1 /*
2 * Copyright (c) 2003, 2011, Oracle and/or its affiliates. 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. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.util;
27
28 import java.nio.file.Path;
29 import java.nio.file.Files;
30 import java.util.regex;
31 import java.io;
32 import java.math;
33 import java.nio;
34 import java.nio.channels;
35 import java.nio.charset;
36 import java.text;
37 import java.util.Locale;
38
39 import sun.misc.LRUCache;
40
41 /**
42 * A simple text scanner which can parse primitive types and strings using
43 * regular expressions.
44 *
45 * <p>A <code>Scanner</code> breaks its input into tokens using a
46 * delimiter pattern, which by default matches whitespace. The resulting
47 * tokens may then be converted into values of different types using the
48 * various <tt>next</tt> methods.
49 *
50 * <p>For example, this code allows a user to read a number from
51 * <tt>System.in</tt>:
52 * <blockquote><pre>
53 * Scanner sc = new Scanner(System.in);
54 * int i = sc.nextInt();
55 * </pre></blockquote>
56 *
57 * <p>As another example, this code allows <code>long</code> types to be
58 * assigned from entries in a file <code>myNumbers</code>:
59 * <blockquote><pre>
60 * Scanner sc = new Scanner(new File("myNumbers"));
61 * while (sc.hasNextLong()) {
62 * long aLong = sc.nextLong();
63 * }</pre></blockquote>
64 *
65 * <p>The scanner can also use delimiters other than whitespace. This
66 * example reads several items in from a string:
67 *<blockquote><pre>
68 * String input = "1 fish 2 fish red fish blue fish";
69 * Scanner s = new Scanner(input).useDelimiter("\\s*fish\\s*");
70 * System.out.println(s.nextInt());
71 * System.out.println(s.nextInt());
72 * System.out.println(s.next());
73 * System.out.println(s.next());
74 * s.close(); </pre></blockquote>
75 * <p>
76 * prints the following output:
77 * <blockquote><pre>
78 * 1
79 * 2
80 * red
81 * blue </pre></blockquote>
82 *
83 * <p>The same output can be generated with this code, which uses a regular
84 * expression to parse all four tokens at once:
85 *<blockquote><pre>
86 * String input = "1 fish 2 fish red fish blue fish";
87 * Scanner s = new Scanner(input);
88 * s.findInLine("(\\d+) fish (\\d+) fish (\\w+) fish (\\w+)");
89 * MatchResult result = s.match();
90 * for (int i=1; i<=result.groupCount(); i++)
91 * System.out.println(result.group(i));
92 * s.close(); </pre></blockquote>
93 *
94 * <p>The <a name="default-delimiter">default whitespace delimiter</a> used
95 * by a scanner is as recognized by {@link java.lang.Character}.{@link
96 * java.lang.Character#isWhitespace(char) isWhitespace}. The {@link #reset}
97 * method will reset the value of the scanner's delimiter to the default
98 * whitespace delimiter regardless of whether it was previously changed.
99 *
100 * <p>A scanning operation may block waiting for input.
101 *
102 * <p>The {@link #next} and {@link #hasNext} methods and their
103 * primitive-type companion methods (such as {@link #nextInt} and
104 * {@link #hasNextInt}) first skip any input that matches the delimiter
105 * pattern, and then attempt to return the next token. Both <tt>hasNext</tt>
106 * and <tt>next</tt> methods may block waiting for further input. Whether a
107 * <tt>hasNext</tt> method blocks has no connection to whether or not its
108 * associated <tt>next</tt> method will block.
109 *
110 * <p> The {@link #findInLine}, {@link #findWithinHorizon}, and {@link #skip}
111 * methods operate independently of the delimiter pattern. These methods will
112 * attempt to match the specified pattern with no regard to delimiters in the
113 * input and thus can be used in special circumstances where delimiters are
114 * not relevant. These methods may block waiting for more input.
115 *
116 * <p>When a scanner throws an {@link InputMismatchException}, the scanner
117 * will not pass the token that caused the exception, so that it may be
118 * retrieved or skipped via some other method.
119 *
120 * <p>Depending upon the type of delimiting pattern, empty tokens may be
121 * returned. For example, the pattern <tt>"\\s+"</tt> will return no empty
122 * tokens since it matches multiple instances of the delimiter. The delimiting
123 * pattern <tt>"\\s"</tt> could return empty tokens since it only passes one
124 * space at a time.
125 *
126 * <p> A scanner can read text from any object which implements the {@link
127 * java.lang.Readable} interface. If an invocation of the underlying
128 * readable's {@link java.lang.Readable#read} method throws an {@link
129 * java.io.IOException} then the scanner assumes that the end of the input
130 * has been reached. The most recent <tt>IOException</tt> thrown by the
131 * underlying readable can be retrieved via the {@link #ioException} method.
132 *
133 * <p>When a <code>Scanner</code> is closed, it will close its input source
134 * if the source implements the {@link java.io.Closeable} interface.
135 *
136 * <p>A <code>Scanner</code> is not safe for multithreaded use without
137 * external synchronization.
138 *
139 * <p>Unless otherwise mentioned, passing a <code>null</code> parameter into
140 * any method of a <code>Scanner</code> will cause a
141 * <code>NullPointerException</code> to be thrown.
142 *
143 * <p>A scanner will default to interpreting numbers as decimal unless a
144 * different radix has been set by using the {@link #useRadix} method. The
145 * {@link #reset} method will reset the value of the scanner's radix to
146 * <code>10</code> regardless of whether it was previously changed.
147 *
148 * <a name="localized-numbers">
149 * <h4> Localized numbers </h4>
150 *
151 * <p> An instance of this class is capable of scanning numbers in the standard
152 * formats as well as in the formats of the scanner's locale. A scanner's
153 * <a name="initial-locale">initial locale </a>is the value returned by the {@link
154 * java.util.Locale#getDefault} method; it may be changed via the {@link
155 * #useLocale} method. The {@link #reset} method will reset the value of the
156 * scanner's locale to the initial locale regardless of whether it was
157 * previously changed.
158 *
159 * <p>The localized formats are defined in terms of the following parameters,
160 * which for a particular locale are taken from that locale's {@link
161 * java.text.DecimalFormat DecimalFormat} object, <tt>df</tt>, and its and
162 * {@link java.text.DecimalFormatSymbols DecimalFormatSymbols} object,
163 * <tt>dfs</tt>.
164 *
165 * <blockquote><table>
166 * <tr><td valign="top"><i>LocalGroupSeparator </i></td>
167 * <td valign="top">The character used to separate thousands groups,
168 * <i>i.e.,</i> <tt>dfs.</tt>{@link
169 * java.text.DecimalFormatSymbols#getGroupingSeparator
170 * getGroupingSeparator()}</td></tr>
171 * <tr><td valign="top"><i>LocalDecimalSeparator </i></td>
172 * <td valign="top">The character used for the decimal point,
173 * <i>i.e.,</i> <tt>dfs.</tt>{@link
174 * java.text.DecimalFormatSymbols#getDecimalSeparator
175 * getDecimalSeparator()}</td></tr>
176 * <tr><td valign="top"><i>LocalPositivePrefix </i></td>
177 * <td valign="top">The string that appears before a positive number (may
178 * be empty), <i>i.e.,</i> <tt>df.</tt>{@link
179 * java.text.DecimalFormat#getPositivePrefix
180 * getPositivePrefix()}</td></tr>
181 * <tr><td valign="top"><i>LocalPositiveSuffix </i></td>
182 * <td valign="top">The string that appears after a positive number (may be
183 * empty), <i>i.e.,</i> <tt>df.</tt>{@link
184 * java.text.DecimalFormat#getPositiveSuffix
185 * getPositiveSuffix()}</td></tr>
186 * <tr><td valign="top"><i>LocalNegativePrefix </i></td>
187 * <td valign="top">The string that appears before a negative number (may
188 * be empty), <i>i.e.,</i> <tt>df.</tt>{@link
189 * java.text.DecimalFormat#getNegativePrefix
190 * getNegativePrefix()}</td></tr>
191 * <tr><td valign="top"><i>LocalNegativeSuffix </i></td>
192 * <td valign="top">The string that appears after a negative number (may be
193 * empty), <i>i.e.,</i> <tt>df.</tt>{@link
194 * java.text.DecimalFormat#getNegativeSuffix
195 * getNegativeSuffix()}</td></tr>
196 * <tr><td valign="top"><i>LocalNaN </i></td>
197 * <td valign="top">The string that represents not-a-number for
198 * floating-point values,
199 * <i>i.e.,</i> <tt>dfs.</tt>{@link
200 * java.text.DecimalFormatSymbols#getNaN
201 * getNaN()}</td></tr>
202 * <tr><td valign="top"><i>LocalInfinity </i></td>
203 * <td valign="top">The string that represents infinity for floating-point
204 * values, <i>i.e.,</i> <tt>dfs.</tt>{@link
205 * java.text.DecimalFormatSymbols#getInfinity
206 * getInfinity()}</td></tr>
207 * </table></blockquote>
208 *
209 * <a name="number-syntax">
210 * <h4> Number syntax </h4>
211 *
212 * <p> The strings that can be parsed as numbers by an instance of this class
213 * are specified in terms of the following regular-expression grammar, where
214 * Rmax is the highest digit in the radix being used (for example, Rmax is 9
215 * in base 10).
216 *
217 * <p>
218 * <table cellspacing=0 cellpadding=0 align=center>
219 *
220 * <tr><td valign=top align=right><i>NonASCIIDigit</i> ::</td>
221 * <td valign=top>= A non-ASCII character c for which
222 * {@link java.lang.Character#isDigit Character.isDigit}<tt>(c)</tt>
223 * returns true</td></tr>
224 *
225 * <tr><td> </td></tr>
226 *
227 * <tr><td align=right><i>Non0Digit</i> ::</td>
228 * <td><tt>= [1-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr>
229 *
230 * <tr><td> </td></tr>
231 *
232 * <tr><td align=right><i>Digit</i> ::</td>
233 * <td><tt>= [0-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr>
234 *
235 * <tr><td> </td></tr>
236 *
237 * <tr><td valign=top align=right><i>GroupedNumeral</i> ::</td>
238 * <td valign=top>
239 * <table cellpadding=0 cellspacing=0>
240 * <tr><td><tt>= ( </tt></td>
241 * <td><i>Non0Digit</i><tt>
242 * </tt><i>Digit</i><tt>?
