1 /** |
|
2 * Copyright (c) 2012, Ben Fortuna |
|
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 the |
|
14 * documentation and/or other materials provided with the distribution. |
|
15 * |
|
16 * o Neither the name of Ben Fortuna nor the names of any other contributors |
|
17 * may be used to endorse or promote products derived from this software |
|
18 * without specific prior written permission. |
|
19 * |
|
20 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
21 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
22 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
|
23 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR |
|
24 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
|
25 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
|
26 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
|
27 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
|
28 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
|
29 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
|
30 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
31 */ |
|
32 package net.fortuna.ical4j.data; |
|
33 |
|
34 import java.io.IOException; |
|
35 import java.io.InputStream; |
|
36 import java.io.InputStreamReader; |
|
37 import java.io.Reader; |
|
38 import java.io.StreamTokenizer; |
|
39 import java.net.URISyntaxException; |
|
40 import java.text.MessageFormat; |
|
41 import java.text.ParseException; |
|
42 |
|
43 import net.fortuna.ical4j.model.Calendar; |
|
44 import net.fortuna.ical4j.model.Component; |
|
45 |
|
46 import org.apache.commons.logging.Log; |
|
47 import org.apache.commons.logging.LogFactory; |
|
48 |
|
49 /** |
|
50 * <pre> |
|
51 * $Id$ |
|
52 * |
|
53 * Created [Nov 5, 2004] |
|
54 * </pre> |
|
55 * |
|
56 * The default implementation of a calendar parser. |
|
57 * @author Ben Fortuna |
|
58 */ |
|
59 public class CalendarParserImpl implements CalendarParser { |
|
60 |
|
61 private static final int WORD_CHAR_START = 32; |
|
62 |
|
63 private static final int WORD_CHAR_END = 255; |
|
64 |
|
65 private static final int WHITESPACE_CHAR_START = 0; |
|
66 |
|
67 private static final int WHITESPACE_CHAR_END = 20; |
|
68 |
|
69 private static final String UNEXPECTED_TOKEN_MESSAGE = "Expected [{0}], read [{1}]"; |
|
70 |
|
71 private Log log = LogFactory.getLog(CalendarParserImpl.class); |
|
72 |
|
73 private final ComponentListParser componentListParser = new ComponentListParser(); |
|
74 |
|
75 private final ComponentParser componentParser = new ComponentParser(); |
|
76 |
|
77 private final PropertyListParser propertyListParser = new PropertyListParser(); |
|
78 |
|
79 private final PropertyParser propertyParser = new PropertyParser(); |
|
80 |
|
81 private final ParameterListParser paramListParser = new ParameterListParser(); |
|
82 |
|
83 private final ParameterParser paramParser = new ParameterParser(); |
|
84 |
|
85 /** |
|
86 * {@inheritDoc} |
|
87 */ |
|
88 public final void parse(final InputStream in, final ContentHandler handler) |
|
89 throws IOException, ParserException { |
|
90 parse(new InputStreamReader(in), handler); |
|
91 } |
|
92 |
|
93 /** |
|
94 * {@inheritDoc} |
|
95 */ |
|
96 public final void parse(final Reader in, final ContentHandler handler) |
|
97 throws IOException, ParserException { |
|
98 |
|
99 final StreamTokenizer tokeniser = new StreamTokenizer(in); |
|
100 try { |
|
101 tokeniser.resetSyntax(); |
|
102 tokeniser.wordChars(WORD_CHAR_START, WORD_CHAR_END); |
|
103 tokeniser.whitespaceChars(WHITESPACE_CHAR_START, |
|
104 WHITESPACE_CHAR_END); |
