OLD | NEW |
1 /* | 1 /* |
2 * Simplified by Andrey Novikov for AdBlock Plus | 2 * Simplified by Andrey Novikov for AdBlock Plus |
3 */ | 3 */ |
4 | 4 |
5 /* | 5 /* |
6 * Licensed to the Apache Software Foundation (ASF) under one or more | 6 * Licensed to the Apache Software Foundation (ASF) under one or more |
7 * contributor license agreements. See the NOTICE file distributed with | 7 * contributor license agreements. See the NOTICE file distributed with |
8 * this work for additional information regarding copyright ownership. | 8 * this work for additional information regarding copyright ownership. |
9 * The ASF licenses this file to You under the Apache License, Version 2.0 | 9 * The ASF licenses this file to You under the Apache License, Version 2.0 |
10 * (the "License"); you may not use this file except in compliance with | 10 * (the "License"); you may not use this file except in compliance with |
(...skipping 22 matching lines...) Expand all Loading... |
33 * @author <a href="mailto:alex@purpletech.com">Alexander Day Chaffee</a> | 33 * @author <a href="mailto:alex@purpletech.com">Alexander Day Chaffee</a> |
34 * @author Antony Riley | 34 * @author Antony Riley |
35 * @author Helge Tesgaard | 35 * @author Helge Tesgaard |
36 * @author <a href="sean@boohai.com">Sean Brown</a> | 36 * @author <a href="sean@boohai.com">Sean Brown</a> |
37 * @author <a href="mailto:ggregory@seagullsw.com">Gary Gregory</a> | 37 * @author <a href="mailto:ggregory@seagullsw.com">Gary Gregory</a> |
38 * @author Phil Steitz | 38 * @author Phil Steitz |
39 * @author Pete Gieser | 39 * @author Pete Gieser |
40 * @since 2.0 | 40 * @since 2.0 |
41 * @version $Id: StringEscapeUtils.java 612880 2008-01-17 17:34:43Z ggregory $ | 41 * @version $Id: StringEscapeUtils.java 612880 2008-01-17 17:34:43Z ggregory $ |
42 */ | 42 */ |
43 public class StringEscapeUtils { | 43 public class StringEscapeUtils |
44 | 44 { |
45 private static final char CSV_DELIMITER = ','; | 45 private static final char CSV_DELIMITER = ','; |
46 private static final char CSV_QUOTE = '"'; | 46 private static final char CSV_QUOTE = '"'; |
47 private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE); | 47 private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE); |
48 private static final char[] CSV_SEARCH_CHARS = new char[] {CSV_DELIMITER, CS
V_QUOTE, CharUtils.CR, CharUtils.LF}; | 48 private static final char[] CSV_SEARCH_CHARS = new char[]{CSV_DELIMITER, CSV_Q
UOTE, CharUtils.CR, CharUtils.LF}; |
49 | 49 |
50 /** | 50 /** |
51 * <p><code>StringEscapeUtils</code> instances should NOT be constructed in | 51 * <p><code>StringEscapeUtils</code> instances should NOT be constructed in |
52 * standard programming.</p> | 52 * standard programming.</p> |
53 * | 53 * |
54 * <p>Instead, the class should be used as: | 54 * <p>Instead, the class should be used as: |
55 * <pre>StringEscapeUtils.escapeJava("foo");</pre></p> | 55 * <pre>StringEscapeUtils.escapeJava("foo");</pre></p> |
56 * | 56 * |
57 * <p>This constructor is public to permit tools that require a JavaBean | 57 * <p>This constructor is public to permit tools that require a JavaBean |
58 * instance to operate.</p> | 58 * instance to operate.</p> |
59 */ | 59 */ |
60 public StringEscapeUtils() { | 60 public StringEscapeUtils() |
61 super(); | 61 { |
62 } | 62 super(); |
63 | 63 } |
64 // Java and JavaScript | 64 |
65 //-------------------------------------------------------------------------- | 65 // Java and JavaScript |
66 /** | 66 //-------------------------------------------------------------------------- |
67 * <p>Escapes the characters in a <code>String</code> using Java String rule
s.</p> | 67 |
68 * | 68 /** |
69 * <p>Deals correctly with quotes and control-chars (tab, backslash, cr, ff,
etc.) </p> | 69 * <p>Escapes the characters in a <code>String</code> using Java String rules.
