001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3;
018
019import java.io.IOException;
020import java.io.Writer;
021
022import org.apache.commons.lang3.text.translate.AggregateTranslator;
023import org.apache.commons.lang3.text.translate.CharSequenceTranslator;
024import org.apache.commons.lang3.text.translate.EntityArrays;
025import org.apache.commons.lang3.text.translate.JavaUnicodeEscaper;
026import org.apache.commons.lang3.text.translate.LookupTranslator;
027import org.apache.commons.lang3.text.translate.NumericEntityEscaper;
028import org.apache.commons.lang3.text.translate.NumericEntityUnescaper;
029import org.apache.commons.lang3.text.translate.OctalUnescaper;
030import org.apache.commons.lang3.text.translate.UnicodeUnescaper;
031import org.apache.commons.lang3.text.translate.UnicodeUnpairedSurrogateRemover;
032
033/**
034 * <p>Escapes and unescapes {@code String}s for
035 * Java, Java Script, HTML and XML.</p>
036 *
037 * <p>#ThreadSafe#</p>
038 * @since 2.0
039 * @deprecated as of 3.6, use commons-text
040 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/StringEscapeUtils.html">
041 * StringEscapeUtils</a> instead
042 */
043@Deprecated
044public class StringEscapeUtils {
045
046    /* ESCAPE TRANSLATORS */
047
048    /**
049     * Translator object for escaping Java.
050     *
051     * While {@link #escapeJava(String)} is the expected method of use, this
052     * object allows the Java escaping functionality to be used
053     * as the foundation for a custom translator.
054     *
055     * @since 3.0
056     */
057    public static final CharSequenceTranslator ESCAPE_JAVA =
058          new LookupTranslator(
059            new String[][] {
060              {"\"", "\\\""},
061              {"\\", "\\\\"},
062          }).with(
063            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE())
064          ).with(
065            JavaUnicodeEscaper.outsideOf(32, 0x7f)
066        );
067
068    /**
069     * Translator object for escaping EcmaScript/JavaScript.
070     *
071     * While {@link #escapeEcmaScript(String)} is the expected method of use, this
072     * object allows the EcmaScript escaping functionality to be used
073     * as the foundation for a custom translator.
074     *
075     * @since 3.0
076     */
077    public static final CharSequenceTranslator ESCAPE_ECMASCRIPT =
078        new AggregateTranslator(
079            new LookupTranslator(
080                      new String[][] {
081                            {"'", "\\'"},
082                            {"\"", "\\\""},
083                            {"\\", "\\\\"},
084                            {"/", "\\/"}
085                      }),
086            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
087            JavaUnicodeEscaper.outsideOf(32, 0x7f)
088        );
089
090    /**
091     * Translator object for escaping Json.
092     *
093     * While {@link #escapeJson(String)} is the expected method of use, this
094     * object allows the Json escaping functionality to be used
095     * as the foundation for a custom translator.
096     *
097     * @since 3.2
098     */
099    public static final CharSequenceTranslator ESCAPE_JSON =
100        new AggregateTranslator(
101            new LookupTranslator(
102                      new String[][] {
103                            {"\"", "\\\""},
104                            {"\\", "\\\\"},
105                            {"/", "\\/"}
106                      }),
107            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
108            JavaUnicodeEscaper.outsideOf(32, 0x7f)
109        );
110
111    /**
112     * Translator object for escaping XML.
113     *
114     * While {@link #escapeXml(String)} is the expected method of use, this
115     * object allows the XML escaping functionality to be used
116     * as the foundation for a custom translator.
117     *
118     * @since 3.0
119     * @deprecated use {@link #ESCAPE_XML10} or {@link #ESCAPE_XML11} instead.
120     */
121    @Deprecated
122    public static final CharSequenceTranslator ESCAPE_XML =
123        new AggregateTranslator(
124            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
125            new LookupTranslator(EntityArrays.APOS_ESCAPE())
126        );
127
128    /**
129     * Translator object for escaping XML 1.0.
130     *
131     * While {@link #escapeXml10(String)} is the expected method of use, this
132     * object allows the XML escaping functionality to be used
133     * as the foundation for a custom translator.
