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 * https://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.text; 018 019import java.io.IOException; 020import java.io.Writer; 021import java.util.Collections; 022import java.util.HashMap; 023import java.util.Map; 024 025import org.apache.commons.lang3.StringUtils; 026import org.apache.commons.text.translate.AggregateTranslator; 027import org.apache.commons.text.translate.CharSequenceTranslator; 028import org.apache.commons.text.translate.CsvTranslators; 029import org.apache.commons.text.translate.EntityArrays; 030import org.apache.commons.text.translate.JavaUnicodeEscaper; 031import org.apache.commons.text.translate.LookupTranslator; 032import org.apache.commons.text.translate.NumericEntityEscaper; 033import org.apache.commons.text.translate.NumericEntityUnescaper; 034import org.apache.commons.text.translate.OctalUnescaper; 035import org.apache.commons.text.translate.UnicodeUnescaper; 036import org.apache.commons.text.translate.UnicodeUnpairedSurrogateRemover; 037 038/** 039 * <p> 040 * Escapes and unescapes {@code String}s for Java, Java Script, HTML and XML. 041 * </p> 042 * 043 * <p> 044 * #ThreadSafe# 045 * </p> 046 * 047 * <p> 048 * This code has been adapted from Apache Commons Lang 3.5. 049 * </p> 050 * 051 * @since 1.0 052 */ 053public class StringEscapeUtils { 054 055 /* ESCAPE TRANSLATORS */ 056 057 /** 058 * Convenience wrapper for {@link StringBuilder} providing escape methods. 059 * 060 * <p>Example:</p> 061 * <pre> 062 * new Builder(ESCAPE_HTML4) 063 * .append("<p>") 064 * .escape("This is paragraph 1 and special chars like & get escaped.") 065 * .append("</p><p>") 066 * .escape("This is paragraph 2 & more...") 067 * .append("</p>") 068 * .toString() 069 * </pre> 070 */ 071 public static final class Builder { 072 073 /** 074 * StringBuilder to be used in the Builder class. 075 */ 076 private final StringBuilder sb; 077 078 /** 079 * CharSequenceTranslator to be used in the Builder class. 080 */ 081 private final CharSequenceTranslator translator; 082 083 /** 084 * Builder constructor. 085 * 086 * @param translator a CharSequenceTranslator. 087 */ 088 private Builder(final CharSequenceTranslator translator) { 089 this.sb = new StringBuilder(); 090 this.translator = translator; 091 } 092 093 /** 094 * Literal append, no escaping being done. 095 * 096 * @param input the String to append 097 * @return {@code this}, to enable chaining 098 */ 099 public Builder append(final String input) { 100 sb.append(input); 101 return this; 102 } 103 104 /** 105 * Escape {@code input} according to the given {@link CharSequenceTranslator}. 106 * 107 * @param input the String to escape 108 * @return {@code this}, to enable chaining 109 */ 110 public Builder escape(final String input) { 111 sb.append(translator.translate(input)); 112 return this; 113 } 114 115 /** 116 * Return the escaped string. 117 * 118 * @return The escaped string 119 */ 120 @Override 121 public String toString() { 122 return sb.toString(); 123 } 124 } 125 126 /** 127 * Translator object for unescaping backslash escaped entries. 128 */ 129 static class XsiUnescaper extends CharSequenceTranslator { 130 131 /** 132 * Escaped backslash constant. 133 */ 134 private static final char BACKSLASH = '\\'; 135 136 @Override 137 public int translate(final CharSequence input, final int index, final Writer writer) throws IOException { 138 139 if (index != 0) { 140 throw new IllegalStateException("XsiUnescaper should never reach the [1] index"); 141 } 142 143 final String s = input.toString(); 144 145 int segmentStart = 0; 146 int searchOffset = 0; 147 while (true) { 148 final int pos = s.indexOf(BACKSLASH, searchOffset); 149 if (pos == -1) { 150 if (segmentStart < s.length()) { 151 writer.write(s.substring(segmentStart)); 152 } 153 break; 154 } 155 if (pos > segmentStart) { 156 writer.write(s.substring(segmentStart, pos)); 157 } 158 segmentStart = pos + 1; 159 searchOffset = pos + 2; 160 } 161 162 return Character.codePointCount(input, 0, input.length()); 163 } 164 } 165 166 /** 167 * Translator object for escaping Java. 168 * 169 * While {@link #escapeJava(String)} is the expected method of use, this object allows the Java escaping functionality to be used as the foundation for a 170 * custom translator. 