List of usage examples for java.util PriorityQueue add
public boolean add(E e)
From source file:org.apache.hadoop.hdfs.qjournal.client.QuorumJournalManager.java
@Override public void selectInputStreams(Collection<EditLogInputStream> streams, long fromTxnId, boolean inProgressOk) throws IOException { QuorumCall<AsyncLogger, RemoteEditLogManifest> q = loggers.getEditLogManifest(fromTxnId, inProgressOk); Map<AsyncLogger, RemoteEditLogManifest> resps = loggers.waitForWriteQuorum(q, selectInputStreamsTimeoutMs, "selectInputStreams"); LOG.debug("selectInputStream manifests:\n" + Joiner.on("\n").withKeyValueSeparator(": ").join(resps)); final PriorityQueue<EditLogInputStream> allStreams = new PriorityQueue<EditLogInputStream>(64, JournalSet.EDIT_LOG_INPUT_STREAM_COMPARATOR); for (Map.Entry<AsyncLogger, RemoteEditLogManifest> e : resps.entrySet()) { AsyncLogger logger = e.getKey(); RemoteEditLogManifest manifest = e.getValue(); for (RemoteEditLog remoteLog : manifest.getLogs()) { URL url = logger.buildURLToFetchLogs(remoteLog.getStartTxId()); EditLogInputStream elis = EditLogFileInputStream.fromUrl(connectionFactory, url, remoteLog.getStartTxId(), remoteLog.getEndTxId(), remoteLog.isInProgress()); allStreams.add(elis); }/*from w ww . j a v a2 s. com*/ } JournalSet.chainAndMakeRedundantStreams(streams, allStreams, fromTxnId); }
From source file:com.joliciel.talismane.tokeniser.patterns.CompoundPatternTokeniser.java
@Override public List<TokenisedAtomicTokenSequence> tokeniseWithDecisions(Sentence sentence) { MONITOR.startTask("tokeniseWithDecisions"); try {/*from ww w . j a v a 2 s. c o m*/ // apply any pre-tokenisation decisions via filters // we only want one placeholder per start index - the first one that gets added Map<Integer, TokenPlaceholder> placeholderMap = new HashMap<Integer, TokenPlaceholder>(); for (TokenFilter tokenFilter : this.tokenFilters) { Set<TokenPlaceholder> myPlaceholders = tokenFilter.apply(sentence.getText()); for (TokenPlaceholder placeholder : myPlaceholders) { if (!placeholderMap.containsKey(placeholder.getStartIndex())) { placeholderMap.put(placeholder.getStartIndex(), placeholder); } } if (LOG.isTraceEnabled()) { if (myPlaceholders.size() > 0) { LOG.trace("TokenFilter: " + tokenFilter); LOG.trace("placeholders: " + myPlaceholders); } } } Set<TokenPlaceholder> placeholders = new HashSet<TokenPlaceholder>(placeholderMap.values()); // Initially, separate the sentence into tokens using the separators provided TokenSequence tokenSequence = this.tokeniserService.getTokenSequence(sentence, Tokeniser.SEPARATORS, placeholders); // apply any pre-processing filters that have been added for (TokenSequenceFilter tokenSequenceFilter : this.tokenSequenceFilters) { tokenSequenceFilter.apply(tokenSequence); } // Assign each separator its default value List<TokeniserOutcome> defaultOutcomes = this.tokeniserPatternManager.getDefaultOutcomes(tokenSequence); List<Decision<TokeniserOutcome>> defaultDecisions = new ArrayList<Decision<TokeniserOutcome>>( defaultOutcomes.size()); for (TokeniserOutcome outcome : defaultOutcomes) { Decision<TokeniserOutcome> tokeniserDecision = this.tokeniserDecisionFactory .createDefaultDecision(outcome); tokeniserDecision.addAuthority("_" + this.getClass().getSimpleName()); tokeniserDecision.addAuthority("_" + "DefaultDecision"); defaultDecisions.add(tokeniserDecision); } List<TokenisedAtomicTokenSequence> sequences = null; // For each test pattern, see if anything in the sentence matches it if (this.decisionMaker != null) { List<TokenPatternMatchSequence> matchingSequences = new ArrayList<TokenPatternMatchSequence>(); Map<Token, Set<TokenPatternMatchSequence>> tokenMatchSequenceMap = new HashMap<Token, Set<TokenPatternMatchSequence>>(); Map<TokenPatternMatchSequence, TokenPatternMatch> primaryMatchMap = new HashMap<TokenPatternMatchSequence, TokenPatternMatch>(); Set<Token> matchedTokens = new HashSet<Token>(); MONITOR.startTask("pattern matching"); try { for (TokenPattern parsedPattern : this.getTokeniserPatternManager().getParsedTestPatterns()) { List<TokenPatternMatchSequence> matchesForThisPattern = parsedPattern.match(tokenSequence); for (TokenPatternMatchSequence matchSequence : matchesForThisPattern) { matchingSequences.add(matchSequence); matchedTokens.addAll(matchSequence.getTokensToCheck()); TokenPatternMatch primaryMatch = null; Token token = matchSequence.getTokensToCheck().get(0); Set<TokenPatternMatchSequence> matchSequences = tokenMatchSequenceMap.get(token); if (matchSequences == null) { matchSequences = new TreeSet<TokenPatternMatchSequence>(); tokenMatchSequenceMap.put(token, matchSequences); } matchSequences.add(matchSequence); for (TokenPatternMatch patternMatch : matchSequence.getTokenPatternMatches()) { if (patternMatch.getToken().equals(token)) { primaryMatch = patternMatch; break; } } if (LOG.isTraceEnabled()) { LOG.trace("Found match: " + primaryMatch); } primaryMatchMap.put(matchSequence, primaryMatch); } } } finally { MONITOR.endTask("pattern matching"); } // we want to create the n most likely token sequences // the sequence has to correspond to a token pattern Map<TokenPatternMatchSequence, List<Decision<TokeniserOutcome>>> matchSequenceDecisionMap = new HashMap<TokenPatternMatchSequence, List<Decision<TokeniserOutcome>>>(); for (TokenPatternMatchSequence matchSequence : matchingSequences) { TokenPatternMatch match = primaryMatchMap.get(matchSequence); LOG.debug("next pattern match: " + match.toString()); List<FeatureResult<?>> tokenFeatureResults = new ArrayList<FeatureResult<?>>(); MONITOR.startTask("analyse features"); try { for (TokenPatternMatchFeature<?> feature : features) { RuntimeEnvironment env = this.featureService.getRuntimeEnvironment(); FeatureResult<?> featureResult = feature.check(match, env); if (featureResult != null) { tokenFeatureResults.add(featureResult); } } if (LOG.isTraceEnabled()) { for (FeatureResult<?