Source Code Cross Referenced for UTF8StreamReader.java in  » Development » Javolution » javolution » io » Java Source Code / Java DocumentationJava Source Code and Java Documentation

Java Source Code / Java Documentation
1. 6.0 JDK Core
2. 6.0 JDK Modules
3. 6.0 JDK Modules com.sun
4. 6.0 JDK Modules com.sun.java
5. 6.0 JDK Modules sun
6. 6.0 JDK Platform
7. Ajax
8. Apache Harmony Java SE
9. Aspect oriented
10. Authentication Authorization
11. Blogger System
12. Build
13. Byte Code
14. Cache
15. Chart
16. Chat
17. Code Analyzer
18. Collaboration
19. Content Management System
20. Database Client
21. Database DBMS
22. Database JDBC Connection Pool
23. Database ORM
24. Development
25. EJB Server geronimo
26. EJB Server GlassFish
27. EJB Server JBoss 4.2.1
28. EJB Server resin 3.1.5
29. ERP CRM Financial
30. ESB
31. Forum
32. GIS
33. Graphic Library
34. Groupware
35. HTML Parser
36. IDE
37. IDE Eclipse
38. IDE Netbeans
39. Installer
40. Internationalization Localization
41. Inversion of Control
42. Issue Tracking
43. J2EE
44. JBoss
45. JMS
46. JMX
47. Library
48. Mail Clients
49. Net
50. Parser
51. PDF
52. Portal
53. Profiler
54. Project Management
55. Report
56. RSS RDF
57. Rule Engine
58. Science
59. Scripting
60. Search Engine
61. Security
62. Sevlet Container
63. Source Control
64. Swing Library
65. Template Engine
66. Test Coverage
67. Testing
68. UML
69. Web Crawler
70. Web Framework
71. Web Mail
72. Web Server
73. Web Services
74. Web Services apache cxf 2.0.1
75. Web Services AXIS2
76. Wiki Engine
77. Workflow Engines
78. XML
79. XML UI
Java
Java Tutorial
Java Open Source
Jar File Download
Java Articles
Java Products
Java by API
Photoshop Tutorials
Maya Tutorials
Flash Tutorials
3ds-Max Tutorials
Illustrator Tutorials
GIMP Tutorials
C# / C Sharp
C# / CSharp Tutorial
C# / CSharp Open Source
ASP.Net
ASP.NET Tutorial
JavaScript DHTML
JavaScript Tutorial
JavaScript Reference
HTML / CSS
HTML CSS Reference
C / ANSI-C
C Tutorial
C++
C++ Tutorial
Ruby
PHP
Python
Python Tutorial
Python Open Source
SQL Server / T-SQL
SQL Server / T-SQL Tutorial
Oracle PL / SQL
Oracle PL/SQL Tutorial
PostgreSQL
SQL / MySQL
MySQL Tutorial
VB.Net
VB.Net Tutorial
Flash / Flex / ActionScript
VBA / Excel / Access / Word
XML
XML Tutorial
Microsoft Office PowerPoint 2007 Tutorial
Microsoft Office Excel 2007 Tutorial
Microsoft Office Word 2007 Tutorial
Java Source Code / Java Documentation » Development » Javolution » javolution.io 
Source Cross Referenced  Class Diagram Java Document (Java Doc) 


001:        /*
002:         * Javolution - Java(TM) Solution for Real-Time and Embedded Systems
003:         * Copyright (C) 2006 - Javolution (http://javolution.org/)
004:         * All rights reserved.
005:         * 
006:         * Permission to use, copy, modify, and distribute this software is
007:         * freely granted, provided that this notice is preserved.
