1 | /* |
2 | * Copyright (C) Christian Schulte, 2012-253 |
3 | * All rights reserved. |
4 | * |
5 | * Redistribution and use in source and binary forms, with or without |
6 | * modification, are permitted provided that the following conditions |
7 | * are met: |
8 | * |
9 | * o Redistributions of source code must retain the above copyright |
10 | * notice, this list of conditions and the following disclaimer. |
11 | * |
12 | * o Redistributions in binary form must reproduce the above copyright |
13 | * notice, this list of conditions and the following disclaimer in |
14 | * the documentation and/or other materials provided with the |
15 | * distribution. |
16 | * |
17 | * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, |
18 | * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY |
19 | * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL |
20 | * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY DIRECT, INDIRECT, |
21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
27 | * |
28 | * $JOMC: JavaIdentifier.java 4704 2013-01-02 05:15:52Z schulte $ |
29 | * |
30 | */ |
31 | package org.jomc.model; |
32 | |
33 | import java.io.Serializable; |
34 | import java.lang.ref.Reference; |
35 | import java.lang.ref.SoftReference; |
36 | import java.text.MessageFormat; |
37 | import java.text.ParseException; |
38 | import java.util.ArrayList; |
39 | import java.util.HashMap; |
40 | import java.util.List; |
41 | import java.util.Locale; |
42 | import java.util.Map; |
43 | import java.util.ResourceBundle; |
44 | |
45 | /** |
46 | * Data type of a Java identifier. |
47 | * <p>This class provides support for parsing and normalizing text to java identifiers as specified in the Java |
48 | * Language Specification - Java SE 7 Edition - Chapter 3.8ff.</p> |
49 | * |
50 | * @author <a href="mailto:cs@schulte.it">Christian Schulte</a> |
51 | * @version $JOMC: JavaIdentifier.java 4704 2013-01-02 05:15:52Z schulte $ |
52 | * @see #normalize(java.lang.String, org.jomc.model.JavaIdentifier.NormalizationMode) |
53 | * @see #parse(java.lang.String) |
54 | * @see #valueOf(java.lang.String) |
55 | * @since 1.4 |
56 | */ |
57 | public final class JavaIdentifier implements CharSequence, Serializable |
58 | { |
59 | |
60 | /** |
61 | * Normalization modes. |
62 | * |
63 | * @author <a href="mailto:cs@schulte.it">Christian Schulte</a> |
64 | * @version $JOMC: JavaIdentifier.java 4704 2013-01-02 05:15:52Z schulte $ |
65 | * @since 1.4 |
66 | * @see JavaIdentifier#normalize(java.lang.String, org.jomc.model.JavaIdentifier.NormalizationMode) |
67 | */ |
68 | public static enum NormalizationMode |
69 | { |
70 | |
71 | /** Mode to normalize by compacting words using camel-case. */ |
72 | CAMEL_CASE, |
73 | /** Mode to normalize by separating words using '_' and by converting all characters to lower-case. */ |
74 | LOWER_CASE, |
75 | /** Mode to normalize by separating words using '_' and by converting all characters to upper-case. */ |
76 | UPPER_CASE, |
77 | /** |
78 | * Mode to normalize according to the |
79 | * <cite>Code Conventions for the Java Programming Language - 9 - Naming Conventions - Constants</cite>. |
80 | * <blockquote> |
81 | * The names of variables declared class constants and of ANSI constants should be all uppercase with words |
82 | * separated by underscores ("_"). (ANSI constants should be avoided, for ease of debugging.) |
83 | * </blockquote> |
84 | */ |
85 | CONSTANT_NAME_CONVENTION, |
86 | /** |
87 | * Mode to normalize according to the |
88 | * <cite>Code Conventions for the Java Programming Language - 9 - Naming Conventions - Methods</cite>. |
89 | * <blockquote> |
90 | * Methods should be verbs, in mixed case with the first letter lowercase, with the first letter of each |
91 | * internal word capitalized. |
92 | * </blockquote> |
93 | */ |
94 | METHOD_NAME_CONVENTION, |
95 | /** |
96 | * Mode to normalize according to the |