> featureResult : tokenFeatureResults) { LOG.trace(featureResult.toString()); } } } finally { MONITOR.endTask("analyse features"); } List<Decision<TokeniserOutcome>> decisions = null; MONITOR.startTask("make decision"); try { decisions = this.decisionMaker.decide(tokenFeatureResults); for (ClassificationObserver<TokeniserOutcome> observer : this.observers) observer.onAnalyse(match.getToken(), tokenFeatureResults, decisions); for (Decision<TokeniserOutcome> decision : decisions) { decision.addAuthority("_" + this.getClass().getSimpleName()); decision.addAuthority("_" + "Patterns"); decision.addAuthority(match.getPattern().getName()); } } finally { MONITOR.endTask("make decision"); } matchSequenceDecisionMap.put(matchSequence, decisions); } // initially create a heap with a single, empty sequence PriorityQueue<TokenisedAtomicTokenSequence> heap = new PriorityQueue<TokenisedAtomicTokenSequence>(); TokenisedAtomicTokenSequence emptySequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(sentence, 0); heap.add(emptySequence); for (int i = 0; i < tokenSequence.listWithWhiteSpace().size(); i++) { Token token = tokenSequence.listWithWhiteSpace().get(i); if (LOG.isTraceEnabled()) { LOG.trace("Token : \"" + token.getText() + "\""); } // build a new heap for this iteration PriorityQueue<TokenisedAtomicTokenSequence> previousHeap = heap; heap = new PriorityQueue<TokenisedAtomicTokenSequence>(); if (i == 0) { // first token is always "separate" from the outside world Decision<TokeniserOutcome> decision = this.tokeniserDecisionFactory .createDefaultDecision(TokeniserOutcome.SEPARATE); decision.addAuthority("_" + this.getClass().getSimpleName()); decision.addAuthority("_" + "DefaultDecision"); TaggedToken<TokeniserOutcome> taggedToken = this.tokeniserService.getTaggedToken(token, decision); TokenisedAtomicTokenSequence newSequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(emptySequence); newSequence.add(taggedToken); heap.add(newSequence); continue; } // limit the heap breadth to K int maxSequences = previousHeap.size() > this.getBeamWidth() ? this.getBeamWidth() : previousHeap.size(); MONITOR.startTask("heap sort"); try { for (int j = 0; j < maxSequences; j++) { TokenisedAtomicTokenSequence history = previousHeap.poll(); // Find the separating & non-separating decisions if (history.size() > i) { // token already added as part of a sequence introduced by another token heap.add(history); } else if (tokenMatchSequenceMap.containsKey(token)) { // token begins one or more match sequences // these are ordered from shortest to longest (via TreeSet) List<TokenPatternMatchSequence> matchSequences = new ArrayList<TokenPatternMatchSequence>( tokenMatchSequenceMap.get(token)); // Since sequences P1..Pn contain each other, // there can be exactly matchSequences.size() consistent solutions // Assume the default is separate // 0: all separate // 1: join P1, separate rest // 2: join P2, separate rest // ... // n: join Pn // We need to add each of these to the heap // by taking the product of all probabilities consistent with each solution // The probabities for each solution are (j=join, s=separate) // All separate: s1 x s2 x ... x sn // P1: j1 x s2 x ... x sn // P2: j1 x j2 x ... x sn // ... // Pn: j1 x j2 x ... x jn // Any solution of the form s1 x j2 would be inconsistent, and is not considered // If Pi and Pj start and end on the exact same token, then the solution for both is // Pi: j1 x ... x ji x jj x sj+1 ... x sn // Pj: j1 x ... x ji x jj x sj+1 ... x sn // Note of course that we're never likely to have more than two Ps here, // but we need a solution for more just to be sure to be sure TokeniserOutcome defaultOutcome = defaultDecisions .get(token.getIndexWithWhiteSpace()).getOutcome(); TokeniserOutcome otherOutcome = null; if (defaultOutcome == TokeniserOutcome.SEPARATE) otherOutcome = TokeniserOutcome.JOIN; else otherOutcome = TokeniserOutcome.SEPARATE; double[] decisionProbs = new double[matchSequences.size() + 1]; for (int k = 0; k < decisionProbs.length; k++) decisionProbs[k] = 1; // Note: k0 = default decision (e.g. separate all), k1=first pattern // p1 = first pattern int p = 1; int prevEndIndex = -1; for (TokenPatternMatchSequence matchSequence : matchSequences) { int endIndex = matchSequence.getTokensToCheck() .get(matchSequence.getTokensToCheck().size() - 1).getEndIndex(); List<Decision<TokeniserOutcome>> decisions = matchSequenceDecisionMap .get(matchSequence); for (Decision<TokeniserOutcome> decision : decisions) { for (int k = 0; k < decisionProbs.length; k++) { if (decision.getOutcome() == defaultOutcome) { // e.g. separate in most cases if (k < p && endIndex > prevEndIndex) decisionProbs[k] *= decision.getProbability(); else if (k + 1 < p && endIndex <= prevEndIndex) decisionProbs[k] *= decision.getProbability(); } else { // e.g. join in most cases if (k >= p && endIndex > prevEndIndex) decisionProbs[k] *= decision.getProbability(); else if (k + 1 >= p && endIndex <= prevEndIndex) decisionProbs[k] *= decision.getProbability(); } } // next k } // next decision (only 2 of these) prevEndIndex = endIndex; p++; } // transform to probability distribution double sumProbs = 0; for (int k = 0; k < decisionProbs.length; k++) sumProbs += decisionProbs[k]; if (sumProbs > 0) for (int k = 0; k < decisionProbs.length; k++) decisionProbs[k] /= sumProbs; // Apply default decision // Since this is the default decision for all tokens in the sequence, we don't add the other tokens for now, // so as to allow them // to get examined one at a time, just in case one of them starts its own separate sequence Decision<TokeniserOutcome> defaultDecision = this.tokeniserDecisionFactory .createDecision(defaultOutcome.getCode(), decisionProbs[0]); defaultDecision.addAuthority("_" + this.getClass().getSimpleName()); defaultDecision.addAuthority("_" + "Patterns"); for (TokenPatternMatchSequence matchSequence : matchSequences) { defaultDecision.addAuthority(matchSequence.getTokenPattern().getName()); } TaggedToken<TokeniserOutcome> defaultTaggedToken = this.tokeniserService .getTaggedToken(token, defaultDecision); TokenisedAtomicTokenSequence defaultSequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(history); defaultSequence.add(defaultTaggedToken); defaultSequence.addDecision(defaultDecision); heap.add(defaultSequence); // Apply one non-default decision per match sequence for (int k = 0; k < matchSequences.size(); k++) { TokenPatternMatchSequence matchSequence = matchSequences.get(k); double prob = decisionProbs[k + 1]; Decision<TokeniserOutcome> decision = this.tokeniserDecisionFactory .createDecision(otherOutcome.getCode(), prob); decision.addAuthority("_" + this.getClass().getSimpleName()); decision.addAuthority("_" + "Patterns"); decision.addAuthority(matchSequence.getTokenPattern().getName()); TaggedToken<TokeniserOutcome> taggedToken = this.tokeniserService .getTaggedToken(token, decision); TokenisedAtomicTokenSequence newSequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(history); newSequence.add(taggedToken); newSequence.addDecision(decision); // The decision is NOT the default decision for all tokens in the sequence, add all other tokens // in this sequence to the solution for (Token tokenInSequence : matchSequence.getTokensToCheck()) { if (tokenInSequence.equals(token)) { continue; } Decision<TokeniserOutcome> decisionInSequence = this.tokeniserDecisionFactory .createDefaultDecision(decision.getOutcome()); decisionInSequence.addAuthority("_" + this.getClass().getSimpleName()); decisionInSequence.addAuthority("_" + "DecisionInSequence"); decisionInSequence.addAuthority("_" + "DecisionInSequence_non_default"); decisionInSequence.addAuthority("_" + "Patterns"); TaggedToken<TokeniserOutcome> taggedTokenInSequence = this.tokeniserService .getTaggedToken(tokenInSequence, decisionInSequence); newSequence.add(taggedTokenInSequence); } heap.add(newSequence); } // next sequence } else { // token doesn't start match sequence, and hasn't already been added to the current sequence Decision<TokeniserOutcome> decision = defaultDecisions.get(i); if (matchedTokens.contains(token)) { decision = this.tokeniserDecisionFactory .createDefaultDecision(decision.getOutcome()); decision.addAuthority("_" + this.getClass().getSimpleName()); decision.addAuthority("_" + "DecisionInSequence"); decision.addAuthority("_" + "DecisionInSequence_default"); decision.addAuthority("_" + "Patterns"); } TaggedToken<TokeniserOutcome> taggedToken = this.tokeniserService .getTaggedToken(token, decision); TokenisedAtomicTokenSequence newSequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(history); newSequence.add(taggedToken); heap.add(newSequence); } } // next sequence in the old heap } finally { MONITOR.endTask("heap sort"); } } // next token sequences = new ArrayList<TokenisedAtomicTokenSequence>(); int k = 0; while (!heap.isEmpty()) { sequences.add(heap.poll()); k++; if (k >= this.getBeamWidth()) break; } } else { sequences = new ArrayList<TokenisedAtomicTokenSequence>(); TokenisedAtomicTokenSequence defaultSequence = this.getTokeniserService() .getTokenisedAtomicTokenSequence(sentence, 0); int i = 0; for (Token token : tokenSequence.listWithWhiteSpace()) { TaggedToken<TokeniserOutcome> taggedToken = this.tokeniserService.getTaggedToken(token, defaultDecisions.get(i++)); defaultSequence.add(taggedToken); } sequences.add(defaultSequence); } // have decision maker? LOG.debug("####Final token sequences:"); int j = 1; for (TokenisedAtomicTokenSequence sequence : sequences) { TokenSequence newTokenSequence = sequence.inferTokenSequence(); if (LOG.isDebugEnabled()) { LOG.debug("Token sequence " + (j++) + ", score=" + df.format(sequence.getScore())); LOG.debug("Atomic sequence: " + sequence); LOG.debug("Resulting sequence: " + newTokenSequence); } // need to re-apply the pre-processing filters, because the tokens are all new // Question: why can't we conserve the initial tokens when they haven't changed at all? // Answer: because the tokenSequence and index in the sequence is referenced by the token. // Question: should we create a separate class, Token and TokenInSequence, // one with index & sequence access & one without? for (TokenSequenceFilter tokenSequenceFilter : this.tokenSequenceFilters) { tokenSequenceFilter.apply(newTokenSequence); } if (LOG.isDebugEnabled()) { LOG.debug("After filters: " + newTokenSequence); } } return sequences; } finally { MONITOR.endTask("tokeniseWithDecisions"); } }
From source file:com.datatorrent.contrib.hdht.HDHTWalManager.java
/** * Copy content from parent WAL files to new location ordered by WindowID. * @param parentWals//from w w w . j a v a 2s .c om * @param walPositions */ public void mergeWalFiles(List<PreviousWALDetails> parentWals, HashMap<Long, WalPosition> walPositions) { Map<Long, Iterator<Map.Entry<Long, WalPosition>>> iteratorsMap = Maps.newHashMap(); Map<Long, WalPosition> startPositionMap = Maps.newHashMap(); for (PreviousWALDetails walDetails : parentWals) { Iterator<Map.Entry<Long, WalPosition>> it = walDetails.walPositions.entrySet().iterator(); iteratorsMap.put(walDetails.getWalKey(), it); if (walDetails.getCommittedWalPosition() != null) { startPositionMap.put(walDetails.getWalKey(), walDetails.getCommittedWalPosition()); } else { startPositionMap.put(walDetails.getWalKey(), new WalPosition(0, 0)); } } PriorityQueue<WalWindowPosition> currentValues = new PriorityQueue<>(parentWals.size(), new Comparator<WalWindowPosition>() { @Override public int compare(WalWindowPosition o1, WalWindowPosition o2) { return (int) (o1.windowId - o2.windowId); } }); do { for (Map.Entry<Long, Iterator<Map.Entry<Long, WalPosition>>> entry : iteratorsMap.entrySet()) { if (entry.getValue().hasNext()) { Map.Entry<Long, WalPosition> windowWalPosition = entry.getValue().next(); currentValues.add(new WalWindowPosition(entry.getKey(), windowWalPosition.getKey(), windowWalPosition.getValue())); } } if (!currentValues.isEmpty()) { WalWindowPosition minWindowWalEntry = currentValues.remove(); copyWALFiles(startPositionMap.get(minWindowWalEntry.walKey), minWindowWalEntry.walPosition, minWindowWalEntry.walKey); // Set next start position for WAL key startPositionMap.put(minWindowWalEntry.walKey, minWindowWalEntry.walPosition); // Set end position for windowId for checkpointed positions walPositions.put(minWindowWalEntry.windowId, this.getCurrentPosition()); } } while (!currentValues.isEmpty()); }
From source file:com.joliciel.talismane.parser.TransitionBasedParserImpl.java
