Frames | No Frames |
1: /* InputStreamReader.java -- Reader than transforms bytes to chars 2: Copyright (C) 1998, 1999, 2001, 2003, 2004, 2005 Free Software Foundation, Inc. 3: 4: This file is part of GNU Classpath. 5: 6: GNU Classpath is free software; you can redistribute it and/or modify 7: it under the terms of the GNU General Public License as published by 8: the Free Software Foundation; either version 2, or (at your option) 9: any later version. 10: 11: GNU Classpath is distributed in the hope that it will be useful, but 12: WITHOUT ANY WARRANTY; without even the implied warranty of 13: MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14: General Public License for more details. 15: 16: You should have received a copy of the GNU General Public License 17: along with GNU Classpath; see the file COPYING. If not, write to the 18: Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 19: 02110-1301 USA. 20: 21: Linking this library statically or dynamically with other modules is 22: making a combined work based on this library. Thus, the terms and 23: conditions of the GNU General Public License cover the whole 24: combination. 25: 26: As a special exception, the copyright holders of this library give you 27: permission to link this library with independent modules to produce an 28: executable, regardless of the license terms of these independent 29: modules, and to copy and distribute the resulting executable under 30: terms of your choice, provided that you also meet, for each linked 31: independent module, the terms and conditions of the license of that 32: module. An independent module is a module which is not derived from 33: or based on this library. If you modify this library, you may extend 34: this exception to your version of the library, but you are not 35: obligated to do so. If you do not wish to do so, delete this 36: exception statement from your version. */ 37: 38: 39: package java.io; 40: 41: import gnu.gcj.convert.*; 42: import java.nio.charset.Charset; 43: import java.nio.charset.CharsetDecoder; 44: 45: /** 46: * This class reads characters from a byte input stream. The characters 47: * read are converted from bytes in the underlying stream by a 48: * decoding layer. The decoding layer transforms bytes to chars according 49: * to an encoding standard. There are many available encodings to choose 50: * from. The desired encoding can either be specified by name, or if no 51: * encoding is selected, the system default encoding will be used. The 52: * system default encoding name is determined from the system property 53: * <code>file.encoding</code>. The only encodings that are guaranteed to 54: * be availalbe are "8859_1" (the Latin-1 character set) and "UTF8". 55: * Unforunately, Java does not provide a mechanism for listing the 56: * ecodings that are supported in a given implementation. 57: * <p> 58: * Here is a list of standard encoding names that may be available: 59: * <p> 60: * <ul> 61: * <li>8859_1 (ISO-8859-1/Latin-1)</li> 62: * <li>8859_2 (ISO-8859-2/Latin-2)</li> 63: * <li>8859_3 (ISO-8859-3/Latin-3)</li> 64: * <li>8859_4 (ISO-8859-4/Latin-4)</li> 65: * <li>8859_5 (ISO-8859-5/Latin-5)</li> 66: * <li>8859_6 (ISO-8859-6/Latin-6)</li> 67: * <li>8859_7 (ISO-8859-7/Latin-7)</li> 68: * <li>8859_8 (ISO-8859-8/Latin-8)</li> 69: * <li>8859_9 (ISO-8859-9/Latin-9)</li> 70: * <li>ASCII (7-bit ASCII)</li> 71: * <li>UTF8 (UCS Transformation Format-8)</li> 72: * <li>More later</li> 73: * </ul> 74: * <p> 75: * It is recommended that applications do not use 76: * <code>InputStreamReader</code>'s 77: * directly. Rather, for efficiency purposes, an object of this class 78: * should be wrapped by a <code>BufferedReader</code>. 79: * <p> 80: * Due to a deficiency the Java class library design, there is no standard 81: * way for an application to install its own byte-character encoding. 82: * 83: * @see BufferedReader 84: * @see InputStream 85: * 86: * @author Aaron M. Renn (arenn@urbanophile.com) 87: * @author Per Bothner (bothner@cygnus.com) 88: * @date April 22, 1998. 89: */ 90: public class InputStreamReader extends Reader 91: { 92: BufferedInputStream in; 93: 94: // Buffer of chars read from in and converted but not consumed. 95: char[] work; 96: // Next available character (in work buffer) to read. 97: int wpos; 98: // Last available character (in work buffer) to read. 99: int wcount; 100: 101: /* 102: * This is the byte-character decoder class that does the reading and 103: * translation of bytes from the underlying stream. 104: */ 105: BytesToUnicode converter; 106: 107: /** 108: * This method initializes a new instance of <code>InputStreamReader</code> 109: * to read from the specified stream using the default encoding. 110: * 111: * @param in The <code>InputStream</code> to read from 112: */ 113: public InputStreamReader(InputStream in) 114: { 115: this(in, BytesToUnicode.getDefaultDecoder()); 116: } 117: 118: /** 119: * This method initializes a new instance of <code>InputStreamReader</code> 120: * to read from the specified stream using a caller supplied character 121: * encoding scheme. Note that due to a deficiency in the Java language 122: * design, there is no way to determine which encodings are supported. 123: * 124: * @param in The <code>InputStream</code> to read from 125: * @param encoding_name The name of the encoding scheme to use 126: * 127: * @exception UnsupportedEncodingException If the encoding scheme 128: * requested is not available. 129: */ 130: public InputStreamReader(InputStream in, String encoding_name) 131: throws UnsupportedEncodingException 132: { 133: this(in, BytesToUnicode.getDecoder(encoding_name)); 134: } 135: 136: /** 137: * Creates an InputStreamReader that uses a decoder of the given 138: * charset to decode the bytes in the InputStream into 139: * characters. 