1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/src/net/fortuna/ical4j/data/CalendarParserImpl.java Tue Feb 10 18:12:00 2015 +0100
1.3 @@ -0,0 +1,521 @@
1.4 +/**
1.5 + * Copyright (c) 2012, Ben Fortuna
1.6 + * All rights reserved.
1.7 + *
1.8 + * Redistribution and use in source and binary forms, with or without
1.9 + * modification, are permitted provided that the following conditions
1.10 + * are met:
1.11 + *
1.12 + * o Redistributions of source code must retain the above copyright
1.13 + * notice, this list of conditions and the following disclaimer.
1.14 + *
1.15 + * o Redistributions in binary form must reproduce the above copyright
1.16 + * notice, this list of conditions and the following disclaimer in the
1.17 + * documentation and/or other materials provided with the distribution.
1.18 + *
1.19 + * o Neither the name of Ben Fortuna nor the names of any other contributors
1.20 + * may be used to endorse or promote products derived from this software
1.21 + * without specific prior written permission.
1.22 + *
1.23 + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
1.24 + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
1.25 + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
1.26 + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
1.27 + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
1.28 + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
1.29 + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
1.30 + * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
1.31 + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
1.32 + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
1.33 + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
1.34 + */
1.35 +package net.fortuna.ical4j.data;
1.36 +
1.37 +import java.io.IOException;
1.38 +import java.io.InputStream;
1.39 +import java.io.InputStreamReader;
1.40 +import java.io.Reader;
1.41 +import java.io.StreamTokenizer;
1.42 +import java.net.URISyntaxException;
1.43 +import java.text.MessageFormat;
1.44 +import java.text.ParseException;
1.45 +
1.46 +import net.fortuna.ical4j.model.Calendar;
1.47 +import net.fortuna.ical4j.model.Component;
1.48 +
1.49 +import org.apache.commons.logging.Log;
1.50 +import org.apache.commons.logging.LogFactory;
1.51 +
1.52 +/**
1.53 + * <pre>
1.54 + * $Id$
1.55 + *
1.56 + * Created [Nov 5, 2004]
1.57 + * </pre>
1.58 + *
1.59 + * The default implementation of a calendar parser.
1.60 + * @author Ben Fortuna
1.61 + */
1.62 +public class CalendarParserImpl implements CalendarParser {
1.63 +
1.64 + private static final int WORD_CHAR_START = 32;
1.65 +
1.66 + private static final int WORD_CHAR_END = 255;
1.67 +
1.68 + private static final int WHITESPACE_CHAR_START = 0;
1.69 +
1.70 + private static final int WHITESPACE_CHAR_END = 20;
1.71 +
1.72 + private static final String UNEXPECTED_TOKEN_MESSAGE = "Expected [{0}], read [{1}]";
1.73 +
1.74 + private Log log = LogFactory.getLog(CalendarParserImpl.class);
1.75 +
1.76 + private final ComponentListParser componentListParser = new ComponentListParser();
1.77 +
1.78 + private final ComponentParser componentParser = new ComponentParser();
1.79 +
1.80 + private final PropertyListParser propertyListParser = new PropertyListParser();
1.81 +
1.82 + private final PropertyParser propertyParser = new PropertyParser();
1.83 +
1.84 + private final ParameterListParser paramListParser = new ParameterListParser();
1.85 +
1.86 + private final ParameterParser paramParser = new ParameterParser();
1.87 +
1.88 + /**
1.89 + * {@inheritDoc}
1.90 + */
1.91 + public final void parse(final InputStream in, final ContentHandler handler)
1.92 + throws IOException, ParserException {
1.93 + parse(new InputStreamReader(in), handler);
1.94 + }
1.95 +
1.96 + /**
1.97 + * {@inheritDoc}
1.98 + */
1.99 + public final void parse(final Reader in, final ContentHandler handler)
1.100 + throws IOException, ParserException {
1.101 +
1.102 + final StreamTokenizer tokeniser = new StreamTokenizer(in);
1.103 + try {
1.104 + tokeniser.resetSyntax();
1.105 + tokeniser.wordChars(WORD_CHAR_START, WORD_CHAR_END);
1.106 + tokeniser.whitespaceChars(WHITESPACE_CHAR_START,
1.107 + WHITESPACE_CHAR_END);
1.108 + tokeniser.ordinaryChar(':');
1.109 + tokeniser.ordinaryChar(';');
1.110 + tokeniser.ordinaryChar('=');
1.111 + tokeniser.ordinaryChar('\t');
1.112 + tokeniser.eolIsSignificant(true);
1.113 + tokeniser.whitespaceChars(0, 0);
1.114 + tokeniser.quoteChar('"');
1.115 +
1.116 + // BEGIN:VCALENDAR
1.117 + assertToken(tokeniser, in, Calendar.BEGIN);
1.118 +
1.119 + assertToken(tokeniser, in, ':');
1.120 +
1.121 + assertToken(tokeniser, in, Calendar.VCALENDAR, true);
1.122 +
1.123 + assertToken(tokeniser, in, StreamTokenizer.TT_EOL);
1.124 +
1.125 + handler.startCalendar();
1.126 +
1.127 + // parse calendar properties..
