J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2003-2006 Sun Microsystems, Inc. All Rights Reserved. |
| 3 | * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
| 4 | * |
| 5 | * This code is free software; you can redistribute it and/or modify it |
| 6 | * under the terms of the GNU General Public License version 2 only, as |
| 7 | * published by the Free Software Foundation. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun in the LICENSE file that accompanied this code. |
| 10 | * |
| 11 | * This code is distributed in the hope that it will be useful, but WITHOUT |
| 12 | * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
| 13 | * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
| 14 | * version 2 for more details (a copy is included in the LICENSE file that |
| 15 | * accompanied this code). |
| 16 | * |
| 17 | * You should have received a copy of the GNU General Public License version |
| 18 | * 2 along with this work; if not, write to the Free Software Foundation, |
| 19 | * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
| 20 | * |
| 21 | * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | package java.util; |
| 27 | |
| 28 | import java.util.regex.*; |
| 29 | import java.io.*; |
| 30 | import java.math.*; |
| 31 | import java.nio.*; |
| 32 | import java.nio.channels.*; |
| 33 | import java.nio.charset.*; |
| 34 | import java.text.*; |
| 35 | import java.util.Locale; |
| 36 | import sun.misc.LRUCache; |
| 37 | |
| 38 | /** |
| 39 | * A simple text scanner which can parse primitive types and strings using |
| 40 | * regular expressions. |
| 41 | * |
| 42 | * <p>A <code>Scanner</code> breaks its input into tokens using a |
| 43 | * delimiter pattern, which by default matches whitespace. The resulting |
| 44 | * tokens may then be converted into values of different types using the |
| 45 | * various <tt>next</tt> methods. |
| 46 | * |
| 47 | * <p>For example, this code allows a user to read a number from |
| 48 | * <tt>System.in</tt>: |
| 49 | * <blockquote><pre> |
| 50 | * Scanner sc = new Scanner(System.in); |
| 51 | * int i = sc.nextInt(); |
| 52 | * </pre></blockquote> |
| 53 | * |
| 54 | * <p>As another example, this code allows <code>long</code> types to be |
| 55 | * assigned from entries in a file <code>myNumbers</code>: |
| 56 | * <blockquote><pre> |
| 57 | * Scanner sc = new Scanner(new File("myNumbers")); |
| 58 | * while (sc.hasNextLong()) { |
| 59 | * long aLong = sc.nextLong(); |
| 60 | * }</pre></blockquote> |
| 61 | * |
| 62 | * <p>The scanner can also use delimiters other than whitespace. This |
| 63 | * example reads several items in from a string: |
| 64 | *<blockquote><pre> |
| 65 | * String input = "1 fish 2 fish red fish blue fish"; |
| 66 | * Scanner s = new Scanner(input).useDelimiter("\\s*fish\\s*"); |
| 67 | * System.out.println(s.nextInt()); |
| 68 | * System.out.println(s.nextInt()); |
| 69 | * System.out.println(s.next()); |
| 70 | * System.out.println(s.next()); |
| 71 | * s.close(); </pre></blockquote> |
| 72 | * <p> |
| 73 | * prints the following output: |
| 74 | * <blockquote><pre> |
| 75 | * 1 |
| 76 | * 2 |
| 77 | * red |
| 78 | * blue </pre></blockquote> |
| 79 | * |
| 80 | * <p>The same output can be generated with this code, which uses a regular |
| 81 | * expression to parse all four tokens at once: |
| 82 | *<blockquote><pre> |
| 83 | * String input = "1 fish 2 fish red fish blue fish"; |
| 84 | * Scanner s = new Scanner(input); |
| 85 | * s.findInLine("(\\d+) fish (\\d+) fish (\\w+) fish (\\w+)"); |
| 86 | * MatchResult result = s.match(); |
| 87 | * for (int i=1; i<=result.groupCount(); i++) |
| 88 | * System.out.println(result.group(i)); |
| 89 | * s.close(); </pre></blockquote> |
| 90 | * |
| 91 | * <p>The <a name="default-delimiter">default whitespace delimiter</a> used |
| 92 | * by a scanner is as recognized by {@link java.lang.Character}.{@link |
| 93 | * java.lang.Character#isWhitespace(char) isWhitespace}. The {@link #reset} |
| 94 | * method will reset the value of the scanner's delimiter to the default |
| 95 | * whitespace delimiter regardless of whether it was previously changed. |
| 96 | * |
| 97 | * <p>A scanning operation may block waiting for input. |
| 98 | * |
| 99 | * <p>The {@link #next} and {@link #hasNext} methods and their |
| 100 | * primitive-type companion methods (such as {@link #nextInt} and |
| 101 | * {@link #hasNextInt}) first skip any input that matches the delimiter |
| 102 | * pattern, and then attempt to return the next token. Both <tt>hasNext</tt> |
| 103 | * and <tt>next</tt> methods may block waiting for further input. Whether a |
| 104 | * <tt>hasNext</tt> method blocks has no connection to whether or not its |
| 105 | * associated <tt>next</tt> method will block. |
| 106 | * |
| 107 | * <p> The {@link #findInLine}, {@link #findWithinHorizon}, and {@link #skip} |
| 108 | * methods operate independently of the delimiter pattern. These methods will |
| 109 | * attempt to match the specified pattern with no regard to delimiters in the |
| 110 | * input and thus can be used in special circumstances where delimiters are |
| 111 | * not relevant. These methods may block waiting for more input. |
| 112 | * |
| 113 | * <p>When a scanner throws an {@link InputMismatchException}, the scanner |
| 114 | * will not pass the token that caused the exception, so that it may be |
| 115 | * retrieved or skipped via some other method. |
| 116 | * |
| 117 | * <p>Depending upon the type of delimiting pattern, empty tokens may be |
| 118 | * returned. For example, the pattern <tt>"\\s+"</tt> will return no empty |
| 119 | * tokens since it matches multiple instances of the delimiter. The delimiting |
| 120 | * pattern <tt>"\\s"</tt> could return empty tokens since it only passes one |
| 121 | * space at a time. |
| 122 | * |
| 123 | * <p> A scanner can read text from any object which implements the {@link |
| 124 | * java.lang.Readable} interface. If an invocation of the underlying |
| 125 | * readable's {@link java.lang.Readable#read} method throws an {@link |
| 126 | * java.io.IOException} then the scanner assumes that the end of the input |
| 127 | * has been reached. The most recent <tt>IOException</tt> thrown by the |
| 128 | * underlying readable can be retrieved via the {@link #ioException} method. |
| 129 | * |
| 130 | * <p>When a <code>Scanner</code> is closed, it will close its input source |
| 131 | * if the source implements the {@link java.io.Closeable} interface. |
| 132 | * |
| 133 | * <p>A <code>Scanner</code> is not safe for multithreaded use without |
| 134 | * external synchronization. |
| 135 | * |
| 136 | * <p>Unless otherwise mentioned, passing a <code>null</code> parameter into |
| 137 | * any method of a <code>Scanner</code> will cause a |
| 138 | * <code>NullPointerException</code> to be thrown. |
| 139 | * |
| 140 | * <p>A scanner will default to interpreting numbers as decimal unless a |
| 141 | * different radix has been set by using the {@link #useRadix} method. The |
| 142 | * {@link #reset} method will reset the value of the scanner's radix to |
| 143 | * <code>10</code> regardless of whether it was previously changed. |
| 144 | * |
| 145 | * <a name="localized-numbers"> |
| 146 | * <h4> Localized numbers </h4> |
| 147 | * |
| 148 | * <p> An instance of this class is capable of scanning numbers in the standard |
| 149 | * formats as well as in the formats of the scanner's locale. A scanner's |
| 150 | * <a name="initial-locale">initial locale </a>is the value returned by the {@link |
| 151 | * java.util.Locale#getDefault} method; it may be changed via the {@link |
| 152 | * #useLocale} method. The {@link #reset} method will reset the value of the |
| 153 | * scanner's locale to the initial locale regardless of whether it was |
| 154 | * previously changed. |
| 155 | * |
| 156 | * <p>The localized formats are defined in terms of the following parameters, |
| 157 | * which for a particular locale are taken from that locale's {@link |
| 158 | * java.text.DecimalFormat DecimalFormat} object, <tt>df</tt>, and its and |
| 159 | * {@link java.text.DecimalFormatSymbols DecimalFormatSymbols} object, |
| 160 | * <tt>dfs</tt>. |
| 161 | * |
| 162 | * <blockquote><table> |
| 163 | * <tr><td valign="top"><i>LocalGroupSeparator </i></td> |
| 164 | * <td valign="top">The character used to separate thousands groups, |
| 165 | * <i>i.e.,</i> <tt>dfs.</tt>{@link |
| 166 | * java.text.DecimalFormatSymbols#getGroupingSeparator |
| 167 | * getGroupingSeparator()}</td></tr> |
| 168 | * <tr><td valign="top"><i>LocalDecimalSeparator </i></td> |
| 169 | * <td valign="top">The character used for the decimal point, |
| 170 | * <i>i.e.,</i> <tt>dfs.</tt>{@link |
| 171 | * java.text.DecimalFormatSymbols#getDecimalSeparator |
| 172 | * getDecimalSeparator()}</td></tr> |
| 173 | * <tr><td valign="top"><i>LocalPositivePrefix </i></td> |
| 174 | * <td valign="top">The string that appears before a positive number (may |
| 175 | * be empty), <i>i.e.,</i> <tt>df.</tt>{@link |
| 176 | * java.text.DecimalFormat#getPositivePrefix |
| 177 | * getPositivePrefix()}</td></tr> |
| 178 | * <tr><td valign="top"><i>LocalPositiveSuffix </i></td> |
| 179 | * <td valign="top">The string that appears after a positive number (may be |
| 180 | * empty), <i>i.e.,</i> <tt>df.</tt>{@link |
| 181 | * java.text.DecimalFormat#getPositiveSuffix |
| 182 | * getPositiveSuffix()}</td></tr> |
| 183 | * <tr><td valign="top"><i>LocalNegativePrefix </i></td> |
| 184 | * <td valign="top">The string that appears before a negative number (may |
| 185 | * be empty), <i>i.e.,</i> <tt>df.</tt>{@link |
| 186 | * java.text.DecimalFormat#getNegativePrefix |
| 187 | * getNegativePrefix()}</td></tr> |
| 188 | * <tr><td valign="top"><i>LocalNegativeSuffix </i></td> |
| 189 | * <td valign="top">The string that appears after a negative number (may be |
| 190 | * empty), <i>i.e.,</i> <tt>df.</tt>{@link |
| 191 | * java.text.DecimalFormat#getNegativeSuffix |
| 192 | * getNegativeSuffix()}</td></tr> |
| 193 | * <tr><td valign="top"><i>LocalNaN </i></td> |
| 194 | * <td valign="top">The string that represents not-a-number for |
| 195 | * floating-point values, |
| 196 | * <i>i.e.,</i> <tt>dfs.</tt>{@link |
| 197 | * java.text.DecimalFormatSymbols#getNaN |
| 198 | * getNaN()}</td></tr> |
| 199 | * <tr><td valign="top"><i>LocalInfinity </i></td> |
| 200 | * <td valign="top">The string that represents infinity for floating-point |
| 201 | * values, <i>i.e.,</i> <tt>dfs.</tt>{@link |
| 202 | * java.text.DecimalFormatSymbols#getInfinity |
| 203 | * getInfinity()}</td></tr> |
| 204 | * </table></blockquote> |
| 205 | * |
| 206 | * <a name="number-syntax"> |
| 207 | * <h4> Number syntax </h4> |
| 208 | * |
| 209 | * <p> The strings that can be parsed as numbers by an instance of this class |
| 210 | * are specified in terms of the following regular-expression grammar, where |
| 211 | * Rmax is the highest digit in the radix being used (for example, Rmax is 9 |
| 212 | * in base 10). |
| 213 | * |
| 214 | * <p> |
| 215 | * <table cellspacing=0 cellpadding=0 align=center> |
| 216 | * |
| 217 | * <tr><td valign=top align=right><i>NonASCIIDigit</i> ::</td> |
| 218 | * <td valign=top>= A non-ASCII character c for which |
| 219 | * {@link java.lang.Character#isDigit Character.isDigit}<tt>(c)</tt> |
| 220 | * returns true</td></tr> |
| 221 | * |
| 222 | * <tr><td> </td></tr> |
| 223 | * |
| 224 | * <tr><td align=right><i>Non0Digit</i> ::</td> |
| 225 | * <td><tt>= [1-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr> |
| 226 | * |
| 227 | * <tr><td> </td></tr> |
| 228 | * |
| 229 | * <tr><td align=right><i>Digit</i> ::</td> |
| 230 | * <td><tt>= [0-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr> |
| 231 | * |
| 232 | * <tr><td> </td></tr> |
| 233 | * |
| 234 | * <tr><td valign=top align=right><i>GroupedNumeral</i> ::</td> |
| 235 | * <td valign=top> |
| 236 | * <table cellpadding=0 cellspacing=0> |
| 237 | * <tr><td><tt>= ( </tt></td> |
| 238 | * <td><i>Non0Digit</i><tt> |
| 239 | * </tt><i>Digit</i><tt>? |
| 240 | * </tt><i>Digit</i><tt>?</tt></td></tr> |
| 241 | * <tr><td></td> |
| 242 | * <td><tt>( </tt><i>LocalGroupSeparator</i><tt> |
| 243 | * </tt><i>Digit</i><tt> |
| 244 | * </tt><i>Digit</i><tt> |
| 245 | * </tt><i>Digit</i><tt> )+ )</tt></td></tr> |
| 246 | * </table></td></tr> |
| 247 | * |
| 248 | * <tr><td> </td></tr> |
| 249 | * |
| 250 | * <tr><td align=right><i>Numeral</i> ::</td> |
| 251 | * <td><tt>= ( ( </tt><i>Digit</i><tt>+ ) |
| 252 | * | </tt><i>GroupedNumeral</i><tt> )</tt></td></tr> |
| 253 | * |
| 254 | * <tr><td> </td></tr> |
| 255 | * |
| 256 | * <tr><td valign=top align=right> |
| 257 | * <a name="Integer-regex"><i>Integer</i> ::</td> |
| 258 | * <td valign=top><tt>= ( [-+]? ( </tt><i>Numeral</i><tt> |
| 259 | * ) )</tt></td></tr> |
| 260 | * <tr><td></td> |
| 261 | * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> </tt><i>Numeral</i><tt> |
| 262 | * </tt><i>LocalPositiveSuffix</i></td></tr> |
| 263 | * <tr><td></td> |
| 264 | * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> </tt><i>Numeral</i><tt> |
| 265 | * </tt><i>LocalNegativeSuffix</i></td></tr> |
| 266 | * |
| 267 | * <tr><td> </td></tr> |
| 268 | * |
| 269 | * <tr><td align=right><i>DecimalNumeral</i> ::</td> |
| 270 | * <td><tt>= </tt><i>Numeral</i></td></tr> |
| 271 | * <tr><td></td> |
| 272 | * <td><tt>| </tt><i>Numeral</i><tt> |
| 273 | * </tt><i>LocalDecimalSeparator</i><tt> |
| 274 | * </tt><i>Digit</i><tt>*</tt></td></tr> |
| 275 | * <tr><td></td> |
| 276 | * <td><tt>| </tt><i>LocalDecimalSeparator</i><tt> |
| 277 | * </tt><i>Digit</i><tt>+</tt></td></tr> |
| 278 | * |
| 279 | * <tr><td> </td></tr> |
| 280 | * |