243 * </tt><i>Digit</i><tt>?</tt></td></tr>
244 * <tr><td></td>
245 * <td><tt>( </tt><i>LocalGroupSeparator</i><tt>
246 * </tt><i>Digit</i><tt>
247 * </tt><i>Digit</i><tt>
248 * </tt><i>Digit</i><tt> )+ )</tt></td></tr>
249 * </table></td></tr>
250 *
251 * <tr><td> </td></tr>
252 *
253 * <tr><td align=right><i>Numeral</i> ::</td>
254 * <td><tt>= ( ( </tt><i>Digit</i><tt>+ )
255 * | </tt><i>GroupedNumeral</i><tt> )</tt></td></tr>
256 *
257 * <tr><td> </td></tr>
258 *
259 * <tr><td valign=top align=right>
260 * <a name="Integer-regex"><i>Integer</i> ::</td>
261 * <td valign=top><tt>= ( [-+]? ( </tt><i>Numeral</i><tt>
262 * ) )</tt></td></tr>
263 * <tr><td></td>
264 * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> </tt><i>Numeral</i><tt>
265 * </tt><i>LocalPositiveSuffix</i></td></tr>
266 * <tr><td></td>
267 * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> </tt><i>Numeral</i><tt>
268 * </tt><i>LocalNegativeSuffix</i></td></tr>
269 *
270 * <tr><td> </td></tr>
271 *
272 * <tr><td align=right><i>DecimalNumeral</i> ::</td>
273 * <td><tt>= </tt><i>Numeral</i></td></tr>
274 * <tr><td></td>
275 * <td><tt>| </tt><i>Numeral</i><tt>
276 * </tt><i>LocalDecimalSeparator</i><tt>
277 * </tt><i>Digit</i><tt>*</tt></td></tr>
278 * <tr><td></td>
279 * <td><tt>| </tt><i>LocalDecimalSeparator</i><tt>
280 * </tt><i>Digit</i><tt>+</tt></td></tr>
281 *
282 * <tr><td> </td></tr>
283 *
284 * <tr><td align=right><i>Exponent</i> ::</td>
285 * <td><tt>= ( [eE] [+-]? </tt><i>Digit</i><tt>+ )</tt></td></tr>
286 *
287 * <tr><td> </td></tr>
288 *
289 * <tr><td align=right>
290 * <a name="Decimal-regex"><i>Decimal</i> ::</td>
291 * <td><tt>= ( [-+]? </tt><i>DecimalNumeral</i><tt>
292 * </tt><i>Exponent</i><tt>? )</tt></td></tr>
293 * <tr><td></td>
294 * <td><tt>| </tt><i>LocalPositivePrefix</i><tt>
295 * </tt><i>DecimalNumeral</i><tt>
296 * </tt><i>LocalPositiveSuffix</i>
297 * </tt><i>Exponent</i><tt>?</td></tr>
298 * <tr><td></td>
299 * <td><tt>| </tt><i>LocalNegativePrefix</i><tt>
300 * </tt><i>DecimalNumeral</i><tt>
301 * </tt><i>LocalNegativeSuffix</i>
302 * </tt><i>Exponent</i><tt>?</td></tr>
303 *
304 * <tr><td> </td></tr>
305 *
306 * <tr><td align=right><i>HexFloat</i> ::</td>
307 * <td><tt>= [-+]? 0[xX][0-9a-fA-F]*\.[0-9a-fA-F]+
308 * ([pP][-+]?[0-9]+)?</tt></td></tr>
309 *
310 * <tr><td> </td></tr>
311 *
312 * <tr><td align=right><i>NonNumber</i> ::</td>
313 * <td valign=top><tt>= NaN
314 * | </tt><i>LocalNan</i><tt>
315 * | Infinity
316 * | </tt><i>LocalInfinity</i></td></tr>
317 *
318 * <tr><td> </td></tr>
319 *
320 * <tr><td align=right><i>SignedNonNumber</i> ::</td>
321 * <td><tt>= ( [-+]? </tt><i>NonNumber</i><tt> )</tt></td></tr>
322 * <tr><td></td>
323 * <td><tt>| </tt><i>LocalPositivePrefix</i><tt>
324 * </tt><i>NonNumber</i><tt>
325 * </tt><i>LocalPositiveSuffix</i></td></tr>
326 * <tr><td></td>
327 * <td><tt>| </tt><i>LocalNegativePrefix</i><tt>
328 * </tt><i>NonNumber</i><tt>
329 * </tt><i>LocalNegativeSuffix</i></td></tr>
330 *
331 * <tr><td> </td></tr>
332 *
333 * <tr><td valign=top align=right>
334 * <a name="Float-regex"><i>Float</i> ::</td>
335 * <td valign=top><tt>= </tt><i>Decimal</i><tt></td></tr>
336 * <tr><td></td>
337 * <td><tt>| </tt><i>HexFloat</i><tt></td></tr>
338 * <tr><td></td>
339 * <td><tt>| </tt><i>SignedNonNumber</i><tt></td></tr>
340 *
341 * </table>
342 * </center>
343 *
344 * <p> Whitespace is not significant in the above regular expressions.
345 *
346 * @since 1.5
347 */
348 public final class Scanner implements Iterator<String>, Closeable {
349
350 // Internal buffer used to hold input
351 private CharBuffer buf;
352
353 // Size of internal character buffer
354 private static final int BUFFER_SIZE = 1024; // change to 1024;
355
356 // The index into the buffer currently held by the Scanner
357 private int position;
358
359 // Internal matcher used for finding delimiters
360 private Matcher matcher;
361
362 // Pattern used to delimit tokens
363 private Pattern delimPattern;
364
365 // Pattern found in last hasNext operation
366 private Pattern hasNextPattern;
367
368 // Position after last hasNext operation
369 private int hasNextPosition;
370
371 // Result after last hasNext operation
372 private String hasNextResult;
373
374 // The input source
375 private Readable source;
376
377 // Boolean is true if source is done
378 private boolean sourceClosed = false;
379
380 // Boolean indicating more input is required
381 private boolean needInput = false;
382
383 // Boolean indicating if a delim has been skipped this operation
384 private boolean skipped = false;
385
386 // A store of a position that the scanner may fall back to
387 private int savedScannerPosition = -1;
388
389 // A cache of the last primitive type scanned
390 private Object typeCache = null;
391
392 // Boolean indicating if a match result is available
393 private boolean matchValid = false;
394
395 // Boolean indicating if this scanner has been closed
396 private boolean closed = false;
397
398 // The current radix used by this scanner
399 private int radix = 10;
400
401 // The default radix for this scanner
402 private int defaultRadix = 10;
403
404 // The locale used by this scanner
405 private Locale locale = null;
406
407 // A cache of the last few recently used Patterns
408 private LRUCache<String,Pattern> patternCache =
409 new LRUCache<String,Pattern>(7) {
410 protected Pattern create(String s) {
411 return Pattern.compile(s);
412 }
413 protected boolean hasName(Pattern p, String s) {
414 return p.pattern().equals(s);
415 }
416 };
417
418 // A holder of the last IOException encountered
419 private IOException lastException;
420
421 // A pattern for java whitespace
422 private static Pattern WHITESPACE_PATTERN = Pattern.compile(
423 "\\p{javaWhitespace}+");
424
425 // A pattern for any token
426 private static Pattern FIND_ANY_PATTERN = Pattern.compile("(?s).*");
427
428 // A pattern for non-ASCII digits
429 private static Pattern NON_ASCII_DIGIT = Pattern.compile(
430 "[\\p{javaDigit}&&[^0-9]]");
431
432 // Fields and methods to support scanning primitive types
433
434 /**
435 * Locale dependent values used to scan numbers
436 */
437 private String groupSeparator = "\\,";
438 private String decimalSeparator = "\\.";
439 private String nanString = "NaN";
440 private String infinityString = "Infinity";
441 private String positivePrefix = "";
442 private String negativePrefix = "\\-";
443 private String positiveSuffix = "";
444 private String negativeSuffix = "";
445
446 /**
447 * Fields and an accessor method to match booleans
448 */
449 private static volatile Pattern boolPattern;
450 private static final String BOOLEAN_PATTERN = "true|false";
451 private static Pattern boolPattern() {
452 Pattern bp = boolPattern;
453 if (bp == null)
454 boolPattern = bp = Pattern.compile(BOOLEAN_PATTERN,
455 Pattern.CASE_INSENSITIVE);
456 return bp;
457 }
458
459 /**
460 * Fields and methods to match bytes, shorts, ints, and longs
461 */
462 private Pattern integerPattern;
463 private String digits = "0123456789abcdefghijklmnopqrstuvwxyz";
464 private String non0Digit = "[\\p{javaDigit}&&[^0]]";
465 private int SIMPLE_GROUP_INDEX = 5;
466 private String buildIntegerPatternString() {
467 String radixDigits = digits.substring(0, radix);
468 // \\p{javaDigit} is not guaranteed to be appropriate
469 // here but what can we do? The final authority will be
470 // whatever parse method is invoked, so ultimately the
471 // Scanner will do the right thing
472 String digit = "((?i)["+radixDigits+"]|\\p{javaDigit})";
473 String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+
474 groupSeparator+digit+digit+digit+")+)";
475 // digit++ is the possessive form which is necessary for reducing
476 // backtracking that would otherwise cause unacceptable performance
477 String numeral = "(("+ digit+"++)|"+groupedNumeral+")";
478 String javaStyleInteger = "([-+]?(" + numeral + "))";
479 String negativeInteger = negativePrefix + numeral + negativeSuffix;
480 String positiveInteger = positivePrefix + numeral + positiveSuffix;
481 return "("+ javaStyleInteger + ")|(" +
482 positiveInteger + ")|(" +
483 negativeInteger + ")";
484 }
485 private Pattern integerPattern() {
486 if (integerPattern == null) {
487 integerPattern = patternCache.forName(buildIntegerPatternString());
488 }
489 return integerPattern;
490 }
491
492 /**
493 * Fields and an accessor method to match line separators
494 */
495 private static volatile Pattern separatorPattern;
496 private static volatile Pattern linePattern;
497 private static final String LINE_SEPARATOR_PATTERN =
498 "\r\n|[\n\r\u2028\u2029\u0085]";
499 private static final String LINE_PATTERN = ".*("+LINE_SEPARATOR_PATTERN+")|.+$";
500
501 private static Pattern separatorPattern() {
502 Pattern sp = separatorPattern;
503 if (sp == null)
504 separatorPattern = sp = Pattern.compile(LINE_SEPARATOR_PATTERN);
505 return sp;
506 }
507
508 private static Pattern linePattern() {
509 Pattern lp = linePattern;
510 if (lp == null)
511 linePattern = lp = Pattern.compile(LINE_PATTERN);
512 return lp;
513 }
514
515 /**
516 * Fields and methods to match floats and doubles
517 */
518 private Pattern floatPattern;
519 private Pattern decimalPattern;
520 private void buildFloatAndDecimalPattern() {
521 // \\p{javaDigit} may not be perfect, see above
522 String digit = "([0-9]|(\\p{javaDigit}))";
523 String exponent = "([eE][+-]?"+digit+"+)?";
524 String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+
525 groupSeparator+digit+digit+digit+")+)";
526 // Once again digit++ is used for performance, as above
527 String numeral = "(("+digit+"++)|"+groupedNumeral+")";
528 String decimalNumeral = "("+numeral+"|"+numeral +
529 decimalSeparator + digit + "*+|"+ decimalSeparator +
530 digit + "++)";
531 String nonNumber = "(NaN|"+nanString+"|Infinity|"+
532 infinityString+")";
533 String positiveFloat = "(" + positivePrefix + decimalNumeral +
534 positiveSuffix + exponent + ")";
535 String negativeFloat = "(" + negativePrefix + decimalNumeral +
536 negativeSuffix + exponent + ")";
537 String decimal = "(([-+]?" + decimalNumeral + exponent + ")|"+
538 positiveFloat + "|" + negativeFloat + ")";
539 String hexFloat =
540 "[-+]?0[xX][0-9a-fA-F]*\\.[0-9a-fA-F]+([pP][-+]?[0-9]+)?";
541 String positiveNonNumber = "(" + positivePrefix + nonNumber +
542 positiveSuffix + ")";
543 String negativeNonNumber = "(" + negativePrefix + nonNumber +
544 negativeSuffix + ")";
545 String signedNonNumber = "(([-+]?"+nonNumber+")|" +
546 positiveNonNumber + "|" +
547 negativeNonNumber + ")";
548 floatPattern = Pattern.compile(decimal + "|" + hexFloat + "|" +
549 signedNonNumber);
550 decimalPattern = Pattern.compile(decimal);
551 }
552 private Pattern floatPattern() {
553 if (floatPattern == null) {
554 buildFloatAndDecimalPattern();
555 }
556 return floatPattern;
557 }
558 private Pattern decimalPattern() {
559 if (decimalPattern == null) {
560 buildFloatAndDecimalPattern();
561 }
562 return decimalPattern;
563 }
564
565 // Constructors
566
567 /**
568 * Constructs a <code>Scanner</code> that returns values scanned
569 * from the specified source delimited by the specified pattern.
570 *
571 * @param source A character source implementing the Readable interface
572 * @param pattern A delimiting pattern
573 * @return A scanner with the specified source and pattern
574 */
575 private Scanner(Readable source, Pattern pattern) {
576 assert source != null : "source should not be null";
577 assert pattern != null : "pattern should not be null";
578 this.source = source;
579 delimPattern = pattern;
580 buf = CharBuffer.allocate(BUFFER_SIZE);
581 buf.limit(0);
582 matcher = delimPattern.matcher(buf);
583 matcher.useTransparentBounds(true);
584 matcher.useAnchoringBounds(false);
585 useLocale(Locale.getDefault(Locale.Category.FORMAT));
586 }
587
588 /**
589 * Constructs a new <code>Scanner</code> that produces values scanned
590 * from the specified source.
