Examples of edu.ucla.sspace.text.Document

edu.ucla.sspace.text.Document
An abstraction for a document that allows document processors to access text in a uniform manner.

        long processStart = System.currentTimeMillis();
        int count = 0;


        while (docIter.hasNext()) {
            long startTime = System.currentTimeMillis();
            Document doc = docIter.next();
            int docNumber = ++count;
            int terms = 0;
            sspace.processDocument(doc.reader());
            long endTime = System.currentTimeMillis();
            verbose("processed document #%d in %.3f seconds",
                    docNumber, ((endTime - startTime) / 1000d));
        }

View Full Code Here

                public void run() {
                    // repeatedly try to process documents while some still
                    // remain
                    while (docIter.hasNext()) {
                        long startTime = System.currentTimeMillis();
                        Document doc = docIter.next();
                        int docNumber = count.incrementAndGet();
                        int terms = 0;
                        try {
                            sspace.processDocument(doc.reader());
                        } catch (Throwable t) {
                            t.printStackTrace();
                        }
                        long endTime = System.currentTimeMillis();
                        verbose("parsed document #%d in %.3f seconds",

View Full Code Here


        /**
         * {@inheritDoc}
         */
        public synchronized Document next() {
            Document doc = new StringDocument(currentDoc);
            currentDoc = advance();
            return doc;
        }

View Full Code Here


        /**
         * {@inheritDoc}
         */
        public Document next() {
            Document doc = new StringDocument(next);
            next = advance();
            return doc;
        }

View Full Code Here


        /**
         * {@inheritDoc}
         */
        public Document next() {
            Document doc = new StringDocument(next);
            next = advance();
            return doc;
        }

View Full Code Here

                              Arrays.asList(expectedRelations)));
    }


    @Test public void testSingleExtraction() throws Exception {
        DependencyExtractor extractor = new CoNLLDependencyExtractor();
        Document doc = new StringDocument(toTabs(SINGLE_PARSE));
        DependencyTreeNode[] nodes = extractor.readNextTree(doc.reader());


        assertEquals(12, nodes.length);


        // Check the basics of the node.
        assertEquals("review", nodes[8].word());

View Full Code Here

                    Arrays.asList(expectedRelations)));
    }


    @Test public void testDoubleExtraction() throws Exception {
        DependencyExtractor extractor = new CoNLLDependencyExtractor();
        Document doc = new StringDocument("\n\n" +
                                          toTabs(SINGLE_PARSE) +
                                          "\n" +
                                          toTabs(SECOND_PARSE));
        BufferedReader reader = doc.reader();
        DependencyTreeNode[] relations = extractor.readNextTree(reader);
        assertTrue(relations != null);
        assertEquals(12, relations.length);


        testFirstRoot(relations, 2);

View Full Code Here

        testSecondRoot(relations, 1);
    }
    
    @Test public void testRootNode() throws Exception {
        DependencyExtractor extractor = new CoNLLDependencyExtractor();
        Document doc = new StringDocument(toTabs(SINGLE_PARSE));
        DependencyTreeNode[] relations = extractor.readNextTree(doc.reader());


        assertEquals(12, relations.length);


        testFirstRoot(relations, 2);
    }

View Full Code Here

        testFirstRoot(relations, 2);
    }


    @Test public void testConcatonatedTrees() throws Exception {
        DependencyExtractor extractor = new CoNLLDependencyExtractor();
        Document doc = new StringDocument(toTabs(CONCATONATED_PARSE));
        DependencyTreeNode[] relations = extractor.readNextTree(doc.reader());
        
        assertEquals(16, relations.length);
        testFirstRoot(relations, 2);
        testSecondRoot(relations, 13);
    }

View Full Code Here

        testSecondRoot(relations, 13);
    }


    @Test public void testConcatonatedTreesZeroOffset() throws Exception {
        DependencyExtractor extractor = new CoNLLDependencyExtractor();
        Document doc = new StringDocument(toTabs(DOUBLE_ZERO_OFFSET_PARSE));
        DependencyTreeNode[] relations = extractor.readNextTree(doc.reader());
        
        assertEquals(16, relations.length);
        testFirstRoot(relations, 2);
        testSecondRoot(relations, 13);
    }

View Full Code Here

0 1

TOP

Related Classes of edu.ucla.sspace.text.Document

edu.ucla.sspace.dependency.CoNLLDependencyExtractorTest

edu.ucla.sspace.dependency.WaCKyDependencyExtractorTest

edu.ucla.sspace.mains.GenericMain

edu.ucla.sspace.text.corpora.PukWacCorpusReader$UkWacIterator

edu.ucla.sspace.text.corpora.PukWacDependencyCorpusReader$UkWacIterator

edu.ucla.sspace.text.corpora.SenseEvalDependencyCorpusReader$SenseEvalIterator

edu.ucla.sspace.tools.DepPsdTokenCounter

edu.ucla.sspace.tools.DepSemTokenCounter

edu.ucla.sspace.tools.DepTokenCounter

edu.ucla.sspace.tools.IterativeBigramExtractor

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.