@Override public List<ParseConfiguration> parseSentence(List<PosTagSequence> posTagSequences) { MONITOR.startTask("parseSentence"); try {/*from w ww. jav a2 s. co m*/ long startTime = (new Date()).getTime(); int maxAnalysisTimeMilliseconds = maxAnalysisTimePerSentence * 1000; int minFreeMemoryBytes = minFreeMemory * KILOBYTE; TokenSequence tokenSequence = posTagSequences.get(0).getTokenSequence(); TreeMap<Integer, PriorityQueue<ParseConfiguration>> heaps = new TreeMap<Integer, PriorityQueue<ParseConfiguration>>(); PriorityQueue<ParseConfiguration> heap0 = new PriorityQueue<ParseConfiguration>(); for (PosTagSequence posTagSequence : posTagSequences) { // add an initial ParseConfiguration for each postag sequence ParseConfiguration initialConfiguration = this.getParserServiceInternal() .getInitialConfiguration(posTagSequence); initialConfiguration.setScoringStrategy(decisionMaker.getDefaultScoringStrategy()); heap0.add(initialConfiguration); if (LOG.isDebugEnabled()) { LOG.debug("Adding initial posTagSequence: " + posTagSequence); } } heaps.put(0, heap0); PriorityQueue<ParseConfiguration> backupHeap = null; PriorityQueue<ParseConfiguration> finalHeap = null; PriorityQueue<ParseConfiguration> terminalHeap = new PriorityQueue<ParseConfiguration>(); while (heaps.size() > 0) { Entry<Integer, PriorityQueue<ParseConfiguration>> heapEntry = heaps.pollFirstEntry(); PriorityQueue<ParseConfiguration> currentHeap = heapEntry.getValue(); int currentHeapIndex = heapEntry.getKey(); if (LOG.isTraceEnabled()) { LOG.trace("##### Polling next heap: " + heapEntry.getKey() + ", size: " + heapEntry.getValue().size()); } boolean finished = false; // systematically set the final heap here, just in case we exit "naturally" with no more heaps finalHeap = heapEntry.getValue(); backupHeap = new PriorityQueue<ParseConfiguration>(); // we jump out when either (a) all tokens have been attached or (b) we go over the max alloted time ParseConfiguration topConf = currentHeap.peek(); if (topConf.isTerminal()) { LOG.trace("Exiting with terminal heap: " + heapEntry.getKey() + ", size: " + heapEntry.getValue().size()); finished = true; } if (earlyStop && terminalHeap.size() >= beamWidth) { LOG.debug( "Early stop activated and terminal heap contains " + beamWidth + " entries. Exiting."); finalHeap = terminalHeap; finished = true; } long analysisTime = (new Date()).getTime() - startTime; if (maxAnalysisTimePerSentence > 0 && analysisTime > maxAnalysisTimeMilliseconds) { LOG.info("Parse tree analysis took too long for sentence: " + tokenSequence.getText()); LOG.info("Breaking out after " + maxAnalysisTimePerSentence + " seconds."); finished = true; } if (minFreeMemory > 0) { long freeMemory = Runtime.getRuntime().freeMemory(); if (freeMemory < minFreeMemoryBytes) { LOG.info("Not enough memory left to parse sentence: " + tokenSequence.getText()); LOG.info("Min free memory (bytes):" + minFreeMemoryBytes); LOG.info("Current free memory (bytes): " + freeMemory); finished = true; } } if (finished) { break; } // limit the breadth to K int maxSequences = currentHeap.size() > this.beamWidth ? this.beamWidth : currentHeap.size(); int j = 0; while (currentHeap.size() > 0) { ParseConfiguration history = currentHeap.poll(); if (LOG.isTraceEnabled()) { LOG.trace("### Next configuration on heap " + heapEntry.getKey() + ":"); LOG.trace(history.toString()); LOG.trace("Score: " + df.format(history.getScore())); LOG.trace(history.getPosTagSequence()); } List<Decision<Transition>> decisions = new ArrayList<Decision<Transition>>(); // test the positive rules on the current configuration boolean ruleApplied = false; if (parserPositiveRules != null) { MONITOR.startTask("check rules"); try { for (ParserRule rule : parserPositiveRules) { if (LOG.isTraceEnabled()) { LOG.trace("Checking rule: " + rule.toString()); } RuntimeEnvironment env = this.featureService.getRuntimeEnvironment(); FeatureResult<Boolean> ruleResult = rule.getCondition().check(history, env); if (ruleResult != null && ruleResult.getOutcome()) { Decision<Transition> positiveRuleDecision = TalismaneSession .getTransitionSystem().createDefaultDecision(rule.getTransition()); decisions.add(positiveRuleDecision); positiveRuleDecision.addAuthority(rule.getCondition().getName()); ruleApplied = true; if (LOG.isTraceEnabled()) { LOG.trace("Rule applies. Setting transition to: " + rule.getTransition().getCode()); } break; } } } finally { MONITOR.endTask("check rules"); } } if (!ruleApplied) { // test the features on the current configuration List<FeatureResult<?>> parseFeatureResults = new ArrayList<FeatureResult<?>>(); MONITOR.startTask("feature analyse"); try { for (ParseConfigurationFeature<?> feature : this.parseFeatures) { MONITOR.startTask(feature.getName()); try { RuntimeEnvironment env = this.featureService.getRuntimeEnvironment(); FeatureResult<?> featureResult = feature.check(history, env); if (featureResult != null) parseFeatureResults.add(featureResult); } finally { MONITOR.endTask(feature.getName()); } } if (LOG_FEATURES.isTraceEnabled()) { for (FeatureResult<?> featureResult : parseFeatureResults) { LOG_FEATURES.trace(featureResult.toString()); } } } finally { MONITOR.endTask("feature analyse"); } // evaluate the feature results using the decision maker MONITOR.startTask("make decision"); try { decisions = this.decisionMaker.decide(parseFeatureResults); for (ClassificationObserver<Transition> observer : this.observers) { observer.onAnalyse(history, parseFeatureResults, decisions); } List<Decision<Transition>> decisionShortList = new ArrayList<Decision<Transition>>( decisions.size()); for (Decision<Transition> decision : decisions) { if (decision.getProbability() > MIN_PROB_TO_STORE) decisionShortList.add(decision); } decisions = decisionShortList; } finally { MONITOR.endTask("make decision"); } // apply the negative rules Set<Transition> eliminatedTransitions = new HashSet<Transition>(); if (parserNegativeRules != null) { MONITOR.startTask("check negative rules"); try { for (ParserRule rule : parserNegativeRules) { if (LOG.isTraceEnabled()) { LOG.trace("Checking negative rule: " + rule.toString()); } RuntimeEnvironment env = this.featureService.getRuntimeEnvironment(); FeatureResult<Boolean> ruleResult = rule.getCondition().check(history, env); if (ruleResult != null && ruleResult.getOutcome()) { eliminatedTransitions.addAll(rule.getTransitions()); if (LOG.isTraceEnabled()) { for (Transition eliminatedTransition : rule.getTransitions()) LOG.trace("Rule applies. Eliminating transition: " + eliminatedTransition.getCode()); } } } if (eliminatedTransitions.size() > 0) { List<Decision<Transition>> decisionShortList = new ArrayList<Decision<Transition>>(); for (Decision<Transition> decision : decisions) { if (!eliminatedTransitions.contains(decision.getOutcome())) { decisionShortList.add(decision); } else { LOG.trace("Eliminating decision: " + decision.toString()); } } if (decisionShortList.size() > 0) { decisions = decisionShortList; } else { LOG.debug("All decisions eliminated! Restoring original decisions."); } } } finally { MONITOR.endTask("check negative rules"); } } } // has a positive rule been applied? boolean transitionApplied = false; // add new configuration to the heap, one