171 */ 172 public static final CharSequenceTranslator ESCAPE_JAVA; 173 static { 174 final Map<CharSequence, CharSequence> escapeJavaMap = new HashMap<>(); 175 escapeJavaMap.put("\"", "\\\""); 176 escapeJavaMap.put("\\", "\\\\"); 177 ESCAPE_JAVA = new AggregateTranslator( 178 new LookupTranslator(Collections.unmodifiableMap(escapeJavaMap)), 179 new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE), 180 JavaUnicodeEscaper.outsideOf(32, 0x7f) 181 ); 182 } 183 184 /** 185 * Translator object for escaping EcmaScript/JavaScript. 186 * 187 * While {@link #escapeEcmaScript(String)} is the expected method of use, this object allows the EcmaScript escaping functionality to be used as the 188 * foundation for a custom translator. 189 */ 190 public static final CharSequenceTranslator ESCAPE_ECMASCRIPT; 191 static { 192 final Map<CharSequence, CharSequence> escapeEcmaScriptMap = new HashMap<>(); 193 escapeEcmaScriptMap.put("'", "\\'"); 194 escapeEcmaScriptMap.put("\"", "\\\""); 195 escapeEcmaScriptMap.put("\\", "\\\\"); 196 escapeEcmaScriptMap.put("/", "\\/"); 197 ESCAPE_ECMASCRIPT = new AggregateTranslator( 198 new LookupTranslator(Collections.unmodifiableMap(escapeEcmaScriptMap)), 199 new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE), 200 JavaUnicodeEscaper.outsideOf(32, 0x7f) 201 ); 202 } 203 204 /** 205 * Translator object for escaping Json. 206 * 207 * While {@link #escapeJson(String)} is the expected method of use, this object allows the Json escaping functionality to be used as the foundation for a 208 * custom translator. 209 */ 210 public static final CharSequenceTranslator ESCAPE_JSON; 211 static { 212 final Map<CharSequence, CharSequence> escapeJsonMap = new HashMap<>(); 213 escapeJsonMap.put("\"", "\\\""); 214 escapeJsonMap.put("\\", "\\\\"); 215 escapeJsonMap.put("/", "\\/"); 216 ESCAPE_JSON = new AggregateTranslator( 217 new LookupTranslator(Collections.unmodifiableMap(escapeJsonMap)), 218 new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE), 219 JavaUnicodeEscaper.outsideOf(32, 0x7e) 220 ); 221 } 222 223 /** 224 * Translator object for escaping XML 1.0. 225 * 226 * While {@link #escapeXml10(String)} is the expected method of use, this object allows the XML escaping functionality to be used as the foundation for a 227 * custom translator. 228 */ 229 public static final CharSequenceTranslator ESCAPE_XML10; 230 static { 231 final Map<CharSequence, CharSequence> escapeXml10Map = new HashMap<>(); 232 escapeXml10Map.put("\u0000", StringUtils.EMPTY); 233 escapeXml10Map.put("\u0001", StringUtils.EMPTY); 234 escapeXml10Map.put("\u0002", StringUtils.EMPTY); 235 escapeXml10Map.put("\u0003", StringUtils.EMPTY); 236 escapeXml10Map.put("\u0004", StringUtils.EMPTY); 237 escapeXml10Map.put("\u0005", StringUtils.EMPTY); 238 escapeXml10Map.put("\u0006", StringUtils.EMPTY); 239 escapeXml10Map.put("\u0007", StringUtils.EMPTY); 240 escapeXml10Map.put("\u0008", StringUtils.EMPTY); 241 escapeXml10Map.put("\u000b", StringUtils.EMPTY); 242 escapeXml10Map.put("\u000c", StringUtils.EMPTY); 243 escapeXml10Map.put("\u000e", StringUtils.EMPTY); 244 escapeXml10Map.put("\u000f", StringUtils.EMPTY); 245 escapeXml10Map.put("\u0010", StringUtils.EMPTY); 246 escapeXml10Map.put("\u0011", StringUtils.EMPTY); 247 escapeXml10Map.put("\u0012", StringUtils.EMPTY); 248 escapeXml10Map.put("\u0013", StringUtils.EMPTY); 249 escapeXml10Map.put("\u0014", StringUtils.EMPTY); 250 escapeXml10Map.put("\u0015", StringUtils.EMPTY); 251 escapeXml10Map.put("\u0016", StringUtils.EMPTY); 252 escapeXml10Map.put("\u0017", StringUtils.EMPTY); 253 escapeXml10Map.put("\u0018", StringUtils.EMPTY); 