0
나는 opennlp에 익숙하지 않고 파일에서 도시 이름을 추출하는 프로그램을 구현하려고하지만 문자열에 대한 코드를 먼저 테스트하고 일부 오류가 발생한다. 코드는opennlp 이클립스의 스팬 클래스
이다.import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import main.java.opennlp.tools.namefind.NameFinderME;
import main.java.opennlp.tools.namefind.TokenNameFinderModel;
import main.java.opennlp.tools.util.InvalidFormatException;
import main.java.opennlp.tools.util.Span;
import opennlp.tools.tokenize.Tokenizer;
import opennlp.tools.tokenize.TokenizerME;
import opennlp.tools.tokenize.TokenizerModel;
import opennlp.tools.tokenize.SimpleTokenizer;
import opennlp.tools.sentdetect.SentenceDetectorME;
import opennlp.tools.sentdetect.SentenceModel;
import org.xml.sax.SAXException;
public class CityFinder {
public String Tokens[];
public static void main(String[] args) throws IOException, SAXException {
CityFinder toi = new CityFinder();
String cnt;
cnt="John is planning to specialize in Electrical Engineering in UC Berkley and pursue a career with IBM.";
toi.tokenization(cnt);
String cities = toi.namefind(toi.Tokens);
String org = toi.orgfind(toi.Tokens);
System.out.println("City name is : "+cities);
System.out.println("organization name is: "+org);
}
public String namefind(String cnt[]) {
InputStream is;
TokenNameFinderModel tnf;
NameFinderME nf;
String sd = "";
try {
is = new FileInputStream("en-ner-location.bin");
tnf = new TokenNameFinderModel(is);
nf = new NameFinderME(tnf);
Span sp[] = nf.find(cnt);
StringBuilder fd = new StringBuilder();
int l = a.length;
for (int j = 0; j < l; j++) {
fd = fd.append(a[j] + "\n");
}
sd = fd.toString();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (InvalidFormatException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return sd;
}
public String orgfind(String cnt[]) {
InputStream is;
TokenNameFinderModel tnf;
NameFinderME nf;
String sd = "";
try {
is = new FileInputStream("en-ner-organization.bin");
tnf = new TokenNameFinderModel(is);
nf = new NameFinderME(tnf);
Span sp[] = nf.find(cnt);
String a[] = Span.spansToStrings(sp, cnt);
StringBuilder fd = new StringBuilder();
int l = a.length;
for (int j = 0; j < l; j++) {
fd = fd.append(a[j] + "\n");
}
sd = fd.toString();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (InvalidFormatException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return sd;
}
public void tokenization(String tokens) {
InputStream is;
TokenizerModel tm;
try {
is = new FileInputStream("en-token.bin");
tm = new TokenizerModel(is);
Tokenizer tz = new TokenizerME(tm);
Tokens = tz.tokenize(tokens);
// System.out.println(Tokens[1]);
} catch (IOException e) {
e.printStackTrace();
}
}
}
난 스팬 verialble 스팬 SP [] = nf.find (CNT)를 얻고 에러; 오류가 형식 불일치입니다 : opennlp.tools.util.Span에서 변환 할 수 없습니다 [] main.java.opennlp.tools.util.Span은 [] 나는 두 위치에서 그것을 해결하는 방법을 모르는에
어떤 제안 .... .... ?? 미리 감사드립니다.