134     *
135     * @since 3.3
136     */
137    public static final CharSequenceTranslator ESCAPE_XML10 =
138        new AggregateTranslator(
139            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
140            new LookupTranslator(EntityArrays.APOS_ESCAPE()),
141            new LookupTranslator(
142                    new String[][] {
143                            { "\u0000", StringUtils.EMPTY },
144                            { "\u0001", StringUtils.EMPTY },
145                            { "\u0002", StringUtils.EMPTY },
146                            { "\u0003", StringUtils.EMPTY },
147                            { "\u0004", StringUtils.EMPTY },
148                            { "\u0005", StringUtils.EMPTY },
149                            { "\u0006", StringUtils.EMPTY },
150                            { "\u0007", StringUtils.EMPTY },
151                            { "\u0008", StringUtils.EMPTY },
152                            { "\u000b", StringUtils.EMPTY },
153                            { "\u000c", StringUtils.EMPTY },
154                            { "\u000e", StringUtils.EMPTY },
155                            { "\u000f", StringUtils.EMPTY },
156                            { "\u0010", StringUtils.EMPTY },
157                            { "\u0011", StringUtils.EMPTY },
158                            { "\u0012", StringUtils.EMPTY },
159                            { "\u0013", StringUtils.EMPTY },
160                            { "\u0014", StringUtils.EMPTY },
161                            { "\u0015", StringUtils.EMPTY },
162                            { "\u0016", StringUtils.EMPTY },
163                            { "\u0017", StringUtils.EMPTY },
164                            { "\u0018", StringUtils.EMPTY },
165                            { "\u0019", StringUtils.EMPTY },
166                            { "\u001a", StringUtils.EMPTY },
167                            { "\u001b", StringUtils.EMPTY },
168                            { "\u001c", StringUtils.EMPTY },
169                            { "\u001d", StringUtils.EMPTY },
170                            { "\u001e", StringUtils.EMPTY },
171                            { "\u001f", StringUtils.EMPTY },
172                            { "\ufffe", StringUtils.EMPTY },
173                            { "\uffff", StringUtils.EMPTY }
174                    }),
175            NumericEntityEscaper.between(0x7f, 0x84),
176            NumericEntityEscaper.between(0x86, 0x9f),
177            new UnicodeUnpairedSurrogateRemover()
178        );
179
180    /**
181     * Translator object for escaping XML 1.1.
182     *
183     * While {@link #escapeXml11(String)} is the expected method of use, this
184     * object allows the XML escaping functionality to be used
185     * as the foundation for a custom translator.
186     *
187     * @since 3.3
188     */
189    public static final CharSequenceTranslator ESCAPE_XML11 =
190        new AggregateTranslator(
191            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
192            new LookupTranslator(EntityArrays.APOS_ESCAPE()),
193            new LookupTranslator(
194                    new String[][] {
195                            { "\u0000", StringUtils.EMPTY },
196                            { "\u000b", "&#11;" },
197                            { "\u000c", "&#12;" },
198                            { "\ufffe", StringUtils.EMPTY },
199                            { "\uffff", StringUtils.EMPTY }
200                    }),
201            NumericEntityEscaper.between(0x1, 0x8),
202            NumericEntityEscaper.between(0xe, 0x1f),
203            NumericEntityEscaper.between(0x7f, 0x84),
204            NumericEntityEscaper.between(0x86, 0x9f),
205            new UnicodeUnpairedSurrogateRemover()
206        );
207
208    /**
209     * Translator object for escaping HTML version 3.0.
210     *
211     * While {@link #escapeHtml3(String)} is the expected method of use, this
212     * object allows the HTML escaping functionality to be used
213     * as the foundation for a custom translator.
214     *
215     * @since 3.0
216     */
217    public static final CharSequenceTranslator ESCAPE_HTML3 =
218        new AggregateTranslator(
219            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
220            new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE())
221        );
222
223    /**
224     * Translator object for escaping HTML version 4.0.
225     *
226     * While {@link #escapeHtml4(String)} is the expected method of use, this
227     * object allows the HTML escaping functionality to be used
228     * as the foundation for a custom translator.
