Example usage for org.apache.lucene.benchmark.byTask.feeds DocData getBody

Introduction

In this page you can find the example usage for org.apache.lucene.benchmark.byTask.feeds DocData getBody.

Prototype

public String getBody() 

Source Link

Usage

From source file:com.datastax.dse.demos.solr.Wikipedia.java

License:Open Source License

public static boolean addDoc(SolrInputDocument doc, DocData d) {

    if (d.getTitle().indexOf(":") > 0)
        return false;

    doc.clear();//from ww  w  . j a v  a2s .  c  o  m
    doc.addField("id", d.getName());
    doc.addField("title", d.getTitle());
    doc.addField("body", d.getBody());
    doc.addField("date", d.getDate());

    return true;
}

---

From source file:com.grantingersoll.intell.index.Indexer.java

License:Apache License

public int index(File wikipediaXML, int numDocs, int batchSize) throws Exception {
    int result = 0;
    if (wikipediaXML != null && wikipediaXML.exists()) {
        EnwikiContentSource contentSource = new EnwikiContentSource();
        Properties properties = new Properties();
        //fileName = config.get("docs.file", null);
        String filePath = wikipediaXML.getAbsolutePath();
        properties.setProperty("docs.file", filePath);
        properties.setProperty("doc.maker.forever", "false");
        contentSource.setConfig(new Config(properties));
        contentSource.resetInputs();//from w w  w.  j  a v  a2  s .  c  o m
        //docMaker.openFile();
        List<SolrInputDocument> docs = new ArrayList<SolrInputDocument>(1000);
        int i = 0;
        SolrInputDocument sDoc = null;
        long start = System.currentTimeMillis();
        try {
            DocData docData = new DocData();

            while ((docData = contentSource.getNextDocData(docData)) != null && i < numDocs) {
                int mod = i % batchSize;

                sDoc = new SolrInputDocument();
                docs.add(sDoc);
                sDoc.addField("file", filePath + "_" + i);

                sDoc.addField("docid", docData.getName());
                sDoc.addField("body", docData.getBody());
                sDoc.addField("doctitle", docData.getTitle());
                sDoc.addField("docnum_i", String.valueOf(i));

                if (mod == batchSize - 1) {
                    log.info("Sending: " + docs.size() + " docs" + " total sent for this file: " + i);
                    server.add(docs);
                    docs.clear();
                }
                i++;
            }
        } catch (NoMoreDataException e) {

        }
        long finish = System.currentTimeMillis();
        if (log.isInfoEnabled()) {
            log.info("Indexing took " + (finish - start) + " ms");
        }
        if (docs.size() > 0) {
            server.add(docs);
        }
        result = i + docs.size();
        server.commit();
        server.optimize();
    } else {
        System.out.println("Can't find file: " + wikipediaXML);
    }
    return result;
}

---

From source file:com.tamingtext.qa.WikipediaIndexer.java

License:Apache License

public int index(File wikipediaXML, int numDocs, int batchSize) throws Exception {
    int result = 0;
    if (wikipediaXML != null && wikipediaXML.exists()) {
        EnwikiContentSource contentSource = new EnwikiContentSource();
        Properties properties = new Properties();
        //fileName = config.get("docs.file", null);
        String filePath = wikipediaXML.getAbsolutePath();
        properties.setProperty("docs.file", filePath);
        properties.setProperty("doc.maker.forever", "false");
        contentSource.setConfig(new Config(properties));
        contentSource.resetInputs();/*from   w w  w .  jav a2 s . c o  m*/
        //docMaker.openFile();
        List<SolrInputDocument> docs = new ArrayList<SolrInputDocument>(1000);
        int i = 0;
        SolrInputDocument sDoc = null;
        long start = System.currentTimeMillis();
        try {
            DocData docData = new DocData();

            while ((docData = contentSource.getNextDocData(docData)) != null && i < numDocs) {
                int mod = i % batchSize;

                sDoc = new SolrInputDocument();
                docs.add(sDoc);
                sDoc.addField("file", filePath + "_" + i);

                sDoc.addField("docid", String.valueOf(i));
                sDoc.addField("body", docData.getBody());
                sDoc.addField("doctitle", docData.getTitle());
                sDoc.addField("name_s", docData.getName());

                if (mod == batchSize - 1) {
                    log.info("Sending: " + docs.size() + " docs" + " total sent for this file: " + i);
                    server.add(docs);
                    docs.clear();
                }
                i++;
            }
        } catch (NoMoreDataException e) {

