Examples with Token com.joliciel.talismane.tokeniser.Token used on opensource projects

Example 16 with Token

use of com.joliciel.talismane.tokeniser.Token in project talismane by joliciel-informatique.

the class TokenOffsetAddressFunction method checkInternal.

@Override
public FeatureResult<TokenWrapper> checkInternal(TokenWrapper tokenWrapper, RuntimeEnvironment env) throws TalismaneException {
    TokenWrapper innerWrapper = this.getToken(tokenWrapper, env);
    if (innerWrapper == null)
        return null;
    Token token = innerWrapper.getToken();
    FeatureResult<TokenWrapper> result = null;
    Token offsetToken = null;
    FeatureResult<Integer> offsetResult = offsetFeature.check(innerWrapper, env);
    if (offsetResult != null) {
        int offset = offsetResult.getOutcome();
        if (offset == 0)
            offsetToken = token;
        else {
            int index = 0;
            if (token.isWhiteSpace()) {
                // non-whitespace token
                if (offset > 0) {
                    if (token.getIndexWithWhiteSpace() - 1 >= 0) {
                        index = token.getTokenSequence().listWithWhiteSpace().get(token.getIndexWithWhiteSpace() - 1).getIndex();
                    } else {
                        index = -1;
                    }
                } else if (offset < 0) {
                    if (token.getIndexWithWhiteSpace() + 1 < token.getTokenSequence().listWithWhiteSpace().size()) {
                        index = token.getTokenSequence().listWithWhiteSpace().get(token.getIndexWithWhiteSpace() + 1).getIndex();
                    } else {
                        index = token.getTokenSequence().size();
                    }
                }
            } else {
                // not whitespace
                index = token.getIndex();
            }
            int offsetIndex = index + offset;
            if (offsetIndex >= 0 && offsetIndex < token.getTokenSequence().size()) {
                offsetToken = token.getTokenSequence().get(offsetIndex);
            }
        }
    }
    if (offsetToken != null) {
        result = this.generateResult(offsetToken);
    }
    return result;
}

Example 17 with Token

use of com.joliciel.talismane.tokeniser.Token in project talismane by joliciel-informatique.

the class TokeniserPatternsAndIndexesFeature method checkInternal.

@Override
public FeatureResult<List<WeightedOutcome<String>>> checkInternal(TokenWrapper tokenWrapper, RuntimeEnvironment env) throws TalismaneException {
    Token token = tokenWrapper.getToken();
    List<WeightedOutcome<String>> resultList = new ArrayList<WeightedOutcome<String>>();
    for (TokenPatternMatch tokenMatch : token.getMatches()) {
        if (tokenMatch.getIndex() != tokenMatch.getPattern().getIndexesToTest().get(0)) {
            resultList.add(new WeightedOutcome<String>(tokenMatch.getPattern().getName() + "¤" + tokenMatch.getIndex(), 1.0));
        }
    }
    return this.generateResult(resultList);
}

Example 18 with Token

use of com.joliciel.talismane.tokeniser.Token in project talismane by joliciel-informatique.

the class PatternTokeniser method tokeniseInternal.

