-/*
- * Copyright (C) 1994-2002, Index Data
- * All rights reserved.
- *
- * $Id: recgrs.c,v 1.49 2002-05-13 14:13:43 adam Exp $
- */
+/* $Id: recgrs.c,v 1.66 2002-09-02 11:19:33 adam Exp $
+ Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
+ Index Data Aps
+
+This file is part of the Zebra server.
+
+Zebra 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.
+
+Zebra 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 Zebra; see the file LICENSE.zebra. If not, write to the
+Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
+02111-1307, USA.
+*/
#include <stdio.h>
#include <assert.h>
grs_add_handler (h, recTypeGrs_tcl);
#endif
grs_add_handler (h, recTypeGrs_marc);
-#if YAZ_HAVE_EXPAT
+#if HAVE_EXPAT_H
grs_add_handler (h, recTypeGrs_xml);
#endif
return h;
xfree (h);
}
+/* use
+ 1 start element (tag)
+ 2 end element
+ 3 start attr (and attr-exact)
+ 4 end attr
+
+ 1016 cdata
+ 1015 attr data
+*/
+
static void index_xpath (data1_node *n, struct recExtractCtrl *p,
int level, RecWord *wrd, int use)
{
case DATA1N_tag:
for (nn = n; nn; nn = nn->parent)
{
- if (n->which == DATA1N_tag)
+ if (nn->which == DATA1N_tag)
{
size_t tlen = strlen(nn->u.tag.tag);
if (tlen + flen > (sizeof(tag_path_full)-2))
flen += tlen;
tag_path_full[flen++] = '/';
}
- else if (n->which == DATA1N_root)
- {
- size_t tlen = strlen(nn->u.root.type);
- if (tlen + flen > (sizeof(tag_path_full)-2))
- return;
- memcpy (tag_path_full + flen, nn->u.root.type, tlen);
- flen += tlen;
- tag_path_full[flen++] = '/';
+ else if (nn->which == DATA1N_root)
break;
- }
}
wrd->reg_type = '0';
wrd->string = tag_path_full;
wrd->length = flen;
- wrd->attrSet = VAL_IDXPATH,
+ wrd->attrSet = VAL_IDXPATH;
wrd->attrUse = use;
if (p->flagShowRecords)
{
}
else
{
- (*p->tokenAdd)(wrd);
+ data1_xattr *xp;
+ (*p->tokenAdd)(wrd); /* index element pag (AKA tag path) */
+ if (use == 1)
+ {
+ for (xp = n->u.tag.attributes; xp; xp = xp->next)
+ {
+ char comb[512];
+ /* attribute (no value) */
+ wrd->reg_type = '0';
+ wrd->attrUse = 3;
+ wrd->string = xp->name;
+ wrd->length = strlen(xp->name);
+
+ wrd->seqno--;
+ (*p->tokenAdd)(wrd);
+
+ if (xp->value &&
+ strlen(xp->name) + strlen(xp->value) < sizeof(comb)-2)
+ {
+ /* attribute value exact */
+ strcpy (comb, xp->name);
+ strcat (comb, "=");
+ strcat (comb, xp->value);
+
+ wrd->attrUse = 3;
+ wrd->reg_type = '0';
+ wrd->string = comb;
+ wrd->length = strlen(comb);
+ wrd->seqno--;
+
+ (*p->tokenAdd)(wrd);
+ }
+ }
+ for (xp = n->u.tag.attributes; xp; xp = xp->next)
+ {
+ char attr_tag_path_full[1024];
+ int int_len = flen;
+
+ sprintf (attr_tag_path_full, "@%s/%.*s",
+ xp->name, int_len, tag_path_full);
+
+ wrd->reg_type = '0';
+ wrd->attrUse = 1;
+ wrd->string = attr_tag_path_full;
+ wrd->length = strlen(attr_tag_path_full);
+ (*p->tokenAdd)(wrd);
+
+ if (xp->value)
+ {
+ wrd->attrUse = 1015;
+ wrd->reg_type = 'w';
+ wrd->string = xp->value;
+ wrd->length = strlen(xp->value);
+ (*p->tokenAdd)(wrd);
+ }
+
+ wrd->reg_type = '0';
+ wrd->attrUse = 2;