229     *
230     * @since 3.0
231     */
232    public static final CharSequenceTranslator ESCAPE_HTML4 =
233        new AggregateTranslator(
234            new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
235            new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE()),
236            new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE())
237        );
238
239    /**
240     * Translator object for escaping individual Comma Separated Values.
241     *
242     * While {@link #escapeCsv(String)} is the expected method of use, this
243     * object allows the CSV escaping functionality to be used
244     * as the foundation for a custom translator.
245     *
246     * @since 3.0
247     */
248    public static final CharSequenceTranslator ESCAPE_CSV = new CsvEscaper();
249
250    // TODO: Create a parent class - 'SinglePassTranslator' ?
251    //       It would handle the index checking + length returning,
252    //       and could also have an optimization check method.
253    static class CsvEscaper extends CharSequenceTranslator {
254
255        private static final char CSV_DELIMITER = ',';
256        private static final char CSV_QUOTE = '"';
257        private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
258        private static final char[] CSV_SEARCH_CHARS = { CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF };
259
260        @Override
261        public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
262
263            if(index != 0) {
264                throw new IllegalStateException("CsvEscaper should never reach the [1] index");
265            }
266
267            if (StringUtils.containsNone(input.toString(), CSV_SEARCH_CHARS)) {
268                out.write(input.toString());
269            } else {
270                out.write(CSV_QUOTE);
271                out.write(StringUtils.replace(input.toString(), CSV_QUOTE_STR, CSV_QUOTE_STR + CSV_QUOTE_STR));
272                out.write(CSV_QUOTE);
273            }
274            return Character.codePointCount(input, 0, input.length());
275        }
276    }
277
278    /* UNESCAPE TRANSLATORS */
279
280    /**
281     * Translator object for unescaping escaped Java.
282     *
283     * While {@link #unescapeJava(String)} is the expected method of use, this
284     * object allows the Java unescaping functionality to be used
285     * as the foundation for a custom translator.
286     *
287     * @since 3.0
288     */
289    // TODO: throw "illegal character: \92" as an Exception if a \ on the end of the Java (as per the compiler)?
290    public static final CharSequenceTranslator UNESCAPE_JAVA =
291        new AggregateTranslator(
292            new OctalUnescaper(),     // .between('\1', '\377'),
293            new UnicodeUnescaper(),
294            new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE()),
295            new LookupTranslator(
296                      new String[][] {
297                            {"\\\\", "\\"},
298                            {"\\\"", "\""},
299                            {"\\'", "'"},
300                            {"\\", ""}
301                      })
302        );
303
304    /**
305     * Translator object for unescaping escaped EcmaScript.
306     *
307     * While {@link #unescapeEcmaScript(String)} is the expected method of use, this
308     * object allows the EcmaScript unescaping functionality to be used
309     * as the foundation for a custom translator.
310     *
311     * @since 3.0
312     */
313    public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA;
314
315    /**
316     * Translator object for unescaping escaped Json.
317     *
318     * While {@link #unescapeJson(String)} is the expected method of use, this
319     * object allows the Json unescaping functionality to be used
320     * as the foundation for a custom translator.
321     *
322     * @since 3.2
323     */
324    public static final CharSequenceTranslator UNESCAPE_JSON = UNESCAPE_JAVA;
325
326    /**
327     * Translator object for unescaping escaped HTML 3.0.
328     *
329     * While {@link #unescapeHtml3(String)} is the expected method of use, this
330     * object allows the HTML unescaping functionality to be used
331     * as the foundation for a custom translator.
332     *
333     * @since 3.0
334     */
335    public static final CharSequenceTranslator UNESCAPE_HTML3 =
336        new AggregateTranslator(
337            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
338            new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
339            new NumericEntityUnescaper()
340        );
341
342    /**
343     * Translator object for unescaping escaped HTML 4.0.
344     *
345     * While {@link #unescapeHtml4(String)} is the expected method of use, this
346     * object allows the HTML unescaping functionality to be used
347     * as the foundation for a custom translator.
348     *
349     * @since 3.0
350     */
351    public static final CharSequenceTranslator UNESCAPE_HTML4 =
352        new AggregateTranslator(
353            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
354            new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
355            new LookupTranslator(EntityArrays.HTML40_EXTENDED_UNESCAPE()),
356            new NumericEntityUnescaper()
357        );
358
359    /**
360     * Translator object for unescaping escaped XML.
