[improvement][project] supersonic 0.6.0 version update (#16)

Co-authored-by: lexluo <lexluo@tencent.com>
This commit is contained in:
lexluo09
2023-07-16 21:32:33 +08:00
committed by GitHub
parent a0869dc7bd
commit 041daad1e4
261 changed files with 12031 additions and 3266 deletions

View File

@@ -14,8 +14,12 @@ import com.hankcs.hanlp.seg.common.Term;
import com.hankcs.hanlp.seg.common.Vertex;
import com.hankcs.hanlp.seg.common.WordNet;
import com.hankcs.hanlp.utility.TextUtility;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import java.util.ListIterator;
import java.util.*;
public abstract class WordBasedSegment extends Segment {

View File

@@ -6,12 +6,15 @@ import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.dictionary.CoreDictionary;
import com.hankcs.hanlp.dictionary.DynamicCustomDictionary;
import com.hankcs.hanlp.seg.Segment;
import com.hankcs.hanlp.seg.common.Term;
import com.tencent.supersonic.common.nlp.MapResult;
import com.tencent.supersonic.common.nlp.NatureType;
import com.tencent.supersonic.common.nlp.WordNature;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.util.CollectionUtils;
@@ -173,5 +176,10 @@ public class HanlpHelper {
}
}
public static List<Term> getTerms(String text) {
return getSegment().seg(text.toLowerCase()).stream()
.filter(term -> term.getNature().startsWith(NatureType.NATURE_SPILT))
.collect(Collectors.toList());
}
}