+ wrd->string = attr_tag_path_full;
+ wrd->length = strlen(attr_tag_path_full);
+ (*p->tokenAdd)(wrd);
+ }
+ }
}
- break;
}
}
{
index_termlist (n, n, p, level, wrd);
/* index start tag */
+ assert (n->root->u.root.absyn);
+
if (!n->root->u.root.absyn)
index_xpath (n, p, level, wrd, 1);
+ else if (n->root->u.root.absyn->enable_xpath_indexing)
+ index_xpath (n, p, level, wrd, 1);
}
if (n->child)
{
printf("%*s", level * 4, "");
printf("Data: ");
- if (n->u.data.len > 32)
- printf("'%.24s ... %.6s'\n", n->u.data.data,
+ if (n->u.data.len > 256)
+ printf("'%.240s ... %.6s'\n", n->u.data.data,
n->u.data.data + n->u.data.len-6);
else if (n->u.data.len > 0)
printf("'%.*s'\n", n->u.data.len, n->u.data.data);
index_termlist (par, n, p, level, wrd);
if (!n->root->u.root.absyn)
index_xpath (n, p, level, wrd, 1016);
-
+ else if (n->root->u.root.absyn->enable_xpath_indexing)
+ index_xpath (n, p, level, wrd, 1016);
}
if (n->which == DATA1N_tag)
/* index end tag */
if (!n->root->u.root.absyn)
index_xpath (n, p, level, wrd, 2);
+ else if (n->root->u.root.absyn->enable_xpath_indexing)
+ index_xpath (n, p, level, wrd, 2);
}
-
if (p->flagShowRecords && n->which == DATA1N_root)
{
printf("%*s-------------\n\n", level * 4, "");
(*p->schemaAdd)(p, oidtmp);
}
(*p->init)(p, &wrd);
+
return dumpkeys(n, p, 0, &wrd);
}
gri.dh = p->dh;
if (read_grs_type (h, &gri, p->subType, &n))
- return RECCTRL_EXTRACT_ERROR;
+ return RECCTRL_EXTRACT_ERROR_NO_SUCH_FILTER;
if (!n)
return RECCTRL_EXTRACT_EOF;
oe.proto = PROTO_Z3950;
if ((oid_ent_to_oid (&oe, oidtmp)))
(*p->schemaAdd)(p, oidtmp);
}
+
+ /* ensure our data1 tree is UTF-8 */
+ data1_iconv (p->dh, mem, n, "UTF-8", data1_get_encoding(p->dh, n));
+
#if 0
data1_pr_tree (p->dh, n, stdout);
#endif
+
(*p->init)(p, &wrd);
if (dumpkeys(n, p, 0, &wrd) < 0)
{
data1_free_tree(p->dh, n);
- return RECCTRL_EXTRACT_ERROR;
+ return RECCTRL_EXTRACT_ERROR_GENERIC;
}
data1_free_tree(p->dh, n);
return RECCTRL_EXTRACT_OK;
}
}
+static void add_nice_whitespace (struct recRetrieveCtrl *p, data1_node *top,
+ NMEM mem)
+{
+ data1_node *n = top->child;
+ while (n && n->which == DATA1N_data && n->u.data.what == DATA1I_text)
+ {
+ data1_mk_text_n(p->dh, mem, n->u.data.data, n->u.data.len, top);
+ n = n->next;
+ }
+}
+
+static void add_idzebra_info (struct recRetrieveCtrl *p, data1_node *top,
+ NMEM mem)
+{
+ const char *idzebra_ns[7];
+
+ idzebra_ns[0] = "xmlns:idzebra";
+ idzebra_ns[1] = "http://www.indexdata.dk/zebra/";
+ idzebra_ns[2] = 0;
+
+ data1_tag_add_attr (p->dh, mem, top, idzebra_ns);
+
+ add_nice_whitespace (p, top, mem);
+ data1_mk_tag_data_int (p->dh, top, "idzebra:size", p->recordSize,
+ mem);
+ if (p->score != -1)
+ {
+ add_nice_whitespace (p, top, mem);
+ data1_mk_tag_data_int (p->dh, top, "idzebra:score",
+ p->score, mem);
+ }
+ add_nice_whitespace (p, top, mem);
+ data1_mk_tag_data_int (p->dh, top, "idzebra:localnumber", p->localno,
+ mem);
+ if (p->fname)
+ {
+ add_nice_whitespace (p, top, mem);
+ data1_mk_tag_data_text(p->dh, top, "idzebra:filename",
