-/* $Id: charmap.c,v 1.33 2004-12-13 20:51:33 adam Exp $
- Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002,2003,2004
- Index Data Aps
+/* $Id: charmap.c,v 1.44 2007-01-15 15:10:26 adam Exp $
+ Copyright (C) 1995-2007
+ Index Data ApS
This file is part of the Zebra server.
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 <ctype.h>
#include <string.h>
+#include <stdlib.h>
#include <assert.h>
typedef unsigned ucs4_t;
const char *CHR_UNKNOWN = "\001";
const char *CHR_SPACE = "\002";
const char *CHR_CUT = "\003";
-const char *CHR_BASE = "\005";
+const char *CHR_BASE = "\005"; /* CHECK CHR_BASE_CHAR as well */
struct chrmaptab_info
{
} chrwork;
/*
+ * Callback for equivalent stuff
+ */
+typedef struct
+{
+ NMEM nmem;
+ int no_eq;
+ char *eq[CHR_MAXEQUIV];
+} chr_equiv_work;
+/*
* Add an entry to the character map.
*/
static chr_t_entry *set_map_string(chr_t_entry *root, NMEM nmem,
}
if (!len)
{
- if (!root->target || !root->target[0] || strcmp(root->target[0], to))
+ if (!root->target || !root->target[0] ||
+ strcmp((const char *) root->target[0], to))
{
if (from_0 &&
root->target && root->target[0] && root->target[0][0] &&
- strcmp (root->target[0], CHR_UNKNOWN))
+ strcmp((const char *) root->target[0], CHR_UNKNOWN))
{
yaz_log (YLOG_WARN, "duplicate entry for charmap from '%s'",
from_0);
return (const char **) (res->target);
}
-const char *chr_map_output(chrmaptab maptab, const char **from, int len)
+const char **chr_map_q_input(chrmaptab maptab,
+ const char **from, int len, int first)
{
- unsigned char c = ** (unsigned char **) from;
- (*from)++;
- return (const char*) maptab->output[c];
+ chr_t_entry *t = maptab->q_input;
+ chr_t_entry *res;
+ int len_tmp[2];
+
+ len_tmp[0] = len;
+ len_tmp[1] = -1;
+ if (!(res = find_entry_x(t, from, len_tmp, first)))
+ return 0;
+ return (const char **) (res->target);
}
-unsigned char zebra_prim(char **s)
+const char *chr_map_output(chrmaptab maptab, const char **from, int len)
{
- unsigned char c;
- unsigned int i = 0;
+ unsigned char c = ** (unsigned char **) from;
+ const char *out = (const char*) maptab->output[c];
- yaz_log (YLOG_DEBUG, "prim %.3s", *s);
- if (**s == '\\')
- {
- (*s)++;
- c = **s;
- switch (c)
- {
- case '\\': c = '\\'; (*s)++; break;
- case 'r': c = '\r'; (*s)++; break;
- case 'n': c = '\n'; (*s)++; break;
- case 't': c = '\t'; (*s)++; break;
- case 's': c = ' '; (*s)++; break;
- case 'x': sscanf(*s, "x%2x", &i); c = i; *s += 3; break;
- case '0':
- case '1':
- case '2':
- case '3':
- case '4':
- case '5':
- case '6':
- case '7':
- case '8':
- case '9':
- sscanf(*s, "%3o", &i);
- c = i;
- *s += 3;
- break;
- default:
- (*s)++;
- }
- }
- else
- {
- c = **s;
- ++(*s);
- }
- return c;
+ if (out)
+ (*from)++;
+ return out;
}
static int zebra_ucs4_strlen(ucs4_t *s)
char fmtstr[8];
yaz_log (YLOG_DEBUG, "prim_w %.3s", (char *) *s);
- if (**s == '\\')
+ if (**s == '\\' && 1[*s])
{
(*s)++;
c = **s;
}
/*
+ * Create an unmodified string (scan_string handler).
+ */
+static void fun_add_equivalent_string(const char *s, void *data, int num)
+{
+ chr_equiv_work *arg = (chr_equiv_work *) data;
+
+ if (arg->no_eq == CHR_MAXEQUIV)
+ return;
+ arg->eq[arg->no_eq++] = nmem_strdup(arg->nmem, s);
+}
+
+/*
* Add a map to the string contained in the argument.
*/
static void fun_add_map(const char *s, void *data, int num)
yaz_log (YLOG_DEBUG, " %3d", (unsigned char) *s);
}
-/*
- * Add a query map to the string contained in the argument.
