List of usage examples for java.util.regex Matcher end
public int end()
From source file:com.thero.framework.util.AntPathStringMatcher.java
private Pattern createPattern(String pattern) { StringBuilder patternBuilder = new StringBuilder(); Matcher m = GLOB_PATTERN.matcher(pattern); int end = 0;/*from ww w .j a v a2 s. co m*/ while (m.find()) { patternBuilder.append(quote(pattern, end, m.start())); String match = m.group(); if ("?".equals(match)) { patternBuilder.append('.'); } else if ("*".equals(match)) { patternBuilder.append(".*"); } else if (match.startsWith("{") && match.endsWith("}")) { int colonIdx = match.indexOf(':'); if (colonIdx == -1) { patternBuilder.append(DEFAULT_VARIABLE_PATTERN); variableNames.add(m.group(1)); } else { String variablePattern = match.substring(colonIdx + 1, match.length() - 1); patternBuilder.append('('); patternBuilder.append(variablePattern); patternBuilder.append(')'); String variableName = match.substring(1, colonIdx); variableNames.add(variableName); } } end = m.end(); } patternBuilder.append(quote(pattern, end, pattern.length())); return Pattern.compile(patternBuilder.toString()); }
From source file:tr.edu.gsu.nerwip.recognition.internal.modelless.subee.Subee.java
/** * Receives the entities detected thanks to the hyperlinks, and tries * to find their other occurrences in the text. * //from ww w . j ava2 s. c o m * @param article * Article to process. * @param sureEntities * Entities already detected, corresponding to hyperlinks. * @return * A new list of possible entities, to be merged later with the sure entities. */ private List<AbstractEntity<?>> processOccurrences(Article article, List<AbstractEntity<?>> sureEntities) { logger.increaseOffset(); String rawText = article.getRawText(); List<AbstractEntity<?>> result = new ArrayList<AbstractEntity<?>>(); // // sort entities by type (we want to prioritize them) // logger.log("Sort entity by type"); // TreeSet<AbstractEntity<?>> temp = new TreeSet<AbstractEntity<?>>(new Comparator<AbstractEntity<?>>() // { @Override // public int compare(AbstractEntity<?> o1, AbstractEntity<?> o2) // { int result = 0; // EntityType t1 = o1.getType(); // EntityType t2 = o2.getType(); // if(t1==EntityType.ORGANIZATION && t2!=EntityType.ORGANIZATION // || t1==EntityType.PERSON && t2==EntityType.LOCATION) // result = -1; // else if(t2==EntityType.ORGANIZATION && t1!=EntityType.ORGANIZATION // || t2==EntityType.PERSON && t1==EntityType.LOCATION) // result = 1; // else // result = o1.compareTo(o2); // return result; // } // }); // temp.addAll(sureEntities); // look for additional occurrences logger.log("Look for additional occurrences"); for (AbstractEntity<?> entity : sureEntities) { String valueStr = entity.getStringValue(); // look for the entity in the text String escapedStr = Pattern.quote(valueStr); Pattern p = Pattern.compile("\\b" + escapedStr + "\\b"); Matcher m = p.matcher(rawText); while (m.find()) { int startPos = m.start(); // // don't use the same position for several entities // if(!positionAlreadyUsed(startPos, result)) // this test is now done later { int endPos = m.end(); EntityType type = entity.getType(); AbstractEntity<?> ent = AbstractEntity.build(type, startPos, endPos, RecognizerName.SUBEE, valueStr); result.add(ent); } } } logger.decreaseOffset(); return result; }
From source file:com.manydesigns.portofino.pageactions.text.TextAction.java