</p> |
70 * | 70 * |
71 * <p>So a tab becomes the characters <code>'\\'</code> and | 71 * <p>Deals correctly with quotes and control-chars (tab, backslash, cr, ff, e
tc.) </p> |
72 * <code>'t'</code>.</p> | 72 * |
73 * | 73 * <p>So a tab becomes the characters <code>'\\'</code> and |
74 * <p>The only difference between Java strings and JavaScript strings | 74 * <code>'t'</code>.</p> |
75 * is that in JavaScript, a single quote must be escaped.</p> | 75 * |
76 * | 76 * <p>The only difference between Java strings and JavaScript strings |
77 * <p>Example: | 77 * is that in JavaScript, a single quote must be escaped.</p> |
78 * <pre> | 78 * |
79 * input string: He didn't say, "Stop!" | 79 * <p>Example: |
80 * output string: He didn't say, \"Stop!\" | 80 * <pre> |
81 * </pre> | 81 * input string: He didn't say, "Stop!" |
82 * </p> | 82 * output string: He didn't say, \"Stop!\" |
83 * | 83 * </pre> |
84 * @param str String to escape values in, may be null | 84 * </p> |
85 * @return String with escaped values, <code>null</code> if null string inpu
t | 85 * |
86 */ | 86 * @param str String to escape values in, may be null |
87 public static String escapeJava(String str) { | 87 * @return String with escaped values, <code>null</code> if null string input |
88 return escapeJavaStyleString(str, false); | 88 */ |
89 } | 89 public static String escapeJava(String str) |
90 | 90 { |
91 /** | 91 return escapeJavaStyleString(str, false); |
92 * <p>Escapes the characters in a <code>String</code> using Java String rule
s to | 92 } |
93 * a <code>Writer</code>.</p> | 93 |
94 * | 94 /** |
95 * <p>A <code>null</code> string input has no effect.</p> | 95 * <p>Escapes the characters in a <code>String</code> using Java String rules
to |
96 * | 96 * a <code>Writer</code>.</p> |
97 * @see #escapeJava(java.lang.String) | 97 * |
98 * @param out Writer to write escaped string into | 98 * <p>A <code>null</code> string input has no effect.</p> |
99 * @param str String to escape values in, may be null | 99 * |
100 * @throws IllegalArgumentException if the Writer is <code>null</code> | 100 * @see #escapeJava(java.lang.String) |
101 * @throws IOException if error occurs on underlying Writer | 101 * @param out Writer to write escaped string into |
102 */ | 102 * @param str String to escape values in, may be null |
103 public static void escapeJava(Writer out, String str) throws IOException { | 103 * @throws IllegalArgumentException if the Writer is <code>null</code> |
104 escapeJavaStyleString(out, str, false); | 104 * @throws IOException if error occurs on underlying Writer |
105 } | 105 */ |
106 | 106 public static void escapeJava(Writer out, String str) throws IOException |
107 /** | 107 { |
108 * <p>Escapes the characters in a <code>String</code> using JavaScript Strin
g rules.</p> | 108 escapeJavaStyleString(out, str, false); |
109 * <p>Escapes any values it finds into their JavaScript String form. | 109 } |
110 * Deals correctly with quotes and control-chars (tab, backslash, cr, ff, et
c.) </p> | 110 |
111 * | 111 /** |
112 * <p>So a tab becomes the characters <code>'\\'</code> and | 112 * <p>Escapes the characters in a <code>String</code> using JavaScript String
rules.</p> |
113 * <code>'t'</code>.</p> | 113 * <p>Escapes any values it finds into their JavaScript String form. |
114 * | 114 * Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.
) </p> |
115 * <p>The only difference between Java strings and JavaScript strings | 115 * |
116 * is that in JavaScript, a single quote must be escaped.</p> | 116 * <p>So a tab becomes the characters <code>'\\'</code> and |
117 * | 117 * <code>'t'</code>.</p> |
118 * <p>Example: | 118 * |
119 * <pre> | 119 * <p>The only difference between Java strings and JavaScript strings |
120 * input string: He didn't say, "Stop!" | 120 * is that in JavaScript, a single quote must be escaped.</p> |
121 * output string: He didn\'t say, \"Stop!\" | 121 * |
122 * </pre> | 122 * <p>Example: |
123 * </p> | 123 * <pre> |
124 * | 124 * input string: He didn't say, "Stop!" |
125 * @param str String to escape values in, may be null | 125 * output string: He didn\'t say, \"Stop!\" |
126 * @return String with escaped values, <code>null</code> if null string inpu
t | 126 * </pre> |
127 */ | 127 * </p> |
128 public static String escapeJavaScript(String str) { | 128 * |
129 return escapeJavaStyleString(str, true); | 129 * @param str String to escape values in, may be null |
130 } | 130 * @return String with escaped values, <code>null</code> if null string input |
131 | 131 */ |
132 /** | 132 public static String escapeJavaScript(String str) |
133 * <p>Escapes the characters in a <code>String</code> using JavaScript Strin
g rules | 133 { |
134 * to a <code>Writer</code>.</p> | 134 return escapeJavaStyleString(str, true); |
135 * | 135 } |
136 * <p>A <code>null</code> string input has no effect.</p> | 136 |
137 * | 137 /** |
138 * @see #escapeJavaScript(java.lang.String) | 138 * <p>Escapes the characters in a <code>String</code> using JavaScript String
rules |
139 * @param out Writer to write escaped string into | 139 * to a <code>Writer</code>.</p> |
140 * @param str String to escape values in, may be null | 140 * |
141 * @throws IllegalArgumentException if the Writer is <code>null</code> | 141 * <p>A <code>null</code> string input has no effect.</p> |
142 * @throws IOException if error occurs on underlying Writer | 142 * |
143 **/ | 143 * @see #escapeJavaScript(java.lang.String) |
