Mercurial > hg > mpdl-group
comparison software/eXist/mpdl-modules/src/de/mpg/mpiwg/berlin/mpdl/lt/analyzer/lang/MpdlNormalizerLexDE.java @ 9:1ec29fdd0db8
neue .lex Dateien f?r Normalisierung / externe Objekte update
author | Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de> |
---|---|
date | Tue, 22 Feb 2011 16:03:45 +0100 |
parents | |
children | 5df60f24e997 |
comparison
equal
deleted
inserted
replaced
8:d2a1c14fde31 | 9:1ec29fdd0db8 |
---|---|
1 /* The following code was generated by JFlex 1.4.3 on 22.02.11 12:03 */ | |
2 | |
3 /* | |
4 * Normalization rules for German text | |
5 * [this is a JFlex specification] | |
6 * | |
7 * Wolfgang Schmidle | |
8 * version 0.96 | |
9 * 2011-02-21 | |
10 * | |
11 */ | |
12 | |
13 package de.mpg.mpiwg.berlin.mpdl.lt.analyzer.lang; | |
14 | |
15 | |
16 /** | |
17 * This class is a scanner generated by | |
18 * <a href="http://www.jflex.de/">JFlex</a> 1.4.3 | |
19 * on 22.02.11 12:03 from the specification file | |
20 * <tt>MpdlNormalizerLexDE.lex</tt> | |
21 */ | |
22 public class MpdlNormalizerLexDE { | |
23 | |
24 /** This character denotes the end of file */ | |
25 public static final int YYEOF = -1; | |
26 | |
27 /** initial size of the lookahead buffer */ | |
28 private static final int ZZ_BUFFERSIZE = 16384; | |
29 | |
30 /** lexical states */ | |
31 public static final int SEARCH = 6; | |
32 public static final int DICT = 4; | |
33 public static final int YYINITIAL = 0; | |
34 public static final int CELEX = 8; | |
35 public static final int DISP = 2; | |
36 public static final int GRIMM = 10; | |
37 | |
38 /** | |
39 * ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l | |
40 * ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l | |
41 * at the beginning of a line | |
42 * l is of the form l = 2*k, k a non negative integer | |
43 */ | |
44 private static final int ZZ_LEXSTATE[] = { | |
45 0, 0, 1, 1, 2, 2, 1, 1, 3, 3, 4, 4 | |
46 }; | |
47 | |
48 /** | |
49 * Translates characters to character classes | |
50 */ | |
51 private static final String ZZ_CMAP_PACKED = | |
52 "\12\0\1\1\65\0\1\15\32\2\6\0\1\6\15\2\1\10\5\2"+ | |
53 "\1\4\5\2\111\0\1\11\21\0\1\12\5\0\1\13\2\0\1\14"+ | |
54 "\4\0\1\11\21\0\1\12\5\0\1\13\202\0\1\3\u01e4\0\1\7"+ | |
55 "\1\0\1\5\ufc99\0"; | |
56 | |
57 /** | |
58 * Translates characters to character classes | |
59 */ | |
60 private static final char [] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED); | |
61 | |
62 /** | |
63 * Translates DFA states to action switch labels. | |
64 */ | |
65 private static final int [] ZZ_ACTION = zzUnpackAction(); | |
66 | |
67 private static final String ZZ_ACTION_PACKED_0 = | |
68 "\5\0\1\1\1\2\1\3\1\4\3\1\1\5\3\1"+ | |
69 "\1\6\1\7\1\10\1\11\1\12\1\13\1\14\1\15"+ | |
70 "\1\16"; | |
71 | |
72 private static int [] zzUnpackAction() { | |
73 int [] result = new int[25]; | |
74 int offset = 0; | |
75 offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result); | |
76 return result; | |
77 } | |
78 | |
79 private static int zzUnpackAction(String packed, int offset, int [] result) { | |
80 int i = 0; /* index in packed string */ | |
81 int j = offset; /* index in unpacked array */ | |
82 int l = packed.length(); | |
83 while (i < l) { | |
84 int count = packed.charAt(i++); | |
85 int value = packed.charAt(i++); | |
86 do result[j++] = value; while (--count > 0); | |
87 } | |
88 return j; | |
89 } | |
90 | |
91 | |
92 /** | |
93 * Translates a state to a row index in the transition table | |
94 */ | |
95 private static final int [] ZZ_ROWMAP = zzUnpackRowMap(); | |
96 | |
97 private static final String ZZ_ROWMAP_PACKED_0 = | |
98 "\0\0\0\16\0\34\0\52\0\70\0\106\0\106\0\106"+ | |
99 "\0\106\0\124\0\142\0\160\0\106\0\176\0\214\0\232"+ | |
100 "\0\106\0\106\0\106\0\106\0\106\0\106\0\106\0\106"+ | |
101 "\0\106"; | |
102 | |
103 private static int [] zzUnpackRowMap() { | |
