X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=index%2Fmod_dom.c;h=f369c68904ccf3734cdd0cc26b5e39af00d55459;hb=896b30853daabb6294afe8b0a2f74fa6d6e397d8;hp=1832b056f06391f4093c3e9bd9d8f0ee5175e414;hpb=30d8682ec25b5468a8158a7a457fe6ca8345d765;p=idzebra-moved-to-github.git

diff --git a/index/mod_dom.c b/index/mod_dom.c
index 1832b05..f369c68 100644
--- a/index/mod_dom.c
+++ b/index/mod_dom.c
@@ -1,4 +1,4 @@
-/* $Id: mod_dom.c,v 1.34 2007-04-07 22:18:46 adam Exp $
+/* $Id: mod_dom.c,v 1.41 2007-10-29 16:57:52 adam Exp $
    Copyright (C) 1995-2007
    Index Data ApS
 
@@ -43,6 +43,7 @@
 
 #include <idzebra/util.h>
 #include <idzebra/recctrl.h>
+#include <yaz/oid_db.h>
 
 /* DOM filter style indexing */
 #define ZEBRA_DOM_NS "http://indexdata.com/zebra-2.0"
@@ -726,7 +727,7 @@ static void index_value_of(struct filter_info *tinfo,
     {
         xmlChar *text = xmlNodeGetContent(node);
         size_t text_len = strlen((const char *)text);
-        
+       
         /* if there is no text, we do not need to proceed */
         if (text_len)
         {            
@@ -776,15 +777,10 @@ static void index_value_of(struct filter_info *tinfo,
                 }
 
                 /* actually indexing the text given */
-                dom_log(YLOG_DEBUG, tinfo, 0, 
-                        "INDEX '%s:%s' '%s'", 
-                        index ? (const char *) index : "null",
-                        type ? (const char *) type : "null", 
-                        text ? (const char *) text : "null");
 
                 recword->index_name = (const char *)index;
                 if (type && *type)
-                    recword->index_type = *type;
+                    recword->index_type = (const char *) type;
 
                 /* writing debug out */
                 if (extctr->flagShowRecords)
@@ -794,10 +790,6 @@ static void index_value_of(struct filter_info *tinfo,
                             type ? (const char *) type : "null", 
                             text ? (const char *) text : "null");
                 
-                /* actually indexing the text given */
-                recword->index_name = (const char *)index;
-                if (type && *type)
-                    recword->index_type = *type;
                 (extctr->tokenAdd)(recword);
 
                 /* eat whitespaces */
@@ -1089,9 +1081,25 @@ static int convert_extract_doc(struct filter_info *tinfo,
     params[0] = 0;
     set_param_str(params, "schema", zebra_dom_ns, tinfo->odr_record);
 
+    if (p && p->flagShowRecords)
+    {
+        xmlChar *buf_out;
+        int len_out;
+#if 0 
+        FILE *outf = fopen("extract.xml", "w");
+        xmlDocDumpMemory(doc, &buf_out, &len_out);
+        fwrite(buf_out, 1, len_out, outf);
+#endif
+        yaz_log(YLOG_LOG, "Extract Doc: %.*s", len_out, buf_out);
+#if 0
+        fclose(outf);
+#endif
+    }
+
     /* input conversion */
     perform_convert(tinfo, p, input->convert, params, &doc, 0);
 
+
     if (tinfo->store)
     {
         /* store conversion */
@@ -1107,7 +1115,8 @@ static int convert_extract_doc(struct filter_info *tinfo,
     else
         xmlDocDumpMemory(store_doc ? store_doc : doc, &buf_out, &len_out);
 
-    (*p->setStoreData)(p, buf_out, len_out);
+    if (p->setStoreData)
+        (*p->setStoreData)(p, buf_out, len_out);
     xmlFree(buf_out);
 
     if (store_doc)
@@ -1275,7 +1284,8 @@ static int extract_iso2709(struct filter_info *tinfo,
     {
         xmlDocPtr rdoc;
         xmlNode *root_ptr;
-        yaz_marc_write_xml(input->u.marc.handle, &root_ptr, 0, 0, 0);
+        yaz_marc_write_xml(input->u.marc.handle, &root_ptr, 
+                           "http://www.loc.gov/MARC21/slim", 0, 0);
         rdoc = xmlNewDoc((const xmlChar*) "1.0");
         xmlDocSetRootElement(rdoc, root_ptr);
         return convert_extract_doc(tinfo, input, p, rdoc);        
@@ -1292,6 +1302,9 @@ static int filter_extract(void *clientData, struct recExtractCtrl *p)
         return RECCTRL_EXTRACT_ERROR_GENERIC;
     
     odr_reset(tinfo->odr_record);
+
+    if (p->setStoreData == 0)
+        return extract_xml_full(tinfo, input, p);
     switch(input->type)
     {
     case DOM_INPUT_XMLREADER:
@@ -1347,6 +1360,7 @@ static int filter_retrieve (void *clientData, struct recRetrieveCtrl *p)
     {
         p->diagnostic =
             YAZ_BIB1_SPECIFIED_ELEMENT_SET_NAME_NOT_VALID_FOR_SPECIFIED_;
+        p->addinfo = odr_strdup(p->odr, esn);
         return 0;
     }
 
@@ -1387,7 +1401,8 @@ static int filter_retrieve (void *clientData, struct recRetrieveCtrl *p)
     {
         p->diagnostic = YAZ_BIB1_SYSTEM_ERROR_IN_PRESENTING_RECORDS;
     }
-    else if (p->input_format == VAL_NONE || p->input_format == VAL_TEXT_XML)
+    else if (!p->input_format
+             || !oid_oidcmp(p->input_format, yaz_oid_recsyn_xml))
     {
         xmlChar *buf_out;
         int len_out;
@@ -1397,13 +1412,13 @@ static int filter_retrieve (void *clientData, struct recRetrieveCtrl *p)
         else
             xmlDocDumpMemory(doc, &buf_out, &len_out);            
 
-        p->output_format = VAL_TEXT_XML;
+        p->output_format = yaz_oid_recsyn_xml;
         p->rec_len = len_out;
         p->rec_buf = odr_malloc(p->odr, p->rec_len);
         memcpy(p->rec_buf, buf_out, p->rec_len);
         xmlFree(buf_out);
     }
-    else if (p->output_format == VAL_SUTRS)
+    else if (!oid_oidcmp(p->output_format, yaz_oid_recsyn_sutrs))
     {
         xmlChar *buf_out;
         int len_out;
@@ -1413,7 +1428,7 @@ static int filter_retrieve (void *clientData, struct recRetrieveCtrl *p)
         else
             xmlDocDumpMemory(doc, &buf_out, &len_out);            
         
-        p->output_format = VAL_SUTRS;
+        p->output_format = yaz_oid_recsyn_sutrs;
         p->rec_len = len_out;
         p->rec_buf = odr_malloc(p->odr, p->rec_len);
         memcpy(p->rec_buf, buf_out, p->rec_len);