protected String restoreAttachmentUrls(String content) { Pattern pattern = Pattern.compile(PORTOFINO_ATTACHMENT_PATTERN); Matcher matcher = pattern.matcher(content); int lastEnd = 0; StringBuilder sb = new StringBuilder(); while (matcher.find()) { String attachmentId = matcher.group(1); //Default to src for old texts String hrefAttribute = (matcher.groupCount() >= 3 && matcher.group(3) != null) ? matcher.group(3) : "src"; sb.append(content.substring(lastEnd, matcher.start())).append(hrefAttribute).append("=\"") .append(StringEscapeUtils.escapeHtml(generateViewAttachmentUrl(attachmentId))).append("\""); lastEnd = matcher.end(); }/*from w ww. j a v a2 s .co m*/ sb.append(content.substring(lastEnd)); return sb.toString(); }
From source file:gtu._work.ui.RegexDirReplacer.java
/** * @param fromPattern// w w w .j a v a 2 s . c o m * ???pattern * @param toFormat * ??pattern * @param replaceText * ?? */ String replacer(String fromPattern, String toFormat, String replaceText, File file) { String errorRtn = replaceText.toString(); try { Pattern pattern = Pattern.compile(fromPattern); Matcher matcher = pattern.matcher(replaceText); StringBuilder sb = new StringBuilder(); int startPos = 0; String tempStr = null; for (; matcher.find();) { tempStr = toFormat.toString(); sb.append(replaceText.substring(startPos, matcher.start())); for (int ii = 0; ii <= matcher.groupCount(); ii++) { tempStr = tempStr.replaceAll("#" + ii + "#", Matcher.quoteReplacement(matcher.group(ii))); System.out.println("group[" + ii + "] -- " + matcher.group(ii) + "\t--> " + tempStr); } sb.append(tempStr); startPos = matcher.end(); } sb.append(replaceText.substring(startPos)); return sb.toString(); } catch (Exception ex) { // JOptionPaneUtil.newInstance().iconErrorMessage().showMessageDialog(ex.getMessage(), // getTitle()); errMsg.append(file.getName() + ":" + ex + "\n"); return errorRtn; } }
From source file:com.joliciel.frenchTreebank.export.FrenchTreebankTokenReader.java
PosTagSequence nextSentenceInternal() {
MONITOR.startTask("nextSentenceInternal");
try {/* w w w . j a va 2s.com*/
Sentence sentence = treebankReader.nextSentence();
LOG.debug("Sentence " + sentence.getSentenceNumber());
List<Integer> tokenSplits = new ArrayList<Integer>();
PosTagSet posTagSet = TalismaneSession.getPosTagSet();
String text = sentence.getText();
// get rid of duplicate white space
Pattern duplicateWhiteSpace = Pattern.compile("\\s[\\s]+");
text = duplicateWhiteSpace.matcher(text).replaceAll(" ");
// there's no guarantee that the phrase units align to the original sentence text
// given the issues we had for aligning sentences in the first place
List<PhraseUnit> phraseUnits = sentence.getAllPhraseUnits();
LOG.trace("Phrase units: " + phraseUnits.size());
Pattern separators = Tokeniser.SEPARATORS;
Pattern whitespace = Pattern.compile("\\s+");
Matcher matcher = separators.matcher(text);
List<String> allTokens = new ArrayList<String>();
int currentPos = 0;
while (matcher.find()) {
if (matcher.start() > currentPos) {
String leftoverToken = text.substring(currentPos, matcher.start());
allTokens.add(leftoverToken);
}
String token = text.substring(matcher.start(), matcher.end());
allTokens.add(token);
currentPos = matcher.end();
}
if (currentPos < text.length())
allTokens.add(text.substring(currentPos));
com.joliciel.talismane.filters.Sentence oneSentence = this.filterService.getSentence(text);
TokenSequence tokenSequence = this.tokeniserService.getTokenSequence(oneSentence);
List<PosTaggedToken> posTaggedTokens = new ArrayList<PosTaggedToken>();
PhraseUnitReader phraseUnitReader = new ComplexPhraseUnitReaderWithEmptyTokens(phraseUnits);
phraseUnitReader.setTreebankService(treebankService);
if (ftbPosTagMapper != null)
phraseUnitReader.setFtbPosTagMapper(ftbPosTagMapper);
String phraseUnitText = phraseUnitReader.nextString();
LOG.trace("phrase unit: " + phraseUnitText);
currentPos = 0;
int lastSplit = 0;
tokenSplits.add(0);
while (phraseUnitText != null && phraseUnitText.length() == 0) {
tokenSplits.add(currentPos);
