2 // Open Service Platform
3 // Copyright (c) 2012 Samsung Electronics Co., Ltd.
5 // Licensed under the Apache License, Version 2.0 (the License);
6 // you may not use this file except in compliance with the License.
7 // You may obtain a copy of the License at
9 // http://www.apache.org/licenses/LICENSE-2.0
11 // Unless required by applicable law or agreed to in writing, software
12 // distributed under the License is distributed on an "AS IS" BASIS,
13 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 // See the License for the specific language governing permissions and
15 // limitations under the License.
19 * @file FTextUtf8Encoder.h
20 * @brief This is the header file for the %Utf8Encoder class.
22 * This header file contains the declarations of the %Utf8Encoder class.
25 #ifndef _FTEXT_UTF8_ENCODER_H_
26 #define _FTEXT_UTF8_ENCODER_H_
28 #include <FTextEncoder.h>
29 #include <FBaseByteBuffer.h>
32 namespace Tizen { namespace Text
37 * @brief This class is an implementation of the UTF-8 encoder.
41 * @final This class is not intended for extension.
43 * The %Utf8Encoder class converts the blocks of characters into encoded blocks of bytes.
44 * Universal Transformation Format-8 (UTF-8) is a translated language that is used on the internet. It converts the
45 * unicode into 8-bit bytes. @n UTF-8 encoding supports all unicode character values and surrogates.
46 * Note that %Utf8Encoder is not used in reality, because keeping the internal state of encoding from unicode
47 * to UTF-8 can be avoided if the translation unit is even.
48 * This means that the real implementation of %Utf8Encoder is the same as that of Utf8Encoding in this state.
50 * For more information on the class features, see <a href="../org.tizen.native.appprogramming/html/guide/text/converting_text_data_separate_blocks.htm">Converting Text Data in Separate Blocks</a>.
52 * The following example demonstrates how to use the %Utf8Encoder class.
59 * using namespace Tizen::Base;
60 * using namespace Tizen::Text;
63 * MyClass::Utf8EncoderSample(void)
67 * // Fills a WcharBuffer with the unicode strings to encode it into UTF8 format bytes.
68 * WcharBuffer* pMB = PrepareUtf8EncoderSample();
70 * int charBufSize = pMB->GetCapacity();
73 * utf8En.GetByteCount(*pMB, 0, charBufSize, byteCount);
76 * enBytes.Construct(byteCount);
79 * int charCount = 100;
81 * while (charIndex < charBufSize)
83 * ByteBuffer* pBB = null;
85 * if (charBufSize - charIndex < charCount)
87 * charCount = charBufSize - charIndex;
90 * // Converts Unicode to Utf8 using Utf8Encoder.
91 * pBB = utf8En.GetBytesN(*pMB, charIndex, charCount); // flush is false
93 * enBytes.CopyFrom(*pBB);
94 * charIndex += charCount;
99 * enBytes.SetByte('\0');
108 class _OSP_EXPORT_ Utf8Encoder
113 * This is the default constructor for this class.
121 * This is the destructor for this class. @n
122 * This destructor overrides Tizen::Text::Encoder::~Encoder().
126 virtual ~Utf8Encoder(void);
129 * Gets the total number of bytes that are required to encode a range of characters in the specified Tizen::Base::WcharBuffer instance.
133 * @return An error code
134 * @param[in] chars An instance of Tizen::Base::WcharBuffer to encode
135 * @param[in] charIndex The index from where encoding begins in the Tizen::Base::WcharBuffer instance
136 * @param[in] charCount The total number of characters to encode
137 * @param[in] flush Set to @c true to allow this instance to flush its state at the end of the conversion, @n
139 * @param[out] byteCount The total number of bytes required to encode the specified range of characters
140 * @exception E_SUCCESS The method is successful.
141 * @exception E_INVALID_ARG A specified input parameter is invalid, or
142 * the specified @c chars is empty.
143 * @exception E_OUT_OF_RANGE The value of an argument is outside the valid range defined by the method, or
144 * the length of the specified @c charIndex or @c charCount is greater than the length of the specified @c chars.