for each valid transition MONITOR.startTask("heap sort"); try { // Why apply all decisions here? Why not just the top N (where N = beamwidth)? // Answer: because we're not always adding solutions to the same heap // And yet: a decision here can only do one of two things: process a token (heap+1000), or add a non-processing transition (heap+1) // So, if we've already applied N decisions of each type, we should be able to stop for (Decision<Transition> decision : decisions) { Transition transition = decision.getOutcome(); if (LOG.isTraceEnabled()) LOG.trace("Outcome: " + transition.getCode() + ", " + decision.getProbability()); if (transition.checkPreconditions(history)) { transitionApplied = true; ParseConfiguration configuration = this.parserServiceInternal .getConfiguration(history); if (decision.isStatistical()) configuration.addDecision(decision); transition.apply(configuration); int nextHeapIndex = parseComparisonStrategy.getComparisonIndex(configuration) * 1000; if (configuration.isTerminal()) { nextHeapIndex = Integer.MAX_VALUE; } else { while (nextHeapIndex <= currentHeapIndex) nextHeapIndex++; } PriorityQueue<ParseConfiguration> nextHeap = heaps.get(nextHeapIndex); if (nextHeap == null) { if (configuration.isTerminal()) nextHeap = terminalHeap; else nextHeap = new PriorityQueue<ParseConfiguration>(); heaps.put(nextHeapIndex, nextHeap); if (LOG.isTraceEnabled()) LOG.trace("Created heap with index: " + nextHeapIndex); } nextHeap.add(configuration); if (LOG.isTraceEnabled()) { LOG.trace("Added configuration with score " + configuration.getScore() + " to heap: " + nextHeapIndex + ", total size: " + nextHeap.size()); } configuration.clearMemory(); } else { if (LOG.isTraceEnabled()) LOG.trace("Cannot apply transition: doesn't meet pre-conditions"); // just in case the we run out of both heaps and analyses, we build this backup heap backupHeap.add(history); } // does transition meet pre-conditions? } // next transition } finally { MONITOR.endTask("heap sort"); } if (transitionApplied) { j++; } else { LOG.trace("No transitions could be applied: not counting this history as part of the beam"); } // beam width test if (j == maxSequences) break; } // next history } // next atomic index // return the best sequences on the heap List<ParseConfiguration> bestConfigurations = new ArrayList<ParseConfiguration>(); int i = 0; if (finalHeap.isEmpty()) finalHeap = backupHeap; while (!finalHeap.isEmpty()) { bestConfigurations.add(finalHeap.poll()); i++; if (i >= this.getBeamWidth()) break; } if (LOG.isDebugEnabled()) { for (ParseConfiguration finalConfiguration : bestConfigurations) { LOG.debug(df.format(finalConfiguration.getScore()) + ": " + finalConfiguration.toString()); LOG.debug("Pos tag sequence: " + finalConfiguration.getPosTagSequence()); LOG.debug("Transitions: " + finalConfiguration.getTransitions()); LOG.debug("Decisions: " + finalConfiguration.getDecisions()); if (LOG.isTraceEnabled()) { StringBuilder sb = new StringBuilder(); for (Decision<Transition> decision : finalConfiguration.getDecisions()) { sb.append(" * "); sb.append(df.format(decision.getProbability())); } sb.append(" root "); sb.append(finalConfiguration.getTransitions().size()); LOG.trace(sb.toString()); sb = new StringBuilder(); sb.append(" * PosTag sequence score "); sb.append(df.format(finalConfiguration.getPosTagSequence().getScore())); sb.append(" = "); for (PosTaggedToken posTaggedToken : finalConfiguration.getPosTagSequence()) { sb.append(" * "); sb.append(df.format(posTaggedToken.getDecision().getProbability())); } sb.append(" root "); sb.append(finalConfiguration.getPosTagSequence().size()); LOG.trace(sb.toString()); sb = new StringBuilder(); sb.append(" * Token sequence score = "); sb.append(df.format(finalConfiguration.getPosTagSequence().getTokenSequence().getScore())); LOG.trace(sb.toString()); } } } return bestConfigurations; } finally { MONITOR.endTask("parseSentence"); } }
From source file:org.apache.hadoop.hbase.io.hfile.bucket.BucketCache.java
/** * Free the space if the used size reaches acceptableSize() or one size block * couldn't be allocated. When freeing the space, we use the LRU algorithm and * ensure there must be some blocks evicted *//*from ww w . j a va 2 s . co m*/ private void freeSpace() { // Ensure only one freeSpace progress at a time if (!freeSpaceLock.tryLock()) return; try { freeInProgress = true; long bytesToFreeWithoutExtra = 0; /* * Calculate free byte for each bucketSizeinfo */ StringBuffer msgBuffer = new StringBuffer(); BucketAllocator.IndexStatistics[] stats = bucketAllocator.getIndexStatistics(); long[] bytesToFreeForBucket = new long[stats.length]; for (int i = 0; i < stats.length; i++) { bytesToFreeForBucket[i] = 0; long freeGoal = (long) Math.floor(stats[i].totalCount() * (1 - DEFAULT_MIN_FACTOR)); freeGoal = Math.max(freeGoal, 1); if (stats[i].freeCount() < freeGoal) { bytesToFreeForBucket[i] = stats[i].itemSize() * (freeGoal - stats[i].freeCount()); bytesToFreeWithoutExtra += bytesToFreeForBucket[i]; msgBuffer.append("Free for bucketSize(" + stats[i].itemSize() + ")=" + StringUtils.byteDesc(bytesToFreeForBucket[i]) + ", "); } } msgBuffer.append("Free for total=" + StringUtils.byteDesc(bytesToFreeWithoutExtra) + ", "); if (bytesToFreeWithoutExtra <= 0) { return; } long currentSize = bucketAllocator.getUsedSize(); long totalSize = bucketAllocator.getTotalSize(); LOG.debug("Bucket cache free space started; Attempting to " + msgBuffer.toString() + " of current used=" + StringUtils.byteDesc(currentSize) + ",actual cacheSize=" + StringUtils.byteDesc(realCacheSize.get()) + ",total=" + StringUtils.byteDesc(totalSize)); long bytesToFreeWithExtra = (long) Math .floor(bytesToFreeWithoutExtra * (1 + DEFAULT_EXTRA_FREE_FACTOR)); // Instantiate priority buckets BucketEntryGroup bucketSingle = new BucketEntryGroup(bytesToFreeWithExtra, blockSize, singleSize()); BucketEntryGroup bucketMulti = new BucketEntryGroup(bytesToFreeWithExtra, blockSize, multiSize()); BucketEntryGroup bucketMemory = new BucketEntryGroup(bytesToFreeWithExtra, blockSize, memorySize()); // Scan entire map putting bucket entry into appropriate bucket entry // group for (Map.Entry<BlockCacheKey, BucketEntry> bucketEntryWithKey : backingMap.entrySet()) { switch (bucketEntryWithKey.getValue().getPriority()) { case SINGLE: { bucketSingle.add(bucketEntryWithKey); break; } case MULTI: { bucketMulti.add(bucketEntryWithKey); break; } case