254 escapeXml10Map.put("\u0019", StringUtils.EMPTY); 255 escapeXml10Map.put("\u001a", StringUtils.EMPTY); 256 escapeXml10Map.put("\u001b", StringUtils.EMPTY); 257 escapeXml10Map.put("\u001c", StringUtils.EMPTY); 258 escapeXml10Map.put("\u001d", StringUtils.EMPTY); 259 escapeXml10Map.put("\u001e", StringUtils.EMPTY); 260 escapeXml10Map.put("\u001f", StringUtils.EMPTY); 261 escapeXml10Map.put("\ufffe", StringUtils.EMPTY); 262 escapeXml10Map.put("\uffff", StringUtils.EMPTY); 263 ESCAPE_XML10 = new AggregateTranslator( 264 new LookupTranslator(EntityArrays.BASIC_ESCAPE), 265 new LookupTranslator(EntityArrays.APOS_ESCAPE), 266 new LookupTranslator(Collections.unmodifiableMap(escapeXml10Map)), 267 NumericEntityEscaper.between(0x7f, 0x84), 268 NumericEntityEscaper.between(0x86, 0x9f), 269 new UnicodeUnpairedSurrogateRemover() 270 ); 271 } 272 273 /** 274 * Translator object for escaping XML 1.1. 275 * 276 * While {@link #escapeXml11(String)} is the expected method of use, this 277 * object allows the XML escaping functionality to be used 278 * as the foundation for a custom translator. 279 */ 280 public static final CharSequenceTranslator ESCAPE_XML11; 281 282 static { 283 final Map<CharSequence, CharSequence> escapeXml11Map = new HashMap<>(); 284 escapeXml11Map.put("\u0000", StringUtils.EMPTY); 285 escapeXml11Map.put("\u000b", ""); 286 escapeXml11Map.put("\u000c", ""); 287 escapeXml11Map.put("\ufffe", StringUtils.EMPTY); 288 escapeXml11Map.put("\uffff", StringUtils.EMPTY); 289 ESCAPE_XML11 = new AggregateTranslator( 290 new LookupTranslator(EntityArrays.BASIC_ESCAPE), 291 new LookupTranslator(EntityArrays.APOS_ESCAPE), 292 new LookupTranslator(Collections.unmodifiableMap(escapeXml11Map)), 293 NumericEntityEscaper.between(0x1, 0x8), 294 NumericEntityEscaper.between(0xe, 0x1f), 295 NumericEntityEscaper.between(0x7f, 0x84), 296 NumericEntityEscaper.between(0x86, 0x9f), 297 new UnicodeUnpairedSurrogateRemover() 298 ); 299 } 300 301 /** 302 * Translator object for escaping HTML version 3.0. 303 * 304 * While {@link #escapeHtml3(String)} is the expected method of use, this 305 * object allows the HTML escaping functionality to be used 306 * as the foundation for a custom translator. 307 */ 308 public static final CharSequenceTranslator ESCAPE_HTML3 = 309 new AggregateTranslator( 310 new LookupTranslator(EntityArrays.BASIC_ESCAPE), 311 new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE) 312 ); 313 314 /** 315 * Translator object for escaping HTML version 4.0. 316 * 317 * While {@link #escapeHtml4(String)} is the expected method of use, this 318 * object allows the HTML escaping functionality to be used 319 * as the foundation for a custom translator. 320 */ 321 public static final CharSequenceTranslator ESCAPE_HTML4 = 322 new AggregateTranslator( 323 new LookupTranslator(EntityArrays.BASIC_ESCAPE), 324 new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE), 325 new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE) 326 ); 327 328 /** 329 * Translator object for escaping individual Comma Separated Values. 330 * 331 * While {@link #escapeCsv(String)} is the expected method of use, this 332 * object allows the CSV escaping functionality to be used 333 * as the foundation for a custom translator. 334 */ 335 public static final CharSequenceTranslator ESCAPE_CSV = new CsvTranslators.CsvEscaper(); 336 337 /* UNESCAPE TRANSLATORS */ 338 339 /** 340 * Translator object for escaping Shell command language. 