145 * @exception E_UNDERFLOW This operation has caused the memory to underflow, or
146 * the sum of the length of the specified @c charIndex and @c charCount is greater than the length of the specified @c chars.
147 * @exception E_INVALID_ENCODING_RANGE The specified string contains code points that are outside the bounds of the character encoding scheme.
148 * @see Utf8Decoder::GetCharCount()
150 virtual result GetByteCount(const Tizen::Base::WcharBuffer& chars,
151 int charIndex, int charCount, int& byteCount, bool flush = false) const;
154 * Encodes an instance of Tizen::Base::WcharBuffer into an instance of Tizen::Base::ByteBuffer.
158 * @return A pointer to the Tizen::Base::ByteBuffer instance where the resultant encoded string is stored, @n
159 * else @c null if an exception occurs @n
160 * The buffer limit is the position of the last encoded byte plus one and the starting position is zero.
161 * @param[in] chars An instance of Tizen::Base::WcharBuffer to encode
162 * @param[in] flush Set to @c true to allow this instance to flush its state at the end of the conversion, @n
164 * @exception E_SUCCESS The method is successful.
165 * @exception E_OUT_OF_MEMORY The memory is insufficient.
166 * @exception E_INVALID_ARG A specified input parameter is invalid, or
167 * the specified @c chars is empty.
168 * @exception E_INVALID_ENCODING_RANGE The specified string contains code points that are outside the bounds of the character encoding scheme.
169 * @remarks The specific error code can be accessed using the GetLastResult() method.
170 * @see Utf8Decoder::GetCharsN()
172 virtual Tizen::Base::ByteBuffer* GetBytesN(const Tizen::Base::WcharBuffer& chars, bool flush = false) const;
175 * Encodes an instance of Tizen::Base::WcharBuffer into an instance of Tizen::Base::ByteBuffer as per the specified range.
179 * @return A pointer to the Tizen::Base::ByteBuffer instance where the resultant encoded string is stored, @n
180 * else @c null if an exception occurs @n
181 * The buffer limit is the position of the last encoded byte and the starting position is zero.
182 * @param[in] chars An instance of Tizen::Base::WcharBuffer to encode
183 * @param[in] charIndex The index from where encoding begins in the Tizen::Base::WcharBuffer instance
184 * @param[in] charCount The total number of characters to encode
185 * @param[in] flush Set to @c true to allow this instance to flush its state at the end of the conversion, @n
187 * @exception E_SUCCESS The method is successful.
188 * @exception E_OUT_OF_MEMORY The memory is insufficient.
189 * @exception E_INVALID_ARG A specified input parameter is invalid, or
190 * the specified @c chars is empty.
191 * @exception E_OUT_OF_RANGE The value of an argument is outside the valid range defined by the method, or
192 * the length of the specified @c charIndex or @c charCount is greater than the length of the specified @c chars.
193 * @exception E_UNDERFLOW This operation has caused the memory to underflow, or
194 * the sum of the length of the specified @c charIndex and @c charCount is greater than the length of the specified @c chars.
195 * @exception E_INVALID_ENCODING_RANGE The specified string contains code points that are outside the bounds of the character encoding scheme.
196 * @remarks The specific error code can be accessed using the GetLastResult() method.
197 * @remarks The pointer to the Tizen::Base::ByteBuffer instance is not terminated by a @c null character.
198 * @see Utf8Decoder::GetCharsN()
200 virtual Tizen::Base::ByteBuffer* GetBytesN(const Tizen::Base::WcharBuffer& chars, int charIndex, int charCount,
201 bool flush = false) const;
205 * The implementation of this copy constructor is intentionally blank and declared as private to
206 * prohibit copying of objects.
208 Utf8Encoder(const Utf8Encoder& utf8Encoder);
211 * The implementation of this copy assignment operator is intentionally blank and declared as private
212 * to prohibit copying of objects.
214 Utf8Encoder& operator =(const Utf8Encoder& utf8Encoder);
216 friend class _Utf8EncoderImpl;
217 class _Utf8EncoderImpl* __pUtf8EncoderImpl;
221 #endif //_FTEXT_UTF8_ENCODER_H_