| 281 | * <tr><td align=right><i>Exponent</i> ::</td> |
| 282 | * <td><tt>= ( [eE] [+-]? </tt><i>Digit</i><tt>+ )</tt></td></tr> |
| 283 | * |
| 284 | * <tr><td> </td></tr> |
| 285 | * |
| 286 | * <tr><td align=right> |
| 287 | * <a name="Decimal-regex"><i>Decimal</i> ::</td> |
| 288 | * <td><tt>= ( [-+]? </tt><i>DecimalNumeral</i><tt> |
| 289 | * </tt><i>Exponent</i><tt>? )</tt></td></tr> |
| 290 | * <tr><td></td> |
| 291 | * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> |
| 292 | * </tt><i>DecimalNumeral</i><tt> |
| 293 | * </tt><i>LocalPositiveSuffix</i> |
| 294 | * </tt><i>Exponent</i><tt>?</td></tr> |
| 295 | * <tr><td></td> |
| 296 | * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> |
| 297 | * </tt><i>DecimalNumeral</i><tt> |
| 298 | * </tt><i>LocalNegativeSuffix</i> |
| 299 | * </tt><i>Exponent</i><tt>?</td></tr> |
| 300 | * |
| 301 | * <tr><td> </td></tr> |
| 302 | * |
| 303 | * <tr><td align=right><i>HexFloat</i> ::</td> |
| 304 | * <td><tt>= [-+]? 0[xX][0-9a-fA-F]*\.[0-9a-fA-F]+ |
| 305 | * ([pP][-+]?[0-9]+)?</tt></td></tr> |
| 306 | * |
| 307 | * <tr><td> </td></tr> |
| 308 | * |
| 309 | * <tr><td align=right><i>NonNumber</i> ::</td> |
| 310 | * <td valign=top><tt>= NaN |
| 311 | * | </tt><i>LocalNan</i><tt> |
| 312 | * | Infinity |
| 313 | * | </tt><i>LocalInfinity</i></td></tr> |
| 314 | * |
| 315 | * <tr><td> </td></tr> |
| 316 | * |
| 317 | * <tr><td align=right><i>SignedNonNumber</i> ::</td> |
| 318 | * <td><tt>= ( [-+]? </tt><i>NonNumber</i><tt> )</tt></td></tr> |
| 319 | * <tr><td></td> |
| 320 | * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> |
| 321 | * </tt><i>NonNumber</i><tt> |
| 322 | * </tt><i>LocalPositiveSuffix</i></td></tr> |
| 323 | * <tr><td></td> |
| 324 | * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> |
| 325 | * </tt><i>NonNumber</i><tt> |
| 326 | * </tt><i>LocalNegativeSuffix</i></td></tr> |
| 327 | * |
| 328 | * <tr><td> </td></tr> |
| 329 | * |
| 330 | * <tr><td valign=top align=right> |
| 331 | * <a name="Float-regex"><i>Float</i> ::</td> |
| 332 | * <td valign=top><tt>= </tt><i>Decimal</i><tt></td></tr> |
| 333 | * <tr><td></td> |
| 334 | * <td><tt>| </tt><i>HexFloat</i><tt></td></tr> |
| 335 | * <tr><td></td> |
| 336 | * <td><tt>| </tt><i>SignedNonNumber</i><tt></td></tr> |
| 337 | * |
| 338 | * </table> |
| 339 | * </center> |
| 340 | * |
| 341 | * <p> Whitespace is not significant in the above regular expressions. |
| 342 | * |
| 343 | * @since 1.5 |
| 344 | */ |
| 345 | public final class Scanner implements Iterator<String> { |
| 346 | |
| 347 | // Internal buffer used to hold input |
| 348 | private CharBuffer buf; |
| 349 | |
| 350 | // Size of internal character buffer |
| 351 | private static final int BUFFER_SIZE = 1024; // change to 1024; |
| 352 | |
| 353 | // The index into the buffer currently held by the Scanner |
| 354 | private int position; |
| 355 | |
| 356 | // Internal matcher used for finding delimiters |
| 357 | private Matcher matcher; |
| 358 | |
| 359 | // Pattern used to delimit tokens |
| 360 | private Pattern delimPattern; |
| 361 | |
| 362 | // Pattern found in last hasNext operation |
| 363 | private Pattern hasNextPattern; |
| 364 | |
| 365 | // Position after last hasNext operation |
| 366 | private int hasNextPosition; |
| 367 | |
| 368 | // Result after last hasNext operation |
| 369 | private String hasNextResult; |
| 370 | |
| 371 | // The input source |
| 372 | private Readable source; |
| 373 | |
| 374 | // Boolean is true if source is done |
| 375 | private boolean sourceClosed = false; |
| 376 | |
| 377 | // Boolean indicating more input is required |
| 378 | private boolean needInput = false; |
| 379 | |
| 380 | // Boolean indicating if a delim has been skipped this operation |
| 381 | private boolean skipped = false; |
| 382 | |
| 383 | // A store of a position that the scanner may fall back to |
| 384 | private int savedScannerPosition = -1; |
| 385 | |
| 386 | // A cache of the last primitive type scanned |
| 387 | private Object typeCache = null; |
| 388 | |
| 389 | // Boolean indicating if a match result is available |
| 390 | private boolean matchValid = false; |
| 391 | |
| 392 | // Boolean indicating if this scanner has been closed |
| 393 | private boolean closed = false; |
| 394 | |
| 395 | // The current radix used by this scanner |
| 396 | private int radix = 10; |
| 397 | |
| 398 | // The default radix for this scanner |
| 399 | private int defaultRadix = 10; |
| 400 | |
| 401 | // The locale used by this scanner |
| 402 | private Locale locale = null; |
| 403 | |
| 404 | // A cache of the last few recently used Patterns |
| 405 | private LRUCache<String,Pattern> patternCache = |
| 406 | new LRUCache<String,Pattern>(7) { |
| 407 | protected Pattern create(String s) { |
| 408 | return Pattern.compile(s); |
| 409 | } |
| 410 | protected boolean hasName(Pattern p, String s) { |
| 411 | return p.pattern().equals(s); |
| 412 | } |
| 413 | }; |
| 414 | |
| 415 | // A holder of the last IOException encountered |
| 416 | private IOException lastException; |
| 417 | |
| 418 | // A pattern for java whitespace |
| 419 | private static Pattern WHITESPACE_PATTERN = Pattern.compile( |
| 420 | "\\p{javaWhitespace}+"); |
| 421 | |
| 422 | // A pattern for any token |
| 423 | private static Pattern FIND_ANY_PATTERN = Pattern.compile("(?s).*"); |
| 424 | |
| 425 | // A pattern for non-ASCII digits |
| 426 | private static Pattern NON_ASCII_DIGIT = Pattern.compile( |
| 427 | "[\\p{javaDigit}&&[^0-9]]"); |
| 428 | |
| 429 | // Fields and methods to support scanning primitive types |
| 430 | |
| 431 | /** |
| 432 | * Locale dependent values used to scan numbers |
| 433 | */ |
| 434 | private String groupSeparator = "\\,"; |
| 435 | private String decimalSeparator = "\\."; |
| 436 | private String nanString = "NaN"; |
| 437 | private String infinityString = "Infinity"; |
| 438 | private String positivePrefix = ""; |
| 439 | private String negativePrefix = "\\-"; |
| 440 | private String positiveSuffix = ""; |
| 441 | private String negativeSuffix = ""; |
| 442 | |
| 443 | /** |
| 444 | * Fields and an accessor method to match booleans |
| 445 | */ |
| 446 | private static volatile Pattern boolPattern; |
| 447 | private static final String BOOLEAN_PATTERN = "true|false"; |
| 448 | private static Pattern boolPattern() { |
| 449 | Pattern bp = boolPattern; |
| 450 | if (bp == null) |
| 451 | boolPattern = bp = Pattern.compile(BOOLEAN_PATTERN, |
| 452 | Pattern.CASE_INSENSITIVE); |
| 453 | return bp; |
| 454 | } |
| 455 | |
| 456 | /** |
| 457 | * Fields and methods to match bytes, shorts, ints, and longs |
| 458 | */ |
| 459 | private Pattern integerPattern; |
| 460 | private String digits = "0123456789abcdefghijklmnopqrstuvwxyz"; |
| 461 | private String non0Digit = "[\\p{javaDigit}&&[^0]]"; |
| 462 | private int SIMPLE_GROUP_INDEX = 5; |
| 463 | private String buildIntegerPatternString() { |
| 464 | String radixDigits = digits.substring(0, radix); |
| 465 | // \\p{javaDigit} is not guaranteed to be appropriate |
| 466 | // here but what can we do? The final authority will be |
| 467 | // whatever parse method is invoked, so ultimately the |
| 468 | // Scanner will do the right thing |
| 469 | String digit = "((?i)["+radixDigits+"]|\\p{javaDigit})"; |
| 470 | String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+ |
| 471 | groupSeparator+digit+digit+digit+")+)"; |
| 472 | // digit++ is the possessive form which is necessary for reducing |
| 473 | // backtracking that would otherwise cause unacceptable performance |
| 474 | String numeral = "(("+ digit+"++)|"+groupedNumeral+")"; |
| 475 | String javaStyleInteger = "([-+]?(" + numeral + "))"; |
| 476 | String negativeInteger = negativePrefix + numeral + negativeSuffix; |
| 477 | String positiveInteger = positivePrefix + numeral + positiveSuffix; |
| 478 | return "("+ javaStyleInteger + ")|(" + |
| 479 | positiveInteger + ")|(" + |
| 480 | negativeInteger + ")"; |
| 481 | } |
| 482 | private Pattern integerPattern() { |
| 483 | if (integerPattern == null) { |
| 484 | integerPattern = patternCache.forName(buildIntegerPatternString()); |
| 485 | } |
| 486 | return integerPattern; |
| 487 | } |
| 488 | |
| 489 | /** |
| 490 | * Fields and an accessor method to match line separators |
| 491 | */ |
| 492 | private static volatile Pattern separatorPattern; |
| 493 | private static volatile Pattern linePattern; |
| 494 | private static final String LINE_SEPARATOR_PATTERN = |
| 495 | "\r\n|[\n\r\u2028\u2029\u0085]"; |
| 496 | private static final String LINE_PATTERN = ".*("+LINE_SEPARATOR_PATTERN+")|.+$"; |
| 497 | |
| 498 | private static Pattern separatorPattern() { |
| 499 | Pattern sp = separatorPattern; |
| 500 | if (sp == null) |
| 501 | separatorPattern = sp = Pattern.compile(LINE_SEPARATOR_PATTERN); |
| 502 | return sp; |
| 503 | } |
| 504 | |
| 505 | private static Pattern linePattern() { |
| 506 | Pattern lp = linePattern; |
| 507 | if (lp == null) |
| 508 | linePattern = lp = Pattern.compile(LINE_PATTERN); |
| 509 | return lp; |
| 510 | } |
| 511 | |
| 512 | /** |
| 513 | * Fields and methods to match floats and doubles |
| 514 | */ |
| 515 | private Pattern floatPattern; |
| 516 | private Pattern decimalPattern; |
| 517 | private void buildFloatAndDecimalPattern() { |
| 518 | // \\p{javaDigit} may not be perfect, see above |
| 519 | String digit = "([0-9]|(\\p{javaDigit}))"; |
| 520 | String exponent = "([eE][+-]?"+digit+"+)?"; |
| 521 | String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+ |
| 522 | groupSeparator+digit+digit+digit+")+)"; |
| 523 | // Once again digit++ is used for performance, as above |
| 524 | String numeral = "(("+digit+"++)|"+groupedNumeral+")"; |
| 525 | String decimalNumeral = "("+numeral+"|"+numeral + |
| 526 | decimalSeparator + digit + "*+|"+ decimalSeparator + |
| 527 | digit + "++)"; |
| 528 | String nonNumber = "(NaN|"+nanString+"|Infinity|"+ |
| 529 | infinityString+")"; |
| 530 | String positiveFloat = "(" + positivePrefix + decimalNumeral + |
| 531 | positiveSuffix + exponent + ")"; |
| 532 | String negativeFloat = "(" + negativePrefix + decimalNumeral + |
| 533 | negativeSuffix + exponent + ")"; |
| 534 | String decimal = "(([-+]?" + decimalNumeral + exponent + ")|"+ |
| 535 | positiveFloat + "|" + negativeFloat + ")"; |
| 536 | String hexFloat = |
| 537 | "[-+]?0[xX][0-9a-fA-F]*\\.[0-9a-fA-F]+([pP][-+]?[0-9]+)?"; |
| 538 | String positiveNonNumber = "(" + positivePrefix + nonNumber + |
| 539 | positiveSuffix + ")"; |
| 540 | String negativeNonNumber = "(" + negativePrefix + nonNumber + |
| 541 | negativeSuffix + ")"; |
| 542 | String signedNonNumber = "(([-+]?"+nonNumber+")|" + |
| 543 | positiveNonNumber + "|" + |
| 544 | negativeNonNumber + ")"; |
| 545 | floatPattern = Pattern.compile(decimal + "|" + hexFloat + "|" + |
| 546 | signedNonNumber); |
| 547 | decimalPattern = Pattern.compile(decimal); |
| 548 | } |
| 549 | private Pattern floatPattern() { |
| 550 | if (floatPattern == null) { |
| 551 | buildFloatAndDecimalPattern(); |
| 552 | } |
| 553 | return floatPattern; |
| 554 | } |
| 555 | private Pattern decimalPattern() { |
| 556 | if (decimalPattern == null) { |
| 557 | buildFloatAndDecimalPattern(); |
| 558 | } |
| 559 | return decimalPattern; |
| 560 | } |
| 561 | |
| 562 | // Constructors |
| 563 | |
| 564 | /** |
| 565 | * Constructs a <code>Scanner</code> that returns values scanned |
| 566 | * from the specified source delimited by the specified pattern. |
| 567 | * |
| 568 | * @param source A character source implementing the Readable interface |
| 569 | * @param pattern A delimiting pattern |
| 570 | * @return A scanner with the specified source and pattern |
| 571 | */ |
| 572 | private Scanner(Readable source, Pattern pattern) { |
| 573 | if (source == null) |
| 574 | throw new NullPointerException("source"); |
| 575 | if (pattern == null) |
| 576 | throw new NullPointerException("pattern"); |
| 577 | this.source = source; |
| 578 | delimPattern = pattern; |
| 579 | buf = CharBuffer.allocate(BUFFER_SIZE); |
| 580 | buf.limit(0); |
| 581 | matcher = delimPattern.matcher(buf); |
| 582 | matcher.useTransparentBounds(true); |
| 583 | matcher.useAnchoringBounds(false); |
| 584 | useLocale(Locale.getDefault()); |
| 585 | } |
| 586 | |
| 587 | /** |
| 588 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 589 | * from the specified source. |
| 590 | * |
| 591 | * @param source A character source implementing the {@link Readable} |
| 592 | * interface |
| 593 | */ |
| 594 | public Scanner(Readable source) { |
| 595 | this(source, WHITESPACE_PATTERN); |
| 596 | } |
| 597 | |
| 598 | /** |
| 599 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 600 | * from the specified input stream. Bytes from the stream are converted |
| 601 | * into characters using the underlying platform's |
| 602 | * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. |
| 603 | * |
| 604 | * @param source An input stream to be scanned |
| 605 | */ |
| 606 | public Scanner(InputStream source) { |
| 607 | this(new InputStreamReader(source), WHITESPACE_PATTERN); |
| 608 | } |
| 609 | |
| 610 | /** |
| 611 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 612 | * from the specified input stream. Bytes from the stream are converted |
| 613 | * into characters using the specified charset. |
| 614 | * |
| 615 | * @param source An input stream to be scanned |
| 616 | * @param charsetName The encoding type used to convert bytes from the |
| 617 | * stream into characters to be scanned |
| 618 | * @throws IllegalArgumentException if the specified character set |
| 619 | * does not exist |
| 620 | */ |
| 621 | public Scanner(InputStream source, String charsetName) { |