97 | * <cite>Code Conventions for the Java Programming Language - 9 - Naming Conventions - Variables</cite>. |
98 | * <blockquote> |
99 | * Except for variables, all instance, class, and class constants are in mixed case with a lowercase first |
100 | * letter. Internal words start with capital letters. Variable names should not start with underscore _ or |
101 | * dollar sign $ characters, even though both are allowed. Variable names should be short yet meaningful. The |
102 | * choice of a variable name should be mnemonic - that is - designed to indicate to the casual observer the |
103 | * intent of its use. One-character variable names should be avoided except for temporary "throwaway" variables. |
104 | * Common names for temporary variables are i, j, k, m, and n for integers; c, d, and e for characters. |
105 | * </blockquote> |
106 | */ |
107 | VARIABLE_NAME_CONVENTION |
108 | |
109 | } |
110 | |
111 | /** |
112 | * The value of the instance. |
113 | * @serial |
114 | */ |
115 | private String identifier; |
116 | |
117 | /** Cached instances. */ |
118 | private static volatile Reference<Map<CacheKey, JavaIdentifier>> cache; |
119 | |
120 | /** Serial version UID for backwards compatibility with 1.4.x object streams. */ |
121 | private static final long serialVersionUID = 7600377999055800720L; |
122 | |
123 | /** Underscore character. */ |
124 | private static final int UNDERSCORE_CODEPOINT = Character.codePointAt( "_", 0 ); |
125 | |
126 | /** Creates a new {@code JavaIdentifier} instance. */ |
127 | private JavaIdentifier() |
128 | { |
129 | super(); |
130 | } |
131 | |
132 | /** |
133 | * Returns the length of this character sequence. |
134 | * |
135 | * @return The number of {@code char}s in this sequence. |
136 | */ |
137 | public int length() |
138 | { |
139 | return this.identifier.length(); |
140 | } |
141 | |
142 | /** |
143 | * Returns the {@code char} value at a given index. |
144 | * |
145 | * @param index The index of the {@code char} value to return. |
146 | * |
147 | * @return The {@code char} value at {@code index}. |
148 | * |
149 | * @throws IndexOutOfBoundsException if {@code index} is negative or not less than the length of the sequence. |
150 | */ |
151 | public char charAt( final int index ) |
152 | { |
153 | return this.identifier.charAt( index ); |
154 | } |
155 | |
156 | /** |
157 | * Returns a new {@code CharSequence} that is a subsequence of this sequence. |
158 | * |
159 | * @param start The start index, inclusive. |
160 | * @param end The end index, exclusive. |
161 | * |
162 | * @return The sequence of characters starting at index {@code start} up to index {@code end - 1}. |
163 | * |
164 | * @throws IndexOutOfBoundsException if {@code start} or {@code end} are negative, if {@code end} is greater than |
165 | * the length of the sequence, or if {@code start} is greater than {@code end}. |
166 | */ |
167 | public CharSequence subSequence( final int start, final int end ) |
168 | { |
169 | return this.identifier.subSequence( start, end ); |
170 | } |
171 | |
172 | /** |
173 | * Returns a string containing the characters in this sequence in the same order as this sequence. The length of the |
174 | * string will be the length of this sequence. |
175 | * |
176 | * @return A string consisting of exactly this sequence of characters. |
177 | */ |
178 | @Override |
179 | public String toString() |
180 | { |
181 | return this.identifier; |
182 | } |
183 | |
184 | /** |
185 | * Returns the hash-code value of the object. |
186 | * |
187 | * @return The hash-code value of the object. |
188 | */ |
189 | @Override |
190 | public int hashCode() |
191 | { |
192 | return this.identifier.hashCode(); |
193 | } |
194 | |
195 | /** |
196 | * Tests whether some other object is equal to the object. |
197 | * |
198 | * @param o The object to test. |
199 | * |
200 | * @return {@code true}, if {@code o} is an instance of the class of the object and its string value is equal to the |
