FileDocCategorySizeDatePackage
UTF8Reader.javaAPI DocJava SE 6 API23884Tue Jun 10 00:22:42 BST 2008com.sun.org.apache.xerces.internal.impl.io

UTF8Reader

public class UTF8Reader extends Reader

A UTF-8 reader.

xerces.internal
author
Andy Clark, IBM
version
$Id: UTF8Reader.java,v 1.3 2005/09/26 13:02:28 sunithareddy Exp $

Fields Summary
public static final int
DEFAULT_BUFFER_SIZE
Default byte buffer size (2048).
private static final boolean
DEBUG_READ
Debug read.
protected InputStream
fInputStream
Input stream.
protected byte[]
fBuffer
Byte buffer.
protected int
fOffset
Offset into buffer.
private int
fSurrogate
Surrogate character.
private MessageFormatter
fFormatter
private Locale
fLocale
Constructors Summary
public UTF8Reader(InputStream inputStream)
Constructs a UTF-8 reader from the specified input stream using the default buffer size. Primarily for testing.

param
inputStream The input stream.


    //
    // Constructors
    //

                                
       
        this(inputStream, DEFAULT_BUFFER_SIZE, new XMLMessageFormatter(), Locale.getDefault());
    
public UTF8Reader(InputStream inputStream, MessageFormatter messageFormatter, Locale locale)
Constructs a UTF-8 reader from the specified input stream using the default buffer size and the given MessageFormatter.

param
inputStream The input stream.
param
messageFormatter given MessageFormatter
param
locale Locale to use for messages

        this(inputStream, DEFAULT_BUFFER_SIZE, messageFormatter, locale);
    
public UTF8Reader(InputStream inputStream, int size, MessageFormatter messageFormatter, Locale locale)
Constructs a UTF-8 reader from the specified input stream, buffer size and MessageFormatter.

param
inputStream The input stream.
param
size The initial buffer size.
param
messageFormatter the formatter for localizing/formatting errors.
param
locale the Locale to use for messages

        fInputStream = inputStream;
        fBuffer = new byte[size];
        fFormatter = messageFormatter;
        fLocale = locale;
    
Methods Summary
public voidclose()
Close the stream. Once a stream has been closed, further read(), ready(), mark(), or reset() invocations will throw an IOException. Closing a previously-closed stream, however, has no effect.

exception
IOException If an I/O error occurs

        fInputStream.close();
    
private voidexpectedByte(int position, int count)
Throws an exception for expected byte.


        throw new MalformedByteSequenceException(fFormatter,
            fLocale,
            XMLMessageFormatter.XML_DOMAIN,
            "ExpectedByte",
            new Object[] {Integer.toString(position), Integer.toString(count)});

    
private voidinvalidByte(int position, int count, int c)
Throws an exception for invalid byte.


        throw new MalformedByteSequenceException(fFormatter,
            fLocale,
            XMLMessageFormatter.XML_DOMAIN,
            "InvalidByte", 
            new Object [] {Integer.toString(position), Integer.toString(count)});

    
private voidinvalidSurrogate(int uuuuu)
Throws an exception for invalid surrogate bits.


        throw new MalformedByteSequenceException(fFormatter,
            fLocale,
            XMLMessageFormatter.XML_DOMAIN,
            "InvalidHighSurrogate", 
            new Object[] {Integer.toHexString(uuuuu)});

    
public voidmark(int readAheadLimit)
Mark the present position in the stream. Subsequent calls to reset() will attempt to reposition the stream to this point. Not all character-input streams support the mark() operation.

param
readAheadLimit Limit on the number of characters that may be read while still preserving the mark. After reading this many characters, attempting to reset the stream may fail.
exception
IOException If the stream does not support mark(), or if some other I/O error occurs

        throw new IOException(fFormatter.formatMessage(fLocale, "OperationNotSupported", new Object[]{"mark()", "UTF-8"}));
    
public booleanmarkSupported()
Tell whether this stream supports the mark() operation.

        return false;
    
public intread()
Read a single character. This method will block until a character is available, an I/O error occurs, or the end of the stream is reached.