| 622 | this(makeReadable(source, charsetName), WHITESPACE_PATTERN); |
| 623 | } |
| 624 | |
| 625 | private static Readable makeReadable(InputStream source, |
| 626 | String charsetName) |
| 627 | { |
| 628 | if (source == null) |
| 629 | throw new NullPointerException("source"); |
| 630 | InputStreamReader isr = null; |
| 631 | try { |
| 632 | isr = new InputStreamReader(source, charsetName); |
| 633 | } catch (UnsupportedEncodingException uee) { |
| 634 | IllegalArgumentException iae = new IllegalArgumentException(); |
| 635 | iae.initCause(uee); |
| 636 | throw iae; |
| 637 | } |
| 638 | return isr; |
| 639 | } |
| 640 | |
| 641 | /** |
| 642 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 643 | * from the specified file. Bytes from the file are converted into |
| 644 | * characters using the underlying platform's |
| 645 | * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. |
| 646 | * |
| 647 | * @param source A file to be scanned |
| 648 | * @throws FileNotFoundException if source is not found |
| 649 | */ |
| 650 | public Scanner(File source) |
| 651 | throws FileNotFoundException |
| 652 | { |
| 653 | this((ReadableByteChannel)(new FileInputStream(source).getChannel())); |
| 654 | } |
| 655 | |
| 656 | /** |
| 657 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 658 | * from the specified file. Bytes from the file are converted into |
| 659 | * characters using the specified charset. |
| 660 | * |
| 661 | * @param source A file to be scanned |
| 662 | * @param charsetName The encoding type used to convert bytes from the file |
| 663 | * into characters to be scanned |
| 664 | * @throws FileNotFoundException if source is not found |
| 665 | * @throws IllegalArgumentException if the specified encoding is |
| 666 | * not found |
| 667 | */ |
| 668 | public Scanner(File source, String charsetName) |
| 669 | throws FileNotFoundException |
| 670 | { |
| 671 | this((ReadableByteChannel)(new FileInputStream(source).getChannel()), |
| 672 | charsetName); |
| 673 | } |
| 674 | |
| 675 | /** |
| 676 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 677 | * from the specified string. |
| 678 | * |
| 679 | * @param source A string to scan |
| 680 | */ |
| 681 | public Scanner(String source) { |
| 682 | this(new StringReader(source), WHITESPACE_PATTERN); |
| 683 | } |
| 684 | |
| 685 | /** |
| 686 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 687 | * from the specified channel. Bytes from the source are converted into |
| 688 | * characters using the underlying platform's |
| 689 | * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. |
| 690 | * |
| 691 | * @param source A channel to scan |
| 692 | */ |
| 693 | public Scanner(ReadableByteChannel source) { |
| 694 | this(makeReadable(source), WHITESPACE_PATTERN); |
| 695 | } |
| 696 | |
| 697 | private static Readable makeReadable(ReadableByteChannel source) { |
| 698 | if (source == null) |
| 699 | throw new NullPointerException("source"); |
| 700 | String defaultCharsetName = |
| 701 | java.nio.charset.Charset.defaultCharset().name(); |
| 702 | return Channels.newReader(source, |
| 703 | java.nio.charset.Charset.defaultCharset().name()); |
| 704 | } |
| 705 | |
| 706 | /** |
| 707 | * Constructs a new <code>Scanner</code> that produces values scanned |
| 708 | * from the specified channel. Bytes from the source are converted into |
| 709 | * characters using the specified charset. |
| 710 | * |
| 711 | * @param source A channel to scan |
| 712 | * @param charsetName The encoding type used to convert bytes from the |
| 713 | * channel into characters to be scanned |
| 714 | * @throws IllegalArgumentException if the specified character set |
| 715 | * does not exist |
| 716 | */ |
| 717 | public Scanner(ReadableByteChannel source, String charsetName) { |
| 718 | this(makeReadable(source, charsetName), WHITESPACE_PATTERN); |
| 719 | } |
| 720 | |
| 721 | private static Readable makeReadable(ReadableByteChannel source, |
| 722 | String charsetName) |
| 723 | { |
| 724 | if (source == null) |
| 725 | throw new NullPointerException("source"); |
| 726 | if (!Charset.isSupported(charsetName)) |
| 727 | throw new IllegalArgumentException(charsetName); |
| 728 | return Channels.newReader(source, charsetName); |
| 729 | } |
| 730 | |
| 731 | // Private primitives used to support scanning |
| 732 | |
| 733 | private void saveState() { |
| 734 | savedScannerPosition = position; |
| 735 | } |
| 736 | |
| 737 | private void revertState() { |
| 738 | this.position = savedScannerPosition; |
| 739 | savedScannerPosition = -1; |
| 740 | skipped = false; |
| 741 | } |
| 742 | |
| 743 | private boolean revertState(boolean b) { |
| 744 | this.position = savedScannerPosition; |
| 745 | savedScannerPosition = -1; |
| 746 | skipped = false; |
| 747 | return b; |
| 748 | } |
| 749 | |
| 750 | private void cacheResult() { |
| 751 | hasNextResult = matcher.group(); |
| 752 | hasNextPosition = matcher.end(); |
| 753 | hasNextPattern = matcher.pattern(); |
| 754 | } |
| 755 | |
| 756 | private void cacheResult(String result) { |
| 757 | hasNextResult = result; |
| 758 | hasNextPosition = matcher.end(); |
| 759 | hasNextPattern = matcher.pattern(); |
| 760 | } |
| 761 | |
| 762 | // Clears both regular cache and type cache |
| 763 | private void clearCaches() { |
| 764 | hasNextPattern = null; |
| 765 | typeCache = null; |
| 766 | } |
| 767 | |
| 768 | // Also clears both the regular cache and the type cache |
| 769 | private String getCachedResult() { |
| 770 | position = hasNextPosition; |
| 771 | hasNextPattern = null; |
| 772 | typeCache = null; |
| 773 | return hasNextResult; |
| 774 | } |
| 775 | |
| 776 | // Also clears both the regular cache and the type cache |
| 777 | private void useTypeCache() { |
| 778 | if (closed) |
| 779 | throw new IllegalStateException("Scanner closed"); |
| 780 | position = hasNextPosition; |
| 781 | hasNextPattern = null; |
| 782 | typeCache = null; |
| 783 | } |
| 784 | |
| 785 | // Tries to read more input. May block. |
| 786 | private void readInput() { |
| 787 | if (buf.limit() == buf.capacity()) |
| 788 | makeSpace(); |
| 789 | |
| 790 | // Prepare to receive data |
| 791 | int p = buf.position(); |
| 792 | buf.position(buf.limit()); |
| 793 | buf.limit(buf.capacity()); |
| 794 | |
| 795 | int n = 0; |
| 796 | try { |
| 797 | n = source.read(buf); |
| 798 | } catch (IOException ioe) { |
| 799 | lastException = ioe; |
| 800 | n = -1; |
| 801 | } |
| 802 | |
| 803 | if (n == -1) { |
| 804 | sourceClosed = true; |
| 805 | needInput = false; |
| 806 | } |
| 807 | |
| 808 | if (n > 0) |
| 809 | needInput = false; |
| 810 | |
| 811 | // Restore current position and limit for reading |
| 812 | buf.limit(buf.position()); |
| 813 | buf.position(p); |
| 814 | } |
| 815 | |
| 816 | // After this method is called there will either be an exception |
| 817 | // or else there will be space in the buffer |
| 818 | private boolean makeSpace() { |
| 819 | clearCaches(); |
| 820 | int offset = savedScannerPosition == -1 ? |
| 821 | position : savedScannerPosition; |
| 822 | buf.position(offset); |
| 823 | // Gain space by compacting buffer |
| 824 | if (offset > 0) { |
| 825 | buf.compact(); |
| 826 | translateSavedIndexes(offset); |
| 827 | position -= offset; |
| 828 | buf.flip(); |
| 829 | return true; |
| 830 | } |
| 831 | // Gain space by growing buffer |
| 832 | int newSize = buf.capacity() * 2; |
| 833 | CharBuffer newBuf = CharBuffer.allocate(newSize); |
| 834 | newBuf.put(buf); |
| 835 | newBuf.flip(); |
| 836 | translateSavedIndexes(offset); |
| 837 | position -= offset; |
| 838 | buf = newBuf; |
| 839 | matcher.reset(buf); |
| 840 | return true; |
| 841 | } |
| 842 | |
| 843 | // When a buffer compaction/reallocation occurs the saved indexes must |
| 844 | // be modified appropriately |
| 845 | private void translateSavedIndexes(int offset) { |
| 846 | if (savedScannerPosition != -1) |
| 847 | savedScannerPosition -= offset; |
| 848 | } |
| 849 | |
| 850 | // If we are at the end of input then NoSuchElement; |
| 851 | // If there is still input left then InputMismatch |
| 852 | private void throwFor() { |
| 853 | skipped = false; |
| 854 | if ((sourceClosed) && (position == buf.limit())) |
| 855 | throw new NoSuchElementException(); |
| 856 | else |
| 857 | throw new InputMismatchException(); |
| 858 | } |
| 859 | |
| 860 | // Returns true if a complete token or partial token is in the buffer. |
| 861 | // It is not necessary to find a complete token since a partial token |
| 862 | // means that there will be another token with or without more input. |
| 863 | private boolean hasTokenInBuffer() { |
| 864 | matchValid = false; |
| 865 | matcher.usePattern(delimPattern); |
| 866 | matcher.region(position, buf.limit()); |
| 867 | |
| 868 | // Skip delims first |
| 869 | if (matcher.lookingAt()) |
| 870 | position = matcher.end(); |
| 871 | |
| 872 | // If we are sitting at the end, no more tokens in buffer |
| 873 | if (position == buf.limit()) |
| 874 | return false; |
| 875 | |
| 876 | return true; |
| 877 | } |
| 878 | |
| 879 | /* |
| 880 | * Returns a "complete token" that matches the specified pattern |
| 881 | * |
| 882 | * A token is complete if surrounded by delims; a partial token |
| 883 | * is prefixed by delims but not postfixed by them |
| 884 | * |
| 885 | * The position is advanced to the end of that complete token |
| 886 | * |
| 887 | * Pattern == null means accept any token at all |
| 888 | * |
| 889 | * Triple return: |
| 890 | * 1. valid string means it was found |
| 891 | * 2. null with needInput=false means we won't ever find it |
| 892 | * 3. null with needInput=true means try again after readInput |
| 893 | */ |
| 894 | private String getCompleteTokenInBuffer(Pattern pattern) { |
| 895 | matchValid = false; |
| 896 | |
| 897 | // Skip delims first |
| 898 | matcher.usePattern(delimPattern); |
| 899 | if (!skipped) { // Enforcing only one skip of leading delims |
| 900 | matcher.region(position, buf.limit()); |
| 901 | if (matcher.lookingAt()) { |
| 902 | // If more input could extend the delimiters then we must wait |
| 903 | // for more input |
| 904 | if (matcher.hitEnd() && !sourceClosed) { |
| 905 | needInput = true; |
| 906 | return null; |
| 907 | } |
| 908 | // The delims were whole and the matcher should skip them |
| 909 | skipped = true; |
| 910 | position = matcher.end(); |
| 911 | } |
| 912 | } |
| 913 | |
| 914 | // If we are sitting at the end, no more tokens in buffer |
| 915 | if (position == buf.limit()) { |
| 916 | if (sourceClosed) |
| 917 | return null; |
| 918 | needInput = true; |
| 919 | return null; |
| 920 | } |
| 921 | |
| 922 | // Must look for next delims. Simply attempting to match the |
| 923 | // pattern at this point may find a match but it might not be |
| 924 | // the first longest match because of missing input, or it might |
| 925 | // match a partial token instead of the whole thing. |
| 926 | |
| 927 | // Then look for next delims |
| 928 | matcher.region(position, buf.limit()); |
| 929 | boolean foundNextDelim = matcher.find(); |
| 930 | if (foundNextDelim && (matcher.end() == position)) { |
| 931 | // Zero length delimiter match; we should find the next one |
| 932 | // using the automatic advance past a zero length match; |
| 933 | // Otherwise we have just found the same one we just skipped |
| 934 | foundNextDelim = matcher.find(); |
| 935 | } |
| 936 | if (foundNextDelim) { |
| 937 | // In the rare case that more input could cause the match |
| 938 | // to be lost and there is more input coming we must wait |
| 939 | // for more input. Note that hitting the end is okay as long |
| 940 | // as the match cannot go away. It is the beginning of the |
| 941 | // next delims we want to be sure about, we don't care if |
| 942 | // they potentially extend further. |
| 943 | if (matcher.requireEnd() && !sourceClosed) { |
| 944 | needInput = true; |
| 945 | return null; |
| 946 | } |
| 947 | int tokenEnd = matcher.start(); |
| 948 | // There is a complete token. |
| 949 | if (pattern == null) { |
| 950 | // Must continue with match to provide valid MatchResult |
| 951 | pattern = FIND_ANY_PATTERN; |
| 952 | } |
| 953 | // Attempt to match against the desired pattern |
| 954 | matcher.usePattern(pattern); |
| 955 | matcher.region(position, tokenEnd); |
| 956 | if (matcher.matches()) { |
| 957 | String s = matcher.group(); |
| 958 | position = matcher.end(); |
| 959 | return s; |
| 960 | } else { // Complete token but it does not match |
| 961 | return null; |
| 962 | } |
| 963 | } |
| 964 | |
| 965 | // If we can't find the next delims but no more input is coming, |
| 966 | // then we can treat the remainder as a whole token |
| 967 | if (sourceClosed) { |
| 968 | if (pattern == null) { |
| 969 | // Must continue with match to provide valid MatchResult |
| 970 | pattern = FIND_ANY_PATTERN; |
| 971 | } |
| 972 | // Last token; Match the pattern here or throw |
| 973 | matcher.usePattern(pattern); |
| 974 | matcher.region(position, buf.limit()); |
| 975 | if (matcher.matches()) { |
| 976 | String s = matcher.group(); |
| 977 | position = matcher.end(); |
| 978 | return s; |
| 979 | } |
| 980 | // Last piece does not match |
| 981 | return null; |
| 982 | } |
| 983 | |
| 984 | // There is a partial token in the buffer; must read more |
| 985 | // to complete it |
| 986 | needInput = true; |
| 987 | return null; |
| 988 | } |
| 989 | |
| 990 | // Finds the specified pattern in the buffer up to horizon. |
| 991 | // Returns a match for the specified input pattern. |
| 992 | private String findPatternInBuffer(Pattern pattern, int horizon) { |
| 993 | matchValid = false; |
| 994 | matcher.usePattern(pattern); |
| 995 | int bufferLimit = buf.limit(); |