|
105 tokeniser.ordinaryChar(':'); |
|
106 tokeniser.ordinaryChar(';'); |
|
107 tokeniser.ordinaryChar('='); |
|
108 tokeniser.ordinaryChar('\t'); |
|
109 tokeniser.eolIsSignificant(true); |
|
110 tokeniser.whitespaceChars(0, 0); |
|
111 tokeniser.quoteChar('"'); |
|
112 |
|
113 // BEGIN:VCALENDAR |
|
114 assertToken(tokeniser, in, Calendar.BEGIN); |
|
115 |
|
116 assertToken(tokeniser, in, ':'); |
|
117 |
|
118 assertToken(tokeniser, in, Calendar.VCALENDAR, true); |
|
119 |
|
120 assertToken(tokeniser, in, StreamTokenizer.TT_EOL); |
|
121 |
|
122 handler.startCalendar(); |
|
123 |
|
124 // parse calendar properties.. |
|
125 propertyListParser.parse(tokeniser, in, handler); |
|
126 |
|
127 // parse components.. |
|
128 componentListParser.parse(tokeniser, in, handler); |
|
129 |
|
130 // END:VCALENDAR |
|
131 // assertToken(tokeniser,Calendar.END); |
|
132 |
|
133 assertToken(tokeniser, in, ':'); |
|
134 |
|
135 assertToken(tokeniser, in, Calendar.VCALENDAR, true); |
|
136 |
|
137 handler.endCalendar(); |
|
138 } |
|
139 catch (Exception e) { |
|
140 |
|
141 if (e instanceof IOException) { |
|
142 throw (IOException) e; |
|
143 } |
|
144 if (e instanceof ParserException) { |
|
145 throw (ParserException) e; |
|
146 } |
|
147 else { |
|
148 throw new ParserException(e.getMessage(), getLineNumber(tokeniser, in), e); |
|
149 } |
|
150 } |
|
151 } |
|
152 |
|
153 /** |
|
154 * Parses an iCalendar property list from the specified stream tokeniser. |
|
155 * @param tokeniser |
|
156 * @throws IOException |
|
157 * @throws ParseException |
|
158 * @throws URISyntaxException |
|
159 * @throws URISyntaxException |
|
160 * @throws ParserException |
|
161 */ |
|
162 private class PropertyListParser { |
|
163 |
|
164 public void parse(final StreamTokenizer tokeniser, Reader in, |
|
165 final ContentHandler handler) throws IOException, ParseException, |
|
166 URISyntaxException, ParserException { |
|
167 |
|
168 assertToken(tokeniser, in, StreamTokenizer.TT_WORD); |
|
169 |
|
170 while (/* |
|
171 * !Component.BEGIN.equals(tokeniser.sval) && |
|
172 */!Component.END.equals(tokeniser.sval)) { |
|
173 // check for timezones observances or vevent/vtodo alarms.. |
|
174 if (Component.BEGIN.equals(tokeniser.sval)) { |
|
175 componentParser.parse(tokeniser, in, handler); |
|
176 } |
|
177 else { |
|
178 propertyParser.parse(tokeniser, in, handler); |
|
179 } |
|
180 absorbWhitespace(tokeniser, in); |
|
181 // assertToken(tokeniser, StreamTokenizer.TT_WORD); |
|
182 } |
|
183 } |
|
184 } |
|
185 |
|
186 /** |
|
187 * Parses an iCalendar property from the specified stream tokeniser. |
|
188 * @param tokeniser |
|
189 * @throws IOException |
|
190 * @throws ParserException |
|
191 * @throws URISyntaxException |
|
192 * @throws ParseException |
|
193 */ |
|
194 private class PropertyParser { |
|
195 |
|
196 private static final String PARSE_DEBUG_MESSAGE = "Property [{0}]"; |
|
197 |
|
198 private static final String PARSE_EXCEPTION_MESSAGE = "Property [{0}]"; |
|
199 |
|
200 private void parse(final StreamTokenizer tokeniser, Reader in, |
|
201 final ContentHandler handler) throws IOException, ParserException, |
|
202 URISyntaxException, ParseException { |
|
203 |
|
204 final String name = tokeniser.sval; |
|
205 |
|
206 // debugging.. |
|
207 if (log.isDebugEnabled()) { |
|
208 log.debug(MessageFormat.format(PARSE_DEBUG_MESSAGE, new Object[] {name})); |
|
209 } |
|
210 |
|
211 handler.startProperty(name); |
|
212 |
|
213 paramListParser.parse(tokeniser, in, handler); |
|
214 |
|
