hadoop Text 源码
haddop Text 代码
文件路径：/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/Text.java
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.hadoop.io;
import java.io.IOException;
import java.io.DataInput;
import java.io.DataOutput;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.MalformedInputException;
import java.nio.charset.StandardCharsets;
import java.text.CharacterIterator;
import java.text.StringCharacterIterator;
import java.util.Arrays;
import org.apache.avro.reflect.Stringable;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
/** This class stores text using standard UTF8 encoding. It provides methods
* to serialize, deserialize, and compare texts at byte level. The type of
* length is integer and is serialized using zero-compressed format. <p>In
* addition, it provides methods for string traversal without converting the
* byte array to a string. <p>Also includes utilities for
* serializing/deserialing a string, coding/decoding a string, checking if a
* byte array contains valid UTF8 code, calculating the length of an encoded
* string.
*/
@Stringable
@InterfaceAudience.Public
@InterfaceStability.Stable
public class Text extends BinaryComparable
implements WritableComparable<BinaryComparable> {
private static final ThreadLocal<CharsetEncoder> ENCODER_FACTORY =
new ThreadLocal<CharsetEncoder>() {
@Override
protected CharsetEncoder initialValue() {
return StandardCharsets.UTF_8.newEncoder().
onMalformedInput(CodingErrorAction.REPORT).
onUnmappableCharacter(CodingErrorAction.REPORT);
}
};
private static final ThreadLocal<CharsetDecoder> DECODER_FACTORY =
new ThreadLocal<CharsetDecoder>() {
@Override
protected CharsetDecoder initialValue() {
return StandardCharsets.UTF_8.newDecoder().
onMalformedInput(CodingErrorAction.REPORT).
onUnmappableCharacter(CodingErrorAction.REPORT);
}
};
// max size of the byte array, seems to be a safe choice for multiple JVMs
// (see ArrayList.MAX_ARRAY_SIZE)
private static final int ARRAY_MAX_SIZE = Integer.MAX_VALUE - 8;
private static final byte[] EMPTY_BYTES = new byte[0];
private byte[] bytes = EMPTY_BYTES;
private int length = 0;
private int textLength = -1;
/**
* Construct an empty text string.
*/
public Text() {
}
/**
* Construct from a string.
* @param string input string.
*/
public Text(String string) {
set(string);
}
/**
* Construct from another text.
* @param utf8 input utf8.
*/
public Text(Text utf8) {
set(utf8);
}
/**
* Construct from a byte array.
*
* @param utf8 input utf8.
*/
public Text(byte[] utf8) {
set(utf8);
}
/**
* @return Get a copy of the bytes that is exactly the length of the data.
* See {@link #getBytes()} for faster access to the underlying array.
*/
public byte[] copyBytes() {
return Arrays.copyOf(bytes, length);
}
/**
* Returns the raw bytes; however, only data up to {@link #getLength()} is
* valid. Please use {@link #copyBytes()} if you
* need the returned array to be precisely the length of the data.
*/
@Override
public byte[] getBytes() {
return bytes;
}
/**
* Returns the number of bytes in the byte array.
*/
@Override
public int getLength() {
return length;
}
/**
* @return Returns the length of this text. The length is equal to the number of
* Unicode code units in the text.
*/
public int getTextLength() {
if (textLength < 0) {
textLength = toString().length();
}
return textLength;
}
/**
* Returns the Unicode Scalar Value (32-bit integer value)
* for the character at <code>position</code>. Note that this
* method avoids using the converter or doing String instantiation.
*
* @param position input position.
* @return the Unicode scalar value at position or -1
* if the position is invalid or points to a
* trailing byte
*/
public int charAt(int position) {
if (position > this.length) return -1; // too long
if (position < 0) return -1; // duh.
ByteBuffer bb = (ByteBuffer)ByteBuffer.wrap(bytes).position(position);
return bytesToCodePoint(bb.slice());
}
public int find(String what) {
return find(what, 0);
}
/**
* Finds any occurrence of <code>what</code> in the backing
* buffer, starting as position <code>start</code>. The starting
* position is measured in bytes and the return value is in
* terms of byte position in the buffer. The backing buffer is
* not converted to a string for this operation.
*
* @param what input what.
* @param start input start.