008:         */
009:        package javolution.io;
010:
011:        import j2me.lang.IllegalStateException;
012:        import j2me.io.CharConversionException;
013:
014:        import java.io.IOException;
015:        import java.io.InputStream;
016:        import java.io.Reader;
017:
018:        import javolution.lang.Reusable;
019:        import javolution.text.Appendable;
020:
021:        /**
022:         * <p> This class represents a UTF-8 stream reader.</p>
023:         *
024:         * <p> This reader supports surrogate <code>char</code> pairs (representing
025:         *     characters in the range [U+10000 .. U+10FFFF]). It can also be used
026:         *     to read characters unicodes (31 bits) directly
027:         *     (ref. {@link #read()}).</p>
028:         *
029:         * <p> Each invocation of one of the <code>read()</code> methods may cause one
030:         *     or more bytes to be read from the underlying byte-input stream.
031:         *     To enable the efficient conversion of bytes to characters, more bytes may
032:         *     be read ahead from the underlying stream than are necessary to satisfy
033:         *     the current read operation.</p>
034:         *
035:         * <p> Instances of this class can be reused for different input streams
036:         *     and can be part of a higher level component (e.g. parser) in order
037:         *     to avoid dynamic buffer allocation when the input source changes.
038:         *     Also wrapping using a <code>java.io.BufferedReader</code> is unnescessary
039:         *     as instances of this class embed their own data buffers.</p>
040:         *
041:         * <p> Note: This reader is unsynchronized and does not test if the UTF-8
042:         *           encoding is well-formed (e.g. UTF-8 sequences longer than
043:         *           necessary to encode a character).</p>
044:         *
045:         * @author  <a href="mailto:jean-marie@dautelle.com">Jean-Marie Dautelle</a>
046:         * @version 2.0, December 9, 2004
047:         * @see     UTF8StreamWriter
048:         */
049:        public final class UTF8StreamReader extends Reader implements  Reusable {
050:
051:            /**
052:             * Holds the current input stream or <code>null</code> if closed.
053:             */
054:            private InputStream _inputStream;
055:
056:            /**
057:             * Holds the start index.
058:             */
059:            private int _start;
060:
061:            /**
062:             * Holds the end index.
063:             */
064:            private int _end;
065:
066:            /**
067:             * Holds the bytes buffer.
068:             */
069:            private final byte[] _bytes;
070:
071:            /**
072:             * Creates a UTF-8 reader having a byte buffer of moderate capacity (2048).
073:             */
074:            public UTF8StreamReader() {
075:                _bytes = new byte[2048];
076:            }
077:
078:            /**
079:             * Creates a UTF-8 reader having a byte buffer of specified capacity.
080:             * 
081:             * @param capacity the capacity of the byte buffer.
082:             */
083:            public UTF8StreamReader(int capacity) {
084:                _bytes = new byte[capacity];
085:            }
086:
087:            /**
088:             * Sets the input stream to use for reading until this reader is closed.
089:             * For example:[code]
090:             *     Reader reader = new UTF8StreamReader().setInput(inStream);
091:             * [/code] is equivalent but reads twice as fast as [code]
092:             *     Reader reader = new j2me.io.InputStreamReader(inStream, "UTF-8");
093:             * [/code]
094:             *
095:             * @param  inStream the input stream.
096:             * @return this UTF-8 reader.
097:             * @throws IllegalStateException if this reader is being reused and 
098:             *         it has not been {@link #close closed} or {@link #reset reset}.
099:             */
100:            public UTF8StreamReader setInput(InputStream inStream) {
101:                if (_inputStream != null)
102:                    throw new IllegalStateException(
103:                            "Reader not closed or reset");
104:                _inputStream = inStream;
105:                return this ;
106:            }
107:
108:            /**
109:             * Indicates if this stream is ready to be read.
110:             *
111:             * @return <code>true</code> if the next read() is guaranteed not to block
112:             *         for input; <code>false</code> otherwise.
113:             * @throws  IOException if an I/O error occurs.
114:             */
115:            public boolean ready() throws IOException {
116:                if (_inputStream == null)
117:                    throw new IOException("Stream closed");
118:                return ((_end - _start) > 0) || (_inputStream.available() != 0);
119:            }
120:
121:            /**
122:             * Closes and {@link #reset resets} this reader for reuse.