215 // it appears that control tokens (ie. ':') are allowed |
|
216 // after the first instance on a line is used.. as such |
|
217 // we must continue appending to value until EOL is |
|
218 // reached.. |
|
219 // assertToken(tokeniser, StreamTokenizer.TT_WORD); |
|
220 |
|
221 // String value = tokeniser.sval; |
|
222 final StringBuffer value = new StringBuffer(); |
|
223 |
|
224 // assertToken(tokeniser,StreamTokenizer.TT_EOL); |
|
225 |
|
226 // DQUOTE is ordinary char for property value |
|
227 // From sec 4.3.11 of rfc-2445: |
|
228 // text = *(TSAFE-CHAR / ":" / DQUOTE / ESCAPED-CHAR) |
|
229 // |
|
230 tokeniser.ordinaryChar('"'); |
|
231 int nextToken = nextToken(tokeniser, in); |
|
232 |
|
233 while (nextToken != StreamTokenizer.TT_EOL) { |
|
234 |
|
235 if (tokeniser.ttype == StreamTokenizer.TT_WORD) { |
|
236 value.append(tokeniser.sval); |
|
237 } |
|
238 else { |
|
239 value.append((char) tokeniser.ttype); |
|
240 } |
|
241 |
|
242 nextToken = nextToken(tokeniser, in); |
|
243 } |
|
244 |
|
245 // reset DQUOTE to be quote char |
|
246 tokeniser.quoteChar('"'); |
|
247 |
|
248 try { |
|
249 handler.propertyValue(value.toString()); |
|
250 } |
|
251 catch (ParseException e) { |
|
252 final ParseException eNew = new ParseException("[" + name + "] " |
|
253 + e.getMessage(), e.getErrorOffset()); |
|
254 eNew.initCause(e); |
|
255 throw eNew; |
|
256 } |
|
257 |
|
258 handler.endProperty(name); |
|
259 |
|
260 } |
|
261 } |
|
262 |
|
263 /** |
|
264 * Parses a list of iCalendar parameters by parsing the specified stream tokeniser. |
|
265 * @param tokeniser |
|
266 * @throws IOException |
|
267 * @throws ParserException |
|
268 * @throws URISyntaxException |
|
269 */ |
|
270 private class ParameterListParser { |
|
271 |
|
272 public void parse(final StreamTokenizer tokeniser, Reader in, |
|
273 final ContentHandler handler) throws IOException, ParserException, |
|
274 URISyntaxException { |
|
275 |
|
276 while (nextToken(tokeniser, in) == ';') { |
|
277 paramParser.parse(tokeniser, in, handler); |
|
278 } |
|
279 } |
|
280 } |
|
281 |
|
282 /** |
|
283 * @param tokeniser |
|
284 * @param handler |
|
285 * @throws IOException |
|
286 * @throws ParserException |
|
287 * @throws URISyntaxException |
|
288 */ |
|
289 private class ParameterParser { |
|
290 |
|
291 private void parse(final StreamTokenizer tokeniser, Reader in, |
|
292 final ContentHandler handler) throws IOException, ParserException, |
|
293 URISyntaxException { |
|
294 |
|
295 assertToken(tokeniser, in, StreamTokenizer.TT_WORD); |
|
296 |
|
297 final String paramName = tokeniser.sval; |
|
298 |
|
299 // debugging.. |
|
300 if (log.isDebugEnabled()) { |
|
301 log.debug("Parameter [" + paramName + "]"); |
|
302 } |
|
303 |
|
304 assertToken(tokeniser, in, '='); |
|
305 |
|
306 final StringBuffer paramValue = new StringBuffer(); |
|
307 |
|
308 // preserve quote chars.. |
|
309 if (nextToken(tokeniser, in) == '"') { |
|
310 paramValue.append('"'); |
|
311 paramValue.append(tokeniser.sval); |
|
312 paramValue.append('"'); |
|
313 } |
|
314 else if (tokeniser.sval != null) { |
|
315 paramValue.append(tokeniser.sval); |
|
316 // check for additional words to account for equals (=) in param-value |
|
317 int nextToken = nextToken(tokeniser, in); |
|
318 |
|
319 while (nextToken != ';' && nextToken != ':' && nextToken != ',') { |
|
320 |
|
321 if (tokeniser.ttype == StreamTokenizer.TT_WORD) { |
|
322 paramValue.append(tokeniser.sval); |
|
323 } |
|
324 else { |
|
325 paramValue.append((char) tokeniser.ttype); |
|
326 } |
|
327 |
|
328 nextToken = nextToken(tokeniser, in); |
