466           0 :             pfree(lexeme);
     467             :         }
     468             :     }
     469           0 : }
     470             : 
     471             : /*
     472             :  * Hash functions for lexemes. They are strings, but not NULL terminated,
     473             :  * so we need a special hash function.
     474             :  */
     475             : static uint32
     476      115200 : lexeme_hash(const void *key, Size keysize)
     477             : {
     478      115200 :     const LexemeHashKey *l = (const LexemeHashKey *) key;
     479             : 
     480      115200 :     return DatumGetUInt32(hash_any((const unsigned char *) l->lexeme,
     481             :                                    l->length));
     482             : }
     483             : 
     484             : /*
     485             :  *  Matching function for lexemes, to be used in hashtable lookups.
     486             :  */
     487             : static int
     488      110636 : lexeme_match(const void *key1, const void *key2, Size keysize)
     489             : {
     490             :     /* The keysize parameter is superfluous, the keys store their lengths */
     491      110636 :     return lexeme_compare(key1, key2);
     492             : }
     493             : 
     494             : /*
     495             :  *  Comparison function for lexemes.
     496             :  */
     497             : static int
     498      151352 : lexeme_compare(const void *key1, const void *key2)
     499             : {
     500      151352 :     const LexemeHashKey *d1 = (const LexemeHashKey *) key1;
     501      151352 :     const LexemeHashKey *d2 = (const LexemeHashKey *) key2;
     502             : 
     503             :     /* First, compare by length */
     504      151352 :     if (d1->length > d2->length)
     505           0 :         return 1;
     506      151352 :     else if (d1->length < d2->length)
     507           0 :         return -1;
     508             :     /* Lengths are equal, do a byte-by-byte comparison */
     509      151352 :     return strncmp(d1->lexeme, d2->lexeme, d1->length);
     510             : }
     511             : 
     512             : /*
     513             :  *  qsort() comparator for sorting TrackItems on frequencies (descending sort)
     514             :  */
     515             : static int
     516       25640 : trackitem_compare_frequencies_desc(const void *e1, const void *e2)
     517             : {
     518       25640 :     const TrackItem *const *t1 = (const TrackItem *const *) e1;
     519       25640 :     const TrackItem *const *t2 = (const TrackItem *const *) e2;
     520             : 
     521       25640 :     return (*t2)->frequency - (*t1)->frequency;
     522             : }
     523             : 
     524             : /*
     525             :  *  qsort() comparator for sorting TrackItems on lexemes
     526             :  */
     527             : static int
     528       40716 : trackitem_compare_lexemes(const void *e1, const void *e2)
     529             : {
     530       40716 :     const TrackItem *const *t1 = (const TrackItem *const *) e1;
     531       40716 :     const TrackItem *const *t2 = (const TrackItem *const *) e2;
     532             : 
     533       40716 :     return lexeme_compare(&(*t1)->key, &(*t2)->key);
     534             : }

Generated by: LCOV version 1.14