341 * 342 * @see <a href="https://pubs.opengroup.org/onlinepubs/7908799/xcu/chap2.html">Shell Command Language</a> 343 */ 344 public static final CharSequenceTranslator ESCAPE_XSI; 345 static { 346 final Map<CharSequence, CharSequence> escapeXsiMap = new HashMap<>(); 347 escapeXsiMap.put("|", "\\|"); 348 escapeXsiMap.put("&", "\\&"); 349 escapeXsiMap.put(";", "\\;"); 350 escapeXsiMap.put("<", "\\<"); 351 escapeXsiMap.put(">", "\\>"); 352 escapeXsiMap.put("(", "\\("); 353 escapeXsiMap.put(")", "\\)"); 354 escapeXsiMap.put("$", "\\$"); 355 escapeXsiMap.put("`", "\\`"); 356 escapeXsiMap.put("\\", "\\\\"); 357 escapeXsiMap.put("\"", "\\\""); 358 escapeXsiMap.put("'", "\\'"); 359 escapeXsiMap.put(" ", "\\ "); 360 escapeXsiMap.put("\t", "\\\t"); 361 escapeXsiMap.put("\r\n", StringUtils.EMPTY); 362 escapeXsiMap.put("\n", StringUtils.EMPTY); 363 escapeXsiMap.put("*", "\\*"); 364 escapeXsiMap.put("?", "\\?"); 365 escapeXsiMap.put("[", "\\["); 366 escapeXsiMap.put("#", "\\#"); 367 escapeXsiMap.put("~", "\\~"); 368 escapeXsiMap.put("=", "\\="); 369 escapeXsiMap.put("%", "\\%"); 370 ESCAPE_XSI = new LookupTranslator( 371 Collections.unmodifiableMap(escapeXsiMap) 372 ); 373 } 374 375 /** 376 * Translator object for unescaping escaped Java. 377 * 378 * While {@link #unescapeJava(String)} is the expected method of use, this 379 * object allows the Java unescaping functionality to be used 380 * as the foundation for a custom translator. 381 */ 382 public static final CharSequenceTranslator UNESCAPE_JAVA; 383 384 static { 385 final Map<CharSequence, CharSequence> unescapeJavaMap = new HashMap<>(); 386 unescapeJavaMap.put("\\\\", "\\"); 387 unescapeJavaMap.put("\\\"", "\""); 388 unescapeJavaMap.put("\\'", "'"); 389 unescapeJavaMap.put("\\", StringUtils.EMPTY); 390 UNESCAPE_JAVA = new AggregateTranslator( 391 new OctalUnescaper(), // .between('\1', '\377'), 392 new UnicodeUnescaper(), 393 new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE), 394 new LookupTranslator(Collections.unmodifiableMap(unescapeJavaMap)) 395 ); 396 } 397 398 /** 399 * Translator object for unescaping escaped EcmaScript. 400 * 401 * While {@link #unescapeEcmaScript(String)} is the expected method of use, this 402 * object allows the EcmaScript unescaping functionality to be used 403 * as the foundation for a custom translator. 404 */ 405 public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA; 406 407 /** 408 * Translator object for unescaping escaped Json. 409 * 410 * While {@link #unescapeJson(String)} is the expected method of use, this 411 * object allows the Json unescaping functionality to be used 412 * as the foundation for a custom translator. 413 */ 414 public static final CharSequenceTranslator UNESCAPE_JSON = UNESCAPE_JAVA; 415 416 /** 417 * Translator object for unescaping escaped HTML 3.0. 418 * 419 * While {@link #unescapeHtml3(String)} is the expected method of use, this 420 * object allows the HTML unescaping functionality to be used 421 * as the foundation for a custom translator. 422 */ 423 public static final CharSequenceTranslator UNESCAPE_HTML3 = 424 new AggregateTranslator( 425 new LookupTranslator(EntityArrays.BASIC_UNESCAPE), 426 new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE), 427 new NumericEntityUnescaper() 428 ); 429 430 /** 431 * Translator object for unescaping escaped HTML 4.0. 432 * 433 * While {@link #unescapeHtml4(String)} is the expected method of use, this 434 * object allows the HTML unescaping functionality to be used 435 * as the foundation for a custom translator. 436 */ 437 public static final CharSequenceTranslator UNESCAPE_HTML4 = 438 new AggregateTranslator( 439 new LookupTranslator(EntityArrays.BASIC_UNESCAPE), 440 new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE), 441 new LookupTranslator(EntityArrays.HTML40_EXTENDED_UNESCAPE), 442 new NumericEntityUnescaper() 443 ); 444 445 /** 446 * Translator object for unescaping escaped XML. 447 * 448 * While {@link #unescapeXml(String)} is the expected method of use, this 449 * object allows the XML unescaping functionality to be used 450 * as the foundation for a custom translator. 451 */ 452 public static final CharSequenceTranslator UNESCAPE_XML = 453 new AggregateTranslator( 454 new LookupTranslator(EntityArrays.BASIC_UNESCAPE), 455 new LookupTranslator(EntityArrays.APOS_UNESCAPE), 456 new NumericEntityUnescaper() 457 ); 458 459 /** 460 * Translator object for unescaping escaped Comma Separated Value entries. 