361     *
362     * While {@link #unescapeXml(String)} is the expected method of use, this
363     * object allows the XML unescaping functionality to be used
364     * as the foundation for a custom translator.
365     *
366     * @since 3.0
367     */
368    public static final CharSequenceTranslator UNESCAPE_XML =
369        new AggregateTranslator(
370            new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
371            new LookupTranslator(EntityArrays.APOS_UNESCAPE()),
372            new NumericEntityUnescaper()
373        );
374
375    /**
376     * Translator object for unescaping escaped Comma Separated Value entries.
377     *
378     * While {@link #unescapeCsv(String)} is the expected method of use, this
379     * object allows the CSV unescaping functionality to be used
380     * as the foundation for a custom translator.
381     *
382     * @since 3.0
383     */
384    public static final CharSequenceTranslator UNESCAPE_CSV = new CsvUnescaper();
385
386    static class CsvUnescaper extends CharSequenceTranslator {
387
388        private static final char CSV_DELIMITER = ',';
389        private static final char CSV_QUOTE = '"';
390        private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
391        private static final char[] CSV_SEARCH_CHARS = {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};
392
393        @Override
394        public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
395
396            if(index != 0) {
397                throw new IllegalStateException("CsvUnescaper should never reach the [1] index");
398            }
399
400            if ( input.charAt(0) != CSV_QUOTE || input.charAt(input.length() - 1) != CSV_QUOTE ) {
401                out.write(input.toString());
402                return Character.codePointCount(input, 0, input.length());
403            }
404
405            // strip quotes
406            final String quoteless = input.subSequence(1, input.length() - 1).toString();
407
408            if ( StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS) ) {
409                // deal with escaped quotes; ie) ""
410                out.write(StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR, CSV_QUOTE_STR));
411            } else {
412                out.write(input.toString());
413            }
414            return Character.codePointCount(input, 0, input.length());
415        }
416    }
417
418    /* Helper functions */
419
420    /**
421     * <p>{@code StringEscapeUtils} instances should NOT be constructed in
422     * standard programming.</p>
423     *
424     * <p>Instead, the class should be used as:</p>
425     * <pre>StringEscapeUtils.escapeJava("foo");</pre>
426     *
427     * <p>This constructor is public to permit tools that require a JavaBean
428     * instance to operate.</p>
429     */
430    public StringEscapeUtils() {
431      super();
432    }
433
434    // Java and JavaScript
435    //--------------------------------------------------------------------------
436    /**
437     * <p>Escapes the characters in a {@code String} using Java String rules.</p>
438     *
439     * <p>Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) </p>
440     *
441     * <p>So a tab becomes the characters {@code '\\'} and
442     * {@code 't'}.</p>
443     *
444     * <p>The only difference between Java strings and JavaScript strings
445     * is that in JavaScript, a single quote and forward-slash (/) are escaped.</p>
446     *
447     * <p>Example:</p>
448     * <pre>
449     * input string: He didn't say, "Stop!"
450     * output string: He didn't say, \"Stop!\"
451     * </pre>
452     *
453     * @param input  String to escape values in, may be null
454     * @return String with escaped values, {@code null} if null string input
455     */
456    public static final String escapeJava(final String input) {
457        return ESCAPE_JAVA.translate(input);
458    }
459
460    /**
461     * <p>Escapes the characters in a {@code String} using EcmaScript String rules.</p>
462     * <p>Escapes any values it finds into their EcmaScript String form.
463     * Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) </p>
464     *
465     * <p>So a tab becomes the characters {@code '\\'} and
466     * {@code 't'}.</p>
467     *
468     * <p>The only difference between Java strings and EcmaScript strings
469     * is that in EcmaScript, a single quote and forward-slash (/) are escaped.</p>
470     *
471     * <p>Note that EcmaScript is best known by the JavaScript and ActionScript dialects. </p>
472     *
473     * <p>Example:</p>
474     * <pre>
475     * input string: He didn't say, "Stop!"