@Override
protected List<TokenisedAtomicTokenSequence> tokeniseInternal(TokenSequence initialSequence, Sentence sentence) throws TalismaneException, IOException {
    List<TokenisedAtomicTokenSequence> sequences;
    // Assign each separator its default value
    List<TokeniserOutcome> defaultOutcomes = this.tokeniserPatternManager.getDefaultOutcomes(initialSequence);
    List<Decision> defaultDecisions = new ArrayList<Decision>(defaultOutcomes.size());
    for (TokeniserOutcome outcome : defaultOutcomes) {
        Decision tokeniserDecision = new Decision(outcome.name());
        tokeniserDecision.addAuthority("_" + this.getClass().getSimpleName());
        tokeniserDecision.addAuthority("_" + "DefaultDecision");
        defaultDecisions.add(tokeniserDecision);
    }
    // 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>();
        for (TokenPattern parsedPattern : this.getTokeniserPatternManager().getParsedTestPatterns()) {
            List<TokenPatternMatchSequence> matchesForThisPattern = parsedPattern.match(initialSequence);
            for (TokenPatternMatchSequence matchSequence : matchesForThisPattern) {
                if (matchSequence.getTokensToCheck().size() > 0) {
                    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);
                }
            }
        }
        // we want to create the n most likely token sequences
        // the sequence has to correspond to a token pattern
        Map<TokenPatternMatchSequence, List<Decision>> matchSequenceDecisionMap = new HashMap<TokenPatternMatchSequence, List<Decision>>();
        for (TokenPatternMatchSequence matchSequence : matchingSequences) {
            TokenPatternMatch match = primaryMatchMap.get(matchSequence);
            LOG.debug("next pattern match: " + match.toString());
            List<FeatureResult<?>> tokenFeatureResults = new ArrayList<FeatureResult<?>>();
            for (TokenPatternMatchFeature<?> feature : features) {
                RuntimeEnvironment env = new RuntimeEnvironment();
                FeatureResult<?> featureResult = feature.check(match, env);
                if (featureResult != null) {
                    tokenFeatureResults.add(featureResult);
                }
            }
            if (LOG.isTraceEnabled()) {
                SortedSet<String> featureResultSet = tokenFeatureResults.stream().map(f -> f.toString()).collect(Collectors.toCollection(() -> new TreeSet<String>()));
                for (String featureResultString : featureResultSet) {
                    LOG.trace(featureResultString);
                }
            }
            List<Decision> decisions = this.decisionMaker.decide(tokenFeatureResults);
            for (ClassificationObserver observer : this.observers) observer.onAnalyse(match.getToken(), tokenFeatureResults, decisions);
            for (Decision decision : decisions) {
                decision.addAuthority("_" + this.getClass().getSimpleName());
                decision.addAuthority("_" + "Patterns");
                decision.addAuthority(match.getPattern().getName());
            }
            matchSequenceDecisionMap.put(matchSequence, decisions);
        }
        // initially create a heap with a single, empty sequence
        PriorityQueue<TokenisedAtomicTokenSequence> heap = new PriorityQueue<TokenisedAtomicTokenSequence>();
        TokenisedAtomicTokenSequence emptySequence = new TokenisedAtomicTokenSequence(sentence, 0, this.getSessionId());
        heap.add(emptySequence);
        for (int i = 0; i < initialSequence.listWithWhiteSpace().size(); i++) {
            Token token = initialSequence.listWithWhiteSpace().get(i);
            if (LOG.isTraceEnabled()) {
                LOG.trace("Token : \"" + token.getAnalyisText() + "\"");
            }
            // 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 decision = new Decision(TokeniserOutcome.SEPARATE.name());
                decision.addAuthority("_" + this.getClass().getSimpleName());
                decision.addAuthority("_" + "DefaultDecision");
                TaggedToken<TokeniserOutcome> taggedToken = new TaggedToken<>(token, decision, TokeniserOutcome.valueOf(decision.getOutcome()));
                TokenisedAtomicTokenSequence newSequence = new TokenisedAtomicTokenSequence(emptySequence);
                newSequence.add(taggedToken);
                heap.add(newSequence);
                continue;
            }
            // limit the heap breadth to K
            int maxSequences = previousHeap.size() > this.getBeamWidth() ? this.getBeamWidth() : previousHeap.size();