591 *
592 * @param source A character source implementing the {@link Readable}
593 * interface
594 */
595 public Scanner(Readable source) {
596 this(Objects.requireNonNull(source, "source"), WHITESPACE_PATTERN);
597 }
598
599 /**
600 * Constructs a new <code>Scanner</code> that produces values scanned
601 * from the specified input stream. Bytes from the stream are converted
602 * into characters using the underlying platform's
603 * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}.
604 *
605 * @param source An input stream to be scanned
606 */
607 public Scanner(InputStream source) {
608 this(new InputStreamReader(source), WHITESPACE_PATTERN);
609 }
610
611 /**
612 * Constructs a new <code>Scanner</code> that produces values scanned
613 * from the specified input stream. Bytes from the stream are converted
614 * into characters using the specified charset.
615 *
616 * @param source An input stream to be scanned
617 * @param charsetName The encoding type used to convert bytes from the
618 * stream into characters to be scanned
619 * @throws IllegalArgumentException if the specified character set
620 * does not exist
621 */
622 public Scanner(InputStream source, String charsetName) {
623 this(makeReadable(Objects.requireNonNull(source, "source"), toCharset(charsetName)),
624 WHITESPACE_PATTERN);
625 }
626
627 /**
628 * Returns a charset object for the given charset name.
629 * @throws NullPointerException is csn is null
630 * @throws IllegalArgumentException if the charset is not supported
631 */
632 private static Charset toCharset(String csn) {
633 Objects.requireNonNull(csn, "charsetName");
634 try {
635 return Charset.forName(csn);
636 } catch (IllegalCharsetNameException|UnsupportedCharsetException e) {
637 // IllegalArgumentException should be thrown
638 throw new IllegalArgumentException(e);
639 }
640 }
641
642 private static Readable makeReadable(InputStream source, Charset charset) {
643 return new InputStreamReader(source, charset);
644 }
645
646 /**
647 * Constructs a new <code>Scanner</code> that produces values scanned
648 * from the specified file. Bytes from the file are converted into
649 * characters using the underlying platform's
650 * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}.
651 *
652 * @param source A file to be scanned
653 * @throws FileNotFoundException if source is not found
654 */
655 public Scanner(File source) throws FileNotFoundException {
656 this((ReadableByteChannel)(new FileInputStream(source).getChannel()));
657 }
658
659 /**
660 * Constructs a new <code>Scanner</code> that produces values scanned
661 * from the specified file. Bytes from the file are converted into
662 * characters using the specified charset.
663 *
664 * @param source A file to be scanned
665 * @param charsetName The encoding type used to convert bytes from the file
666 * into characters to be scanned
667 * @throws FileNotFoundException if source is not found
668 * @throws IllegalArgumentException if the specified encoding is
669 * not found
670 */
671 public Scanner(File source, String charsetName)
672 throws FileNotFoundException
673 {
674 this(Objects.requireNonNull(source), toDecoder(charsetName));
675 }
676
677 private Scanner(File source, CharsetDecoder dec)
678 throws FileNotFoundException
679 {
680 this(makeReadable((ReadableByteChannel)(new FileInputStream(source).getChannel()), dec));
681 }
682
683 private static CharsetDecoder toDecoder(String charsetName) {
684 Objects.requireNonNull(charsetName, "charsetName");
685 try {
686 return Charset.forName(charsetName).newDecoder();
687 } catch (IllegalCharsetNameException|UnsupportedCharsetException unused) {
688 throw new IllegalArgumentException(charsetName);
689 }
690 }
691
692 private static Readable makeReadable(ReadableByteChannel source,
693 CharsetDecoder dec) {
694 return Channels.newReader(source, dec, -1);
695 }
696
697 /**
698 * Constructs a new <code>Scanner</code> that produces values scanned
699 * from the specified file. Bytes from the file are converted into
700 * characters using the underlying platform's
701 * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}.
702 *
703 * @param source
704 * the path to the file to be scanned
705 * @throws IOException
706 * if an I/O error occurs opening source
707 *
708 * @since 1.7
709 */
710 public Scanner(Path source)
711 throws IOException
712 {
713 this(Files.newInputStream(source));
714 }
715
716 /**
717 * Constructs a new <code>Scanner</code> that produces values scanned
718 * from the specified file. Bytes from the file are converted into
719 * characters using the specified charset.
720 *
721 * @param source
722 * the path to the file to be scanned
723 * @param charsetName
724 * The encoding type used to convert bytes from the file
725 * into characters to be scanned
726 * @throws IOException
727 * if an I/O error occurs opening source
728 * @throws IllegalArgumentException
729 * if the specified encoding is not found
730 * @since 1.7
731 */
732 public Scanner(Path source, String charsetName) throws IOException {
733 this(Objects.requireNonNull(source), toCharset(charsetName));
734 }
735
736 private Scanner(Path source, Charset charset) throws IOException {
737 this(makeReadable(Files.newInputStream(source), charset));
738 }
739
740 /**
741 * Constructs a new <code>Scanner</code> that produces values scanned
742 * from the specified string.
743 *
744 * @param source A string to scan
745 */
746 public Scanner(String source) {
747 this(new StringReader(source), WHITESPACE_PATTERN);
748 }
749
750 /**
751 * Constructs a new <code>Scanner</code> that produces values scanned
752 * from the specified channel. Bytes from the source are converted into
753 * characters using the underlying platform's
754 * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}.
755 *
756 * @param source A channel to scan
757 */
758 public Scanner(ReadableByteChannel source) {
759 this(makeReadable(Objects.requireNonNull(source, "source")),
760 WHITESPACE_PATTERN);
761 }
762
763 private static Readable makeReadable(ReadableByteChannel source) {
764 return makeReadable(source, Charset.defaultCharset().newDecoder());
765 }
766
767 /**
768 * Constructs a new <code>Scanner</code> that produces values scanned
769 * from the specified channel. Bytes from the source are converted into
770 * characters using the specified charset.
771 *
772 * @param source A channel to scan
773 * @param charsetName The encoding type used to convert bytes from the
774 * channel into characters to be scanned
775 * @throws IllegalArgumentException if the specified character set
776 * does not exist
777 */
778 public Scanner(ReadableByteChannel source, String charsetName) {
779 this(makeReadable(Objects.requireNonNull(source, "source"), toDecoder(charsetName)),
780 WHITESPACE_PATTERN);
781 }
782
783 // Private primitives used to support scanning
784
785 private void saveState() {
786 savedScannerPosition = position;
787 }
788
789 private void revertState() {
790 this.position = savedScannerPosition;
791 savedScannerPosition = -1;
792 skipped = false;
793 }
794
795 private boolean revertState(boolean b) {
796 this.position = savedScannerPosition;
797 savedScannerPosition = -1;
798 skipped = false;
799 return b;
800 }
801
802 private void cacheResult() {
803 hasNextResult = matcher.group();
804 hasNextPosition = matcher.end();
805 hasNextPattern = matcher.pattern();
806 }
807
808 private void cacheResult(String result) {
809 hasNextResult = result;
810 hasNextPosition = matcher.end();
811 hasNextPattern = matcher.pattern();
812 }
813
814 // Clears both regular cache and type cache
815 private void clearCaches() {
816 hasNextPattern = null;
817 typeCache = null;
818 }
819
820 // Also clears both the regular cache and the type cache
821 private String getCachedResult() {
822 position = hasNextPosition;
823 hasNextPattern = null;
824 typeCache = null;
825 return hasNextResult;
826 }
827
828 // Also clears both the regular cache and the type cache
829 private void useTypeCache() {
830 if (closed)
831 throw new IllegalStateException("Scanner closed");
832 position = hasNextPosition;
833 hasNextPattern = null;
834 typeCache = null;
835 }
836
837 // Tries to read more input. May block.
838 private void readInput() {
839 if (buf.limit() == buf.capacity())
840 makeSpace();
841
842 // Prepare to receive data
843 int p = buf.position();
844 buf.position(buf.limit());
845 buf.limit(buf.capacity());
846
847 int n = 0;
848 try {
849 n = source.read(buf);
850 } catch (IOException ioe) {
851 lastException = ioe;
852 n = -1;
853 }
854
855 if (n == -1) {
856 sourceClosed = true;
857 needInput = false;
858 }
859
860 if (n > 0)
861 needInput = false;
862
863 // Restore current position and limit for reading
864 buf.limit(buf.position());
865 buf.position(p);
866 }
867
868 // After this method is called there will either be an exception
869 // or else there will be space in the buffer
870 private boolean makeSpace() {
871 clearCaches();
872 int offset = savedScannerPosition == -1 ?
873 position : savedScannerPosition;
874 buf.position(offset);
875 // Gain space by compacting buffer
876 if (offset > 0) {
877 buf.compact();
878 translateSavedIndexes(offset);
879 position -= offset;
880 buf.flip();
881 return true;
882 }
883 // Gain space by growing buffer
884 int newSize = buf.capacity() * 2;
885 CharBuffer newBuf = CharBuffer.allocate(newSize);
886 newBuf.put(buf);
887 newBuf.flip();
888 translateSavedIndexes(offset);
889 position -= offset;
890 buf = newBuf;
891 matcher.reset(buf);
892 return true;
893 }
894
895 // When a buffer compaction/reallocation occurs the saved indexes must
896 // be modified appropriately
897 private void translateSavedIndexes(int offset) {
898 if (savedScannerPosition != -1)
899 savedScannerPosition -= offset;
900 }
901
902 // If we are at the end of input then NoSuchElement;
903 // If there is still input left then InputMismatch
904 private void throwFor() {
905 skipped = false;
906 if ((sourceClosed) && (position == buf.limit()))
907 throw new NoSuchElementException();
908 else
909 throw new InputMismatchException();
910 }
911
912 // Returns true if a complete token or partial token is in the buffer.
913 // It is not necessary to find a complete token since a partial token
914 // means that there will be another token with or without more input.
915 private boolean hasTokenInBuffer() {
916 matchValid = false;
917 matcher.usePattern(delimPattern);
918 matcher.region(position, buf.limit());
919
920 // Skip delims first
921 if (matcher.lookingAt())
922 position = matcher.end();
923
924 // If we are sitting at the end, no more tokens in buffer
925 if (position == buf.limit())
926 return false;
927
928 return true;
929 }
930
931 /*
932 * Returns a "complete token" that matches the specified pattern
933 *
934 * A token is complete if surrounded by delims; a partial token
935 * is prefixed by delims but not postfixed by them
936 *
937 * The position is advanced to the end of that complete token
938 *
939 * Pattern == null means accept any token at all
940 *
941 * Triple return:
942 * 1. valid string means it was found
943 * 2. null with needInput=false means we won't ever find it
944 * 3. null with needInput=true means try again after readInput
945 */
946 private String getCompleteTokenInBuffer(Pattern pattern) {
947 matchValid = false;
948
949 // Skip delims first
950 matcher.usePattern(delimPattern);
951 if (!skipped) { // Enforcing only one skip of leading delims
952 matcher.region(position, buf.limit());
953 if (matcher.lookingAt()) {
954 // If more input could extend the delimiters then we must wait
955 // for more input
956 if (matcher.hitEnd() && !sourceClosed) {
957 needInput = true;
958 return null;
959 }
960 // The delims were whole and the matcher should skip them
961 skipped = true;
962 position = matcher.end();
963 }
964 }
965
966 // If we are sitting at the end, no more tokens in buffer
967 if (position == buf.limit()) {
968 if (sourceClosed)
969 return null;
970 needInput = true;
971 return null;
972 }
973
974 // Must look for next delims. Simply attempting to match the
975 // pattern at this point may find a match but it might not be
976 // the first longest match because of missing input, or it might
977 // match a partial token instead of the whole thing.
978
979 // Then look for next delims
980 matcher.region(position, buf.limit());
981 boolean foundNextDelim = matcher.find();
982 if (foundNextDelim && (matcher.end() == position)) {
983 // Zero length delimiter match; we should find the next one
984 // using the automatic advance past a zero length match;
985 // Otherwise we have just found the same one we just skipped
986 foundNextDelim = matcher.find();
987 }
988 if (foundNextDelim) {
989 // In the rare case that more input could cause the match
990 // to be lost and there is more input coming we must wait
991 // for more input. Note that hitting the end is okay as long
992 // as the match cannot go away. It is the beginning of the
993 // next delims we want to be sure about, we don't care if
994 // they potentially extend further.