|
329 } |
|
330 tokeniser.pushBack(); |
|
331 } else if(tokeniser.sval == null) { |
|
332 tokeniser.pushBack(); |
|
333 } |
|
334 |
|
335 try { |
|
336 handler.parameter(paramName, paramValue.toString()); |
|
337 } |
|
338 catch (ClassCastException cce) { |
|
339 throw new ParserException("Error parsing parameter", getLineNumber(tokeniser, in), cce); |
|
340 } |
|
341 } |
|
342 } |
|
343 |
|
344 /** |
|
345 * Parses an iCalendar component list from the specified stream tokeniser. |
|
346 * @param tokeniser |
|
347 * @throws IOException |
|
348 * @throws ParseException |
|
349 * @throws URISyntaxException |
|
350 * @throws ParserException |
|
351 */ |
|
352 private class ComponentListParser { |
|
353 |
|
354 private void parse(final StreamTokenizer tokeniser, Reader in, |
|
355 final ContentHandler handler) throws IOException, ParseException, |
|
356 URISyntaxException, ParserException { |
|
357 |
|
358 while (Component.BEGIN.equals(tokeniser.sval)) { |
|
359 componentParser.parse(tokeniser, in, handler); |
|
360 absorbWhitespace(tokeniser, in); |
|
361 // assertToken(tokeniser, StreamTokenizer.TT_WORD); |
|
362 } |
|
363 } |
|
364 } |
|
365 |
|
366 /** |
|
367 * Parses an iCalendar component from the specified stream tokeniser. |
|
368 * @param tokeniser |
|
369 * @throws IOException |
|
370 * @throws ParseException |
|
371 * @throws URISyntaxException |
|
372 * @throws ParserException |
|
373 */ |
|
374 private class ComponentParser { |
|
375 |
|
376 private void parse(final StreamTokenizer tokeniser, Reader in, |
|
377 final ContentHandler handler) throws IOException, ParseException, |
|
378 URISyntaxException, ParserException { |
|
379 |
|
380 assertToken(tokeniser, in, ':'); |
|
381 |
|
382 assertToken(tokeniser, in, StreamTokenizer.TT_WORD); |
|
383 |
|
384 final String name = tokeniser.sval; |
|
385 |
|
386 handler.startComponent(name); |
|
387 |
|
388 assertToken(tokeniser, in, StreamTokenizer.TT_EOL); |
|
389 |
|
390 propertyListParser.parse(tokeniser, in, handler); |
|
391 |
|
392 /* |
|
393 * // a special case for VTIMEZONE component which contains |
|
394 * // sub-components.. |
|
395 * if (Component.VTIMEZONE.equals(name)) { |
|
396 * parseComponentList(tokeniser, handler); |
|
397 * } |
|
398 * // VEVENT/VTODO components may optionally have embedded VALARM |
|
399 * // components.. |
|
400 * else if ((Component.VEVENT.equals(name) || Component.VTODO.equals(name)) |
|
401 * && Component.BEGIN.equals(tokeniser.sval)) { |
|
402 * parseComponentList(tokeniser, handler); |
|
403 * } |
|
404 */ |
|
405 |
|
406 assertToken(tokeniser, in, ':'); |
|
407 |
|
408 assertToken(tokeniser, in, name); |
|
409 |
|
410 assertToken(tokeniser, in, StreamTokenizer.TT_EOL); |
|
411 |
|
412 handler.endComponent(name); |
|
413 } |
|
414 } |
|
415 |
|
416 /** |
|
417 * Asserts that the next token in the stream matches the specified token. |
|
418 * @param tokeniser stream tokeniser to perform assertion on |
|
419 * @param token expected token |
|
420 * @throws IOException when unable to read from stream |
|
421 * @throws ParserException when next token in the stream does not match the expected token |
|
422 */ |
|
423 private void assertToken(final StreamTokenizer tokeniser, Reader in, final int token) |
|
424 throws IOException, ParserException { |
|
425 |
|
426 if (nextToken(tokeniser, in) != token) { |
|
427 throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] { |
|
428 new Integer(token), new Integer(tokeniser.ttype), |
|
429 }), getLineNumber(tokeniser, in)); |
|
430 } |