144 public static void escapeJavaScript(Writer out, String str) throws IOExcepti
on { | 144 * @param out Writer to write escaped string into |
145 escapeJavaStyleString(out, str, true); | 145 * @param str String to escape values in, may be null |
146 } | 146 * @throws IllegalArgumentException if the Writer is <code>null</code> |
147 | 147 * @throws IOException if error occurs on underlying Writer |
148 /** | 148 */ |
149 * <p>Worker method for the {@link #escapeJavaScript(String)} method.</p> | 149 public static void escapeJavaScript(Writer out, String str) throws IOException |
150 * | 150 { |
151 * @param str String to escape values in, may be null | 151 escapeJavaStyleString(out, str, true); |
152 * @param escapeSingleQuotes escapes single quotes if <code>true</code> | 152 } |
153 * @return the escaped string | 153 |
154 */ | 154 /** |
155 private static String escapeJavaStyleString(String str, boolean escapeSingle
Quotes) { | 155 * <p>Worker method for the {@link #escapeJavaScript(String)} method.</p> |
156 if (str == null) { | 156 * |
157 return null; | 157 * @param str String to escape values in, may be null |
| 158 * @param escapeSingleQuotes escapes single quotes if <code>true</code> |
| 159 * @return the escaped string |
| 160 */ |
| 161 private static String escapeJavaStyleString(String str, boolean escapeSingleQu
otes) |
| 162 { |
| 163 if (str == null) |
| 164 { |
| 165 return null; |
| 166 } |
| 167 try |
| 168 { |
| 169 StringWriter writer = new StringWriter(str.length() * 2); |
| 170 escapeJavaStyleString(writer, str, escapeSingleQuotes); |
| 171 return writer.toString(); |
| 172 } |
| 173 catch (IOException ioe) |
| 174 { |
| 175 // this should never ever happen while writing to a StringWriter |
| 176 ioe.printStackTrace(); |
| 177 return null; |
| 178 } |
| 179 } |
| 180 |
| 181 /** |
| 182 * <p>Worker method for the {@link #escapeJavaScript(String)} method.</p> |
| 183 * |
| 184 * @param out write to receieve the escaped string |
| 185 * @param str String to escape values in, may be null |
| 186 * @param escapeSingleQuote escapes single quotes if <code>true</code> |
| 187 * @throws IOException if an IOException occurs |
| 188 */ |
| 189 private static void escapeJavaStyleString(Writer out, String str, boolean esca
peSingleQuote) throws IOException |
| 190 { |
| 191 if (out == null) |
| 192 { |
| 193 throw new IllegalArgumentException("The Writer must not be null"); |
| 194 } |
| 195 if (str == null) |
| 196 { |
| 197 return; |
| 198 } |
| 199 int sz; |
| 200 sz = str.length(); |
| 201 for (int i = 0; i < sz; i++) |
| 202 { |
| 203 char ch = str.charAt(i); |
| 204 |
| 205 // handle unicode |
| 206 if (ch > 0xfff) |
| 207 { |
| 208 out.write("\\u" + hex(ch)); |
| 209 } else if (ch > 0xff) |
| 210 { |
| 211 out.write("\\u0" + hex(ch)); |
| 212 } else if (ch > 0x7f) |
| 213 { |
| 214 out.write("\\u00" + hex(ch)); |
| 215 } else if (ch < 32) |
| 216 { |
| 217 switch (ch) |
| 218 { |
| 219 case '\b': |
| 220 out.write('\\'); |
| 221 out.write('b'); |
| 222 break; |
| 223 case '\n': |
| 224 out.write('\\'); |
| 225 out.write('n'); |
| 226 break; |
| 227 case '\t': |
| 228 out.write('\\'); |
| 229 out.write('t'); |
| 230 break; |
| 231 case '\f': |
| 232 out.write('\\'); |
| 233 out.write('f'); |
| 234 break; |
| 235 case '\r': |
| 236 out.write('\\'); |
| 237 out.write('r'); |
| 238 break; |
| 239 default: |
| 240 if (ch > 0xf) |
| 241 { |
| 242 out.write("\\u00" + hex(ch)); |
| 243 } else |
| 244 { |
| 245 out.write("\\u000" + hex(ch)); |
| 246 } |
| 247 break; |
158 } | 248 } |
159 try { | 249 } else |
160 StringWriter writer = new StringWriter(str.length() * 2); | 250 { |
161 escapeJavaStyleString(writer, str, escapeSingleQuotes); | 251 switch (ch) |
162 return writer.toString(); | 252 { |
163 } catch (IOException ioe) { | 253 case '\'': |
164 // this should never ever happen while writing to a StringWriter | 254 if (escapeSingleQuote) |
165 ioe.printStackTrace(); | 255 { |
166 return null; | 256 out.write('\\'); |
| 257 } |
| 258 out.write('\''); |
| 259 break; |
| 260 case '"': |
| 261 out.write('\\'); |
| 262 out.write('"'); |
| 263 break; |
| 264 case '\\': |
| 265 out.write('\\'); |
| 266 out.write('\\'); |
| 267 break; |
| 268 case '/': |
| 269 out.write('\\'); |
| 270 out.write('/'); |
| 271 break; |
| 272 default: |
| 273 out.write(ch); |
| 274 break; |
167 } | 275 } |
168 } | 276 } |
169 | 277 } |
170 /** | 278 } |
171 * <p>Worker method for the {@link #escapeJavaScript(String)} method.</p> | 279 |
172 * | 280 /** |
173 * @param out write to receieve the escaped string | 281 * <p>Returns an upper case hexadecimal <code>String</code> for the given |
174 * @param str String to escape values in, may be null | 282 * character.</p> |
175 * @param escapeSingleQuote escapes single quotes if <code>true</code> | 283 * |
176 * @throws IOException if an IOException occurs | 284 * @param ch The character to convert. |
177 */ | 285 * @return An upper case hexadecimal <code>String</code> |
178 private static void escapeJavaStyleString(Writer out, String str, boolean es
capeSingleQuote) throws IOException { | 286 */ |
179 if (out == null) { | 287 private static String hex(char ch) |
180 throw new IllegalArgumentException("The Writer must not be null"); | 288 { |
| 289 return Integer.toHexString(ch).toUpperCase(); |
| 290 } |
| 291 |
| 292 /** |
| 293 * <p>Unescapes any Java literals found in the <code>String</code>. |
| 294 * For example, it will turn a sequence of <code>'\'</code> and |
