Java Code Examples for org.ansj.domain.Result#getTerms()

The following examples show how to use org.ansj.domain.Result#getTerms() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: DicSegment.java    From youkefu with Apache License 2.0 5 votes vote down vote up
public static String[] byNature(String content , Set<String> expectedNature){
	List<String> wordList = new ArrayList<String>();
	if (!StringUtils.isBlank(content) && expectedNature != null && expectedNature.size() > 0) {
		Result result = NlpAnalysis.parse(content,DicLibrary.gets(librarykeyList));//分词结果的一个封装,主要是一个List<Term>的terms
           List<Term> terms = result.getTerms(); //拿到terms
           for(int i=0; i<terms.size(); i++) {
               String word = terms.get(i).getName(); //拿到词
               String natureStr = terms.get(i).getNatureStr(); //拿到词性
               if(expectedNature.contains(natureStr)) {
                   wordList.add(word+"/"+natureStr);
               }
           }
	}
	return wordList.toArray(new String[wordList.size()]);
}
 
Example 2
Source File: StopRecognition.java    From deeplearning4j with Apache License 2.0 5 votes vote down vote up
@Override
public void recognition(Result result) {
    List<Term> list = result.getTerms();
    Iterator<Term> iterator = list.iterator();

    while (iterator.hasNext()) {
        Term term = iterator.next();
        if (filter(term)) {
            iterator.remove();
        }
    }

}
 
Example 3
Source File: TimeRecognition.java    From deeplearning4j with Apache License 2.0 4 votes vote down vote up
@Override
public void recognition(Result result) {
    String name = "";
    String timeWord = "";
    List<Term> terms = result.getTerms();
    LinkedList<Term> mergeList = new LinkedList<>();
    List<Term> list = new LinkedList<>();

    Pattern pattern =
                    Pattern.compile("((\\d|[0123456789]){1,4}年(\\d|[0123456789]){1,2}月(\\d|[0123456789]){1,2}[日|号](上午|下午|中午|晚)?(\\s)*((\\d|[0123456789]){1,2}([点|时|點|時])?((:)?(\\d|[0123456789]){1,2}(分)?((:)?(\\d|[0123456789]){1,2}(秒)?)?)?)?(\\s)*(PM|AM)?|(\\d|[0123456789]){1,2}(月|月份)(\\d|[0123456789]){1,2}([日|号])?(上午|下午|中午|晚)?(\\s)*((\\d|[0123456789]){1,2}([点|时|點|時])?((:)?(\\d|[0123456789]){1,2}(分)?((:)?(\\d|[0123456789]){1,2}(秒)?)?)?)?(\\s)*(PM|AM)?|(\\d|[0123456789]){1,2}日(上午|下午|中午|晚)?(\\s)*((\\d|[0123456789]){1,2}([点|时|點|時])?((:)?(\\d|[0123456789]){1,2}(分)?((:)?(\\d|[0123456789]){1,2}(秒)?)?)?)?(\\s)*(PM|AM)?|(昨天|昨日|昨日上午|昨日下午|昨日晚上|昨天早上|昨天上午|昨天中午|昨天下午|昨晚|昨夜|昨天晚上|今天早上|今天上午|今天下午|今晚|今天晚上|今日上午|今日下午|今日|今天|前天|今年|去年|当日|当日上午|上午|下午|中午|清晨|前晚|早上|凌晨|今晨|近日|日前|不久前)((\\d|[0123456789]){1,2}[点|时|點|時])?((:)?(\\d|[0123456789]){1,2}(分)?((:)?(\\d|[0123456789]){1,2}(秒)?)?)?(\\s)*(PM|AM)?|[\\“|\"](1|2|3|4|5|6|7|8|9|10|11|12)[·|.| |-](\\d|[0123456789]){1,2}[\\”|\"]|星期[一|二|三|四|五|六|天|日]|(\\d|[0123456789]){1,2}[点|时|點|時]((:)?(\\d|[0123456789]){1,2}(分)?((:)?(\\d|[0123456789]){1,2}(秒)?)?)?(\\s)*(PM|AM)?|(\\d|[0123456789]){4}年((\\d|[0123456789]){1,2}月)?|(\\d|[0123456789]){1,2}月|(正|一|二|三|四|五|六|七|八|九|十|十一|十二|腊)月((初|十|二十|三十)[ 一二三四五六七八九十])?(上午|下午|中午|晚)?|((\\d|[0123456789]){4}-(\\d|[0123456789]){2}-(\\d|[0123456789]){2})?(\\s)*(\\d|[0123456789]){2}:(\\d|[0123456789]){2}:(\\d|[0123456789]){2}|(\\d|[0123456789]){4}-(\\d|[0123456789]){2}-(\\d|[0123456789]){2}(\\s)*((\\d|[0123456789]){2}:(\\d|[0123456789]){2}:(\\d|[0123456789]){2})?)",
                                    Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);

    for (int i = 0; i < terms.size(); i++) {
        boolean isTime = false;
        Term termBase = terms.get(i);
        int timeTermsLength = 1;
        int matchLength = 0; //匹配长度
        for (int j = i; j < terms.size() && matchLength < 11; j++) { //向后最大找14个词匹配是否是时间词
            Term term = terms.get(j);
            name = term.getName();
            timeWord += name;
            Matcher matcher = pattern.matcher(timeWord);
            mergeList.add(term);
            if (matcher.matches()) {
                isTime = true;
                timeTermsLength += (j - i);
                i = j;
            }
            matchLength++;
        }
        if (isTime) {
            Term ft = mergeList.pollFirst();
            for (int k = 0; k < timeTermsLength - 1; k++) {
                ft.merageWithBlank(mergeList.get(k));
            }
            ft.setNature(nature);
            list.add(ft);
        } else {
            list.add(termBase);
        }
        mergeList.clear();
        timeWord = "";

    }
    result.setTerms(list);
}
 
Example 4
Source File: ChineseTokenizer.java    From deeplearning4j with Apache License 2.0 4 votes vote down vote up
public ChineseTokenizer(String toTokenize) {
    Result result = NlpAnalysis.parse(toTokenize);
    this.tokenList = result.getTerms();
    this.tokenIter = tokenList.iterator();
}
 
Example 5
Source File: DicRecognition.java    From deeplearning4j with Apache License 2.0 2 votes vote down vote up
private void recognition(Result result, Forest forest) {
    List<Term> terms = result.getTerms();

}