2 * Copyright (C) 1999-2002, 2016 Free Software Foundation, Inc.
3 * This file is part of the GNU LIBICONV Library.
5 * The GNU LIBICONV Library is free software; you can redistribute it
6 * and/or modify it under the terms of the GNU Library General Public
7 * License as published by the Free Software Foundation; either version 2
8 * of the License, or (at your option) any later version.
10 * The GNU LIBICONV Library is distributed in the hope that it will be
11 * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * Library General Public License for more details.
15 * You should have received a copy of the GNU Library General Public
16 * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
17 * If not, see <http://www.gnu.org/licenses/>.
22 * This is ISO 8859-1 with \uXXXX escape sequences, denoting Unicode BMP
23 * characters. Consecutive pairs of \uXXXX escape sequences in the surrogate
24 * range, as in UTF-16, denote Unicode characters outside the BMP.
28 java_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, size_t n)
42 goto simply_backslash;
44 for (i = 2; i < 6; i++) {
48 if (c >= '0' && c <= '9')
50 else if (c >= 'A' && c <= 'Z')
52 else if (c >= 'a' && c <= 'z')
55 goto simply_backslash;
56 wc |= (ucs4_t) c << (4 * (5-i));
58 if (!(wc >= 0xd800 && wc < 0xe000)) {
63 goto simply_backslash;
67 goto simply_backslash;
71 goto simply_backslash;
73 for (i = 8; i < 12; i++) {
77 if (c >= '0' && c <= '9')
79 else if (c >= 'A' && c <= 'Z')
81 else if (c >= 'a' && c <= 'z')
84 goto simply_backslash;
85 wc2 |= (ucs4_t) c << (4 * (11-i));
87 if (!(wc2 >= 0xdc00 && wc2 < 0xe000))
88 goto simply_backslash;
89 *pwc = 0x10000 + ((wc - 0xd800) << 10) + (wc2 - 0xdc00);
97 java_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n)
102 } else if (wc < 0x10000) {
107 i = (wc >> 12) & 0x0f; r[2] = (i < 10 ? '0'+i : 'a'-10+i);
108 i = (wc >> 8) & 0x0f; r[3] = (i < 10 ? '0'+i : 'a'-10+i);
109 i = (wc >> 4) & 0x0f; r[4] = (i < 10 ? '0'+i : 'a'-10+i);
110 i = wc & 0x0f; r[5] = (i < 10 ? '0'+i : 'a'-10+i);
114 } else if (wc < 0x110000) {
116 ucs4_t wc1 = 0xd800 + ((wc - 0x10000) >> 10);
117 ucs4_t wc2 = 0xdc00 + ((wc - 0x10000) & 0x3ff);
121 i = (wc1 >> 12) & 0x0f; r[2] = (i < 10 ? '0'+i : 'a'-10+i);
122 i = (wc1 >> 8) & 0x0f; r[3] = (i < 10 ? '0'+i : 'a'-10+i);
123 i = (wc1 >> 4) & 0x0f; r[4] = (i < 10 ? '0'+i : 'a'-10+i);
124 i = wc1 & 0x0f; r[5] = (i < 10 ? '0'+i : 'a'-10+i);
127 i = (wc2 >> 12) & 0x0f; r[8] = (i < 10 ? '0'+i : 'a'-10+i);
128 i = (wc2 >> 8) & 0x0f; r[9] = (i < 10 ? '0'+i : 'a'-10+i);
129 i = (wc2 >> 4) & 0x0f; r[10] = (i < 10 ? '0'+i : 'a'-10+i);
130 i = wc2 & 0x0f; r[11] = (i < 10 ? '0'+i : 'a'-10+i);