1.128 + propertyListParser.parse(tokeniser, in, handler);
1.129 +
1.130 + // parse components..
1.131 + componentListParser.parse(tokeniser, in, handler);
1.132 +
1.133 + // END:VCALENDAR
1.134 + // assertToken(tokeniser,Calendar.END);
1.135 +
1.136 + assertToken(tokeniser, in, ':');
1.137 +
1.138 + assertToken(tokeniser, in, Calendar.VCALENDAR, true);
1.139 +
1.140 + handler.endCalendar();
1.141 + }
1.142 + catch (Exception e) {
1.143 +
1.144 + if (e instanceof IOException) {
1.145 + throw (IOException) e;
1.146 + }
1.147 + if (e instanceof ParserException) {
1.148 + throw (ParserException) e;
1.149 + }
1.150 + else {
1.151 + throw new ParserException(e.getMessage(), getLineNumber(tokeniser, in), e);
1.152 + }
1.153 + }
1.154 + }
1.155 +
1.156 + /**
1.157 + * Parses an iCalendar property list from the specified stream tokeniser.
1.158 + * @param tokeniser
1.159 + * @throws IOException
1.160 + * @throws ParseException
1.161 + * @throws URISyntaxException
1.162 + * @throws URISyntaxException
1.163 + * @throws ParserException
1.164 + */
1.165 + private class PropertyListParser {
1.166 +
1.167 + public void parse(final StreamTokenizer tokeniser, Reader in,
1.168 + final ContentHandler handler) throws IOException, ParseException,
1.169 + URISyntaxException, ParserException {
1.170 +
1.171 + assertToken(tokeniser, in, StreamTokenizer.TT_WORD);
1.172 +
1.173 + while (/*
1.174 + * !Component.BEGIN.equals(tokeniser.sval) &&
1.175 + */!Component.END.equals(tokeniser.sval)) {
1.176 + // check for timezones observances or vevent/vtodo alarms..
1.177 + if (Component.BEGIN.equals(tokeniser.sval)) {
1.178 + componentParser.parse(tokeniser, in, handler);
1.179 + }
1.180 + else {
1.181 + propertyParser.parse(tokeniser, in, handler);
1.182 + }
1.183 + absorbWhitespace(tokeniser);
1.184 + // assertToken(tokeniser, StreamTokenizer.TT_WORD);
1.185 + }
1.186 + }
1.187 + }
1.188 +
1.189 + /**
1.190 + * Parses an iCalendar property from the specified stream tokeniser.
1.191 + * @param tokeniser
1.192 + * @throws IOException
1.193 + * @throws ParserException
1.194 + * @throws URISyntaxException
1.195 + * @throws ParseException
1.196 + */
1.197 + private class PropertyParser {
1.198 +
1.199 + private static final String PARSE_DEBUG_MESSAGE = "Property [{0}]";
1.200 +
1.201 + private static final String PARSE_EXCEPTION_MESSAGE = "Property [{0}]";
1.202 +
1.203 + private void parse(final StreamTokenizer tokeniser, Reader in,
1.204 + final ContentHandler handler) throws IOException, ParserException,
1.205 + URISyntaxException, ParseException {
1.206 +
1.207 + final String name = tokeniser.sval;
1.208 +
1.209 + // debugging..