| 295 * <code>'n'</code> into a newline character, unless the <code>'\'</code> |
| 296 * is preceded by another <code>'\'</code>.</p> |
| 297 * |
| 298 * @param str the <code>String</code> to unescape, may be null |
| 299 * @return a new unescaped <code>String</code>, <code>null</code> if null stri
ng input |
| 300 */ |
| 301 public static String unescapeJava(String str) |
| 302 { |
| 303 if (str == null) |
| 304 { |
| 305 return null; |
| 306 } |
| 307 try |
| 308 { |
| 309 StringWriter writer = new StringWriter(str.length()); |
| 310 unescapeJava(writer, str); |
| 311 return writer.toString(); |
| 312 } catch (IOException ioe) |
| 313 { |
| 314 // this should never ever happen while writing to a StringWriter |
| 315 ioe.printStackTrace(); |
| 316 return null; |
| 317 } |
| 318 } |
| 319 |
| 320 /** |
| 321 * <p>Unescapes any Java literals found in the <code>String</code> to a |
| 322 * <code>Writer</code>.</p> |
| 323 * |
| 324 * <p>For example, it will turn a sequence of <code>'\'</code> and |
| 325 * <code>'n'</code> into a newline character, unless the <code>'\'</code> |
| 326 * is preceded by another <code>'\'</code>.</p> |
| 327 * |
| 328 * <p>A <code>null</code> string input has no effect.</p> |
| 329 * |
| 330 * @param out the <code>Writer</code> used to output unescaped characters |
| 331 * @param str the <code>String</code> to unescape, may be null |
| 332 * @throws IllegalArgumentException if the Writer is <code>null</code> |
| 333 * @throws IOException if error occurs on underlying Writer |
| 334 */ |
| 335 public static void unescapeJava(Writer out, String str) throws IOException |
| 336 { |
| 337 if (out == null) |
| 338 { |
| 339 throw new IllegalArgumentException("The Writer must not be null"); |
| 340 } |
| 341 if (str == null) |
| 342 { |
| 343 return; |
| 344 } |
| 345 int sz = str.length(); |
| 346 StringBuffer unicode = new StringBuffer(4); |
| 347 boolean hadSlash = false; |
| 348 boolean inUnicode = false; |
| 349 for (int i = 0; i < sz; i++) |
| 350 { |
| 351 char ch = str.charAt(i); |
| 352 if (inUnicode) |
| 353 { |
| 354 // if in unicode, then we're reading unicode |
| 355 // values in somehow |
| 356 unicode.append(ch); |
| 357 if (unicode.length() == 4) |
| 358 { |
| 359 // unicode now contains the four hex digits |
| 360 // which represents our unicode character |
| 361 try |
| 362 { |
| 363 int value = Integer.parseInt(unicode.toString(), 16); |
| 364 out.write((char) value); |
| 365 unicode.setLength(0); |
| 366 inUnicode = false; |
| 367 hadSlash = false; |
| 368 } catch (NumberFormatException nfe) |
| 369 { |
| 370 throw (IOException) new IOException("Unable to parse unicode value:
" + unicode).initCause(nfe); |
| 371 } |
181 } | 372 } |
182 if (str == null) { | 373 continue; |
183 return; | 374 } |
| 375 if (hadSlash) |
| 376 { |
| 377 // handle an escaped value |
| 378 hadSlash = false; |
| 379 switch (ch) |
| 380 { |
| 381 case '\\': |
| 382 out.write('\\'); |
| 383 break; |
| 384 case '\'': |
| 385 out.write('\''); |
| 386 break; |
| 387 case '\"': |
| 388 out.write('"'); |
| 389 break; |
| 390 case 'r': |
| 391 out.write('\r'); |
| 392 break; |
| 393 case 'f': |
| 394 out.write('\f'); |
| 395 break; |
| 396 case 't': |
| 397 out.write('\t'); |
| 398 break; |
| 399 case 'n': |
| 400 out.write('\n'); |
| 401 break; |
| 402 case 'b': |
| 403 out.write('\b'); |
| 404 break; |
| 405 case 'u': |
| 406 { |
| 407 // uh-oh, we're in unicode country.... |
| 408 inUnicode = true; |
| 409 break; |
| 410 } |
| 411 default: |
| 412 out.write(ch); |
| 413 break; |
184 } | 414 } |
185 int sz; | 415 continue; |
186 sz = str.length(); | 416 } else if (ch == '\\') |
187 for (int i = 0; i < sz; i++) { | 417 { |
188 char ch = str.charAt(i); | 418 hadSlash = true; |
189 | 419 continue; |
190 // handle unicode | 420 } |
191 if (ch > 0xfff) { | 421 out.write(ch); |
192 out.write("\\u" + hex(ch)); | 422 } |
193 } else if (ch > 0xff) { | 423 if (hadSlash) |
194 out.write("\\u0" + hex(ch)); | 424 { |
195 } else if (ch > 0x7f) { | 425 // then we're in the weird case of a \ at the end of the |
196 out.write("\\u00" + hex(ch)); | 426 // string, let's output it anyway. |
197 } else if (ch < 32) { | 427 out.write('\\'); |
198 switch (ch) { | 428 } |
199 case '\b': | 429 } |
200 out.write('\\'); | 430 |
201 out.write('b'); | 431 /** |
202 break; | 432 * <p>Unescapes any JavaScript literals found in the <code>String</code>.</p> |
203 case '\n': | 433 * |
204 out.write('\\'); | 434 * <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'</
code> |
205 out.write('n'); | 435 * into a newline character, unless the <code>'\'</code> is preceded by anothe
r |
206 break; | 436 * <code>'\'</code>.</p> |
207 case '\t': | 437 * |
208 out.write('\\'); | 438 * @see #unescapeJava(String) |
209 out.write('t'); | 439 * @param str the <code>String</code> to unescape, may be null |
210 break; | 440 * @return A new unescaped <code>String</code>, <code>null</code> if null stri
ng input |
211 case '\f': | 441 */ |
212 out.write('\\'); | 442 public static String unescapeJavaScript(String str) |
213 out.write('f'); | 443 { |
214 break; | 444 return unescapeJava(str); |
215 case '\r': | 445 } |
216 out.write('\\'); | 446 |
217 out.write('r'); | 447 /** |
218 break; | 448 * <p>Unescapes any JavaScript literals found in the <code>String</code> to a |
219 default : | 449 * <code>Writer</code>.</p> |
220 if (ch > 0xf) { | 450 * |
221 out.write("\\u00" + hex(ch)); | 451 * <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'</