104 int [] result = new int[25]; | |
105 int offset = 0; | |
106 offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result); | |
107 return result; | |
108 } | |
109 | |
110 private static int zzUnpackRowMap(String packed, int offset, int [] result) { | |
111 int i = 0; /* index in packed string */ | |
112 int j = offset; /* index in unpacked array */ | |
113 int l = packed.length(); | |
114 while (i < l) { | |
115 int high = packed.charAt(i++) << 16; | |
116 result[j++] = high | packed.charAt(i++); | |
117 } | |
118 return j; | |
119 } | |
120 | |
121 /** | |
122 * The transition table of the DFA | |
123 */ | |
124 private static final int [] ZZ_TRANS = zzUnpackTrans(); | |
125 | |
126 private static final String ZZ_TRANS_PACKED_0 = | |
127 "\1\6\1\0\1\6\1\7\11\6\1\10\1\6\1\11"+ | |
128 "\1\6\1\7\1\12\1\6\1\13\1\6\1\14\4\6"+ | |
129 "\1\10\1\6\1\15\1\6\1\7\1\12\1\6\1\13"+ | |
130 "\1\6\1\14\4\6\2\10\1\15\1\6\1\7\1\16"+ | |
131 "\1\10\1\17\1\10\1\20\1\21\1\22\1\23\1\24"+ | |
132 "\1\10\1\6\1\15\1\6\1\7\1\12\1\6\1\13"+ | |
133 "\1\6\1\14\3\6\1\25\1\10\23\0\1\26\1\0"+ | |
134 "\1\27\15\0\1\30\15\0\1\31\13\0\1\26\1\0"+ | |
135 "\1\23\15\0\1\21\15\0\1\22\6\0"; | |
136 | |
137 private static int [] zzUnpackTrans() { | |
138 int [] result = new int[168]; | |
139 int offset = 0; | |
140 offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result); | |
141 return result; | |
142 } | |
143 | |
144 private static int zzUnpackTrans(String packed, int offset, int [] result) { | |
145 int i = 0; /* index in packed string */ | |
146 int j = offset; /* index in unpacked array */ | |
147 int l = packed.length(); | |
148 while (i < l) { | |
149 int count = packed.charAt(i++); | |
150 int value = packed.charAt(i++); | |
151 value--; | |
152 do result[j++] = value; while (--count > 0); | |
153 } | |
154 return j; | |
155 } | |
156 | |
157 | |
158 /* error codes */ | |
159 private static final int ZZ_UNKNOWN_ERROR = 0; | |
160 private static final int ZZ_NO_MATCH = 1; | |
161 private static final int ZZ_PUSHBACK_2BIG = 2; | |
162 | |
163 /* error messages for the codes above */ | |
164 private static final String ZZ_ERROR_MSG[] = { | |
165 "Unkown internal scanner error", | |
166 "Error: could not match input", | |
167 "Error: pushback value was too large" | |
168 }; | |
169 | |
170 /** | |
171 * ZZ_ATTRIBUTE[aState] contains the attributes of state <code>aState</code> | |
172 */ | |
173 private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute(); | |
174 | |
175 private static final String ZZ_ATTRIBUTE_PACKED_0 = | |
176 "\5\0\4\11\3\1\1\11\3\1\11\11"; | |
177 | |
178 private static int [] zzUnpackAttribute() { | |
179 int [] result = new int[25]; | |
180 int offset = 0; | |
181 offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result); | |
182 return result; | |
183 } | |
184 | |
185 private static int zzUnpackAttribute(String packed, int offset, int [] result) { | |
186 int i = 0; /* index in packed string */ | |
187 int j = offset; /* index in unpacked array */ | |
188 int l = packed.length(); | |
189 while (i < l) { | |
190 int count = packed.charAt(i++); | |
191 int value = packed.charAt(i++); | |
192 do result[j++] = value; while (--count > 0); | |
193 } | |
194 return j; | |
195 } | |
196 | |
197 /** the input device */ | |
198 private java.io.Reader zzReader; | |
199 | |
200 /** the current state of the DFA */ | |
201 private int zzState; | |
202 | |
203 /** the current lexical state */ | |
204 private int zzLexicalState = YYINITIAL; | |
205 | |
206 /** this buffer contains the current text to be matched and is | |
207 the source of the yytext() string */ | |
208 private char zzBuffer[] = new char[ZZ_BUFFERSIZE]; | |
209 | |
210 /** the textposition at the last accepting state */ | |
211 private int zzMarkedPos; | |
212 | |
213 /** the current text position in the buffer */ | |