476     * output string: He didn\'t say, \"Stop!\"
477     * </pre>
478     *
479     * @param input  String to escape values in, may be null
480     * @return String with escaped values, {@code null} if null string input
481     *
482     * @since 3.0
483     */
484    public static final String escapeEcmaScript(final String input) {
485        return ESCAPE_ECMASCRIPT.translate(input);
486    }
487
488    /**
489     * <p>Escapes the characters in a {@code String} using Json String rules.</p>
490     * <p>Escapes any values it finds into their Json String form.
491     * Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) </p>
492     *
493     * <p>So a tab becomes the characters {@code '\\'} and
494     * {@code 't'}.</p>
495     *
496     * <p>The only difference between Java strings and Json strings
497     * is that in Json, forward-slash (/) is escaped.</p>
498     *
499     * <p>See http://www.ietf.org/rfc/rfc4627.txt for further details. </p>
500     *
501     * <p>Example:</p>
502     * <pre>
503     * input string: He didn't say, "Stop!"
504     * output string: He didn't say, \"Stop!\"
505     * </pre>
506     *
507     * @param input  String to escape values in, may be null
508     * @return String with escaped values, {@code null} if null string input
509     *
510     * @since 3.2
511     */
512    public static final String escapeJson(final String input) {
513        return ESCAPE_JSON.translate(input);
514    }
515
516    /**
517     * <p>Unescapes any Java literals found in the {@code String}.
518     * For example, it will turn a sequence of {@code '\'} and
519     * {@code 'n'} into a newline character, unless the {@code '\'}
520     * is preceded by another {@code '\'}.</p>
521     *
522     * @param input  the {@code String} to unescape, may be null
523     * @return a new unescaped {@code String}, {@code null} if null string input
524     */
525    public static final String unescapeJava(final String input) {
526        return UNESCAPE_JAVA.translate(input);
527    }
528
529    /**
530     * <p>Unescapes any EcmaScript literals found in the {@code String}.</p>
531     *
532     * <p>For example, it will turn a sequence of {@code '\'} and {@code 'n'}
533     * into a newline character, unless the {@code '\'} is preceded by another
534     * {@code '\'}.</p>
535     *
536     * @see #unescapeJava(String)
537     * @param input  the {@code String} to unescape, may be null
538     * @return A new unescaped {@code String}, {@code null} if null string input
539     *
540     * @since 3.0
541     */
542    public static final String unescapeEcmaScript(final String input) {
543        return UNESCAPE_ECMASCRIPT.translate(input);
544    }
545
546    /**
547     * <p>Unescapes any Json literals found in the {@code String}.</p>
548     *
549     * <p>For example, it will turn a sequence of {@code '\'} and {@code 'n'}
550     * into a newline character, unless the {@code '\'} is preceded by another
551     * {@code '\'}.</p>
552     *
553     * @see #unescapeJava(String)
554     * @param input  the {@code String} to unescape, may be null
555     * @return A new unescaped {@code String}, {@code null} if null string input
556     *
557     * @since 3.2
558     */
559    public static final String unescapeJson(final String input) {
560        return UNESCAPE_JSON.translate(input);
561    }
562
563    // HTML and XML
564    //--------------------------------------------------------------------------
565    /**
566     * <p>Escapes the characters in a {@code String} using HTML entities.</p>
567     *
568     * <p>
569     * For example:
570     * </p>
571     * <p><code>"bread" &amp; "butter"</code></p>
572     * becomes:
573     * <p>
574     * <code>&amp;quot;bread&amp;quot; &amp;amp; &amp;quot;butter&amp;quot;</code>.
575     * </p>
576     *
577     * <p>Supports all known HTML 4.0 entities, including funky accents.