201 | * string value of the object. |
202 | */ |
203 | @Override |
204 | public boolean equals( final Object o ) |
205 | { |
206 | boolean equal = o == this; |
207 | |
208 | if ( !equal && o instanceof JavaIdentifier ) |
209 | { |
210 | equal = this.toString().equals( o.toString() ); |
211 | } |
212 | |
213 | return equal; |
214 | } |
215 | |
216 | /** |
217 | * Normalizes text from the beginning of the given string to produce a {@code JavaIdentifier}. |
218 | * |
219 | * @param text The text to normalize. |
220 | * @param mode The normalization to apply. |
221 | * |
222 | * @return A {@code JavaIdentifier} instance constructed by normalizing {@code text} according to {@code mode}. |
223 | * |
224 | * @throws NullPointerException if {@code text} or {@code mode} is {@code null}. |
225 | * @throws ParseException if normalization fails. |
226 | */ |
227 | public static JavaIdentifier normalize( final String text, final NormalizationMode mode ) throws ParseException |
228 | { |
229 | if ( text == null ) |
230 | { |
231 | throw new NullPointerException( "text" ); |
232 | } |
233 | if ( mode == null ) |
234 | { |
235 | throw new NullPointerException( "mode" ); |
236 | } |
237 | |
238 | return parse( text, mode, false ); |
239 | } |
240 | |
241 | /** |
242 | * Parses text from the beginning of a given string to produce a {@code JavaIdentifier} instance. |
243 | * |
244 | * @param text The text to parse. |
245 | * |
246 | * @return A {@code JavaIdentifier} instance constructed by parsing {@code text}. |
247 | * |
248 | * @throws NullPointerException if {@code text} is {@code null}. |
249 | * @throws ParseException if parsing fails. |
250 | * |
251 | * @see #valueOf(java.lang.String) |
252 | */ |
253 | public static JavaIdentifier parse( final String text ) throws ParseException |
254 | { |
255 | if ( text == null ) |
256 | { |
257 | throw new NullPointerException( "text" ); |
258 | } |
259 | |
260 | return parse( text, null, false ); |
261 | } |
262 | |
263 | /** |
264 | * Parses text from the beginning of a given string to produce a {@code JavaIdentifier} instance. |
265 | * <p>Unlike the {@link #parse(String)} method, this method throws an {@code IllegalArgumentException} if parsing |
266 | * fails.</p> |
267 | * |
268 | * @param text The text to parse. |
269 | * |
270 | * @return A {@code JavaIdentifier} instance constructed by parsing {@code text}. |
271 | * |
272 | * @throws NullPointerException if {@code text} is {@code null}. |
273 | * @throws IllegalArgumentException if parsing fails. |
274 | * |
275 | * @see #parse(java.lang.String) |
276 | */ |
277 | public static JavaIdentifier valueOf( final String text ) throws IllegalArgumentException |
278 | { |
279 | if ( text == null ) |
280 | { |
281 | throw new NullPointerException( "text" ); |
282 | } |
283 | |
284 | try |
285 | { |
286 | return parse( text, null, true ); |
287 | } |
288 | catch ( final ParseException e ) |
289 | { |
290 | throw new AssertionError( e ); |
291 | } |
292 | } |
293 | |
294 | private static JavaIdentifier parse( final String text, final NormalizationMode mode, |
295 | final boolean runtimeException ) |
296 | throws ParseException |
297 | { |
298 | Map<CacheKey, JavaIdentifier> map = cache == null ? null : cache.get(); |
299 | |
300 | if ( map == null ) |
301 | { |
302 | map = new HashMap<CacheKey, JavaIdentifier>( 128 ); |
303 | cache = new SoftReference<Map<CacheKey, JavaIdentifier>>( map ); |
304 | } |
305 | |
306 | synchronized ( map ) |
307 | { |
308 | final CacheKey key = new CacheKey( text, mode ); |
309 | JavaIdentifier javaIdentifier = map.get( key ); |
310 | |
311 | if ( javaIdentifier == null ) |
312 | { |
313 | javaIdentifier = new JavaIdentifier(); |
314 | parseIdentifier( javaIdentifier, text, mode, runtimeException ); |
315 | |
316 | if ( mode != null ) |
317 | { |
318 | final CacheKey normalizedKey = new CacheKey( javaIdentifier.toString(), mode ); |
