X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=index%2Fextract.c;h=aed06509d9995f7d750a8ce62bfac2a012342970;hb=e4b67f7065d49c87839442f19f72141098d16920;hp=5be148815d0c6c1c593b9f652ef5a71f48211f21;hpb=3731bdaf94aeba2550fc553aebe34831c203dc36;p=idzebra-moved-to-github.git

diff --git a/index/extract.c b/index/extract.c
index 5be1488..aed0650 100644
--- a/index/extract.c
+++ b/index/extract.c
@@ -1,4 +1,4 @@
-/* $Id: extract.c,v 1.270 2007-11-30 12:19:08 adam Exp $
+/* $Id: extract.c,v 1.273 2007-12-13 11:09:20 adam Exp $
    Copyright (C) 1995-2007
    Index Data ApS
 
@@ -265,6 +265,26 @@ static void snippet_add_incomplete_field(RecWord *p, int ord, zebra_map_t zm)
 
 }
 
+static void snippet_add_icu(RecWord *p, int ord, zebra_map_t zm)
+{
+    struct snip_rec_info *h = p->extractCtrl->handle;
+
+    const char *res_buf = 0;
+    size_t res_len = 0;
+
+    const char *display_buf = 0;
+    size_t display_len = 0;
+
+    zebra_map_tokenize_start(zm, p->term_buf, p->term_len);
+    while (zebra_map_tokenize_next(zm, &res_buf, &res_len,
+                                   &display_buf, &display_len))
+    {
+        zebra_snippets_appendn(h->snippets, p->seqno, 0, ord,
+                               display_buf, display_len);
+        p->seqno++;
+    }
+}
+
 static void snippet_token_add(RecWord *p)
 {
     struct snip_rec_info *h = p->extractCtrl->handle;
@@ -277,10 +297,15 @@ static void snippet_token_add(RecWord *p)
         int ch = zebraExplain_lookup_attr_str(
             zei, zinfo_index_category_index, p->index_type, p->index_name);
 
-        if (zebra_maps_is_complete(zm))
-            snippet_add_complete_field(p, ch, zm);
+        if (zebra_maps_is_icu(zm))
+            snippet_add_icu(p, ch, zm);
         else
-            snippet_add_incomplete_field(p, ch, zm);
+        {
+            if (zebra_maps_is_complete(zm))
+                snippet_add_complete_field(p, ch, zm);
+            else
+                snippet_add_incomplete_field(p, ch, zm);
+        }
     }
 }
 
@@ -1456,7 +1481,7 @@ void extract_flush_record_keys2(ZebraHandle zh, zint sysno,
 }
 
 
-ZEBRA_RES zebra_rec_keys_to_snippets(ZebraHandle zh,
+ZEBRA_RES zebra_rec_keys_to_snippets1(ZebraHandle zh,
                                      zebra_rec_keys_t reckeys,
                                      zebra_snippets *snippets)
 {
@@ -1729,13 +1754,15 @@ static void extract_add_icu(RecWord *p, zebra_map_t zm)
     const char *res_buf = 0;
     size_t res_len = 0;
     ZebraHandle zh = p->extractCtrl->handle;
-    int r = zebra_map_tokenize(zm, p->term_buf, p->term_len,
-                               &res_buf, &res_len);
+    
     int cat = zinfo_index_category_index;
-    int ch = zebraExplain_lookup_attr_str(zh->reg->zei, cat, p->index_type, p->index_name);
+    int ch = zebraExplain_lookup_attr_str(zh->reg->zei, cat, 
+                                          p->index_type, p->index_name);
     if (ch < 0)
-        ch = zebraExplain_add_attr_str(zh->reg->zei, cat, p->index_type, p->index_name);
-    while (r)
+        ch = zebraExplain_add_attr_str(zh->reg->zei, cat, 
+                                       p->index_type, p->index_name);
+    zebra_map_tokenize_start(zm, p->term_buf, p->term_len);
+    while (zebra_map_tokenize_next(zm, &res_buf, &res_len, 0, 0))
     {
         int i = 0;
         key.mem[i++] = ch;
@@ -1750,7 +1777,6 @@ static void extract_add_icu(RecWord *p, zebra_map_t zm)
         zebra_rec_keys_write(zh->reg->keys, res_buf, res_len, &key);
         
         p->seqno++;
-        r = zebra_map_tokenize(zm, 0, 0, &res_buf, &res_len);
     }
 }
 
@@ -1759,8 +1785,8 @@ static void extract_add_icu(RecWord *p, zebra_map_t zm)
     \param p token data to be indexed
 
     Call sequence:
-    extract_token
-    zebra_add_{in}_complete
+    extract_token_add
+    extract_add_{in}_complete
     extract_add_string
     
     extract_add_index_string