461 * 462 * While {@link #unescapeCsv(String)} is the expected method of use, this 463 * object allows the CSV unescaping functionality to be used 464 * as the foundation for a custom translator. 465 */ 466 public static final CharSequenceTranslator UNESCAPE_CSV = new CsvTranslators.CsvUnescaper(); 467 468 /* Helper functions */ 469 470 /** 471 * Translator object for unescaping escaped XSI Value entries. 472 * 473 * While {@link #unescapeXSI(String)} is the expected method of use, this 474 * object allows the XSI unescaping functionality to be used 475 * as the foundation for a custom translator. 476 */ 477 public static final CharSequenceTranslator UNESCAPE_XSI = new XsiUnescaper(); 478 479 /** 480 * Gets a {@link Builder}. 481 * 482 * @param translator the text translator. 483 * @return {@link Builder} 484 */ 485 public static StringEscapeUtils.Builder builder(final CharSequenceTranslator translator) { 486 return new Builder(translator); 487 } 488 489 /** 490 * Returns a {@code String} value for a CSV column enclosed in double quotes, if required. 491 * 492 * <p> 493 * If the value contains a comma, newline or double quote, then the String value is returned enclosed in double quotes. 494 * </p> 495 * 496 * <p> 497 * Any double quote characters in the value are escaped with another double quote. 498 * </p> 499 * 500 * <p> 501 * If the value does not contain a comma, newline or double quote, then the String value is returned unchanged. 502 * </p> 503 * <p> 504 * See <a href="https://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and <a href="https://tools.ietf.org/html/rfc4180">RFC 4180</a>. 505 * </p> 506 * 507 * @param input the input CSV column String, may be null. 508 * @return The input String, enclosed in double quotes if the value contains a comma, newline or double quote, {@code null} if null string input. 509 */ 510 public static String escapeCsv(final String input) { 511 return ESCAPE_CSV.translate(input); 512 } 513 514 /** 515 * Escapes the characters in a {@code String} using EcmaScript String rules. 516 * 517 * <p> 518 * Escapes any values it finds into their EcmaScript String form. Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) 519 * </p> 520 * 521 * <p> 522 * So a tab becomes the characters {@code '\\'} and {@code 't'}. 523 * </p> 524 * 525 * <p> 526 * The only difference between Java strings and EcmaScript strings is that in EcmaScript, a single quote and forward-slash (/) are escaped. 527 * </p> 528 * 529 * <p> 530 * Note that EcmaScript is best known by the JavaScript and ActionScript dialects. 531 * </p> 532 * 533 * <p> 534 * Example: 535 * </p> 536 * 537 * <pre> 538 * input string: He didn't say, "Stop!" 539 * output string: He didn\'t say, \"Stop!\" 540 * </pre> 541 * <p> 542 * <strong>Security Note.</strong> We only provide backslash escaping in this method. For example, {@code '\"'} has the output {@code '\\\"'} which could 543 * result in potential issues in the case where the string being escaped is being used in an HTML tag like {@code <select onmouseover="..." />}. If you wish 544 * to have more rigorous string escaping, you may consider the <a href="https://www.owasp.org/index.php/Category:OWASP_Enterprise_Security_API_JAVA">ESAPI 545 * Libraries</a>. Further, you can view the <a href="https://github.com/esapi">ESAPI GitHub Org</a>. 546 * </p> 547 * 548 * @param input String to escape values in, may be null. 549 * @return String with escaped values, {@code null} if null string input. 550 */ 551 public static String escapeEcmaScript(final String input) { 552 return ESCAPE_ECMASCRIPT.translate(input); 553 } 554 555 /** 556 * Escapes the characters in a {@code String} using HTML entities. 557 * 558 * <p>Supports only the HTML 3.0 entities.</p> 559 * 560 * @param input the {@code String} to escape, may be null. 561 * @return a new escaped {@code String}, {@code null} if null string input. 