* @return byte position of the first occurrence of the search
* string in the UTF-8 buffer or -1 if not found
*/
public int find(String what, int start) {
try {
ByteBuffer src = ByteBuffer.wrap(this.bytes, 0, this.length);
ByteBuffer tgt = encode(what);
byte b = tgt.get();
src.position(start);
while (src.hasRemaining()) {
if (b == src.get()) { // matching first byte
src.mark(); // save position in loop
tgt.mark(); // save position in target
boolean found = true;
int pos = src.position()-1;
while (tgt.hasRemaining()) {
if (!src.hasRemaining()) { // src expired first
tgt.reset();
src.reset();
found = false;
break;
}
if (!(tgt.get() == src.get())) {
tgt.reset();
src.reset();
found = false;
break; // no match
}
}
if (found) return pos;
}
}
return -1; // not found
} catch (CharacterCodingException e) {
throw new RuntimeException("Should not have happened", e);
}
}
/**
* Set to contain the contents of a string.
*
* @param string input string.
*/
public void set(String string) {
try {
ByteBuffer bb = encode(string, true);
bytes = bb.array();
length = bb.limit();
textLength = string.length();
} catch (CharacterCodingException e) {
throw new RuntimeException("Should not have happened", e);
}
}
/**
* Set to a utf8 byte array. If the length of <code>utf8</code> is
* <em>zero</em>, actually clear {@link #bytes} and any existing
* data is lost.
*
* @param utf8 input utf8.
*/
public void set(byte[] utf8) {
if (utf8.length == 0) {
bytes = EMPTY_BYTES;
length = 0;
textLength = -1;
} else {
set(utf8, 0, utf8.length);
}
}
/**
* Copy a text.
* @param other other.
*/
public void set(Text other) {
set(other.getBytes(), 0, other.getLength());
this.textLength = other.textLength;
}
/**
* Set the Text to range of bytes.
*
* @param utf8 the data to copy from
* @param start the first position of the new string
* @param len the number of bytes of the new string
*/
public void set(byte[] utf8, int start, int len) {
ensureCapacity(len);
System.arraycopy(utf8, start, bytes, 0, len);
this.length = len;
this.textLength = -1;
}
/**
* Append a range of bytes to the end of the given text.
*
* @param utf8 the data to copy from
* @param start the first position to append from utf8
* @param len the number of bytes to append
*/
public void append(byte[] utf8, int start, int len) {
byte[] original = bytes;
if (ensureCapacity(length + len)) {
System.arraycopy(original, 0, bytes, 0, length);
}
System.arraycopy(utf8, start, bytes, length, len);
length += len;
textLength = -1;
}
/**
* Clear the string to empty.
*
* <em>Note</em>: For performance reasons, this call does not clear the
* underlying byte array that is retrievable via {@link #getBytes()}.
* In order to free the byte-array memory, call {@link #set(byte[])}
* with an empty byte array (For example, <code>new byte[0]</code>).
*/
public void clear() {
length = 0;
textLength = -1;
}
/**
* Sets the capacity of this Text object to <em>at least</em>
* <code>capacity</code> bytes. If the current buffer is longer, then the
* capacity and existing content of the buffer are unchanged. If
* <code>capacity</code> is larger than the current capacity, the Text
* object's capacity is increased to match and any existing data is lost.
*
* @param capacity the number of bytes we need
* @return true if the internal array was resized or false otherwise
*/
private boolean ensureCapacity(final int capacity) {
if (bytes.length < capacity) {
// Try to expand the backing array by the factor of 1.5x
// (by taking the current size + diving it by half).
//
// If the calculated value is beyond the size
// limit, we cap it to ARRAY_MAX_SIZE
long targetSizeLong = bytes.length + (bytes.length >> 1);
int targetSize = (int)Math.min(targetSizeLong, ARRAY_MAX_SIZE);
targetSize = Math.max(capacity, targetSize);
bytes = new byte[targetSize];
return true;
}
return false;
}
@Override
public String toString() {
try {
return decode(bytes, 0, length);
} catch (CharacterCodingException e) {
throw new RuntimeException("Should not have happened", e);
}
}
@Override
public void readFields(DataInput in) throws IOException {
int newLength = WritableUtils.readVInt(in);
readWithKnownLength(in, newLength);
}
public void readFields(DataInput in, int maxLength) throws IOException {
int newLength = WritableUtils.readVInt(in);
if (newLength < 0) {
throw new IOException("tried to deserialize " + newLength +
" bytes of data! newLength must be non-negative.");
} else if (newLength >= maxLength) {
throw new IOException("tried to deserialize " + newLength +
" bytes of data, but maxLength = " + maxLength);
}
readWithKnownLength(in, newLength);
}
/**
* Skips over one Text in the input.