995 if (matcher.requireEnd() && !sourceClosed) {
996 needInput = true;
997 return null;
998 }
999 int tokenEnd = matcher.start();
1000 // There is a complete token.
1001 if (pattern == null) {
1002 // Must continue with match to provide valid MatchResult
1003 pattern = FIND_ANY_PATTERN;
1004 }
1005 // Attempt to match against the desired pattern
1006 matcher.usePattern(pattern);
1007 matcher.region(position, tokenEnd);
1008 if (matcher.matches()) {
1009 String s = matcher.group();
1010 position = matcher.end();
1011 return s;
1012 } else { // Complete token but it does not match
1013 return null;
1014 }
1015 }
1016
1017 // If we can't find the next delims but no more input is coming,
1018 // then we can treat the remainder as a whole token
1019 if (sourceClosed) {
1020 if (pattern == null) {
1021 // Must continue with match to provide valid MatchResult
1022 pattern = FIND_ANY_PATTERN;
1023 }
1024 // Last token; Match the pattern here or throw
1025 matcher.usePattern(pattern);
1026 matcher.region(position, buf.limit());
1027 if (matcher.matches()) {
1028 String s = matcher.group();
1029 position = matcher.end();
1030 return s;
1031 }
1032 // Last piece does not match
1033 return null;
1034 }
1035
1036 // There is a partial token in the buffer; must read more
1037 // to complete it
1038 needInput = true;
1039 return null;
1040 }
1041
1042 // Finds the specified pattern in the buffer up to horizon.
1043 // Returns a match for the specified input pattern.
1044 private String findPatternInBuffer(Pattern pattern, int horizon) {
1045 matchValid = false;
1046 matcher.usePattern(pattern);
1047 int bufferLimit = buf.limit();
1048 int horizonLimit = -1;
1049 int searchLimit = bufferLimit;
1050 if (horizon > 0) {
1051 horizonLimit = position + horizon;
1052 if (horizonLimit < bufferLimit)
1053 searchLimit = horizonLimit;
1054 }
1055 matcher.region(position, searchLimit);
1056 if (matcher.find()) {
1057 if (matcher.hitEnd() && (!sourceClosed)) {
1058 // The match may be longer if didn't hit horizon or real end
1059 if (searchLimit != horizonLimit) {
1060 // Hit an artificial end; try to extend the match
1061 needInput = true;
1062 return null;
1063 }
1064 // The match could go away depending on what is next
1065 if ((searchLimit == horizonLimit) && matcher.requireEnd()) {
1066 // Rare case: we hit the end of input and it happens
1067 // that it is at the horizon and the end of input is
1068 // required for the match.
1069 needInput = true;
1070 return null;
1071 }
1072 }
1073 // Did not hit end, or hit real end, or hit horizon
1074 position = matcher.end();
1075 return matcher.group();
1076 }
1077
1078 if (sourceClosed)
1079 return null;
1080
1081 // If there is no specified horizon, or if we have not searched
1082 // to the specified horizon yet, get more input
1083 if ((horizon == 0) || (searchLimit != horizonLimit))
1084 needInput = true;
1085 return null;
1086 }
1087
1088 // Returns a match for the specified input pattern anchored at
1089 // the current position
1090 private String matchPatternInBuffer(Pattern pattern) {
1091 matchValid = false;
1092 matcher.usePattern(pattern);
1093 matcher.region(position, buf.limit());
1094 if (matcher.lookingAt()) {
1095 if (matcher.hitEnd() && (!sourceClosed)) {
1096 // Get more input and try again
1097 needInput = true;
1098 return null;
1099 }
1100 position = matcher.end();
1101 return matcher.group();
1102 }
1103
1104 if (sourceClosed)
1105 return null;
1106
1107 // Read more to find pattern
1108 needInput = true;
1109 return null;
1110 }
1111
1112 // Throws if the scanner is closed
1113 private void ensureOpen() {
1114 if (closed)
1115 throw new IllegalStateException("Scanner closed");
1116 }
1117
1118 // Public methods
1119
1120 /**
1121 * Closes this scanner.
1122 *
1123 * <p> If this scanner has not yet been closed then if its underlying
1124 * {@linkplain java.lang.Readable readable} also implements the {@link
1125 * java.io.Closeable} interface then the readable's <tt>close</tt> method
1126 * will be invoked. If this scanner is already closed then invoking this
1127 * method will have no effect.
1128 *
1129 * <p>Attempting to perform search operations after a scanner has
1130 * been closed will result in an {@link IllegalStateException}.
1131 *
1132 */
1133 public void close() {
1134 if (closed)
1135 return;
1136 if (source instanceof Closeable) {
1137 try {
1138 ((Closeable)source).close();
1139 } catch (IOException ioe) {
1140 lastException = ioe;
1141 }
1142 }
1143 sourceClosed = true;
1144 source = null;
1145 closed = true;
1146 }
1147
1148 /**
1149 * Returns the <code>IOException</code> last thrown by this
1150 * <code>Scanner</code>'s underlying <code>Readable</code>. This method
1151 * returns <code>null</code> if no such exception exists.
1152 *
1153 * @return the last exception thrown by this scanner's readable
1154 */
1155 public IOException ioException() {
1156 return lastException;
1157 }
1158
1159 /**
1160 * Returns the <code>Pattern</code> this <code>Scanner</code> is currently
1161 * using to match delimiters.
1162 *
1163 * @return this scanner's delimiting pattern.
1164 */
1165 public Pattern delimiter() {
1166 return delimPattern;
1167 }
1168
1169 /**
1170 * Sets this scanner's delimiting pattern to the specified pattern.
1171 *
1172 * @param pattern A delimiting pattern
1173 * @return this scanner
1174 */
1175 public Scanner useDelimiter(Pattern pattern) {
1176 delimPattern = pattern;
1177 return this;
1178 }
1179
1180 /**
1181 * Sets this scanner's delimiting pattern to a pattern constructed from
1182 * the specified <code>String</code>.
1183 *
1184 * <p> An invocation of this method of the form
1185 * <tt>useDelimiter(pattern)</tt> behaves in exactly the same way as the
1186 * invocation <tt>useDelimiter(Pattern.compile(pattern))</tt>.
1187 *
1188 * <p> Invoking the {@link #reset} method will set the scanner's delimiter
1189 * to the <a href= "#default-delimiter">default</a>.
1190 *
1191 * @param pattern A string specifying a delimiting pattern
1192 * @return this scanner
1193 */
1194 public Scanner useDelimiter(String pattern) {
1195 delimPattern = patternCache.forName(pattern);
1196 return this;
1197 }
1198
1199 /**
1200 * Returns this scanner's locale.
1201 *
1202 * <p>A scanner's locale affects many elements of its default
1203 * primitive matching regular expressions; see
1204 * <a href= "#localized-numbers">localized numbers</a> above.
1205 *
1206 * @return this scanner's locale
1207 */
1208 public Locale locale() {
1209 return this.locale;
1210 }
1211
1212 /**
1213 * Sets this scanner's locale to the specified locale.
1214 *
1215 * <p>A scanner's locale affects many elements of its default
1216 * primitive matching regular expressions; see
1217 * <a href= "#localized-numbers">localized numbers</a> above.
1218 *
1219 * <p>Invoking the {@link #reset} method will set the scanner's locale to
1220 * the <a href= "#initial-locale">initial locale</a>.
1221 *
1222 * @param locale A string specifying the locale to use
1223 * @return this scanner
1224 */
1225 public Scanner useLocale(Locale locale) {
1226 if (locale.equals(this.locale))
1227 return this;
1228
1229 this.locale = locale;
1230 DecimalFormat df =
1231 (DecimalFormat)NumberFormat.getNumberInstance(locale);
1232 DecimalFormatSymbols dfs = DecimalFormatSymbols.getInstance(locale);
1233
1234 // These must be literalized to avoid collision with regex
1235 // metacharacters such as dot or parenthesis
1236 groupSeparator = "\\" + dfs.getGroupingSeparator();
1237 decimalSeparator = "\\" + dfs.getDecimalSeparator();
1238
1239 // Quoting the nonzero length locale-specific things
1240 // to avoid potential conflict with metacharacters
1241 nanString = "\\Q" + dfs.getNaN() + "\\E";
1242 infinityString = "\\Q" + dfs.getInfinity() + "\\E";
1243 positivePrefix = df.getPositivePrefix();
1244 if (positivePrefix.length() > 0)
1245 positivePrefix = "\\Q" + positivePrefix + "\\E";
1246 negativePrefix = df.getNegativePrefix();
1247 if (negativePrefix.length() > 0)
1248 negativePrefix = "\\Q" + negativePrefix + "\\E";
1249 positiveSuffix = df.getPositiveSuffix();
1250 if (positiveSuffix.length() > 0)
1251 positiveSuffix = "\\Q" + positiveSuffix + "\\E";
1252 negativeSuffix = df.getNegativeSuffix();
1253 if (negativeSuffix.length() > 0)
1254 negativeSuffix = "\\Q" + negativeSuffix + "\\E";
1255
1256 // Force rebuilding and recompilation of locale dependent
1257 // primitive patterns
1258 integerPattern = null;
1259 floatPattern = null;
1260
1261 return this;
1262 }
1263
1264 /**
1265 * Returns this scanner's default radix.
1266 *
1267 * <p>A scanner's radix affects elements of its default
1268 * number matching regular expressions; see
1269 * <a href= "#localized-numbers">localized numbers</a> above.
1270 *
1271 * @return the default radix of this scanner
1272 */
1273 public int radix() {
1274 return this.defaultRadix;
1275 }
1276
1277 /**
1278 * Sets this scanner's default radix to the specified radix.
1279 *
1280 * <p>A scanner's radix affects elements of its default
1281 * number matching regular expressions; see
1282 * <a href= "#localized-numbers">localized numbers</a> above.
1283 *
1284 * <p>If the radix is less than <code>Character.MIN_RADIX</code>
1285 * or greater than <code>Character.MAX_RADIX</code>, then an
1286 * <code>IllegalArgumentException</code> is thrown.
1287 *
1288 * <p>Invoking the {@link #reset} method will set the scanner's radix to
1289 * <code>10</code>.
1290 *
1291 * @param radix The radix to use when scanning numbers
1292 * @return this scanner
1293 * @throws IllegalArgumentException if radix is out of range
1294 */
1295 public Scanner useRadix(int radix) {
1296 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX))
1297 throw new IllegalArgumentException("radix:"+radix);
1298
1299 if (this.defaultRadix == radix)
1300 return this;
1301 this.defaultRadix = radix;
1302 // Force rebuilding and recompilation of radix dependent patterns
1303 integerPattern = null;
1304 return this;
1305 }
1306
1307 // The next operation should occur in the specified radix but
1308 // the default is left untouched.
1309 private void setRadix(int radix) {
1310 if (this.radix != radix) {
1311 // Force rebuilding and recompilation of radix dependent patterns
1312 integerPattern = null;
1313 this.radix = radix;
1314 }
1315 }
1316
1317 /**
1318 * Returns the match result of the last scanning operation performed
1319 * by this scanner. This method throws <code>IllegalStateException</code>
1320 * if no match has been performed, or if the last match was
1321 * not successful.
1322 *
1323 * <p>The various <code>next</code>methods of <code>Scanner</code>
1324 * make a match result available if they complete without throwing an
1325 * exception. For instance, after an invocation of the {@link #nextInt}
1326 * method that returned an int, this method returns a
1327 * <code>MatchResult</code> for the search of the
1328 * <a href="#Integer-regex"><i>Integer</i></a> regular expression
1329 * defined above. Similarly the {@link #findInLine},
1330 * {@link #findWithinHorizon}, and {@link #skip} methods will make a
1331 * match available if they succeed.
1332 *
1333 * @return a match result for the last match operation
1334 * @throws IllegalStateException If no match result is available
1335 */
1336 public MatchResult match() {
1337 if (!matchValid)
1338 throw new IllegalStateException("No match result available");
1339 return matcher.toMatchResult();
1340 }
1341
1342 /**
1343 * <p>Returns the string representation of this <code>Scanner</code>. The
1344 * string representation of a <code>Scanner</code> contains information
1345 * that may be useful for debugging. The exact format is unspecified.
