Example usage for org.apache.lucene.index IndexableField stringValue

List of usage examples for org.apache.lucene.index IndexableField stringValue

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexableField
  6. stringValue

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexableField stringValue.

Prototype

public String stringValue();

Source Link

Document

Non-null if this field has a string value

Usage

From source file:KNearestNeighborClassifier.java

License:Apache License

/**
 * build a list of classification results from search results
 * @param topDocs the search results as a {@link TopDocs} object
 * @return a {@link List} of {@link ClassificationResult}, one for each existing class
 * @throws IOException if it's not possible to get the stored value of class field
 *///from  www  .ja  v a 2s  .c  o m
protected List<ClassificationResult<BytesRef>> buildListFromTopDocs(TopDocs topDocs) throws IOException {
    Map<BytesRef, Integer> classCounts = new HashMap<>();
    Map<BytesRef, Double> classBoosts = new HashMap<>(); // this is a boost based on class ranking positions in topDocs
    float maxScore = topDocs.getMaxScore();
    for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
        IndexableField storableField = indexSearcher.doc(scoreDoc.doc).getField(classFieldName);
        if (storableField != null) {
            BytesRef cl = new BytesRef(storableField.stringValue());
            //update count
            Integer count = classCounts.get(cl);
            if (count != null) {
                classCounts.put(cl, count + 1);
            } else {
                classCounts.put(cl, 1);
            }
            //update boost, the boost is based on the best score
            Double totalBoost = classBoosts.get(cl);
            double singleBoost = scoreDoc.score / maxScore;
            if (totalBoost != null) {
                classBoosts.put(cl, totalBoost + singleBoost);
            } else {
                classBoosts.put(cl, singleBoost);
            }
        }
    }
    List<ClassificationResult<BytesRef>> returnList = new ArrayList<>();
    List<ClassificationResult<BytesRef>> temporaryList = new ArrayList<>();
    int sumdoc = 0;
    for (Map.Entry<BytesRef, Integer> entry : classCounts.entrySet()) {
        Integer count = entry.getValue();
        Double normBoost = classBoosts.get(entry.getKey()) / count; //the boost is normalized to be 0<b<1
        temporaryList.add(new ClassificationResult<>(entry.getKey().clone(), (count * normBoost) / (double) k));
        sumdoc += count;
    }

    //correction
    if (sumdoc < k) {
        for (ClassificationResult<BytesRef> cr : temporaryList) {
            returnList.add(
                    new ClassificationResult<>(cr.getAssignedClass(), cr.getScore() * k / (double) sumdoc));
        }
    } else {
        returnList = temporaryList;
    }
    return returnList;
}

From source file:alix.lucene.MoreLikeThis.java

License:Apache License

/**
 * Find words for a more-like-this query former.
 *
 * @param docNum the id of the lucene document from which to find terms
 *//*from  w w  w.ja  v a 2  s.com*/
private PriorityQueue<ScoreTerm> retrieveTerms(int docNum) throws IOException {
    Map<String, Int> termFreqMap = new HashMap<>();
    for (String fieldName : fieldNames) {
        final Terms vector = ir.getTermVector(docNum, fieldName);
        // field does not store term vector info
        if (vector == null) {
            Document d = ir.document(docNum);
            IndexableField[] fields = d.getFields(fieldName);
            for (IndexableField field : fields) {
                final String stringValue = field.stringValue();
                if (stringValue != null) {
                    addTermFrequencies(new StringReader(stringValue), termFreqMap, fieldName);
                }
            }
        } else {
            addTermFrequencies(termFreqMap, vector);
        }
    }

    return createQueue(termFreqMap);
}

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.utils.NewsItemLuceneDocConverter.java

License:Apache License

/**
 * Converts a Lucene Document to a NewsItem
 *
 * @param d//from  w w  w . j av  a  2 s.  c om
 * @return
 */
public static RecommendedNewsItem documentToNewsItem(Document d) {
    RecommendedNewsItem item = new RecommendedNewsItem();
    IndexableField field;

    field = d.getField("description");
    if (field != null) {
        item.setDescription(field.stringValue());
    } else {
        item.setDescription("No description available");
    }

    field = d.getField("source");
    if (field != null) {
        item.setSource(field.stringValue());
    } else {
        item.setSource("No source available");
    }

    field = d.getField("text");
    if (field != null) {
        item.setFulltext(field.stringValue());
    } else {
        item.setFulltext("No text available");
    }

    field = d.getField("id");
    if (field != null) {
        item.setId(field.stringValue());
    } else {
        item.setId("");
    }

    field = d.getField("imageUrl");
    if (field != null) {
        try {
            item.setImageUrl(new URL(field.stringValue()));
        } catch (MalformedURLException ex) {
            item.setImageUrl(null);
        }
    }

    field = d.getField("locale");
    if (field != null) {
        item.setLocale(Locale.forLanguageTag(field.stringValue()));
    } else {
        item.setLocale(Locale.getDefault());
    }

    field = d.getField("timestamp");
    if (field != null) {
        item.setTimestamp(new Date(field.numericValue().longValue()));
    } else {
        item.setTimestamp(new Date());
    }

    field = d.getField("title");
    if (field != null) {
        item.setTitle(field.stringValue());
    } else {
        item.setTitle("");
    }

    field = d.getField("url");
    if (field != null) {
        try {
            item.setUrl(new URL(field.stringValue()));
        } catch (MalformedURLException ex) {
            item.setUrl(null);
        }
    } else {
        item.setTitle("");
    }

    field = d.getField("terms");
    if (field != null) {
        Map<String, Double> terms = gson.fromJson(field.stringValue(), HashMap.class);
        item.addTerms(terms);
    }

    return item;
}

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 w  w  . j  ava  2s .  co  m*/
            }
        }
    }
    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:com.b2international.index.lucene.BooleanIndexField.java