319 | final JavaIdentifier normalizedInstance = map.get( normalizedKey ); |
320 | |
321 | if ( normalizedInstance != null ) |
322 | { |
323 | map.put( key, normalizedInstance ); |
324 | javaIdentifier = normalizedInstance; |
325 | } |
326 | else |
327 | { |
328 | map.put( key, javaIdentifier ); |
329 | map.put( normalizedKey, javaIdentifier ); |
330 | } |
331 | } |
332 | else |
333 | { |
334 | map.put( key, javaIdentifier ); |
335 | } |
336 | } |
337 | |
338 | return javaIdentifier; |
339 | } |
340 | } |
341 | |
342 | private static void parseIdentifier( final JavaIdentifier t, final String text, final NormalizationMode mode, |
343 | final boolean runtimeException ) |
344 | throws ParseException |
345 | { |
346 | if ( text.length() <= 0 ) |
347 | { |
348 | if ( runtimeException ) |
349 | { |
350 | throw new IllegalArgumentException( getMessage( "invalidEmptyString" ) ); |
351 | } |
352 | else |
353 | { |
354 | throw new ParseException( getMessage( "invalidEmptyString" ), 0 ); |
355 | } |
356 | } |
357 | |
358 | final StringBuilder identifierBuilder = new StringBuilder( text.length() ); |
359 | final List<Integer> retainedIndices = new ArrayList<Integer>( text.length() ); |
360 | boolean start_of_word = true; |
361 | int words = 0; |
362 | |
363 | for ( int i = 0, j = 1, s0 = text.length(), last_codepoint = -1; i < s0; i++, j++ ) |
364 | { |
365 | if ( !isWordSeparator( text.codePointAt( i ), mode, identifierBuilder.length() <= 0 ) ) |
366 | { |
367 | if ( mode != null ) |
368 | { |
369 | switch ( mode ) |
370 | { |
371 | case CAMEL_CASE: |
372 | if ( start_of_word ) |
373 | { |
374 | identifierBuilder.append( Character.toUpperCase( text.charAt( i ) ) ); |
375 | } |
376 | else if ( last_codepoint > -1 && j < s0 |
377 | && isCamelCase( last_codepoint, text.codePointAt( i ), text.codePointAt( j ) ) ) |
378 | { // Retain camel-case in words. |
379 | identifierBuilder.append( text.charAt( i ) ); |
380 | retainedIndices.add( identifierBuilder.length() - 1 ); |
381 | } |
382 | else |
383 | { |
384 | identifierBuilder.append( Character.toLowerCase( text.charAt( i ) ) ); |
385 | } |
386 | break; |
387 | |
388 | case LOWER_CASE: |
389 | if ( start_of_word && last_codepoint > -1 && last_codepoint != UNDERSCORE_CODEPOINT ) |
390 | { |
391 | identifierBuilder.append( Character.toChars( UNDERSCORE_CODEPOINT ) ); |
392 | } |
393 | |
394 | identifierBuilder.append( Character.toLowerCase( text.charAt( i ) ) ); |
395 | break; |
396 | |
397 | case UPPER_CASE: |
398 | case CONSTANT_NAME_CONVENTION: |
399 | if ( start_of_word && last_codepoint > -1 && last_codepoint != UNDERSCORE_CODEPOINT ) |
400 | { |
401 | identifierBuilder.append( Character.toChars( UNDERSCORE_CODEPOINT ) ); |
402 | } |
403 | |
404 | identifierBuilder.append( Character.toUpperCase( text.charAt( i ) ) ); |
405 | break; |
406 | |
407 | case VARIABLE_NAME_CONVENTION: |
408 | case METHOD_NAME_CONVENTION: |
409 | if ( start_of_word ) |
410 | { |
411 | identifierBuilder.append( words == 0 ? Character.toLowerCase( text.charAt( i ) ) |
412 | : Character.toUpperCase( text.charAt( i ) ) ); |
413 | |
414 | } |
415 | else if ( last_codepoint > -1 && j < s0 |
416 | && isCamelCase( last_codepoint, text.codePointAt( i ), text.codePointAt( j ) ) ) |
417 | { // Retain camel-case in words. |
418 | identifierBuilder.append( text.charAt( i ) ); |
419 | retainedIndices.add( identifierBuilder.length() - 1 ); |
420 | } |
421 | else |
422 | { |
423 | identifierBuilder.append( Character.toLowerCase( text.charAt( i ) ) ); |
424 | } |
425 | break; |
426 | |
427 | default: |
428 | throw new AssertionError( mode ); |
429 | |
430 | } |
431 | } |
432 | else |
433 | { |
434 | identifierBuilder.append( text.charAt( i ) ); |
435 | } |
436 | |
437 | last_codepoint = identifierBuilder.codePointAt( identifierBuilder.length() - 1 ); |
438 | start_of_word = false; |
439 | } |
440 | else |
441 | { |
442 | if ( mode != null ) |
443 | { |
444 | if ( !start_of_word ) |
