-/* $Id: recgrs.c,v 1.1 2006-07-03 14:27:09 adam Exp $
+/* $Id: recgrs.c,v 1.6 2006-09-28 18:38:47 adam Exp $
Copyright (C) 1995-2006
Index Data ApS
for more details.
You should have received a copy of the GNU General Public License
-along with Zebra; see the file LICENSE.zebra. If not, write to the
-Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
-02111-1307, USA.
+along with this program; if not, write to the Free Software
+Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
*/
#include <stdio.h>
data1_termlist *xpath_termlist_by_tagpath(char *tagpath, data1_node *n)
{
data1_absyn *abs = n->root->u.root.absyn;
- data1_xpelement *xpe = abs->xp_elements;
+
+ data1_xpelement *xpe = 0;
data1_node *nn;
#ifdef ENHANCED_XELM
struct xpath_location_step *xp;
#endif
char *pexpr = xmalloc(strlen(tagpath)+5);
- int ok = 0;
sprintf (pexpr, "/%s\n", tagpath);
- for (; xpe; xpe = xpe->next)
+
+ for (xpe = abs->xp_elements; xpe; xpe = xpe->next)
+ xpe->match_state = -1; /* don't know if it matches yet */
+
+ for (xpe = abs->xp_elements; xpe; xpe = xpe->next)
{
int i;
- ok = dfa_match_first(xpe->dfa->states, pexpr);
+ int ok = xpe->match_state;
+ if (ok == -1)
+ { /* don't know whether there is a match yet */
+ data1_xpelement *xpe1;
+ assert(xpe->dfa);
+ ok = dfa_match_first(xpe->dfa->states, pexpr);
+
+#if OPTIMIZE_MELM
+ /* mark this and following ones with same regexp */
+ for (xpe1 = xpe; xpe1; xpe1 = xpe1->next)
+ {
+ if (!strcmp(xpe1->regexp, xpe->regexp))
+ xpe1->match_state = ok;
+ }
+#endif
+ }
+ assert (ok == 0 || ok == 1);
if (ok) {
#ifdef ENHANCED_XELM
/* we have to check the perdicates up to the root node */
xfree(pexpr);
- if (ok) {
+ if (xpe) {
yaz_log(YLOG_DEBUG, "Got it");
return xpe->termlists;
} else {
}
(*p->init)(p, &wrd);
+ /* data1_pr_tree(p->dh, n, stdout); */
+
return dumpkeys(n, p, &wrd);
}
int oidtmp[OID_SIZE];
RecWord wrd;
- gri.readf = p->readf;
- gri.seekf = p->seekf;
- gri.tellf = p->tellf;
- gri.endf = p->endf;
- gri.fh = p->fh;
- gri.offset = p->offset;
+ gri.stream = p->stream;
gri.mem = mem;
gri.dh = p->dh;
gri.clientData = clientData;
/* ensure our data1 tree is UTF-8 */
data1_iconv (p->dh, mem, n, "UTF-8", data1_get_encoding(p->dh, n));
+
+ data1_remove_idzebra_subtree (p->dh, n);
+
#if 0
data1_pr_tree (p->dh, n, stdout);
#endif
(*p->init)(p, &wrd);
if (dumpkeys(n, p, &wrd) < 0)
{
- data1_free_tree(p->dh, n);
return RECCTRL_EXTRACT_ERROR_GENERIC;
}
- data1_free_tree(p->dh, n);
return RECCTRL_EXTRACT_OK;
}
int dummy;
mem = nmem_create();
- gri.readf = p->readf;
- gri.seekf = p->seekf;
- gri.tellf = p->tellf;
- gri.endf = NULL;
- gri.fh = p->fh;
- gri.offset = 0;
+ gri.stream = p->stream;
gri.mem = mem;
gri.dh = p->dh;
gri.clientData = clientData;
}
data1_concat_text(p->dh, mem, node);
+ data1_remove_idzebra_subtree (p->dh, node);
+
#if 0
data1_pr_tree (p->dh, node, stdout);
#endif
p->odr)) > 0)
{
p->diagnostic = res;
- if (onode)
- data1_free_tree(p->dh, onode);
- data1_free_tree(p->dh, node);
nmem_destroy(mem);
return 0;
}
p->rec_buf = new_buf;
}
}
- if (node)
- data1_free_tree(p->dh, node);
- if (onode)
- data1_free_tree(p->dh, onode);
nmem_destroy(mem);
return 0;
}