2 * This program is free software; you can redistribute it and/or
3 * modify it under the terms of the GNU General Public License
4 * as published by the Free Software Foundation; either version 2
5 * of the License, or (at your option) any later version.
7 * This program is distributed in the hope that it will be useful,
8 * but WITHOUT ANY WARRANTY; without even the implied warranty of
9 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
10 * GNU General Public License for more details.
12 * You should have received a copy of the GNU General Public License
13 * along with this program; if not, write to the Free Software Foundation,
14 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
16 * The Original Code is Copyright (C) 2012 Blender Foundation.
17 * All rights reserved.
23 size_t count_utf_8_from_16(const wchar_t *string16)
32 for (i = 0; (u = string16[i]); i++) {
47 if ((u = string16[i]) == 0) {
50 if (u >= 0xDC00 && u < 0xE000) {
71 size_t count_utf_16_from_8(const char *string8)
78 if (!string8) return 0;
80 for (; (u = *string8); string8++) {
82 if ((u & 0x01 << 7) == 0) { count++; u32 = 0; continue; } //1 utf-8 char
83 if ((u & 0x07 << 5) == 0xC0) { type = 1; u32 = u & 0x1F; continue; } //2 utf-8 char
84 if ((u & 0x0F << 4) == 0xE0) { type = 2; u32 = u & 0x0F; continue; } //3 utf-8 char
85 if ((u & 0x1F << 3) == 0xF0) { type = 3; u32 = u & 0x07; continue; } //4 utf-8 char
89 if ((u & 0xC0) == 0x80) {
90 u32 = (u32 << 6) | (u & 0x3F);
100 if ((0 < u32 && u32 < 0xD800) || (0xE000 <= u32 && u32 < 0x10000)) count++;
101 else if (0x10000 <= u32 && u32 < 0x110000) count += 2;
110 int conv_utf_16_to_8(const wchar_t *in16, char *out8, size_t size8)
112 char *out8end = out8 + size8;
115 if (!size8 || !in16 || !out8) return UTF_ERROR_NULL_IN;
118 for (; out8 < out8end && (u = *in16); in16++, out8++) {
122 else if (u < 0x0800) {
123 if (out8 + 1 >= out8end) break;
124 *out8++ = (0x3 << 6) | (0x1F & (u >> 6));
125 *out8 = (0x1 << 7) | (0x3F & (u));
127 else if (u < 0xD800 || u >= 0xE000) {
128 if (out8 + 2 >= out8end) break;
129 *out8++ = (0x7 << 5) | (0xF & (u >> 12));
130 *out8++ = (0x1 << 7) | (0x3F & (u >> 6));
131 *out8 = (0x1 << 7) | (0x3F & (u));
133 else if (u < 0xDC00) {
134 wchar_t u2 = *++in16;
137 if (u2 >= 0xDC00 && u2 < 0xE000) {
138 if (out8 + 3 >= out8end) break; else {
139 unsigned int uc = 0x10000 + (u2 - 0xDC00) + ((u - 0xD800) << 10);
141 *out8++ = (0xF << 4) | (0x7 & (uc >> 18));
142 *out8++ = (0x1 << 7) | (0x3F & (uc >> 12));
143 *out8++ = (0x1 << 7) | (0x3F & (uc >> 6));
144 *out8 = (0x1 << 7) | (0x3F & (uc));
148 out8--; err |= UTF_ERROR_ILLCHAR;
151 else if (u < 0xE000) {
152 out8--; err |= UTF_ERROR_ILLCHAR;
156 *out8 = *out8end = 0;
158 if (*in16) err |= UTF_ERROR_SMALL;
164 int conv_utf_8_to_16(const char *in8, wchar_t *out16, size_t size16)
168 unsigned int u32 = 0;
169 wchar_t *out16end = out16 + size16;
171 if (!size16 || !in8 || !out16) return UTF_ERROR_NULL_IN;
174 for (; out16 < out16end && (u = *in8); in8++) {
176 if ((u & 0x01 << 7) == 0) { *out16 = u; out16++; u32 = 0; continue; } //1 utf-8 char
177 if ((u & 0x07 << 5) == 0xC0) { type = 1; u32 = u & 0x1F; continue; } //2 utf-8 char
178 if ((u & 0x0F << 4) == 0xE0) { type = 2; u32 = u & 0x0F; continue; } //3 utf-8 char
179 if ((u & 0x1F << 3) == 0xF0) { type = 3; u32 = u & 0x07; continue; } //4 utf-8 char
180 err |= UTF_ERROR_ILLCHAR;
184 if ((u & 0xC0) == 0x80) {
185 u32 = (u32 << 6) | (u & 0x3F);
189 u32 = 0; type = 0; err |= UTF_ERROR_ILLSEQ;
193 if ((0 < u32 && u32 < 0xD800) || (0xE000 <= u32 && u32 < 0x10000)) {
197 else if (0x10000 <= u32 && u32 < 0x110000) {
198 if (out16 + 1 >= out16end) break;
200 *out16 = 0xD800 + (u32 >> 10);
202 *out16 = 0xDC00 + (u32 & 0x3FF);
210 *out16 = *out16end = 0;
212 if (*in8) err |= UTF_ERROR_SMALL;
217 /* UNUSED FUNCTIONS */
219 static int is_ascii(const char *in8)
222 if (0x80 & *in8) return 0;
227 static void utf_8_cut_end(char *inout8, size_t maxcutpoint)
229 char *cur = inout8 + maxcutpoint;
238 char *alloc_utf_8_from_16(const wchar_t *in16, size_t add)
240 size_t bsize = count_utf_8_from_16(in16);
242 if (!bsize) return NULL;
243 out8 = (char *)malloc(sizeof(char) * (bsize + add));
244 conv_utf_16_to_8(in16, out8, bsize);
248 wchar_t *alloc_utf16_from_8(const char *in8, size_t add)
250 size_t bsize = count_utf_16_from_8(in8);
251 wchar_t *out16 = NULL;
252 if (!bsize) return NULL;
253 out16 = (wchar_t *) malloc(sizeof(wchar_t) * (bsize + add));
254 conv_utf_8_to_16(in8, out16, bsize);