            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 = TokeniserOutcome.valueOf(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> decisions = matchSequenceDecisionMap.get(matchSequence);
                        for (Decision decision : decisions) {
                            for (int k = 0; k < decisionProbs.length; k++) {
                                if (decision.getOutcome().equals(defaultOutcome.name())) {
                                    // 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 defaultDecision = new Decision(defaultOutcome.name(), decisionProbs[0]);
                    defaultDecision.addAuthority("_" + this.getClass().getSimpleName());
                    defaultDecision.addAuthority("_" + "Patterns");
                    for (TokenPatternMatchSequence matchSequence : matchSequences) {
                        defaultDecision.addAuthority(matchSequence.getTokenPattern().getName());
                    }
                    TaggedToken<TokeniserOutcome> defaultTaggedToken = new TaggedToken<>(token, defaultDecision, TokeniserOutcome.valueOf(defaultDecision.getOutcome()));
                    TokenisedAtomicTokenSequence defaultSequence = new TokenisedAtomicTokenSequence(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 decision = new Decision(otherOutcome.name(), prob);
                        decision.addAuthority("_" + this.getClass().getSimpleName());
                        decision.addAuthority("_" + "Patterns");
                        decision.addAuthority(matchSequence.getTokenPattern().getName());
                        TaggedToken<TokeniserOutcome> taggedToken = new TaggedToken<>(token, decision, TokeniserOutcome.valueOf(decision.getOutcome()));
                        TokenisedAtomicTokenSequence newSequence = new TokenisedAtomicTokenSequence(history);
                        newSequence.add(taggedToken);
                        newSequence.addDecision(decision);
                        // in this sequence to the solution
                        for (Token tokenInSequence : matchSequence.getTokensToCheck()) {
                            if (tokenInSequence.equals(token)) {
                                continue;
                            }
                            Decision decisionInSequence = new Decision(decision.getOutcome());
                            decisionInSequence.addAuthority("_" + this.getClass().getSimpleName());
                            decisionInSequence.addAuthority("_" + "DecisionInSequence");
                            decisionInSequence.addAuthority("_" + "DecisionInSequence_non_default");
                            decisionInSequence.addAuthority("_" + "Patterns");
                            TaggedToken<TokeniserOutcome> taggedTokenInSequence = new TaggedToken<>(tokenInSequence, decisionInSequence, TokeniserOutcome.valueOf(decisionInSequence.getOutcome()));
                            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 decision = defaultDecisions.get(i);
                    if (matchedTokens.contains(token)) {
                        decision = new Decision(decision.getOutcome());
                        decision.addAuthority("_" + this.getClass().getSimpleName());
                        decision.addAuthority("_" + "DecisionInSequence");
                        decision.addAuthority("_" + "DecisionInSequence_default");
                        decision.addAuthority("_" + "Patterns");
                    }
                    TaggedToken<TokeniserOutcome> taggedToken = new TaggedToken<>(token, decision, TokeniserOutcome.valueOf(decision.getOutcome()));
                    TokenisedAtomicTokenSequence newSequence = new TokenisedAtomicTokenSequence(history);
                    newSequence.add(taggedToken);
                    heap.add(newSequence);
                }
            }
        // next sequence in the old heap
        }
        // 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 = new TokenisedAtomicTokenSequence(sentence, 0, this.getSessionId());
        int i = 0;
        for (Token token : initialSequence.listWithWhiteSpace()) {
            Decision decision = defaultDecisions.get(i++);
            TaggedToken<TokeniserOutcome> taggedToken = new TaggedToken<>(token, decision, TokeniserOutcome.valueOf(decision.getOutcome()));
            defaultSequence.add(taggedToken);
        }
        sequences.add(defaultSequence);
    }
    // have decision maker?
    return sequences;
}

