Metadata 'skiparticle works for ICU normalization

[pazpar2-moved-to-github.git] / src / relevance.c

diff --git a/src/relevance.c b/src/relevance.c
index 072a894..0234d91 100644 (file)
--- a/src/relevance.c
+++ b/src/relevance.c
@@ -77,7 +77,7 @@ static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem,
 
     for (; *p; p++)
     {
-        pp2_relevance_token_t prt = pp2_relevance_tokenize(pct, *p);
+        pp2_relevance_token_t prt = pp2_relevance_tokenize(pct, *p, 0);
         const char *norm_str;
 
         while ((norm_str = pp2_relevance_token_next(prt)))
@@ -93,7 +93,7 @@ static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem,
 void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
                           const char *words, int multiplier, const char *name)
 {
-    pp2_relevance_token_t prt = pp2_relevance_tokenize(r->pct, words);
+    pp2_relevance_token_t prt = pp2_relevance_tokenize(r->pct, words, 0);
     int *mult = cluster->term_frequency_vec_tmp;
     const char *norm_str;
     int i, length = 0;
@@ -114,7 +114,8 @@ void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
 
     for (i = 1; i < r->vec_len; i++)
     {
-        cluster->term_frequency_vecf[i] += (double) mult[i] / length;
+        if (length > 0) /* only add if non-empty */
+            cluster->term_frequency_vecf[i] += (double) mult[i] / length;
         cluster->term_frequency_vec[i] += mult[i];
     }