| 996 | int horizonLimit = -1; |
| 997 | int searchLimit = bufferLimit; |
| 998 | if (horizon > 0) { |
| 999 | horizonLimit = position + horizon; |
| 1000 | if (horizonLimit < bufferLimit) |
| 1001 | searchLimit = horizonLimit; |
| 1002 | } |
| 1003 | matcher.region(position, searchLimit); |
| 1004 | if (matcher.find()) { |
| 1005 | if (matcher.hitEnd() && (!sourceClosed)) { |
| 1006 | // The match may be longer if didn't hit horizon or real end |
| 1007 | if (searchLimit != horizonLimit) { |
| 1008 | // Hit an artificial end; try to extend the match |
| 1009 | needInput = true; |
| 1010 | return null; |
| 1011 | } |
| 1012 | // The match could go away depending on what is next |
| 1013 | if ((searchLimit == horizonLimit) && matcher.requireEnd()) { |
| 1014 | // Rare case: we hit the end of input and it happens |
| 1015 | // that it is at the horizon and the end of input is |
| 1016 | // required for the match. |
| 1017 | needInput = true; |
| 1018 | return null; |
| 1019 | } |
| 1020 | } |
| 1021 | // Did not hit end, or hit real end, or hit horizon |
| 1022 | position = matcher.end(); |
| 1023 | return matcher.group(); |
| 1024 | } |
| 1025 | |
| 1026 | if (sourceClosed) |
| 1027 | return null; |
| 1028 | |
| 1029 | // If there is no specified horizon, or if we have not searched |
| 1030 | // to the specified horizon yet, get more input |
| 1031 | if ((horizon == 0) || (searchLimit != horizonLimit)) |
| 1032 | needInput = true; |
| 1033 | return null; |
| 1034 | } |
| 1035 | |
| 1036 | // Returns a match for the specified input pattern anchored at |
| 1037 | // the current position |
| 1038 | private String matchPatternInBuffer(Pattern pattern) { |
| 1039 | matchValid = false; |
| 1040 | matcher.usePattern(pattern); |
| 1041 | matcher.region(position, buf.limit()); |
| 1042 | if (matcher.lookingAt()) { |
| 1043 | if (matcher.hitEnd() && (!sourceClosed)) { |
| 1044 | // Get more input and try again |
| 1045 | needInput = true; |
| 1046 | return null; |
| 1047 | } |
| 1048 | position = matcher.end(); |
| 1049 | return matcher.group(); |
| 1050 | } |
| 1051 | |
| 1052 | if (sourceClosed) |
| 1053 | return null; |
| 1054 | |
| 1055 | // Read more to find pattern |
| 1056 | needInput = true; |
| 1057 | return null; |
| 1058 | } |
| 1059 | |
| 1060 | // Throws if the scanner is closed |
| 1061 | private void ensureOpen() { |
| 1062 | if (closed) |
| 1063 | throw new IllegalStateException("Scanner closed"); |
| 1064 | } |
| 1065 | |
| 1066 | // Public methods |
| 1067 | |
| 1068 | /** |
| 1069 | * Closes this scanner. |
| 1070 | * |
| 1071 | * <p> If this scanner has not yet been closed then if its underlying |
| 1072 | * {@linkplain java.lang.Readable readable} also implements the {@link |
| 1073 | * java.io.Closeable} interface then the readable's <tt>close</tt> method |
| 1074 | * will be invoked. If this scanner is already closed then invoking this |
| 1075 | * method will have no effect. |
| 1076 | * |
| 1077 | * <p>Attempting to perform search operations after a scanner has |
| 1078 | * been closed will result in an {@link IllegalStateException}. |
| 1079 | * |
| 1080 | */ |
| 1081 | public void close() { |
| 1082 | if (closed) |
| 1083 | return; |
| 1084 | if (source instanceof Closeable) { |
| 1085 | try { |
| 1086 | ((Closeable)source).close(); |
| 1087 | } catch (IOException ioe) { |
| 1088 | lastException = ioe; |
| 1089 | } |
| 1090 | } |
| 1091 | sourceClosed = true; |
| 1092 | source = null; |
| 1093 | closed = true; |
| 1094 | } |
| 1095 | |
| 1096 | /** |
| 1097 | * Returns the <code>IOException</code> last thrown by this |
| 1098 | * <code>Scanner</code>'s underlying <code>Readable</code>. This method |
| 1099 | * returns <code>null</code> if no such exception exists. |
| 1100 | * |
| 1101 | * @return the last exception thrown by this scanner's readable |
| 1102 | */ |
| 1103 | public IOException ioException() { |
| 1104 | return lastException; |
| 1105 | } |
| 1106 | |
| 1107 | /** |
| 1108 | * Returns the <code>Pattern</code> this <code>Scanner</code> is currently |
| 1109 | * using to match delimiters. |
| 1110 | * |
| 1111 | * @return this scanner's delimiting pattern. |
| 1112 | */ |
| 1113 | public Pattern delimiter() { |
| 1114 | return delimPattern; |
| 1115 | } |
| 1116 | |
| 1117 | /** |
| 1118 | * Sets this scanner's delimiting pattern to the specified pattern. |
| 1119 | * |
| 1120 | * @param pattern A delimiting pattern |
| 1121 | * @return this scanner |
| 1122 | */ |
| 1123 | public Scanner useDelimiter(Pattern pattern) { |
| 1124 | delimPattern = pattern; |
| 1125 | return this; |
| 1126 | } |
| 1127 | |
| 1128 | /** |
| 1129 | * Sets this scanner's delimiting pattern to a pattern constructed from |
| 1130 | * the specified <code>String</code>. |
| 1131 | * |
| 1132 | * <p> An invocation of this method of the form |
| 1133 | * <tt>useDelimiter(pattern)</tt> behaves in exactly the same way as the |
| 1134 | * invocation <tt>useDelimiter(Pattern.compile(pattern))</tt>. |
| 1135 | * |
| 1136 | * <p> Invoking the {@link #reset} method will set the scanner's delimiter |
| 1137 | * to the <a href= "#default-delimiter">default</a>. |
| 1138 | * |
| 1139 | * @param pattern A string specifying a delimiting pattern |
| 1140 | * @return this scanner |
| 1141 | */ |
| 1142 | public Scanner useDelimiter(String pattern) { |
| 1143 | delimPattern = patternCache.forName(pattern); |
| 1144 | return this; |
| 1145 | } |
| 1146 | |
| 1147 | /** |
| 1148 | * Returns this scanner's locale. |
| 1149 | * |
| 1150 | * <p>A scanner's locale affects many elements of its default |
| 1151 | * primitive matching regular expressions; see |
| 1152 | * <a href= "#localized-numbers">localized numbers</a> above. |
| 1153 | * |
| 1154 | * @return this scanner's locale |
| 1155 | */ |
| 1156 | public Locale locale() { |
| 1157 | return this.locale; |
| 1158 | } |
| 1159 | |
| 1160 | /** |
| 1161 | * Sets this scanner's locale to the specified locale. |
| 1162 | * |
| 1163 | * <p>A scanner's locale affects many elements of its default |
| 1164 | * primitive matching regular expressions; see |
| 1165 | * <a href= "#localized-numbers">localized numbers</a> above. |
| 1166 | * |
| 1167 | * <p>Invoking the {@link #reset} method will set the scanner's locale to |
| 1168 | * the <a href= "#initial-locale">initial locale</a>. |
| 1169 | * |
| 1170 | * @param locale A string specifying the locale to use |
| 1171 | * @return this scanner |
| 1172 | */ |
| 1173 | public Scanner useLocale(Locale locale) { |
| 1174 | if (locale.equals(this.locale)) |
| 1175 | return this; |
| 1176 | |
| 1177 | this.locale = locale; |
| 1178 | DecimalFormat df = |
| 1179 | (DecimalFormat)NumberFormat.getNumberInstance(locale); |
| 1180 | DecimalFormatSymbols dfs = DecimalFormatSymbols.getInstance(locale); |
| 1181 | |
| 1182 | // These must be literalized to avoid collision with regex |
| 1183 | // metacharacters such as dot or parenthesis |
| 1184 | groupSeparator = "\\" + dfs.getGroupingSeparator(); |
| 1185 | decimalSeparator = "\\" + dfs.getDecimalSeparator(); |
| 1186 | |
| 1187 | // Quoting the nonzero length locale-specific things |
| 1188 | // to avoid potential conflict with metacharacters |
| 1189 | nanString = "\\Q" + dfs.getNaN() + "\\E"; |
| 1190 | infinityString = "\\Q" + dfs.getInfinity() + "\\E"; |
| 1191 | positivePrefix = df.getPositivePrefix(); |
| 1192 | if (positivePrefix.length() > 0) |
| 1193 | positivePrefix = "\\Q" + positivePrefix + "\\E"; |
| 1194 | negativePrefix = df.getNegativePrefix(); |
| 1195 | if (negativePrefix.length() > 0) |
| 1196 | negativePrefix = "\\Q" + negativePrefix + "\\E"; |
| 1197 | positiveSuffix = df.getPositiveSuffix(); |
| 1198 | if (positiveSuffix.length() > 0) |
| 1199 | positiveSuffix = "\\Q" + positiveSuffix + "\\E"; |
| 1200 | negativeSuffix = df.getNegativeSuffix(); |
| 1201 | if (negativeSuffix.length() > 0) |
| 1202 | negativeSuffix = "\\Q" + negativeSuffix + "\\E"; |
| 1203 | |
| 1204 | // Force rebuilding and recompilation of locale dependent |
| 1205 | // primitive patterns |
| 1206 | integerPattern = null; |
| 1207 | floatPattern = null; |
| 1208 | |
| 1209 | return this; |
| 1210 | } |
| 1211 | |
| 1212 | /** |
| 1213 | * Returns this scanner's default radix. |
| 1214 | * |
| 1215 | * <p>A scanner's radix affects elements of its default |
| 1216 | * number matching regular expressions; see |
| 1217 | * <a href= "#localized-numbers">localized numbers</a> above. |
| 1218 | * |
| 1219 | * @return the default radix of this scanner |
| 1220 | */ |
| 1221 | public int radix() { |
| 1222 | return this.defaultRadix; |
| 1223 | } |
| 1224 | |
| 1225 | /** |
| 1226 | * Sets this scanner's default radix to the specified radix. |
| 1227 | * |
| 1228 | * <p>A scanner's radix affects elements of its default |
| 1229 | * number matching regular expressions; see |
| 1230 | * <a href= "#localized-numbers">localized numbers</a> above. |
| 1231 | * |
| 1232 | * <p>If the radix is less than <code>Character.MIN_RADIX</code> |
| 1233 | * or greater than <code>Character.MAX_RADIX</code>, then an |
| 1234 | * <code>IllegalArgumentException</code> is thrown. |
| 1235 | * |
| 1236 | * <p>Invoking the {@link #reset} method will set the scanner's radix to |
| 1237 | * <code>10</code>. |
| 1238 | * |
| 1239 | * @param radix The radix to use when scanning numbers |
| 1240 | * @return this scanner |
| 1241 | * @throws IllegalArgumentException if radix is out of range |
| 1242 | */ |
| 1243 | public Scanner useRadix(int radix) { |
| 1244 | if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) |
| 1245 | throw new IllegalArgumentException("radix:"+radix); |
| 1246 | |
| 1247 | if (this.defaultRadix == radix) |
| 1248 | return this; |
| 1249 | this.defaultRadix = radix; |
| 1250 | // Force rebuilding and recompilation of radix dependent patterns |
| 1251 | integerPattern = null; |
| 1252 | return this; |
| 1253 | } |
| 1254 | |
| 1255 | // The next operation should occur in the specified radix but |
| 1256 | // the default is left untouched. |
| 1257 | private void setRadix(int radix) { |
| 1258 | if (this.radix != radix) { |
| 1259 | // Force rebuilding and recompilation of radix dependent patterns |
| 1260 | integerPattern = null; |
| 1261 | this.radix = radix; |
| 1262 | } |
| 1263 | } |
| 1264 | |
| 1265 | /** |
| 1266 | * Returns the match result of the last scanning operation performed |
| 1267 | * by this scanner. This method throws <code>IllegalStateException</code> |
| 1268 | * if no match has been performed, or if the last match was |
| 1269 | * not successful. |
| 1270 | * |
| 1271 | * <p>The various <code>next</code>methods of <code>Scanner</code> |
| 1272 | * make a match result available if they complete without throwing an |
| 1273 | * exception. For instance, after an invocation of the {@link #nextInt} |
| 1274 | * method that returned an int, this method returns a |
| 1275 | * <code>MatchResult</code> for the search of the |
| 1276 | * <a href="#Integer-regex"><i>Integer</i></a> regular expression |
| 1277 | * defined above. Similarly the {@link #findInLine}, |
| 1278 | * {@link #findWithinHorizon}, and {@link #skip} methods will make a |
| 1279 | * match available if they succeed. |
| 1280 | * |
| 1281 | * @return a match result for the last match operation |
| 1282 | * @throws IllegalStateException If no match result is available |
| 1283 | */ |
| 1284 | public MatchResult match() { |
| 1285 | if (!matchValid) |
| 1286 | throw new IllegalStateException("No match result available"); |
| 1287 | return matcher.toMatchResult(); |
| 1288 | } |
| 1289 | |
| 1290 | /** |
| 1291 | * <p>Returns the string representation of this <code>Scanner</code>. The |
| 1292 | * string representation of a <code>Scanner</code> contains information |
| 1293 | * that may be useful for debugging. The exact format is unspecified. |
| 1294 | * |
| 1295 | * @return The string representation of this scanner |
| 1296 | */ |
| 1297 | public String toString() { |
| 1298 | StringBuilder sb = new StringBuilder(); |
| 1299 | sb.append("java.util.Scanner"); |
| 1300 | sb.append("[delimiters=" + delimPattern + "]"); |
| 1301 | sb.append("[position=" + position + "]"); |
| 1302 | sb.append("[match valid=" + matchValid + "]"); |
| 1303 | sb.append("[need input=" + needInput + "]"); |
| 1304 | sb.append("[source closed=" + sourceClosed + "]"); |
| 1305 | sb.append("[skipped=" + skipped + "]"); |
| 1306 | sb.append("[group separator=" + groupSeparator + "]"); |
| 1307 | sb.append("[decimal separator=" + decimalSeparator + "]"); |
| 1308 | sb.append("[positive prefix=" + positivePrefix + "]"); |
| 1309 | sb.append("[negative prefix=" + negativePrefix + "]"); |
| 1310 | sb.append("[positive suffix=" + positiveSuffix + "]"); |
| 1311 | sb.append("[negative suffix=" + negativeSuffix + "]"); |
| 1312 | sb.append("[NaN string=" + nanString + "]"); |
| 1313 | sb.append("[infinity string=" + infinityString + "]"); |
| 1314 | return sb.toString(); |
| 1315 | } |
| 1316 | |
| 1317 | /** |
| 1318 | * Returns true if this scanner has another token in its input. |
| 1319 | * This method may block while waiting for input to scan. |
| 1320 | * The scanner does not advance past any input. |
| 1321 | * |
| 1322 | * @return true if and only if this scanner has another token |
| 1323 | * @throws IllegalStateException if this scanner is closed |
| 1324 | * @see java.util.Iterator |
| 1325 | */ |
| 1326 | public boolean hasNext() { |
| 1327 | ensureOpen(); |
| 1328 | saveState(); |
| 1329 | while (!sourceClosed) { |
| 1330 | if (hasTokenInBuffer()) |
| 1331 | return revertState(true); |
| 1332 | readInput(); |
| 1333 | } |
| 1334 | boolean result = hasTokenInBuffer(); |
