字符串编码工具类解析-CSDN博客

点击(此处)折叠或打开

/*
* 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.
*/
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
/**
* Converts String to and from bytes using the encodings required by the Java specification. These encodings are
* specified in <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">
* Standard charsets</a>.
*
*
This class is immutable and thread-safe.
*
* @see CharEncoding
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @version $Id: StringUtils.java 1378740 2012-08-29 21:18:47Z tn $
* @since 1.4
*/
public class StringUtils {
/**
* Calls {@link String#getBytes(Charset)}
*
* @param string
* The string to encode (if null, return null).
* @param charset
* The {@link Charset} to encode the {@code String}
* @return the encoded bytes
*/
private static byte[] getBytes(String string, Charset charset) {
if (string == null) {
return null;
}
return string.getBytes(charset);
}
/**
* Encodes the given string into a sequence of bytes using the ISO-8859-1 charset, storing the result into a new
* byte array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#ISO_8859_1} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesIso8859_1(String string) {
return getBytes(string, Charsets.ISO_8859_1);
}
/**
* Encodes the given string into a sequence of bytes using the named charset, storing the result into a new byte
* array.
*
* This method catches {@link UnsupportedEncodingException} and rethrows it as {@link IllegalStateException}, which
* should never happen for a required charset name. Use this method when the encoding is required to be in the JRE.
*
*
* @param string
* the String to encode, may be {@code null}
* @param charsetName
* The name of a required {@link java.nio.charset.Charset}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws IllegalStateException
* Thrown when a {@link UnsupportedEncodingException} is caught, which should never happen for a
* required charset name.
* @see CharEncoding
* @see String#getBytes(String)
*/
public static byte[] getBytesUnchecked(String string, String charsetName) {
if (string == null) {
return null;
}
try {
return string.getBytes(charsetName);
} catch (UnsupportedEncodingException e) {
throw StringUtils.newIllegalStateException(charsetName, e);
}
}
/**
* Encodes the given string into a sequence of bytes using the US-ASCII charset, storing the result into a new byte
* array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#US_ASCII} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUsAscii(String string) {
return getBytes(string, Charsets.US_ASCII);
}
/**
* Encodes the given string into a sequence of bytes using the UTF-16 charset, storing the result into a new byte
* array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16(String string) {
return getBytes(string, Charsets.UTF_16);
}
/**
* Encodes the given string into a sequence of bytes using the UTF-16BE charset, storing the result into a new byte
* array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16BE} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16Be(String string) {
return getBytes(string, Charsets.UTF_16BE);
}
/**
* Encodes the given string into a sequence of bytes using the UTF-16LE charset, storing the result into a new byte
* array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16LE} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16Le(String string) {
return getBytes(string, Charsets.UTF_16LE);
}
/**
* Encodes the given string into a sequence of bytes using the UTF-8 charset, storing the result into a new byte
* array.
*
* @param string
* the String to encode, may be {@code null}
* @return encoded bytes, or {@code null} if the input string was {@code null}
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
* @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf8(String string) {
return getBytes(string, Charsets.UTF_8);
}
private static IllegalStateException newIllegalStateException(String charsetName, UnsupportedEncodingException e) {
return new IllegalStateException(charsetName + ": " + e);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the given charset.
*
* @param bytes
* The bytes to be decoded into characters
* @param charset
* The {@link Charset} to encode the {@code String}
* @return A new <code>String</code> decoded from the specified array of bytes using the given charset,
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is
* required by the Java platform specification.
*/
private static String newString(byte[] bytes, Charset charset) {
return bytes == null ? null : new String(bytes, charset);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the given charset.
*
* This method catches {@link UnsupportedEncodingException} and re-throws it as {@link IllegalStateException}, which
* should never happen for a required charset name. Use this method when the encoding is required to be in the JRE.
*
*
* @param bytes
* The bytes to be decoded into characters, may be {@code null}
* @param charsetName
* The name of a required {@link java.nio.charset.Charset}
* @return A new <code>String</code> decoded from the specified array of bytes using the given charset,
* or {@code null} if the input byte array was {@code null}.
* @throws IllegalStateException
* Thrown when a {@link UnsupportedEncodingException} is caught, which should never happen for a
* required charset name.
* @see CharEncoding
* @see String#String(byte[], String)
*/
public static String newString(byte[] bytes, String charsetName) {
if (bytes == null) {
return null;
}
try {
return new String(bytes, charsetName);
} catch (UnsupportedEncodingException e) {
throw StringUtils.newIllegalStateException(charsetName, e);
}
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the ISO-8859-1 charset.
*
* @param bytes
* The bytes to be decoded into characters, may be {@code null}
* @return A new <code>String</code> decoded from the specified array of bytes using the ISO-8859-1 charset, or
* {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#ISO_8859_1} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringIso8859_1(byte[] bytes) {
return new String(bytes, Charsets.ISO_8859_1);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the US-ASCII charset.
*
* @param bytes
* The bytes to be decoded into characters
* @return A new <code>String</code> decoded from the specified array of bytes using the US-ASCII charset,
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#US_ASCII} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringUsAscii(byte[] bytes) {
return new String(bytes, Charsets.US_ASCII);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16 charset.
*
* @param bytes
* The bytes to be decoded into characters
* @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16 charset
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringUtf16(byte[] bytes) {
return new String(bytes, Charsets.UTF_16);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16BE charset.
*
* @param bytes
* The bytes to be decoded into characters
* @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16BE charset,
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16BE} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringUtf16Be(byte[] bytes) {
return new String(bytes, Charsets.UTF_16BE);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16LE charset.
*
* @param bytes
* The bytes to be decoded into characters
* @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16LE charset,
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_16LE} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringUtf16Le(byte[] bytes) {
return new String(bytes, Charsets.UTF_16LE);
}
/**
* Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-8 charset.
*
* @param bytes
* The bytes to be decoded into characters
* @return A new <code>String</code> decoded from the specified array of bytes using the UTF-8 charset,
* or {@code null} if the input byte array was {@code null}.
* @throws NullPointerException
* Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException
*/
public static String newStringUtf8(byte[] bytes) {
return newString(bytes, Charsets.UTF_8);
}
}
class CharEncoding {
public static final String ISO_8859_1 = "ISO-8859-1";
public static final String US_ASCII = "US-ASCII";
public static final String UTF_16 = "UTF-16";
public static final String UTF_16BE = "UTF-16BE";
public static final String UTF_16LE = "UTF-16LE";
public static final String UTF_8 = "UTF-8";
}
class Charsets {
public static Charset toCharset(Charset charset) {
return charset == null ? Charset.defaultCharset() : charset;
}
public static Charset toCharset(String charset) {
return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
}
public static final Charset ISO_8859_1 = Charset.forName(CharEncoding.ISO_8859_1);
public static final Charset US_ASCII = Charset.forName(CharEncoding.US_ASCII);
public static final Charset UTF_16 = Charset.forName(CharEncoding.UTF_16);
public static final Charset UTF_16BE = Charset.forName(CharEncoding.UTF_16BE);
public static final Charset UTF_16LE = Charset.forName(CharEncoding.UTF_16LE);
public static final Charset UTF_8 = Charset.forName(CharEncoding.UTF_8);
}