214 private int zzCurrentPos; | |
215 | |
216 /** startRead marks the beginning of the yytext() string in the buffer */ | |
217 private int zzStartRead; | |
218 | |
219 /** endRead marks the last character in the buffer, that has been read | |
220 from input */ | |
221 private int zzEndRead; | |
222 | |
223 /** number of newlines encountered up to the start of the matched text */ | |
224 private int yyline; | |
225 | |
226 /** the number of characters up to the start of the matched text */ | |
227 private int yychar; | |
228 | |
229 /** | |
230 * the number of characters from the last newline up to the start of the | |
231 * matched text | |
232 */ | |
233 private int yycolumn; | |
234 | |
235 /** | |
236 * zzAtBOL == true <=> the scanner is currently at the beginning of a line | |
237 */ | |
238 private boolean zzAtBOL = true; | |
239 | |
240 /** zzAtEOF == true <=> the scanner is at the EOF */ | |
241 private boolean zzAtEOF; | |
242 | |
243 /** denotes if the user-EOF-code has already been executed */ | |
244 private boolean zzEOFDone; | |
245 | |
246 /* user code: */ | |
247 private String original = ""; | |
248 private String normalized = ""; | |
249 private int problem = 0; | |
250 | |
251 private void add (String norm) { | |
252 original += yytext(); | |
253 normalized += norm; | |
254 } | |
255 | |
256 | |
257 /** | |
258 * Creates a new scanner | |
259 * There is also a java.io.InputStream version of this constructor. | |
260 * | |
261 * @param in the java.io.Reader to read input from. | |
262 */ | |
263 public MpdlNormalizerLexDE(java.io.Reader in) { | |
264 this.zzReader = in; | |
265 } | |
266 | |
267 /** | |
268 * Creates a new scanner. | |
269 * There is also java.io.Reader version of this constructor. | |
270 * | |
271 * @param in the java.io.Inputstream to read input from. | |
272 */ | |
273 public MpdlNormalizerLexDE(java.io.InputStream in) { | |
274 this(new java.io.InputStreamReader(in)); | |
275 } | |
276 | |
277 /** | |
278 * Unpacks the compressed character translation table. | |
279 * | |
280 * @param packed the packed character translation table | |
281 * @return the unpacked character translation table | |
282 */ | |
283 private static char [] zzUnpackCMap(String packed) { | |
284 char [] map = new char[0x10000]; | |
285 int i = 0; /* index in packed string */ | |
286 int j = 0; /* index in unpacked array */ | |
287 while (i < 66) { | |
288 int count = packed.charAt(i++); | |
289 char value = packed.charAt(i++); | |
290 do map[j++] = value; while (--count > 0); | |
291 } | |
292 return map; | |
293 } | |
294 | |
295 | |
296 /** | |
297 * Refills the input buffer. | |
298 * | |
299 * @return <code>false</code>, iff there was new input. | |
300 * | |
301 * @exception java.io.IOException if any I/O-Error occurs | |
302 */ | |
303 private boolean zzRefill() throws java.io.IOException { | |
304 | |
305 /* first: make room (if you can) */ | |
306 if (zzStartRead > 0) { | |
307 System.arraycopy(zzBuffer, zzStartRead, | |
308 zzBuffer, 0, | |
309 zzEndRead-zzStartRead); | |
310 | |
311 /* translate stored positions */ | |
312 zzEndRead-= zzStartRead; | |
313 zzCurrentPos-= zzStartRead; | |
314 zzMarkedPos-= zzStartRead; | |
315 zzStartRead = 0; | |
316 } | |
317 | |
318 /* is the buffer big enough? */ | |
319 if (zzCurrentPos >= zzBuffer.length) { | |
320 /* if not: blow it up */ | |
321 char newBuffer[] = new char[zzCurrentPos*2]; | |
322 System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length); | |
323 zzBuffer = newBuffer; | |
324 } | |
325 | |
326 /* finally: fill the buffer with new input */ | |
327 int numRead = zzReader.read(zzBuffer, zzEndRead, | |
328 zzBuffer.length-zzEndRead); | |
329 | |
330 if (numRead > 0) { | |
331 zzEndRead+= numRead; | |
332 return false; | |
333 } | |
334 // unlikely but not impossible: read 0 characters, but not at end of stream | |
335 if (numRead == 0) { | |
