Examples with TreeReaderFactory edu.stanford.nlp.trees.TreeReaderFactory used on opensource projects

Example 11 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class TreeToTSV method main.

public static void main(String[] args) {
    if (args.length < 1) {
        System.err.printf("Usage: java %s tree_file%n", TreeToTSV.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        StringBuilder sb = new StringBuilder();
        String nl = System.getProperty("line.separator");
        Pattern nePattern = Pattern.compile("^grup\\.nom\\.");
        Pattern npPattern = Pattern.compile("^np0000.$");
        for (Tree tree; (tree = tr.readTree()) != null; ) {
            for (Tree t : tree) {
                if (!t.isPreTerminal())
                    continue;
                char type = 'O';
                Tree grandma = t.ancestor(1, tree);
                String grandmaValue = ((CoreLabel) grandma.label()).value();
                // grup.nom.x
                if (nePattern.matcher(grandmaValue).find())
                    type = grandmaValue.charAt(9);
                else // else check the pos for np0000x or not
                {
                    String pos = ((CoreLabel) t.label()).value();
                    if (npPattern.matcher(pos).find())
                        type = pos.charAt(6);
                }
                Tree wordNode = t.firstChild();
                String word = ((CoreLabel) wordNode.label()).value();
                sb.append(word).append("\t");
                switch(type) {
                    case 'p':
                        sb.append("PERS");
                        break;
                    case 'l':
                        sb.append("LUG");
                        break;
                    case 'o':
                        sb.append("ORG");
                        break;
                    case '0':
                        sb.append("OTROS");
                        break;
                    default:
                        sb.append("O");
                }
                sb.append(nl);
            }
            sb.append(nl);
        }
        System.out.print(sb.toString());
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 12 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class MWETreeVisitorExternal method main.

/**
   * For debugging.
   * 
   * @param args
   */
public static void main(String[] args) {
    if (args.length != 1) {
        System.err.printf("Usage: java %s atb_tree_file > atb_tree_file.out%n", MWETreeVisitorExternal.class.getName());
        System.exit(-1);
    }
    TreeReaderFactory trf = new ArabicTreeReaderFactory();
    try {
        TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(args[0]), "UTF-8")));
        TreeVisitor visitor = new MWETreeVisitorExternal();
        int treeId = 0;
        for (Tree tree; (tree = tr.readTree()) != null; ++treeId) {
            if (tree.value().equals("ROOT")) {
                // Skip over the ROOT tag
                tree = tree.firstChild();
            }
            visitor.visitTree(tree);
            System.out.println(tree.toString());
        }
        tr.close();
        System.err.printf("Processed %d trees.%n", treeId);
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 13 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class MWEFrequencyDist method main.

public static void main(String[] args) {
    if (args.length != 1) {
        System.err.printf("Usage: java %s file%n", MWEFrequencyDist.class.getName());
        System.exit(-1);
    }
    final File treeFile = new File(args[0]);
    TwoDimensionalCounter<String, String> mweLabelToString = new TwoDimensionalCounter<>();
    Set<String> uniquePOSSequences = Generics.newHashSet();
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new FrenchTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        final TregexPattern pMWE = TregexPattern.compile("/^MW/");
        for (Tree t; (t = tr.readTree()) != null; ) {
            //Count MWE statistics
            TregexMatcher m = pMWE.matcher(t);
            while (m.findNextMatchingNode()) {
                Tree match = m.getMatch();
                String label = match.value();
                List<CoreLabel> yield = match.taggedLabeledYield();
                StringBuilder termYield = new StringBuilder();
                StringBuilder posYield = new StringBuilder();
                for (CoreLabel cl : yield) {
                    termYield.append(cl.word()).append(" ");
                    posYield.append(cl.tag()).append(" ");
                }
                mweLabelToString.incrementCount(label, termYield.toString().trim());
                uniquePOSSequences.add(posYield.toString().trim());
            }
        }
        //Closes the underlying reader
        tr.close();
        System.out.printf("Type\t#Type\t#Single\t%%Single\t%%Total%n");
        double nMWEs = mweLabelToString.totalCount();
        int nAllSingletons = 0;
        int nTokens = 0;
        for (String mweLabel : mweLabelToString.firstKeySet()) {
            int nSingletons = 0;
            double totalCount = mweLabelToString.totalCount(mweLabel);
            Counter<String> mc = mweLabelToString.getCounter(mweLabel);
            for (String term : mc.keySet()) {
                if (mc.getCount(term) == 1.0)
                    nSingletons++;
                nTokens += term.split("\\s+").length * (int) mc.getCount(term);
            }
            nAllSingletons += nSingletons;
            System.out.printf("%s\t%d\t%d\t%.2f\t%.2f%n", mweLabel, (int) totalCount, nSingletons, 100.0 * nSingletons / totalCount, 100.0 * totalCount / nMWEs);
        }
        System.out.printf("TOTAL:\t%d\t%d\t%.2f%n", (int) nMWEs, nAllSingletons, 100.0 * nAllSingletons / nMWEs);
        System.out.println("#tokens = " + nTokens);
        System.out.println("#unique MWE POS sequences = " + uniquePOSSequences.size());
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (TregexParseException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 14 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class MungeTreesWithMorfetteAnalyses method main.

/**
   * @param args
   */
public static void main(String[] args) {
    if (args.length != 2) {
        System.err.printf("Usage: java %s tree_file morfette_tnt_file%n", MungeTreesWithMorfetteAnalyses.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    String morfetteFile = args[1];
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
        TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
        Iterator<List<CoreLabel>> morfetteItr = new MorfetteFileIterator(morfetteFile);
        for (Tree tree; (tree = tr.readTree()) != null && morfetteItr.hasNext(); ) {
            List<CoreLabel> analysis = morfetteItr.next();
            List<Label> yield = tree.yield();
            assert analysis.size() == yield.size();
            int yieldLen = yield.size();
            for (int i = 0; i < yieldLen; ++i) {
                CoreLabel tokenAnalysis = analysis.get(i);
                Label token = yield.get(i);
                String lemma = getLemma(token.value(), tokenAnalysis.lemma());
                String newLeaf = String.format("%s%s%s%s%s", token.value(), MorphoFeatureSpecification.MORPHO_MARK, lemma, MorphoFeatureSpecification.LEMMA_MARK, tokenAnalysis.tag());
                ((CoreLabel) token).setValue(newLeaf);
            }
            System.out.println(tree.toString());
        }
        if (tr.readTree() != null || morfetteItr.hasNext()) {
            log.info("WARNING: Uneven input files!");
        }
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 15 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class TreeToMorfette method main.

/**
   * @param args
   */
public static void main(String[] args) {
    if (args.length != 1) {
        System.err.printf("Usage: java %s tree_file%n", TreeToMorfette.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
        TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
        for (Tree tree1; (tree1 = tr.readTree()) != null; ) {
            List<Label> pretermYield = tree1.preTerminalYield();
            List<Label> yield = tree1.yield();
            int yieldLen = yield.size();
            for (int i = 0; i < yieldLen; ++i) {
                CoreLabel rawToken = (CoreLabel) yield.get(i);
                String word = rawToken.value();
                String morphStr = rawToken.originalText();
                Pair<String, String> lemmaMorph = MorphoFeatureSpecification.splitMorphString(word, morphStr);
                String lemma = lemmaMorph.first();
                String morph = lemmaMorph.second();
                if (morph == null || morph.equals("") || morph.equals("XXX")) {
                    morph = ((CoreLabel) pretermYield.get(i)).value();
                }
                System.out.printf("%s %s %s%n", word, lemma, morph);
            }
            System.out.println();
        }
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}