1346 *
1347 * @return The string representation of this scanner
1348 */
1349 public String toString() {
1350 StringBuilder sb = new StringBuilder();
1351 sb.append("java.util.Scanner");
1352 sb.append("[delimiters=" + delimPattern + "]");
1353 sb.append("[position=" + position + "]");
1354 sb.append("[match valid=" + matchValid + "]");
1355 sb.append("[need input=" + needInput + "]");
1356 sb.append("[source closed=" + sourceClosed + "]");
1357 sb.append("[skipped=" + skipped + "]");
1358 sb.append("[group separator=" + groupSeparator + "]");
1359 sb.append("[decimal separator=" + decimalSeparator + "]");
1360 sb.append("[positive prefix=" + positivePrefix + "]");
1361 sb.append("[negative prefix=" + negativePrefix + "]");
1362 sb.append("[positive suffix=" + positiveSuffix + "]");
1363 sb.append("[negative suffix=" + negativeSuffix + "]");
1364 sb.append("[NaN string=" + nanString + "]");
1365 sb.append("[infinity string=" + infinityString + "]");
1366 return sb.toString();
1367 }
1368
1369 /**
1370 * Returns true if this scanner has another token in its input.
1371 * This method may block while waiting for input to scan.
1372 * The scanner does not advance past any input.
1373 *
1374 * @return true if and only if this scanner has another token
1375 * @throws IllegalStateException if this scanner is closed
1376 * @see java.util.Iterator
1377 */
1378 public boolean hasNext() {
1379 ensureOpen();
1380 saveState();
1381 while (!sourceClosed) {
1382 if (hasTokenInBuffer())
1383 return revertState(true);
1384 readInput();
1385 }
1386 boolean result = hasTokenInBuffer();
1387 return revertState(result);
1388 }
1389
1390 /**
1391 * Finds and returns the next complete token from this scanner.
1392 * A complete token is preceded and followed by input that matches
1393 * the delimiter pattern. This method may block while waiting for input
1394 * to scan, even if a previous invocation of {@link #hasNext} returned
1395 * <code>true</code>.
1396 *
1397 * @return the next token
1398 * @throws NoSuchElementException if no more tokens are available
1399 * @throws IllegalStateException if this scanner is closed
1400 * @see java.util.Iterator
1401 */
1402 public String next() {
1403 ensureOpen();
1404 clearCaches();
1405
1406 while (true) {
1407 String token = getCompleteTokenInBuffer(null);
1408 if (token != null) {
1409 matchValid = true;
1410 skipped = false;
1411 return token;
1412 }
1413 if (needInput)
1414 readInput();
1415 else
1416 throwFor();
1417 }
1418 }
1419
1420 /**
1421 * The remove operation is not supported by this implementation of
1422 * <code>Iterator</code>.
1423 *
1424 * @throws UnsupportedOperationException if this method is invoked.
1425 * @see java.util.Iterator
1426 */
1427 public void remove() {
1428 throw new UnsupportedOperationException();
1429 }
1430
1431 /**
1432 * Returns true if the next token matches the pattern constructed from the
1433 * specified string. The scanner does not advance past any input.
1434 *
1435 * <p> An invocation of this method of the form <tt>hasNext(pattern)</tt>
1436 * behaves in exactly the same way as the invocation
1437 * <tt>hasNext(Pattern.compile(pattern))</tt>.
1438 *
1439 * @param pattern a string specifying the pattern to scan
1440 * @return true if and only if this scanner has another token matching
1441 * the specified pattern
1442 * @throws IllegalStateException if this scanner is closed
1443 */
1444 public boolean hasNext(String pattern) {
1445 return hasNext(patternCache.forName(pattern));
1446 }
1447
1448 /**
1449 * Returns the next token if it matches the pattern constructed from the
1450 * specified string. If the match is successful, the scanner advances
1451 * past the input that matched the pattern.
1452 *
1453 * <p> An invocation of this method of the form <tt>next(pattern)</tt>
1454 * behaves in exactly the same way as the invocation
1455 * <tt>next(Pattern.compile(pattern))</tt>.
1456 *
1457 * @param pattern a string specifying the pattern to scan
1458 * @return the next token
1459 * @throws NoSuchElementException if no such tokens are available
1460 * @throws IllegalStateException if this scanner is closed
1461 */
1462 public String next(String pattern) {
1463 return next(patternCache.forName(pattern));
1464 }
1465
1466 /**
1467 * Returns true if the next complete token matches the specified pattern.
1468 * A complete token is prefixed and postfixed by input that matches
1469 * the delimiter pattern. This method may block while waiting for input.
1470 * The scanner does not advance past any input.
1471 *
1472 * @param pattern the pattern to scan for
1473 * @return true if and only if this scanner has another token matching
1474 * the specified pattern
1475 * @throws IllegalStateException if this scanner is closed
1476 */
1477 public boolean hasNext(Pattern pattern) {
1478 ensureOpen();
1479 if (pattern == null)
1480 throw new NullPointerException();
1481 hasNextPattern = null;
1482 saveState();
1483
1484 while (true) {
1485 if (getCompleteTokenInBuffer(pattern) != null) {
1486 matchValid = true;
1487 cacheResult();
1488 return revertState(true);
1489 }
1490 if (needInput)
1491 readInput();
1492 else
1493 return revertState(false);
1494 }
1495 }
1496
1497 /**
1498 * Returns the next token if it matches the specified pattern. This
1499 * method may block while waiting for input to scan, even if a previous
1500 * invocation of {@link #hasNext(Pattern)} returned <code>true</code>.
1501 * If the match is successful, the scanner advances past the input that
1502 * matched the pattern.
1503 *
1504 * @param pattern the pattern to scan for
1505 * @return the next token
1506 * @throws NoSuchElementException if no more tokens are available
1507 * @throws IllegalStateException if this scanner is closed
1508 */
1509 public String next(Pattern pattern) {
1510 ensureOpen();
1511 if (pattern == null)
1512 throw new NullPointerException();
1513
1514 // Did we already find this pattern?
1515 if (hasNextPattern == pattern)
1516 return getCachedResult();
1517 clearCaches();
1518
1519 // Search for the pattern
1520 while (true) {
1521 String token = getCompleteTokenInBuffer(pattern);
1522 if (token != null) {
1523 matchValid = true;
1524 skipped = false;
1525 return token;
1526 }
1527 if (needInput)
1528 readInput();
1529 else
1530 throwFor();
1531 }
1532 }
1533
1534 /**
1535 * Returns true if there is another line in the input of this scanner.
1536 * This method may block while waiting for input. The scanner does not
1537 * advance past any input.
1538 *
1539 * @return true if and only if this scanner has another line of input
1540 * @throws IllegalStateException if this scanner is closed
1541 */
1542 public boolean hasNextLine() {
1543 saveState();
1544
1545 String result = findWithinHorizon(linePattern(), 0);
1546 if (result != null) {
1547 MatchResult mr = this.match();
1548 String lineSep = mr.group(1);
1549 if (lineSep != null) {
1550 result = result.substring(0, result.length() -
1551 lineSep.length());
1552 cacheResult(result);
1553
1554 } else {
1555 cacheResult();
1556 }
1557 }
1558 revertState();
1559 return (result != null);
1560 }
1561
1562 /**
1563 * Advances this scanner past the current line and returns the input
1564 * that was skipped.
1565 *
1566 * This method returns the rest of the current line, excluding any line
1567 * separator at the end. The position is set to the beginning of the next
1568 * line.
1569 *
1570 * <p>Since this method continues to search through the input looking
1571 * for a line separator, it may buffer all of the input searching for
1572 * the line to skip if no line separators are present.
1573 *
1574 * @return the line that was skipped
1575 * @throws NoSuchElementException if no line was found
1576 * @throws IllegalStateException if this scanner is closed
1577 */
1578 public String nextLine() {
1579 if (hasNextPattern == linePattern())
1580 return getCachedResult();
1581 clearCaches();
1582
1583 String result = findWithinHorizon(linePattern, 0);
1584 if (result == null)
1585 throw new NoSuchElementException("No line found");
1586 MatchResult mr = this.match();
1587 String lineSep = mr.group(1);
1588 if (lineSep != null)
1589 result = result.substring(0, result.length() - lineSep.length());
1590 if (result == null)
1591 throw new NoSuchElementException();
1592 else
1593 return result;
1594 }
1595
1596 // Public methods that ignore delimiters
1597
1598 /**
1599 * Attempts to find the next occurrence of a pattern constructed from the
1600 * specified string, ignoring delimiters.
1601 *
1602 * <p>An invocation of this method of the form <tt>findInLine(pattern)</tt>
1603 * behaves in exactly the same way as the invocation
1604 * <tt>findInLine(Pattern.compile(pattern))</tt>.
1605 *
1606 * @param pattern a string specifying the pattern to search for
1607 * @return the text that matched the specified pattern
1608 * @throws IllegalStateException if this scanner is closed
1609 */
1610 public String findInLine(String pattern) {
1611 return findInLine(patternCache.forName(pattern));
1612 }
1613
1614 /**
1615 * Attempts to find the next occurrence of the specified pattern ignoring
1616 * delimiters. If the pattern is found before the next line separator, the
1617 * scanner advances past the input that matched and returns the string that
1618 * matched the pattern.
1619 * If no such pattern is detected in the input up to the next line
1620 * separator, then <code>null</code> is returned and the scanner's
1621 * position is unchanged. This method may block waiting for input that
1622 * matches the pattern.
1623 *
1624 * <p>Since this method continues to search through the input looking
1625 * for the specified pattern, it may buffer all of the input searching for
1626 * the desired token if no line separators are present.
1627 *
1628 * @param pattern the pattern to scan for
1629 * @return the text that matched the specified pattern
1630 * @throws IllegalStateException if this scanner is closed
1631 */
1632 public String findInLine(Pattern pattern) {
1633 ensureOpen();
1634 if (pattern == null)
1635 throw new NullPointerException();
1636 clearCaches();
1637 // Expand buffer to include the next newline or end of input
1638 int endPosition = 0;
1639 saveState();
1640 while (true) {
1641 String token = findPatternInBuffer(separatorPattern(), 0);
1642 if (token != null) {
1643 endPosition = matcher.start();
1644 break; // up to next newline
1645 }
1646 if (needInput) {
1647 readInput();
1648 } else {
1649 endPosition = buf.limit();
1650 break; // up to end of input
1651 }
1652 }
1653 revertState();
1654 int horizonForLine = endPosition - position;
1655 // If there is nothing between the current pos and the next
1656 // newline simply return null, invoking findWithinHorizon
1657 // with "horizon=0" will scan beyond the line bound.
1658 if (horizonForLine == 0)
1659 return null;
1660 // Search for the pattern
1661 return findWithinHorizon(pattern, horizonForLine);
1662 }
1663
1664 /**
1665 * Attempts to find the next occurrence of a pattern constructed from the
1666 * specified string, ignoring delimiters.
1667 *
1668 * <p>An invocation of this method of the form
1669 * <tt>findWithinHorizon(pattern)</tt> behaves in exactly the same way as
1670 * the invocation
1671 * <tt>findWithinHorizon(Pattern.compile(pattern, horizon))</tt>.
1672 *
1673 * @param pattern a string specifying the pattern to search for
1674 * @return the text that matched the specified pattern
1675 * @throws IllegalStateException if this scanner is closed
1676 * @throws IllegalArgumentException if horizon is negative
1677 */
1678 public String findWithinHorizon(String pattern, int horizon) {
1679 return findWithinHorizon(patternCache.forName(pattern), horizon);
1680 }
1681
1682 /**
1683 * Attempts to find the next occurrence of the specified pattern.
1684 *
1685 * <p>This method searches through the input up to the specified
1686 * search horizon, ignoring delimiters. If the pattern is found the
1687 * scanner advances past the input that matched and returns the string
1688 * that matched the pattern. If no such pattern is detected then the
1689 * null is returned and the scanner's position remains unchanged. This
1690 * method may block waiting for input that matches the pattern.
1691 *
1692 * <p>A scanner will never search more than <code>horizon</code> code
1693 * points beyond its current position. Note that a match may be clipped
1694 * by the horizon; that is, an arbitrary match result may have been
1695 * different if the horizon had been larger. The scanner treats the
1696 * horizon as a transparent, non-anchoring bound (see {@link
1697 * Matcher#useTransparentBounds} and {@link Matcher#useAnchoringBounds}).