| 1335 | return revertState(result); |
| 1336 | } |
| 1337 | |
| 1338 | /** |
| 1339 | * Finds and returns the next complete token from this scanner. |
| 1340 | * A complete token is preceded and followed by input that matches |
| 1341 | * the delimiter pattern. This method may block while waiting for input |
| 1342 | * to scan, even if a previous invocation of {@link #hasNext} returned |
| 1343 | * <code>true</code>. |
| 1344 | * |
| 1345 | * @return the next token |
| 1346 | * @throws NoSuchElementException if no more tokens are available |
| 1347 | * @throws IllegalStateException if this scanner is closed |
| 1348 | * @see java.util.Iterator |
| 1349 | */ |
| 1350 | public String next() { |
| 1351 | ensureOpen(); |
| 1352 | clearCaches(); |
| 1353 | |
| 1354 | while (true) { |
| 1355 | String token = getCompleteTokenInBuffer(null); |
| 1356 | if (token != null) { |
| 1357 | matchValid = true; |
| 1358 | skipped = false; |
| 1359 | return token; |
| 1360 | } |
| 1361 | if (needInput) |
| 1362 | readInput(); |
| 1363 | else |
| 1364 | throwFor(); |
| 1365 | } |
| 1366 | } |
| 1367 | |
| 1368 | /** |
| 1369 | * The remove operation is not supported by this implementation of |
| 1370 | * <code>Iterator</code>. |
| 1371 | * |
| 1372 | * @throws UnsupportedOperationException if this method is invoked. |
| 1373 | * @see java.util.Iterator |
| 1374 | */ |
| 1375 | public void remove() { |
| 1376 | throw new UnsupportedOperationException(); |
| 1377 | } |
| 1378 | |
| 1379 | /** |
| 1380 | * Returns true if the next token matches the pattern constructed from the |
| 1381 | * specified string. The scanner does not advance past any input. |
| 1382 | * |
| 1383 | * <p> An invocation of this method of the form <tt>hasNext(pattern)</tt> |
| 1384 | * behaves in exactly the same way as the invocation |
| 1385 | * <tt>hasNext(Pattern.compile(pattern))</tt>. |
| 1386 | * |
| 1387 | * @param pattern a string specifying the pattern to scan |
| 1388 | * @return true if and only if this scanner has another token matching |
| 1389 | * the specified pattern |
| 1390 | * @throws IllegalStateException if this scanner is closed |
| 1391 | */ |
| 1392 | public boolean hasNext(String pattern) { |
| 1393 | return hasNext(patternCache.forName(pattern)); |
| 1394 | } |
| 1395 | |
| 1396 | /** |
| 1397 | * Returns the next token if it matches the pattern constructed from the |
| 1398 | * specified string. If the match is successful, the scanner advances |
| 1399 | * past the input that matched the pattern. |
| 1400 | * |
| 1401 | * <p> An invocation of this method of the form <tt>next(pattern)</tt> |
| 1402 | * behaves in exactly the same way as the invocation |
| 1403 | * <tt>next(Pattern.compile(pattern))</tt>. |
| 1404 | * |
| 1405 | * @param pattern a string specifying the pattern to scan |
| 1406 | * @return the next token |
| 1407 | * @throws NoSuchElementException if no such tokens are available |
| 1408 | * @throws IllegalStateException if this scanner is closed |
| 1409 | */ |
| 1410 | public String next(String pattern) { |
| 1411 | return next(patternCache.forName(pattern)); |
| 1412 | } |
| 1413 | |
| 1414 | /** |
| 1415 | * Returns true if the next complete token matches the specified pattern. |
| 1416 | * A complete token is prefixed and postfixed by input that matches |
| 1417 | * the delimiter pattern. This method may block while waiting for input. |
| 1418 | * The scanner does not advance past any input. |
| 1419 | * |
| 1420 | * @param pattern the pattern to scan for |
| 1421 | * @return true if and only if this scanner has another token matching |
| 1422 | * the specified pattern |
| 1423 | * @throws IllegalStateException if this scanner is closed |
| 1424 | */ |
| 1425 | public boolean hasNext(Pattern pattern) { |
| 1426 | ensureOpen(); |
| 1427 | if (pattern == null) |
| 1428 | throw new NullPointerException(); |
| 1429 | hasNextPattern = null; |
| 1430 | saveState(); |
| 1431 | |
| 1432 | while (true) { |
| 1433 | if (getCompleteTokenInBuffer(pattern) != null) { |
| 1434 | matchValid = true; |
| 1435 | cacheResult(); |
| 1436 | return revertState(true); |
| 1437 | } |
| 1438 | if (needInput) |
| 1439 | readInput(); |
| 1440 | else |
| 1441 | return revertState(false); |
| 1442 | } |
| 1443 | } |
| 1444 | |
| 1445 | /** |
| 1446 | * Returns the next token if it matches the specified pattern. This |
| 1447 | * method may block while waiting for input to scan, even if a previous |
| 1448 | * invocation of {@link #hasNext(Pattern)} returned <code>true</code>. |
| 1449 | * If the match is successful, the scanner advances past the input that |
| 1450 | * matched the pattern. |
| 1451 | * |
| 1452 | * @param pattern the pattern to scan for |
| 1453 | * @return the next token |
| 1454 | * @throws NoSuchElementException if no more tokens are available |
| 1455 | * @throws IllegalStateException if this scanner is closed |
| 1456 | */ |
| 1457 | public String next(Pattern pattern) { |
| 1458 | ensureOpen(); |
| 1459 | if (pattern == null) |
| 1460 | throw new NullPointerException(); |
| 1461 | |
| 1462 | // Did we already find this pattern? |
| 1463 | if (hasNextPattern == pattern) |
| 1464 | return getCachedResult(); |
| 1465 | clearCaches(); |
| 1466 | |
| 1467 | // Search for the pattern |
| 1468 | while (true) { |
| 1469 | String token = getCompleteTokenInBuffer(pattern); |
| 1470 | if (token != null) { |
| 1471 | matchValid = true; |
| 1472 | skipped = false; |
| 1473 | return token; |
| 1474 | } |
| 1475 | if (needInput) |
| 1476 | readInput(); |
| 1477 | else |
| 1478 | throwFor(); |
| 1479 | } |
| 1480 | } |
| 1481 | |
| 1482 | /** |
| 1483 | * Returns true if there is another line in the input of this scanner. |
| 1484 | * This method may block while waiting for input. The scanner does not |
| 1485 | * advance past any input. |
| 1486 | * |
| 1487 | * @return true if and only if this scanner has another line of input |
| 1488 | * @throws IllegalStateException if this scanner is closed |
| 1489 | */ |
| 1490 | public boolean hasNextLine() { |
| 1491 | saveState(); |
| 1492 | |
| 1493 | String result = findWithinHorizon(linePattern(), 0); |
| 1494 | if (result != null) { |
| 1495 | MatchResult mr = this.match(); |
| 1496 | String lineSep = mr.group(1); |
| 1497 | if (lineSep != null) { |
| 1498 | result = result.substring(0, result.length() - |
| 1499 | lineSep.length()); |
| 1500 | cacheResult(result); |
| 1501 | |
| 1502 | } else { |
| 1503 | cacheResult(); |
| 1504 | } |
| 1505 | } |
| 1506 | revertState(); |
| 1507 | return (result != null); |
| 1508 | } |
| 1509 | |
| 1510 | /** |
| 1511 | * Advances this scanner past the current line and returns the input |
| 1512 | * that was skipped. |
| 1513 | * |
| 1514 | * This method returns the rest of the current line, excluding any line |
| 1515 | * separator at the end. The position is set to the beginning of the next |
| 1516 | * line. |
| 1517 | * |
| 1518 | * <p>Since this method continues to search through the input looking |
| 1519 | * for a line separator, it may buffer all of the input searching for |
| 1520 | * the line to skip if no line separators are present. |
| 1521 | * |
| 1522 | * @return the line that was skipped |
| 1523 | * @throws NoSuchElementException if no line was found |
| 1524 | * @throws IllegalStateException if this scanner is closed |
| 1525 | */ |
| 1526 | public String nextLine() { |
| 1527 | if (hasNextPattern == linePattern()) |
| 1528 | return getCachedResult(); |
| 1529 | clearCaches(); |
| 1530 | |
| 1531 | String result = findWithinHorizon(linePattern, 0); |
| 1532 | if (result == null) |
| 1533 | throw new NoSuchElementException("No line found"); |
| 1534 | MatchResult mr = this.match(); |
| 1535 | String lineSep = mr.group(1); |
| 1536 | if (lineSep != null) |
| 1537 | result = result.substring(0, result.length() - lineSep.length()); |
| 1538 | if (result == null) |
| 1539 | throw new NoSuchElementException(); |
| 1540 | else |
| 1541 | return result; |
| 1542 | } |
| 1543 | |
| 1544 | // Public methods that ignore delimiters |
| 1545 | |
| 1546 | /** |
| 1547 | * Attempts to find the next occurrence of a pattern constructed from the |
| 1548 | * specified string, ignoring delimiters. |
| 1549 | * |
| 1550 | * <p>An invocation of this method of the form <tt>findInLine(pattern)</tt> |
| 1551 | * behaves in exactly the same way as the invocation |
| 1552 | * <tt>findInLine(Pattern.compile(pattern))</tt>. |
| 1553 | * |
| 1554 | * @param pattern a string specifying the pattern to search for |
| 1555 | * @return the text that matched the specified pattern |
| 1556 | * @throws IllegalStateException if this scanner is closed |
| 1557 | */ |
| 1558 | public String findInLine(String pattern) { |
| 1559 | return findInLine(patternCache.forName(pattern)); |
| 1560 | } |
| 1561 | |
| 1562 | /** |
| 1563 | * Attempts to find the next occurrence of the specified pattern ignoring |
| 1564 | * delimiters. If the pattern is found before the next line separator, the |
| 1565 | * scanner advances past the input that matched and returns the string that |
| 1566 | * matched the pattern. |
| 1567 | * If no such pattern is detected in the input up to the next line |
| 1568 | * separator, then <code>null</code> is returned and the scanner's |
| 1569 | * position is unchanged. This method may block waiting for input that |
| 1570 | * matches the pattern. |
| 1571 | * |
| 1572 | * <p>Since this method continues to search through the input looking |
| 1573 | * for the specified pattern, it may buffer all of the input searching for |
| 1574 | * the desired token if no line separators are present. |
| 1575 | * |
| 1576 | * @param pattern the pattern to scan for |
| 1577 | * @return the text that matched the specified pattern |
| 1578 | * @throws IllegalStateException if this scanner is closed |
| 1579 | */ |
| 1580 | public String findInLine(Pattern pattern) { |
| 1581 | ensureOpen(); |
| 1582 | if (pattern == null) |
| 1583 | throw new NullPointerException(); |
| 1584 | clearCaches(); |
| 1585 | // Expand buffer to include the next newline or end of input |
| 1586 | int endPosition = 0; |
| 1587 | saveState(); |
| 1588 | while (true) { |
| 1589 | String token = findPatternInBuffer(separatorPattern(), 0); |
| 1590 | if (token != null) { |
| 1591 | endPosition = matcher.start(); |
| 1592 | break; // up to next newline |
| 1593 | } |
| 1594 | if (needInput) { |
| 1595 | readInput(); |
| 1596 | } else { |
| 1597 | endPosition = buf.limit(); |
| 1598 | break; // up to end of input |
| 1599 | } |
| 1600 | } |
| 1601 | revertState(); |
| 1602 | int horizonForLine = endPosition - position; |
| 1603 | // If there is nothing between the current pos and the next |
| 1604 | // newline simply return null, invoking findWithinHorizon |
| 1605 | // with "horizon=0" will scan beyond the line bound. |
| 1606 | if (horizonForLine == 0) |
| 1607 | return null; |
| 1608 | // Search for the pattern |
| 1609 | return findWithinHorizon(pattern, horizonForLine); |
| 1610 | } |
| 1611 | |
| 1612 | /** |
| 1613 | * Attempts to find the next occurrence of a pattern constructed from the |
| 1614 | * specified string, ignoring delimiters. |
| 1615 | * |
| 1616 | * <p>An invocation of this method of the form |
| 1617 | * <tt>findWithinHorizon(pattern)</tt> behaves in exactly the same way as |
| 1618 | * the invocation |
| 1619 | * <tt>findWithinHorizon(Pattern.compile(pattern, horizon))</tt>. |
| 1620 | * |
| 1621 | * @param pattern a string specifying the pattern to search for |
| 1622 | * @return the text that matched the specified pattern |
| 1623 | * @throws IllegalStateException if this scanner is closed |
| 1624 | * @throws IllegalArgumentException if horizon is negative |
| 1625 | */ |
| 1626 | public String findWithinHorizon(String pattern, int horizon) { |
| 1627 | return findWithinHorizon(patternCache.forName(pattern), horizon); |
| 1628 | } |
| 1629 | |
| 1630 | /** |
| 1631 | * Attempts to find the next occurrence of the specified pattern. |
| 1632 | * |
| 1633 | * <p>This method searches through the input up to the specified |
| 1634 | * search horizon, ignoring delimiters. If the pattern is found the |
| 1635 | * scanner advances past the input that matched and returns the string |
| 1636 | * that matched the pattern. If no such pattern is detected then the |
| 1637 | * null is returned and the scanner's position remains unchanged. This |
| 1638 | * method may block waiting for input that matches the pattern. |
| 1639 | * |
| 1640 | * <p>A scanner will never search more than <code>horizon</code> code |
| 1641 | * points beyond its current position. Note that a match may be clipped |
| 1642 | * by the horizon; that is, an arbitrary match result may have been |
| 1643 | * different if the horizon had been larger. The scanner treats the |
| 1644 | * horizon as a transparent, non-anchoring bound (see {@link |
| 1645 | * Matcher#useTransparentBounds} and {@link Matcher#useAnchoringBounds}). |
| 1646 | * |
| 1647 | * <p>If horizon is <code>0</code>, then the horizon is ignored and |
| 1648 | * this method continues to search through the input looking for the |
| 1649 | * specified pattern without bound. In this case it may buffer all of |
| 1650 | * the input searching for the pattern. |
| 1651 | * |
| 1652 | * <p>If horizon is negative, then an IllegalArgumentException is |
| 1653 | * thrown. |
| 1654 | * |
| 1655 | * @param pattern the pattern to scan for |
| 1656 | * @return the text that matched the specified pattern |
| 1657 | * @throws IllegalStateException if this scanner is closed |
| 1658 | * @throws IllegalArgumentException if horizon is negative |
| 1659 | */ |
| 1660 | public String findWithinHorizon(Pattern pattern, int horizon) { |
