projects
/
yaz-moved-to-github.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
3.0.37.
[yaz-moved-to-github.git]
/
util
/
yaz-icu.c
diff --git
a/util/yaz-icu.c
b/util/yaz-icu.c
index
00b390d
..
30d9048
100644
(file)
--- a/
util/yaz-icu.c
+++ b/
util/yaz-icu.c
@@
-1,8
+1,6
@@
-/*
- * Copyright (C) 1995-2007, Index Data ApS
+/* This file is part of the YAZ toolkit.
+ * Copyright (C) 1995-2008 Index Data
* See the file LICENSE for details.
* See the file LICENSE for details.
- *
- * $Id: yaz-icu.c,v 1.12 2007-11-08 18:02:04 adam Exp $
*/
#if HAVE_CONFIG_H
*/
#if HAVE_CONFIG_H
@@
-25,6
+23,7
@@
#include <unicode/utrans.h>
#include <yaz/icu.h>
#include <unicode/utrans.h>
#include <yaz/icu.h>
+#include <yaz/wrbuf.h>
/* commando line and config parameters */
static struct config_t {
/* commando line and config parameters */
static struct config_t {
@@
-53,10
+52,10
@@
void print_option_error(const struct config_t *p_config)
"./yaz-icu -p t -x\n"
"\n"
"Example ICU chain XML configuration file:\n"
"./yaz-icu -p t -x\n"
"\n"
"Example ICU chain XML configuration file:\n"
- "<icu_chain id=\"en:word\" locale=\"en\">\n"
- " <normalize rule=\"[:Control:] Any-Remove\"/>\n"
+ "<icu_chain locale=\"en\">\n"
+ " <transform rule=\"[:Control:] Any-Remove\"/>\n"
" <tokenize rule=\"l\"/>\n"
" <tokenize rule=\"l\"/>\n"
- " <normalize rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>\n"
+ " <transform rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>\n"
" <casemap rule=\"l\"/>\n"
"</icu_chain>\n"
);
" <casemap rule=\"l\"/>\n"
"</icu_chain>\n"
);
@@
-156,7
+155,7
@@
static void print_icu_converters(const struct config_t *p_config)
static void print_icu_transliterators(const struct config_t *p_config)
{
int32_t buf_cap = 128;
static void print_icu_transliterators(const struct config_t *p_config)
{
int32_t buf_cap = 128;
- char buf[buf_cap];
+ char buf[128];
int32_t i;
int32_t count = utrans_countAvailableIDs();
int32_t i;
int32_t count = utrans_countAvailableIDs();
@@
-446,7
+445,7
@@
static void process_text_file(const struct config_t *p_config)
exit (1);
}
exit (1);
}
- config.chain = icu_chain_xml_config(xml_node, 0, &status);
+ config.chain = icu_chain_xml_config(xml_node, 1, &status);
if (config.chain && U_SUCCESS(status))
success = 1;
if (config.chain && U_SUCCESS(status))
success = 1;
@@
-470,25
+469,35
@@
static void process_text_file(const struct config_t *p_config)
while (success && icu_chain_next_token(config.chain, &status))
{
while (success && icu_chain_next_token(config.chain, &status))
{
+ WRBUF sw = wrbuf_alloc();
if (U_FAILURE(status))
success = 0;
else {
if (U_FAILURE(status))
success = 0;
else {
+ const char *sortkey = icu_chain_token_sortkey(config.chain);
+ wrbuf_rewind(sw);
+ wrbuf_puts_escaped(sw, sortkey);
token_count++;
if (p_config->xmloutput)
token_count++;
if (p_config->xmloutput)
+ {
+ /* should XML encode this. Bug #1902 */
fprintf(config.outfile,
fprintf(config.outfile,
- "<token id=\%lu\" line=\"%lu\""
- " norm=\"%s\" display=\"%s\"/>\n",
+ "<token id=\"%lu\" line=\"%lu\""
+ " norm=\"%s\" display=\"%s\" sortkey=\"%s\"/>\n",
token_count,
line_count,
icu_chain_token_norm(config.chain),
token_count,
line_count,
icu_chain_token_norm(config.chain),
- icu_chain_token_display(config.chain));
+ icu_chain_token_display(config.chain),
+ wrbuf_cstr(sw));
+ }
else
else
- fprintf(config.outfile, "%lu %lu '%s' '%s'\n",
+ fprintf(config.outfile, "%lu %lu '%s' '%s' '%s'\n",
token_count,
line_count,
icu_chain_token_norm(config.chain),
token_count,
line_count,
icu_chain_token_norm(config.chain),
- icu_chain_token_display(config.chain));
+ icu_chain_token_display(config.chain),
+ wrbuf_cstr(sw));
}
}
+ wrbuf_destroy(sw);
}
}
}
}