1.210 + if (log.isDebugEnabled()) {
1.211 + log.debug(MessageFormat.format(PARSE_DEBUG_MESSAGE, new Object[] {name}));
1.212 + }
1.213 +
1.214 + handler.startProperty(name);
1.215 +
1.216 + paramListParser.parse(tokeniser, in, handler);
1.217 +
1.218 + // it appears that control tokens (ie. ':') are allowed
1.219 + // after the first instance on a line is used.. as such
1.220 + // we must continue appending to value until EOL is
1.221 + // reached..
1.222 + // assertToken(tokeniser, StreamTokenizer.TT_WORD);
1.223 +
1.224 + // String value = tokeniser.sval;
1.225 + final StringBuffer value = new StringBuffer();
1.226 +
1.227 + // assertToken(tokeniser,StreamTokenizer.TT_EOL);
1.228 +
1.229 + // DQUOTE is ordinary char for property value
1.230 + // From sec 4.3.11 of rfc-2445:
1.231 + // text = *(TSAFE-CHAR / ":" / DQUOTE / ESCAPED-CHAR)
1.232 + //
1.233 + tokeniser.ordinaryChar('"');
1.234 + int nextToken = tokeniser.nextToken();
1.235 +
1.236 + while (nextToken != StreamTokenizer.TT_EOL
1.237 + && nextToken != StreamTokenizer.TT_EOF) {
1.238 +
1.239 + if (tokeniser.ttype == StreamTokenizer.TT_WORD) {
1.240 + value.append(tokeniser.sval);
1.241 + }
1.242 + else {
1.243 + value.append((char) tokeniser.ttype);
1.244 + }
1.245 +
1.246 + nextToken = tokeniser.nextToken();
1.247 + }
1.248 +
1.249 + // reset DQUOTE to be quote char
1.250 + tokeniser.quoteChar('"');
1.251 +
1.252 + if (nextToken == StreamTokenizer.TT_EOF) {
1.253 + throw new ParserException("Unexpected end of file",
1.254 + getLineNumber(tokeniser, in));
1.255 + }
1.256 +
1.257 + try {
1.258 + handler.propertyValue(value.toString());
1.259 + }
1.260 + catch (ParseException e) {
1.261 + final ParseException eNew = new ParseException("[" + name + "] "
1.262 + + e.getMessage(), e.getErrorOffset());
1.263 + eNew.initCause(e);
1.264 + throw eNew;
1.265 + }
1.266 +
1.267 + handler.endProperty(name);
1.268 +
1.269 + }
1.270 + }
1.271 +
1.272 + /**
1.273 + * Parses a list of iCalendar parameters by parsing the specified stream tokeniser.
1.274 + * @param tokeniser
1.275 + * @throws IOException
1.276 + * @throws ParserException
1.277 + * @throws URISyntaxException
1.278 + */
1.279 + private class ParameterListParser {
1.280 +
1.281 + public void parse(final StreamTokenizer tokeniser, Reader in,
1.282 + final ContentHandler handler) throws IOException, ParserException,
1.283 + URISyntaxException {
1.284 +
1.285 + while (tokeniser.nextToken() == ';') {
1.286 + paramParser.parse(tokeniser, in, handler);
1.287 + }
1.288 + }
1.289 + }
1.290 +
1.291 + /**
1.292 + * @param tokeniser
1.293 + * @param handler
1.294 + * @throws IOException
1.295 + * @throws ParserException
1.296 + * @throws URISyntaxException
1.297 + */
1.298 + private class ParameterParser {
1.299 +
1.300 + private void parse(final StreamTokenizer tokeniser, Reader in,
1.301 + final ContentHandler handler) throws IOException, ParserException,
1.302 + URISyntaxException {
1.303 +
1.304 + assertToken(tokeniser, in, StreamTokenizer.TT_WORD);
1.305 +
1.306 + final String paramName = tokeniser.sval;
1.307 +
1.308 + // debugging..
1.309 + if (log.isDebugEnabled()) {
1.310 + log.debug("Parameter [" + paramName + "]");
1.311 + }
1.312 +
1.313 + assertToken(tokeniser, in, '=');
1.314 +
1.315 + final StringBuffer paramValue = new StringBuffer();
1.316 +
1.317 + // preserve quote chars..