336 int c = zzReader.read(); | |
337 if (c == -1) { | |
338 return true; | |
339 } else { | |
340 zzBuffer[zzEndRead++] = (char) c; | |
341 return false; | |
342 } | |
343 } | |
344 | |
345 // numRead < 0 | |
346 return true; | |
347 } | |
348 | |
349 | |
350 /** | |
351 * Closes the input stream. | |
352 */ | |
353 public final void yyclose() throws java.io.IOException { | |
354 zzAtEOF = true; /* indicate end of file */ | |
355 zzEndRead = zzStartRead; /* invalidate buffer */ | |
356 | |
357 if (zzReader != null) | |
358 zzReader.close(); | |
359 } | |
360 | |
361 | |
362 /** | |
363 * Resets the scanner to read from a new input stream. | |
364 * Does not close the old reader. | |
365 * | |
366 * All internal variables are reset, the old input stream | |
367 * <b>cannot</b> be reused (internal buffer is discarded and lost). | |
368 * Lexical state is set to <tt>ZZ_INITIAL</tt>. | |
369 * | |
370 * @param reader the new input stream | |
371 */ | |
372 public final void yyreset(java.io.Reader reader) { | |
373 zzReader = reader; | |
374 zzAtBOL = true; | |
375 zzAtEOF = false; | |
376 zzEOFDone = false; | |
377 zzEndRead = zzStartRead = 0; | |
378 zzCurrentPos = zzMarkedPos = 0; | |
379 yyline = yychar = yycolumn = 0; | |
380 zzLexicalState = YYINITIAL; | |
381 } | |
382 | |
383 | |
384 /** | |
385 * Returns the current lexical state. | |
386 */ | |
387 public final int yystate() { | |
388 return zzLexicalState; | |
389 } | |
390 | |
391 | |
392 /** | |
393 * Enters a new lexical state | |
394 * | |
395 * @param newState the new lexical state | |
396 */ | |
397 public final void yybegin(int newState) { | |
398 zzLexicalState = newState; | |
399 } | |
400 | |
401 | |
402 /** | |
403 * Returns the text matched by the current regular expression. | |
404 */ | |
405 public final String yytext() { | |
406 return new String( zzBuffer, zzStartRead, zzMarkedPos-zzStartRead ); | |
407 } | |
408 | |
409 | |
410 /** | |
411 * Returns the character at position <tt>pos</tt> from the | |
412 * matched text. | |
413 * | |
414 * It is equivalent to yytext().charAt(pos), but faster | |
415 * | |
416 * @param pos the position of the character to fetch. | |
417 * A value from 0 to yylength()-1. | |
418 * | |
419 * @return the character at position pos | |
420 */ | |
421 public final char yycharat(int pos) { | |
422 return zzBuffer[zzStartRead+pos]; | |
423 } | |
424 | |
425 | |
426 /** | |
427 * Returns the length of the matched text region. | |
428 */ | |
429 public final int yylength() { | |
430 return zzMarkedPos-zzStartRead; | |
431 } | |
432 | |
433 | |
434 /** | |
435 * Reports an error that occured while scanning. | |
436 * | |
437 * In a wellformed scanner (no or only correct usage of | |
438 * yypushback(int) and a match-all fallback rule) this method | |
439 * will only be called with things that "Can't Possibly Happen". | |
440 * If this method is called, something is seriously wrong | |
441 * (e.g. a JFlex bug producing a faulty scanner etc.). | |
442 * | |
443 * Usual syntax/scanner level error handling should be done | |
444 * in error fallback rules. | |
445 * | |
446 * @param errorCode the code of the errormessage to display | |
447 */ | |
448 private void zzScanError(int errorCode) { | |
449 String message; | |
450 try { | |
451 message = ZZ_ERROR_MSG[errorCode]; | |
452 } | |
453 catch (ArrayIndexOutOfBoundsException e) { | |
454 message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR]; | |
455 } | |
456 | |
457 throw new Error(message); | |
458 } | |
459 | |
460 | |
461 /** | |
462 * Pushes the specified amount of characters back into the input stream. | |
463 * | |
464 * They will be read again by then next call of the scanning method | |
465 * | |
466 * @param number the number of characters to be read again. | |
467 * This number must not be greater than yylength()! | |
468 */ | |
