X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=src%2Frelevance.c;h=35b7d8312c040b677350d28a3485addcea460f7a;hb=48e0165508cf435576b6b479ef504d9fba7da66a;hp=c88676eab5cb1bc1d04a18e84f7080ee1b505feb;hpb=6a3be08c0fb5c7ad1f14168435b3de51028945d2;p=pazpar2-moved-to-github.git

diff --git a/src/relevance.c b/src/relevance.c
index c88676e..35b7d83 100644
--- a/src/relevance.c
+++ b/src/relevance.c
@@ -1,5 +1,5 @@
 /* This file is part of Pazpar2.
-   Copyright (C) 2006-2009 Index Data
+   Copyright (C) 2006-2010 Index Data
 
 Pazpar2 is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free
@@ -26,14 +26,14 @@ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 #include <stdlib.h>
 
 #include "relevance.h"
-#include "pazpar2.h"
+#include "session.h"
 
 struct relevance
 {
     int *doc_frequency_vec;
     int vec_len;
     struct word_entry *entries;
-    pp2_charset_t pct;
+    pp2_relevance_token_t prt;
     NMEM nmem;
 };
 
@@ -68,7 +68,8 @@ int word_entry_match(struct word_entry *entries, const char *norm_str)
     return 0;
 }
 
-static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem,
+static struct word_entry *build_word_entries(pp2_relevance_token_t prt,
+                                             NMEM nmem,
                                              const char **terms)
 {
     int termno = 1; /* >0 signals THERE is an entry */
@@ -77,14 +78,11 @@ 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);
         const char *norm_str;
 
+        pp2_relevance_first(prt, *p, 0);
         while ((norm_str = pp2_relevance_token_next(prt)))
             add_word_entry(nmem, &entries, norm_str, termno);
-
-        pp2_relevance_token_destroy(prt);
-
         termno++;
     }
     return entries;
@@ -93,15 +91,15 @@ 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);
     int *mult = cluster->term_frequency_vec_tmp;
     const char *norm_str;
     int i, length = 0;
 
+    pp2_relevance_first(r->prt, words, 0);
     for (i = 1; i < r->vec_len; i++)
         mult[i] = 0;
 
-    while ((norm_str = pp2_relevance_token_next(prt)))
+    while ((norm_str = pp2_relevance_token_next(r->prt)))
     {
         int res = word_entry_match(r->entries, norm_str);
         if (res)
@@ -120,7 +118,6 @@ void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
     }
 
     cluster->term_frequency_vec[0] += length;
-    pp2_relevance_token_destroy(prt);
 }
 
 struct relevance *relevance_create(pp2_charset_t pct,
@@ -136,11 +133,20 @@ struct relevance *relevance_create(pp2_charset_t pct,
     res->doc_frequency_vec = nmem_malloc(nmem, res->vec_len * sizeof(int));
     memset(res->doc_frequency_vec, 0, res->vec_len * sizeof(int));
     res->nmem = nmem;
-    res->entries = build_word_entries(pct, nmem, terms);
-    res->pct = pct;
+    res->prt = pp2_relevance_tokenize(pct);
+    res->entries = build_word_entries(res->prt, nmem, terms);
     return res;
 }
 
+void relevance_destroy(struct relevance **rp)
+{
+    if (*rp)
+    {
+        pp2_relevance_token_destroy((*rp)->prt);
+        *rp = 0;
+    }
+}
+
 void relevance_newrec(struct relevance *r, struct record_cluster *rec)
 {
     if (!rec->term_frequency_vec)
@@ -186,7 +192,7 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist)
     int i;
     float *idfvec = xmalloc(rel->vec_len * sizeof(float));
 
-    reclist_rewind(reclist);
+    reclist_enter(reclist);
     // Calculate document frequency vector for each term.
     for (i = 1; i < rel->vec_len; i++)
     {
@@ -230,9 +236,9 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist)
 #endif
             relevance += 100000 * (termfreq * idfvec[t] + 0.0000005);  
         }
-        rec->relevance = relevance;
+        rec->relevance_score = relevance;
     }
-    reclist_rewind(reclist);
+    reclist_leave(reclist);
     xfree(idfvec);
 }