Example 19 with Token

use of com.joliciel.talismane.tokeniser.Token in project talismane by joliciel-informatique.

the class TokenPattern method match.

/**
 * Return a TokenPatternMatchSequence for each sequence of <i>n</i> tokens in
 * a TokenSequence which match this pattern. Will also add any matches to
 * Token.getMatches() for the matched tokens.
 */
public List<TokenPatternMatchSequence> match(TokenSequence tokenSequence) {
    List<TokenPatternMatchSequence> matchingSequences = new ArrayList<TokenPatternMatchSequence>();
    boolean matchSentenceStart = false;
    if (this.getParsedPattern().get(0).pattern().equals("\\b")) {
        matchSentenceStart = true;
    }
    boolean matchSentenceEnd = false;
    if (this.getParsedPattern().get(this.getParsedPattern().size() - 1).pattern().equals("\\b")) {
        matchSentenceEnd = true;
    }
    for (int t0 = -1; t0 < tokenSequence.listWithWhiteSpace().size(); t0++) {
        boolean haveMatch = false;
        List<Token> matchingSequence = new ArrayList<Token>();
        if (t0 >= 0) {
            // does the current token match the beginning of the pattern?
            Token token = tokenSequence.listWithWhiteSpace().get(t0);
            if (checkTokenForMatch(this.getParsedPattern().get(0), token)) {
                // potential match, let's follow it through
                haveMatch = true;
                // we match so far, add it to the temp list
                matchingSequence.add(token);
            }
        } else if (matchSentenceStart) {
            // automatically match start of sentence
            haveMatch = true;
            // add null token to the temp list
            matchingSequence.add(null);
        }
        if (haveMatch) {
            int p = 1;
            int t1 = t0 + 1;
            while (p < this.getParsedPattern().size() && t1 < tokenSequence.listWithWhiteSpace().size()) {
                Token aToken = tokenSequence.listWithWhiteSpace().get(t1);
                Pattern pattern = this.getParsedPattern().get(p);
                if (checkTokenForMatch(pattern, aToken)) {
                    // we match so far, add it to the temp list
                    matchingSequence.add(aToken);
                } else {
                    // pattern doesn't match
                    haveMatch = false;
                    break;
                }
                p++;
                t1++;
            }
            if (t1 == tokenSequence.listWithWhiteSpace().size() && p == this.getParsedPattern().size() - 1 && matchSentenceEnd) {
                // add a null token representing the sentence end
                matchingSequence.add(null);
            }
            // sentence first)
            if (matchingSequence.size() != this.getParsedPattern().size()) {
                haveMatch = false;
            }
        }
        if (haveMatch) {
            TokenPatternMatchSequence tokenPatternMatchSequence = new TokenPatternMatchSequence(this, matchingSequence);
            matchingSequences.add(tokenPatternMatchSequence);
            for (Token aToken : matchingSequence) {
                tokenPatternMatchSequence.addMatch(aToken);
            }
        }
    }
    if (LOG.isTraceEnabled()) {
        if (matchingSequences.size() > 0)
            LOG.trace(this.getName() + ": matchingSequences = " + matchingSequences);
    }
    return matchingSequences;
}

Example 20 with Token

use of com.joliciel.talismane.tokeniser.Token in project talismane by joliciel-informatique.

the class TokeniserPatternManager method getDefaultOutcomes.

/**
 * Takes a sequence of atomic tokens and applies default decisions for each
 * separator.
 */
public List<TokeniserOutcome> getDefaultOutcomes(TokenSequence tokenSequence) {
    List<TokeniserOutcome> defaultOutcomes = new ArrayList<TokeniserOutcome>();
    // Assign each separator its default value
    TokeniserOutcome nextOutcome = TokeniserOutcome.SEPARATE;
    Pattern tokenSeparators = Tokeniser.getTokenSeparators(sessionId);
    for (Token token : tokenSequence.listWithWhiteSpace()) {
        TokeniserOutcome outcome = null;
        if (tokenSeparators.matcher(token.getAnalyisText()).matches()) {
            boolean defaultValueFound = false;
            for (Entry<SeparatorDecision, Pattern> entry : this.getSeparatorDefaultPatterns().entrySet()) {
                if (entry.getValue().matcher(token.getAnalyisText()).matches()) {
                    defaultValueFound = true;
                    SeparatorDecision defaultSeparatorDecision = entry.getKey();
                    switch(defaultSeparatorDecision) {
                        case IS_SEPARATOR:
                            outcome = TokeniserOutcome.SEPARATE;
                            nextOutcome = TokeniserOutcome.SEPARATE;
                            break;
                        case IS_NOT_SEPARATOR:
                            outcome = TokeniserOutcome.JOIN;
                            nextOutcome = TokeniserOutcome.JOIN;
                            break;
                        case IS_SEPARATOR_BEFORE:
                            outcome = TokeniserOutcome.SEPARATE;
                            nextOutcome = TokeniserOutcome.JOIN;
                        case IS_SEPARATOR_AFTER:
                            outcome = TokeniserOutcome.JOIN;
                            nextOutcome = TokeniserOutcome.SEPARATE;
                        case NOT_APPLICABLE:
                            break;
                        default:
                            break;
                    }
                    break;
                }
            }
            if (!defaultValueFound) {
                outcome = TokeniserOutcome.SEPARATE;
                nextOutcome = TokeniserOutcome.SEPARATE;
            }
            defaultOutcomes.add(outcome);
        } else {
            defaultOutcomes.add(nextOutcome);
        }
    }
    return defaultOutcomes;
}