org.apache.commons.codec.binary.StringUtils Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of gwt-commons-codec Show documentation
Show all versions of gwt-commons-codec Show documentation
The Apache Commons Codec component contains encoders and decoders for
various formats such as Base16, Base32, Base64, digest, and Hexadecimal. In addition to these
widely used encoders and decoders, the codec package also maintains a
collection of phonetic encoding utilities.
This is a port for GWT, which enables program, to use Apache Commons Codec
also in the frontend compiled by the gwt compiler to java-script.
/*
* 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.commons.codec.binary;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import org.apache.commons.codec.CharEncoding;
import com.google.gwt.core.shared.GwtIncompatible;
/**
* Converts String to and from bytes using the encodings required by the Java specification. These encodings are
* specified in
* Standard charsets.
*
* This class is immutable and thread-safe.
*
* @see CharEncoding
* @see Standard charsets
* @since 1.4
*/
public class StringUtils {
/**
*
* Compares two CharSequences, returning {@code true} if they represent equal sequences of characters.
*
*
*
* {@code null}s are handled without exceptions. Two {@code null} references are considered to be equal.
* The comparison is case sensitive.
*
*
*
* StringUtils.equals(null, null) = true
* StringUtils.equals(null, "abc") = false
* StringUtils.equals("abc", null) = false
* StringUtils.equals("abc", "abc") = true
* StringUtils.equals("abc", "ABC") = false
*
*
*
* Copied from Apache Commons Lang r1583482 on April 10, 2014 (day of 3.3.2 release).
*
*
* @see Object#equals(Object)
* @param cs1
* the first CharSequence, may be {@code null}
* @param cs2
* the second CharSequence, may be {@code null}
* @return {@code true} if the CharSequences are equal (case-sensitive), or both {@code null}
* @since 1.10
*/
public static boolean equals(final CharSequence cs1, final CharSequence cs2) {
if (cs1 == cs2) {
return true;
}
if (cs1 == null || cs2 == null) {
return false;
}
if (cs1 instanceof String && cs2 instanceof String) {
return cs1.equals(cs2);
}
return cs1.length() == cs2.length() && CharSequenceUtils.regionMatches(cs1, false, 0, cs2, 0, cs1.length());
}
/**
* 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
*/
@GwtIncompatible("incompatible method")
private static byte[] getBytes(final String string, final Charset charset) {
if (string == null) {
return null;
}
return string.getBytes(charset);
}
/**
* 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
*/
@GwtIncompatible("incompatible method")
private static ByteBuffer getByteBuffer(final String string, final Charset charset) {
if (string == null) {
return null;
}
return ByteBuffer.wrap(string.getBytes(charset));
}
/**
* Encodes the given string into a byte buffer 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 StandardCharsets#UTF_8} is not initialized, which should never happen since it is
* required by the Java platform specification.
* @see Standard charsets
* @see #getBytesUnchecked(String, String)
* @since 1.11
*/
@GwtIncompatible("incompatible method")
public static ByteBuffer getByteBufferUtf8(final String string) {
return getByteBuffer(string, StandardCharsets.UTF_8);
}
/**
* 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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesIso8859_1(final String string) {
return getBytesUnchecked(string, "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(final String string, final String charsetName) {
if (string == null) {
return null;
}
try {
return string.getBytes(charsetName);
} catch (final 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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUsAscii(final String string) {
return getBytesUnchecked(string, "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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16(final String string) {
return getBytesUnchecked(string, "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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16Be(final String string) {
return getBytesUnchecked(string, "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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf16Le(final String string) {
return getBytesUnchecked(string, "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 StandardCharsets#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 Standard charsets
* @see #getBytesUnchecked(String, String)
*/
public static byte[] getBytesUtf8(final String string) {
return getBytesUnchecked(string, "UTF-8");
}
private static IllegalStateException newIllegalStateException(final String charsetName,
final UnsupportedEncodingException e) {
return new IllegalStateException(charsetName + ": " + e);
}
/**
* Constructs a new {@code String} 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}; not {@code null}
* @return A new {@code String} 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 charset is {@code null}
*/
private static String newString(final byte[] bytes, final Charset charset) {
return bytes == null ? null : new String(bytes, charset);
}
/**
* Constructs a new {@code String} 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} 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(final byte[] bytes, final String charsetName) {
if (bytes == null) {
return null;
}
try {
return new String(bytes, charsetName);
} catch (final UnsupportedEncodingException e) {
throw StringUtils.newIllegalStateException(charsetName, e);
}
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "ISO-8859-1");
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "US-ASCII");
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "UTF-16");
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "UTF-16BE");
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "UTF-16LE");
}
/**
* Constructs a new {@code String} 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} 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 StandardCharsets#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(final byte[] bytes) {
return newString(bytes, "UTF-8");
}
}