469 public void yypushback(int number) { | |
470 if ( number > yylength() ) | |
471 zzScanError(ZZ_PUSHBACK_2BIG); | |
472 | |
473 zzMarkedPos -= number; | |
474 } | |
475 | |
476 | |
477 /** | |
478 * Resumes scanning until the next regular expression is matched, | |
479 * the end of input is encountered or an I/O-Error occurs. | |
480 * | |
481 * @return the next token | |
482 * @exception java.io.IOException if any I/O-Error occurs | |
483 */ | |
484 public java.lang.String yylex() throws java.io.IOException { | |
485 int zzInput; | |
486 int zzAction; | |
487 | |
488 // cached fields: | |
489 int zzCurrentPosL; | |
490 int zzMarkedPosL; | |
491 int zzEndReadL = zzEndRead; | |
492 char [] zzBufferL = zzBuffer; | |
493 char [] zzCMapL = ZZ_CMAP; | |
494 | |
495 int [] zzTransL = ZZ_TRANS; | |
496 int [] zzRowMapL = ZZ_ROWMAP; | |
497 int [] zzAttrL = ZZ_ATTRIBUTE; | |
498 | |
499 while (true) { | |
500 zzMarkedPosL = zzMarkedPos; | |
501 | |
502 zzAction = -1; | |
503 | |
504 zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; | |
505 | |
506 zzState = ZZ_LEXSTATE[zzLexicalState]; | |
507 | |
508 | |
509 zzForAction: { | |
510 while (true) { | |
511 | |
512 if (zzCurrentPosL < zzEndReadL) | |
513 zzInput = zzBufferL[zzCurrentPosL++]; | |
514 else if (zzAtEOF) { | |
515 zzInput = YYEOF; | |
516 break zzForAction; | |
517 } | |
518 else { | |
519 // store back cached positions | |
520 zzCurrentPos = zzCurrentPosL; | |
521 zzMarkedPos = zzMarkedPosL; | |
522 boolean eof = zzRefill(); | |
523 // get translated positions and possibly new buffer | |
524 zzCurrentPosL = zzCurrentPos; | |
525 zzMarkedPosL = zzMarkedPos; | |
526 zzBufferL = zzBuffer; | |
527 zzEndReadL = zzEndRead; | |
528 if (eof) { | |
529 zzInput = YYEOF; | |
530 break zzForAction; | |
531 } | |
532 else { | |
533 zzInput = zzBufferL[zzCurrentPosL++]; | |
534 } | |
535 } | |
536 int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMapL[zzInput] ]; | |
537 if (zzNext == -1) break zzForAction; | |
538 zzState = zzNext; | |
539 | |
540 int zzAttributes = zzAttrL[zzState]; | |
541 if ( (zzAttributes & 1) == 1 ) { | |
542 zzAction = zzState; | |
543 zzMarkedPosL = zzCurrentPosL; | |
544 if ( (zzAttributes & 8) == 8 ) break zzForAction; | |
545 } | |
546 | |
547 } | |
548 } | |
549 | |
550 // store back cached position | |
551 zzMarkedPos = zzMarkedPosL; | |
552 | |
553 switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) { | |
554 case 10: | |
555 { add("sz"); | |
556 } | |
557 case 15: break; | |
558 case 3: | |
559 { problem = 1; add(yytext()); | |
560 } | |
561 case 16: break; | |
562 case 6: | |
563 { add("ae"); | |
564 } | |
565 case 17: break; | |
566 case 2: | |
567 { add("s"); | |
568 } | |
569 case 18: break; | |
570 case 4: | |
571 { switch (problem) { | |
572 case 1: return original; | |
573 default: return normalized; | |
574 } | |
575 } | |
576 case 19: break; | |
577 case 12: | |
578 { add("ü"); | |
579 } | |
580 case 20: break; | |
581 case 8: | |
582 { add("ue"); | |
583 } | |
584 case 21: break; | |
585 case 11: | |
586 { add("u"); | |
587 } | |
588 case 22: break; | |
589 case 13: | |
590 { add("ä"); | |
591 } | |
592 case 23: break; | |
593 case 1: | |
594 { add(yytext()); | |
595 } | |
596 case 24: break; | |
597 case 9: | |
598 { add("ss"); | |
599 } | |
600 case 25: break; | |
601 case 7: | |
602 { add("oe"); | |
603 } | |
604 case 26: break; | |
605 case 14: | |
606 { add("ö"); | |
607 } | |
608 case 27: break; | |
609 case 5: | |
610 { switch (problem) { | |
611 case 1: return ""; | |
612 default: return normalized; | |
613 } | |
614 } | |
615 case 28: break; | |
616 default: | |
617 if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { | |
618 zzAtEOF = true; | |
619 return null; | |
620 } | |
621 else { | |
622 zzScanError(ZZ_NO_MATCH); | |
623 } | |
624 } | |
625 } | |
626 } | |
627 | |
628 | |
629 } |