-# $Id: Makefile.am,v 1.26 2007-10-23 12:26:25 adam Exp $
+# $Id: Makefile.am,v 1.27 2007-10-24 13:55:55 adam Exp $
noinst_HEADERS = bset.h charmap.h \
direntz.h passwddb.h dfa.h zebra_xpath.h d1_absyn.h \
rset.h dfaset.h sortidx.h zebra-lock.h attrfind.h zebramap.h \
- it_key.h su_codec.h index_rules.h rob_regexp.h
+ it_key.h su_codec.h index_rules.h
SUBDIRS = idzebra
+++ /dev/null
-/* $Id: rob_regexp.h,v 1.2 2007-10-23 12:36:22 adam Exp $
- Copyright (C) 1995-2007
- 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 this program; if not, write to the Free Software
-Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-
-*/
-
-/**
- \file rob_regexp.h
- \brief Rob Pike's regular expression matcher
-*/
-
-#ifndef ZEBRA_ROB_REGEXP_H
-#define ZEBRA_ROB_REGEXP_H
-
-#include <yaz/yconfig.h>
-
-YAZ_BEGIN_CDECL
-
-/** \brief matches a regular expression against text
- \param regexp regular expression
- \param text the text
- \retval 0 no match
- \retval 1 match
-
- Operators: c (literal char), . (any char), ^ (begin), $ (end),
- * (zero or more)
-*/
-int zebra_rob_regexp(const char *regexp, const char *text);
-
-YAZ_END_CDECL
-
-#endif
-/*
- * Local variables:
- * c-basic-offset: 4
- * indent-tabs-mode: nil
- * End:
- * vim: shiftwidth=4 tabstop=8 expandtab
- */
-
-## $Id: Makefile.am,v 1.34 2007-10-23 12:26:26 adam Exp $
+## $Id: Makefile.am,v 1.35 2007-10-24 13:55:55 adam Exp $
noinst_LTLIBRARIES = libidzebra-util.la
libidzebra_util_la_SOURCES = version.c zint.c res.c charmap.c zebramap.c \
passwddb.c zebra-lock.c dirent.c xpath.c atoi_zn.c snippet.c flock.c \
- attrfind.c exit.c it_key.c su_codec.c index_rules.c rob_regexp.c
+ attrfind.c exit.c it_key.c su_codec.c index_rules.c
tstpass_SOURCES = tstpass.c
-/* $Id: index_rules.c,v 1.1 2007-10-23 12:26:26 adam Exp $
+/* $Id: index_rules.c,v 1.2 2007-10-24 13:55:55 adam Exp $
Copyright (C) 1995-2007
Index Data ApS
#include <string.h>
#include "index_rules.h"
-#include "rob_regexp.h"
+#include <yaz/match_glob.h>
#include <yaz/xmalloc.h>
#include <yaz/wrbuf.h>
#include <yaz/log.h>
struct zebra_index_rules_s {
- WRBUF last_id;
#if YAZ_HAVE_XML2
struct zebra_index_rule *rules;
- struct zebra_index_rule *last_rule_match;
xmlDocPtr doc;
#endif
};
const xmlNode *top = xmlDocGetRootElement(doc);
r->doc = doc;
- r->last_rule_match = 0;
- r->last_id = wrbuf_alloc();
*rp = 0;
if (top && top->type == XML_ELEMENT_NODE
&& !strcmp((const char *) top->name, "indexrules"))
xmlFreeDoc(r->doc);
#endif
- wrbuf_destroy(r->last_id);
xfree(r);
}
const char *zebra_index_rule_lookup_str(zebra_index_rules_t r, const char *id)
{
#if YAZ_HAVE_XML2
- if (r->last_rule_match && !strcmp(wrbuf_cstr(r->last_id), id))
- return r->last_rule_match->id;
- else
- {
- struct zebra_index_rule *rule = r->rules;
+
+ struct zebra_index_rule *rule = r->rules;
- wrbuf_rewind(r->last_id);
- wrbuf_puts(r->last_id, id);
- while (rule && !zebra_rob_regexp(rule->id, id))
- rule = rule->next;
- r->last_rule_match = rule;
- if (rule)
- return rule->id;
- }
+ while (rule && !yaz_match_glob(rule->id, id))
+ rule = rule->next;
+ if (rule)
+ return rule->id;
#endif
return 0;
}
+++ /dev/null
-/* $Id: rob_regexp.c,v 1.2 2007-10-23 12:36:22 adam Exp $
- Copyright (C) 1995-2007
- 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.
