Examples with LeafReader org.apache.lucene.index.LeafReader used on opensource projects

Example 41 with LeafReader

use of org.apache.lucene.index.LeafReader in project lucene-solr by apache.

the class TestMemoryIndex method testOmitNorms.

@Test
public void testOmitNorms() throws IOException {
    MemoryIndex mi = new MemoryIndex();
    FieldType ft = new FieldType();
    ft.setTokenized(true);
    ft.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
    ft.setOmitNorms(true);
    mi.addField(new Field("f1", "some text in here", ft), analyzer);
    mi.freeze();
    LeafReader leader = (LeafReader) mi.createSearcher().getIndexReader();
    NumericDocValues norms = leader.getNormValues("f1");
    assertNull(norms);
}

Example 42 with LeafReader

use of org.apache.lucene.index.LeafReader in project lucene-solr by apache.

the class TestMemoryIndex method testPointValuesDoNotAffectPositionsOrOffset.

public void testPointValuesDoNotAffectPositionsOrOffset() throws Exception {
    MemoryIndex mi = new MemoryIndex(true, true);
    mi.addField(new TextField("text", "quick brown fox", Field.Store.NO), analyzer);
    mi.addField(new BinaryPoint("text", "quick".getBytes(StandardCharsets.UTF_8)), analyzer);
    mi.addField(new BinaryPoint("text", "brown".getBytes(StandardCharsets.UTF_8)), analyzer);
    LeafReader leafReader = mi.createSearcher().getIndexReader().leaves().get(0).reader();
    TermsEnum tenum = leafReader.terms("text").iterator();
    assertEquals("brown", tenum.next().utf8ToString());
    PostingsEnum penum = tenum.postings(null, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(1, penum.nextPosition());
    assertEquals(6, penum.startOffset());
    assertEquals(11, penum.endOffset());
    assertEquals("fox", tenum.next().utf8ToString());
    penum = tenum.postings(penum, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(2, penum.nextPosition());
    assertEquals(12, penum.startOffset());
    assertEquals(15, penum.endOffset());
    assertEquals("quick", tenum.next().utf8ToString());
    penum = tenum.postings(penum, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(0, penum.nextPosition());
    assertEquals(0, penum.startOffset());
    assertEquals(5, penum.endOffset());
    IndexSearcher indexSearcher = mi.createSearcher();
    assertEquals(1, indexSearcher.count(BinaryPoint.newExactQuery("text", "quick".getBytes(StandardCharsets.UTF_8))));
    assertEquals(1, indexSearcher.count(BinaryPoint.newExactQuery("text", "brown".getBytes(StandardCharsets.UTF_8))));
    assertEquals(0, indexSearcher.count(BinaryPoint.newExactQuery("text", "jumps".getBytes(StandardCharsets.UTF_8))));
}

Example 43 with LeafReader

use of org.apache.lucene.index.LeafReader in project lucene-solr by apache.

the class CompletionQuery method rewrite.

@Override
public Query rewrite(IndexReader reader) throws IOException {
    byte type = 0;
    boolean first = true;
    Terms terms;
    for (LeafReaderContext context : reader.leaves()) {
        LeafReader leafReader = context.reader();
        try {
            if ((terms = leafReader.terms(getField())) == null) {
                continue;
            }
        } catch (IOException e) {
            continue;
        }
        if (terms instanceof CompletionTerms) {
            CompletionTerms completionTerms = (CompletionTerms) terms;
            byte t = completionTerms.getType();
            if (first) {
                type = t;
                first = false;
            } else if (type != t) {
                throw new IllegalStateException(getField() + " has values of multiple types");
            }
        }
    }
    if (first == false) {
        if (this instanceof ContextQuery) {
            if (type == SuggestField.TYPE) {
                throw new IllegalStateException(this.getClass().getSimpleName() + " can not be executed against a non context-enabled SuggestField: " + getField());
            }
        } else {
            if (type == ContextSuggestField.TYPE) {
                return new ContextQuery(this);
            }
        }
    }
    return super.rewrite(reader);
}

Example 44 with LeafReader

use of org.apache.lucene.index.LeafReader in project lucene-solr by apache.

the class ExpandComponent method process.