code> |
222 } else { | 452 * into a newline character, unless the <code>'\'</code> is preceded by anothe
r |
223 out.write("\\u000" + hex(ch)); | 453 * <code>'\'</code>.</p> |
224 } | 454 * |
225 break; | 455 * <p>A <code>null</code> string input has no effect.</p> |
226 } | 456 * |
227 } else { | 457 * @see #unescapeJava(Writer, String) |
228 switch (ch) { | 458 * @param out the <code>Writer</code> used to output unescaped characters |
229 case '\'': | 459 * @param str the <code>String</code> to unescape, may be null |
230 if (escapeSingleQuote) { | 460 * @throws IllegalArgumentException if the Writer is <code>null</code> |
231 out.write('\\'); | 461 * @throws IOException if error occurs on underlying Writer |
232 } | 462 */ |
233 out.write('\''); | 463 public static void unescapeJavaScript(Writer out, String str) throws IOExcepti
on |
234 break; | 464 { |
235 case '"': | 465 unescapeJava(out, str); |
236 out.write('\\'); | 466 } |
237 out.write('"'); | 467 |
238 break; | 468 //----------------------------------------------------------------------- |
239 case '\\': | 469 |
240 out.write('\\'); | 470 /** |
241 out.write('\\'); | 471 * <p>Escapes the characters in a <code>String</code> to be suitable to pass t
o |
242 break; | 472 * an SQL query.</p> |
243 case '/': | 473 * |
244 out.write('\\'); | 474 * <p>For example, |
245 out.write('/'); | 475 * <pre>statement.executeQuery("SELECT * FROM MOVIES WHERE TITLE='" + |
246 break; | 476 * StringEscapeUtils.escapeSql("McHale's Navy") + |
247 default : | 477 * "'");</pre> |
248 out.write(ch); | 478 * </p> |
249 break; | 479 * |
250 } | 480 * <p>At present, this method only turns single-quotes into doubled single-quo
tes |
251 } | 481 * (<code>"McHale's Navy"</code> => <code>"McHale''s Navy"</code>). It does no
t |
252 } | 482 * handle the cases of percent (%) or underscore (_) for use in LIKE clauses.<
/p> |
253 } | 483 * |
254 | 484 * see http://www.jguru.com/faq/view.jsp?EID=8881 |
255 /** | 485 * |
256 * <p>Returns an upper case hexadecimal <code>String</code> for the given | 486 * @param str the string to escape, may be null |
257 * character.</p> | 487 * @return a new String, escaped for SQL, <code>null</code> if null string inp
ut |
258 * | 488 */ |
259 * @param ch The character to convert. | 489 public static String escapeSql(String str) |
260 * @return An upper case hexadecimal <code>String</code> | 490 { |
261 */ | 491 if (str == null) |
262 private static String hex(char ch) { | 492 { |
263 return Integer.toHexString(ch).toUpperCase(); | 493 return null; |
264 } | 494 } |
265 | 495 return StringUtils.replace(str, "'", "''"); |
266 /** | 496 } |
267 * <p>Unescapes any Java literals found in the <code>String</code>. | 497 |
268 * For example, it will turn a sequence of <code>'\'</code> and | 498 //----------------------------------------------------------------------- |
269 * <code>'n'</code> into a newline character, unless the <code>'\'</code> | 499 |
270 * is preceded by another <code>'\'</code>.</p> | 500 /** |
271 * | 501 * <p>Returns a <code>String</code> value for a CSV column enclosed in double
quotes, |
272 * @param str the <code>String</code> to unescape, may be null | 502 * if required.</p> |
273 * @return a new unescaped <code>String</code>, <code>null</code> if null st
ring input | 503 * |
274 */ | 504 * <p>If the value contains a comma, newline or double quote, then the |
275 public static String unescapeJava(String str) { | 505 * String value is returned enclosed in double quotes.</p> |
276 if (str == null) { | 506 * </p> |
277 return null; | 507 * |
278 } | 508 * <p>Any double quote characters in the value are escaped with another double
quote.</p> |
279 try { | 509 * |
280 StringWriter writer = new StringWriter(str.length()); | 510 * <p>If the value does not contain a comma, newline or double quote, then the |
281 unescapeJava(writer, str); | 511 * String value is returned unchanged.</p> |
282 return writer.toString(); | 512 * </p> |
283 } catch (IOException ioe) { | 513 * |
284 // this should never ever happen while writing to a StringWriter | 514 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia
</a> and |
285 ioe.printStackTrace(); | 515 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. |
286 return null; | 516 * |
287 } | 517 * @param str the input CSV column String, may be null |
288 } | 518 * @return the input String, enclosed in double quotes if the value contains a
comma, |
289 | 519 * newline or double quote, <code>null</code> if null string input |
290 /** | 520 * @since 2.4 |
291 * <p>Unescapes any Java literals found in the <code>String</code> to a | 521 */ |
292 * <code>Writer</code>.</p> | 522 public static String escapeCsv(String str) |
293 * | 523 { |
294 * <p>For example, it will turn a sequence of <code>'\'</code> and | 524 if (StringUtils.containsNone(str, CSV_SEARCH_CHARS)) |
295 * <code>'n'</code> into a newline character, unless the <code>'\'</code> | 525 { |
296 * is preceded by another <code>'\'</code>.</p> | 526 return str; |
297 * | 527 } |
298 * <p>A <code>null</code> string input has no effect.</p> | 528 try |
299 * | 529 { |
300 * @param out the <code>Writer</code> used to output unescaped characters | 530 StringWriter writer = new StringWriter(); |
301 * @param str the <code>String</code> to unescape, may be null | 531 escapeCsv(writer, str); |
302 * @throws IllegalArgumentException if the Writer is <code>null</code> | 532 return writer.toString(); |
