1 /*
2 * Copyright © 2012 Intel Corporation
3 * Copyright © 2014 Ran Benita <ran234@gmail.com>
4 *
5 * Permission is hereby granted, free of charge, to any person obtaining a
6 * copy of this software and associated documentation files (the "Software"),
7 * to deal in the Software without restriction, including without limitation
8 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
9 * and/or sell copies of the Software, and to permit persons to whom the
10 * Software is furnished to do so, subject to the following conditions:
11 *
12 * The above copyright notice and this permission notice (including the next
13 * paragraph) shall be included in all copies or substantial portions of the
14 * Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
19 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
21 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
22 * DEALINGS IN THE SOFTWARE.
23 *
24 * Author: Rob Bradford <rob@linux.intel.com>
25 */
26
27 #include "config.h"
28
29 #include <stddef.h>
30 #include <stdbool.h>
31 #include <inttypes.h>
32
33 #include "utf8.h"
34
35 int
utf32_to_utf8(uint32_t unichar,char * buffer)36 utf32_to_utf8(uint32_t unichar, char *buffer)
37 {
38 int count, shift, length;
39 uint8_t head;
40
41 if (unichar <= 0x007f) {
42 buffer[0] = unichar;
43 buffer[1] = '\0';
44 return 2;
45 }
46 else if (unichar <= 0x07FF) {
47 length = 2;
48 head = 0xc0;
49 }
50 else if (unichar <= 0xffff) {
51 length = 3;
52 head = 0xe0;
53 }
54 else if (unichar <= 0x10ffff) {
55 length = 4;
56 head = 0xf0;
57 }
58 else {
59 buffer[0] = '\0';
60 return 0;
61 }
62
63 for (count = length - 1, shift = 0; count > 0; count--, shift += 6)
64 buffer[count] = 0x80 | ((unichar >> shift) & 0x3f);
65
66 buffer[0] = head | ((unichar >> shift) & 0x3f);
67 buffer[length] = '\0';
68
69 return length + 1;
70 }
71
72 bool
is_valid_utf8(const char * ss,size_t len)73 is_valid_utf8(const char *ss, size_t len)
74 {
75 size_t i = 0;
76 size_t tail_bytes = 0;
77 const uint8_t *s = (const uint8_t *) ss;
78
79 /* This beauty is from:
80 * The Unicode Standard Version 6.2 - Core Specification, Table 3.7
81 * https://www.unicode.org/versions/Unicode6.2.0/ch03.pdf#G7404
82 * We can optimize if needed. */
83 while (i < len)
84 {
85 if (s[i] <= 0x7F) {
86 tail_bytes = 0;
87 }
88 else if (s[i] >= 0xC2 && s[i] <= 0xDF) {
89 tail_bytes = 1;
90 }
91 else if (s[i] == 0xE0) {
92 i++;
93 if (i >= len || !(s[i] >= 0xA0 && s[i] <= 0xBF))
94 return false;
95 tail_bytes = 1;
96 }
97 else if (s[i] >= 0xE1 && s[i] <= 0xEC) {
98 tail_bytes = 2;
99 }
100 else if (s[i] == 0xED) {
101 i++;
102 if (i >= len || !(s[i] >= 0x80 && s[i] <= 0x9F))
103 return false;
104 tail_bytes = 1;
105 }
106 else if (s[i] >= 0xEE && s[i] <= 0xEF) {
107 tail_bytes = 2;
108 }
109 else if (s[i] == 0xF0) {
110 i++;
111 if (i >= len || !(s[i] >= 0x90 && s[i] <= 0xBF))
112 return false;
113 tail_bytes = 2;
114 }
115 else if (s[i] >= 0xF1 && s[i] <= 0xF3) {
116 tail_bytes = 3;
117 }
118 else if (s[i] == 0xF4) {
119 i++;
120 if (i >= len || !(s[i] >= 0x80 && s[i] <= 0x8F))
121 return false;
122 tail_bytes = 2;
123 }
124 else {
125 return false;
126 }
127
128 i++;
129
130 while (i < len && tail_bytes > 0 && s[i] >= 0x80 && s[i] <= 0xBF) {
131 i++;
132 tail_bytes--;
133 }
134
135 if (tail_bytes != 0)
136 return false;
137 }
138
139 return true;
140 }
141