1698 *
1699 * <p>If horizon is <code>0</code>, then the horizon is ignored and
1700 * this method continues to search through the input looking for the
1701 * specified pattern without bound. In this case it may buffer all of
1702 * the input searching for the pattern.
1703 *
1704 * <p>If horizon is negative, then an IllegalArgumentException is
1705 * thrown.
1706 *
1707 * @param pattern the pattern to scan for
1708 * @return the text that matched the specified pattern
1709 * @throws IllegalStateException if this scanner is closed
1710 * @throws IllegalArgumentException if horizon is negative
1711 */
1712 public String findWithinHorizon(Pattern pattern, int horizon) {
1713 ensureOpen();
1714 if (pattern == null)
1715 throw new NullPointerException();
1716 if (horizon < 0)
1717 throw new IllegalArgumentException("horizon < 0");
1718 clearCaches();
1719
1720 // Search for the pattern
1721 while (true) {
1722 String token = findPatternInBuffer(pattern, horizon);
1723 if (token != null) {
1724 matchValid = true;
1725 return token;
1726 }
1727 if (needInput)
1728 readInput();
1729 else
1730 break; // up to end of input
1731 }
1732 return null;
1733 }
1734
1735 /**
1736 * Skips input that matches the specified pattern, ignoring delimiters.
1737 * This method will skip input if an anchored match of the specified
1738 * pattern succeeds.
1739 *
1740 * <p>If a match to the specified pattern is not found at the
1741 * current position, then no input is skipped and a
1742 * <tt>NoSuchElementException</tt> is thrown.
1743 *
1744 * <p>Since this method seeks to match the specified pattern starting at
1745 * the scanner's current position, patterns that can match a lot of
1746 * input (".*", for example) may cause the scanner to buffer a large
1747 * amount of input.
1748 *
1749 * <p>Note that it is possible to skip something without risking a
1750 * <code>NoSuchElementException</code> by using a pattern that can
1751 * match nothing, e.g., <code>sc.skip("[ \t]*")</code>.
1752 *
1753 * @param pattern a string specifying the pattern to skip over
1754 * @return this scanner
1755 * @throws NoSuchElementException if the specified pattern is not found
1756 * @throws IllegalStateException if this scanner is closed
1757 */
1758 public Scanner skip(Pattern pattern) {
1759 ensureOpen();
1760 if (pattern == null)
1761 throw new NullPointerException();
1762 clearCaches();
1763
1764 // Search for the pattern
1765 while (true) {
1766 String token = matchPatternInBuffer(pattern);
1767 if (token != null) {
1768 matchValid = true;
1769 position = matcher.end();
1770 return this;
1771 }
1772 if (needInput)
1773 readInput();
1774 else
1775 throw new NoSuchElementException();
1776 }
1777 }
1778
1779 /**
1780 * Skips input that matches a pattern constructed from the specified
1781 * string.
1782 *
1783 * <p> An invocation of this method of the form <tt>skip(pattern)</tt>
1784 * behaves in exactly the same way as the invocation
1785 * <tt>skip(Pattern.compile(pattern))</tt>.
1786 *
1787 * @param pattern a string specifying the pattern to skip over
1788 * @return this scanner
1789 * @throws IllegalStateException if this scanner is closed
1790 */
1791 public Scanner skip(String pattern) {
1792 return skip(patternCache.forName(pattern));
1793 }
1794
1795 // Convenience methods for scanning primitives
1796
1797 /**
1798 * Returns true if the next token in this scanner's input can be
1799 * interpreted as a boolean value using a case insensitive pattern
1800 * created from the string "true|false". The scanner does not
1801 * advance past the input that matched.
1802 *
1803 * @return true if and only if this scanner's next token is a valid
1804 * boolean value
1805 * @throws IllegalStateException if this scanner is closed
1806 */
1807 public boolean hasNextBoolean() {
1808 return hasNext(boolPattern());
1809 }
1810
1811 /**
1812 * Scans the next token of the input into a boolean value and returns
1813 * that value. This method will throw <code>InputMismatchException</code>
1814 * if the next token cannot be translated into a valid boolean value.
1815 * If the match is successful, the scanner advances past the input that
1816 * matched.
1817 *
1818 * @return the boolean scanned from the input
1819 * @throws InputMismatchException if the next token is not a valid boolean
1820 * @throws NoSuchElementException if input is exhausted
1821 * @throws IllegalStateException if this scanner is closed
1822 */
1823 public boolean nextBoolean() {
1824 clearCaches();
1825 return Boolean.parseBoolean(next(boolPattern()));
1826 }
1827
1828 /**
1829 * Returns true if the next token in this scanner's input can be
1830 * interpreted as a byte value in the default radix using the
1831 * {@link #nextByte} method. The scanner does not advance past any input.
1832 *
1833 * @return true if and only if this scanner's next token is a valid
1834 * byte value
1835 * @throws IllegalStateException if this scanner is closed
1836 */
1837 public boolean hasNextByte() {
1838 return hasNextByte(defaultRadix);
1839 }
1840
1841 /**
1842 * Returns true if the next token in this scanner's input can be
1843 * interpreted as a byte value in the specified radix using the
1844 * {@link #nextByte} method. The scanner does not advance past any input.
1845 *
1846 * @param radix the radix used to interpret the token as a byte value
1847 * @return true if and only if this scanner's next token is a valid
1848 * byte value
1849 * @throws IllegalStateException if this scanner is closed
1850 */
1851 public boolean hasNextByte(int radix) {
1852 setRadix(radix);
1853 boolean result = hasNext(integerPattern());
1854 if (result) { // Cache it
1855 try {
1856 String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ?
1857 processIntegerToken(hasNextResult) :
1858 hasNextResult;
1859 typeCache = Byte.parseByte(s, radix);
1860 } catch (NumberFormatException nfe) {
1861 result = false;
1862 }
1863 }
1864 return result;
1865 }
1866
1867 /**
1868 * Scans the next token of the input as a <tt>byte</tt>.
1869 *
1870 * <p> An invocation of this method of the form
1871 * <tt>nextByte()</tt> behaves in exactly the same way as the
1872 * invocation <tt>nextByte(radix)</tt>, where <code>radix</code>
1873 * is the default radix of this scanner.
1874 *
1875 * @return the <tt>byte</tt> scanned from the input
1876 * @throws InputMismatchException
1877 * if the next token does not match the <i>Integer</i>
1878 * regular expression, or is out of range
1879 * @throws NoSuchElementException if input is exhausted
1880 * @throws IllegalStateException if this scanner is closed
1881 */
1882 public byte nextByte() {
1883 return nextByte(defaultRadix);
1884 }
1885
1886 /**
1887 * Scans the next token of the input as a <tt>byte</tt>.
1888 * This method will throw <code>InputMismatchException</code>
1889 * if the next token cannot be translated into a valid byte value as
1890 * described below. If the translation is successful, the scanner advances
1891 * past the input that matched.
1892 *
1893 * <p> If the next token matches the <a
1894 * href="#Integer-regex"><i>Integer</i></a> regular expression defined
1895 * above then the token is converted into a <tt>byte</tt> value as if by
1896 * removing all locale specific prefixes, group separators, and locale
1897 * specific suffixes, then mapping non-ASCII digits into ASCII
1898 * digits via {@link Character#digit Character.digit}, prepending a
1899 * negative sign (-) if the locale specific negative prefixes and suffixes
1900 * were present, and passing the resulting string to
1901 * {@link Byte#parseByte(String, int) Byte.parseByte} with the
1902 * specified radix.
1903 *
1904 * @param radix the radix used to interpret the token as a byte value
1905 * @return the <tt>byte</tt> scanned from the input
1906 * @throws InputMismatchException
1907 * if the next token does not match the <i>Integer</i>
1908 * regular expression, or is out of range
1909 * @throws NoSuchElementException if input is exhausted
1910 * @throws IllegalStateException if this scanner is closed
1911 */
1912 public byte nextByte(int radix) {
1913 // Check cached result
1914 if ((typeCache != null) && (typeCache instanceof Byte)
1915 && this.radix == radix) {
1916 byte val = ((Byte)typeCache).byteValue();
1917 useTypeCache();
1918 return val;
1919 }
1920 setRadix(radix);
1921 clearCaches();
1922 // Search for next byte
1923 try {
1924 String s = next(integerPattern());
1925 if (matcher.group(SIMPLE_GROUP_INDEX) == null)
1926 s = processIntegerToken(s);
1927 return Byte.parseByte(s, radix);
1928 } catch (NumberFormatException nfe) {
1929 position = matcher.start(); // don't skip bad token
1930 throw new InputMismatchException(nfe.getMessage());
1931 }
1932 }
1933
1934 /**
1935 * Returns true if the next token in this scanner's input can be
1936 * interpreted as a short value in the default radix using the
1937 * {@link #nextShort} method. The scanner does not advance past any input.
1938 *
1939 * @return true if and only if this scanner's next token is a valid
1940 * short value in the default radix
1941 * @throws IllegalStateException if this scanner is closed
1942 */
1943 public boolean hasNextShort() {
1944 return hasNextShort(defaultRadix);
1945 }
1946
1947 /**
1948 * Returns true if the next token in this scanner's input can be
1949 * interpreted as a short value in the specified radix using the
1950 * {@link #nextShort} method. The scanner does not advance past any input.
1951 *
1952 * @param radix the radix used to interpret the token as a short value
1953 * @return true if and only if this scanner's next token is a valid
1954 * short value in the specified radix
1955 * @throws IllegalStateException if this scanner is closed
1956 */
1957 public boolean hasNextShort(int radix) {
1958 setRadix(radix);
1959 boolean result = hasNext(integerPattern());
1960 if (result) { // Cache it
1961 try {
1962 String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ?
1963 processIntegerToken(hasNextResult) :
1964 hasNextResult;
1965 typeCache = Short.parseShort(s, radix);
1966 } catch (NumberFormatException nfe) {
1967 result = false;
1968 }
1969 }
1970 return result;
1971 }
1972
1973 /**
1974 * Scans the next token of the input as a <tt>short</tt>.
1975 *
1976 * <p> An invocation of this method of the form
1977 * <tt>nextShort()</tt> behaves in exactly the same way as the
1978 * invocation <tt>nextShort(radix)</tt>, where <code>radix</code>
1979 * is the default radix of this scanner.
1980 *
1981 * @return the <tt>short</tt> scanned from the input
1982 * @throws InputMismatchException
1983 * if the next token does not match the <i>Integer</i>
1984 * regular expression, or is out of range
1985 * @throws NoSuchElementException if input is exhausted
1986 * @throws IllegalStateException if this scanner is closed
1987 */
1988 public short nextShort() {
1989 return nextShort(defaultRadix);
1990 }
1991
1992 /**
1993 * Scans the next token of the input as a <tt>short</tt>.
1994 * This method will throw <code>InputMismatchException</code>
1995 * if the next token cannot be translated into a valid short value as
1996 * described below. If the translation is successful, the scanner advances
1997 * past the input that matched.
1998 *
1999 * <p> If the next token matches the <a
2000 * href="#Integer-regex"><i>Integer</i></a> regular expression defined
2001 * above then the token is converted into a <tt>short</tt> value as if by
2002 * removing all locale specific prefixes, group separators, and locale
2003 * specific suffixes, then mapping non-ASCII digits into ASCII
2004 * digits via {@link Character#digit Character.digit}, prepending a
2005 * negative sign (-) if the locale specific negative prefixes and suffixes
2006 * were present, and passing the resulting string to
2007 * {@link Short#parseShort(String, int) Short.parseShort} with the
2008 * specified radix.
