如果给定无效的Base64编码字符串,如何使Android Base64.decode可靠抛出异常(或返回null)?

最初,我计划使用Apache isBase64 ,以在传入之前验证输入 Base64.decode .

https://github.com/apache/commons-codec/blob/master/src/main/java/org/apache/commons/codec/binary/Base64.java

后来,我注意到逻辑不够严格。他们不检查中提到的以下规则 https://stackoverflow.com/a/8571544/72437

• 检查集合A-Z、A-Z、0-9、+、/中的每个字符,除了结尾处的填充为0、1或2'='个字符

isBase64

/*
 * 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.nio.charset.Charset;

import static com.yocto.wenote.Constants.UTF_8;

/**
 * Provides Base64 encoding and decoding as defined by <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a>.
 *
 * <p>
 * This class implements section <cite>6.8. Base64 Content-Transfer-Encoding</cite> from RFC 2045 <cite>Multipurpose
 * Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</cite> by Freed and Borenstein.
 * </p>
 * <p>
 * The class can be parameterized in the following manner with various constructors:
 * </p>
 * <ul>
 * <li>URL-safe mode: Default off.</li>
 * <li>Line length: Default 76. Line length that aren't multiples of 4 will still essentially end up being multiples of
 * 4 in the encoded data.
 * <li>Line separator: Default is CRLF ("\r\n")</li>
 * </ul>
 * <p>
 * The URL-safe parameter is only applied to encode operations. Decoding seamlessly handles both modes.
 * </p>
 * <p>
 * Since this class operates directly on byte streams, and not character streams, it is hard-coded to only
 * encode/decode character encodings which are compatible with the lower 127 ASCII chart (ISO-8859-1, Windows-1252,
 * UTF-8, etc).
 * </p>
 * <p>
 * This class is thread-safe.
 * </p>
 *
 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a>
 * @since 1.0
 */
public class Base64 {
    /**
     * Byte used to pad output.
     */
    protected static final byte PAD_DEFAULT = '='; // Allow static access to default

    /**
     * This array is a lookup table that translates Unicode characters drawn from the "Base64 Alphabet" (as specified
     * in Table 1 of RFC 2045) into their 6-bit positive integer equivalents. Characters that are not in the Base64
     * alphabet but fall within the bounds of the array are translated to -1.
     *
     * Thanks to "commons" project in ws.apache.org for this code.
     * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/
     */
    private static final byte[] DECODE_TABLE = {
            //   0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, -1, -1, 63, // 20-2f + /
            52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
            -1,  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, // 40-4f A-O
            15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1, // 50-5f P-Z
            -1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, // 60-6f a-o
            41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51                      // 70-7a p-z
    };

    /**
     * Returns whether or not the <code>octet</code> is in the base 64 alphabet.
     *
     * @param octet
     *            The value to test
     * @return <code>true</code> if the value is defined in the the base 64 alphabet, <code>false</code> otherwise.
     * @since 1.4
     */
    static boolean isBase64(final byte octet) {
        return (octet >= 0 && octet < DECODE_TABLE.length && DECODE_TABLE[octet] != -1);
    }

    private static boolean isPadding(final byte octet) {
        return octet == PAD_DEFAULT;
    }

    /**
     * Tests a given String to see if it contains only valid characters within the Base64 alphabet. Currently the
     * method treats whitespace as valid.
     *
     * @param base64
     *            String to test
     * @return <code>true</code> if all characters in the String are valid characters in the Base64 alphabet or if
     *         the String is empty; <code>false</code>, otherwise
     *  @since 1.5
     */
    public static boolean isBase64(final String base64) {
        return isBase64(getBytesUtf8(base64));
    }

    /**
     * Tests a given byte array to see if it contains only valid characters within the Base64 alphabet. Currently the
     * method treats whitespace as valid.
     *
     * @param arrayOctet
     *            byte array to test
     * @return <code>true</code> if all bytes are valid characters in the Base64 alphabet or if the byte array is empty;
     *         <code>false</code>, otherwise
     * @since 1.5
     */
    private static boolean isBase64(final byte[] arrayOctet) {
        final int length = arrayOctet.length;

        // Check that the length is a multiple of 4 characters
        if (length%4 != 0) {
            return false;
        }

        // Check that every character is in the set A-Z, a-z, 0-9, +, / except for padding at the
        // end which is 0, 1 or 2 '=' characters.
        final int end = Math.max(0, length-2);

        for (int i = 0; i < end; i++) {
            if (!isBase64(arrayOctet[i])) {
                return false;
            }
        }

        boolean padding = false;

        for (int i = end; i < arrayOctet.length; i++) {
            byte octet = arrayOctet[i];
            if (padding) {
                if (!isPadding(octet)) {
                    return false;
                }
            } else {
                if (isPadding(octet)) {
                    padding = true;
                } else if (!isBase64(octet)) {
                    return false;
                }
            }
        }

        return true;
    }

    /**
     * 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</code>
     * @return encoded bytes, or <code>null</code> if the input string was <code>null</code>
     * @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/7/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
     * @see #getBytesUnchecked(String, String)
     */
    private static byte[] getBytesUtf8(final String string) {
        return getBytes(string, UTF_8);
    }

    /**
     * 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</code>
     * @return the encoded bytes
     */
    private static byte[] getBytes(final String string, final Charset charset) {
        if (string == null) {
            return null;
        }
        return string.getBytes(charset);
    }
}