@SuppressWarnings("unchecked")
@Override
public void process(ResponseBuilder rb) throws IOException {
    if (!rb.doExpand) {
        return;
    }
    SolrQueryRequest req = rb.req;
    SolrParams params = req.getParams();
    String field = params.get(ExpandParams.EXPAND_FIELD);
    String hint = null;
    if (field == null) {
        List<Query> filters = rb.getFilters();
        if (filters != null) {
            for (Query q : filters) {
                if (q instanceof CollapsingQParserPlugin.CollapsingPostFilter) {
                    CollapsingQParserPlugin.CollapsingPostFilter cp = (CollapsingQParserPlugin.CollapsingPostFilter) q;
                    field = cp.getField();
                    hint = cp.hint;
                }
            }
        }
    }
    if (field == null) {
        throw new IOException("Expand field is null.");
    }
    String sortParam = params.get(ExpandParams.EXPAND_SORT);
    String[] fqs = params.getParams(ExpandParams.EXPAND_FQ);
    String qs = params.get(ExpandParams.EXPAND_Q);
    int limit = params.getInt(ExpandParams.EXPAND_ROWS, 5);
    Sort sort = null;
    if (sortParam != null) {
        sort = SortSpecParsing.parseSortSpec(sortParam, rb.req).getSort();
    }
    Query query;
    if (qs == null) {
        query = rb.getQuery();
    } else {
        try {
            QParser parser = QParser.getParser(qs, req);
            query = parser.getQuery();
        } catch (Exception e) {
            throw new IOException(e);
        }
    }
    List<Query> newFilters = new ArrayList<>();
    if (fqs == null) {
        List<Query> filters = rb.getFilters();
        if (filters != null) {
            for (Query q : filters) {
                if (!(q instanceof CollapsingQParserPlugin.CollapsingPostFilter)) {
                    newFilters.add(q);
                }
            }
        }
    } else {
        try {
            for (String fq : fqs) {
                if (fq != null && fq.trim().length() != 0 && !fq.equals("*:*")) {
                    QParser fqp = QParser.getParser(fq, req);
                    newFilters.add(fqp.getQuery());
                }
            }
        } catch (Exception e) {
            throw new IOException(e);
        }
    }
    SolrIndexSearcher searcher = req.getSearcher();
    LeafReader reader = searcher.getSlowAtomicReader();
    SchemaField schemaField = searcher.getSchema().getField(field);
    FieldType fieldType = schemaField.getType();
    SortedDocValues values = null;
    long nullValue = 0L;
    if (fieldType instanceof StrField) {
        //Get The Top Level SortedDocValues
        if (CollapsingQParserPlugin.HINT_TOP_FC.equals(hint)) {
            Map<String, UninvertingReader.Type> mapping = new HashMap();
            mapping.put(field, UninvertingReader.Type.SORTED);
            UninvertingReader uninvertingReader = new UninvertingReader(new ReaderWrapper(searcher.getSlowAtomicReader(), field), mapping);
            values = uninvertingReader.getSortedDocValues(field);
        } else {
            values = DocValues.getSorted(reader, field);
        }
    } else {
        //Get the nullValue for the numeric collapse field
        String defaultValue = searcher.getSchema().getField(field).getDefaultValue();
        final NumberType numType = fieldType.getNumberType();
        // we don't need to handle invalid 64-bit field types here.
        if (defaultValue != null) {
            if (numType == NumberType.INTEGER) {
                nullValue = Long.parseLong(defaultValue);
            } else if (numType == NumberType.FLOAT) {
                nullValue = Float.floatToIntBits(Float.parseFloat(defaultValue));
            }
        } else if (NumberType.FLOAT.equals(numType)) {
            // Integer case already handled by nullValue defaulting to 0
            nullValue = Float.floatToIntBits(0.0f);
        }
    }
    FixedBitSet groupBits = null;
    LongHashSet groupSet = null;
    DocList docList = rb.getResults().docList;
    IntHashSet collapsedSet = new IntHashSet(docList.size() * 2);
    //Gather the groups for the current page of documents