578     * Note that the commonly used apostrophe escape character (&amp;apos;)
579     * is not a legal entity and so is not supported). </p>
580     *
581     * @param input  the {@code String} to escape, may be null
582     * @return a new escaped {@code String}, {@code null} if null string input
583     *
584     * @see <a href="http://hotwired.lycos.com/webmonkey/reference/special_characters/">ISO Entities</a>
585     * @see <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO Latin-1</a>
586     * @see <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity references</a>
587     * @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a>
588     * @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a>
589     *
590     * @since 3.0
591     */
592    public static final String escapeHtml4(final String input) {
593        return ESCAPE_HTML4.translate(input);
594    }
595
596    /**
597     * <p>Escapes the characters in a {@code String} using HTML entities.</p>
598     * <p>Supports only the HTML 3.0 entities. </p>
599     *
600     * @param input  the {@code String} to escape, may be null
601     * @return a new escaped {@code String}, {@code null} if null string input
602     *
603     * @since 3.0
604     */
605    public static final String escapeHtml3(final String input) {
606        return ESCAPE_HTML3.translate(input);
607    }
608
609    //-----------------------------------------------------------------------
610    /**
611     * <p>Unescapes a string containing entity escapes to a string
612     * containing the actual Unicode characters corresponding to the
613     * escapes. Supports HTML 4.0 entities.</p>
614     *
615     * <p>For example, the string {@code "&lt;Fran&ccedil;ais&gt;"}
616     * will become {@code "<Fran├žais>"}</p>
617     *
618     * <p>If an entity is unrecognized, it is left alone, and inserted
619     * verbatim into the result string. e.g. {@code "&gt;&zzzz;x"} will
620     * become {@code ">&zzzz;x"}.</p>
621     *
622     * @param input  the {@code String} to unescape, may be null
623     * @return a new unescaped {@code String}, {@code null} if null string input
624     *
625     * @since 3.0
626     */
627    public static final String unescapeHtml4(final String input) {
628        return UNESCAPE_HTML4.translate(input);
629    }
630
631    /**
632     * <p>Unescapes a string containing entity escapes to a string
633     * containing the actual Unicode characters corresponding to the
634     * escapes. Supports only HTML 3.0 entities.</p>
635     *
636     * @param input  the {@code String} to unescape, may be null
637     * @return a new unescaped {@code String}, {@code null} if null string input
638     *
639     * @since 3.0
640     */
641    public static final String unescapeHtml3(final String input) {
642        return UNESCAPE_HTML3.translate(input);
643    }
644
645    //-----------------------------------------------------------------------
646    /**
647     * <p>Escapes the characters in a {@code String} using XML entities.</p>
648     *
649     * <p>For example: {@code "bread" & "butter"} =&gt;
650     * {@code &quot;bread&quot; &amp; &quot;butter&quot;}.
651     * </p>
652     *
653     * <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos).
654     * Does not support DTDs or external entities.</p>
655     *
656     * <p>Note that Unicode characters greater than 0x7f are as of 3.0, no longer
657     *    escaped. If you still wish this functionality, you can achieve it
658     *    via the following:
659     * {@code StringEscapeUtils.ESCAPE_XML.with( NumericEntityEscaper.between(0x7f, Integer.MAX_VALUE) );}</p>
660     *
661     * @param input  the {@code String} to escape, may be null
662     * @return a new escaped {@code String}, {@code null} if null string input
663     * @see #unescapeXml(java.lang.String)
664     * @deprecated use {@link #escapeXml10(java.lang.String)} or {@link #escapeXml11(java.lang.String)} instead.
665     */
666    @Deprecated
667    public static final String escapeXml(final String input) {
668        return ESCAPE_XML.translate(input);
669    }
670
671    /**
672     * <p>Escapes the characters in a {@code String} using XML entities.</p>
673     *
674     * <p>For example: {@code "bread" & "butter"} =&gt;
675     * {@code &quot;bread&quot; &amp; &quot;butter&quot;}.
676     * </p>
677     *
678     * <p>Note that XML 1.0 is a text-only format: it cannot represent control
679     * characters or unpaired Unicode surrogate codepoints, even after escaping.