Subclasses that intend to support efficient single-character input should override this method.

return
The character read, as an integer in the range 0 to 16383 (0x00-0xffff), or -1 if the end of the stream has been reached
exception
IOException If an I/O error occurs


        // decode character
        int c = fSurrogate;
        if (fSurrogate == -1) {
            // NOTE: We use the index into the buffer if there are remaining
            //       bytes from the last block read. -Ac
            int index = 0;

            // get first byte
            int b0 = index == fOffset
                   ? fInputStream.read() : fBuffer[index++] & 0x00FF;
            if (b0 == -1) {
                return -1;
            }

            // UTF-8:   [0xxx xxxx]
            // Unicode: [0000 0000] [0xxx xxxx]
            if (b0 < 0x80) {
                c = (char)b0;
            }

            // UTF-8:   [110y yyyy] [10xx xxxx]
            // Unicode: [0000 0yyy] [yyxx xxxx]
            else if ((b0 & 0xE0) == 0xC0 && (b0 & 0x1E) != 0) {
                int b1 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b1 == -1) {
                    expectedByte(2, 2);
                }
                if ((b1 & 0xC0) != 0x80) {
                    invalidByte(2, 2, b1);
                }
                c = ((b0 << 6) & 0x07C0) | (b1 & 0x003F);
            }

            // UTF-8:   [1110 zzzz] [10yy yyyy] [10xx xxxx]
            // Unicode: [zzzz yyyy] [yyxx xxxx]
            else if ((b0 & 0xF0) == 0xE0) {
                int b1 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b1 == -1) {
                    expectedByte(2, 3);
                }
                if ((b1 & 0xC0) != 0x80 
                    || (b0 == 0xED && b1 >= 0xA0)
                    || ((b0 & 0x0F) == 0 && (b1 & 0x20) == 0)) {
                    invalidByte(2, 3, b1);
                }
                int b2 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b2 == -1) {
                    expectedByte(3, 3);
                }
                if ((b2 & 0xC0) != 0x80) {
                    invalidByte(3, 3, b2);
                }
                c = ((b0 << 12) & 0xF000) | ((b1 << 6) & 0x0FC0) |
                    (b2 & 0x003F);
            }

            // UTF-8:   [1111 0uuu] [10uu zzzz] [10yy yyyy] [10xx xxxx]*
            // Unicode: [1101 10ww] [wwzz zzyy] (high surrogate)
            //          [1101 11yy] [yyxx xxxx] (low surrogate)
            //          * uuuuu = wwww + 1
            else if ((b0 & 0xF8) == 0xF0) {
                int b1 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b1 == -1) {
                    expectedByte(2, 4);
                }
                if ((b1 & 0xC0) != 0x80
                    || ((b1 & 0x30) == 0 && (b0 & 0x07) == 0)) {
                    invalidByte(2, 3, b1);
                }
                int b2 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b2 == -1) {
                    expectedByte(3, 4);
                }
                if ((b2 & 0xC0) != 0x80) {
                    invalidByte(3, 3, b2);
                }
                int b3 = index == fOffset
                       ? fInputStream.read() : fBuffer[index++] & 0x00FF;
                if (b3 == -1) {
                    expectedByte(4, 4);
                }
                if ((b3 & 0xC0) != 0x80) {
                    invalidByte(4, 4, b3);
                }
                int uuuuu = ((b0 << 2) & 0x001C) | ((b1 >> 4) & 0x0003);
                if (uuuuu > 0x10) {
                    invalidSurrogate(uuuuu);
                }
                int wwww = uuuuu - 1;
                int hs = 0xD800 |
                         ((wwww << 6) & 0x03C0) | ((b1 << 2) & 0x003C) |
                         ((b2 >> 4) & 0x0003);
                int ls = 0xDC00 | ((b2 << 6) & 0x03C0) | (b3 & 0x003F);
                c = hs;
                fSurrogate = ls;
            }

            // error
            else {
                invalidByte(1, 1, b0);
            }
        }

        // use surrogate
        else {
            fSurrogate = -1;
        }

        // return character
        if (DEBUG_READ) {
            System.out.println("read(): 0x"+Integer.toHexString(c));
        }
        return c;

    
public intread(char[] ch, int offset, int length)
Read characters into a portion of an array. This method will block until some input is available, an I/O error occurs, or the end of the stream is reached.