1.318 + if (tokeniser.nextToken() == '"') {
1.319 + paramValue.append('"');
1.320 + paramValue.append(tokeniser.sval);
1.321 + paramValue.append('"');
1.322 + }
1.323 + else if (tokeniser.sval != null) {
1.324 + paramValue.append(tokeniser.sval);
1.325 + // check for additional words to account for equals (=) in param-value
1.326 + int nextToken = tokeniser.nextToken();
1.327 +
1.328 + while (nextToken != ';' && nextToken != ':' && nextToken != ',') {
1.329 +
1.330 + if (tokeniser.ttype == StreamTokenizer.TT_WORD) {
1.331 + paramValue.append(tokeniser.sval);
1.332 + }
1.333 + else {
1.334 + paramValue.append((char) tokeniser.ttype);
1.335 + }
1.336 +
1.337 + nextToken = tokeniser.nextToken();
1.338 + }
1.339 + tokeniser.pushBack();
1.340 + } else if(tokeniser.sval == null) {
1.341 + tokeniser.pushBack();
1.342 + }
1.343 +
1.344 + try {
1.345 + handler.parameter(paramName, paramValue.toString());
1.346 + }
1.347 + catch (ClassCastException cce) {
1.348 + throw new ParserException("Error parsing parameter", getLineNumber(tokeniser, in), cce);
1.349 + }
1.350 + }
1.351 + }
1.352 +
1.353 + /**
1.354 + * Parses an iCalendar component list from the specified stream tokeniser.
1.355 + * @param tokeniser
1.356 + * @throws IOException
1.357 + * @throws ParseException
1.358 + * @throws URISyntaxException
1.359 + * @throws ParserException
1.360 + */
1.361 + private class ComponentListParser {
1.362 +
1.363 + private void parse(final StreamTokenizer tokeniser, Reader in,
1.364 + final ContentHandler handler) throws IOException, ParseException,
1.365 + URISyntaxException, ParserException {
1.366 +
1.367 + while (Component.BEGIN.equals(tokeniser.sval)) {
1.368 + componentParser.parse(tokeniser, in, handler);
1.369 + absorbWhitespace(tokeniser);
1.370 + // assertToken(tokeniser, StreamTokenizer.TT_WORD);
1.371 + }
1.372 + }
1.373 + }
1.374 +
1.375 + /**
1.376 + * Parses an iCalendar component from the specified stream tokeniser.
1.377 + * @param tokeniser
1.378 + * @throws IOException
1.379 + * @throws ParseException
1.380 + * @throws URISyntaxException
1.381 + * @throws ParserException
1.382 + */
1.383 + private class ComponentParser {
1.384 +
1.385 + private void parse(final StreamTokenizer tokeniser, Reader in,
1.386 + final ContentHandler handler) throws IOException, ParseException,
1.387 + URISyntaxException, ParserException {
1.388 +
1.389 + assertToken(tokeniser, in, ':');
1.390 +
1.391 + assertToken(tokeniser, in, StreamTokenizer.TT_WORD);
1.392 +
1.393 + final String name = tokeniser.sval;
1.394 +
1.395 + handler.startComponent(name);
1.396 +
1.397 + assertToken(tokeniser, in, StreamTokenizer.TT_EOL);
1.398 +
1.399 + propertyListParser.parse(tokeniser, in, handler);
1.400 +
1.401 + /*
1.402 + * // a special case for VTIMEZONE component which contains
1.403 + * // sub-components..
1.404 + * if (Component.VTIMEZONE.equals(name)) {
1.405 + * parseComponentList(tokeniser, handler);
1.406 + * }
1.407 + * // VEVENT/VTODO components may optionally have embedded VALARM
1.408 + * // components..
1.409 + * else if ((Component.VEVENT.equals(name) || Component.VTODO.equals(name))
1.410 + * && Component.BEGIN.equals(tokeniser.sval)) {
1.411 + * parseComponentList(tokeniser, handler);
1.412 + * }
1.413 + */
1.414 +
1.415 + assertToken(tokeniser, in, ':');
1.416 +
1.417 + assertToken(tokeniser, in, name);
1.418 +
1.419 + assertToken(tokeniser, in, StreamTokenizer.TT_EOL);
1.420 +
1.421 + handler.endComponent(name);
1.422 + }
1.423 + }
1.424 +
1.425 + /**
1.426 + * Asserts that the next token in the stream matches the specified token.