123:             *
124:             * @throws IOException if an I/O error occurs.
125:             */
126:            public void close() throws IOException {
127:                if (_inputStream != null) {
128:                    _inputStream.close();
129:                    reset();
130:                }
131:            }
132:
133:            /**
134:             * Reads a single character.  This method will block until a character is
135:             * available, an I/O error occurs or the end of the stream is reached.
136:             *
137:             * @return the 31-bits Unicode of the character read, or -1 if the end of
138:             *         the stream has been reached.
139:             * @throws IOException if an I/O error occurs.
140:             */
141:            public int read() throws IOException {
142:                byte b = _bytes[_start];
143:                return ((b >= 0) && (_start++ < _end)) ? b : read2();
144:            }
145:
146:            // Reads one full character, blocks if necessary.
147:            private int read2() throws IOException {
148:                if (_start < _end) {
149:                    byte b = _bytes[_start++];
150:
151:                    // Decodes UTF-8.
152:                    if ((b >= 0) && (_moreBytes == 0)) {
153:                        // 0xxxxxxx
154:                        return b;
155:                    } else if (((b & 0xc0) == 0x80) && (_moreBytes != 0)) {
156:                        // 10xxxxxx (continuation byte)
157:                        _code = (_code << 6) | (b & 0x3f); // Adds 6 bits to code.
158:                        if (--_moreBytes == 0) {
159:                            return _code;
160:                        } else {
161:                            return read2();
162:                        }
163:                    } else if (((b & 0xe0) == 0xc0) && (_moreBytes == 0)) {
164:                        // 110xxxxx
165:                        _code = b & 0x1f;
166:                        _moreBytes = 1;
167:                        return read2();
168:                    } else if (((b & 0xf0) == 0xe0) && (_moreBytes == 0)) {
169:                        // 1110xxxx
170:                        _code = b & 0x0f;
171:                        _moreBytes = 2;
172:                        return read2();
173:                    } else if (((b & 0xf8) == 0xf0) && (_moreBytes == 0)) {
174:                        // 11110xxx
175:                        _code = b & 0x07;
176:                        _moreBytes = 3;
177:                        return read2();
178:                    } else if (((b & 0xfc) == 0xf8) && (_moreBytes == 0)) {
179:                        // 111110xx
180:                        _code = b & 0x03;
181:                        _moreBytes = 4;
182:                        return read2();
183:                    } else if (((b & 0xfe) == 0xfc) && (_moreBytes == 0)) {
184:                        // 1111110x
185:                        _code = b & 0x01;
186:                        _moreBytes = 5;
187:                        return read2();
188:                    } else {
189:                        throw new CharConversionException(
190:                                "Invalid UTF-8 Encoding");
191:                    }
192:                } else { // No more bytes in buffer.
193:                    if (_inputStream == null)
194:                        throw new IOException(
195:                                "No input stream or stream closed");
196:                    _start = 0;
197:                    _end = _inputStream.read(_bytes, 0, _bytes.length);
198:                    if (_end > 0) {
199:                        return read2(); // Continues.
200:                    } else { // Done.
201:                        if (_moreBytes == 0) {
202:                            return -1;
203:                        } else { // Incomplete sequence.
204:                            throw new CharConversionException(
205:                                    "Unexpected end of stream");
206:                        }
207:                    }
208:                }
209:            }
210:
211:            private int _code;
212:
213:            private int _moreBytes;
214:
215:            /**
216:             * Reads characters into a portion of an array.  This method will block
217:             * until some input is available, an I/O error occurs or the end of 
218:             * the stream is reached.
219:             *
220:             * <p> Note: Characters between U+10000 and U+10FFFF are represented
221:             *     by surrogate pairs (two <code>char</code>).</p>
222:             *
223:             * @param  cbuf the destination buffer.
224:             * @param  off the offset at which to start storing characters.