| 1661 | ensureOpen(); |
| 1662 | if (pattern == null) |
| 1663 | throw new NullPointerException(); |
| 1664 | if (horizon < 0) |
| 1665 | throw new IllegalArgumentException("horizon < 0"); |
| 1666 | clearCaches(); |
| 1667 | |
| 1668 | // Search for the pattern |
| 1669 | while (true) { |
| 1670 | String token = findPatternInBuffer(pattern, horizon); |
| 1671 | if (token != null) { |
| 1672 | matchValid = true; |
| 1673 | return token; |
| 1674 | } |
| 1675 | if (needInput) |
| 1676 | readInput(); |
| 1677 | else |
| 1678 | break; // up to end of input |
| 1679 | } |
| 1680 | return null; |
| 1681 | } |
| 1682 | |
| 1683 | /** |
| 1684 | * Skips input that matches the specified pattern, ignoring delimiters. |
| 1685 | * This method will skip input if an anchored match of the specified |
| 1686 | * pattern succeeds. |
| 1687 | * |
| 1688 | * <p>If a match to the specified pattern is not found at the |
| 1689 | * current position, then no input is skipped and a |
| 1690 | * <tt>NoSuchElementException</tt> is thrown. |
| 1691 | * |
| 1692 | * <p>Since this method seeks to match the specified pattern starting at |
| 1693 | * the scanner's current position, patterns that can match a lot of |
| 1694 | * input (".*", for example) may cause the scanner to buffer a large |
| 1695 | * amount of input. |
| 1696 | * |
| 1697 | * <p>Note that it is possible to skip something without risking a |
| 1698 | * <code>NoSuchElementException</code> by using a pattern that can |
| 1699 | * match nothing, e.g., <code>sc.skip("[ \t]*")</code>. |
| 1700 | * |
| 1701 | * @param pattern a string specifying the pattern to skip over |
| 1702 | * @return this scanner |
| 1703 | * @throws NoSuchElementException if the specified pattern is not found |
| 1704 | * @throws IllegalStateException if this scanner is closed |
| 1705 | */ |
| 1706 | public Scanner skip(Pattern pattern) { |
| 1707 | ensureOpen(); |
| 1708 | if (pattern == null) |
| 1709 | throw new NullPointerException(); |
| 1710 | clearCaches(); |
| 1711 | |
| 1712 | // Search for the pattern |
| 1713 | while (true) { |
| 1714 | String token = matchPatternInBuffer(pattern); |
| 1715 | if (token != null) { |
| 1716 | matchValid = true; |
| 1717 | position = matcher.end(); |
| 1718 | return this; |
| 1719 | } |
| 1720 | if (needInput) |
| 1721 | readInput(); |
| 1722 | else |
| 1723 | throw new NoSuchElementException(); |
| 1724 | } |
| 1725 | } |
| 1726 | |
| 1727 | /** |
| 1728 | * Skips input that matches a pattern constructed from the specified |
| 1729 | * string. |
| 1730 | * |
| 1731 | * <p> An invocation of this method of the form <tt>skip(pattern)</tt> |
| 1732 | * behaves in exactly the same way as the invocation |
| 1733 | * <tt>skip(Pattern.compile(pattern))</tt>. |
| 1734 | * |
| 1735 | * @param pattern a string specifying the pattern to skip over |
| 1736 | * @return this scanner |
| 1737 | * @throws IllegalStateException if this scanner is closed |
| 1738 | */ |
| 1739 | public Scanner skip(String pattern) { |
| 1740 | return skip(patternCache.forName(pattern)); |
| 1741 | } |
| 1742 | |
| 1743 | // Convenience methods for scanning primitives |
| 1744 | |
| 1745 | /** |
| 1746 | * Returns true if the next token in this scanner's input can be |
| 1747 | * interpreted as a boolean value using a case insensitive pattern |
| 1748 | * created from the string "true|false". The scanner does not |
| 1749 | * advance past the input that matched. |
| 1750 | * |
| 1751 | * @return true if and only if this scanner's next token is a valid |
| 1752 | * boolean value |
| 1753 | * @throws IllegalStateException if this scanner is closed |
| 1754 | */ |
| 1755 | public boolean hasNextBoolean() { |
| 1756 | return hasNext(boolPattern()); |
| 1757 | } |
| 1758 | |
| 1759 | /** |
| 1760 | * Scans the next token of the input into a boolean value and returns |
| 1761 | * that value. This method will throw <code>InputMismatchException</code> |
| 1762 | * if the next token cannot be translated into a valid boolean value. |
| 1763 | * If the match is successful, the scanner advances past the input that |
| 1764 | * matched. |
| 1765 | * |
| 1766 | * @return the boolean scanned from the input |
| 1767 | * @throws InputMismatchException if the next token is not a valid boolean |
| 1768 | * @throws NoSuchElementException if input is exhausted |
| 1769 | * @throws IllegalStateException if this scanner is closed |
| 1770 | */ |
| 1771 | public boolean nextBoolean() { |
| 1772 | clearCaches(); |
| 1773 | return Boolean.parseBoolean(next(boolPattern())); |
| 1774 | } |
| 1775 | |
| 1776 | /** |
| 1777 | * Returns true if the next token in this scanner's input can be |
| 1778 | * interpreted as a byte value in the default radix using the |
| 1779 | * {@link #nextByte} method. The scanner does not advance past any input. |
| 1780 | * |
| 1781 | * @return true if and only if this scanner's next token is a valid |
| 1782 | * byte value |
| 1783 | * @throws IllegalStateException if this scanner is closed |
| 1784 | */ |
| 1785 | public boolean hasNextByte() { |
| 1786 | return hasNextByte(defaultRadix); |
| 1787 | } |
| 1788 | |
| 1789 | /** |
| 1790 | * Returns true if the next token in this scanner's input can be |
| 1791 | * interpreted as a byte value in the specified radix using the |
| 1792 | * {@link #nextByte} method. The scanner does not advance past any input. |
| 1793 | * |
| 1794 | * @param radix the radix used to interpret the token as a byte value |
| 1795 | * @return true if and only if this scanner's next token is a valid |
| 1796 | * byte value |
| 1797 | * @throws IllegalStateException if this scanner is closed |
| 1798 | */ |
| 1799 | public boolean hasNextByte(int radix) { |
| 1800 | setRadix(radix); |
| 1801 | boolean result = hasNext(integerPattern()); |
| 1802 | if (result) { // Cache it |
| 1803 | try { |
| 1804 | String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? |
| 1805 | processIntegerToken(hasNextResult) : |
| 1806 | hasNextResult; |
| 1807 | typeCache = Byte.parseByte(s, radix); |
| 1808 | } catch (NumberFormatException nfe) { |
| 1809 | result = false; |
| 1810 | } |
| 1811 | } |
| 1812 | return result; |
| 1813 | } |
| 1814 | |
| 1815 | /** |
| 1816 | * Scans the next token of the input as a <tt>byte</tt>. |
| 1817 | * |
| 1818 | * <p> An invocation of this method of the form |
| 1819 | * <tt>nextByte()</tt> behaves in exactly the same way as the |
| 1820 | * invocation <tt>nextByte(radix)</tt>, where <code>radix</code> |
| 1821 | * is the default radix of this scanner. |
| 1822 | * |
| 1823 | * @return the <tt>byte</tt> scanned from the input |
| 1824 | * @throws InputMismatchException |
| 1825 | * if the next token does not match the <i>Integer</i> |
| 1826 | * regular expression, or is out of range |
| 1827 | * @throws NoSuchElementException if input is exhausted |
| 1828 | * @throws IllegalStateException if this scanner is closed |
| 1829 | */ |
| 1830 | public byte nextByte() { |
| 1831 | return nextByte(defaultRadix); |
| 1832 | } |
| 1833 | |
| 1834 | /** |
| 1835 | * Scans the next token of the input as a <tt>byte</tt>. |
| 1836 | * This method will throw <code>InputMismatchException</code> |
| 1837 | * if the next token cannot be translated into a valid byte value as |
| 1838 | * described below. If the translation is successful, the scanner advances |
| 1839 | * past the input that matched. |
| 1840 | * |
| 1841 | * <p> If the next token matches the <a |
| 1842 | * href="#Integer-regex"><i>Integer</i></a> regular expression defined |
| 1843 | * above then the token is converted into a <tt>byte</tt> value as if by |
| 1844 | * removing all locale specific prefixes, group separators, and locale |
| 1845 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 1846 | * digits via {@link Character#digit Character.digit}, prepending a |
| 1847 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 1848 | * were present, and passing the resulting string to |
| 1849 | * {@link Byte#parseByte(String, int) Byte.parseByte} with the |
| 1850 | * specified radix. |
| 1851 | * |
| 1852 | * @param radix the radix used to interpret the token as a byte value |
| 1853 | * @return the <tt>byte</tt> scanned from the input |
| 1854 | * @throws InputMismatchException |
| 1855 | * if the next token does not match the <i>Integer</i> |
| 1856 | * regular expression, or is out of range |
| 1857 | * @throws NoSuchElementException if input is exhausted |
| 1858 | * @throws IllegalStateException if this scanner is closed |
| 1859 | */ |
| 1860 | public byte nextByte(int radix) { |
| 1861 | // Check cached result |
| 1862 | if ((typeCache != null) && (typeCache instanceof Byte) |
| 1863 | && this.radix == radix) { |
| 1864 | byte val = ((Byte)typeCache).byteValue(); |
| 1865 | useTypeCache(); |
| 1866 | return val; |
| 1867 | } |
| 1868 | setRadix(radix); |
| 1869 | clearCaches(); |
| 1870 | // Search for next byte |
| 1871 | try { |
| 1872 | String s = next(integerPattern()); |
| 1873 | if (matcher.group(SIMPLE_GROUP_INDEX) == null) |
| 1874 | s = processIntegerToken(s); |
| 1875 | return Byte.parseByte(s, radix); |
| 1876 | } catch (NumberFormatException nfe) { |
| 1877 | position = matcher.start(); // don't skip bad token |
| 1878 | throw new InputMismatchException(nfe.getMessage()); |
| 1879 | } |
| 1880 | } |
| 1881 | |
| 1882 | /** |
| 1883 | * Returns true if the next token in this scanner's input can be |
| 1884 | * interpreted as a short value in the default radix using the |
| 1885 | * {@link #nextShort} method. The scanner does not advance past any input. |
| 1886 | * |
| 1887 | * @return true if and only if this scanner's next token is a valid |
| 1888 | * short value in the default radix |
| 1889 | * @throws IllegalStateException if this scanner is closed |
| 1890 | */ |
| 1891 | public boolean hasNextShort() { |
| 1892 | return hasNextShort(defaultRadix); |
| 1893 | } |
| 1894 | |
| 1895 | /** |
| 1896 | * Returns true if the next token in this scanner's input can be |
| 1897 | * interpreted as a short value in the specified radix using the |
| 1898 | * {@link #nextShort} method. The scanner does not advance past any input. |
| 1899 | * |
| 1900 | * @param radix the radix used to interpret the token as a short value |
| 1901 | * @return true if and only if this scanner's next token is a valid |
| 1902 | * short value in the specified radix |
| 1903 | * @throws IllegalStateException if this scanner is closed |
| 1904 | */ |
| 1905 | public boolean hasNextShort(int radix) { |
| 1906 | setRadix(radix); |
| 1907 | boolean result = hasNext(integerPattern()); |
| 1908 | if (result) { // Cache it |
| 1909 | try { |
| 1910 | String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? |
| 1911 | processIntegerToken(hasNextResult) : |
| 1912 | hasNextResult; |
| 1913 | typeCache = Short.parseShort(s, radix); |
| 1914 | } catch (NumberFormatException nfe) { |
| 1915 | result = false; |
| 1916 | } |
| 1917 | } |
| 1918 | return result; |
| 1919 | } |
| 1920 | |
| 1921 | /** |
| 1922 | * Scans the next token of the input as a <tt>short</tt>. |
| 1923 | * |
| 1924 | * <p> An invocation of this method of the form |
| 1925 | * <tt>nextShort()</tt> behaves in exactly the same way as the |
| 1926 | * invocation <tt>nextShort(radix)</tt>, where <code>radix</code> |
| 1927 | * is the default radix of this scanner. |
| 1928 | * |
| 1929 | * @return the <tt>short</tt> scanned from the input |
| 1930 | * @throws InputMismatchException |
| 1931 | * if the next token does not match the <i>Integer</i> |
| 1932 | * regular expression, or is out of range |
| 1933 | * @throws NoSuchElementException if input is exhausted |
| 1934 | * @throws IllegalStateException if this scanner is closed |
| 1935 | */ |
| 1936 | public short nextShort() { |
| 1937 | return nextShort(defaultRadix); |
| 1938 | } |
| 1939 | |
| 1940 | /** |
| 1941 | * Scans the next token of the input as a <tt>short</tt>. |
| 1942 | * This method will throw <code>InputMismatchException</code> |
| 1943 | * if the next token cannot be translated into a valid short value as |
| 1944 | * described below. If the translation is successful, the scanner advances |
| 1945 | * past the input that matched. |
| 1946 | * |
| 1947 | * <p> If the next token matches the <a |
| 1948 | * href="#Integer-regex"><i>Integer</i></a> regular expression defined |
| 1949 | * above then the token is converted into a <tt>short</tt> value as if by |
| 1950 | * removing all locale specific prefixes, group separators, and locale |
| 1951 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 1952 | * digits via {@link Character#digit Character.digit}, prepending a |
| 1953 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 1954 | * were present, and passing the resulting string to |
| 1955 | * {@link Short#parseShort(String, int) Short.parseShort} with the |
| 1956 | * specified radix. |
| 1957 | * |
| 1958 | * @param radix the radix used to interpret the token as a short value |
| 1959 | * @return the <tt>short</tt> scanned from the input |
| 1960 | * @throws InputMismatchException |
| 1961 | * if the next token does not match the <i>Integer</i> |
| 1962 | * regular expression, or is out of range |
| 1963 | * @throws NoSuchElementException if input is exhausted |
| 1964 | * @throws IllegalStateException if this scanner is closed |
| 1965 | */ |
| 1966 | public short nextShort(int radix) { |
| 1967 | // Check cached result |
| 1968 | if ((typeCache != null) && (typeCache instanceof Short) |
| 1969 | && this.radix == radix) { |
| 1970 | short val = ((Short)typeCache).shortValue(); |
| 1971 | useTypeCache(); |
| 1972 | return val; |
| 1973 | } |
| 1974 | setRadix(radix); |
| 1975 | clearCaches(); |
