Examples with CoreMap edu.stanford.nlp.util.CoreMap used on opensource projects

Example 81 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class TokenSequenceMatcherITest method testMultiPatternMatcher.

public void testMultiPatternMatcher() throws IOException {
    CoreMap doc = createDocument(testText1);
    // Test simple sequence
    TokenSequencePattern p1 = TokenSequencePattern.compile("/Archbishop/ /of/ /Canterbury/");
    p1.setPriority(1);
    TokenSequencePattern p2 = TokenSequencePattern.compile("/[a-zA-Z]+/{1,2}  /of/ /[a-zA-Z]+/+");
    MultiPatternMatcher<CoreMap> m = new MultiPatternMatcher<CoreMap>(p2, p1);
    List<SequenceMatchResult<CoreMap>> matched = m.findNonOverlapping(doc.get(CoreAnnotations.TokensAnnotation.class));
    assertEquals(4, matched.size());
    assertEquals("first Bishop of London", matched.get(0).group());
    assertEquals("Archbishop of Canterbury", matched.get(1).group());
    assertEquals("a member of the Gregorian mission sent to England to convert the", matched.get(2).group());
    assertEquals("as Bishop of London in", matched.get(3).group());
}

Example 82 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class TokenSequenceMatcherITest method testTokenSequenceMatcherABs.

public void testTokenSequenceMatcherABs() throws IOException {
    CoreMap doc = createDocument("A A A A A A A B A A B A C A E A A A A A A A A A A A B A A A");
    // Test sequence with groups
    TokenSequencePattern p = TokenSequencePattern.compile("/A/+ B");
    TokenSequenceMatcher m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    boolean match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("A A A A A A A B", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("A A B", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("A A A A A A A A A A A B", m.group());
    match = m.find();
    assertFalse(match);
    p = TokenSequencePattern.compile("(/A/+ B)+");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A B A A B", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A A A A A B", m.group());
    match = m.find();
    assertFalse(match);
    p = TokenSequencePattern.compile("( A+ ( /B/+ )? )*");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("A A A A A A A B A A B A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("A A A A A A A A A A A B A A A", m.group());
    match = m.find();
    assertFalse(match);
    p = TokenSequencePattern.compile("(/A/+ /B/+ )+");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A B A A B", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A A A A A B", m.group());
    match = m.find();
    assertFalse(match);
    p = TokenSequencePattern.compile("(/A/+ /C/? /A/* )+");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A C A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A A A A A A A A A", m.group());
    match = m.find();
    assertTrue(match);
    assertEquals(1, m.groupCount());
    assertEquals("A A A", m.group());
    match = m.find();
    assertFalse(match);
}

Example 83 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class TokenSequenceMatcherITest method testTokenSequenceMatcher3.

public void testTokenSequenceMatcher3() throws IOException {
    CoreMap doc = createDocument(testText1);
    // Test sequence with groups
    TokenSequencePattern p = TokenSequencePattern.compile(new SequencePattern.SequencePatternExpr(new SequencePattern.GroupPatternExpr(new SequencePattern.RepeatPatternExpr(getSequencePatternExpr("[A-Za-z]+"), 1, 2)), getNodePatternExpr("of"), new SequencePattern.GroupPatternExpr(new SequencePattern.RepeatPatternExpr(getSequencePatternExpr("[A-Za-z]+"), 1, 3))));
    TokenSequenceMatcher m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    boolean match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("first Bishop of London", m.group());
    assertEquals("first Bishop", m.group(1));
    assertEquals("London", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("third Archbishop of Canterbury", m.group());
    assertEquals("third Archbishop", m.group(1));
    assertEquals("Canterbury", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("a member of the Gregorian mission", m.group());
    assertEquals("a member", m.group(1));
    assertEquals("the Gregorian mission", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("as Bishop of London in", m.group());
    assertEquals("as Bishop", m.group(1));
    assertEquals("London in", m.group(2));
    match = m.find();
    assertFalse(match);
    p = TokenSequencePattern.compile(new SequencePattern.SequencePatternExpr(new SequencePattern.GroupPatternExpr(new SequencePattern.RepeatPatternExpr(getNodePatternExpr("[A-Za-z]+"), 2, 2)), getNodePatternExpr("of"), new SequencePattern.GroupPatternExpr(new SequencePattern.RepeatPatternExpr(getNodePatternExpr("[A-Za-z]+"), 1, 3, false))));
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("first Bishop of London", m.group());
    assertEquals("first Bishop", m.group(1));
    assertEquals("London", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("third Archbishop of Canterbury", m.group());
    assertEquals("third Archbishop", m.group(1));
    assertEquals("Canterbury", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("a member of the", m.group());
    assertEquals("a member", m.group(1));
    assertEquals("the", m.group(2));
    match = m.find();
    assertTrue(match);
    assertEquals(2, m.groupCount());
    assertEquals("as Bishop of London", m.group());
    assertEquals("as Bishop", m.group(1));
    assertEquals("London", m.group(2));
    match = m.find();
    assertFalse(match);
}

Example 84 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class TokenSequenceMatcherITest method _testTokenSequenceFindsWildcard.

public void _testTokenSequenceFindsWildcard() throws IOException {
    CoreMap doc = createDocument("word1 word2");
    // Test sequence with groups
    TokenSequencePattern p = TokenSequencePattern.compile("[]{2}|[]");
    TokenSequenceMatcher m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    boolean match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("word1 word2", m.group());
    match = m.find();
    assertFalse(match);
    // Reverse order
    p = TokenSequencePattern.compile("[]|[]{2}");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("word1 word2", m.group());
    match = m.find();
    assertFalse(match);
    // Using {1,2}
    p = TokenSequencePattern.compile("[]{2}");
    m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    match = m.find();
    assertTrue(match);
    assertEquals(0, m.groupCount());
    assertEquals("word1 word2", m.group());
    match = m.find();
    assertFalse(match);
}

Example 85 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class TokenSequenceMatcherITest method testTokenSequenceMatcherNonOverlapping.

public void testTokenSequenceMatcherNonOverlapping() throws IOException {
    String text = "DATE1 PROD1 PRICE1 PROD2 PRICE2 PROD3 PRICE3 DATE2 PROD4 PRICE4 PROD5 PRICE5 PROD6 PRICE6";
    CoreMap doc = createDocument(text);
    TokenSequencePattern p = TokenSequencePattern.compile("(/DATE.*/) ((/PROD.*/ /PRICE.*/)+)");
    TokenSequenceMatcher m = p.getMatcher(doc.get(CoreAnnotations.TokensAnnotation.class));
    boolean match = m.find();
    assertTrue(match);
    assertEquals(3, m.groupCount());
    assertEquals("DATE1", m.group(1));
    assertEquals("PROD1 PRICE1 PROD2 PRICE2 PROD3 PRICE3", m.group(2));
    assertEquals("PROD3 PRICE3", m.group(3));
    match = m.find();
    assertTrue(match);
    assertEquals(3, m.groupCount());
    assertEquals("DATE2", m.group(1));
    assertEquals("PROD4 PRICE4 PROD5 PRICE5 PROD6 PRICE6", m.group(2));
    assertEquals("PROD6 PRICE6", m.group(3));
    match = m.find();
    assertFalse(match);
}