562 */ 563 public static String escapeHtml3(final String input) { 564 return ESCAPE_HTML3.translate(input); 565 } 566 567 /** 568 * Escapes the characters in a {@code String} using HTML entities. 569 * 570 * <p> 571 * For example: 572 * </p> 573 * <p>{@code "bread" & "butter"}</p> 574 * becomes: 575 * <p> 576 * {@code "bread" &amp; "butter"}. 577 * </p> 578 * 579 * <p>Supports all known HTML 4.0 entities, including funky accents. 580 * Note that the commonly used apostrophe escape character (&apos;) 581 * is not a legal entity and so is not supported).</p> 582 * 583 * @param input the {@code String} to escape, may be null. 584 * @return a new escaped {@code String}, {@code null} if null string input. 585 * @see <a href="https://hotwired.lycos.com/webmonkey/reference/special_characters/">ISO Entities</a> 586 * @see <a href="https://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO Latin-1</a> 587 * @see <a href="https://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity references</a> 588 * @see <a href="https://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a> 589 * @see <a href="https://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a> 590 */ 591 public static String escapeHtml4(final String input) { 592 return ESCAPE_HTML4.translate(input); 593 } 594 595 /** 596 * Escapes the characters in a {@code String} using Java String rules. 597 * 598 * <p> 599 * Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) 600 * </p> 601 * 602 * <p> 603 * So a tab becomes the characters {@code '\\'} and {@code 't'}. 604 * </p> 605 * 606 * <p> 607 * The only difference between Java strings and JavaScript strings is that in JavaScript, a single quote and forward-slash (/) are escaped. 608 * </p> 609 * 610 * <p> 611 * Example: 612 * </p> 613 * 614 * <pre> 615 * input string: He didn't say, "Stop!" 616 * output string: He didn't say, \"Stop!\" 617 * </pre> 618 * 619 * @param input String to escape values in, may be null. 620 * @return String with escaped values, {@code null} if null string input. 621 */ 622 public static String escapeJava(final String input) { 623 return ESCAPE_JAVA.translate(input); 624 } 625 626 /** 627 * Escapes the characters in a {@code String} using Json String rules. 628 * 629 * <p> 630 * Escapes any values it finds into their Json String form. Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) 631 * </p> 632 * 633 * <p> 634 * So a tab becomes the characters {@code '\\'} and {@code 't'}. 635 * </p> 636 * 637 * <p> 638 * The only difference between Java strings and Json strings is that in Json, forward-slash (/) is escaped. 639 * </p> 640 * 641 * <p> 642 * See http://www.ietf.org/rfc/rfc4627.txt for further details. 643 * </p> 644 * 645 * <p> 646 * Example: 647 * </p> 648 * 649 * <pre> 650 * input string: He didn't say, "Stop!" 651 * output string: He didn't say, \"Stop!\" 652 * </pre> 653 * 654 * @param input String to escape values in, may be null. 655 * @return String with escaped values, {@code null} if null string input. 656 */ 657 public static String escapeJson(final String input) { 658 return ESCAPE_JSON.translate(input); 659 } 660 661 /** 662 * Escapes the characters in a {@code String} using XML entities. 663 * 664 * <p> 665 * For example: {@code "bread" & "butter"} => {@code "bread" & "butter"}. 666 * </p> 667 * 668 * <p> 669 * Note that XML 1.0 is a text-only format: it cannot represent control characters or unpaired Unicode surrogate code points, even after escaping. 670 * {@code escapeXml10} will remove characters that do not fit in the following ranges: 671 * </p> 672 * 673 * <p> 674 * {@code #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]} 675 * </p> 676 * 677 * <p> 678 * Though not strictly necessary, {@code escapeXml10} will escape characters in the following ranges: 679 * </p> 680 * 681 * <p> 682 * {@code [#x7F-#x84] | [#x86-#x9F]} 683 * </p> 684 * 685 * <p> 686 * The returned string can be inserted into a valid XML 1.0 or XML 1.1 document. If you want to allow more non-text characters in an XML 1.1 document, use 687 * {@link #escapeXml11(String)}. 