MEMORY: { bucketMemory.add(bucketEntryWithKey); break; } } } PriorityQueue<BucketEntryGroup> bucketQueue = new PriorityQueue<BucketEntryGroup>(3); bucketQueue.add(bucketSingle); bucketQueue.add(bucketMulti); bucketQueue.add(bucketMemory); int remainingBuckets = 3; long bytesFreed = 0; BucketEntryGroup bucketGroup; while ((bucketGroup = bucketQueue.poll()) != null) { long overflow = bucketGroup.overflow(); if (overflow > 0) { long bucketBytesToFree = Math.min(overflow, (bytesToFreeWithoutExtra - bytesFreed) / remainingBuckets); bytesFreed += bucketGroup.free(bucketBytesToFree); } remainingBuckets--; } /** * Check whether need extra free because some bucketSizeinfo still needs * free space */ stats = bucketAllocator.getIndexStatistics(); boolean needFreeForExtra = false; for (int i = 0; i < stats.length; i++) { long freeGoal = (long) Math.floor(stats[i].totalCount() * (1 - DEFAULT_MIN_FACTOR)); freeGoal = Math.max(freeGoal, 1); if (stats[i].freeCount() < freeGoal) { needFreeForExtra = true; break; } } if (needFreeForExtra) { bucketQueue.clear(); remainingBuckets = 2; bucketQueue.add(bucketSingle); bucketQueue.add(bucketMulti); while ((bucketGroup = bucketQueue.poll()) != null) { long bucketBytesToFree = (bytesToFreeWithExtra - bytesFreed) / remainingBuckets; bytesFreed += bucketGroup.free(bucketBytesToFree); remainingBuckets--; } } if (LOG.isDebugEnabled()) { long single = bucketSingle.totalSize(); long multi = bucketMulti.totalSize(); long memory = bucketMemory.totalSize(); LOG.debug("Bucket cache free space completed; " + "freed=" + StringUtils.byteDesc(bytesFreed) + ", " + "total=" + StringUtils.byteDesc(totalSize) + ", " + "single=" + StringUtils.byteDesc(single) + ", " + "multi=" + StringUtils.byteDesc(multi) + ", " + "memory=" + StringUtils.byteDesc(memory)); } } finally { cacheStats.evict(); freeInProgress = false; freeSpaceLock.unlock(); } }
From source file:io.anserini.rerank.lib.AxiomReranker.java
/** * Calculate the scores (weights) of each term that occured in the reranking pool. * The Process:// w w w .j a v a 2 s . c om * 1. For each query term, calculate its score for each term in the reranking pool. the score * is calcuated as * <pre> * P(both occurs)*log{P(both occurs)/P(t1 occurs)/P(t2 occurs)} * + P(both not occurs)*log{P(both not occurs)/P(t1 not occurs)/P(t2 not occurs)} * + P(t1 occurs t2 not occurs)*log{P(t1 occurs t2 not occurs)/P(t1 occurs)/P(t2 not occurs)} * + P(t1 not occurs t2 occurs)*log{P(t1 not occurs t2 occurs)/P(t1 not occurs)/P(t2 occurs)} * </pre> * 2. For each query term the scores of every other term in the reranking pool are stored in a * PriorityQueue, only the top {@code K} are kept. * 3. Add the scores of the same term together and pick the top {@code M} ones. * * @param termInvertedList A Map of <term -> Set<docId>> where the Set of docIds is where the term occurs * @param context An instance of RerankerContext * @return Map<String, Double> Top terms and their weight scores in a HashMap */ private Map<String, Double> computeTermScore(Map<String, Set<Integer>> termInvertedList, RerankerContext<T> context) throws IOException { class ScoreComparator implements Comparator<Pair<String, Double>> { public int compare(Pair<String, Double> a, Pair<String, Double> b) { int cmp = Double.compare(b.getRight(), a.getRight()); if (cmp == 0) { return a.getLeft().compareToIgnoreCase(b.getLeft()); } else { return cmp; } } } // get collection statistics so that we can get idf later on. IndexReader reader; if (this.externalIndexPath != null) { Path indexPath = Paths.get(this.externalIndexPath); if (!Files.exists(indexPath) || !Files.isDirectory(indexPath) || !Files.isReadable(indexPath)) { throw new IllegalArgumentException( this.externalIndexPath + " does not exist or is not a directory."); } reader = DirectoryReader.open(FSDirectory.open(indexPath)); } else { IndexSearcher searcher = context.getIndexSearcher(); reader = searcher.getIndexReader(); } final long docCount = reader.numDocs() == -1 ? reader.maxDoc() : reader.numDocs(); //calculate the Mutual Information between term with each query term List<String> queryTerms = context.getQueryTokens(); Map<String, Integer> queryTermsCounts = new HashMap<>(); for (String qt : queryTerms) { queryTermsCounts.put(qt, queryTermsCounts.getOrDefault(qt, 0) + 1); } Set<Integer> allDocIds = new HashSet<>(); for (Set<Integer> s : termInvertedList.values()) { allDocIds.addAll(s); } int docIdsCount = allDocIds.size(); // Each priority queue corresponds to a query term: The p-queue itself stores all terms // in the reranking pool and their reranking scores to the query term. List<PriorityQueue<Pair<String, Double>>> allTermScoresPQ = new ArrayList<>(); for (Map.Entry<String, Integer> q : queryTermsCounts.entrySet()) { String queryTerm = q.getKey(); long df = reader.docFreq(new Term(LuceneDocumentGenerator.FIELD_BODY, queryTerm)); if (df == 0L) { continue; } float idf = (float) Math.log((1 + docCount) / df); int qtf = q.getValue(); if (termInvertedList.containsKey(queryTerm)) { PriorityQueue<Pair<String, Double>> termScorePQ = new PriorityQueue<>(new ScoreComparator()); double selfMI = computeMutualInformation(termInvertedList.get(queryTerm), termInvertedList.get(queryTerm), docIdsCount); for (Map.Entry<String, Set<Integer>> termEntry : termInvertedList.entrySet()) { double score; if (termEntry.getKey().equals(queryTerm)) { // The mutual information to itself will always be 1 score = idf * qtf; } else { double crossMI = computeMutualInformation(termInvertedList.get(queryTerm), termEntry.getValue(), docIdsCount); score = idf * beta * qtf * crossMI / selfMI; } termScorePQ.add(Pair.of(termEntry.getKey(), score)); } allTermScoresPQ.add(termScorePQ); } } Map<String, Double> aggTermScores = new HashMap<>(); for (PriorityQueue<Pair<String, Double>> termScores : allTermScoresPQ) { for (int i = 0; i < Math.min(termScores.size(), this.K); i++) { Pair<String, Double> termScore = termScores.poll(); String term = termScore.getLeft(); Double score = termScore.getRight(); if (score - 0.0 > 1e-8) { aggTermScores.put(term, aggTermScores.getOrDefault(term, 0.0) + score); } } } PriorityQueue<Pair<String, Double>> termScoresPQ = new PriorityQueue<>(new ScoreComparator()); for (Map.Entry<String, Double> termScore : aggTermScores.entrySet()) { termScoresPQ.add(Pair.of(termScore.getKey(), termScore.getValue() / queryTerms.size())); } Map<String, Double> resultTermScores = new HashMap<>(); for (int i = 0; i < Math.min(termScoresPQ.size(), this.M); i++) { Pair<String, Double> termScore = termScoresPQ.poll(); String term = termScore.getKey(); double score = termScore.getValue(); resultTermScores.put(term, score); } return resultTermScores; }