Token aToken = tokenSequence.addEmptyToken(currentPos);
PosTag posTag = phraseUnitReader.getPosTag();
Decision<PosTag> corpusDecision = posTagSet.createDefaultDecision(posTag);
PosTaggedToken posTaggedToken = posTaggerService.getPosTaggedToken(aToken, corpusDecision);
posTaggedTokens.add(posTaggedToken);
phraseUnitText = phraseUnitReader.nextString();
}
boolean inPhraseUnit = false;
boolean addEmptyTokenBeforeNextToken = false;
PosTag emptyTokenPosTag = null;
for (String token : allTokens) {
if (LOG.isTraceEnabled())
LOG.trace("token: " + token);
currentPos += token.length();
if ((!ignoreCase && phraseUnitText.equals(token))
|| (ignoreCase && phraseUnitText.equalsIgnoreCase(token))) {
// exact match
if (addEmptyTokenBeforeNextToken) {
if (LOG.isTraceEnabled())
LOG.trace("Adding empty token at " + (currentPos - token.length()));
tokenSplits.add((currentPos - token.length()));
Token emptyToken = tokenSequence.addEmptyToken((currentPos - token.length()));
Decision<PosTag> emptyTokenDecision = posTagSet.createDefaultDecision(emptyTokenPosTag);
PosTaggedToken posTaggedToken2 = posTaggerService.getPosTaggedToken(emptyToken,
emptyTokenDecision);
posTaggedTokens.add(posTaggedToken2);
addEmptyTokenBeforeNextToken = false;
}
if (LOG.isTraceEnabled())
LOG.trace("Adding split " + currentPos);
tokenSplits.add(currentPos);
Token aToken = tokenSequence.addToken(lastSplit, currentPos);
PosTag posTag = phraseUnitReader.getPosTag();
Decision<PosTag> corpusDecision = posTagSet.createDefaultDecision(posTag);
PosTaggedToken posTaggedToken = posTaggerService.getPosTaggedToken(aToken, corpusDecision);
posTaggedTokens.add(posTaggedToken);
lastSplit = currentPos;
phraseUnitText = phraseUnitReader.nextString();
if (LOG.isTraceEnabled())
LOG.trace("phrase unit: " + phraseUnitText);
while (phraseUnitText != null && phraseUnitText.length() == 0) {
Token emptyToken = null;
emptyTokenPosTag = phraseUnitReader.getPosTag();
phraseUnitText = phraseUnitReader.nextString();
if (LOG.isTraceEnabled())
LOG.trace("phrase unit: " + phraseUnitText);
// Empty tokens need to be attached either to the right (auquel, duquel)
// or to the left (du, des)
if (phraseUnitText.equals("duquel") || phraseUnitText.equals("auquel")
|| phraseUnitText.equals("desquels") || phraseUnitText.equals("auxquels")
|| phraseUnitText.equals("desquelles") || phraseUnitText.equals("auxquelles")) {
// attach empty token to the "duquel" that follows it
addEmptyTokenBeforeNextToken = true;
} else {
if (LOG.isTraceEnabled())
LOG.trace("Adding empty token at " + currentPos);
tokenSplits.add(currentPos);
emptyToken = tokenSequence.addEmptyToken(currentPos);
Decision<PosTag> emptyTokenDecision = posTagSet.createDefaultDecision(emptyTokenPosTag);
PosTaggedToken posTaggedToken2 = posTaggerService.getPosTaggedToken(emptyToken,
emptyTokenDecision);
posTaggedTokens.add(posTaggedToken2);
}
}
inPhraseUnit = false;
} else if (phraseUnitText.length() >= token.length() && ((!ignoreCase
&& phraseUnitText.substring(0, token.length()).equals(token))
|| (ignoreCase && phraseUnitText.substring(0, token.length()).equalsIgnoreCase(token)))) {
// the current phrase unit text starts with this token
phraseUnitText = phraseUnitText.substring(token.length());
if (LOG.isTraceEnabled())
LOG.trace("phrase unit: " + phraseUnitText);
inPhraseUnit = true;
} else if (token.length() == 1 && whitespace.matcher(token).matches()) {
// white space, always add split unless we're already inside white space
if (!inPhraseUnit) {
if (LOG.isTraceEnabled())
LOG.trace("Adding split " + currentPos);
tokenSplits.add(currentPos);
tokenSequence.addToken(lastSplit, currentPos);
lastSplit = currentPos;
}
} else {
// non-white space, what to do? either we skip the token, or we skip the phrase unit!
