-/* $Id: charmap.c,v 1.27 2003-01-13 10:53:16 oleg Exp $
- Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002
+/* $Id: charmap.c,v 1.29 2004-07-28 09:47:42 adam Exp $
+ Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002,2003,2004
Index Data Aps
This file is part of the Zebra server.
const char *CHR_UNKNOWN = "\001";
const char *CHR_SPACE = "\002";
-const char *CHR_BASE = "\003";
+const char *CHR_CUT = "\003";
+const char *CHR_BASE = "\005";
struct chrmaptab_info
{
return c;
}
+static int zebra_ucs4_strlen(ucs4_t *s)
+{
+ int i = 0;
+ while (*s++)
+ i++;
+ return i;
+}
+
ucs4_t zebra_prim_w(ucs4_t **s)
{
ucs4_t c;
case 't': c = '\t'; (*s)++; break;
case 's': c = ' '; (*s)++; break;
case 'x':
- fmtstr[0] = (*s)[0];
- fmtstr[1] = (*s)[1];
- fmtstr[2] = (*s)[2];
- fmtstr[3] = 0;
- sscanf(fmtstr, "x%2x", &i);
- c = i;
- *s += 3; break;
+ if (zebra_ucs4_strlen(*s) >= 3)
+ {
+ fmtstr[0] = (*s)[1];
+ fmtstr[1] = (*s)[2];
+ fmtstr[2] = 0;
+ sscanf(fmtstr, "%x", &i);
+ c = i;
+ *s += 3;
+ }
+ break;
case '0':
case '1':
case '2':
case '7':
case '8':
case '9':
- fmtstr[0] = (*s)[0];
- fmtstr[1] = (*s)[1];
- fmtstr[2] = (*s)[2];
- fmtstr[3] = 0;
- sscanf(fmtstr, "%3o", &i);
- c = i;
- *s += 3;
+ if (zebra_ucs4_strlen(*s) >= 3)
+ {
+ fmtstr[0] = (*s)[0];
+ fmtstr[1] = (*s)[1];
+ fmtstr[2] = (*s)[2];
+ fmtstr[3] = 0;
+ sscanf(fmtstr, "%o", &i);
+ c = i;
+ *s += 3;
+ }
break;
+ case 'L':
+ if (zebra_ucs4_strlen(*s) >= 5)
+ {
+ fmtstr[0] = (*s)[1];
+ fmtstr[1] = (*s)[2];
+ fmtstr[2] = (*s)[3];
+ fmtstr[3] = (*s)[4];
+ fmtstr[4] = 0;
+ sscanf(fmtstr, "%x", &i);
+ c = i;
+ *s += 5;
+ }
+ break;
default:
(*s)++;
}
(char*) CHR_SPACE, 0);
}
+/*
+ * Callback function.
+ * Add a space-entry to the value space.
+ */
+static void fun_addcut(const char *s, void *data, int num)
+{
+ chrmaptab tab = (chrmaptab) data;
+ tab->input = set_map_string(tab->input, tab->nmem, s, strlen(s),
+ (char*) CHR_CUT, 0);
+}
+
/*
* Create a string containing the mapped characters provided.
*/
ret = yaz_iconv (t, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (ret == (size_t) (-1))
{
+ yaz_log(LOG_LOG, "from: %2X %2X %2X %2X",
+ from[0], from[1], from[2], from[3]);
yaz_log (LOG_WARN|LOG_ERRNO, "bad unicode sequence");
return -1;
}
{
if (argc != 2)
{
- logf(LOG_FATAL, "Syntax error in charmap");
+ logf(LOG_FATAL, "Syntax error in charmap for space");
++errors;
}
if (scan_string(argv[1], t_unicode, t_utf8,
++errors;
}
}
+ else if (!map_only && !yaz_matchstr(argv[0], "cut"))
+ {
+ if (argc != 2)
+ {
+ logf(LOG_FATAL, "Syntax error in charmap for cut");
+ ++errors;
+ }
+ if (scan_string(argv[1], t_unicode, t_utf8,
+ fun_addcut, res, 0) < 0)
+ {
+ logf(LOG_FATAL, "Bad cut specification");
+ ++errors;
+ }
+ }
else if (!yaz_matchstr(argv[0], "map"))
{
chrwork buf;
* zebra need to comment next part of code.
*/
- /*
+ /* Original code */
+#if 1
if (t_unicode != 0)
yaz_iconv_close (t_unicode);
t_unicode = yaz_iconv_open (ucs4_native, argv[1]);
- */
-
+#endif
/*
* Fix me. It is additional staff for conversion of characters from local encoding
* of *.chr file to UTF-8 (internal encoding).
* NOTE: The derective encoding must be first directive in *.chr file.
*/
+ /* For whatever reason Oleg enabled this.. */
+#if 0
if (t_utf8 != 0)
yaz_iconv_close(t_utf8);
t_utf8 = yaz_iconv_open ("UTF-8", argv[1]);
+#endif
}
else
{