140: */ 141: public InputStreamReader(InputStream in, Charset charset) 142: { 143: this(in, new BytesToCharsetAdaptor(charset)); 144: } 145: 146: /** 147: * Creates an InputStreamReader that uses the given charset decoder 148: * to decode the bytes in the InputStream into characters. 149: */ 150: public InputStreamReader(InputStream in, CharsetDecoder decoder) 151: { 152: this(in, new BytesToCharsetAdaptor(decoder)); 153: } 154: 155: private InputStreamReader(InputStream in, BytesToUnicode decoder) 156: { 157: // FIXME: someone could pass in a BufferedInputStream whose buffer 158: // is smaller than the longest encoded character for this 159: // encoding. We will probably go into an infinite loop in this 160: // case. We probably ought to just have our own byte buffering 161: // here. 162: this.in = in instanceof BufferedInputStream 163: ? (BufferedInputStream) in 164: : new BufferedInputStream(in); 165: /* Don't need to call super(in) here as long as the lock gets set. */ 166: this.lock = in; 167: converter = decoder; 168: converter.setInput(this.in.buf, 0, 0); 169: } 170: 171: /** 172: * This method closes this stream, as well as the underlying 173: * <code>InputStream</code>. 174: * 175: * @exception IOException If an error occurs 176: */ 177: public void close() throws IOException 178: { 179: synchronized (lock) 180: { 181: if (in != null) 182: in.close(); 183: in = null; 184: work = null; 185: wpos = wcount = 0; 186: } 187: } 188: 189: /** 190: * This method returns the name of the encoding that is currently in use 191: * by this object. If the stream has been closed, this method is allowed 192: * to return <code>null</code>. 193: * 194: * @return The current encoding name 195: */ 196: public String getEncoding() 197: { 198: return in != null ? converter.getName() : null; 199: } 200: 201: /** 202: * This method checks to see if the stream is read to be read. It 203: * will return <code>true</code> if is, or <code>false</code> if it is not. 204: * If the stream is not ready to be read, it could (although is not required 205: * to) block on the next read attempt. 206: * 207: * @return <code>true</code> if the stream is ready to be read, 208: * <code>false</code> otherwise 209: * 210: * @exception IOException If an error occurs 211: */ 212: public boolean ready() throws IOException 213: { 214: synchronized (lock) 215: { 216: if (in == null) 217: throw new IOException("Stream closed"); 218: 219: if (wpos < wcount) 220: return true; 221: 222: // According to the spec, an InputStreamReader is ready if its 223: // input buffer is not empty (above), or if bytes are 224: // available on the underlying byte stream. 225: return in.available () > 0; 226: } 227: } 228: 229: /** 230: * This method reads up to <code>length</code> characters from the stream into 231: * the specified array starting at index <code>offset</code> into the 232: * array. 233: * 234: * @param buf The character array to recieve the data read 235: * @param offset The offset into the array to start storing characters 236: * @param length The requested number of characters to read. 237: * 238: * @return The actual number of characters read, or -1 if end of stream. 239: * 240: * @exception IOException If an error occurs 241: */ 242: public int read (char[] buf, int offset, int length) throws IOException 243: { 244: synchronized (lock) 245: { 246: if (in == null) 247: throw new IOException("Stream closed"); 248: 249: if (length == 0) 250: return 0; 251: 252: int wavail = wcount - wpos; 253: if (wavail <= 0) 254: { 255: // Nothing waiting, so refill their buffer. 256: return refill(buf, offset, length); 257: } 258: 259: if (length > wavail) 260: length = wavail; 261: System.arraycopy(work, wpos, buf, offset, length); 262: wpos += length; 263: return length; 264: } 265: } 266: 267: /** 268: * This method reads a single character of data from the stream. 269: * 270: * @return The char read, as an int, or -1 if end of stream. 271: * 272: * @exception IOException If an error occurs 273: */ 274: public int read() throws IOException 275: { 276: synchronized (lock) 277: { 278: if (in == null) 279: throw new IOException("Stream closed"); 280: 281: int wavail = wcount - wpos; 282: if (wavail <= 0) 283: { 284: // Nothing waiting, so refill our internal buffer. 285: wpos = wcount = 0; 286: if (work == null) 287: work = new char[100]; 288: int count = refill(work, 0, work.length); 289: if (count == -1) 290: return -1; 291: wcount += count; 292: } 293: 294: return work[wpos++]; 295: } 296: } 297: 298: // Read more bytes and convert them into the specified buffer. 299: // Returns the number of converted characters or -1 on EOF. 300: private int refill(char[] buf, int offset, int length) throws IOException 301: { 302: for (;;) 303: { 304: // We have knowledge of the internals of BufferedInputStream 305: // here. Eww. 306: // BufferedInputStream.refill() can only be called when 307: // `pos>=count'. 308: boolean r = in.pos < in.count || in.refill (); 309: if (! r) 310: return -1; 311: converter.setInput(in.buf, in.pos, in.count); 312: int count = converter.read(buf, offset, length); 313: 314: // We might have bytes but not have made any progress. In 315: // this case we try to refill. If refilling fails, we assume 316: // we have a malformed character at the end of the stream. 317: if (count == 0 && converter.inpos == in.pos) 318: { 319: in.mark(in.count); 320: if (! in.refill ()) 321: throw new CharConversionException (); 322: in.reset(); 323: } 324: else 325: { 326: in.skip(converter.inpos - in.pos); 327: if (count > 0) 328: return count; 329: } 330: } 331: } 332: }