License:Apache License

@Override
protected Boolean getValue(IndexableField field) {
    return convertFromString(field.stringValue());
}

From source file:com.b2international.index.lucene.StringIndexFieldBase.java

License:Apache License

@Override
public String getValue(IndexableField field) {
    return field.stringValue();
}

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

License:Open Source License

/**
 * ResultRecord//from   w w  w . j  a  va  2  s .  c  o m
 * 
 * @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));
    }//from   w  w  w .  ja va 2  s.c om
    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;
    }
}

From source file:com.bericotech.clavin.index.IndexField.java

License:Apache License

/**
 * Get the value of this field as set in the given document or <code>null</code>
 * if the field is not set or cannot be retrieved.  If a field has multiple values,
 * the value that is returned may be arbitrarily selected from one of the values. In
 * this instance, use the methods in Document directly to retrieve multiple values.
 * @param <T> the expected return type
 * @param doc the input document/* w  w  w.  j av a2s .  co  m*/
 * @return the value of this field in the input document, if it has been set, or <code>null</code>
 */
@SuppressWarnings("unchecked")
public <T> T getValue(final Document doc) {
    IndexableField field = doc.getField(key);
    Object value = null;
    if (field != null) {
        switch (this) {
        case INDEX_NAME:
        case GEONAME:
        case PREFERRED_NAME:
            value = field.stringValue();
            break;
        case GEONAME_ID:
        case PARENT_ID:
        case ANCESTOR_IDS:
            value = field.numericValue().intValue();
            break;
        case POPULATION:
            value = field.numericValue().longValue();
            break;
        case SORT_POP:
            value = field.numericValue().longValue();
            break;
        case HISTORICAL:
        case FEATURE_CODE:
            // these fields are not stored
            LOG.warn("Attempting to retrieve value for an unstored field: [{}]", this);
            break;
        default:
            LOG.error("Attempting to retrieve value for an unconfigured field: [{}]", this);
            break;
        }
    }
    return (T) value;
}

From source file:com.bluedragon.search.search.QueryRun.java

License:Open Source License

private void addRow(IndexSearcher searcher, int docid, float score, int rank, int searchCount,
        int recordsSearched) throws CorruptIndexException, Exception {
    DocumentWrap document = new DocumentWrap(searcher.doc(docid));

    queryResultData.addRow(1);//from ww w . j a v  a2s .  co m
    queryResultData.setCurrentRow(queryResultData.getSize());

    // Add in the standard columns that we know we have for every search
    queryResultData.setCell(1, new cfStringData(document.getId()));
    queryResultData.setCell(2, new cfStringData(document.getName()));
    queryResultData.setCell(3, new cfNumberData(score));
    queryResultData.setCell(4, new cfNumberData(searchCount));
    queryResultData.setCell(5, new cfNumberData(recordsSearched));
    queryResultData.setCell(6, new cfNumberData(rank + 1));

    String uC = queryAttributes.getUniqueColumn();

    // Now we do the custom ones
    List<IndexableField> fields = document.getDocument().getFields();
    Iterator<IndexableField> it = fields.iterator();
    while (it.hasNext()) {
        IndexableField fieldable = it.next();

        String fieldName = fieldable.name().toLowerCase();

        // Check for the unique
        if (uniqueSet != null && fieldName.equals(uC)) {
            if (uniqueSet.contains(fieldable.stringValue())) {
                queryResultData.deleteRow(queryResultData.getSize());
                return;
            } else
                uniqueSet.add(fieldable.stringValue());
        }

        // Check to see if we have this column
        if (fieldName.equals("contents") && !queryAttributes.getContentFlag())
            continue;

        if (!activeColumns.containsKey(fieldName)) {
            int newcolumn = queryResultData.addColumnData(fieldable.name().toUpperCase(),
                    cfArrayData.createArray(1), null);
            activeColumns.put(fieldName, newcolumn);
        }

        int column = activeColumns.get(fieldName);
        if (column <= 6)
            continue;

        queryResultData.setCell(column, new cfStringData(fieldable.stringValue()));
    }

    // Do the context stuff if enable
    if (queryAttributes.getContextPassages() > 0) {

        Scorer scorer = new QueryScorer(queryAttributes.getQuery());
        SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(queryAttributes.getContextHighlightStart(),
                queryAttributes.getContextHighlightEnd());
        Highlighter highlighter = new Highlighter(formatter, scorer);
        Fragmenter fragmenter = new SimpleFragmenter(queryAttributes.getContextBytes());
        highlighter.setTextFragmenter(fragmenter);

        String nextContext = "";
        String contents = document.getAttribute(DocumentWrap.CONTENTS);

        if (contents != null) {
            TokenStream tokenStream = AnalyzerFactory.get("simple").tokenStream(DocumentWrap.CONTENTS,
                    new StringReader(contents));
            String[] fragments = null;
            try {
                fragments = highlighter.getBestFragments(tokenStream, contents,
                        queryAttributes.getContextPassages());
                if (fragments.length == 1) {
                    nextContext = fragments[0] + "...";
                } else {
                    StringBuilder context = new StringBuilder();
                    for (int f = 0; f < fragments.length; f++) {
                        context.append("...");
                        context.append(fragments[f]);
                    }
                    context.append("...");
                    nextContext = context.toString();
                }
            } catch (Exception e) {
            }

            // Add in the context
            if (!activeColumns.containsKey("context")) {
                int newcolumn = queryResultData.addColumnData("CONTEXT", cfArrayData.createArray(1), null);
                activeColumns.put("context", newcolumn);
            }

            queryResultData.setCell(activeColumns.get("context"), new cfStringData(nextContext));
        }
    }
}