[ 
https://issues.apache.org/jira/browse/OPENNLP-1810?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Martin Wiesner updated OPENNLP-1810:
------------------------------------
    Description: 
// Edge case: The same abbreviation appears twice in a single sentence segment.
@Test
void testSentDetectWithDuplicateAbbreviationInSameSegment() {
prepareResources(true);

final String sent1 = "Lt. Vertrag und lt. Bescheid gelten andere Bedingungen.";

String[] sents = sentenceDetector.sentDetect(sent1);
double[] probs = sentenceDetector.probs();

assertAll(
() -> assertEquals(1, sents.length),
() -> assertEquals(sent1, sents[0]),
() -> assertEquals(1, probs.length));

}

  was:
  // Edge case: The same abbreviation appears twice in a single sentence 
segment.
  @Test
  void testSentDetectWithDuplicateAbbreviationInSameSegment() {
    prepareResources(true);

    final String sent1 = "Lt. Vertrag und lt. Bescheid gelten andere 
Bedingungen.";

    String[] sents = sentenceDetector.sentDetect(sent1);
    double[] probs = sentenceDetector.probs();

    assertAll(
        () -> assertEquals(1, sents.length),
        () -> assertEquals(sent1, sents[0]),
        () -> assertEquals(1, probs.length));



> SentenceDetector fails to detect multiple instances of the same abbreviation 
> in the same sentence.
> --------------------------------------------------------------------------------------------------
>
>                 Key: OPENNLP-1810
>                 URL: https://issues.apache.org/jira/browse/OPENNLP-1810
>             Project: OpenNLP
>          Issue Type: Bug
>          Components: Sentence Detector
>    Affects Versions: 2.5.7, 3.0.0-M1
>            Reporter: Richard Zowalla
>            Priority: Major
>
> // Edge case: The same abbreviation appears twice in a single sentence 
> segment.
> @Test
> void testSentDetectWithDuplicateAbbreviationInSameSegment() {
> prepareResources(true);
> final String sent1 = "Lt. Vertrag und lt. Bescheid gelten andere 
> Bedingungen.";
> String[] sents = sentenceDetector.sentDetect(sent1);
> double[] probs = sentenceDetector.probs();
> assertAll(
> () -> assertEquals(1, sents.length),
> () -> assertEquals(sent1, sents[0]),
> () -> assertEquals(1, probs.length));
> }



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to