| 1976 | // Search for next short |
| 1977 | try { |
| 1978 | String s = next(integerPattern()); |
| 1979 | if (matcher.group(SIMPLE_GROUP_INDEX) == null) |
| 1980 | s = processIntegerToken(s); |
| 1981 | return Short.parseShort(s, radix); |
| 1982 | } catch (NumberFormatException nfe) { |
| 1983 | position = matcher.start(); // don't skip bad token |
| 1984 | throw new InputMismatchException(nfe.getMessage()); |
| 1985 | } |
| 1986 | } |
| 1987 | |
| 1988 | /** |
| 1989 | * Returns true if the next token in this scanner's input can be |
| 1990 | * interpreted as an int value in the default radix using the |
| 1991 | * {@link #nextInt} method. The scanner does not advance past any input. |
| 1992 | * |
| 1993 | * @return true if and only if this scanner's next token is a valid |
| 1994 | * int value |
| 1995 | * @throws IllegalStateException if this scanner is closed |
| 1996 | */ |
| 1997 | public boolean hasNextInt() { |
| 1998 | return hasNextInt(defaultRadix); |
| 1999 | } |
| 2000 | |
| 2001 | /** |
| 2002 | * Returns true if the next token in this scanner's input can be |
| 2003 | * interpreted as an int value in the specified radix using the |
| 2004 | * {@link #nextInt} method. The scanner does not advance past any input. |
| 2005 | * |
| 2006 | * @param radix the radix used to interpret the token as an int value |
| 2007 | * @return true if and only if this scanner's next token is a valid |
| 2008 | * int value |
| 2009 | * @throws IllegalStateException if this scanner is closed |
| 2010 | */ |
| 2011 | public boolean hasNextInt(int radix) { |
| 2012 | setRadix(radix); |
| 2013 | boolean result = hasNext(integerPattern()); |
| 2014 | if (result) { // Cache it |
| 2015 | try { |
| 2016 | String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? |
| 2017 | processIntegerToken(hasNextResult) : |
| 2018 | hasNextResult; |
| 2019 | typeCache = Integer.parseInt(s, radix); |
| 2020 | } catch (NumberFormatException nfe) { |
| 2021 | result = false; |
| 2022 | } |
| 2023 | } |
| 2024 | return result; |
| 2025 | } |
| 2026 | |
| 2027 | /** |
| 2028 | * The integer token must be stripped of prefixes, group separators, |
| 2029 | * and suffixes, non ascii digits must be converted into ascii digits |
| 2030 | * before parse will accept it. |
| 2031 | */ |
| 2032 | private String processIntegerToken(String token) { |
| 2033 | String result = token.replaceAll(""+groupSeparator, ""); |
| 2034 | boolean isNegative = false; |
| 2035 | int preLen = negativePrefix.length(); |
| 2036 | if ((preLen > 0) && result.startsWith(negativePrefix)) { |
| 2037 | isNegative = true; |
| 2038 | result = result.substring(preLen); |
| 2039 | } |
| 2040 | int sufLen = negativeSuffix.length(); |
| 2041 | if ((sufLen > 0) && result.endsWith(negativeSuffix)) { |
| 2042 | isNegative = true; |
| 2043 | result = result.substring(result.length() - sufLen, |
| 2044 | result.length()); |
| 2045 | } |
| 2046 | if (isNegative) |
| 2047 | result = "-" + result; |
| 2048 | return result; |
| 2049 | } |
| 2050 | |
| 2051 | /** |
| 2052 | * Scans the next token of the input as an <tt>int</tt>. |
| 2053 | * |
| 2054 | * <p> An invocation of this method of the form |
| 2055 | * <tt>nextInt()</tt> behaves in exactly the same way as the |
| 2056 | * invocation <tt>nextInt(radix)</tt>, where <code>radix</code> |
| 2057 | * is the default radix of this scanner. |
| 2058 | * |
| 2059 | * @return the <tt>int</tt> scanned from the input |
| 2060 | * @throws InputMismatchException |
| 2061 | * if the next token does not match the <i>Integer</i> |
| 2062 | * regular expression, or is out of range |
| 2063 | * @throws NoSuchElementException if input is exhausted |
| 2064 | * @throws IllegalStateException if this scanner is closed |
| 2065 | */ |
| 2066 | public int nextInt() { |
| 2067 | return nextInt(defaultRadix); |
| 2068 | } |
| 2069 | |
| 2070 | /** |
| 2071 | * Scans the next token of the input as an <tt>int</tt>. |
| 2072 | * This method will throw <code>InputMismatchException</code> |
| 2073 | * if the next token cannot be translated into a valid int value as |
| 2074 | * described below. If the translation is successful, the scanner advances |
| 2075 | * past the input that matched. |
| 2076 | * |
| 2077 | * <p> If the next token matches the <a |
| 2078 | * href="#Integer-regex"><i>Integer</i></a> regular expression defined |
| 2079 | * above then the token is converted into an <tt>int</tt> value as if by |
| 2080 | * removing all locale specific prefixes, group separators, and locale |
| 2081 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 2082 | * digits via {@link Character#digit Character.digit}, prepending a |
| 2083 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 2084 | * were present, and passing the resulting string to |
| 2085 | * {@link Integer#parseInt(String, int) Integer.parseInt} with the |
| 2086 | * specified radix. |
| 2087 | * |
| 2088 | * @param radix the radix used to interpret the token as an int value |
| 2089 | * @return the <tt>int</tt> scanned from the input |
| 2090 | * @throws InputMismatchException |
| 2091 | * if the next token does not match the <i>Integer</i> |
| 2092 | * regular expression, or is out of range |
| 2093 | * @throws NoSuchElementException if input is exhausted |
| 2094 | * @throws IllegalStateException if this scanner is closed |
| 2095 | */ |
| 2096 | public int nextInt(int radix) { |
| 2097 | // Check cached result |
| 2098 | if ((typeCache != null) && (typeCache instanceof Integer) |
| 2099 | && this.radix == radix) { |
| 2100 | int val = ((Integer)typeCache).intValue(); |
| 2101 | useTypeCache(); |
| 2102 | return val; |
| 2103 | } |
| 2104 | setRadix(radix); |
| 2105 | clearCaches(); |
| 2106 | // Search for next int |
| 2107 | try { |
| 2108 | String s = next(integerPattern()); |
| 2109 | if (matcher.group(SIMPLE_GROUP_INDEX) == null) |
| 2110 | s = processIntegerToken(s); |
| 2111 | return Integer.parseInt(s, radix); |
| 2112 | } catch (NumberFormatException nfe) { |
| 2113 | position = matcher.start(); // don't skip bad token |
| 2114 | throw new InputMismatchException(nfe.getMessage()); |
| 2115 | } |
| 2116 | } |
| 2117 | |
| 2118 | /** |
| 2119 | * Returns true if the next token in this scanner's input can be |
| 2120 | * interpreted as a long value in the default radix using the |
| 2121 | * {@link #nextLong} method. The scanner does not advance past any input. |
| 2122 | * |
| 2123 | * @return true if and only if this scanner's next token is a valid |
| 2124 | * long value |
| 2125 | * @throws IllegalStateException if this scanner is closed |
| 2126 | */ |
| 2127 | public boolean hasNextLong() { |
| 2128 | return hasNextLong(defaultRadix); |
| 2129 | } |
| 2130 | |
| 2131 | /** |
| 2132 | * Returns true if the next token in this scanner's input can be |
| 2133 | * interpreted as a long value in the specified radix using the |
| 2134 | * {@link #nextLong} method. The scanner does not advance past any input. |
| 2135 | * |
| 2136 | * @param radix the radix used to interpret the token as a long value |
| 2137 | * @return true if and only if this scanner's next token is a valid |
| 2138 | * long value |
| 2139 | * @throws IllegalStateException if this scanner is closed |
| 2140 | */ |
| 2141 | public boolean hasNextLong(int radix) { |
| 2142 | setRadix(radix); |
| 2143 | boolean result = hasNext(integerPattern()); |
| 2144 | if (result) { // Cache it |
| 2145 | try { |
| 2146 | String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? |
| 2147 | processIntegerToken(hasNextResult) : |
| 2148 | hasNextResult; |
| 2149 | typeCache = Long.parseLong(s, radix); |
| 2150 | } catch (NumberFormatException nfe) { |
| 2151 | result = false; |
| 2152 | } |
| 2153 | } |
| 2154 | return result; |
| 2155 | } |
| 2156 | |
| 2157 | /** |
| 2158 | * Scans the next token of the input as a <tt>long</tt>. |
| 2159 | * |
| 2160 | * <p> An invocation of this method of the form |
| 2161 | * <tt>nextLong()</tt> behaves in exactly the same way as the |
| 2162 | * invocation <tt>nextLong(radix)</tt>, where <code>radix</code> |
| 2163 | * is the default radix of this scanner. |
| 2164 | * |
| 2165 | * @return the <tt>long</tt> scanned from the input |
| 2166 | * @throws InputMismatchException |
| 2167 | * if the next token does not match the <i>Integer</i> |
| 2168 | * regular expression, or is out of range |
| 2169 | * @throws NoSuchElementException if input is exhausted |
| 2170 | * @throws IllegalStateException if this scanner is closed |
| 2171 | */ |
| 2172 | public long nextLong() { |
| 2173 | return nextLong(defaultRadix); |
| 2174 | } |
| 2175 | |
| 2176 | /** |
| 2177 | * Scans the next token of the input as a <tt>long</tt>. |
| 2178 | * This method will throw <code>InputMismatchException</code> |
| 2179 | * if the next token cannot be translated into a valid long value as |
| 2180 | * described below. If the translation is successful, the scanner advances |
| 2181 | * past the input that matched. |
| 2182 | * |
| 2183 | * <p> If the next token matches the <a |
| 2184 | * href="#Integer-regex"><i>Integer</i></a> regular expression defined |
| 2185 | * above then the token is converted into a <tt>long</tt> value as if by |
| 2186 | * removing all locale specific prefixes, group separators, and locale |
| 2187 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 2188 | * digits via {@link Character#digit Character.digit}, prepending a |
| 2189 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 2190 | * were present, and passing the resulting string to |
| 2191 | * {@link Long#parseLong(String, int) Long.parseLong} with the |
| 2192 | * specified radix. |
| 2193 | * |
| 2194 | * @param radix the radix used to interpret the token as an int value |
| 2195 | * @return the <tt>long</tt> scanned from the input |
| 2196 | * @throws InputMismatchException |
| 2197 | * if the next token does not match the <i>Integer</i> |
| 2198 | * regular expression, or is out of range |
| 2199 | * @throws NoSuchElementException if input is exhausted |
| 2200 | * @throws IllegalStateException if this scanner is closed |
| 2201 | */ |
| 2202 | public long nextLong(int radix) { |
| 2203 | // Check cached result |
| 2204 | if ((typeCache != null) && (typeCache instanceof Long) |
| 2205 | && this.radix == radix) { |
| 2206 | long val = ((Long)typeCache).longValue(); |
| 2207 | useTypeCache(); |
| 2208 | return val; |
| 2209 | } |
| 2210 | setRadix(radix); |
| 2211 | clearCaches(); |
| 2212 | try { |
| 2213 | String s = next(integerPattern()); |
| 2214 | if (matcher.group(SIMPLE_GROUP_INDEX) == null) |
| 2215 | s = processIntegerToken(s); |
| 2216 | return Long.parseLong(s, radix); |
| 2217 | } catch (NumberFormatException nfe) { |
| 2218 | position = matcher.start(); // don't skip bad token |
| 2219 | throw new InputMismatchException(nfe.getMessage()); |
| 2220 | } |
| 2221 | } |
| 2222 | |
| 2223 | /** |
| 2224 | * The float token must be stripped of prefixes, group separators, |
| 2225 | * and suffixes, non ascii digits must be converted into ascii digits |
| 2226 | * before parseFloat will accept it. |
| 2227 | * |
| 2228 | * If there are non-ascii digits in the token these digits must |
| 2229 | * be processed before the token is passed to parseFloat. |
| 2230 | */ |
| 2231 | private String processFloatToken(String token) { |
| 2232 | String result = token.replaceAll(groupSeparator, ""); |
| 2233 | if (!decimalSeparator.equals("\\.")) |
| 2234 | result = result.replaceAll(decimalSeparator, "."); |
| 2235 | boolean isNegative = false; |
| 2236 | int preLen = negativePrefix.length(); |
| 2237 | if ((preLen > 0) && result.startsWith(negativePrefix)) { |
| 2238 | isNegative = true; |
| 2239 | result = result.substring(preLen); |
| 2240 | } |
| 2241 | int sufLen = negativeSuffix.length(); |
| 2242 | if ((sufLen > 0) && result.endsWith(negativeSuffix)) { |
| 2243 | isNegative = true; |
| 2244 | result = result.substring(result.length() - sufLen, |
| 2245 | result.length()); |
| 2246 | } |
| 2247 | if (result.equals(nanString)) |
| 2248 | result = "NaN"; |
| 2249 | if (result.equals(infinityString)) |
| 2250 | result = "Infinity"; |
| 2251 | if (isNegative) |
| 2252 | result = "-" + result; |
| 2253 | |
| 2254 | // Translate non-ASCII digits |
| 2255 | Matcher m = NON_ASCII_DIGIT.matcher(result); |
| 2256 | if (m.find()) { |
| 2257 | StringBuilder inASCII = new StringBuilder(); |
| 2258 | for (int i=0; i<result.length(); i++) { |
| 2259 | char nextChar = result.charAt(i); |
| 2260 | if (Character.isDigit(nextChar)) { |
| 2261 | int d = Character.digit(nextChar, 10); |
| 2262 | if (d != -1) |
| 2263 | inASCII.append(d); |
| 2264 | else |
| 2265 | inASCII.append(nextChar); |
| 2266 | } else { |
| 2267 | inASCII.append(nextChar); |
| 2268 | } |
| 2269 | } |
| 2270 | result = inASCII.toString(); |
| 2271 | } |
| 2272 | |
| 2273 | return result; |
| 2274 | } |
| 2275 | |
| 2276 | /** |
| 2277 | * Returns true if the next token in this scanner's input can be |
| 2278 | * interpreted as a float value using the {@link #nextFloat} |
| 2279 | * method. The scanner does not advance past any input. |
| 2280 | * |
| 2281 | * @return true if and only if this scanner's next token is a valid |
| 2282 | * float value |
| 2283 | * @throws IllegalStateException if this scanner is closed |
| 2284 | */ |
| 2285 | public boolean hasNextFloat() { |
| 2286 | setRadix(10); |
| 2287 | boolean result = hasNext(floatPattern()); |
| 2288 | if (result) { // Cache it |
| 2289 | try { |
| 2290 | String s = processFloatToken(hasNextResult); |
| 2291 | typeCache = Float.valueOf(Float.parseFloat(s)); |
| 2292 | } catch (NumberFormatException nfe) { |
| 2293 | result = false; |
| 2294 | } |
| 2295 | } |
| 2296 | return result; |