param
ch Destination buffer
param
offset Offset at which to start storing characters
param
length Maximum number of characters to read
return
The number of characters read, or -1 if the end of the stream has been reached
exception
IOException If an I/O error occurs


        // handle surrogate
        int out = offset;
        if (fSurrogate != -1) {
            ch[offset + 1] = (char)fSurrogate;
            fSurrogate = -1;
            length--;
            out++;
        }

        // read bytes
        int count = 0;
        if (fOffset == 0) {
            // adjust length to read
            if (length > fBuffer.length) {
                length = fBuffer.length;
            }

            // perform read operation
            count = fInputStream.read(fBuffer, 0, length);
            if (count == -1) {
                return -1;
            }
            count += out - offset;
        }

        // skip read; last character was in error
        // NOTE: Having an offset value other than zero means that there was
        //       an error in the last character read. In this case, we have
        //       skipped the read so we don't consume any bytes past the
        //       error. By signalling the error on the next block read we
        //       allow the method to return the most valid characters that
        //       it can on the previous block read. -Ac
        else {
            count = fOffset;
            fOffset = 0;
        }

        // convert bytes to characters
        final int total = count;
        int in;
        byte byte1;
        final byte byte0 = 0;
        for (in = 0; in < total; in++) {
            byte1 = fBuffer[in];
            if (byte1 >= byte0) {
                ch[out++] = (char)byte1;
            }
            else   {
                break;
            }
        }
        for ( ; in < total; in++) {
            byte1 = fBuffer[in];

            // UTF-8:   [0xxx xxxx]
            // Unicode: [0000 0000] [0xxx xxxx]
            if (byte1 >= byte0) {
                ch[out++] = (char)byte1;
                continue;
            }

            // UTF-8:   [110y yyyy] [10xx xxxx]
            // Unicode: [0000 0yyy] [yyxx xxxx]
            int b0 = byte1 & 0x0FF;
            if ((b0 & 0xE0) == 0xC0 && (b0 & 0x1E) != 0) {
                int b1 = -1;
                if (++in < total) {
                    b1 = fBuffer[in] & 0x00FF;
                }
                else {
                    b1 = fInputStream.read();
                    if (b1 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fOffset = 1;
                            return out - offset;
                        }
                        expectedByte(2, 2);
                    }
                    count++;
                }
                if ((b1 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fOffset = 2;
                        return out - offset;
                    }
                    invalidByte(2, 2, b1);
                }
                int c = ((b0 << 6) & 0x07C0) | (b1 & 0x003F);
                ch[out++] = (char)c;
                count -= 1;
                continue;
            }

            // UTF-8:   [1110 zzzz] [10yy yyyy] [10xx xxxx]
            // Unicode: [zzzz yyyy] [yyxx xxxx]
            if ((b0 & 0xF0) == 0xE0) {
                int b1 = -1;
                if (++in < total) {
                    b1 = fBuffer[in] & 0x00FF;
                }
                else {
                    b1 = fInputStream.read();
                    if (b1 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fOffset = 1;
                            return out - offset;
                        }
                        expectedByte(2, 3);
                    }
                    count++;
                }
                if ((b1 & 0xC0) != 0x80 
                    || (b0 == 0xED && b1 >= 0xA0)
                    || ((b0 & 0x0F) == 0 && (b1 & 0x20) == 0)) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fOffset = 2;
                        return out - offset;
                    }
                    invalidByte(2, 3, b1);
                }
                int b2 = -1;
                if (++in < total) {
                    b2 = fBuffer[in] & 0x00FF;
                }
                else {
                    b2 = fInputStream.read();
                    if (b2 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fOffset = 2;
                            return out - offset;
                        }
                        expectedByte(3, 3);
                    }
                    count++;
                }
                if ((b2 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fOffset = 3;
                        return out - offset;
                    }
                    invalidByte(3, 3, b2);
                }
                int c = ((b0 << 12) & 0xF000) | ((b1 << 6) & 0x0FC0) |
                        (b2 & 0x003F);
                ch[out++] = (char)c;
                count -= 2;
                continue;
            }

