Examples with Segment com.hankcs.hanlp.seg.Segment used on opensource projects

Example 1 with Segment

use of com.hankcs.hanlp.seg.Segment in project HanLP by hankcs.

the class TestXianDaiHanYu method testSeg.

public void testSeg() throws Exception {
    Segment segment = new NShortSegment().enableNameRecognize(true);
    HanLP.Config.enableDebug(true);
    System.out.println(segment.seg("我在区人保工作"));
}

Example 2 with Segment

use of com.hankcs.hanlp.seg.Segment in project HanLP by hankcs.

the class TestSegment method testJP.

public void testJP() throws Exception {
    String text = "明天8.9你好abc对了";
    Segment segment = new ViterbiSegment().enableCustomDictionary(false).enableAllNamedEntityRecognize(false);
    System.out.println(segment.seg(text));
}

Example 3 with Segment

use of com.hankcs.hanlp.seg.Segment in project HanLP by hankcs.

the class TestSegment method testIssue290.

public void testIssue290() throws Exception {
    //        HanLP.Config.enableDebug();
    String txt = "而其他肢解出去的七个贝尔公司如西南贝尔、太平洋贝尔、大西洋贝尔。";
    Segment seg_viterbi = new ViterbiSegment().enablePartOfSpeechTagging(true).enableOffset(true).enableNameRecognize(true).enablePlaceRecognize(true).enableOrganizationRecognize(true).enableNumberQuantifierRecognize(true);
    System.out.println(seg_viterbi.seg(txt));
}

Example 4 with Segment

use of com.hankcs.hanlp.seg.Segment in project HanLP by hankcs.

the class TestSegment method testIssue358.

public void testIssue358() throws Exception {
    HanLP.Config.enableDebug();
    String text = "受约束，需要遵守心理学会所定的道德原则，所需要时须说明该实验与所能得到的知识的关系";
    Segment segment = StandardTokenizer.SEGMENT.enableAllNamedEntityRecognize(false).enableCustomDictionary(false).enableOrganizationRecognize(true);
    System.out.println(segment.seg(text));
}

Example 5 with Segment

use of com.hankcs.hanlp.seg.Segment in project HanLP by hankcs.

the class TestSegment method testMultiThreading.

public void testMultiThreading() throws Exception {
    Segment segment = BasicTokenizer.SEGMENT;
    // 测个速度
    String text = "江西鄱阳湖干枯，中国最大淡水湖变成大草原。";
    System.out.println(segment.seg(text));
    int pressure = 100000;
    StringBuilder sbBigText = new StringBuilder(text.length() * pressure);
    for (int i = 0; i < pressure; i++) {
        sbBigText.append(text);
    }
    text = sbBigText.toString();
    long start = System.currentTimeMillis();
    List<Term> termList1 = segment.seg(text);
    double costTime = (System.currentTimeMillis() - start) / (double) 1000;
    System.out.printf("单线程分词速度：%.2f字每秒\n", text.length() / costTime);
    segment.enableMultithreading(4);
    start = System.currentTimeMillis();
    List<Term> termList2 = segment.seg(text);
    costTime = (System.currentTimeMillis() - start) / (double) 1000;
    System.out.printf("四线程分词速度：%.2f字每秒\n", text.length() / costTime);
    assertEquals(termList1.size(), termList2.size());
    Iterator<Term> iterator1 = termList1.iterator();
    Iterator<Term> iterator2 = termList2.iterator();
    while (iterator1.hasNext()) {
        Term term1 = iterator1.next();
        Term term2 = iterator2.next();
        assertEquals(term1.word, term2.word);
        assertEquals(term1.nature, term2.nature);
        assertEquals(term1.offset, term2.offset);
    }
}