From source file:org.kuali.rice.krms.framework.engine.TermResolutionEngineImpl.java
/** * * @param termName//from w w w. ja v a 2 s.co m * @return List<{@link TermResolverKey}> */ protected List<TermResolverKey> buildTermResolutionPlan(String termName) { // our result List<TermResolverKey> resolutionPlan = null; // Holds the resolvers we've visited, along with the needed metadata for generating our final plan Map<TermResolverKey, Visited> visitedByKey = new HashMap<TermResolverKey, Visited>(); // this holds a least cost first list of nodes remaining to be explored PriorityQueue<ToVisit> toVisits = new PriorityQueue<ToVisit>(); // nice grammar there cowboy // dummy resolver to be the root of this tree // Do I really need this? Yes, because there may be more than one resolver that resolves to the desired termName, // so this destination unifies the trees of those candidate resolvers TermResolver destination = createDestination(termName); // problem is we can't get this one out of the registry TermResolverKey destinationKey = new TermResolverKey(destination); LOG.debug("Beginning resolution tree search for " + termName); // seed our queue of resolvers to visit // need to be aware of null parent for root ToVisit toVisits.add(new ToVisit(0, destination, null)); // there may not be a viable plan boolean plannedToDestination = false; // We'll do a modified Dijkstra's shortest path algorithm, where at each leaf we see if we've planned out // termName resolution all the way up to the root, our destination. If so, we just reconstruct our plan. while (!plannedToDestination && toVisits.size() > 0) { // visit least cost node remaining ToVisit visiting = toVisits.poll(); LOG.debug("visiting " + visiting.getTermResolverKey()); // the resolver is the edge in our tree -- we don't get it directly from the termResolversByKey Map, because it could be our destination TermResolver resolver = getResolver(visiting.getTermResolverKey(), destination, destinationKey); TermResolver parent = getResolver(visiting.getParentKey(), destination, destinationKey); if (visitedByKey.containsKey(visiting.getTermResolverKey())) { continue; // We've already visited this one } Visited parentVisited = visitedByKey.get(visiting.getParentKey()); if (resolver == null) throw new RuntimeException("Unable to get TermResolver by its key"); Set<String> prereqs = resolver.getPrerequisites(); // keep track of any prereqs that we already have handy List<String> metPrereqs = new LinkedList<String>(); // see what prereqs we have already, and which we'll need to visit if (prereqs != null) for (String prereq : prereqs) { if (!termCache.containsKey(new Term(prereq, null))) { // enqueue all resolvers in toVisits List<TermResolver<?>> prereqResolvers = termResolversByOutput.get(prereq); if (prereqResolvers != null) for (TermResolver prereqResolver : prereqResolvers) { // Only TermResolvers that don't take paramaterized terms can be chained, so: // if the TermResolver doesn't take parameters, or it resolves the output termName if (CollectionUtils.isEmpty(prereqResolver.getParameterNames()) || termName.equals(prereqResolver.getOutput())) { // queue it up for visiting toVisits.add(new ToVisit(visiting.getCost() /* cost to get to this resolver */, prereqResolver, resolver)); } } } else { metPrereqs.add(prereq); } } // Build visited info Visited visited = buildVisited(resolver, parentVisited, metPrereqs); visitedByKey.put(visited.getResolverKey(), visited); plannedToDestination = isPlannedBackToDestination(visited, destinationKey, visitedByKey); } if (plannedToDestination) { // build result from Visited tree. resolutionPlan = new LinkedList<TermResolverKey>(); assembleLinearResolutionPlan(visitedByKey.get(destinationKey), visitedByKey, resolutionPlan); } return resolutionPlan; }
From source file:$.HyperGraphBuilder$.java
@Override
public V_GenericGraph makeGraphResponse(final V_GraphQuery graphQuery) throws Exception {
nodeList = new HashMap<String, V_GenericNode>();
// edgeMap = new HashMap<String, V_GenericEdge>();
edgeList = new HashMap<String, V_GenericEdge>();
scannedQueries = new HashSet<String>();
final PriorityQueue<G_EntityQuery> queriesToRun = new PriorityQueue<G_EntityQuery>(10,
new ScoreComparator());
Map<String, V_GenericNode> nodesFromPreviousDegree = new HashMap<String, V_GenericNode>();
Map<String, V_GenericEdge> edgesFromPreviousDegree = new HashMap<String, V_GenericEdge>();
if (graphQuery.getMaxHops() <= 0) {
return new V_GenericGraph();
} else {// w ww .j a v a 2 s .co m
logger.debug("Attempting a graph for query " + graphQuery.toString());
}
int intStatus = 0;
String strStatus = "Graph Loaded";
final G_PropertyMatchDescriptor identifierList = G_PropertyMatchDescriptor.newBuilder().setKey("_all")
.setListRange(new ListRangeHelper(G_PropertyType.STRING, graphQuery.getSearchIds()))
.setConstraint(G_Constraint.EQUALS).build();
final QueryHelper qh = new QueryHelper(identifierList);
qh.setTargetSchema(index);
queriesToRun.add(qh);
int currentDegree = 0;
for (currentDegree = 0; (currentDegree < graphQuery.getMaxHops())
&& (nodeList.size() < graphQuery.getMaxNodes()); currentDegree++) {
G_EntityQuery eq = null;
logger.debug("${symbol_dollar}${symbol_dollar}${symbol_dollar}${symbol_dollar}There are "
+ queriesToRun.size() + " queries to run in the current degree.");
while ((queriesToRun.size() > 0) && ((eq = queriesToRun.poll()) != null)
&& (nodeList.size() < graphQuery.getMaxNodes())) {
if (ValidationUtils.isValid(eq.getPropertyMatchDescriptors())) {
nodesFromPreviousDegree = new HashMap<String, V_GenericNode>(nodeList);
edgesFromPreviousDegree = new HashMap<String, V_GenericEdge>(edgeList);
logger.debug("Processing degree " + currentDegree);
/**
* This will end up building nodes and edges, and creating
* new queries for the queue
*/
logger.debug("1111=====Running query " + eq.toString());
getDAO().performCallback(0, eq.getMaxResult(), this, eq);
logger.debug("3333====After running " + eq.toString() + ", there are "
+ queriesToRunNextDegree.size() + " queries to run in the next degree.");
}
} // end while loop
// very important!!