    DocIterator idit = docList.iterator();
    int[] globalDocs = new int[docList.size()];
    int docsIndex = -1;
    while (idit.hasNext()) {
        globalDocs[++docsIndex] = idit.nextDoc();
    }
    Arrays.sort(globalDocs);
    Query groupQuery = null;
    /*
    * This code gathers the group information for the current page.
    */
    List<LeafReaderContext> contexts = searcher.getTopReaderContext().leaves();
    if (contexts.size() == 0) {
        //When no context is available we can skip the expanding
        return;
    }
    int currentContext = 0;
    int currentDocBase = contexts.get(currentContext).docBase;
    int nextDocBase = (currentContext + 1) < contexts.size() ? contexts.get(currentContext + 1).docBase : Integer.MAX_VALUE;
    IntObjectHashMap<BytesRef> ordBytes = null;
    if (values != null) {
        groupBits = new FixedBitSet(values.getValueCount());
        MultiDocValues.OrdinalMap ordinalMap = null;
        SortedDocValues[] sortedDocValues = null;
        LongValues segmentOrdinalMap = null;
        SortedDocValues currentValues = null;
        if (values instanceof MultiDocValues.MultiSortedDocValues) {
            ordinalMap = ((MultiDocValues.MultiSortedDocValues) values).mapping;
            sortedDocValues = ((MultiDocValues.MultiSortedDocValues) values).values;
            currentValues = sortedDocValues[currentContext];
            segmentOrdinalMap = ordinalMap.getGlobalOrds(currentContext);
        }
        int count = 0;
        ordBytes = new IntObjectHashMap<>();
        for (int i = 0; i < globalDocs.length; i++) {
            int globalDoc = globalDocs[i];
            while (globalDoc >= nextDocBase) {
                currentContext++;
                currentDocBase = contexts.get(currentContext).docBase;
                nextDocBase = (currentContext + 1) < contexts.size() ? contexts.get(currentContext + 1).docBase : Integer.MAX_VALUE;
                if (ordinalMap != null) {
                    currentValues = sortedDocValues[currentContext];
                    segmentOrdinalMap = ordinalMap.getGlobalOrds(currentContext);
                }
            }
            int contextDoc = globalDoc - currentDocBase;
            if (ordinalMap != null) {
                if (contextDoc > currentValues.docID()) {
                    currentValues.advance(contextDoc);
                }
                if (contextDoc == currentValues.docID()) {
                    int ord = currentValues.ordValue();
                    ++count;
                    BytesRef ref = currentValues.lookupOrd(ord);
                    ord = (int) segmentOrdinalMap.get(ord);
                    ordBytes.put(ord, BytesRef.deepCopyOf(ref));
                    groupBits.set(ord);
                    collapsedSet.add(globalDoc);
                }
            } else {
                if (globalDoc > values.docID()) {
                    values.advance(globalDoc);
                }
                if (globalDoc == values.docID()) {
                    int ord = values.ordValue();
                    ++count;
                    BytesRef ref = values.lookupOrd(ord);
                    ordBytes.put(ord, BytesRef.deepCopyOf(ref));
                    groupBits.set(ord);
                    collapsedSet.add(globalDoc);
                }
            }
        }
        if (count > 0 && count < 200) {
            try {
                groupQuery = getGroupQuery(field, count, ordBytes);
            } catch (Exception e) {
                throw new IOException(e);
            }
        }
    } else {
        groupSet = new LongHashSet(docList.size());
        NumericDocValues collapseValues = contexts.get(currentContext).reader().getNumericDocValues(field);
        int count = 0;
        for (int i = 0; i < globalDocs.length; i++) {
            int globalDoc = globalDocs[i];
            while (globalDoc >= nextDocBase) {
                currentContext++;
                currentDocBase = contexts.get(currentContext).docBase;
                nextDocBase = currentContext + 1 < contexts.size() ? contexts.get(currentContext + 1).docBase : Integer.MAX_VALUE;