2009 *
2010 * @param radix the radix used to interpret the token as a short value
2011 * @return the <tt>short</tt> scanned from the input
2012 * @throws InputMismatchException
2013 * if the next token does not match the <i>Integer</i>
2014 * regular expression, or is out of range
2015 * @throws NoSuchElementException if input is exhausted
2016 * @throws IllegalStateException if this scanner is closed
2017 */
2018 public short nextShort(int radix) {
2019 // Check cached result
2020 if ((typeCache != null) && (typeCache instanceof Short)
2021 && this.radix == radix) {
2022 short val = ((Short)typeCache).shortValue();
2023 useTypeCache();
2024 return val;
2025 }
2026 setRadix(radix);
2027 clearCaches();
2028 // Search for next short
2029 try {
2030 String s = next(integerPattern());
2031 if (matcher.group(SIMPLE_GROUP_INDEX) == null)
2032 s = processIntegerToken(s);
2033 return Short.parseShort(s, radix);
2034 } catch (NumberFormatException nfe) {
2035 position = matcher.start(); // don't skip bad token
2036 throw new InputMismatchException(nfe.getMessage());
2037 }
2038 }
2039
2040 /**
2041 * Returns true if the next token in this scanner's input can be
2042 * interpreted as an int value in the default radix using the
2043 * {@link #nextInt} method. The scanner does not advance past any input.
2044 *
2045 * @return true if and only if this scanner's next token is a valid
2046 * int value
2047 * @throws IllegalStateException if this scanner is closed
2048 */
2049 public boolean hasNextInt() {
2050 return hasNextInt(defaultRadix);
2051 }
2052
2053 /**
2054 * Returns true if the next token in this scanner's input can be
2055 * interpreted as an int value in the specified radix using the
2056 * {@link #nextInt} method. The scanner does not advance past any input.
2057 *
2058 * @param radix the radix used to interpret the token as an int value
2059 * @return true if and only if this scanner's next token is a valid
2060 * int value
2061 * @throws IllegalStateException if this scanner is closed
2062 */
2063 public boolean hasNextInt(int radix) {
2064 setRadix(radix);
2065 boolean result = hasNext(integerPattern());
2066 if (result) { // Cache it
2067 try {
2068 String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ?
2069 processIntegerToken(hasNextResult) :
2070 hasNextResult;
2071 typeCache = Integer.parseInt(s, radix);
2072 } catch (NumberFormatException nfe) {
2073 result = false;
2074 }
2075 }
2076 return result;
2077 }
2078
2079 /**
2080 * The integer token must be stripped of prefixes, group separators,
2081 * and suffixes, non ascii digits must be converted into ascii digits
2082 * before parse will accept it.
2083 */
2084 private String processIntegerToken(String token) {
2085 String result = token.replaceAll(""+groupSeparator, "");
2086 boolean isNegative = false;
2087 int preLen = negativePrefix.length();
2088 if ((preLen > 0) && result.startsWith(negativePrefix)) {
2089 isNegative = true;
2090 result = result.substring(preLen);
2091 }
2092 int sufLen = negativeSuffix.length();
2093 if ((sufLen > 0) && result.endsWith(negativeSuffix)) {
2094 isNegative = true;
2095 result = result.substring(result.length() - sufLen,
2096 result.length());
2097 }
2098 if (isNegative)
2099 result = "-" + result;
2100 return result;
2101 }
2102
2103 /**
2104 * Scans the next token of the input as an <tt>int</tt>.
2105 *
2106 * <p> An invocation of this method of the form
2107 * <tt>nextInt()</tt> behaves in exactly the same way as the
2108 * invocation <tt>nextInt(radix)</tt>, where <code>radix</code>
2109 * is the default radix of this scanner.
2110 *
2111 * @return the <tt>int</tt> scanned from the input
2112 * @throws InputMismatchException
2113 * if the next token does not match the <i>Integer</i>
2114 * regular expression, or is out of range
2115 * @throws NoSuchElementException if input is exhausted
2116 * @throws IllegalStateException if this scanner is closed
2117 */
2118 public int nextInt() {
2119 return nextInt(defaultRadix);
2120 }
2121
2122 /**
2123 * Scans the next token of the input as an <tt>int</tt>.
2124 * This method will throw <code>InputMismatchException</code>
2125 * if the next token cannot be translated into a valid int value as
2126 * described below. If the translation is successful, the scanner advances
2127 * past the input that matched.
2128 *
2129 * <p> If the next token matches the <a
2130 * href="#Integer-regex"><i>Integer</i></a> regular expression defined
2131 * above then the token is converted into an <tt>int</tt> value as if by
2132 * removing all locale specific prefixes, group separators, and locale
2133 * specific suffixes, then mapping non-ASCII digits into ASCII
2134 * digits via {@link Character#digit Character.digit}, prepending a
2135 * negative sign (-) if the locale specific negative prefixes and suffixes
2136 * were present, and passing the resulting string to
2137 * {@link Integer#parseInt(String, int) Integer.parseInt} with the
2138 * specified radix.
2139 *
2140 * @param radix the radix used to interpret the token as an int value
2141 * @return the <tt>int</tt> scanned from the input
2142 * @throws InputMismatchException
2143 * if the next token does not match the <i>Integer</i>
2144 * regular expression, or is out of range
2145 * @throws NoSuchElementException if input is exhausted
2146 * @throws IllegalStateException if this scanner is closed
2147 */
2148 public int nextInt(int radix) {
2149 // Check cached result
2150 if ((typeCache != null) && (typeCache instanceof Integer)
2151 && this.radix == radix) {
2152 int val = ((Integer)typeCache).intValue();
2153 useTypeCache();
2154 return val;
2155 }
2156 setRadix(radix);
2157 clearCaches();
2158 // Search for next int
2159 try {
2160 String s = next(integerPattern());
2161 if (matcher.group(SIMPLE_GROUP_INDEX) == null)
2162 s = processIntegerToken(s);
2163 return Integer.parseInt(s, radix);
2164 } catch (NumberFormatException nfe) {
2165 position = matcher.start(); // don't skip bad token
2166 throw new InputMismatchException(nfe.getMessage());
2167 }
2168 }
2169
2170 /**
2171 * Returns true if the next token in this scanner's input can be
2172 * interpreted as a long value in the default radix using the
2173 * {@link #nextLong} method. The scanner does not advance past any input.
2174 *
2175 * @return true if and only if this scanner's next token is a valid
2176 * long value
2177 * @throws IllegalStateException if this scanner is closed
2178 */
2179 public boolean hasNextLong() {
2180 return hasNextLong(defaultRadix);
2181 }
2182
2183 /**
2184 * Returns true if the next token in this scanner's input can be
2185 * interpreted as a long value in the specified radix using the
2186 * {@link #nextLong} method. The scanner does not advance past any input.
2187 *
2188 * @param radix the radix used to interpret the token as a long value
2189 * @return true if and only if this scanner's next token is a valid
2190 * long value
2191 * @throws IllegalStateException if this scanner is closed
2192 */
2193 public boolean hasNextLong(int radix) {
2194 setRadix(radix);
2195 boolean result = hasNext(integerPattern());
2196 if (result) { // Cache it
2197 try {
2198 String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ?
2199 processIntegerToken(hasNextResult) :
2200 hasNextResult;
2201 typeCache = Long.parseLong(s, radix);
2202 } catch (NumberFormatException nfe) {
2203 result = false;
2204 }
2205 }
2206 return result;
2207 }
2208
2209 /**
2210 * Scans the next token of the input as a <tt>long</tt>.
2211 *
2212 * <p> An invocation of this method of the form
2213 * <tt>nextLong()</tt> behaves in exactly the same way as the
2214 * invocation <tt>nextLong(radix)</tt>, where <code>radix</code>
2215 * is the default radix of this scanner.
2216 *
2217 * @return the <tt>long</tt> scanned from the input
2218 * @throws InputMismatchException
2219 * if the next token does not match the <i>Integer</i>
2220 * regular expression, or is out of range
2221 * @throws NoSuchElementException if input is exhausted
2222 * @throws IllegalStateException if this scanner is closed
2223 */
2224 public long nextLong() {
2225 return nextLong(defaultRadix);
2226 }
2227
2228 /**
2229 * Scans the next token of the input as a <tt>long</tt>.
2230 * This method will throw <code>InputMismatchException</code>
2231 * if the next token cannot be translated into a valid long value as
2232 * described below. If the translation is successful, the scanner advances
2233 * past the input that matched.
2234 *
2235 * <p> If the next token matches the <a
2236 * href="#Integer-regex"><i>Integer</i></a> regular expression defined
2237 * above then the token is converted into a <tt>long</tt> value as if by
2238 * removing all locale specific prefixes, group separators, and locale
2239 * specific suffixes, then mapping non-ASCII digits into ASCII
2240 * digits via {@link Character#digit Character.digit}, prepending a
2241 * negative sign (-) if the locale specific negative prefixes and suffixes
2242 * were present, and passing the resulting string to
2243 * {@link Long#parseLong(String, int) Long.parseLong} with the
2244 * specified radix.
2245 *
2246 * @param radix the radix used to interpret the token as an int value
2247 * @return the <tt>long</tt> scanned from the input
2248 * @throws InputMismatchException
2249 * if the next token does not match the <i>Integer</i>
2250 * regular expression, or is out of range
2251 * @throws NoSuchElementException if input is exhausted
2252 * @throws IllegalStateException if this scanner is closed
2253 */
2254 public long nextLong(int radix) {
2255 // Check cached result
2256 if ((typeCache != null) && (typeCache instanceof Long)
2257 && this.radix == radix) {
2258 long val = ((Long)typeCache).longValue();
2259 useTypeCache();
2260 return val;
2261 }
2262 setRadix(radix);
2263 clearCaches();
2264 try {
2265 String s = next(integerPattern());
2266 if (matcher.group(SIMPLE_GROUP_INDEX) == null)
2267 s = processIntegerToken(s);
2268 return Long.parseLong(s, radix);
2269 } catch (NumberFormatException nfe) {
2270 position = matcher.start(); // don't skip bad token
2271 throw new InputMismatchException(nfe.getMessage());
2272 }
2273 }
2274
2275 /**
2276 * The float token must be stripped of prefixes, group separators,
2277 * and suffixes, non ascii digits must be converted into ascii digits
2278 * before parseFloat will accept it.
2279 *
2280 * If there are non-ascii digits in the token these digits must
2281 * be processed before the token is passed to parseFloat.
2282 */
2283 private String processFloatToken(String token) {
2284 String result = token.replaceAll(groupSeparator, "");
2285 if (!decimalSeparator.equals("\\."))
2286 result = result.replaceAll(decimalSeparator, ".");
2287 boolean isNegative = false;
2288 int preLen = negativePrefix.length();
2289 if ((preLen > 0) && result.startsWith(negativePrefix)) {
2290 isNegative = true;
2291 result = result.substring(preLen);
2292 }
2293 int sufLen = negativeSuffix.length();
2294 if ((sufLen > 0) && result.endsWith(negativeSuffix)) {
2295 isNegative = true;
2296 result = result.substring(result.length() - sufLen,
2297 result.length());
2298 }
2299 if (result.equals(nanString))
2300 result = "NaN";
2301 if (result.equals(infinityString))
2302 result = "Infinity";
2303 if (isNegative)
2304 result = "-" + result;
2305
2306 // Translate non-ASCII digits
2307 Matcher m = NON_ASCII_DIGIT.matcher(result);
2308 if (m.find()) {
2309 StringBuilder inASCII = new StringBuilder();
2310 for (int i=0; i<result.length(); i++) {
2311 char nextChar = result.charAt(i);
2312 if (Character.isDigit(nextChar)) {
2313 int d = Character.digit(nextChar, 10);
2314 if (d != -1)
2315 inASCII.append(d);
2316 else
2317 inASCII.append(nextChar);
2318 } else {
2319 inASCII.append(nextChar);
2320 }
2321 }
2322 result = inASCII.toString();
2323 }
2324
2325 return result;
2326 }
2327
2328 /**
2329 * Returns true if the next token in this scanner's input can be
2330 * interpreted as a float value using the {@link #nextFloat}
2331 * method. The scanner does not advance past any input.
2332 *
2333 * @return true if and only if this scanner's next token is a valid
2334 * float value
2335 * @throws IllegalStateException if this scanner is closed
2336 */
2337 public boolean hasNextFloat() {
2338 setRadix(10);
2339 boolean result = hasNext(floatPattern());
2340 if (result) { // Cache it
2341 try {
2342 String s = processFloatToken(hasNextResult);
2343 typeCache = Float.valueOf(Float.parseFloat(s));
2344 } catch (NumberFormatException nfe) {
2345 result = false;
2346 }
2347 }
2348 return result;
2349 }
2350
2351 /**
2352 * Scans the next token of the input as a <tt>float</tt>.
