2 * Copyright (c) 2015 Samsung Electronics Co., Ltd.
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
8 * http://www.apache.org/licenses/LICENSE-2.0
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
19 #include <dali-toolkit/internal/text/character-set-conversion.h>
32 const static uint8_t U1 = 1u;
33 const static uint8_t U2 = 2u;
34 const static uint8_t U3 = 3u;
35 const static uint8_t U4 = 4u;
36 const static uint8_t U0 = 0u;
37 const static uint8_t UTF8_LENGTH[256] = {
38 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
39 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
40 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
41 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
42 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
43 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
44 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
45 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
46 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, // lead byte = 0xxx xxxx (U+0000 - U+007F + some extended ascii characters)
47 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
48 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
49 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
50 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
51 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
52 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
53 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
54 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
55 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
56 U1, U1, U1, U1, U1, U1, U1, U1, U1, U1, //
59 U2, U2, U2, U2, U2, U2, U2, U2, U2, U2, //
60 U2, U2, U2, U2, U2, U2, U2, U2, U2, U2, // lead byte = 110x xxxx (U+0080 - U+07FF)
61 U2, U2, U2, U2, U2, U2, U2, U2, U2, U2, //
64 U3, U3, U3, U3, U3, U3, U3, U3, U3, U3, // lead byte = 1110 xxxx (U+0800 - U+FFFF)
65 U3, U3, U3, U3, U3, U3, //
67 U4, U4, U4, U4, U4, U4, U4, U4, // lead byte = 1111 0xxx (U+10000 - U+1FFFFF)
69 U0, U0, U0, U0, // Non valid.
70 U0, U0, U0, U0, // Non valid.
73 const uint8_t CR = 0xd;
74 const uint8_t LF = 0xa;
77 uint8_t GetUtf8Length( uint8_t utf8LeadByte )
79 return UTF8_LENGTH[utf8LeadByte];
82 uint32_t GetNumberOfUtf8Characters( const uint8_t* const utf8, uint32_t length )
84 uint32_t numberOfCharacters = 0u;
86 const uint8_t* begin = utf8;
87 const uint8_t* end = utf8 + length;
89 for( ; begin < end ; begin += UTF8_LENGTH[*begin], ++numberOfCharacters );
91 return numberOfCharacters;
94 uint32_t GetNumberOfUtf8Bytes( const uint32_t* const utf32, uint32_t numberOfCharacters )
96 uint32_t numberOfBytes = 0u;
98 const uint32_t* begin = utf32;
99 const uint32_t* end = utf32 + numberOfCharacters;
101 for( ; begin < end; ++begin )
103 const uint32_t code = *begin;
109 else if( code < 0x800u )
113 else if( code < 0x10000u )
117 else if( code < 0x200000u )
123 return numberOfBytes;
126 uint32_t Utf8ToUtf32( const uint8_t* const utf8, uint32_t length, uint32_t* utf32 )
128 uint32_t numberOfCharacters = 0u;
130 const uint8_t* begin = utf8;
131 const uint8_t* end = utf8 + length;
133 for( ; begin < end ; ++numberOfCharacters )
135 const uint8_t leadByte = *begin;
137 switch( UTF8_LENGTH[leadByte] )
143 // Replace CR+LF or CR by LF
146 // Look ahead if the next one is a LF.
166 uint32_t& code = *utf32++;
167 code = leadByte & 0x1fu;
170 code |= *begin++ & 0x3fu;
176 uint32_t& code = *utf32++;
177 code = leadByte & 0x0fu;
180 code |= *begin++ & 0x3fu;
182 code |= *begin++ & 0x3fu;
188 uint32_t& code = *utf32++;
189 code = leadByte & 0x07u;
192 code |= *begin++ & 0x3fu;
194 code |= *begin++ & 0x3fu;
196 code |= *begin++ & 0x3fu;
200 case U0: // Invalid case
203 *utf32++ = 0x20; // Use white space
209 return numberOfCharacters;
212 uint32_t Utf32ToUtf8( const uint32_t* const utf32, uint32_t numberOfCharacters, uint8_t* utf8 )
214 const uint32_t* begin = utf32;
215 const uint32_t* end = utf32 + numberOfCharacters;
217 uint8_t* utf8Begin = utf8;
219 for( ; begin < end; ++begin )
221 const uint32_t code = *begin;
227 else if( code < 0x800u )
229 *utf8++ = static_cast<uint8_t>( code >> 6u ) | 0xc0u; // lead byte for 2 byte sequence
230 *utf8++ = static_cast<uint8_t>( code & 0x3f ) | 0x80u; // continuation byte
232 else if( code < 0x10000u )
234 *utf8++ = static_cast<uint8_t>( code >> 12u ) | 0xe0u; // lead byte for 2 byte sequence
235 *utf8++ = static_cast<uint8_t>( ( code >> 6u ) & 0x3f ) | 0x80u; // continuation byte
236 *utf8++ = static_cast<uint8_t>( code & 0x3f ) | 0x80u; // continuation byte
238 else if( code < 0x200000u )
240 *utf8++ = static_cast<uint8_t>( code >> 18u ) | 0xf0u; // lead byte for 2 byte sequence
241 *utf8++ = static_cast<uint8_t>( ( code >> 12u ) & 0x3f ) | 0x80u; // continuation byte
242 *utf8++ = static_cast<uint8_t>( ( code >> 6u ) & 0x3f ) | 0x80u; // continuation byte
243 *utf8++ = static_cast<uint8_t>( code & 0x3f ) | 0x80u; // continuation byte
247 return utf8 - utf8Begin;
250 void Utf32ToUtf8( const uint32_t* const utf32, uint32_t numberOfCharacters, std::string& utf8 )
254 uint32_t numberOfBytes = GetNumberOfUtf8Bytes( &utf32[0], numberOfCharacters );
255 utf8.resize( numberOfBytes );
257 // This is a bit horrible but std::string returns a (signed) char*
258 Utf32ToUtf8( utf32, numberOfCharacters, reinterpret_cast<uint8_t*>(&utf8[0]) );
263 } // namespace Toolkit