1 /*
2 * Copyright (c) 2004, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26
27 /**
28 * Determine length of this Standard UTF-8 in Modified UTF-8.
29 * Validation is done of the basic UTF encoding rules, returns
30 * length (no change) when errors are detected in the UTF encoding.
31 *
32 * Note: Accepts Modified UTF-8 also, no verification on the
33 * correctness of Standard UTF-8 is done. e,g, 0xC080 input is ok.
34 */
35 int
modifiedUtf8LengthOfUtf8(char * string,int length)36 modifiedUtf8LengthOfUtf8(char* string, int length) {
37 int new_length;
38 int i;
39
40 new_length = 0;
41 /*
42 * if length < 0 or new_length becomes < 0 => string is too big
43 * (handled as error after the cycle).
44 */
45 for ( i = 0 ; i < length && new_length >= 0 ; i++ ) {
46 unsigned byte;
47
48 byte = (unsigned char)string[i];
49 if ( (byte & 0x80) == 0 ) { /* 1byte encoding */
50 new_length++;
51 if ( byte == 0 ) {
52 new_length++; /* We gain one byte in length on NULL bytes */
53 }
54 } else if ( (byte & 0xE0) == 0xC0 ) { /* 2byte encoding */
55 /* Check encoding of following bytes */
56 if ( (i+1) >= length || (string[i+1] & 0xC0) != 0x80 ) {
57 break; /* Error condition */
58 }
59 i++; /* Skip next byte */
60 new_length += 2;
61 } else if ( (byte & 0xF0) == 0xE0 ) { /* 3byte encoding */
62 /* Check encoding of following bytes */
63 if ( (i+2) >= length || (string[i+1] & 0xC0) != 0x80
64 || (string[i+2] & 0xC0) != 0x80 ) {
65 break; /* Error condition */
66 }
67 i += 2; /* Skip next two bytes */
68 new_length += 3;
69 } else if ( (byte & 0xF8) == 0xF0 ) { /* 4byte encoding */
70 /* Check encoding of following bytes */
71 if ( (i+3) >= length || (string[i+1] & 0xC0) != 0x80
72 || (string[i+2] & 0xC0) != 0x80
73 || (string[i+3] & 0xC0) != 0x80 ) {
74 break; /* Error condition */
75 }
76 i += 3; /* Skip next 3 bytes */
77 new_length += 6; /* 4byte encoding turns into 2 3byte ones */
78 } else {
79 break; /* Error condition */
80 }
81 }
82 if ( i != length ) {
83 /* Error in finding new length, return old length so no conversion */
84 /* FIXUP: ERROR_MESSAGE? */
85 return length;
86 }
87 return new_length;
88 }
89
90 /*
91 * Convert Standard UTF-8 to Modified UTF-8.
92 * Assumes the UTF-8 encoding was validated by modifiedLength() above.
93 *
94 * Note: Accepts Modified UTF-8 also, no verification on the
95 * correctness of Standard UTF-8 is done. e,g, 0xC080 input is ok.
96 */
97 void
convertUtf8ToModifiedUtf8(char * string,int length,char * new_string,int new_length)98 convertUtf8ToModifiedUtf8(char *string, int length, char *new_string, int new_length)
99 {
100 int i;
101 int j;
102
103 j = 0;
104 for ( i = 0 ; i < length ; i++ ) {
105 unsigned byte1;
106
107 byte1 = (unsigned char)string[i];
108
109 /* NULL bytes and bytes starting with 11110xxx are special */
110 if ( (byte1 & 0x80) == 0 ) { /* 1byte encoding */
111 if ( byte1 == 0 ) {
112 /* Bits out: 11000000 10000000 */
113 new_string[j++] = (char)0xC0;
114 new_string[j++] = (char)0x80;
115 } else {
116 /* Single byte */
117 new_string[j++] = byte1;
118 }
119 } else if ( (byte1 & 0xE0) == 0xC0 ) { /* 2byte encoding */
120 new_string[j++] = byte1;
121 new_string[j++] = string[++i];
122 } else if ( (byte1 & 0xF0) == 0xE0 ) { /* 3byte encoding */
123 new_string[j++] = byte1;
124 new_string[j++] = string[++i];
125 new_string[j++] = string[++i];
126 } else if ( (byte1 & 0xF8) == 0xF0 ) { /* 4byte encoding */
127 /* Beginning of 4byte encoding, turn into 2 3byte encodings */
128 unsigned byte2, byte3, byte4, u21;
129
130 /* Bits in: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
131 byte2 = (unsigned char)string[++i];
132 byte3 = (unsigned char)string[++i];
133 byte4 = (unsigned char)string[++i];
134 /* Reconstruct full 21bit value */
135 u21 = (byte1 & 0x07) << 18;
136 u21 += (byte2 & 0x3F) << 12;
137 u21 += (byte3 & 0x3F) << 6;
138 u21 += (byte4 & 0x3F);
139 /* Bits out: 11101101 1010xxxx 10xxxxxx */
140 new_string[j++] = (char)0xED;
141 new_string[j++] = 0xA0 + (((u21 >> 16) - 1) & 0x0F);
142 new_string[j++] = 0x80 + ((u21 >> 10) & 0x3F);
143 /* Bits out: 11101101 1011xxxx 10xxxxxx */
144 new_string[j++] = (char)0xED;
145 new_string[j++] = 0xB0 + ((u21 >> 6) & 0x0F);
146 new_string[j++] = byte4;
147 }
148 }
149 new_string[j] = 0;
150 }
151