// unscannedNodeList.clear();
// ////////////////////////////////////////////////
logger.debug("4444==== At the end of degree " + currentDegree + ", there are " + nodeList.size()
+ " nodes and " + edgeList.size() + " edges");
logger.debug(
"5555====There are " + queriesToRunNextDegree.size() + " queries to run in the next degree.");
queriesToRun.addAll(queriesToRunNextDegree);
queriesToRunNextDegree.clear();
}
// All hops have been done
// Check to see if we have too many nodes.
if (nodeList.size() > graphQuery.getMaxNodes()) {
nodeList = nodesFromPreviousDegree;
edgeList = edgesFromPreviousDegree;
intStatus = 1; // will trigger the message.
strStatus = "Returning only " + currentDegree
+ " hops, as maximum nodes you requested would be exceeded";
} else {
intStatus = 1; // will trigger the message.
strStatus = "Returning " + nodeList.size() + " nodes and " + edgeList.size() + " edges.";
}
// NOW finally add in all those unique edges.
performPostProcess(graphQuery);
final V_GenericGraph g = new V_GenericGraph(nodeList, edgeList);
g.setIntStatus(intStatus);
g.setStrStatus(strStatus);
logger.debug("Graph status: " + g.getStrStatus());
for (final V_LegendItem li : legendItems) {
g.addLegendItem(li);
}
return g;
}
From source file:sg.atom.utils._commons.lang.metadata.ScoringClassMapBuilder.java
public ClassMapBuilder<A, B> byDefault(MappingDirection direction, DefaultFieldMapper... withDefaults) { DefaultFieldMapper[] defaults;//from w ww .jav a 2s. com if (withDefaults.length == 0) { defaults = getDefaultFieldMappers(); } else { defaults = withDefaults; } /* * For our custom 'byDefault' method, we're going to try and match * fields by their Levenshtein distance */ PriorityQueue<FieldMatchScore> matchScores = new PriorityQueue<FieldMatchScore>(); Map<String, Property> propertiesForA = getPropertyExpressions(getAType()); Map<String, Property> propertiesForB = getPropertyExpressions(getBType()); for (final Entry<String, Property> propertyA : propertiesForA.entrySet()) { if (!propertyA.getValue().getName().equals("class")) { for (final Entry<String, Property> propertyB : propertiesForB.entrySet()) { if (!propertyB.getValue().getName().equals("class")) { FieldMatchScore matchScore = new FieldMatchScore(propertyA.getValue(), propertyB.getValue(), matchingWeights); matchScores.add(matchScore); } } } } Set<String> unmatchedFields = new LinkedHashSet<String>(this.getPropertiesForTypeA()); unmatchedFields.remove("class"); for (FieldMatchScore score : matchScores) { if (!this.getMappedPropertiesForTypeA().contains(score.propertyA.getExpression()) && !this.getMappedPropertiesForTypeB().contains(score.propertyB.getExpression())) { if (LOGGER.isTraceEnabled()) { LOGGER.trace("\n" + score.toString()); } if (score.meetsMinimumScore()) { fieldMap(score.propertyA.getExpression(), score.propertyB.getExpression()).direction(direction) .add(); unmatchedFields.remove(score.propertyA.getExpression()); } } } /* * Apply any default field mappers to the unmapped fields */ for (String propertyNameA : unmatchedFields) { Property prop = resolvePropertyForA(propertyNameA); for (DefaultFieldMapper defaulter : defaults) { String suggestion = defaulter.suggestMappedField(propertyNameA, prop.getType()); if (suggestion != null && getPropertiesForTypeB().contains(suggestion)) { if (!getMappedPropertiesForTypeB().contains(suggestion)) { fieldMap(propertyNameA, suggestion).direction(direction).add(); } } } } return this; }
From source file:edu.snu.leader.hidden.SpatialIndividual.java
/** * Finds the nearest neighbors for this individual * * @param simState/* w w w . j a v a 2 s . c o m*/ */ public void findNearestNeighbors(SimulationState simState) { _LOG.trace("Entering findNearestNeighbors( simState )"); // Get the number of nearest neighbors _nearestNeighborCount = simState.getNearestNeighborCount(); // Build a priority queue to sort things for us PriorityQueue<Neighbor> sortedNeighbors = new PriorityQueue<Neighbor>(); // Iterate through all the individuals Iterator<SpatialIndividual> indIter = simState.getAllIndividuals().iterator(); while (indIter.hasNext()) { // Get the individual SpatialIndividual ind = indIter.next(); // If it is us, continue on if (_id.equals(ind._id)) { continue; } // Build a neighbor out of it and put it in the queue Neighbor neighbor = new Neighbor((float) _location.distance(ind._location), ind); sortedNeighbors.add(neighbor); } // Get the "nearest" neighbors int count = Math.min(sortedNeighbors.size(), _nearestNeighborCount); for (int i = 0; i < count; i++) { Neighbor neighbor = sortedNeighbors.poll(); _nearestNeighbors.add(neighbor); neighbor.getIndividual().signalNearestNeighborStatus(this); // _LOG.debug( "Nearest neighbor: id=[" // + getID() // + "] neighbor=[" // + neighbor.getIndividual().getID() // + "]" ); } _LOG.trace("Leaving findNearestNeighbors( simState )"); }