680     * {@code escapeXml10} will remove characters that do not fit in the
681     * following ranges:</p>
682     *
683     * <p>{@code #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]}</p>
684     *
685     * <p>Though not strictly necessary, {@code escapeXml10} will escape
686     * characters in the following ranges:</p>
687     *
688     * <p>{@code [#x7F-#x84] | [#x86-#x9F]}</p>
689     *
690     * <p>The returned string can be inserted into a valid XML 1.0 or XML 1.1
691     * document. If you want to allow more non-text characters in an XML 1.1
692     * document, use {@link #escapeXml11(String)}.</p>
693     *
694     * @param input  the {@code String} to escape, may be null
695     * @return a new escaped {@code String}, {@code null} if null string input
696     * @see #unescapeXml(java.lang.String)
697     * @since 3.3
698     */
699    public static String escapeXml10(final String input) {
700        return ESCAPE_XML10.translate(input);
701    }
702
703    /**
704     * <p>Escapes the characters in a {@code String} using XML entities.</p>
705     *
706     * <p>For example: {@code "bread" & "butter"} =&gt;
707     * {@code &quot;bread&quot; &amp; &quot;butter&quot;}.
708     * </p>
709     *
710     * <p>XML 1.1 can represent certain control characters, but it cannot represent
711     * the null byte or unpaired Unicode surrogate codepoints, even after escaping.
712     * {@code escapeXml11} will remove characters that do not fit in the following
713     * ranges:</p>
714     *
715     * <p>{@code [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]}</p>
716     *
717     * <p>{@code escapeXml11} will escape characters in the following ranges:</p>
718     *
719     * <p>{@code [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]}</p>
720     *
721     * <p>The returned string can be inserted into a valid XML 1.1 document. Do not
722     * use it for XML 1.0 documents.</p>
723     *
724     * @param input  the {@code String} to escape, may be null
725     * @return a new escaped {@code String}, {@code null} if null string input
726     * @see #unescapeXml(java.lang.String)
727     * @since 3.3
728     */
729    public static String escapeXml11(final String input) {
730        return ESCAPE_XML11.translate(input);
731    }
732
733    //-----------------------------------------------------------------------
734    /**
735     * <p>Unescapes a string containing XML entity escapes to a string
736     * containing the actual Unicode characters corresponding to the
737     * escapes.</p>
738     *
739     * <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos).
740     * Does not support DTDs or external entities.</p>
741     *
742     * <p>Note that numerical \\u Unicode codes are unescaped to their respective
743     *    Unicode characters. This may change in future releases. </p>
744     *
745     * @param input  the {@code String} to unescape, may be null
746     * @return a new unescaped {@code String}, {@code null} if null string input
747     * @see #escapeXml(String)
748     * @see #escapeXml10(String)
749     * @see #escapeXml11(String)
750     */
751    public static final String unescapeXml(final String input) {
752        return UNESCAPE_XML.translate(input);
753    }
754
755    //-----------------------------------------------------------------------
756
757    /**
758     * <p>Returns a {@code String} value for a CSV column enclosed in double quotes,
759     * if required.</p>
760     *
761     * <p>If the value contains a comma, newline or double quote, then the
762     *    String value is returned enclosed in double quotes.</p>
763     *
764     * <p>Any double quote characters in the value are escaped with another double quote.</p>
765     *
766     * <p>If the value does not contain a comma, newline or double quote, then the
767     *    String value is returned unchanged.</p>
768     *
769     * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
770     * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
771     *
772     * @param input the input CSV column String, may be null
773     * @return the input String, enclosed in double quotes if the value contains a comma,
774     * newline or double quote, {@code null} if null string input
775     * @since 2.4
776     */
777    public static final String escapeCsv(final String input) {
778        return ESCAPE_CSV.translate(input);
779    }
780
781    /**
782     * <p>Returns a {@code String} value for an unescaped CSV column. </p>
783     *
784     * <p>If the value is enclosed in double quotes, and contains a comma, newline
785     *    or double quote, then quotes are removed.
786     * </p>
787     *
788     * <p>Any double quote escaped characters (a pair of double quotes) are unescaped
789     *    to just one double quote. </p>
790     *
791     * <p>If the value is not enclosed in double quotes, or is and does not contain a
792     *    comma, newline or double quote, then the String value is returned unchanged.</p>
793     *
794     * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
795     * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
796     *
797     * @param input the input CSV column String, may be null
798     * @return the input String, with enclosing double quotes removed and embedded double
799     * quotes unescaped, {@code null} if null string input
800     * @since 2.4
801     */
802    public static final String unescapeCsv(final String input) {
803        return UNESCAPE_CSV.translate(input);
804    }
805
806}