2353 * This method will throw <code>InputMismatchException</code>
2354 * if the next token cannot be translated into a valid float value as
2355 * described below. If the translation is successful, the scanner advances
2356 * past the input that matched.
2357 *
2358 * <p> If the next token matches the <a
2359 * href="#Float-regex"><i>Float</i></a> regular expression defined above
2360 * then the token is converted into a <tt>float</tt> value as if by
2361 * removing all locale specific prefixes, group separators, and locale
2362 * specific suffixes, then mapping non-ASCII digits into ASCII
2363 * digits via {@link Character#digit Character.digit}, prepending a
2364 * negative sign (-) if the locale specific negative prefixes and suffixes
2365 * were present, and passing the resulting string to
2366 * {@link Float#parseFloat Float.parseFloat}. If the token matches
2367 * the localized NaN or infinity strings, then either "Nan" or "Infinity"
2368 * is passed to {@link Float#parseFloat(String) Float.parseFloat} as
2369 * appropriate.
2370 *
2371 * @return the <tt>float</tt> scanned from the input
2372 * @throws InputMismatchException
2373 * if the next token does not match the <i>Float</i>
2374 * regular expression, or is out of range
2375 * @throws NoSuchElementException if input is exhausted
2376 * @throws IllegalStateException if this scanner is closed
2377 */
2378 public float nextFloat() {
2379 // Check cached result
2380 if ((typeCache != null) && (typeCache instanceof Float)) {
2381 float val = ((Float)typeCache).floatValue();
2382 useTypeCache();
2383 return val;
2384 }
2385 setRadix(10);
2386 clearCaches();
2387 try {
2388 return Float.parseFloat(processFloatToken(next(floatPattern())));
2389 } catch (NumberFormatException nfe) {
2390 position = matcher.start(); // don't skip bad token
2391 throw new InputMismatchException(nfe.getMessage());
2392 }
2393 }
2394
2395 /**
2396 * Returns true if the next token in this scanner's input can be
2397 * interpreted as a double value using the {@link #nextDouble}
2398 * method. The scanner does not advance past any input.
2399 *
2400 * @return true if and only if this scanner's next token is a valid
2401 * double value
2402 * @throws IllegalStateException if this scanner is closed
2403 */
2404 public boolean hasNextDouble() {
2405 setRadix(10);
2406 boolean result = hasNext(floatPattern());
2407 if (result) { // Cache it
2408 try {
2409 String s = processFloatToken(hasNextResult);
2410 typeCache = Double.valueOf(Double.parseDouble(s));
2411 } catch (NumberFormatException nfe) {
2412 result = false;
2413 }
2414 }
2415 return result;
2416 }
2417
2418 /**
2419 * Scans the next token of the input as a <tt>double</tt>.
2420 * This method will throw <code>InputMismatchException</code>
2421 * if the next token cannot be translated into a valid double value.
2422 * If the translation is successful, the scanner advances past the input
2423 * that matched.
2424 *
2425 * <p> If the next token matches the <a
2426 * href="#Float-regex"><i>Float</i></a> regular expression defined above
2427 * then the token is converted into a <tt>double</tt> value as if by
2428 * removing all locale specific prefixes, group separators, and locale
2429 * specific suffixes, then mapping non-ASCII digits into ASCII
2430 * digits via {@link Character#digit Character.digit}, prepending a
2431 * negative sign (-) if the locale specific negative prefixes and suffixes
2432 * were present, and passing the resulting string to
2433 * {@link Double#parseDouble Double.parseDouble}. If the token matches
2434 * the localized NaN or infinity strings, then either "Nan" or "Infinity"
2435 * is passed to {@link Double#parseDouble(String) Double.parseDouble} as
2436 * appropriate.
2437 *
2438 * @return the <tt>double</tt> scanned from the input
2439 * @throws InputMismatchException
2440 * if the next token does not match the <i>Float</i>
2441 * regular expression, or is out of range
2442 * @throws NoSuchElementException if the input is exhausted
2443 * @throws IllegalStateException if this scanner is closed
2444 */
2445 public double nextDouble() {
2446 // Check cached result
2447 if ((typeCache != null) && (typeCache instanceof Double)) {
2448 double val = ((Double)typeCache).doubleValue();
2449 useTypeCache();
2450 return val;
2451 }
2452 setRadix(10);
2453 clearCaches();
2454 // Search for next float
2455 try {
2456 return Double.parseDouble(processFloatToken(next(floatPattern())));
2457 } catch (NumberFormatException nfe) {
2458 position = matcher.start(); // don't skip bad token
2459 throw new InputMismatchException(nfe.getMessage());
2460 }
2461 }
2462
2463 // Convenience methods for scanning multi precision numbers
2464
2465 /**
2466 * Returns true if the next token in this scanner's input can be
2467 * interpreted as a <code>BigInteger</code> in the default radix using the
2468 * {@link #nextBigInteger} method. The scanner does not advance past any
2469 * input.
2470 *
2471 * @return true if and only if this scanner's next token is a valid
2472 * <code>BigInteger</code>
2473 * @throws IllegalStateException if this scanner is closed
2474 */
2475 public boolean hasNextBigInteger() {
2476 return hasNextBigInteger(defaultRadix);
2477 }
2478
2479 /**
2480 * Returns true if the next token in this scanner's input can be
2481 * interpreted as a <code>BigInteger</code> in the specified radix using
2482 * the {@link #nextBigInteger} method. The scanner does not advance past
2483 * any input.
2484 *
2485 * @param radix the radix used to interpret the token as an integer
2486 * @return true if and only if this scanner's next token is a valid
2487 * <code>BigInteger</code>
2488 * @throws IllegalStateException if this scanner is closed
2489 */
2490 public boolean hasNextBigInteger(int radix) {
2491 setRadix(radix);
2492 boolean result = hasNext(integerPattern());
2493 if (result) { // Cache it
2494 try {
2495 String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ?
2496 processIntegerToken(hasNextResult) :
2497 hasNextResult;
2498 typeCache = new BigInteger(s, radix);
2499 } catch (NumberFormatException nfe) {
2500 result = false;
2501 }
2502 }
2503 return result;
2504 }
2505
2506 /**
2507 * Scans the next token of the input as a {@link java.math.BigInteger
2508 * BigInteger}.
2509 *
2510 * <p> An invocation of this method of the form
2511 * <tt>nextBigInteger()</tt> behaves in exactly the same way as the
2512 * invocation <tt>nextBigInteger(radix)</tt>, where <code>radix</code>
2513 * is the default radix of this scanner.
2514 *
2515 * @return the <tt>BigInteger</tt> scanned from the input
2516 * @throws InputMismatchException
2517 * if the next token does not match the <i>Integer</i>
2518 * regular expression, or is out of range
2519 * @throws NoSuchElementException if the input is exhausted
2520 * @throws IllegalStateException if this scanner is closed
2521 */
2522 public BigInteger nextBigInteger() {
2523 return nextBigInteger(defaultRadix);
2524 }
2525
2526 /**
2527 * Scans the next token of the input as a {@link java.math.BigInteger
2528 * BigInteger}.
2529 *
2530 * <p> If the next token matches the <a
2531 * href="#Integer-regex"><i>Integer</i></a> regular expression defined
2532 * above then the token is converted into a <tt>BigInteger</tt> value as if
2533 * by removing all group separators, mapping non-ASCII digits into ASCII
2534 * digits via the {@link Character#digit Character.digit}, and passing the
2535 * resulting string to the {@link
2536 * java.math.BigInteger#BigInteger(java.lang.String)
2537 * BigInteger(String, int)} constructor with the specified radix.
2538 *
2539 * @param radix the radix used to interpret the token
2540 * @return the <tt>BigInteger</tt> scanned from the input
2541 * @throws InputMismatchException
2542 * if the next token does not match the <i>Integer</i>
2543 * regular expression, or is out of range
2544 * @throws NoSuchElementException if the input is exhausted
2545 * @throws IllegalStateException if this scanner is closed
2546 */
2547 public BigInteger nextBigInteger(int radix) {
2548 // Check cached result
2549 if ((typeCache != null) && (typeCache instanceof BigInteger)
2550 && this.radix == radix) {
2551 BigInteger val = (BigInteger)typeCache;
2552 useTypeCache();
2553 return val;
2554 }
2555 setRadix(radix);
2556 clearCaches();
2557 // Search for next int
2558 try {
2559 String s = next(integerPattern());
2560 if (matcher.group(SIMPLE_GROUP_INDEX) == null)
2561 s = processIntegerToken(s);
2562 return new BigInteger(s, radix);
2563 } catch (NumberFormatException nfe) {
2564 position = matcher.start(); // don't skip bad token
2565 throw new InputMismatchException(nfe.getMessage());
2566 }
2567 }
2568
2569 /**
2570 * Returns true if the next token in this scanner's input can be
2571 * interpreted as a <code>BigDecimal</code> using the
2572 * {@link #nextBigDecimal} method. The scanner does not advance past any
2573 * input.
2574 *
2575 * @return true if and only if this scanner's next token is a valid
2576 * <code>BigDecimal</code>
2577 * @throws IllegalStateException if this scanner is closed
2578 */
2579 public boolean hasNextBigDecimal() {
2580 setRadix(10);
2581 boolean result = hasNext(decimalPattern());
2582 if (result) { // Cache it
2583 try {
2584 String s = processFloatToken(hasNextResult);
2585 typeCache = new BigDecimal(s);
2586 } catch (NumberFormatException nfe) {
2587 result = false;
2588 }
2589 }
2590 return result;
2591 }
2592
2593 /**
2594 * Scans the next token of the input as a {@link java.math.BigDecimal
2595 * BigDecimal}.
2596 *
2597 * <p> If the next token matches the <a
2598 * href="#Decimal-regex"><i>Decimal</i></a> regular expression defined
2599 * above then the token is converted into a <tt>BigDecimal</tt> value as if
2600 * by removing all group separators, mapping non-ASCII digits into ASCII
2601 * digits via the {@link Character#digit Character.digit}, and passing the
2602 * resulting string to the {@link
2603 * java.math.BigDecimal#BigDecimal(java.lang.String) BigDecimal(String)}
2604 * constructor.
2605 *
2606 * @return the <tt>BigDecimal</tt> scanned from the input
2607 * @throws InputMismatchException
2608 * if the next token does not match the <i>Decimal</i>
2609 * regular expression, or is out of range
2610 * @throws NoSuchElementException if the input is exhausted
2611 * @throws IllegalStateException if this scanner is closed
2612 */
2613 public BigDecimal nextBigDecimal() {
2614 // Check cached result
2615 if ((typeCache != null) && (typeCache instanceof BigDecimal)) {
2616 BigDecimal val = (BigDecimal)typeCache;
2617 useTypeCache();
2618 return val;
2619 }
2620 setRadix(10);
2621 clearCaches();
2622 // Search for next float
2623 try {
2624 String s = processFloatToken(next(decimalPattern()));
2625 return new BigDecimal(s);
2626 } catch (NumberFormatException nfe) {
2627 position = matcher.start(); // don't skip bad token
2628 throw new InputMismatchException(nfe.getMessage());
2629 }
2630 }
2631
2632 /**
2633 * Resets this scanner.
2634 *
2635 * <p> Resetting a scanner discards all of its explicit state
2636 * information which may have been changed by invocations of {@link
2637 * #useDelimiter}, {@link #useLocale}, or {@link #useRadix}.
2638 *
2639 * <p> An invocation of this method of the form
2640 * <tt>scanner.reset()</tt> behaves in exactly the same way as the
2641 * invocation
2642 *
2643 * <blockquote><pre>
2644 * scanner.useDelimiter("\\p{javaWhitespace}+")
2645 * .useLocale(Locale.getDefault())
2646 * .useRadix(10);
2647 * </pre></blockquote>
2648 *
2649 * @return this scanner
2650 *
2651 * @since 1.6
2652 */
2653 public Scanner reset() {
2654 delimPattern = WHITESPACE_PATTERN;
2655 useLocale(Locale.getDefault(Locale.Category.FORMAT));
2656 useRadix(10);
2657 clearCaches();
2658 return this;
2659 }
2660 }
Save This Page