1 /* This file is part of the YAZ toolkit.
2 * Copyright (C) 1995-2013 Index Data
3 * See the file LICENSE for details.
8 * \brief UTF-8 string utilities for ICU
16 #include <yaz/xmalloc.h>
18 #include <yaz/icu_I18N.h>
27 #include <unicode/ustring.h> /* some more string fcns*/
28 #include <unicode/uchar.h> /* char names */
30 struct icu_buf_utf8 *icu_buf_utf8_create(size_t capacity)
32 struct icu_buf_utf8 *buf8
33 = (struct icu_buf_utf8 *) xmalloc(sizeof(struct icu_buf_utf8));
36 buf8->utf8_cap = capacity;
39 buf8->utf8 = (uint8_t *) xmalloc(sizeof(uint8_t) * capacity);
40 buf8->utf8[0] = (uint8_t) 0;
47 struct icu_buf_utf8 *icu_buf_utf8_clear(struct icu_buf_utf8 *buf8)
51 buf8->utf8[0] = (uint8_t) 0;
56 struct icu_buf_utf8 *icu_buf_utf8_resize(struct icu_buf_utf8 *buf8,
63 buf8->utf8 = (uint8_t *) xmalloc(sizeof(uint8_t) * capacity);
66 = (uint8_t *) xrealloc(buf8->utf8, sizeof(uint8_t) * capacity);
68 buf8->utf8_cap = capacity;
73 const char *icu_buf_utf8_to_cstr(struct icu_buf_utf8 *src8)
76 if (src8->utf8_len == 0)
79 if (src8->utf8_len == src8->utf8_cap)
80 src8 = icu_buf_utf8_resize(src8, src8->utf8_len * 2 + 1);
82 src8->utf8[src8->utf8_len] = '\0';
84 return (const char *) src8->utf8;
87 void icu_buf_utf8_destroy(struct icu_buf_utf8 *buf8)
94 UErrorCode icu_utf16_from_utf8_cstr(struct icu_buf_utf16 *dest16,
98 size_t src8cstr_len = 0;
99 int32_t utf16_len = 0;
101 *status = U_ZERO_ERROR;
102 src8cstr_len = strlen(src8cstr);
104 u_strFromUTF8(dest16->utf16, dest16->utf16_cap,
106 src8cstr, src8cstr_len, status);
108 /* check for buffer overflow, resize and retry */
109 if (*status == U_BUFFER_OVERFLOW_ERROR)
111 icu_buf_utf16_resize(dest16, utf16_len * 2);
112 *status = U_ZERO_ERROR;
113 u_strFromUTF8(dest16->utf16, dest16->utf16_cap,
115 src8cstr, src8cstr_len, status);
118 if (U_SUCCESS(*status) && utf16_len <= dest16->utf16_cap)
119 dest16->utf16_len = utf16_len;
121 icu_buf_utf16_clear(dest16);
126 UErrorCode icu_utf16_to_utf8(struct icu_buf_utf8 *dest8,
127 const struct icu_buf_utf16 *src16,
130 int32_t utf8_len = 0;
132 u_strToUTF8((char *) dest8->utf8, dest8->utf8_cap,
134 src16->utf16, src16->utf16_len, status);
136 /* check for buffer overflow, resize and retry */
137 if (*status == U_BUFFER_OVERFLOW_ERROR)
139 icu_buf_utf8_resize(dest8, utf8_len * 2);
140 *status = U_ZERO_ERROR;
141 u_strToUTF8((char *) dest8->utf8, dest8->utf8_cap,
143 src16->utf16, src16->utf16_len, status);
146 if (U_SUCCESS(*status) && utf8_len <= dest8->utf8_cap)
147 dest8->utf8_len = utf8_len;
149 icu_buf_utf8_clear(dest8);
154 #endif /* YAZ_HAVE_ICU */
159 * c-file-style: "Stroustrup"
160 * indent-tabs-mode: nil
162 * vim: shiftwidth=4 tabstop=8 expandtab