1.427 + * @param tokeniser stream tokeniser to perform assertion on
1.428 + * @param token expected token
1.429 + * @throws IOException when unable to read from stream
1.430 + * @throws ParserException when next token in the stream does not match the expected token
1.431 + */
1.432 + private void assertToken(final StreamTokenizer tokeniser, Reader in, final int token)
1.433 + throws IOException, ParserException {
1.434 +
1.435 + if (tokeniser.nextToken() != token) {
1.436 + throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] {
1.437 + new Integer(token), new Integer(tokeniser.ttype),
1.438 + }), getLineNumber(tokeniser, in));
1.439 + }
1.440 +
1.441 + if (log.isDebugEnabled()) {
1.442 + log.debug("[" + token + "]");
1.443 + }
1.444 + }
1.445 +
1.446 + /**
1.447 + * Asserts that the next token in the stream matches the specified token. This method is case-sensitive.
1.448 + * @param tokeniser
1.449 + * @param token
1.450 + * @throws IOException
1.451 + * @throws ParserException
1.452 + */
1.453 + private void assertToken(final StreamTokenizer tokeniser, Reader in, final String token)
1.454 + throws IOException, ParserException {
1.455 + assertToken(tokeniser, in, token, false);
1.456 + }
1.457 +
1.458 + /**
1.459 + * Asserts that the next token in the stream matches the specified token.
1.460 + * @param tokeniser stream tokeniser to perform assertion on
1.461 + * @param token expected token
1.462 + * @throws IOException when unable to read from stream
1.463 + * @throws ParserException when next token in the stream does not match the expected token
1.464 + */
1.465 + private void assertToken(final StreamTokenizer tokeniser, Reader in,
1.466 + final String token, final boolean ignoreCase) throws IOException,
1.467 + ParserException {
1.468 +
1.469 + // ensure next token is a word token..
1.470 + assertToken(tokeniser, in, StreamTokenizer.TT_WORD);
1.471 +
1.472 + if (ignoreCase) {
1.473 + if (!token.equalsIgnoreCase(tokeniser.sval)) {
1.474 + throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] {
1.475 + token, tokeniser.sval,
1.476 + }), getLineNumber(tokeniser, in));
1.477 + }
1.478 + }
1.479 + else if (!token.equals(tokeniser.sval)) {
1.480 + throw new ParserException(MessageFormat.format(UNEXPECTED_TOKEN_MESSAGE, new Object[] {
1.481 + token, tokeniser.sval,
1.482 + }), getLineNumber(tokeniser, in));
1.483 + }
1.484 +
1.485 + if (log.isDebugEnabled()) {
1.486 + log.debug("[" + token + "]");
1.487 + }
1.488 + }
1.489 +
1.490 + /**
1.491 + * Absorbs extraneous newlines.
1.492 + * @param tokeniser
1.493 + * @throws IOException
1.494 + */
1.495 + private void absorbWhitespace(final StreamTokenizer tokeniser) throws IOException {
1.496 + // HACK: absorb extraneous whitespace between components (KOrganizer)..
1.497 + while (tokeniser.nextToken() == StreamTokenizer.TT_EOL) {
1.498 + if (log.isTraceEnabled()) {
1.499 + log.trace("Absorbing extra whitespace..");
1.500 + }
1.501 + }
1.502 + if (log.isTraceEnabled()) {
1.503 + log.trace("Aborting: absorbing extra whitespace complete");
1.504 + }
1.505 + }
1.506 +
1.507 + /**
1.508 + * @param tokeniser
1.509 + * @param in
1.510 + * @return
1.511 + */
1.512 + private int getLineNumber(StreamTokenizer tokeniser, Reader in) {
1.513 + int line = tokeniser.lineno();
1.514 + if (tokeniser.ttype == StreamTokenizer.TT_EOL) {
1.515 + line -= 1;
1.516 + }
1.517 + if (in instanceof UnfoldingReader) {
1.518 + // need to take unfolded lines into account
1.519 + final int unfolded = ((UnfoldingReader) in).getLinesUnfolded();
1.520 + line += unfolded;
1.521 + }
1.522 + return line;
1.523 + }
1.524 +}