// for now let's assume it never happens and see what results!
int pos = 0;
StringBuilder sb = new StringBuilder();
for (int split : tokenSplits) {
String aToken = text.substring(pos, split);
sb.append('|');
sb.append(aToken);
pos = split;
}
LOG.info(sb.toString());
LOG.info("File: " + sentence.getFile().getFileName());
LOG.info("Sentence: " + text);
if (csvFileErrorWriter != null) {
try {
csvFileErrorWriter.write(CSVFormatter.format(phraseUnitText) + ",");
for (String info : phraseUnitReader.getCurrentInfo())
csvFileErrorWriter.write(CSVFormatter.format(info) + ",");
csvFileErrorWriter.write(CSVFormatter.format(token) + ",");
csvFileErrorWriter.write(sentence.getFile().getFileName() + ",");
csvFileErrorWriter.write(sentence.getSentenceNumber() + ",");
csvFileErrorWriter.write(CSVFormatter.format(sentence.getText()) + ",");
csvFileErrorWriter.write("\n");
csvFileErrorWriter.flush();
} catch (IOException ioe) {
throw new RuntimeException(ioe);
}
break;
} else {
// instead of throwing an error, write these to a file (or do both)
// so we can catch them all in one fell swoop
throw new RuntimeException("Unexpected text: " + token);
}
}
}
if (lastSplit < currentPos) {
tokenSplits.add(currentPos);
}
if (LOG.isDebugEnabled()) {
LOG.debug(text);
int pos = 0;
StringBuilder sb = new StringBuilder();
for (int split : tokenSplits) {
String aToken = text.substring(pos, split);
sb.append('|');
sb.append(aToken);
pos = split;
}
LOG.debug(sb.toString());
}
for (TokenSequenceFilter tokenSequenceFilter : this.tokenSequenceFilters) {
if (LOG.isTraceEnabled())
LOG.trace("Applying filter: " + tokenSequenceFilter.getClass().getSimpleName());
tokenSequenceFilter.apply(tokenSequence);
}
if (tokenFilterWrapper == null) {
tokenFilterWrapper = tokenFilterService.getTokenSequenceFilter(this.tokenFilters);
}
tokenFilterWrapper.apply(tokenSequence);
tokenSequence.finalise();
PosTagSequence posTagSequence = this.posTaggerService.getPosTagSequence(tokenSequence,
allTokens.size() / 2);
int i = 0;
for (Token token : tokenSequence) {
if (LOG.isTraceEnabled())
LOG.trace("Token : \"" + token.getText() + "\" (was \"" + token.getOriginalText() + "\")");
PosTaggedToken posTaggedToken = posTaggedTokens.get(i);
if (token.equals(posTaggedToken.getToken())) {
posTagSequence.addPosTaggedToken(posTaggedToken);
i++;
} else if (token.getStartIndex() == token.getEndIndex()) {
LOG.debug("Adding null pos tag at position " + token.getStartIndex());
Decision<PosTag> nullPosTagDecision = posTagSet.createDefaultDecision(PosTag.NULL_POS_TAG);
PosTaggedToken emptyTagToken = posTaggerService.getPosTaggedToken(token, nullPosTagDecision);
posTagSequence.addPosTaggedToken(emptyTagToken);
} else {
throw new RuntimeException("Expected only empty tokens added. Postag Token = "
+ posTaggedToken.getToken().getText() + ", start: " + token.getStartIndex() + ", end:"
+ token.getEndIndex());
}
}
if (useCompoundPosTags) {
PosTagSequence newSequence = this.posTaggerService.getPosTagSequence(tokenSequence,
allTokens.size() / 2);
PosTaggedToken lastPosTaggedToken = null;
i = 0;
for (PosTaggedToken posTaggedToken : posTagSequence) {
boolean removed = false;
if (posTaggedToken.getToken().isEmpty()) {
String lastWord = "";
if (lastPosTaggedToken != null)