|
431 |
|
432 if (log.isDebugEnabled()) { |
|
433 log.debug("[" + token + "]"); |
|
434 } |
|
435 } |
|
436 |
|
437 /** |
|
438 * Asserts that the next token in the stream matches the specified token. This method is case-sensitive. |
|
439 * @param tokeniser |
|
440 * @param token |
|
441 * @throws IOException |
|
442 * @throws ParserException |
|
443 */ |
|
444 private void assertToken(final StreamTokenizer tokeniser, Reader in, final String token) |
|
445 throws IOException, ParserException { |
|
446 assertToken(tokeniser, in, token, false); |
|
447 } |
|
448 |
|
449 /** |
|
450 * Asserts that the next token in the stream matches the specified token. |
|
451 * @param tokeniser stream tokeniser to perform assertion on |
|
452 * @param token expected token |
|
453 * @throws IOException when unable to read from stream |
|
454 * @throws ParserException when next token in the stream does not match the expected token |
|
455 */ |
|
456 private void assertToken(final StreamTokenizer tokeniser, Reader in, |
|
457 final String token, final boolean ignoreCase) throws IOException, |
|
458 ParserException { |
|
459 |
|
460 // ensure next token is a word token.. |
|
461 assertToken(tokeniser, in, StreamTokenizer.TT_WORD); |
|
462 |
|
463 if (ignoreCase) { |
|
464 if (!token.equalsIgnoreCase(tokeniser.sval)) { |
|
465 throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] { |
|
466 token, tokeniser.sval, |
|
467 }), getLineNumber(tokeniser, in)); |
|
468 } |
|
469 } |
|
470 else if (!token.equals(tokeniser.sval)) { |
|
471 throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] { |
|
472 token, tokeniser.sval, |
|
473 }), getLineNumber(tokeniser, in)); |
|
474 } |
|
475 |
|
476 if (log.isDebugEnabled()) { |
|
477 log.debug("[" + token + "]"); |
|
478 } |
|
479 } |
|
480 |
|
481 /** |
|
482 * Absorbs extraneous newlines. |
|
483 * @param tokeniser |
|
484 * @throws IOException |
|
485 */ |
|
486 private void absorbWhitespace(final StreamTokenizer tokeniser, Reader in) throws IOException, ParserException { |
|
487 // HACK: absorb extraneous whitespace between components (KOrganizer).. |
|
488 while (nextToken(tokeniser, in) == StreamTokenizer.TT_EOL) { |
|
489 if (log.isTraceEnabled()) { |
|
490 log.trace("Absorbing extra whitespace.."); |
|
491 } |
|
492 } |
|
493 if (log.isTraceEnabled()) { |
|
494 log.trace("Aborting: absorbing extra whitespace complete"); |
|
495 } |
|
496 } |
|
497 |
|
498 /** |
|
499 * @param tokeniser |
|
500 * @param in |
|
501 * @return |
|
502 */ |
|
503 private int getLineNumber(StreamTokenizer tokeniser, Reader in) { |
|
504 int line = tokeniser.lineno(); |
|
505 if (tokeniser.ttype == StreamTokenizer.TT_EOL) { |
|
506 line -= 1; |
|
507 } |
|
508 if (in instanceof UnfoldingReader) { |
|
509 // need to take unfolded lines into account |
|
510 final int unfolded = ((UnfoldingReader) in).getLinesUnfolded(); |
|
511 line += unfolded; |
|
512 } |
|
513 return line; |
|
514 } |
|
515 |
|
516 /** |
|
517 * Reads the next token from the tokeniser. |
|
518 * This method throws a ParseException when reading EOF. |
|
519 * @param tokeniser |
|
520 * @param in |
|
521 * @return |
|
522 * @throws ParseException When reading EOF. |
|
523 */ |
|
524 private int nextToken(StreamTokenizer tokeniser, Reader in) throws IOException, ParserException { |
|
525 int token = tokeniser.nextToken(); |
|
526 if (token == StreamTokenizer.TT_EOF) { |
|
527 throw new ParserException("Unexpected end of file", getLineNumber(tokeniser, in)); |
|
528 } |
|
529 return token; |
|
530 } |
|
531 } |
|