* @param in input in.
* @throws IOException raised on errors performing I/O.
*/
public static void skip(DataInput in) throws IOException {
int length = WritableUtils.readVInt(in);
WritableUtils.skipFully(in, length);
}
/**
* Read a Text object whose length is already known.
* This allows creating Text from a stream which uses a different serialization
* format.
*
* @param in input in.
* @param len input len.
* @throws IOException raised on errors performing I/O.
*/
public void readWithKnownLength(DataInput in, int len) throws IOException {
ensureCapacity(len);
in.readFully(bytes, 0, len);
length = len;
textLength = -1;
}
/**
* Serialize. Write this object to out length uses zero-compressed encoding.
*
* @see Writable#write(DataOutput)
*/
@Override
public void write(DataOutput out) throws IOException {
WritableUtils.writeVInt(out, length);
out.write(bytes, 0, length);
}
public void write(DataOutput out, int maxLength) throws IOException {
if (length > maxLength) {
throw new IOException("data was too long to write! Expected " +
"less than or equal to " + maxLength + " bytes, but got " +
length + " bytes.");
}
WritableUtils.writeVInt(out, length);
out.write(bytes, 0, length);
}
/**
* Returns true iff <code>o</code> is a Text with the same length and same
* contents.
*/
@Override
public boolean equals(Object o) {
if (o instanceof Text)
return super.equals(o);
return false;
}
@Override
public int hashCode() {
return super.hashCode();
}
/** A WritableComparator optimized for Text keys. */
public static class Comparator extends WritableComparator {
public Comparator() {
super(Text.class);
}
@Override
public int compare(byte[] b1, int s1, int l1,
byte[] b2, int s2, int l2) {
int n1 = WritableUtils.decodeVIntSize(b1[s1]);
int n2 = WritableUtils.decodeVIntSize(b2[s2]);
return compareBytes(b1, s1 + n1, l1 - n1, b2, s2 + n2, l2 - n2);
}
}
static {
// register this comparator
WritableComparator.define(Text.class, new Comparator());
}
/// STATIC UTILITIES FROM HERE DOWN
/**
* @return Converts the provided byte array to a String using the
* UTF-8 encoding. If the input is malformed,
* replace by a default value.
*
* @param utf8 input utf8.
* @throws CharacterCodingException when a character
* encoding or decoding error occurs.
*/
public static String decode(byte[] utf8) throws CharacterCodingException {
return decode(ByteBuffer.wrap(utf8), true);
}
public static String decode(byte[] utf8, int start, int length)
throws CharacterCodingException {
return decode(ByteBuffer.wrap(utf8, start, length), true);
}
/**
* @return Converts the provided byte array to a String using the
* UTF-8 encoding. If <code>replace</code> is true, then
* malformed input is replaced with the
* substitution character, which is U+FFFD. Otherwise the
* method throws a MalformedInputException.
*
* @param utf8 input utf8.
* @param start input start.
* @param length input length.
* @param replace input replace.
* @throws CharacterCodingException when a character
* encoding or decoding error occurs.
*/
public static String decode(byte[] utf8, int start, int length, boolean replace)
throws CharacterCodingException {
return decode(ByteBuffer.wrap(utf8, start, length), replace);
}
private static String decode(ByteBuffer utf8, boolean replace)
throws CharacterCodingException {
CharsetDecoder decoder = DECODER_FACTORY.get();
if (replace) {
decoder.onMalformedInput(
java.nio.charset.CodingErrorAction.REPLACE);
decoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
}
String str = decoder.decode(utf8).toString();
// set decoder back to its default value: REPORT
if (replace) {
decoder.onMalformedInput(CodingErrorAction.REPORT);
decoder.onUnmappableCharacter(CodingErrorAction.REPORT);
}
return str;
}
/**
* Converts the provided String to bytes using the
* UTF-8 encoding. If the input is malformed,
* invalid chars are replaced by a default value.