- */
-static void fun_add_qmap(const char *s, void *data, int num)
-{
- chrwork *arg = (chrwork *) data;
-
- assert(arg->map->q_input);
- yaz_log (YLOG_DEBUG, "set qmap %.*s", (int) strlen(s), s);
- set_map_string(arg->map->q_input, arg->map->nmem, s,
- strlen(s), arg->string, 0);
- for (s = arg->string; *s; s++)
- yaz_log (YLOG_DEBUG, " %3d", (unsigned char) *s);
-}
-
static int scan_to_utf8 (yaz_iconv_t t, ucs4_t *from, size_t inlen,
char *outbuf, size_t outbytesleft)
{
(*fun)(str, data, num ? (*num)++ : 0);
}
break;
- case '[': s++; abort(); break;
case '(':
++s;
s0 = s; i = 0;
return 0;
}
-chrmaptab chrmaptab_create(const char *tabpath, const char *name, int map_only,
- const char *tabroot)
+chrmaptab chrmaptab_create(const char *tabpath, const char *name,
+ const char *tabroot)
{
FILE *f;
char line[512], *argv[50];
unsigned endian = 31;
const char *ucs4_native = "UCS-4";
- if (*(char*) &endian == 31) /* little endian? */
- ucs4_native = "UCS-4LE";
-
- t_utf8 = yaz_iconv_open ("UTF-8", ucs4_native);
-
yaz_log (YLOG_DEBUG, "maptab %s open", name);
if (!(f = yaz_fopen(tabpath, name, "r", tabroot)))
{
yaz_log(YLOG_WARN|YLOG_ERRNO, "%s", name);
return 0;
}
+
+ if (*(char*) &endian == 31) /* little endian? */
+ ucs4_native = "UCS-4LE";
+
+ t_utf8 = yaz_iconv_open ("UTF-8", ucs4_native);
+
nmem = nmem_create ();
res = (chrmaptab) nmem_malloc(nmem, sizeof(*res));
res->nmem = nmem;
res->input->children[i]->target = (unsigned char **)
nmem_malloc (res->nmem, 2 * sizeof(unsigned char *));
res->input->children[i]->target[1] = 0;
- if (map_only)
- {
- res->input->children[i]->target[0] = (unsigned char *)
- nmem_malloc (res->nmem, 2 * sizeof(unsigned char));
- res->input->children[i]->target[0][0] = i;
- res->input->children[i]->target[0][1] = 0;
- }
- else
- res->input->children[i]->target[0] = (unsigned char*) CHR_UNKNOWN;
+ res->input->children[i]->target[0] = (unsigned char*) CHR_UNKNOWN;
}
res->q_input = (chr_t_entry *)
nmem_malloc(res->nmem, sizeof(*res->q_input));
res->base_uppercase = 0;
while (!errors && (argc = readconf_line(f, &lineno, line, 512, argv, 50)))
- if (!map_only && !yaz_matchstr(argv[0], "lowercase"))
+ if (!yaz_matchstr(argv[0], "lowercase"))
{
if (argc != 2)
{
res->output[(int) *CHR_UNKNOWN + num] = (unsigned char*) "@";
num = (int) *CHR_BASE;
}
- else if (!map_only && !yaz_matchstr(argv[0], "uppercase"))
+ else if (!yaz_matchstr(argv[0], "uppercase"))
{
if (!res->base_uppercase)
{
++errors;
}
}
- else if (!map_only && !yaz_matchstr(argv[0], "space"))
+ else if (!yaz_matchstr(argv[0], "space"))
{
if (argc != 2)
{
++errors;
}
}
- else if (!map_only && !yaz_matchstr(argv[0], "cut"))
+ else if (!yaz_matchstr(argv[0], "cut"))
{
if (argc != 2)
{
++errors;
}
}
- else if (!yaz_matchstr(argv[0], "qmap"))
+ else if (!yaz_matchstr(argv[0], "equivalent"))
{
- chrwork buf;
+ chr_equiv_work w;
- if (argc != 3)
+ if (argc != 2)
{
- yaz_log(YLOG_FATAL, "charmap directive qmap requires 2 args");
+ yaz_log(YLOG_FATAL, "equivalent requires 1 argument");
++errors;
}
- buf.map = res;
- buf.string[0] = '\0';
- if (scan_string(argv[2], t_unicode, t_utf8,
- fun_mkstring, &buf, 0) < 0)
+ w.nmem = res->nmem;
+ w.no_eq = 0;
+ if (scan_string(argv[1], t_unicode, t_utf8,
+ fun_add_equivalent_string, &w, 0) < 0)
{
- yaz_log(YLOG_FATAL, "Bad qmap target");
+ yaz_log(YLOG_FATAL, "equivalent: invalid string");
++errors;
}
- if (scan_string(argv[1], t_unicode, t_utf8,
- fun_add_qmap, &buf, 0) < 0)
+ else if (w.no_eq == 0)
{
- yaz_log(YLOG_FATAL, "Bad qmap source");
+ yaz_log(YLOG_FATAL, "equivalent: no strings");
++errors;
}
+ else
+ {
+ char *result_str;
+ int i, slen = 5;
+
+ /* determine length of regular expression */
+ for (i = 0; i<w.no_eq; i++)
+ slen += strlen(w.eq[i]) + 1;
+ result_str = nmem_malloc(res->nmem, slen + 5);
+
+ /* build the regular expression */
+ *result_str = '\0';
+ slen = 0;
+ for (i = 0; i<w.no_eq; i++)
+ {
+ result_str[slen++] = i ? '|' : '(';
+ strcpy(result_str + slen, w.eq[i]);
+ slen += strlen(w.eq[i]);
+ }
+ result_str[slen++] = ')';
+ result_str[slen] = '\0';
+
+ /* each eq will map to this regular expression */
+ for (i = 0; i<w.no_eq; i++)
+ {
+ set_map_string(res->q_input, res->nmem,
+ w.eq[i], strlen(w.eq[i]),
+ result_str, 0);
+ }
+ }
}
else if (!yaz_matchstr(argv[0], "encoding"))
{
}
+/*
+ * Local variables:
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ * vim: shiftwidth=4 tabstop=8 expandtab
+ */
+
projects / idzebra-moved-to-github.git / blobdiff