445 | { |
446 | start_of_word = true; |
447 | words++; |
448 | } |
449 | } |
450 | else if ( runtimeException ) |
451 | { |
452 | throw new IllegalArgumentException( getMessage( "invalidCharacter", text, text.charAt( i ), i ) ); |
453 | } |
454 | else |
455 | { |
456 | throw new ParseException( getMessage( "invalidCharacter", text, text.charAt( i ), i ), i ); |
457 | } |
458 | } |
459 | } |
460 | |
461 | if ( words > 0 ) |
462 | { |
463 | // Multiple words - no camel-case retained in any word. |
464 | toLowerCase( identifierBuilder, retainedIndices ); |
465 | } |
466 | |
467 | t.identifier = identifierBuilder.toString(); |
468 | |
469 | if ( t.identifier.length() <= 0 ) |
470 | { |
471 | if ( runtimeException ) |
472 | { |
473 | throw new IllegalArgumentException( getMessage( "invalidCharacters", text ) ); |
474 | } |
475 | else |
476 | { |
477 | throw new ParseException( getMessage( "invalidCharacters", text ), 0 ); |
478 | } |
479 | } |
480 | |
481 | if ( JavaLanguage.KEYWORDS.contains( t.identifier ) |
482 | || JavaLanguage.BOOLEAN_LITERALS.contains( t.identifier ) |
483 | || JavaLanguage.NULL_LITERAL.equals( t.identifier ) ) |
484 | { |
485 | if ( mode != null ) |
486 | { |
487 | t.identifier = "_" + t.identifier; |
488 | } |
489 | else if ( runtimeException ) |
490 | { |
491 | throw new IllegalArgumentException( getMessage( "invalidWord", text, t.identifier, |
492 | text.indexOf( t.identifier ) ) ); |
493 | |
494 | } |
495 | else |
496 | { |
497 | throw new ParseException( getMessage( "invalidWord", text, t.identifier, text.indexOf( t.identifier ) ), |
498 | text.indexOf( t.identifier ) ); |
499 | |
500 | } |
501 | } |
502 | } |
503 | |
504 | private static boolean isWordSeparator( final int codePoint, final NormalizationMode mode, final boolean first ) |
505 | { |
506 | return !( ( first ? Character.isJavaIdentifierStart( codePoint ) : Character.isJavaIdentifierPart( codePoint ) ) |
507 | && ( mode != null ? Character.isLetterOrDigit( codePoint ) : true ) ); |
508 | |
509 | } |
510 | |
511 | private static boolean isCamelCase( final int left, final int middle, final int right ) |
512 | { |
513 | return Character.isLowerCase( left ) && Character.isUpperCase( middle ) && Character.isLowerCase( right ); |
514 | } |
515 | |
516 | private static void toLowerCase( final StringBuilder stringBuilder, final List<Integer> indices ) |
517 | { |
518 | for ( int i = 0, s0 = indices.size(); i < s0; i++ ) |
519 | { |
520 | final int index = indices.get( i ); |
521 | final int cp = Character.toLowerCase( stringBuilder.codePointAt( index ) ); |
522 | stringBuilder.replace( index, index + 1, String.valueOf( Character.toChars( cp ) ) ); |
523 | } |
524 | } |
525 | |
526 | private static String getMessage( final String key, final Object... args ) |
527 | { |
528 | return MessageFormat.format( ResourceBundle.getBundle( |
529 | JavaIdentifier.class.getName().replace( '.', '/' ), Locale.getDefault() ). |
530 | getString( key ), args ); |
531 | |
532 | } |
533 | |
534 | private static class CacheKey |
535 | { |
536 | |
537 | private final String text; |
538 | |
539 | private final NormalizationMode mode; |
540 | |
541 | private CacheKey( final String text, final NormalizationMode mode ) |
542 | { |
543 | super(); |
544 | this.text = text; |
545 | this.mode = mode; |
546 | } |
547 | |
548 | @Override |
549 | public int hashCode() |
550 | { |
551 | int hc = 23; |
552 | hc = 37 * hc + this.text.hashCode(); |
553 | hc = 37 * hc + ( this.mode == null ? 0 : this.mode.hashCode() ); |
554 | return hc; |
555 | } |
556 | |
557 | @Override |
558 | public boolean equals( final Object o ) |
559 | { |
560 | boolean equal = o == this; |
561 | |
562 | if ( !equal && o instanceof CacheKey ) |
563 | { |
564 | final CacheKey that = (CacheKey) o; |
565 | equal = this.mode == that.mode && this.text.equals( that.text ); |
566 | } |
567 | |
568 | return equal; |
569 | } |
570 | |
571 | } |
572 | |
573 | } |