+Fix MARC transfer . MARC fields had wrong data for multiple fields.
+
+XML record reader moved from YAZ to Zebra, to make YAZ less
+dependant on external libraries.
+
+Zebra uses yaz_iconv which is mini iconv library supporting UTF-8,
+UCS4, ISO-8859-1. This means that Zebra does UNICODE even
+on systems that doesn't offer iconv.
+
+XML record reader supports external system entities.
+
--- 1.3.1 2002/08/20
New .abs-directive "xpath" that takes one argument: "enable"
-/* $Id: index.h,v 1.85 2002-08-02 19:26:55 adam Exp $
+/* $Id: index.h,v 1.86 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
#include <sys/times.h>
#endif
-#if HAVE_ICONV_H
-#include <iconv.h>
-#endif
-
#include <dict.h>
#include <isams.h>
#include <isam.h>
int records_deleted;
int records_processed;
char *record_encoding;
-#if HAVE_ICONV_H
- iconv_t iconv_to_utf8;
- iconv_t iconv_from_utf8;
-#endif
+
+ yaz_iconv_t iconv_to_utf8;
+ yaz_iconv_t iconv_from_utf8;
};
struct rank_control {
-/* $Id: zebraapi.c,v 1.67 2002-08-18 10:20:35 adam Exp $
+/* $Id: zebraapi.c,v 1.68 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
default_encoding = res_get_def(zs->global_res, "encoding", "ISO-8859-1");
zh->record_encoding = xstrdup (default_encoding);
-#if HAVE_ICONV_H
+
zh->iconv_to_utf8 =
- iconv_open ("UTF-8", default_encoding);
- if (zh->iconv_to_utf8 == (iconv_t)(-1))
+ yaz_iconv_open ("UTF-8", default_encoding);
+ if (zh->iconv_to_utf8 == 0)
yaz_log (LOG_WARN, "iconv: %s to UTF-8 unsupported",
default_encoding);
zh->iconv_from_utf8 =
- iconv_open (default_encoding, "UTF-8");
- if (zh->iconv_to_utf8 == (iconv_t)(-1))
+ yaz_iconv_open (default_encoding, "UTF-8");
+ if (zh->iconv_to_utf8 == 0)
yaz_log (LOG_WARN, "iconv: UTF-8 to %s unsupported",
default_encoding);
-#endif
zebra_mutex_cond_lock (&zs->session_lock);
zebra_close_res (zh);
xfree (zh->record_encoding);
-#if HAVE_ICONV_H
- if (zh->iconv_to_utf8 != (iconv_t) (-1))
- iconv_close (zh->iconv_to_utf8);
- if (zh->iconv_from_utf8 != (iconv_t) (-1))
- iconv_close (zh->iconv_from_utf8);
-#endif
+
+ if (zh->iconv_to_utf8 != 0)
+ yaz_iconv_close (zh->iconv_to_utf8);
+ if (zh->iconv_from_utf8 != 0)
+ yaz_iconv_close (zh->iconv_from_utf8);
xfree (zh->admin_databaseName);
zebra_mutex_cond_lock (&zs->session_lock);
-/* $Id: zrpn.c,v 1.121 2002-08-23 14:30:51 adam Exp $
+/* $Id: zrpn.c,v 1.122 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
switch (term->which)
{
case Z_Term_general:
-#if HAVE_ICONV_H
- if (zh->iconv_to_utf8 != (iconv_t)(-1))
+ if (zh->iconv_to_utf8 != 0)
{
char *inbuf = term->u.general->buf;
size_t inleft = term->u.general->len;
size_t ret;
yaz_log (LOG_DEBUG, "converting general from ISO-8859-1");
- ret = iconv(zh->iconv_to_utf8, &inbuf, &inleft,
+ ret = yaz_iconv(zh->iconv_to_utf8, &inbuf, &inleft,
&outbuf, &outleft);
if (ret == (size_t)(-1))
{
- ret = iconv(zh->iconv_to_utf8, 0, 0, 0, 0);
+ ret = yaz_iconv(zh->iconv_to_utf8, 0, 0, 0, 0);
zh->errCode = 125;
return -1;
}
*outbuf = 0;
return 0;
}
-#endif
sizez = term->u.general->len;
if (sizez > IT_MAX_WORD-1)
sizez = IT_MAX_WORD-1;
-/* $Id: zsets.c,v 1.38 2002-08-02 19:26:56 adam Exp $
+/* $Id: zsets.c,v 1.39 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
size_t inleft = strlen(inbuf);
size_t outleft = *len - 1;
int converted = 0;
-#if HAVE_ICONV_H
- if (zh->iconv_from_utf8 != (iconv_t)(-1))
+
+ if (zh->iconv_from_utf8 != 0)
{
char *outbuf = out;
size_t ret;
- ret = iconv(zh->iconv_from_utf8, &inbuf, &inleft,
+ ret = yaz_iconv(zh->iconv_from_utf8, &inbuf, &inleft,
