java对html转移的语言反编译-org.apache.commons.lang3包有个StringEscapeUtils

StringEscapeUtils

用escapeJava方法转义

用unescapeJava方法反转义

用escapeHtml方法转义

用unescapeHtml方法反转义

用escapeXml方法转义

用unescapeXml方法反转义

用escapeJavaScript方法转义

用unescapeJavaScript方法反转义

源码内容方法

/*
 * 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.lang3;

import java.io.IOException;
import java.io.Writer;

import org.apache.commons.lang3.text.translate.AggregateTranslator;
import org.apache.commons.lang3.text.translate.CharSequenceTranslator;
import org.apache.commons.lang3.text.translate.EntityArrays;
import org.apache.commons.lang3.text.translate.LookupTranslator;
import org.apache.commons.lang3.text.translate.NumericEntityUnescaper;
import org.apache.commons.lang3.text.translate.OctalUnescaper;
import org.apache.commons.lang3.text.translate.UnicodeEscaper;
import org.apache.commons.lang3.text.translate.UnicodeUnescaper;

/**
 * <p>Escapes and unescapes {@code String}s for
 * Java, Java Script, HTML and XML.</p>
 *
 * <p>#ThreadSafe#</p>
 * @since 2.0
 * @version $Id: StringEscapeUtils.java 1148520 2011-07-19 20:53:23Z ggregory $
 */
public class StringEscapeUtils {

    /* ESCAPE TRANSLATORS */


    public static final CharSequenceTranslator ESCAPE_JAVA = 
          new LookupTranslator(
            new String[][] { 
              {"\"", "\\\""},
              {"\\", "\\\\"},
          }).with(
            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE())
          ).with(
            UnicodeEscaper.outsideOf(32, 0x7f) 
        );


    public static final CharSequenceTranslator ESCAPE_ECMASCRIPT = 
        new AggregateTranslator(
            new LookupTranslator(
                      new String[][] { 
                            {"'", "\\'"},
                            {"\"", "\\\""},
                            {"\\", "\\\\"},
                            {"/", "\\/"}
                      }),
            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
            UnicodeEscaper.outsideOf(32, 0x7f) 
        );
            

    public static final CharSequenceTranslator ESCAPE_XML = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
            new LookupTranslator(EntityArrays.APOS_ESCAPE())
        );


    public static final CharSequenceTranslator ESCAPE_HTML3 = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
            new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE())
        );


    public static final CharSequenceTranslator ESCAPE_HTML4 = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
            new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE()),
            new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE())
        );


    public static final CharSequenceTranslator ESCAPE_CSV = new CsvEscaper();

    // TODO: Create a parent class - 'SinglePassTranslator' ?
    //       It would handle the index checking + length returning, 
    //       and could also have an optimization check method.
    static class CsvEscaper extends CharSequenceTranslator {

        private static final char CSV_DELIMITER = ',';
        private static final char CSV_QUOTE = '"';
        private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
        private static final char[] CSV_SEARCH_CHARS = 
            new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};

        @Override
        public int translate(CharSequence input, int index, Writer out) throws IOException {

            if(index != 0) {
                throw new IllegalStateException("CsvEscaper should never reach the [1] index");
            }

            if (StringUtils.containsNone(input.toString(), CSV_SEARCH_CHARS)) {
                out.write(input.toString());
            } else {
                out.write(CSV_QUOTE);
                out.write(StringUtils.replace(input.toString(), CSV_QUOTE_STR, CSV_QUOTE_STR + CSV_QUOTE_STR));
                out.write(CSV_QUOTE);
            }
            return input.length();
        }
    }

    /* UNESCAPE TRANSLATORS */

    // TODO: throw "illegal character: \92" as an Exception if a \ on the end of the Java (as per the compiler)?
    public static final CharSequenceTranslator UNESCAPE_JAVA = 
        new AggregateTranslator(
            new OctalUnescaper(),     // .between('\1', '\377'),
            new UnicodeUnescaper(),
            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE()),
            new LookupTranslator(
                      new String[][] { 
                            {"\\\\", "\\"},
                            {"\\\"", "\""},
                            {"\\'", "'"},
                            {"\\", ""}
                      })
        );


    public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA;


    public static final CharSequenceTranslator UNESCAPE_HTML3 = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
            new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
            new NumericEntityUnescaper()
        );


    public static final CharSequenceTranslator UNESCAPE_HTML4 = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
            new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
            new LookupTranslator(EntityArrays.HTML40_EXTENDED_UNESCAPE()),
            new NumericEntityUnescaper()
        );


    public static final CharSequenceTranslator UNESCAPE_XML = 
        new AggregateTranslator(
            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
            new LookupTranslator(EntityArrays.APOS_UNESCAPE()),
            new NumericEntityUnescaper()
        );


    public static final CharSequenceTranslator UNESCAPE_CSV = new CsvUnescaper();

    static class CsvUnescaper extends CharSequenceTranslator {

        private static final char CSV_DELIMITER = ',';
        private static final char CSV_QUOTE = '"';
        private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
        private static final char[] CSV_SEARCH_CHARS = 
            new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};

        @Override
        public int translate(CharSequence input, int index, Writer out) throws IOException {

            if(index != 0) {
                throw new IllegalStateException("CsvUnescaper should never reach the [1] index");
            }

            if ( input.charAt(0) != CSV_QUOTE || input.charAt(input.length() - 1) != CSV_QUOTE ) {
                out.write(input.toString());
                return input.length();
            }

            // strip quotes
            String quoteless = input.subSequence(1, input.length() - 1).toString();

            if ( StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS) ) {
                // deal with escaped quotes; ie) ""
                out.write(StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR, CSV_QUOTE_STR));
            } else {
                out.write(input.toString());
            }
            return input.length();
        }
    }


    public StringEscapeUtils() {
      super();
    }


    public static final String escapeJava(String input) {
        return ESCAPE_JAVA.translate(input);
    }


    public static final String escapeEcmaScript(String input) {
        return ESCAPE_ECMASCRIPT.translate(input);
    }


    public static final String unescapeJava(String input) {
        return UNESCAPE_JAVA.translate(input);
    }


    public static final String unescapeEcmaScript(String input) {
        return UNESCAPE_ECMASCRIPT.translate(input);
    }


    public static final String escapeHtml4(String input) {
        return ESCAPE_HTML4.translate(input);
    }


    public static final String escapeHtml3(String input) {
        return ESCAPE_HTML3.translate(input);
    }
                

    public static final String unescapeHtml4(String input) {
        return UNESCAPE_HTML4.translate(input);
    }

 
    public static final String unescapeHtml3(String input) {
        return UNESCAPE_HTML3.translate(input);
    }

  
    public static final String escapeXml(String input) {
        return ESCAPE_XML.translate(input);
    }
                

 
    public static final String unescapeXml(String input) {
        return UNESCAPE_XML.translate(input);
    }
                

    //-----------------------------------------------------------------------


    public static final String escapeCsv(String input) {
        return ESCAPE_CSV.translate(input);
    }

    public static final String unescapeCsv(String input) {
        return UNESCAPE_CSV.translate(input);
    }

}

针对转译，尽量不要进行转译后入库，只做查询出特殊字符的转译，或者自己写具体字符的转译，防止转译编码等导致字符混乱