303 * @throws IOException if error occurs on underlying Writer | 533 } catch (IOException ioe) |
304 */ | 534 { |
305 public static void unescapeJava(Writer out, String str) throws IOException { | 535 // this should never ever happen while writing to a StringWriter |
306 if (out == null) { | 536 ioe.printStackTrace(); |
307 throw new IllegalArgumentException("The Writer must not be null"); | 537 return null; |
308 } | 538 } |
309 if (str == null) { | 539 } |
310 return; | 540 |
311 } | 541 /** |
312 int sz = str.length(); | 542 * <p>Writes a <code>String</code> value for a CSV column enclosed in double q
uotes, |
313 StringBuffer unicode = new StringBuffer(4); | 543 * if required.</p> |
314 boolean hadSlash = false; | 544 * |
315 boolean inUnicode = false; | 545 * <p>If the value contains a comma, newline or double quote, then the |
316 for (int i = 0; i < sz; i++) { | 546 * String value is written enclosed in double quotes.</p> |
317 char ch = str.charAt(i); | 547 * </p> |
318 if (inUnicode) { | 548 * |
319 // if in unicode, then we're reading unicode | 549 * <p>Any double quote characters in the value are escaped with another double
quote.</p> |
320 // values in somehow | 550 * |
321 unicode.append(ch); | 551 * <p>If the value does not contain a comma, newline or double quote, then the |
322 if (unicode.length() == 4) { | 552 * String value is written unchanged (null values are ignored).</p> |
323 // unicode now contains the four hex digits | 553 * </p> |
324 // which represents our unicode character | 554 * |
325 try { | 555 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia
</a> and |
326 int value = Integer.parseInt(unicode.toString(), 16); | 556 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. |
327 out.write((char) value); | 557 * |
328 unicode.setLength(0); | 558 * @param str the input CSV column String, may be null |
329 inUnicode = false; | 559 * @param out Writer to write input string to, enclosed in double quotes if it
contains |
330 hadSlash = false; | 560 * a comma, newline or double quote |
331 } catch (NumberFormatException nfe) { | 561 * @throws IOException if error occurs on underlying Writer |
332 throw (IOException) new IOException("Unable to parse uni
code value: " + unicode).initCause(nfe); | 562 * @since 2.4 |
333 } | 563 */ |
334 } | 564 public static void escapeCsv(Writer out, String str) throws IOException |
335 continue; | 565 { |
336 } | 566 if (StringUtils.containsNone(str, CSV_SEARCH_CHARS)) |
337 if (hadSlash) { | 567 { |
338 // handle an escaped value | 568 if (str != null) |
339 hadSlash = false; | 569 { |
340 switch (ch) { | |
341 case '\\': | |
342 out.write('\\'); | |
343 break; | |
344 case '\'': | |
345 out.write('\''); | |
346 break; | |
347 case '\"': | |
348 out.write('"'); | |
349 break; | |
350 case 'r': | |
351 out.write('\r'); | |
352 break; | |
353 case 'f': | |
354 out.write('\f'); | |
355 break; | |
356 case 't': | |
357 out.write('\t'); | |
358 break; | |
359 case 'n': | |
360 out.write('\n'); | |
361 break; | |
362 case 'b': | |
363 out.write('\b'); | |
364 break; | |
365 case 'u': | |
366 { | |
367 // uh-oh, we're in unicode country.... | |
368 inUnicode = true; | |
369 break; | |
370 } | |
371 default : | |
372 out.write(ch); | |
373 break; | |
374 } | |
375 continue; | |
376 } else if (ch == '\\') { | |
377 hadSlash = true; | |
378 continue; | |
379 } | |
380 out.write(ch); | |
381 } | |
382 if (hadSlash) { | |
383 // then we're in the weird case of a \ at the end of the | |
384 // string, let's output it anyway. | |
385 out.write('\\'); | |
386 } | |
387 } | |
388 | |
389 /** | |
390 * <p>Unescapes any JavaScript literals found in the <code>String</code>.</p
> | |
391 * | |
392 * <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'
</code> | |
393 * into a newline character, unless the <code>'\'</code> is preceded by anot
her | |
394 * <code>'\'</code>.</p> | |
395 * | |
396 * @see #unescapeJava(String) | |
397 * @param str the <code>String</code> to unescape, may be null | |
398 * @return A new unescaped <code>String</code>, <code>null</code> if null st
ring input | |
399 */ | |
400 public static String unescapeJavaScript(String str) { | |
401 return unescapeJava(str); | |
402 } | |
403 | |
404 /** | |
405 * <p>Unescapes any JavaScript literals found in the <code>String</code> to
a | |
406 * <code>Writer</code>.</p> | |
407 * | |
408 * <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'
</code> | |
409 * into a newline character, unless the <code>'\'</code> is preceded by anot
her | |
410 * <code>'\'</code>.</p> | |
411 * | |
412 * <p>A <code>null</code> string input has no effect.</p> | |
413 * | |
414 * @see #unescapeJava(Writer,String) | |
415 * @param out the <code>Writer</code> used to output unescaped characters | |
416 * @param str the <code>String</code> to unescape, may be null | |
417 * @throws IllegalArgumentException if the Writer is <code>null</code> | |
418 * @throws IOException if error occurs on underlying Writer | |
419 */ | |
420 public static void unescapeJavaScript(Writer out, String str) throws IOExcep
tion { | |
421 unescapeJava(out, str); | |
422 } | |
423 | |
424 //----------------------------------------------------------------------- | |
425 /** | |
426 * <p>Escapes the characters in a <code>String</code> to be suitable to pass
to | |
427 * an SQL query.</p> | |
428 * | |
429 * <p>For example, | |
430 * <pre>statement.executeQuery("SELECT * FROM MOVIES WHERE TITLE='" + | |