&outbuf, &outleft);
if (ret == (size_t)(-1))
*len = 0;
*len = outbuf - out;
converted = 1;
}
-#endif
if (!converted)
{
if (inleft > outleft)
-/* $Id: recgrs.c,v 1.62 2002-08-28 12:47:10 adam Exp $
+/* $Id: recgrs.c,v 1.63 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
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, flen, tag_path_full);
+ xp->name, int_len, tag_path_full);
wrd->reg_type = '0';
wrd->attrUse = 1;
-/* $Id: charmap.c,v 1.25 2002-08-02 19:26:57 adam Exp $
+/* $Id: charmap.c,v 1.26 2002-08-28 19:52:29 adam Exp $
Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
Index Data Aps
#include <string.h>
#include <assert.h>
-#if HAVE_ICONV_H
-#include <iconv.h>
-#else
-typedef int iconv_t;
-static size_t iconv(iconv_t t, char **buf, size_t *inbytesleft,
- char **outbuf, size_t *outbytesleft)
-{
- return -1;
-}
-#endif
-
typedef unsigned ucs4_t;
#include <yaz/yaz-util.h>
logf (LOG_DEBUG, " %3d", (unsigned char) *s);
}
-static int scan_to_utf8 (iconv_t t, ucs4_t *from, size_t inlen,
+static int scan_to_utf8 (yaz_iconv_t t, ucs4_t *from, size_t inlen,
char *outbuf, size_t outbytesleft)
{
size_t inbytesleft = inlen * sizeof(ucs4_t);
char *inbuf = (char*) from;
size_t ret;
- if (t == (iconv_t)(-1))
+ if (t == 0)
*outbuf++ = *from; /* ISO-8859-1 is OK here */
else
{
- ret = iconv (t, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ ret = yaz_iconv (t, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (ret == (size_t) (-1))
{
yaz_log (LOG_WARN|LOG_ERRNO, "bad unicode sequence");
}
static int scan_string(char *s_native,
- iconv_t t_unicode, iconv_t t_utf8,
+ yaz_iconv_t t_unicode, yaz_iconv_t t_utf8,
void (*fun)(const char *c, void *data, int num),
void *data, int *num)
{
ucs4_t arg[512];
ucs4_t *s0, *s = arg;
ucs4_t c, begin, end;
- size_t i, j;
+ size_t i;
- if (t_unicode != (iconv_t)(-1))
+ if (t_unicode != 0)
{
char *outbuf = (char *) arg;
char *inbuf = s_native;
size_t outbytesleft = sizeof(arg)-4;
size_t inbytesleft = strlen(s_native);
size_t ret;
- ret = iconv(t_unicode, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ ret = yaz_iconv(t_unicode, &inbuf, &inbytesleft,
+ &outbuf, &outbytesleft);
if (ret == (size_t)(-1))
return -1;
i = (outbuf - (char*) arg)/sizeof(ucs4_t);
int errors = 0;
int argc, num = (int) *CHR_BASE, i;
NMEM nmem;
- iconv_t t_unicode = (iconv_t)(-1);
- iconv_t t_utf8 = (iconv_t)(-1);
+ yaz_iconv_t t_unicode = 0;
+ yaz_iconv_t t_utf8 = 0;
unsigned endian = 31;
const char *ucs4_native = "UCS-4";
if (*(char*) &endian == 31) /* little endian? */
ucs4_native = "UCS-4LE";
-#if HAVE_ICONV_H
- t_utf8 = iconv_open ("UTF-8", ucs4_native);
-#endif
+ t_utf8 = yaz_iconv_open ("UTF-8", ucs4_native);
logf (LOG_DEBUG, "maptab %s open", name);
if (!(f = yaz_fopen(tabpath, name, "r", tabroot)))
{
}
else if (!yaz_matchstr(argv[0], "encoding"))
{
-#if HAVE_ICONV_H
- if (t_unicode != (iconv_t)(-1))
- iconv_close (t_unicode);
- t_unicode = iconv_open (ucs4_native, argv[1]);
-#else
- logf (LOG_WARN, "Encoding ignored. iconv not installed");
-#endif
+ if (t_unicode != 0)
+ yaz_iconv_close (t_unicode);
+ t_unicode = yaz_iconv_open (ucs4_native, argv[1]);
}
else
{
res = 0;
}
logf (LOG_DEBUG, "maptab %s close %d errors", name, errors);
-#if HAVE_ICONV_H
- if (t_utf8 != (iconv_t)(-1))
- iconv_close(t_utf8);
- if (t_unicode != (iconv_t)(-1))
- iconv_close(t_unicode);
-#endif
+ if (t_utf8 != 0)
+ yaz_iconv_close(t_utf8);
+ if (t_unicode != 0)
+ yaz_iconv_close(t_unicode);
return res;
}