                collapseValues = contexts.get(currentContext).reader().getNumericDocValues(field);
            }
            int contextDoc = globalDoc - currentDocBase;
            int valueDocID = collapseValues.docID();
            if (valueDocID < contextDoc) {
                valueDocID = collapseValues.advance(contextDoc);
            }
            long value;
            if (valueDocID == contextDoc) {
                value = collapseValues.longValue();
            } else {
                value = 0;
            }
            if (value != nullValue) {
                ++count;
                groupSet.add(value);
                collapsedSet.add(globalDoc);
            }
        }
        if (count > 0 && count < 200) {
            if (fieldType.isPointField()) {
                groupQuery = getPointGroupQuery(schemaField, count, groupSet);
            } else {
                groupQuery = getGroupQuery(field, fieldType, count, groupSet);
            }
        }
    }
    Collector collector;
    if (sort != null)
        sort = sort.rewrite(searcher);
    Collector groupExpandCollector = null;
    if (values != null) {
        //Get The Top Level SortedDocValues again so we can re-iterate:
        if (CollapsingQParserPlugin.HINT_TOP_FC.equals(hint)) {
            Map<String, UninvertingReader.Type> mapping = new HashMap();
            mapping.put(field, UninvertingReader.Type.SORTED);
            UninvertingReader uninvertingReader = new UninvertingReader(new ReaderWrapper(searcher.getSlowAtomicReader(), field), mapping);
            values = uninvertingReader.getSortedDocValues(field);
        } else {
            values = DocValues.getSorted(reader, field);
        }
        groupExpandCollector = new GroupExpandCollector(values, groupBits, collapsedSet, limit, sort);
    } else {
        groupExpandCollector = new NumericGroupExpandCollector(field, nullValue, groupSet, collapsedSet, limit, sort);
    }
    if (groupQuery != null) {
        //Limits the results to documents that are in the same group as the documents in the page.
        newFilters.add(groupQuery);
    }
    SolrIndexSearcher.ProcessedFilter pfilter = searcher.getProcessedFilter(null, newFilters);
    if (pfilter.postFilter != null) {
        pfilter.postFilter.setLastDelegate(groupExpandCollector);
        collector = pfilter.postFilter;
    } else {
        collector = groupExpandCollector;
    }
    if (pfilter.filter == null) {
        searcher.search(query, collector);
    } else {
        Query q = new BooleanQuery.Builder().add(query, Occur.MUST).add(pfilter.filter, Occur.FILTER).build();
        searcher.search(q, collector);
    }
    LongObjectMap<Collector> groups = ((GroupCollector) groupExpandCollector).getGroups();
    NamedList outMap = new SimpleOrderedMap();
    CharsRefBuilder charsRef = new CharsRefBuilder();
    for (LongObjectCursor<Collector> cursor : groups) {
        long groupValue = cursor.key;
        TopDocsCollector<?> topDocsCollector = TopDocsCollector.class.cast(cursor.value);
        TopDocs topDocs = topDocsCollector.topDocs();
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        if (scoreDocs.length > 0) {
            int[] docs = new int[scoreDocs.length];
            float[] scores = new float[scoreDocs.length];
            for (int i = 0; i < docs.length; i++) {
                ScoreDoc scoreDoc = scoreDocs[i];
                docs[i] = scoreDoc.doc;
                scores[i] = scoreDoc.score;
            }
            DocSlice slice = new DocSlice(0, docs.length, docs, scores, topDocs.totalHits, topDocs.getMaxScore());
            if (fieldType instanceof StrField) {
                final BytesRef bytesRef = ordBytes.get((int) groupValue);
                fieldType.indexedToReadable(bytesRef, charsRef);
                String group = charsRef.toString();
                outMap.add(group, slice);
            } else {
                outMap.add(numericToString(fieldType, groupValue), slice);
            }
        }
    }
    rb.rsp.add("expanded", outMap);
}