688 * </p> 689 * 690 * @param input the {@code String} to escape, may be null. 691 * @return a new escaped {@code String}, {@code null} if null string input. 692 * @see #unescapeXml(String) 693 */ 694 public static String escapeXml10(final String input) { 695 return ESCAPE_XML10.translate(input); 696 } 697 698 /** 699 * Escapes the characters in a {@code String} using XML entities. 700 * 701 * <p> 702 * For example: {@code "bread" & "butter"} => {@code "bread" & "butter"}. 703 * </p> 704 * 705 * <p> 706 * XML 1.1 can represent certain control characters, but it cannot represent the null byte or unpaired Unicode surrogate code points, even after escaping. 707 * {@code escapeXml11} will remove characters that do not fit in the following ranges: 708 * </p> 709 * 710 * <p> 711 * {@code [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]} 712 * </p> 713 * 714 * <p> 715 * {@code escapeXml11} will escape characters in the following ranges: 716 * </p> 717 * 718 * <p> 719 * {@code [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]} 720 * </p> 721 * 722 * <p> 723 * The returned string can be inserted into a valid XML 1.1 document. Do not use it for XML 1.0 documents. 724 * </p> 725 * 726 * @param input the {@code String} to escape, may be null. 727 * @return a new escaped {@code String}, {@code null} if null string input. 728 * @see #unescapeXml(String) 729 */ 730 public static String escapeXml11(final String input) { 731 return ESCAPE_XML11.translate(input); 732 } 733 734 /** 735 * Escapes the characters in a {@code String} using XSI rules. 736 * 737 * <p> 738 * <strong>Beware!</strong> In most cases you don't want to escape shell commands but use multi-argument methods provided by {@link ProcessBuilder} or 739 * {@link Runtime#exec(String[])} instead. 740 * </p> 741 * 742 * <p> 743 * Example: 744 * </p> 745 * 746 * <pre> 747 * input string: He didn't say, "Stop!" 748 * output string: He\ didn\'t\ say,\ \"Stop!\" 749 * </pre> 750 * 751 * @param input String to escape values in, may be null. 752 * @return String with escaped values, {@code null} if null string input. 753 * @see <a href="https://pubs.opengroup.org/onlinepubs/7908799/xcu/chap2.html">Shell Command Language</a> 754 */ 755 public static String escapeXSI(final String input) { 756 return ESCAPE_XSI.translate(input); 757 } 758 759 /** 760 * Returns a {@code String} value for an unescaped CSV column. 761 * 762 * <p> 763 * If the value is enclosed in double quotes, and contains a comma, newline or double quote, then quotes are removed. 764 * </p> 765 * 766 * <p> 767 * Any double quote escaped characters (a pair of double quotes) are unescaped to just one double quote. 768 * </p> 769 * 770 * <p> 771 * If the value is not enclosed in double quotes, or is and does not contain a comma, newline or double quote, then the String value is returned unchanged. 772 * </p> 773 * 774 * see <a href="https://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and <a href="https://tools.ietf.org/html/rfc4180">RFC 4180</a>. 775 * 776 * @param input the input CSV column String, may be null. 777 * @return The input String, with enclosing double quotes removed and embedded double quotes unescaped, {@code null} if null string input. 778 */ 779 public static String unescapeCsv(final String input) { 780 return UNESCAPE_CSV.translate(input); 781 } 782 783 /** 784 * Unescapes any EcmaScript literals found in the {@code String}. 785 * 786 * <p> 787 * For example, it will turn a sequence of {@code '\'} and {@code 'n'} into a newline character, unless the {@code '\'} is preceded by another {@code '\'}. 788 * </p> 789 * 790 * @param input the {@code String} to unescape, may be null. 791 * @return A new unescaped {@code String}, {@code null} if null string input. 