431 * StringEscapeUtils.escapeSql("McHale's Navy") + | |
432 * "'");</pre> | |
433 * </p> | |
434 * | |
435 * <p>At present, this method only turns single-quotes into doubled single-q
uotes | |
436 * (<code>"McHale's Navy"</code> => <code>"McHale''s Navy"</code>). It does
not | |
437 * handle the cases of percent (%) or underscore (_) for use in LIKE clauses
.</p> | |
438 * | |
439 * see http://www.jguru.com/faq/view.jsp?EID=8881 | |
440 * @param str the string to escape, may be null | |
441 * @return a new String, escaped for SQL, <code>null</code> if null string i
nput | |
442 */ | |
443 public static String escapeSql(String str) { | |
444 if (str == null) { | |
445 return null; | |
446 } | |
447 return StringUtils.replace(str, "'", "''"); | |
448 } | |
449 | |
450 //----------------------------------------------------------------------- | |
451 | |
452 /** | |
453 * <p>Returns a <code>String</code> value for a CSV column enclosed in doubl
e quotes, | |
454 * if required.</p> | |
455 * | |
456 * <p>If the value contains a comma, newline or double quote, then the | |
457 * String value is returned enclosed in double quotes.</p> | |
458 * </p> | |
459 * | |
460 * <p>Any double quote characters in the value are escaped with another doub
le quote.</p> | |
461 * | |
462 * <p>If the value does not contain a comma, newline or double quote, then t
he | |
463 * String value is returned unchanged.</p> | |
464 * </p> | |
465 * | |
466 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikiped
ia</a> and | |
467 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. | |
468 * | |
469 * @param str the input CSV column String, may be null | |
470 * @return the input String, enclosed in double quotes if the value contains
a comma, | |
471 * newline or double quote, <code>null</code> if null string input | |
472 * @since 2.4 | |
473 */ | |
474 public static String escapeCsv(String str) { | |
475 if (StringUtils.containsNone(str, CSV_SEARCH_CHARS)) { | |
476 return str; | |
477 } | |
478 try { | |
479 StringWriter writer = new StringWriter(); | |
480 escapeCsv(writer, str); | |
481 return writer.toString(); | |
482 } catch (IOException ioe) { | |
483 // this should never ever happen while writing to a StringWriter | |
484 ioe.printStackTrace(); | |
485 return null; | |
486 } | |
487 } | |
488 | |
489 /** | |
490 * <p>Writes a <code>String</code> value for a CSV column enclosed in double
quotes, | |
491 * if required.</p> | |
492 * | |
493 * <p>If the value contains a comma, newline or double quote, then the | |
494 * String value is written enclosed in double quotes.</p> | |
495 * </p> | |
496 * | |
497 * <p>Any double quote characters in the value are escaped with another doub
le quote.</p> | |
498 * | |
499 * <p>If the value does not contain a comma, newline or double quote, then t
he | |
500 * String value is written unchanged (null values are ignored).</p> | |
501 * </p> | |
502 * | |
503 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikiped
ia</a> and | |
504 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. | |
505 * | |
506 * @param str the input CSV column String, may be null | |
507 * @param out Writer to write input string to, enclosed in double quotes if
it contains | |
508 * a comma, newline or double quote | |
509 * @throws IOException if error occurs on underlying Writer | |
510 * @since 2.4 | |
511 */ | |
512 public static void escapeCsv(Writer out, String str) throws IOException { | |
513 if (StringUtils.containsNone(str, CSV_SEARCH_CHARS)) { | |
514 if (str != null) { | |
515 out.write(str); | |
516 } | |
517 return; | |
518 } | |
519 out.write(CSV_QUOTE); | |
520 for (int i = 0; i < str.length(); i++) { | |
521 char c = str.charAt(i); | |
522 if (c == CSV_QUOTE) { | |
523 out.write(CSV_QUOTE); // escape double quote | |
524 } | |
525 out.write(c); | |
526 } | |
527 out.write(CSV_QUOTE); | |
528 } | |
529 | |
530 /** | |
531 * <p>Returns a <code>String</code> value for an unescaped CSV column. </p> | |
532 * | |
533 * <p>If the value is enclosed in double quotes, and contains a comma, newli
ne | |
534 * or double quote, then quotes are removed. | |
535 * </p> | |
536 * | |
537 * <p>Any double quote escaped characters (a pair of double quotes) are unes
caped | |
538 * to just one double quote. </p> | |
539 * | |
540 * <p>If the value is not enclosed in double quotes, or is and does not cont
ain a | |
541 * comma, newline or double quote, then the String value is returned unch
anged.</p> | |
542 * </p> | |
543 * | |
544 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikiped
ia</a> and | |
545 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. | |
546 * | |
547 * @param str the input CSV column String, may be null | |
548 * @return the input String, with enclosing double quotes removed and embedd
ed double | |
549 * quotes unescaped, <code>null</code> if null string input | |
550 * @since 2.4 | |
551 */ | |
552 public static String unescapeCsv(String str) { | |
553 if (str == null) { | |
554 return null; | |
555 } | |
556 try { | |
557 StringWriter writer = new StringWriter(); | |
558 unescapeCsv(writer, str); | |
559 return writer.toString(); | |
560 } catch (IOException ioe) { | |
561 // this should never ever happen while writing to a StringWriter | |
562 ioe.printStackTrace(); | |
563 return null; | |
564 } | |
565 } | |
566 | |
567 /** | |
568 * <p>Returns a <code>String</code> value for an unescaped CSV column. </p> | |
