Fixes for record cluster merge, PAZ-901

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

diff --git a/src/relevance.c b/src/relevance.c
index 0551980..74f0e15 100644 (file)
--- a/src/relevance.c
+++ b/src/relevance.c
@@ -83,6 +83,55 @@ static struct word_entry *word_entry_match(struct relevance *r,
     return 0;
 }
 
+int relevance_snippet(struct relevance *r,
+                      const char *words, const char *name,
+                      WRBUF w_snippet)
+{
+    int no = 0;
+    const char *norm_str;
+    int highlight = 0;
+
+    pp2_charset_token_first(r->prt, words, 0);
+    while ((norm_str = pp2_charset_token_next(r->prt)))
+    {
+        size_t org_start, org_len;
+        struct word_entry *entries = r->entries;
+        int i;
+
+        pp2_get_org(r->prt, &org_start, &org_len);
+        for (; entries; entries = entries->next, i++)
+        {
+            if (*norm_str && !strcmp(norm_str, entries->norm_str))
+                break;
+        }
+        if (entries)
+        {
+            if (!highlight)
+            {
+                highlight = 1;
+                wrbuf_puts(w_snippet, "<match>");
+                no++;
+            }
+        }
+        else
+        {
+            if (highlight)
+            {
+                highlight = 0;
+                wrbuf_puts(w_snippet, "</match>");
+            }
+        }
+        wrbuf_xmlputs_n(w_snippet, words + org_start, org_len);
+    }
+    if (highlight)
+        wrbuf_puts(w_snippet, "</match>");
+    if (no)
+    {
+        yaz_log(YLOG_DEBUG, "SNIPPET match: %s", wrbuf_cstr(w_snippet));
+    }
+    return no;
+}
+
 void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
                           const char *words, const char *rank,
                           const char *name)
@@ -269,26 +318,35 @@ void relevance_destroy(struct relevance **rp)
     }
 }
 
-void relevance_newrec(struct relevance *r, struct record_cluster *rec)
+void relevance_mergerec(struct relevance *r, struct record_cluster *dst,
+                        const struct record_cluster *src)
 {
-    if (!rec->term_frequency_vec)
-    {
-        int i;
+    int i;
 
-        // term frequency [1,..] . [0] is total length of all fields
-        rec->term_frequency_vec =
-            nmem_malloc(r->nmem,
-                        r->vec_len * sizeof(*rec->term_frequency_vec));
-        for (i = 0; i < r->vec_len; i++)
-            rec->term_frequency_vec[i] = 0;
+    for (i = 0; i < r->vec_len; i++)
+        dst->term_frequency_vec[i] += src->term_frequency_vec[i];
 
-        // term frequency divided by length of field [1,...]
-        rec->term_frequency_vecf =
-            nmem_malloc(r->nmem,
-                        r->vec_len * sizeof(*rec->term_frequency_vecf));
-        for (i = 0; i < r->vec_len; i++)
-            rec->term_frequency_vecf[i] = 0.0;
-    }
+    for (i = 0; i < r->vec_len; i++)
+        dst->term_frequency_vecf[i] += src->term_frequency_vecf[i];
+}
+
+void relevance_newrec(struct relevance *r, struct record_cluster *rec)
+{
+    int i;
+
+    // term frequency [1,..] . [0] is total length of all fields
+    rec->term_frequency_vec =
+        nmem_malloc(r->nmem,
+                    r->vec_len * sizeof(*rec->term_frequency_vec));
+    for (i = 0; i < r->vec_len; i++)
+        rec->term_frequency_vec[i] = 0;
+
+    // term frequency divided by length of field [1,...]
+    rec->term_frequency_vecf =
+        nmem_malloc(r->nmem,
+                    r->vec_len * sizeof(*rec->term_frequency_vecf));
+    for (i = 0; i < r->vec_len; i++)
+        rec->term_frequency_vecf[i] = 0.0;
 }
 
 void relevance_donerecord(struct relevance *r, struct record_cluster *cluster)