225:             * @param  len the maximum number of characters to read
226:             * @return the number of characters read, or -1 if the end of the
227:             *         stream has been reached
228:             * @throws IOException if an I/O error occurs.
229:             */
230:            public int read(char cbuf[], int off, int len) throws IOException {
231:                if (_inputStream == null)
232:                    throw new IOException("No input stream or stream closed");
233:                if (_start >= _end) { // Fills buffer.
234:                    _start = 0;
235:                    _end = _inputStream.read(_bytes, 0, _bytes.length);
236:                    if (_end <= 0) { // Done.
237:                        return _end;
238:                    }
239:                }
240:                final int off_plus_len = off + len;
241:                for (int i = off; i < off_plus_len;) {
242:                    // assert(_start < _end)
243:                    byte b = _bytes[_start];
244:                    if ((b >= 0) && (++_start < _end)) {
245:                        cbuf[i++] = (char) b; // Most common case.
246:                    } else if (b < 0) {
247:                        if (i < off_plus_len - 1) { // Up to two 'char' can be read.
248:                            int code = read2();
249:                            if (code < 0x10000) {
250:                                cbuf[i++] = (char) code;
251:                            } else if (code <= 0x10ffff) { // Surrogates.
252:                                cbuf[i++] = (char) (((code - 0x10000) >> 10) + 0xd800);
253:                                cbuf[i++] = (char) (((code - 0x10000) & 0x3ff) + 0xdc00);
254:                            } else {
255:                                throw new CharConversionException(
256:                                        "Cannot convert U+"
257:                                                + Integer.toHexString(code)
258:                                                + " to char (code greater than U+10FFFF)");
259:                            }
260:                            if (_start < _end) {
261:                                continue;
262:                            }
263:                        }
264:                        return i - off;
265:                    } else { // End of buffer (_start >= _end).
266:                        cbuf[i++] = (char) b;
267:                        return i - off;
268:                    }
269:                }
270:                return len;
271:            }
272:
273:            /**
274:             * Reads characters into the specified appendable.  This method will block
275:             * until the end of the stream is reached.
276:             *
277:             * @param  dest the destination buffer.
278:             * @throws IOException if an I/O error occurs.
279:             */
280:            public void read(Appendable dest) throws IOException {
281:                if (_inputStream == null)
282:                    throw new IOException("No input stream or stream closed");
283:                while (true) {
284:                    if (_start >= _end) { // Fills buffer.
285:                        _start = 0;
286:                        _end = _inputStream.read(_bytes, 0, _bytes.length);
287:                        if (_end <= 0) { // Done.
288:                            break;
289:                        }
290:                    }
291:                    byte b = _bytes[_start];
292:                    if (b >= 0) {
293:                        dest.append((char) b); // Most common case.
294:                        _start++;
295:                    } else {
296:                        int code = read2();
297:                        if (code < 0x10000) {
298:                            dest.append((char) code);
299:                        } else if (code <= 0x10ffff) { // Surrogates.
300:                            dest
301:                                    .append((char) (((code - 0x10000) >> 10) + 0xd800));
302:                            dest
303:                                    .append((char) (((code - 0x10000) & 0x3ff) + 0xdc00));
304:                        } else {
305:                            throw new CharConversionException(
306:                                    "Cannot convert U+"
307:                                            + Integer.toHexString(code)
308:                                            + " to char (code greater than U+10FFFF)");
309:                        }
310:                    }
311:                }
312:            }
313:
314:            // Implements Reusable.
315:            public void reset() {
316:                _code = 0;
317:                _end = 0;
318:                _inputStream = null;
319:                _moreBytes = 0;
320:                _start = 0;
321:            }
322:
323:            /**
324:             * @deprecated Replaced by {@link #setInput(InputStream)}
325:             */
326:            public UTF8StreamReader setInputStream(InputStream inStream) {
327:                return this.setInput(inStream);
328:            }
329:        }
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.