        }
        long finish = System.currentTimeMillis();
        if (log.isInfoEnabled()) {
            log.info("Indexing took " + (finish - start) + " ms");
        }
        if (docs.size() > 0) {
            server.add(docs);
        }
        result = i + docs.size();
        server.commit();
        server.optimize();
    } else {
        System.out.println("Can't find file: " + wikipediaXML);
    }
    return result;
}

---

From source file:com.tamingtext.qa.WikipediaWexIndexer.java

License:Apache License

public int index(File wikipediaWEX, int numDocs, int batchSize) throws Exception {
    int result = 0;
    if (wikipediaWEX != null && wikipediaWEX.isFile()) {
        WexWikiContentSource contentSource = new WexWikiContentSource();
        Properties properties = new Properties();
        // fileName = config.get("docs.file", null);
        String filePath = wikipediaWEX.getAbsolutePath();
        properties.setProperty("docs.file", filePath);
        properties.setProperty("doc.maker.forever", "false");
        contentSource.setConfig(new Config(properties));
        contentSource.resetInputs();/*from  www .  ja  va  2  s  .  c  om*/
        // docMaker.openFile();
        List<SolrInputDocument> docs = new ArrayList<SolrInputDocument>(1000);
        int i = 0;
        SolrInputDocument sDoc = null;
        long start = System.currentTimeMillis();
        try {
            DocData docData = new DocData();

            while ((docData = contentSource.getNextDocData(docData)) != null && i < numDocs) {
                int mod = i % batchSize;

                sDoc = new SolrInputDocument();
                docs.add(sDoc);
                sDoc.addField("file", filePath + "_" + i);

                sDoc.addField("docid", String.valueOf(docData.getID()));
                sDoc.addField("body", docData.getBody());
                sDoc.addField("doctitle", docData.getTitle());
                sDoc.addField("name_s", docData.getName());

                String[] categories = docData.getProps().getProperty("category").split(";;");

                for (String c : categories) {
                    sDoc.addField("category", c);
                }

                if (mod == batchSize - 1) {
                    log.info("Sending: " + docs.size() + " docs" + " total sent for this file: " + i);
                    server.add(docs);
                    docs.clear();
                }
                i++;
            }
        } catch (NoMoreDataException e) {

        }
        long finish = System.currentTimeMillis();
        if (log.isInfoEnabled()) {
            log.info("Indexing took " + (finish - start) + " ms");
        }
        if (docs.size() > 0) {
            server.add(docs);
        }
        result = i + docs.size();
        server.commit();
        server.optimize();
    } else {
        System.out.println("Can't find file: " + wikipediaWEX);
    }
    return result;
}

---

From source file:io.anserini.index.transform.NekoStringTransform.java

License:Apache License

@Override
public String apply(String s) {
    try {//from  w ww  .  j a v  a2 s . c  o m
        DocData dd = new DocData();
        dd = dhp.parse(dd, "", null, new StringReader(s), null);
        return dd.getTitle() + "\n" + dd.getBody();
    } catch (Exception e) {
        return "";
    }
}

---

From source file:it.unipd.dei.ims.lucene.clef.applications.BuildIndex.java

License:Apache License

public static Document getDocumentFromDocData(DocData docData, FieldType bodyFieldType) {

    Document doc = new Document();

    // add identifier field
    doc.add(new StringField(BuildIndex.ID_FIELD_NAME, docData.getName(), Field.Store.YES));

    // add body field
    doc.add(new Field(BuildIndex.BODY_FIELD_NAME, docData.getBody(), bodyFieldType));

    return doc;/*from  w w  w  . ja  va  2s  . c o m*/

}

---