J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2004 Sun Microsystems, Inc. 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. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any 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 |
| 36 | modifiedUtf8LengthOfUtf8(char* string, int length) { |
| 37 | int new_length; |
| 38 | int i; |
| 39 | |
| 40 | new_length = 0; |
| 41 | for ( i = 0 ; i < length ; i++ ) { |
| 42 | unsigned byte; |
| 43 | |
| 44 | byte = (unsigned char)string[i]; |
| 45 | if ( (byte & 0x80) == 0 ) { /* 1byte encoding */ |
| 46 | new_length++; |
| 47 | if ( byte == 0 ) { |
| 48 | new_length++; /* We gain one byte in length on NULL bytes */ |
| 49 | } |
| 50 | } else if ( (byte & 0xE0) == 0xC0 ) { /* 2byte encoding */ |
| 51 | /* Check encoding of following bytes */ |
| 52 | if ( (i+1) >= length || (string[i+1] & 0xC0) != 0x80 ) { |
| 53 | break; /* Error condition */ |
| 54 | } |
| 55 | i++; /* Skip next byte */ |
| 56 | new_length += 2; |
| 57 | } else if ( (byte & 0xF0) == 0xE0 ) { /* 3byte encoding */ |
| 58 | /* Check encoding of following bytes */ |
| 59 | if ( (i+2) >= length || (string[i+1] & 0xC0) != 0x80 |
| 60 | || (string[i+2] & 0xC0) != 0x80 ) { |
| 61 | break; /* Error condition */ |
| 62 | } |
| 63 | i += 2; /* Skip next two bytes */ |
| 64 | new_length += 3; |
| 65 | } else if ( (byte & 0xF8) == 0xF0 ) { /* 4byte encoding */ |
| 66 | /* Check encoding of following bytes */ |
| 67 | if ( (i+3) >= length || (string[i+1] & 0xC0) != 0x80 |
| 68 | || (string[i+2] & 0xC0) != 0x80 |
| 69 | || (string[i+3] & 0xC0) != 0x80 ) { |
| 70 | break; /* Error condition */ |
| 71 | } |
| 72 | i += 3; /* Skip next 3 bytes */ |
| 73 | new_length += 6; /* 4byte encoding turns into 2 3byte ones */ |
| 74 | } else { |
| 75 | break; /* Error condition */ |
| 76 | } |
| 77 | } |
| 78 | if ( i != length ) { |
| 79 | /* Error in finding new length, return old length so no conversion */ |
| 80 | /* FIXUP: ERROR_MESSAGE? */ |
| 81 | return length; |
| 82 | } |
| 83 | return new_length; |
| 84 | } |
| 85 | |
| 86 | /* |
| 87 | * Convert Standard UTF-8 to Modified UTF-8. |
| 88 | * Assumes the UTF-8 encoding was validated by modifiedLength() above. |
| 89 | * |
| 90 | * Note: Accepts Modified UTF-8 also, no verification on the |
| 91 | * correctness of Standard UTF-8 is done. e,g, 0xC080 input is ok. |
| 92 | */ |
| 93 | void |
| 94 | convertUtf8ToModifiedUtf8(char *string, int length, char *new_string, int new_length) |
| 95 | { |
| 96 | int i; |
| 97 | int j; |
| 98 | |
| 99 | j = 0; |
| 100 | for ( i = 0 ; i < length ; i++ ) { |
| 101 | unsigned byte1; |
| 102 | |
| 103 | byte1 = (unsigned char)string[i]; |
| 104 | |
| 105 | /* NULL bytes and bytes starting with 11110xxx are special */ |
| 106 | if ( (byte1 & 0x80) == 0 ) { /* 1byte encoding */ |
| 107 | if ( byte1 == 0 ) { |
| 108 | /* Bits out: 11000000 10000000 */ |
| 109 | new_string[j++] = (char)0xC0; |
| 110 | new_string[j++] = (char)0x80; |
| 111 | } else { |
| 112 | /* Single byte */ |
| 113 | new_string[j++] = byte1; |
| 114 | } |
| 115 | } else if ( (byte1 & 0xE0) == 0xC0 ) { /* 2byte encoding */ |
| 116 | new_string[j++] = byte1; |
| 117 | new_string[j++] = string[++i]; |
| 118 | } else if ( (byte1 & 0xF0) == 0xE0 ) { /* 3byte encoding */ |
| 119 | new_string[j++] = byte1; |
| 120 | new_string[j++] = string[++i]; |
| 121 | new_string[j++] = string[++i]; |
| 122 | } else if ( (byte1 & 0xF8) == 0xF0 ) { /* 4byte encoding */ |
| 123 | /* Beginning of 4byte encoding, turn into 2 3byte encodings */ |
| 124 | unsigned byte2, byte3, byte4, u21; |
| 125 | |
| 126 | /* Bits in: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
| 127 | byte2 = (unsigned char)string[++i]; |
| 128 | byte3 = (unsigned char)string[++i]; |
| 129 | byte4 = (unsigned char)string[++i]; |
| 130 | /* Reconstruct full 21bit value */ |
| 131 | u21 = (byte1 & 0x07) << 18; |
| 132 | u21 += (byte2 & 0x3F) << 12; |
| 133 | u21 += (byte3 & 0x3F) << 6; |
| 134 | u21 += (byte4 & 0x3F); |
| 135 | /* Bits out: 11101101 1010xxxx 10xxxxxx */ |
| 136 | new_string[j++] = (char)0xED; |
| 137 | new_string[j++] = 0xA0 + (((u21 >> 16) - 1) & 0x0F); |
| 138 | new_string[j++] = 0x80 + ((u21 >> 10) & 0x3F); |
| 139 | /* Bits out: 11101101 1011xxxx 10xxxxxx */ |
| 140 | new_string[j++] = (char)0xED; |
| 141 | new_string[j++] = 0xB0 + ((u21 >> 6) & 0x0F); |
| 142 | new_string[j++] = byte4; |
| 143 | } |
| 144 | } |
| 145 | new_string[j] = 0; |
| 146 | } |