792 * @see #unescapeJava(String) 793 */ 794 public static String unescapeEcmaScript(final String input) { 795 return UNESCAPE_ECMASCRIPT.translate(input); 796 } 797 798 /** 799 * Unescapes a string containing entity escapes to a string containing the actual Unicode characters corresponding to the escapes. Supports only HTML 3.0 800 * entities. 801 * 802 * @param input the {@code String} to unescape, may be null. 803 * @return a new unescaped {@code String}, {@code null} if null string input. 804 */ 805 public static String unescapeHtml3(final String input) { 806 return UNESCAPE_HTML3.translate(input); 807 } 808 809 /** 810 * Unescapes a string containing entity escapes to a string containing the actual Unicode characters corresponding to the escapes. Supports HTML 4.0 811 * entities. 812 * 813 * <p> 814 * For example, the string {@code "<Français>"} will become {@code "<Fran�ais>"} 815 * </p> 816 * 817 * <p> 818 * If an entity is unrecognized, it is left alone, and inserted verbatim into the result string. e.g. {@code ">&zzzz;x"} will become {@code ">&zzzz;x"}. 819 * </p> 820 * 821 * @param input the {@code String} to unescape, may be null. 822 * @return a new unescaped {@code String}, {@code null} if null string input. 823 */ 824 public static String unescapeHtml4(final String input) { 825 return UNESCAPE_HTML4.translate(input); 826 } 827 828 /** 829 * Unescapes any Java literals found in the {@code String}. For example, it will turn a sequence of {@code '\'} and {@code 'n'} into a newline character, 830 * unless the {@code '\'} is preceded by another {@code '\'}. 831 * 832 * @param input the {@code String} to unescape, may be null. 833 * @return a new unescaped {@code String}, {@code null} if null string input. 834 */ 835 public static String unescapeJava(final String input) { 836 return UNESCAPE_JAVA.translate(input); 837 } 838 839 /** 840 * Unescapes any Json literals found in the {@code String}. 841 * 842 * <p> 843 * For example, it will turn a sequence of {@code '\'} and {@code 'n'} into a newline character, unless the {@code '\'} is preceded by another {@code '\'}. 844 * </p> 845 * 846 * @param input the {@code String} to unescape, may be null. 847 * @return A new unescaped {@code String}, {@code null} if null string input. 848 * @see #unescapeJava(String) 849 */ 850 public static String unescapeJson(final String input) { 851 return UNESCAPE_JSON.translate(input); 852 } 853 854 /** 855 * Unescapes a string containing XML entity escapes to a string containing the actual Unicode characters corresponding to the escapes. 856 * 857 * <p> 858 * Supports only the five basic XML entities (gt, lt, quot, amp, apos). Does not support DTDs or external entities. 859 * </p> 860 * 861 * <p> 862 * Note that numerical \\u Unicode codes are unescaped to their respective Unicode characters. This may change in future releases. 863 * </p> 864 * 865 * @param input the {@code String} to unescape, may be null. 866 * @return a new unescaped {@code String}, {@code null} if null string input. 867 * @see #escapeXml10(String) 868 * @see #escapeXml11(String) 869 */ 870 public static String unescapeXml(final String input) { 871 return UNESCAPE_XML.translate(input); 872 } 873 874 /** 875 * Unescapes the characters in a {@code String} using XSI rules. 876 * 877 * @param input the {@code String} to unescape, may be null. 878 * @return a new unescaped {@code String}, {@code null} if null string input. 879 * @see StringEscapeUtils#escapeXSI(String) 880 */ 881 public static String unescapeXSI(final String input) { 882 return UNESCAPE_XSI.translate(input); 883 } 884 885 /** 886 * {@code StringEscapeUtils} instances should NOT be constructed in standard programming. 887 * 888 * <p> 889 * Instead, the class should be used as: 890 * </p> 891 * 892 * <pre> 893 * StringEscapeUtils.escapeJava("foo"); 894 * </pre> 895 * 896 * <p> 897 * This constructor is public to permit tools that require a JavaBean instance to operate. 898 * </p> 899 */ 900 public StringEscapeUtils() { 901 } 902 903}