*
* @param string input string.
* @return ByteBuffer: bytes stores at ByteBuffer.array()
* and length is ByteBuffer.limit()
* @throws CharacterCodingException when a character
* encoding or decoding error occurs.
*/
public static ByteBuffer encode(String string)
throws CharacterCodingException {
return encode(string, true);
}
/**
* Converts the provided String to bytes using the
* UTF-8 encoding. If <code>replace</code> is true, then
* malformed input is replaced with the
* substitution character, which is U+FFFD. Otherwise the
* method throws a MalformedInputException.
*
* @param string input string.
* @param replace input replace.
* @return ByteBuffer: bytes stores at ByteBuffer.array()
* and length is ByteBuffer.limit()
* @throws CharacterCodingException when a character
* encoding or decoding error occurs.
*/
public static ByteBuffer encode(String string, boolean replace)
throws CharacterCodingException {
CharsetEncoder encoder = ENCODER_FACTORY.get();
if (replace) {
encoder.onMalformedInput(CodingErrorAction.REPLACE);
encoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
}
ByteBuffer bytes =
encoder.encode(CharBuffer.wrap(string.toCharArray()));
if (replace) {
encoder.onMalformedInput(CodingErrorAction.REPORT);
encoder.onUnmappableCharacter(CodingErrorAction.REPORT);
}
return bytes;
}
static final public int DEFAULT_MAX_LEN = 1024 * 1024;
/**
* @return Read a UTF8 encoded string from in.
* @param in input in.
* @throws IOException raised on errors performing I/O.
*/
public static String readString(DataInput in) throws IOException {
return readString(in, Integer.MAX_VALUE);
}
/**
* @return Read a UTF8 encoded string with a maximum size.
* @param in input datainput.
* @param maxLength input maxLength.
* @throws IOException raised on errors performing I/O.
*/
public static String readString(DataInput in, int maxLength)
throws IOException {
int length = WritableUtils.readVIntInRange(in, 0, maxLength);
byte [] bytes = new byte[length];
in.readFully(bytes, 0, length);
return decode(bytes);
}
/**
* Write a UTF8 encoded string to out.
*
* @param out input out.
* @param s input s.
* @throws IOException raised on errors performing I/O.
* @return a UTF8 encoded string to out.
*/
public static int writeString(DataOutput out, String s) throws IOException {
ByteBuffer bytes = encode(s);
int length = bytes.limit();
WritableUtils.writeVInt(out, length);
out.write(bytes.array(), 0, length);
return length;
}
/**
* @return Write a UTF8 encoded string with a maximum size to out.
*
* @param out input out.
* @param s input s.
* @param maxLength input maxLength.
* @throws IOException raised on errors performing I/O.
*/
public static int writeString(DataOutput out, String s, int maxLength)
throws IOException {
ByteBuffer bytes = encode(s);
int length = bytes.limit();
if (length > maxLength) {
throw new IOException("string was too long to write! Expected " +
"less than or equal to " + maxLength + " bytes, but got " +
length + " bytes.");
}
WritableUtils.writeVInt(out, length);
out.write(bytes.array(), 0, length);
return length;
}
////// states for validateUTF8
private static final int LEAD_BYTE = 0;
private static final int TRAIL_BYTE_1 = 1;
private static final int TRAIL_BYTE = 2;
/**
* Check if a byte array contains valid UTF-8.
*
* @param utf8 byte array
* @throws MalformedInputException if the byte array contains invalid UTF-8
*/
public static void validateUTF8(byte[] utf8) throws MalformedInputException {
validateUTF8(utf8, 0, utf8.length);
}
/**
* Check to see if a byte array is valid UTF-8.
