GPLv2. Added appendix with full license. Added refernece to that from

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

diff --git a/src/termlists.c b/src/termlists.c
index e586169..cd8fe72 100644 (file)
--- a/src/termlists.c
+++ b/src/termlists.c
@@ -1,9 +1,27 @@
-/*
- * $Id: termlists.c,v 1.2 2007-01-08 12:43:41 adam Exp $
+/* $Id: termlists.c,v 1.7 2007-04-10 08:48:56 adam Exp $
+   Copyright (c) 2006-2007, Index Data.
+
+This file is part of Pazpar2.
+
+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
+Software Foundation; either version 2, or (at your option) any later
+version.
+
+Pazpar2 is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+You should have received a copy of the GNU General Public License
+along with Pazpar2; see the file LICENSE.  If not, write to the
+Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
+02111-1307, USA.
  */
 
 #include <stdlib.h>
 #include <string.h>
+#include <ctype.h>
 #include <yaz/yaz-util.h>
 
 #if HAVE_CONFIG_H
@@ -69,7 +87,7 @@ struct termlist *termlist_create(NMEM nmem, int numterms, int highscore_size)
         hashsize <<= 1;
     res = nmem_malloc(nmem, sizeof(struct termlist));
     res->hashtable = nmem_malloc(nmem, hashsize * sizeof(struct termlist_bucket*));
-    bzero(res->hashtable, hashsize * sizeof(struct termlist_bucket*));
+    memset(res->hashtable, 0, hashsize * sizeof(struct termlist_bucket*));
     res->hashtable_size = hashsize;
     res->nmem = nmem;
     res->hashmask = hashsize - 1; // Creates a bitmask
@@ -88,7 +106,7 @@ static void update_highscore(struct termlist *tl, struct termlist_score *t)
     int smallest;
     int me = -1;
 
-    if (t->frequency < tl->highscore_min)
+    if (tl->highscore_num > tl->highscore_size && t->frequency < tl->highscore_min)
         return;
 
     smallest = 0;
@@ -101,6 +119,8 @@ static void update_highscore(struct termlist *tl, struct termlist_score *t)
     }
     if (tl->highscore_num)
         tl->highscore_min = tl->highscore[smallest]->frequency;
+    if (t->frequency < tl->highscore_min)
+        tl->highscore_min = t->frequency;
     if (me >= 0)
         return;
     if (tl->highscore_num < tl->highscore_size)
@@ -122,11 +142,19 @@ void termlist_insert(struct termlist *tl, const char *term)
 {
     unsigned int bucket;
     struct termlist_bucket **p;
+    char buf[256], *cp;
+
+    if (strlen(term) > 255)
+        return;
+    strcpy(buf, term);
+    for (cp = buf + strlen(buf) - 1; cp > buf &&
+            (*cp == ',' || *cp == '.' || *cp == ' ' || *cp == '-'); cp--)
+        *cp = '\0';
 
-    bucket = hash((unsigned char *)term) & tl->hashmask;
+    bucket = hash((unsigned char *)buf) & tl->hashmask;
     for (p = &tl->hashtable[bucket]; *p; p = &(*p)->next)
     {
-        if (!strcmp(term, (*p)->term.term))
+        if (!strcmp(buf, (*p)->term.term))
         {
             (*p)->term.frequency++;
             update_highscore(tl, &((*p)->term));
@@ -137,7 +165,7 @@ void termlist_insert(struct termlist *tl, const char *term)
     {
         struct termlist_bucket *new = nmem_malloc(tl->nmem,
                 sizeof(struct termlist_bucket));
-        new->term.term = nmem_strdup(tl->nmem, term);
+        new->term.term = nmem_strdup(tl->nmem, buf);
         new->term.frequency = 1;
         new->next = 0;
         *p = new;