Example usage for org.apache.lucene.document Document getFields

Introduction

In this page you can find the example usage for org.apache.lucene.document Document getFields.

Prototype

public final List<IndexableField> getFields() 

Source Link

Document

Returns a List of all the fields in a document.

Usage

From source file:br.bireme.mlts.MoreLikeThat.java

License:Open Source License

private Map<String, List<String>> getDocument(final ScoreDoc sdoc) throws CorruptIndexException, IOException {
    assert sdoc != null;

    final Map<String, List<String>> ret = new HashMap<String, List<String>>();
    final Document hitDoc = is.doc(sdoc.doc);

    if (hitDoc == null) {
        throw new IOException("null hit document");
    }/*ww  w . j  a  va2s .  c om*/
    for (Fieldable fld : hitDoc.getFields()) {
        final String name = fld.name().trim();
        final List<String> value;

        if (ret.containsKey(name)) {
            value = ret.get(name);
        } else {
            value = new ArrayList<String>();
            ret.put(name, value);
        }
        value.add(fld.stringValue().trim());
    }
    return ret;
}

---

From source file:br.bireme.mlts.utils.Document2JSON.java

License:Open Source License

public static Map<String, List<Fieldable>> getMap(final Document doc) {
    if (doc == null) {
        throw new NullPointerException("doc");
    }// www .  j  a va  2  s .c om

    final Map<String, List<Fieldable>> ret = new LinkedHashMap<String, List<Fieldable>>();
    final List<Fieldable> fields = doc.getFields();
    for (Fieldable fld : fields) {
        List<Fieldable> lfld = ret.get(fld.name());
        if (lfld == null) {
            lfld = new ArrayList<Fieldable>();
            ret.put(fld.name(), lfld);
        }
        lfld.add(fld);
    }

    return ret;
}

---

From source file:br.bireme.ngrams.CompareResults.java

private static void writeDocDifferences(final String similarity, final Document doc1, final Document doc2,
        final BufferedWriter bwriter) throws IOException {
    assert similarity != null;
    assert doc1 != null;
    assert doc2 != null;
    assert bwriter != null;

    final StringBuilder builder = new StringBuilder();
    final Set<String> diff = new HashSet<>();
    final String id1 = doc1.get("id");
    final String id2 = doc2.get("id");

    for (IndexableField fld : doc1.getFields()) {
        final String name = fld.name();

        if (name.endsWith("~notnormalized")) {
            if (!name.startsWith("id~")) {
                final String value1 = fld.stringValue();
                final String value2 = doc2.get(name);
                if (((value1 == null) && (null != value2)) || !value1.equals(value2)) {
                    final String name2 = name.substring(0, name.lastIndexOf('~'));
                    diff.add("[" + name2 + "]|" + value1 + "|" + value2);
                }//from   w  ww .ja v a2  s .  c om
            }
        }
    }
    if (diff.isEmpty()) {
        builder.append("<identical>|");
        builder.append(id1 + "|" + id2 + "\n");
    } else {
        if (similarity.equals("1.0")) {
            builder.append("<very similar>|");
        } else {
            builder.append("<similar>|");
        }
        builder.append(id1 + "|" + id2 + "\n");
        for (String di : diff) {
            builder.append(di);
            builder.append("\n");
        }
    }
    builder.append("\n");
    bwriter.append(builder.toString());
}

---

From source file:ca.gnewton.lusql.core.DocumentFactory.java

License:Apache License

public void passivateObject(Object obj) {
    ++returned;/*from   w w w  . j a  v a2 s.  co  m*/
    //if(returned%1000 == 0)
    //System.out.println("DocumentFactory returned: " + returned);
    Document doc = (Document) obj;
    List<Fieldable> fields = doc.getFields();
    Iterator<Fieldable> it = fields.iterator();
    while (it.hasNext()) {
        doc.removeField(((Field) it.next()).name());
    }
}

---

From source file:ca.gnewton.lusql.core.ViewIndex.java

License:Apache License

static void printDoc(Document doc, int i) {
    System.out.println("\nDocument#: " + i);
    List list = doc.getFields();
    Iterator fields = list.iterator();
    while (fields.hasNext()) {
        Field field = (Field) fields.next();
        System.out.println("\t" + field.name() + ": [" + field.stringValue() + "]");
    }/*from w ww .  ja  va  2s  .com*/
}

---

From source file:cc.osint.graphd.graph.Graph.java

License:Apache License

public List<JSONObject> query(IndexSearcher indexSearcher, String queryStr) throws Exception {
    long start_t = System.currentTimeMillis();
    final List<JSONObject> results = new ArrayList<JSONObject>();
    QueryParser qp = new QueryParser(Version.LUCENE_31, KEY_FIELD, analyzer);
    qp.setDefaultOperator(org.apache.lucene.queryParser.QueryParser.Operator.AND);
    qp.setAllowLeadingWildcard(true);/*from  ww  w .  j ava2s.com*/
    Query query = qp.parse(queryStr);
    org.apache.lucene.search.Filter filter = new org.apache.lucene.search.CachingWrapperFilter(
            new QueryWrapperFilter(query));

    indexSearcher.search(new MatchAllDocsQuery(), filter, new Collector() {
        private int docBase;
        IndexReader reader;

        // ignore scoring
        public void setScorer(Scorer scorer) {
        }

        // accept docs out of order
        public boolean acceptsDocsOutOfOrder() {
            return true;
        }

        public void collect(int doc) {
            try {
                Document d = reader.document(doc);
                JSONObject result = new JSONObject();
                for (Fieldable f : d.getFields()) {
                    result.put(f.name(), d.get(f.name()));
                }
                results.add(result);
            } catch (Exception ex) {
                ex.printStackTrace();
            }
        }

        public void setNextReader(IndexReader reader, int docBase) {
            this.reader = reader;
            this.docBase = docBase;
        }
    });
    long end_t = System.currentTimeMillis();
    //log.info("query: hits.scoreDocs.length = " + results.size() + " (" + (end_t-start_t) + "ms)");
    return results;
}