569 * | |
570 * <p>If the value is enclosed in double quotes, and contains a comma, newli
ne | |
571 * or double quote, then quotes are removed. | |
572 * </p> | |
573 * | |
574 * <p>Any double quote escaped characters (a pair of double quotes) are unes
caped | |
575 * to just one double quote. </p> | |
576 * | |
577 * <p>If the value is not enclosed in double quotes, or is and does not cont
ain a | |
578 * comma, newline or double quote, then the String value is returned unch
anged.</p> | |
579 * </p> | |
580 * | |
581 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikiped
ia</a> and | |
582 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. | |
583 * | |
584 * @param str the input CSV column String, may be null | |
585 * @param out Writer to write the input String to, with enclosing double quo
tes | |
586 * removed and embedded double quotes unescaped, <code>null</code> if null s
tring input | |
587 * @throws IOException if error occurs on underlying Writer | |
588 * @since 2.4 | |
589 */ | |
590 public static void unescapeCsv(Writer out, String str) throws IOException { | |
591 if (str == null) { | |
592 return; | |
593 } | |
594 if (str.length() < 2) { | |
595 out.write(str); | |
596 return; | |
597 } | |
598 if ( str.charAt(0) != CSV_QUOTE || str.charAt(str.length() - 1) != CSV_Q
UOTE ) { | |
599 out.write(str); | |
600 return; | |
601 } | |
602 | |
603 // strip quotes | |
604 String quoteless = str.substring(1, str.length() - 1); | |
605 | |
606 if ( StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS) ) { | |
607 // deal with escaped quotes; ie) "" | |
608 str = StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR,
CSV_QUOTE_STR); | |
609 } | |
610 | |
611 out.write(str); | 570 out.write(str); |
612 } | 571 } |
| 572 return; |
| 573 } |
| 574 out.write(CSV_QUOTE); |
| 575 for (int i = 0; i < str.length(); i++) |
| 576 { |
| 577 char c = str.charAt(i); |
| 578 if (c == CSV_QUOTE) |
| 579 { |
| 580 out.write(CSV_QUOTE); // escape double quote |
| 581 } |
| 582 out.write(c); |
| 583 } |
| 584 out.write(CSV_QUOTE); |
| 585 } |
| 586 |
| 587 /** |
| 588 * <p>Returns a <code>String</code> value for an unescaped CSV column. </p> |
| 589 * |
| 590 * <p>If the value is enclosed in double quotes, and contains a comma, newline |
| 591 * or double quote, then quotes are removed. |
| 592 * </p> |
| 593 * |
| 594 * <p>Any double quote escaped characters (a pair of double quotes) are unesca
ped |
| 595 * to just one double quote. </p> |
| 596 * |
| 597 * <p>If the value is not enclosed in double quotes, or is and does not contai
n a |
| 598 * comma, newline or double quote, then the String value is returned unchanged
.</p> |
| 599 * </p> |
| 600 * |
| 601 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia
</a> and |
| 602 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. |
| 603 * |
| 604 * @param str the input CSV column String, may be null |
| 605 * @return the input String, with enclosing double quotes removed and embedded
double |
| 606 * quotes unescaped, <code>null</code> if null string input |
| 607 * @since 2.4 |
| 608 */ |
| 609 public static String unescapeCsv(String str) |
| 610 { |
| 611 if (str == null) |
| 612 { |
| 613 return null; |
| 614 } |
| 615 try |
| 616 { |
| 617 StringWriter writer = new StringWriter(); |
| 618 unescapeCsv(writer, str); |
| 619 return writer.toString(); |
| 620 } catch (IOException ioe) |
| 621 { |
| 622 // this should never ever happen while writing to a StringWriter |
| 623 ioe.printStackTrace(); |
| 624 return null; |
| 625 } |
| 626 } |
| 627 |
| 628 /** |
| 629 * <p>Returns a <code>String</code> value for an unescaped CSV column. </p> |
| 630 * |
| 631 * <p>If the value is enclosed in double quotes, and contains a comma, newline |
| 632 * or double quote, then quotes are removed. |
| 633 * </p> |
| 634 * |
| 635 * <p>Any double quote escaped characters (a pair of double quotes) are unesca
ped |
| 636 * to just one double quote. </p> |
| 637 * |
| 638 * <p>If the value is not enclosed in double quotes, or is and does not contai
n a |
| 639 * comma, newline or double quote, then the String value is returned unchanged
.</p> |
| 640 * </p> |
| 641 * |
| 642 * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia
</a> and |
| 643 * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>. |
| 644 * |
| 645 * @param str the input CSV column String, may be null |
| 646 * @param out Writer to write the input String to, with enclosing double quote
s |
| 647 * removed and embedded double quotes unescaped, <code>null</code> if null str
ing input |
| 648 * @throws IOException if error occurs on underlying Writer |
| 649 * @since 2.4 |
| 650 */ |
| 651 public static void unescapeCsv(Writer out, String str) throws IOException |
| 652 { |
| 653 if (str == null) |
| 654 { |
| 655 return; |
| 656 } |
| 657 if (str.length() < 2) |
| 658 { |
| 659 out.write(str); |
| 660 return; |
| 661 } |
| 662 if (str.charAt(0) != CSV_QUOTE || str.charAt(str.length() - 1) != CSV_QUOTE) |
| 663 { |
| 664 out.write(str); |
| 665 return; |
| 666 } |
| 667 |
| 668 // strip quotes |
| 669 String quoteless = str.substring(1, str.length() - 1); |
| 670 |
| 671 if (StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS)) |
| 672 { |
| 673 // deal with escaped quotes; ie) "" |
| 674 str = StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR, CSV_QU
OTE_STR); |
| 675 } |
| 676 |
| 677 out.write(str); |
| 678 } |
613 | 679 |
614 } | 680 } |
OLD | NEW |