1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
|
/* This file is part of the YAZ toolkit.
* Copyright (C) Index Data
* See the file LICENSE for details.
*/
/**
* \file
* \brief UTF-8 string utilities for ICU
*/
#if HAVE_CONFIG_H
#include "config.h"
#endif
#if YAZ_HAVE_ICU
#include <yaz/xmalloc.h>
#include <yaz/icu_I18N.h>
#include <yaz/log.h>
#include <string.h>
#include <stdlib.h>
#include <stdio.h>
#include <assert.h>
#include <unicode/ustring.h> /* some more string fcns*/
#include <unicode/uchar.h> /* char names */
struct icu_buf_utf8 *icu_buf_utf8_create(size_t capacity)
{
struct icu_buf_utf8 *buf8
= (struct icu_buf_utf8 *) xmalloc(sizeof(struct icu_buf_utf8));
buf8->utf8_len = 0;
buf8->utf8_cap = capacity;
if (capacity > 0)
{
buf8->utf8 = (uint8_t *) xmalloc(sizeof(uint8_t) * capacity);
buf8->utf8[0] = (uint8_t) 0;
}
else
buf8->utf8 = 0;
return buf8;
}
struct icu_buf_utf8 *icu_buf_utf8_clear(struct icu_buf_utf8 *buf8)
{
assert(buf8);
if (buf8->utf8)
buf8->utf8[0] = (uint8_t) 0;
buf8->utf8_len = 0;
return buf8;
}
struct icu_buf_utf8 *icu_buf_utf8_resize(struct icu_buf_utf8 *buf8,
size_t capacity)
{
assert(buf8);
if (capacity > 0)
{
if (0 == buf8->utf8)
buf8->utf8 = (uint8_t *) xmalloc(sizeof(uint8_t) * capacity);
else
buf8->utf8
= (uint8_t *) xrealloc(buf8->utf8, sizeof(uint8_t) * capacity);
buf8->utf8_cap = capacity;
}
return buf8;
}
const char *icu_buf_utf8_to_cstr(struct icu_buf_utf8 *src8)
{
assert(src8);
if (src8->utf8_len == 0)
return "";
if (src8->utf8_len == src8->utf8_cap)
src8 = icu_buf_utf8_resize(src8, src8->utf8_len * 2 + 1);
src8->utf8[src8->utf8_len] = '\0';
return (const char *) src8->utf8;
}
void icu_buf_utf8_destroy(struct icu_buf_utf8 *buf8)
{
if (buf8)
xfree(buf8->utf8);
xfree(buf8);
}
UErrorCode icu_utf16_from_utf8_cstr(struct icu_buf_utf16 *dest16,
const char *src8cstr,
UErrorCode *status)
{
size_t src8cstr_len = 0;
int32_t utf16_len = 0;
*status = U_ZERO_ERROR;
src8cstr_len = strlen(src8cstr);
u_strFromUTF8(dest16->utf16, dest16->utf16_cap,
&utf16_len,
src8cstr, src8cstr_len, status);
/* check for buffer overflow, resize and retry */
if (*status == U_BUFFER_OVERFLOW_ERROR)
{
icu_buf_utf16_resize(dest16, utf16_len * 2);
*status = U_ZERO_ERROR;
u_strFromUTF8(dest16->utf16, dest16->utf16_cap,
&utf16_len,
src8cstr, src8cstr_len, status);
}
if (U_SUCCESS(*status) && utf16_len <= dest16->utf16_cap)
dest16->utf16_len = utf16_len;
else
icu_buf_utf16_clear(dest16);
return *status;
}
UErrorCode icu_utf16_to_utf8(struct icu_buf_utf8 *dest8,
const struct icu_buf_utf16 *src16,
UErrorCode *status)
{
int32_t utf8_len = 0;
u_strToUTF8((char *) dest8->utf8, dest8->utf8_cap,
&utf8_len,
src16->utf16, src16->utf16_len, status);
/* check for buffer overflow, resize and retry */
if (*status == U_BUFFER_OVERFLOW_ERROR)
{
icu_buf_utf8_resize(dest8, utf8_len * 2);
*status = U_ZERO_ERROR;
u_strToUTF8((char *) dest8->utf8, dest8->utf8_cap,
&utf8_len,
src16->utf16, src16->utf16_len, status);
}
if (U_SUCCESS(*status) && utf8_len <= dest8->utf8_cap)
dest8->utf8_len = utf8_len;
else
icu_buf_utf8_clear(dest8);
return *status;
}
#endif /* YAZ_HAVE_ICU */
/*
* Local variables:
* c-basic-offset: 4
* c-file-style: "Stroustrup"
* indent-tabs-mode: nil
* End:
* vim: shiftwidth=4 tabstop=8 expandtab
*/
|