lastWord = lastPosTaggedToken.getToken().getOriginalText().toLowerCase();
if (lastWord.equals("des") || lastWord.equals("du") || lastWord.equals("aux")
|| lastWord.equals("au") || lastWord.endsWith(" des") || lastWord.endsWith(" du")
|| lastWord.endsWith(" aux") || lastWord.endsWith(" au")
|| lastWord.endsWith("'aux") || lastWord.endsWith("'au")) {
if (lastWord.equals("des") || lastWord.equals("du") || lastWord.equals("aux")
|| lastWord.equals("au")) {
if (lastPosTaggedToken.getTag().getCode().equals("P")) {
lastPosTaggedToken.setTag(posTagSet.getPosTag("P+D"));
lastPosTaggedToken.getToken().setText(lastWord);
}
}
posTaggedToken.setTag(PosTag.NULL_POS_TAG);
tokenSequence.removeEmptyToken(posTaggedToken.getToken());
removed = true;
} else if (i == posTagSequence.size() - 1) {
// last token in sequence
// need to remove it now, since it won't get removed in the next iteration
tokenSequence.removeEmptyToken(posTaggedToken.getToken());
removed = true;
}
} else {
newSequence.addPosTaggedToken(posTaggedToken);
}
if (lastPosTaggedToken != null && lastPosTaggedToken.getToken().isEmpty()) {
String word = posTaggedToken.getToken().getOriginalText().toLowerCase();
if (word.equals("duquel") || word.equals("desquels") || word.equals("desquelles")
|| word.equals("auquel") || word.equals("auxquels") || word.equals("auxquelles")) {
posTaggedToken.setTag(posTagSet.getPosTag("P+PRO"));
lastPosTaggedToken.setTag(PosTag.NULL_POS_TAG);
posTaggedToken.getToken().setText(word);
tokenSequence.removeEmptyToken(lastPosTaggedToken.getToken());
} else if (word.equals("dudit")) {
posTaggedToken.setTag(posTagSet.getPosTag("P+D"));
lastPosTaggedToken.setTag(PosTag.NULL_POS_TAG);
posTaggedToken.getToken().setText(word);
tokenSequence.removeEmptyToken(lastPosTaggedToken.getToken());
} else {
LOG.info("Not expecting empty token here (index "
+ lastPosTaggedToken.getToken().getIndex() + ", next token = " + word + "): "
+ posTagSequence);
lastPosTaggedToken.setTag(PosTag.NULL_POS_TAG);
tokenSequence.removeEmptyToken(lastPosTaggedToken.getToken());
}
}
if (!removed)
lastPosTaggedToken = posTaggedToken;
i++;
}
posTagSequence = newSequence;
tokenSequence.finalise();
}
for (PosTagSequenceFilter posTagSequenceFilter : this.posTagSequenceFilters) {
posTagSequenceFilter.apply(posTagSequence);
}
return posTagSequence;
} finally {
MONITOR.endTask("nextSentenceInternal");
}
}
From source file:com.stealthyone.mcb.mcml.MCMLBuilder.java
public MCMLBuilder(String input, Map<String, Object> replacements) { Validate.notNull(input, "Input cannot be null."); this.rawText = input; if (this.replacements != null && replacements != null) { this.replacements.putAll(replacements); for (Entry<String, Object> entry : replacements.entrySet()) { if (entry.getValue() instanceof String) { this.rawText = rawText.replace(entry.getKey(), (String) entry.getValue()); }/*from w ww . j av a2 s .c o m*/ } } this.rawText = rawText.replace(ChatColor.COLOR_CHAR, '&'); // Identify text groups int lastIndex = 0; final Matcher matcher = PATTERN_TEXT_GROUP.matcher(input); while (matcher.find()) { TempPart part = new TempPart(matcher.group(1)); if (!parts.isEmpty()) { TempPart prevPart = parts.get(parts.size() - 1); TextPiece lastPiece = prevPart.text.get(prevPart.text.size() - 1); for (TextPiece piece : part.text) { if (piece.color == null) { piece.color = lastPiece.color; piece.italicize = lastPiece.italicize; piece.bold = lastPiece.bold; piece.underline = lastPiece.underline; piece.strikeout = lastPiece.strikeout; piece.magic = lastPiece.magic; } } } if (matcher.start() > lastIndex) { // Handle ungrouped text TempPart ungroupedPart = new TempPart(rawText.substring(lastIndex, matcher.start())); parts.add(ungroupedPart); } lastIndex = matcher.end(); // Check for event int offset = rawText.length() - input.substring(lastIndex).length(); final Matcher eventMatcher = PATTERN_EVENT.matcher(input.substring(lastIndex)); if (eventMatcher.find()) { handleEvent(part, eventMatcher); lastIndex = eventMatcher.end() + offset; offset = rawText.length() - input.substring(lastIndex).length(); final Matcher secEventMatcher = PATTERN_EVENT.matcher(input.substring(lastIndex)); if (secEventMatcher.find()) { handleEvent(part, secEventMatcher); lastIndex = secEventMatcher.end() + offset; } } parts.add(part); } if (lastIndex != rawText.length()) { TempPart ungroupedPart = new TempPart(rawText.substring(lastIndex)); if (!parts.contains(ungroupedPart)) { parts.add(ungroupedPart); } } }
From source file:com.microsoft.gittf.core.tasks.CheckinHeadCommitTask.java
/** * Parses the comments of the commits to list the mentioned work items *///from w ww . jav a 2 s.c o m private WorkItemCheckinInfo[] getWorkItems(final TaskProgressMonitor progressMonitor, final String commitComment, final boolean isLastCommit) throws Exception { List<WorkItemCheckinInfo> workItemsCheckinInfo = new ArrayList<WorkItemCheckinInfo>(); if (mentions) { final String REGEX = "(\\s|^)#\\d+(\\s|$)(#\\d+(\\s|$))*"; //$NON-NLS-1$ if (commitComment != null && commitComment.length() > 0) { final Pattern pattern = Pattern.compile(REGEX); // get a matcher object final Matcher patternMatcher = pattern.matcher(commitComment); while (patternMatcher.find()) { final String workItemIDREGEX = "#\\d+"; //$NON-NLS-1$ final Pattern workItemIDPattern = Pattern.compile(workItemIDREGEX); final String workItemIDString = commitComment.substring(patternMatcher.start(), patternMatcher.end()); final Matcher workItemIDMatcher = workItemIDPattern.matcher(workItemIDString); while (workItemIDMatcher.find()) { final WorkItem workitem = getWorkItem(progressMonitor, workItemIDString.substring(workItemIDMatcher.start(), workItemIDMatcher.end())); if (workitem != null) { final WorkItemCheckinInfo workItemCheckinInfo = new WorkItemCheckinInfo(workitem, CheckinWorkItemAction.ASSOCIATE); if (!workItemsCheckinInfo.contains(workItemCheckinInfo)) { workItemsCheckinInfo.add(workItemCheckinInfo); } } } } } } if (isLastCommit) { // If there were no work items in the comments if (workItemsCheckinInfo.isEmpty()) { return workItems; } for (final WorkItemCheckinInfo workItem : workItems) { if (!workItemsCheckinInfo.contains(workItem)) { workItemsCheckinInfo.add(workItem); } } } return workItemsCheckinInfo.toArray(new WorkItemCheckinInfo[workItemsCheckinInfo.size()]); }
From source file:com.juick.android.MessageMenu.java