-*/
-
-/**
- \file rob_regexp.c
- \brief Rob Pike's regular expression matcher
-
- Taken verbatim from Beautiful code.. ANSIfied a bit.
- */
-
-
-#include <assert.h>
-#include <stdlib.h>
-#include <ctype.h>
-#include <string.h>
-
-#include "rob_regexp.h"
-#include <yaz/xmalloc.h>
-#include <yaz/wrbuf.h>
-#include <yaz/log.h>
-
-static int matchhere(const char *regexp, const char *text);
-static int matchstar(int c, const char *regexp, const char *text);
-
-int zebra_rob_regexp(const char *regexp, const char *text)
-{
- if (regexp[0] == '^')
- return matchhere(regexp+1, text);
- do
- {
- if (matchhere(regexp, text))
- return 1;
- }
- while (*text++);
- return 0;
-}
-
-static int matchhere(const char *regexp, const char *text)
-{
- if (regexp[0] == '\0')
- return 1;
- if (regexp[1] == '*')
- return matchstar(regexp[0], regexp+2, text);
- if (regexp[0] == '$' && regexp[1] == '\0')
- return *text == '\0';
- if (*text && (regexp[0] == '.' || regexp[0] == *text))
- return matchhere(regexp+1, text+1);
- return 0;
-}
-
-static int matchstar(int c, const char *regexp, const char *text)
-{
- do
- {
- if (matchhere(regexp, text))
- return 1;
- }
- while (*text && (*text++ == c || c == '.'));
- return 0;
-}
-
-
-/*
- * Local variables:
- * c-basic-offset: 4
- * indent-tabs-mode: nil
- * End:
- * vim: shiftwidth=4 tabstop=8 expandtab
- */
-
-/* $Id: tst_index_rules.c,v 1.1 2007-10-23 12:26:26 adam Exp $
+/* $Id: tst_index_rules.c,v 1.2 2007-10-24 13:55:55 adam Exp $
Copyright (C) 1995-2007
Index Data ApS
const char *xml_str =
" <indexrules>"
-" <indexrule id=\"^.*:w:el$\" position=\"1\" alwaysmatches=\"1\" firstinfield=\"1\"\n"
+" <indexrule id=\"*:w:el\" position=\"1\" alwaysmatches=\"1\" firstinfield=\"1\"\n"
" locale=\"el\">\n"
" <!-- conversion rules for words -->\n"
" </indexrule>\n"
-" <indexrule id=\"^.*:w$\" position=\"1\" alwaysmatches=\"1\" firstinfield=\"1\"\n"
+" <indexrule id=\"*:w\" position=\"1\" alwaysmatches=\"1\" firstinfield=\"1\"\n"
" locale=\"en\">\n"
" <!-- conversion rules for words -->\n"
" </indexrule>\n"
-" <indexrule id=\"^.*:p$\" position=\"0\" alwaysmatches=\"0\" firstinfield=\"0\"\n"
+" <indexrule id=\"*:p\" position=\"0\" alwaysmatches=\"0\" firstinfield=\"0\"\n"
" locale=\"en\">\n"
" <!-- conversion rules for phrase -->\n"
" </indexrule>\n"
-" <indexrule id=\"^.*:s$\" sort=\"1\" \n"
+" <indexrule id=\"*:s\" sort=\"1\" \n"
" locale=\"en\">\n"
" <!-- conversion rules for phrase -->\n"
" </indexrule>\n"
if (!rules)
return ;
- YAZ_CHECK(compare_lookup(rules, "title:s", "^.*:s$"));
+ YAZ_CHECK(compare_lookup(rules, "title:s", "*:s"));
YAZ_CHECK(compare_lookup(rules, "title:sx", 0));
YAZ_CHECK(compare_lookup(rules, "title:Sx", 0));
- YAZ_CHECK(compare_lookup(rules, "any:w", "^.*:w$"));
+ YAZ_CHECK(compare_lookup(rules, "any:w", "*:w"));
YAZ_CHECK(compare_lookup(rules, "any:w:en", 0));
- YAZ_CHECK(compare_lookup(rules, "any:w:el", "^.*:w:el$"));
+ YAZ_CHECK(compare_lookup(rules, "any:w:el", "*:w:el"));
{
int i, iter = 3333;
for (i = 0; i < iter; i++)
{
- compare_lookup(rules, "title:s", "^.*:s$");
+ compare_lookup(rules, "title:s", "*:s");
compare_lookup(rules, "title:sx", 0);
compare_lookup(rules, "title:Sx", 0);
}