            // UTF-8:   [1111 0uuu] [10uu zzzz] [10yy yyyy] [10xx xxxx]*
            // Unicode: [1101 10ww] [wwzz zzyy] (high surrogate)
            //          [1101 11yy] [yyxx xxxx] (low surrogate)
            //          * uuuuu = wwww + 1
            if ((b0 & 0xF8) == 0xF0) {
                int b1 = -1;
                if (++in < total) {
                    b1 = fBuffer[in] & 0x00FF;
                }
                else {
                    b1 = fInputStream.read();
                    if (b1 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fOffset = 1;
                            return out - offset;
                        }
                        expectedByte(2, 4);
                    }
                    count++;
                }
                if ((b1 & 0xC0) != 0x80
                    || ((b1 & 0x30) == 0 && (b0 & 0x07) == 0)) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fOffset = 2;
                        return out - offset;
                    }
                    invalidByte(2, 4, b1);
                }
                int b2 = -1;
                if (++in < total) {
                    b2 = fBuffer[in] & 0x00FF;
                }
                else {
                    b2 = fInputStream.read();
                    if (b2 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fOffset = 2;
                            return out - offset;
                        }
                        expectedByte(3, 4);
                    }
                    count++;
                }
                if ((b2 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fOffset = 3;
                        return out - offset;
                    }
                    invalidByte(3, 4, b2);
                }
                int b3 = -1;
                if (++in < total) {
                    b3 = fBuffer[in] & 0x00FF;
                }
                else {
                    b3 = fInputStream.read();
                    if (b3 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fBuffer[2] = (byte)b2;
                            fOffset = 3;
                            return out - offset;
                        }
                        expectedByte(4, 4);
                    }
                    count++;
                }
                if ((b3 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fBuffer[3] = (byte)b3;
                        fOffset = 4;
                        return out - offset;
                    }
                    invalidByte(4, 4, b2);
                }

                // decode bytes into surrogate characters
                int uuuuu = ((b0 << 2) & 0x001C) | ((b1 >> 4) & 0x0003);
                if (uuuuu > 0x10) {
                    invalidSurrogate(uuuuu);
                }
                int wwww = uuuuu - 1;
                int zzzz = b1 & 0x000F;
                int yyyyyy = b2 & 0x003F;
                int xxxxxx = b3 & 0x003F;
                int hs = 0xD800 | ((wwww << 6) & 0x03C0) | (zzzz << 2) | (yyyyyy >> 4);
                int ls = 0xDC00 | ((yyyyyy << 6) & 0x03C0) | xxxxxx;

                // set characters
                ch[out++] = (char)hs;
                ch[out++] = (char)ls;
                count -= 2;
                continue;
            }

            // error
            if (out > offset) {
                fBuffer[0] = (byte)b0;
                fOffset = 1;
                return out - offset;
            }
            invalidByte(1, 1, b0);
        }

        // return number of characters converted
        if (DEBUG_READ) {
            System.out.println("read(char[],"+offset+',"+length+"): count="+count);
        }
        return count;

    
public booleanready()
Tell whether this stream is ready to be read.

return
True if the next read() is guaranteed not to block for input, false otherwise. Note that returning false does not guarantee that the next read will block.
exception
IOException If an I/O error occurs

        return false;
    
public voidreset()
Reset the stream. If the stream has been marked, then attempt to reposition it at the mark. If the stream has not been marked, then attempt to reset it in some way appropriate to the particular stream, for example by repositioning it to its starting point. Not all character-input streams support the reset() operation, and some support reset() without supporting mark().

exception
IOException If the stream has not been marked, or if the mark has been invalidated, or if the stream does not support reset(), or if some other I/O error occurs

        fOffset = 0;
        fSurrogate = -1;
    
public longskip(long n)
Skip characters. This method will block until some characters are available, an I/O error occurs, or the end of the stream is reached.

param
n The number of characters to skip
return
The number of characters actually skipped
exception
IOException If an I/O error occurs


        long remaining = n;
        final char[] ch = new char[fBuffer.length];
        do {
            int length = ch.length < remaining ? ch.length : (int)remaining;
            int count = read(ch, 0, length);
            if (count > 0) {
                remaining -= count;
            }
            else {
                break;
            }
        } while (remaining > 0);

        long skipped = n - remaining;
        return skipped;