protected void collectURLs(String source, MessageID mid) { if (urls == null) urls = new ArrayList<String>(); ArrayList<ExtractURLFromMessage.FoundURL> foundURLs = ExtractURLFromMessage.extractUrls(source, mid); for (ExtractURLFromMessage.FoundURL foundURL : foundURLs) { urls.add(foundURL.url);/*from www .j a v a 2 s .c o m*/ } int pos = 0; Matcher m = JuickMessagesAdapter.getCrossReferenceMsgPattern(mid).matcher(source); while (m.find(pos)) { urls.add(source.substring(m.start(), m.end())); pos = m.end(); } }
From source file:com.application.utils.FastDateParser.java
/** * Initialize derived fields from defining fields. * This is called from constructor and from readObject (de-serialization) * * @param definingCalendar the {@link java.util.Calendar} instance used to initialize this FastDateParser *//*from w ww .j av a 2 s. c o m*/ private void init(Calendar definingCalendar) { final StringBuilder regex = new StringBuilder(); final List<Strategy> collector = new ArrayList<Strategy>(); final Matcher patternMatcher = formatPattern.matcher(pattern); if (!patternMatcher.lookingAt()) { throw new IllegalArgumentException( "Illegal pattern character '" + pattern.charAt(patternMatcher.regionStart()) + "'"); } currentFormatField = patternMatcher.group(); Strategy currentStrategy = getStrategy(currentFormatField, definingCalendar); for (;;) { patternMatcher.region(patternMatcher.end(), patternMatcher.regionEnd()); if (!patternMatcher.lookingAt()) { nextStrategy = null; break; } final String nextFormatField = patternMatcher.group(); nextStrategy = getStrategy(nextFormatField, definingCalendar); if (currentStrategy.addRegex(this, regex)) { collector.add(currentStrategy); } currentFormatField = nextFormatField; currentStrategy = nextStrategy; } if (patternMatcher.regionStart() != patternMatcher.regionEnd()) { throw new IllegalArgumentException( "Failed to parse \"" + pattern + "\" ; gave up at index " + patternMatcher.regionStart()); } if (currentStrategy.addRegex(this, regex)) { collector.add(currentStrategy); } currentFormatField = null; strategies = collector.toArray(new Strategy[collector.size()]); parsePattern = Pattern.compile(regex.toString()); }
From source file:at.ac.tuwien.inso.subcat.utility.commentparser.Parser.java
License:asdf
private void parseQuotes(List<ContentNode<T>> ast, String comment) { Matcher m = pQuote.matcher(comment); int lastEnd = 0; while (m.find()) { if (lastEnd >= 0 && lastEnd != m.start()) { parseParagraphs(ast, comment.substring(lastEnd, m.start())); }// w w w . ja v a 2 s . c o m String content = m.group(0); String idStr = m.group(2); int id = (idStr != null) ? Integer.parseInt(idStr) : -1; Matcher cfm = pCleanFstQuote.matcher(content); content = cfm.replaceAll(""); Matcher csm = pCleanSubQuote.matcher(content); content = csm.replaceAll(""); String[] contentFragments = pQuoteSplitter.split(content.trim()); String[] cleanedFragments = new String[contentFragments.length]; for (int i = 0; i < contentFragments.length; i++) { Matcher normM = pNorm.matcher(contentFragments[i]); cleanedFragments[i] = normM.replaceAll(" "); } ast.add(new QuoteNode<T>(cleanedFragments, id)); lastEnd = m.end(); } if (lastEnd != comment.length()) { String frag = comment.substring(lastEnd, comment.length()); if (frag.trim().length() > 0) { parseGLibMessages(ast, frag); } } }