Java DocumentIndexReader类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Java›Java编程经验

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Java中org.galagosearch.core.parse.DocumentIndexReader类的典型用法代码示例。如果您正苦于以下问题：Java DocumentIndexReader类的具体用法？Java DocumentIndexReader怎么用？Java DocumentIndexReader使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

DocumentIndexReader类属于org.galagosearch.core.parse包，在下文中一共展示了DocumentIndexReader类的8个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Java代码示例。

示例1: handleDumpCorpus

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
private static void handleDumpCorpus(String[] args) throws IOException {
    if (args.length <= 1) {
        commandHelp(args[0]);
        return;
    }

    DocumentIndexReader reader = new DocumentIndexReader(args[1]);
    DocumentIndexReader.Iterator iterator = reader.getIterator();
    while (!iterator.isDone()) {
        System.out.println("#IDENTIFIER: " + iterator.getKey());
        Document document = iterator.getDocument();
        System.out.println("#METADATA");
        for (Entry<String, String> entry : document.metadata.entrySet()) {
            System.out.println(entry.getKey() + "," + entry.getValue());
        }
        System.out.println("#TEXT");
        System.out.println(document.text);
        iterator.nextDocument();
    }
}

开发者ID:jjfiv，项目名称:galagosearch，代码行数:21，代码来源:App.java

示例2: handleDumpCorpus

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
private void handleDumpCorpus(String[] args) throws IOException {
    if (args.length <= 1) {
        commandHelp(args[0]);
        return;
    }

    DocumentIndexReader reader = new DocumentIndexReader(args[1]);
    DocumentIndexReader.Iterator iterator = reader.getIterator();
    while (!iterator.isDone()) {
        output.println("#IDENTIFIER: " + iterator.getKey());
        Document document = iterator.getDocument();
        output.println("#METADATA");
        for (Entry<String, String> entry : document.metadata.entrySet()) {
            output.println(entry.getKey() + "," + entry.getValue());
        }
        output.println("#TEXT");
        output.println(document.text);
        iterator.nextDocument();
    }
}

开发者ID:youngilcho，项目名称:internet-application-2014，代码行数:21，代码来源:App.java

示例3: handleDoc

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
private static void handleDoc(String[] args) throws IOException {
    if (args.length <= 2) {
        commandHelp(args[0]);
        return;
    }

    String indexPath = args[1];
    String identifier = args[2];
    DocumentIndexReader reader = new DocumentIndexReader(indexPath);
    Document document = reader.getDocument(identifier);
    System.out.println(document.text);
}

开发者ID:jjfiv，项目名称:galagosearch，代码行数:13，代码来源:App.java

示例4: get

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
public Document get(String identifier) throws IOException {
    for (DocumentIndexReader reader : readers) {
        Document document = reader.getDocument(identifier);
        if (document != null) {
            return document;
        }
    }
    return null;
}

开发者ID:jjfiv，项目名称:galagosearch，代码行数:10，代码来源:DocumentIndexStore.java

示例5: handleDoc

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
private void handleDoc(String[] args) throws IOException {
    if (args.length <= 2) {
        commandHelp(args[0]);
        return;
    }

    String indexPath = args[1];
    String identifier = args[2];
    DocumentIndexReader reader = new DocumentIndexReader(indexPath);
    Document document = reader.getDocument(identifier);
    output.println(document.text);
}

开发者ID:youngilcho，项目名称:internet-application-2014，代码行数:13，代码来源:App.java

示例6: DocumentIndexStore

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
public DocumentIndexStore(DocumentIndexReader reader) {
    this(Collections.singletonList(reader));
}

开发者ID:jjfiv，项目名称:galagosearch，代码行数:4，代码来源:DocumentIndexStore.java

示例7: close

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
public void close() throws IOException {
    for (DocumentIndexReader reader : readers) {
        reader.close();
    }
}

开发者ID:jjfiv，项目名称:galagosearch，代码行数:6，代码来源:DocumentIndexStore.java

示例8: init

import org.galagosearch.core.parse.DocumentIndexReader; //导入依赖的package包/类
public synchronized void init() throws IOException {
    if (inited) {
        return;
    }

    //here, set path of stopword file
    stopwordFile = "../doc/stopwords.txt";
    //here, set path of corpus file assigned to you
    corpusFile = "../doc/reuter.corpus";

    if (stopwordList == null)
        stopwordList = makeStopWordList(stopwordFile);

    if (documentList == null) {
        // 캐싱된게 없다면 가져오기
        documentList = new ArrayList<String>();
        corpusStr = new StringBuffer();

        // galago 함수 통해서 직접 읽는다.
        DocumentIndexReader reader = new DocumentIndexReader(corpusFile);
        DocumentIndexReader.Iterator iterator = reader.getIterator();


        while (!iterator.isDone()) {
            Document document = iterator.getDocument();
            documentList.add(document.text);
            corpusStr.append(" " + document.text);
            iterator.nextDocument();
        }

        //to get global tf list
        topTerms = getTopTermFreq(corpusStr.toString());
        docFreq = new int[topTerms.length];

        termFreqList = makeTermFreqList(documentList);
    }

    // to get df per term
    for (int index = 0; index < topTerms.length; index++) {
        int docFreqTerm = 0;
        for (int cnt = 0; cnt < termFreqList.size(); cnt++) {
            HashMap<String, Integer> termFreq = termFreqList.get(cnt);
            if (termFreq.containsKey(topTerms[index])) docFreqTerm++;
        }
        docFreq[index] = docFreqTerm;

    }
    inited = true;
}

开发者ID:youngilcho，项目名称:internet-application-2014，代码行数:50，代码来源:TermAssociationManager.java

注：本文中的org.galagosearch.core.parse.DocumentIndexReader类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。