*
* @param utf8 the array of bytes
* @param start the offset of the first byte in the array
* @param len the length of the byte sequence
* @throws MalformedInputException if the byte array contains invalid bytes
*/
public static void validateUTF8(byte[] utf8, int start, int len)
throws MalformedInputException {
int count = start;
int leadByte = 0;
int length = 0;
int state = LEAD_BYTE;
while (count < start+len) {
int aByte = utf8[count] & 0xFF;
switch (state) {
case LEAD_BYTE:
leadByte = aByte;
length = bytesFromUTF8[aByte];
switch (length) {
case 0: // check for ASCII
if (leadByte > 0x7F)
throw new MalformedInputException(count);
break;
case 1:
if (leadByte < 0xC2 || leadByte > 0xDF)
throw new MalformedInputException(count);
state = TRAIL_BYTE_1;
break;
case 2:
if (leadByte < 0xE0 || leadByte > 0xEF)
throw new MalformedInputException(count);
state = TRAIL_BYTE_1;
break;
case 3:
if (leadByte < 0xF0 || leadByte > 0xF4)
throw new MalformedInputException(count);
state = TRAIL_BYTE_1;
break;
default:
// too long! Longest valid UTF-8 is 4 bytes (lead + three)
// or if < 0 we got a trail byte in the lead byte position
throw new MalformedInputException(count);
} // switch (length)
break;
case TRAIL_BYTE_1:
if (leadByte == 0xF0 && aByte < 0x90)
throw new MalformedInputException(count);
if (leadByte == 0xF4 && aByte > 0x8F)
throw new MalformedInputException(count);
if (leadByte == 0xE0 && aByte < 0xA0)
throw new MalformedInputException(count);
if (leadByte == 0xED && aByte > 0x9F)
throw new MalformedInputException(count);
// falls through to regular trail-byte test!!
case TRAIL_BYTE:
if (aByte < 0x80 || aByte > 0xBF)
throw new MalformedInputException(count);
if (--length == 0) {
state = LEAD_BYTE;
} else {
state = TRAIL_BYTE;
}
break;
default:
break;
} // switch (state)
count++;
}
}
/**
* Magic numbers for UTF-8. These are the number of bytes
* that <em>follow</em> a given lead byte. Trailing bytes
* have the value -1. The values 4 and 5 are presented in
* this table, even though valid UTF-8 cannot include the
* five and six byte sequences.
*/
static final int[] bytesFromUTF8 =
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0,
// trail bytes
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3,
3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5 };
/**
* @return Returns the next code point at the current position in
* the buffer. The buffer's position will be incremented.
* Any mark set on this buffer will be changed by this method!
*
* @param bytes input bytes.
*/
public static int bytesToCodePoint(ByteBuffer bytes) {
bytes.mark();
byte b = bytes.get();
bytes.reset();
int extraBytesToRead = bytesFromUTF8[(b & 0xFF)];
if (extraBytesToRead < 0) return -1; // trailing byte!
int ch = 0;
switch (extraBytesToRead) {
case 5: ch += (bytes.get() & 0xFF); ch <<= 6; /* remember, illegal UTF-8 */
case 4: ch += (bytes.get() & 0xFF); ch <<= 6; /* remember, illegal UTF-8 */
case 3: ch += (bytes.get() & 0xFF); ch <<= 6;
case 2: ch += (bytes.get() & 0xFF); ch <<= 6;
case 1: ch += (bytes.get() & 0xFF); ch <<= 6;
case 0: ch += (bytes.get() & 0xFF);
}
ch -= offsetsFromUTF8[extraBytesToRead];
return ch;
}
static final int offsetsFromUTF8[] =
{ 0x00000000, 0x00003080,
0x000E2080, 0x03C82080, 0xFA082080, 0x82082080 };
/**
* For the given string, returns the number of UTF-8 bytes
* required to encode the string.
* @param string text to encode
* @return number of UTF-8 bytes required to encode
*/
public static int utf8Length(String string) {
CharacterIterator iter = new StringCharacterIterator(string);
char ch = iter.first();
int size = 0;
while (ch != CharacterIterator.DONE) {
if ((ch >= 0xD800) && (ch < 0xDC00)) {
// surrogate pair?
char trail = iter.next();
if ((trail > 0xDBFF) && (trail < 0xE000)) {
// valid pair
size += 4;
} else {
// invalid pair
size += 3;
iter.previous(); // rewind one
}
} else if (ch < 0x80) {
size++;
} else if (ch < 0x800) {
size += 2;
} else {
// ch < 0x10000, that is, the largest char value
size += 3;
}
ch = iter.next();
}
return size;
}
}
相关信息
相关文章
hadoop ArrayPrimitiveWritable 源码
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
8、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