---

From source file:ch.sentric.hbase.prospective.Percolator.java

License:Apache License

/**
* Tries to find a set of queries that match the given document.
* 
* @param doc/*from  w  w  w.  j  a  v a2s .  c om*/
*            the Lucene document
* @return the matching queries
* @throws IOException
*             if an I/O error occurs
*/
public Response<T> percolate(final Document doc, final Map<T, Query> queries) throws IOException {
    // first, parse the source doc into a MemoryIndex
    final MemoryIndex memoryIndex = new MemoryIndex();

    for (final Fieldable field : doc.getFields()) {
        if (!field.isIndexed()) {
            continue;
        }

        final TokenStream tokenStream = field.tokenStreamValue();
        if (tokenStream != null) {
            memoryIndex.addField(field.name(), tokenStream, field.getBoost());
        } else {
            final Reader reader = field.readerValue();
            if (reader != null) {
                memoryIndex.addField(field.name(), analyzer.reusableTokenStream(field.name(), reader),
                        field.getBoost());
            } else {
                final String value = field.stringValue();
                if (value != null) {
                    memoryIndex.addField(field.name(),
                            analyzer.reusableTokenStream(field.name(), new CharSequenceReader(value)),
                            field.getBoost());
                }
            }
        }
    }

    // do the search
    final IndexSearcher searcher = memoryIndex.createSearcher();
    final Map<T, Query> matches = new HashMap<T, Query>(0);

    if (queries != null && !queries.isEmpty()) {
        final ExistsCollector collector = new ExistsCollector();
        for (final Map.Entry<T, Query> entry : queries.entrySet()) {
            collector.reset();
            searcher.search(entry.getValue(), collector);
            if (collector.exists()) {
                matches.put(entry.getKey(), entry.getValue());
            }
        }
    }

    return new Response<T>(matches);
}

---

From source file:cn.hbu.cs.esearch.service.impl.EsearchSearchServiceImpl.java

License:Apache License

private static Map<String, String[]> convert(Document document, SearchRequest.SearchType searchType) {
    Map<String, String[]> map = new HashMap<String, String[]>();
    if (document != null) {
        List<IndexableField> fields = document.getFields();
        Iterator<IndexableField> iter = fields.iterator();
        while (iter.hasNext()) {
            IndexableField fld = iter.next();
            String fieldname = fld.name();
            if (searchType == SearchRequest.SearchType.SIMPLE_QUERY) {
                if (fieldname.equals("_path") || fieldname.equals("_name")) {
                    map.put(fieldname, document.getValues(fieldname));
                }//  w w w  .  jav  a  2 s.co m
            } else if (searchType == SearchRequest.SearchType.QUERY_AND_FETCH) {
                map.put(fieldname, document.getValues(fieldname));
            }
        }
    }
    return map;
}

---

From source file:com.baidu.rigel.biplatform.tesseract.resultset.isservice.ResultRecord.java

License:Open Source License

/**
 * ResultRecord// w w w.j  a v  a  2  s . com
 * 
 * @param doc
 *            doc
 */
public ResultRecord(Document doc) {
    super();
    List<IndexableField> idxFields = doc.getFields();
    List<String> fieldNameList = new ArrayList<String>();
    List<String> fieldList = new ArrayList<String>();
    for (IndexableField field : idxFields) {
        fieldNameList.add(field.name());
        fieldList.add(field.stringValue());
    }

    this.fieldArray = fieldList.toArray(new String[0]);
    this.meta = new Meta(fieldNameList.toArray(new String[0]));
}

---

From source file:com.basistech.lucene.tools.LuceneQueryTool.java

License:Apache License

private void printDocument(Document doc, int id, float score, PrintStream out) {
    Multimap<String, String> data = ArrayListMultimap.create();
    List<String> orderedFieldNames = Lists.newArrayList();
    if (showId) {
        orderedFieldNames.add("<id>");
        data.put("<id>", Integer.toString(id));
    }/*w  w w. j av  a  2s. c o m*/
    if (showScore) {
        orderedFieldNames.add("<score>");
        data.put("<score>", Double.toString(score));
    }
    orderedFieldNames.addAll(fieldNames);

    Set<String> setFieldNames = Sets.newHashSet();
    if (fieldNames.isEmpty()) {
        for (IndexableField f : doc.getFields()) {
            if (!setFieldNames.contains(f.name())) {
                orderedFieldNames.add(f.name());
            }
            setFieldNames.add(f.name());
        }
    } else {
        setFieldNames.addAll(fieldNames);
    }
    if (sortFields) {
        Collections.sort(orderedFieldNames);
    }

    for (IndexableField f : doc.getFields()) {
        if (setFieldNames.contains(f.name())) {
            if (f.stringValue() != null) {
                data.put(f.name(), f.stringValue());
            } else if (f.binaryValue() != null) {
                data.put(f.name(), formatBinary(f.binaryValue().bytes));
            } else {
                data.put(f.name(), "null");
            }
        }
    }

    if (docsPrinted == 0 && formatter.getFormat() == Formatter.Format.TABULAR && !formatter.suppressNames()) {

        out.println(Joiner.on('\t').join(orderedFieldNames));
    }

    String formatted = formatter.format(orderedFieldNames, data);
    if (!formatted.isEmpty()) {
        if (docsPrinted > 0 && formatter.getFormat() == Formatter.Format.MULTILINE) {
            out.println();
        }
        out.println(formatted);
        ++docsPrinted;
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• »