| 2297 | } |
| 2298 | |
| 2299 | /** |
| 2300 | * Scans the next token of the input as a <tt>float</tt>. |
| 2301 | * This method will throw <code>InputMismatchException</code> |
| 2302 | * if the next token cannot be translated into a valid float value as |
| 2303 | * described below. If the translation is successful, the scanner advances |
| 2304 | * past the input that matched. |
| 2305 | * |
| 2306 | * <p> If the next token matches the <a |
| 2307 | * href="#Float-regex"><i>Float</i></a> regular expression defined above |
| 2308 | * then the token is converted into a <tt>float</tt> value as if by |
| 2309 | * removing all locale specific prefixes, group separators, and locale |
| 2310 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 2311 | * digits via {@link Character#digit Character.digit}, prepending a |
| 2312 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 2313 | * were present, and passing the resulting string to |
| 2314 | * {@link Float#parseFloat Float.parseFloat}. If the token matches |
| 2315 | * the localized NaN or infinity strings, then either "Nan" or "Infinity" |
| 2316 | * is passed to {@link Float#parseFloat(String) Float.parseFloat} as |
| 2317 | * appropriate. |
| 2318 | * |
| 2319 | * @return the <tt>float</tt> scanned from the input |
| 2320 | * @throws InputMismatchException |
| 2321 | * if the next token does not match the <i>Float</i> |
| 2322 | * regular expression, or is out of range |
| 2323 | * @throws NoSuchElementException if input is exhausted |
| 2324 | * @throws IllegalStateException if this scanner is closed |
| 2325 | */ |
| 2326 | public float nextFloat() { |
| 2327 | // Check cached result |
| 2328 | if ((typeCache != null) && (typeCache instanceof Float)) { |
| 2329 | float val = ((Float)typeCache).floatValue(); |
| 2330 | useTypeCache(); |
| 2331 | return val; |
| 2332 | } |
| 2333 | setRadix(10); |
| 2334 | clearCaches(); |
| 2335 | try { |
| 2336 | return Float.parseFloat(processFloatToken(next(floatPattern()))); |
| 2337 | } catch (NumberFormatException nfe) { |
| 2338 | position = matcher.start(); // don't skip bad token |
| 2339 | throw new InputMismatchException(nfe.getMessage()); |
| 2340 | } |
| 2341 | } |
| 2342 | |
| 2343 | /** |
| 2344 | * Returns true if the next token in this scanner's input can be |
| 2345 | * interpreted as a double value using the {@link #nextDouble} |
| 2346 | * method. The scanner does not advance past any input. |
| 2347 | * |
| 2348 | * @return true if and only if this scanner's next token is a valid |
| 2349 | * double value |
| 2350 | * @throws IllegalStateException if this scanner is closed |
| 2351 | */ |
| 2352 | public boolean hasNextDouble() { |
| 2353 | setRadix(10); |
| 2354 | boolean result = hasNext(floatPattern()); |
| 2355 | if (result) { // Cache it |
| 2356 | try { |
| 2357 | String s = processFloatToken(hasNextResult); |
| 2358 | typeCache = Double.valueOf(Double.parseDouble(s)); |
| 2359 | } catch (NumberFormatException nfe) { |
| 2360 | result = false; |
| 2361 | } |
| 2362 | } |
| 2363 | return result; |
| 2364 | } |
| 2365 | |
| 2366 | /** |
| 2367 | * Scans the next token of the input as a <tt>double</tt>. |
| 2368 | * This method will throw <code>InputMismatchException</code> |
| 2369 | * if the next token cannot be translated into a valid double value. |
| 2370 | * If the translation is successful, the scanner advances past the input |
| 2371 | * that matched. |
| 2372 | * |
| 2373 | * <p> If the next token matches the <a |
| 2374 | * href="#Float-regex"><i>Float</i></a> regular expression defined above |
| 2375 | * then the token is converted into a <tt>double</tt> value as if by |
| 2376 | * removing all locale specific prefixes, group separators, and locale |
| 2377 | * specific suffixes, then mapping non-ASCII digits into ASCII |
| 2378 | * digits via {@link Character#digit Character.digit}, prepending a |
| 2379 | * negative sign (-) if the locale specific negative prefixes and suffixes |
| 2380 | * were present, and passing the resulting string to |
| 2381 | * {@link Double#parseDouble Double.parseDouble}. If the token matches |
| 2382 | * the localized NaN or infinity strings, then either "Nan" or "Infinity" |
| 2383 | * is passed to {@link Double#parseDouble(String) Double.parseDouble} as |
| 2384 | * appropriate. |
| 2385 | * |
| 2386 | * @return the <tt>double</tt> scanned from the input |
| 2387 | * @throws InputMismatchException |
| 2388 | * if the next token does not match the <i>Float</i> |
| 2389 | * regular expression, or is out of range |
| 2390 | * @throws NoSuchElementException if the input is exhausted |
| 2391 | * @throws IllegalStateException if this scanner is closed |
| 2392 | */ |
| 2393 | public double nextDouble() { |
| 2394 | // Check cached result |
| 2395 | if ((typeCache != null) && (typeCache instanceof Double)) { |
| 2396 | double val = ((Double)typeCache).doubleValue(); |
| 2397 | useTypeCache(); |
| 2398 | return val; |
| 2399 | } |
| 2400 | setRadix(10); |
| 2401 | clearCaches(); |
| 2402 | // Search for next float |
| 2403 | try { |
| 2404 | return Double.parseDouble(processFloatToken(next(floatPattern()))); |
| 2405 | } catch (NumberFormatException nfe) { |
| 2406 | position = matcher.start(); // don't skip bad token |
| 2407 | throw new InputMismatchException(nfe.getMessage()); |
| 2408 | } |
| 2409 | } |
| 2410 | |
| 2411 | // Convenience methods for scanning multi precision numbers |
| 2412 | |
| 2413 | /** |
| 2414 | * Returns true if the next token in this scanner's input can be |
| 2415 | * interpreted as a <code>BigInteger</code> in the default radix using the |
| 2416 | * {@link #nextBigInteger} method. The scanner does not advance past any |
| 2417 | * input. |
| 2418 | * |
| 2419 | * @return true if and only if this scanner's next token is a valid |
| 2420 | * <code>BigInteger</code> |
| 2421 | * @throws IllegalStateException if this scanner is closed |
| 2422 | */ |
| 2423 | public boolean hasNextBigInteger() { |
| 2424 | return hasNextBigInteger(defaultRadix); |
| 2425 | } |
| 2426 | |
| 2427 | /** |
| 2428 | * Returns true if the next token in this scanner's input can be |
| 2429 | * interpreted as a <code>BigInteger</code> in the specified radix using |
| 2430 | * the {@link #nextBigInteger} method. The scanner does not advance past |
| 2431 | * any input. |
| 2432 | * |
| 2433 | * @param radix the radix used to interpret the token as an integer |
| 2434 | * @return true if and only if this scanner's next token is a valid |
| 2435 | * <code>BigInteger</code> |
| 2436 | * @throws IllegalStateException if this scanner is closed |
| 2437 | */ |
| 2438 | public boolean hasNextBigInteger(int radix) { |
| 2439 | setRadix(radix); |
| 2440 | boolean result = hasNext(integerPattern()); |
| 2441 | if (result) { // Cache it |
| 2442 | try { |
| 2443 | String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? |
| 2444 | processIntegerToken(hasNextResult) : |
| 2445 | hasNextResult; |
| 2446 | typeCache = new BigInteger(s, radix); |
| 2447 | } catch (NumberFormatException nfe) { |
| 2448 | result = false; |
| 2449 | } |
| 2450 | } |
| 2451 | return result; |
| 2452 | } |
| 2453 | |
| 2454 | /** |
| 2455 | * Scans the next token of the input as a {@link java.math.BigInteger |
| 2456 | * BigInteger}. |
| 2457 | * |
| 2458 | * <p> An invocation of this method of the form |
| 2459 | * <tt>nextBigInteger()</tt> behaves in exactly the same way as the |
| 2460 | * invocation <tt>nextBigInteger(radix)</tt>, where <code>radix</code> |
| 2461 | * is the default radix of this scanner. |
| 2462 | * |
| 2463 | * @return the <tt>BigInteger</tt> scanned from the input |
| 2464 | * @throws InputMismatchException |
| 2465 | * if the next token does not match the <i>Integer</i> |
| 2466 | * regular expression, or is out of range |
| 2467 | * @throws NoSuchElementException if the input is exhausted |
| 2468 | * @throws IllegalStateException if this scanner is closed |
| 2469 | */ |
| 2470 | public BigInteger nextBigInteger() { |
| 2471 | return nextBigInteger(defaultRadix); |
| 2472 | } |
| 2473 | |
| 2474 | /** |
| 2475 | * Scans the next token of the input as a {@link java.math.BigInteger |
| 2476 | * BigInteger}. |
| 2477 | * |
| 2478 | * <p> If the next token matches the <a |
| 2479 | * href="#Integer-regex"><i>Integer</i></a> regular expression defined |
| 2480 | * above then the token is converted into a <tt>BigInteger</tt> value as if |
| 2481 | * by removing all group separators, mapping non-ASCII digits into ASCII |
| 2482 | * digits via the {@link Character#digit Character.digit}, and passing the |
| 2483 | * resulting string to the {@link |
| 2484 | * java.math.BigInteger#BigInteger(java.lang.String) |
| 2485 | * BigInteger(String, int)} constructor with the specified radix. |
| 2486 | * |
| 2487 | * @param radix the radix used to interpret the token |
| 2488 | * @return the <tt>BigInteger</tt> scanned from the input |
| 2489 | * @throws InputMismatchException |
| 2490 | * if the next token does not match the <i>Integer</i> |
| 2491 | * regular expression, or is out of range |
| 2492 | * @throws NoSuchElementException if the input is exhausted |
| 2493 | * @throws IllegalStateException if this scanner is closed |
| 2494 | */ |
| 2495 | public BigInteger nextBigInteger(int radix) { |
| 2496 | // Check cached result |
| 2497 | if ((typeCache != null) && (typeCache instanceof BigInteger) |
| 2498 | && this.radix == radix) { |
| 2499 | BigInteger val = (BigInteger)typeCache; |
| 2500 | useTypeCache(); |
| 2501 | return val; |
| 2502 | } |
| 2503 | setRadix(radix); |
| 2504 | clearCaches(); |
| 2505 | // Search for next int |
| 2506 | try { |
| 2507 | String s = next(integerPattern()); |
| 2508 | if (matcher.group(SIMPLE_GROUP_INDEX) == null) |
| 2509 | s = processIntegerToken(s); |
| 2510 | return new BigInteger(s, radix); |
| 2511 | } catch (NumberFormatException nfe) { |
| 2512 | position = matcher.start(); // don't skip bad token |
| 2513 | throw new InputMismatchException(nfe.getMessage()); |
| 2514 | } |
| 2515 | } |
| 2516 | |
| 2517 | /** |
| 2518 | * Returns true if the next token in this scanner's input can be |
| 2519 | * interpreted as a <code>BigDecimal</code> using the |
| 2520 | * {@link #nextBigDecimal} method. The scanner does not advance past any |
| 2521 | * input. |
| 2522 | * |
| 2523 | * @return true if and only if this scanner's next token is a valid |
| 2524 | * <code>BigDecimal</code> |
| 2525 | * @throws IllegalStateException if this scanner is closed |
| 2526 | */ |
| 2527 | public boolean hasNextBigDecimal() { |
| 2528 | setRadix(10); |
| 2529 | boolean result = hasNext(decimalPattern()); |
| 2530 | if (result) { // Cache it |
| 2531 | try { |
| 2532 | String s = processFloatToken(hasNextResult); |
| 2533 | typeCache = new BigDecimal(s); |
| 2534 | } catch (NumberFormatException nfe) { |
| 2535 | result = false; |
| 2536 | } |
| 2537 | } |
| 2538 | return result; |
| 2539 | } |
| 2540 | |
| 2541 | /** |
| 2542 | * Scans the next token of the input as a {@link java.math.BigDecimal |
| 2543 | * BigDecimal}. |
| 2544 | * |
| 2545 | * <p> If the next token matches the <a |
| 2546 | * href="#Decimal-regex"><i>Decimal</i></a> regular expression defined |
| 2547 | * above then the token is converted into a <tt>BigDecimal</tt> value as if |
| 2548 | * by removing all group separators, mapping non-ASCII digits into ASCII |
| 2549 | * digits via the {@link Character#digit Character.digit}, and passing the |
| 2550 | * resulting string to the {@link |
| 2551 | * java.math.BigDecimal#BigDecimal(java.lang.String) BigDecimal(String)} |
| 2552 | * constructor. |
| 2553 | * |
| 2554 | * @return the <tt>BigDecimal</tt> scanned from the input |
| 2555 | * @throws InputMismatchException |
| 2556 | * if the next token does not match the <i>Decimal</i> |
| 2557 | * regular expression, or is out of range |
| 2558 | * @throws NoSuchElementException if the input is exhausted |
| 2559 | * @throws IllegalStateException if this scanner is closed |
| 2560 | */ |
| 2561 | public BigDecimal nextBigDecimal() { |
| 2562 | // Check cached result |
| 2563 | if ((typeCache != null) && (typeCache instanceof BigDecimal)) { |
| 2564 | BigDecimal val = (BigDecimal)typeCache; |
| 2565 | useTypeCache(); |
| 2566 | return val; |
| 2567 | } |
| 2568 | setRadix(10); |
| 2569 | clearCaches(); |
| 2570 | // Search for next float |
| 2571 | try { |
| 2572 | String s = processFloatToken(next(decimalPattern())); |
| 2573 | return new BigDecimal(s); |
| 2574 | } catch (NumberFormatException nfe) { |
| 2575 | position = matcher.start(); // don't skip bad token |
| 2576 | throw new InputMismatchException(nfe.getMessage()); |
| 2577 | } |
| 2578 | } |
| 2579 | |
| 2580 | /** |
| 2581 | * Resets this scanner. |
| 2582 | * |
| 2583 | * <p> Resetting a scanner discards all of its explicit state |
| 2584 | * information which may have been changed by invocations of {@link |
| 2585 | * #useDelimiter}, {@link #useLocale}, or {@link #useRadix}. |
| 2586 | * |
| 2587 | * <p> An invocation of this method of the form |
| 2588 | * <tt>scanner.reset()</tt> behaves in exactly the same way as the |
| 2589 | * invocation |
| 2590 | * |
| 2591 | * <blockquote><pre> |
| 2592 | * scanner.useDelimiter("\\p{javaWhitespace}+") |
| 2593 | * .useLocale(Locale.getDefault()) |
| 2594 | * .useRadix(10); |
| 2595 | * </pre></blockquote> |
| 2596 | * |
| 2597 | * @return this scanner |
| 2598 | * |
| 2599 | * @since 1.6 |
| 2600 | */ |
| 2601 | public Scanner reset() { |
| 2602 | delimPattern = WHITESPACE_PATTERN; |
| 2603 | useLocale(Locale.getDefault()); |
| 2604 | useRadix(10); |
| 2605 | clearCaches(); |
| 2606 | return this; |
| 2607 | } |
| 2608 | } |