+ p->fname, mem);
+ }
+}
+
static int grs_retrieve(void *clientData, struct recRetrieveCtrl *p)
{
- data1_node *node = 0, *onode = 0;
+ data1_node *node = 0, *onode = 0, *top;
data1_node *dnew;
data1_maptab *map;
int res, selected = 0;
char *tagname;
struct grs_handlers *h = (struct grs_handlers *) clientData;
int requested_schema = VAL_NONE;
+ data1_marctab *marctab;
+ int dummy;
mem = nmem_create();
gri.readf = p->readf;
nmem_destroy (mem);
return 0;
}
+ /* ensure our data1 tree is UTF-8 */
+ data1_iconv (p->dh, mem, node, "UTF-8", data1_get_encoding(p->dh, node));
+
#if 0
data1_pr_tree (p->dh, node, stdout);
#endif
+ top = data1_get_root_tag (p->dh, node);
+
logf (LOG_DEBUG, "grs_retrieve: size");
- if ((dnew = data1_mk_tag_data_wd(p->dh, node, "size", mem)))
+ if ((dnew = data1_mk_tag_data_wd(p->dh, top, "size", mem)))
{
dnew->u.data.what = DATA1I_text;
dnew->u.data.data = dnew->lbuf;
tagname = res_get_def(p->res, "tagrank", "rank");
if (strcmp(tagname, "0") && p->score >= 0 &&
- (dnew = data1_mk_tag_data_wd(p->dh, node, tagname, mem)))
+ (dnew = data1_mk_tag_data_wd(p->dh, top, tagname, mem)))
{
logf (LOG_DEBUG, "grs_retrieve: %s", tagname);
dnew->u.data.what = DATA1I_num;
tagname = res_get_def(p->res, "tagsysno", "localControlNumber");
if (strcmp(tagname, "0") && p->localno > 0 &&
- (dnew = data1_mk_tag_data_wd(p->dh, node, tagname, mem)))
+ (dnew = data1_mk_tag_data_wd(p->dh, top, tagname, mem)))
{
logf (LOG_DEBUG, "grs_retrieve: %s", tagname);
dnew->u.data.what = DATA1I_text;
dnew->u.data.data = dnew->lbuf;
+
sprintf(dnew->u.data.data, "%d", p->localno);
dnew->u.data.len = strlen(dnew->u.data.data);
}
* the overlap of schema and formatting which is inherent in the MARC
* family)
*/
- logf (LOG_DEBUG, "grs_retrieve: syntax mapping");
+ yaz_log (LOG_DEBUG, "grs_retrieve: syntax mapping");
if (node->u.root.absyn)
for (map = node->u.root.absyn->maptabs; map; map = map->next)
{
break;
}
}
- logf (LOG_DEBUG, "grs_retrieve: schemaIdentifier");
+ yaz_log (LOG_DEBUG, "grs_retrieve: schemaIdentifier");
if (node->u.root.absyn &&
node->u.root.absyn->reference != VAL_NONE &&
p->input_format == VAL_GRS1)
switch (p->output_format = (p->input_format != VAL_NONE ?
p->input_format : VAL_SUTRS))
{
- data1_marctab *marctab;
- int dummy;
-
case VAL_TEXT_XML:
+ add_idzebra_info (p, top, mem);
+
+ if (p->encoding)
+ data1_iconv (p->dh, mem, node, p->encoding, "UTF-8");
+
if (!(p->rec_buf = data1_nodetoidsgml(p->dh, node, selected,
&p->rec_len)))
p->diagnostic = 238;
p->rec_len = (size_t) (-1);
break;
case VAL_SUTRS:
+ if (p->encoding)
+ data1_iconv (p->dh, mem, node, p->encoding, "UTF-8");
if (!(p->rec_buf = data1_nodetobuf(p->dh, node, selected,
&p->rec_len)))
p->diagnostic = 238;
p->diagnostic = 238;
break;
}
+ if (p->encoding)
+ data1_iconv (p->dh, mem, node, p->encoding, "UTF-8");
if (!(p->rec_buf = data1_nodetomarc(p->dh, marctab, node,
selected, &p->rec_len)))
p->diagnostic = 238;
projects / idzebra-moved-to-github.git / blobdiff