Example 45 with LeafReader

use of org.apache.lucene.index.LeafReader in project lucene-solr by apache.

the class JoinUtil method createJoinQuery.

/**
   * A query time join using global ordinals over a dedicated join field.
   *
   * This join has certain restrictions and requirements:
   * 1) A document can only refer to one other document. (but can be referred by one or more documents)
   * 2) Documents on each side of the join must be distinguishable. Typically this can be done by adding an extra field
   *    that identifies the "from" and "to" side and then the fromQuery and toQuery must take the this into account.
   * 3) There must be a single sorted doc values join field used by both the "from" and "to" documents. This join field
   *    should store the join values as UTF-8 strings.
   * 4) An ordinal map must be provided that is created on top of the join field.
   *
   * Note: min and max filtering and the avg score mode will require this join to keep track of the number of times
   * a document matches per join value. This will increase the per join cost in terms of execution time and memory.
   *
   * @param joinField   The {@link SortedDocValues} field containing the join values
   * @param fromQuery   The query containing the actual user query. Also the fromQuery can only match "from" documents.
   * @param toQuery     The query identifying all documents on the "to" side.
   * @param searcher    The index searcher used to execute the from query
   * @param scoreMode   Instructs how scores from the fromQuery are mapped to the returned query
   * @param ordinalMap  The ordinal map constructed over the joinField. In case of a single segment index, no ordinal map
   *                    needs to be provided.
   * @param min         Optionally the minimum number of "from" documents that are required to match for a "to" document
   *                    to be a match. The min is inclusive. Setting min to 0 and max to <code>Interger.MAX_VALUE</code>
   *                    disables the min and max "from" documents filtering
   * @param max         Optionally the maximum number of "from" documents that are allowed to match for a "to" document
   *                    to be a match. The max is inclusive. Setting min to 0 and max to <code>Interger.MAX_VALUE</code>
   *                    disables the min and max "from" documents filtering
   * @return a {@link Query} instance that can be used to join documents based on the join field
   * @throws IOException If I/O related errors occur
   */
public static Query createJoinQuery(String joinField, Query fromQuery, Query toQuery, IndexSearcher searcher, ScoreMode scoreMode, MultiDocValues.OrdinalMap ordinalMap, int min, int max) throws IOException {
    int numSegments = searcher.getIndexReader().leaves().size();
    final long valueCount;
    if (numSegments == 0) {
        return new MatchNoDocsQuery("JoinUtil.createJoinQuery with no segments");
    } else if (numSegments == 1) {
        // No need to use the ordinal map, because there is just one segment.
        ordinalMap = null;
        LeafReader leafReader = searcher.getIndexReader().leaves().get(0).reader();
        SortedDocValues joinSortedDocValues = leafReader.getSortedDocValues(joinField);
        if (joinSortedDocValues != null) {
            valueCount = joinSortedDocValues.getValueCount();
        } else {
            return new MatchNoDocsQuery("JoinUtil.createJoinQuery: no join values");
        }
    } else {
        if (ordinalMap == null) {
            throw new IllegalArgumentException("OrdinalMap is required, because there is more than 1 segment");
        }
        valueCount = ordinalMap.getValueCount();
    }
    final Query rewrittenFromQuery = searcher.rewrite(fromQuery);
    final Query rewrittenToQuery = searcher.rewrite(toQuery);
    GlobalOrdinalsWithScoreCollector globalOrdinalsWithScoreCollector;
    switch(scoreMode) {
        case Total:
            globalOrdinalsWithScoreCollector = new GlobalOrdinalsWithScoreCollector.Sum(joinField, ordinalMap, valueCount, min, max);
            break;
        case Min:
            globalOrdinalsWithScoreCollector = new GlobalOrdinalsWithScoreCollector.Min(joinField, ordinalMap, valueCount, min, max);
            break;
        case Max:
            globalOrdinalsWithScoreCollector = new GlobalOrdinalsWithScoreCollector.Max(joinField, ordinalMap, valueCount, min, max);
            break;
        case Avg:
            globalOrdinalsWithScoreCollector = new GlobalOrdinalsWithScoreCollector.Avg(joinField, ordinalMap, valueCount, min, max);
            break;
        case None:
            if (min <= 0 && max == Integer.MAX_VALUE) {
                GlobalOrdinalsCollector globalOrdinalsCollector = new GlobalOrdinalsCollector(joinField, ordinalMap, valueCount);
                searcher.search(rewrittenFromQuery, globalOrdinalsCollector);
                return new GlobalOrdinalsQuery(globalOrdinalsCollector.getCollectorOrdinals(), joinField, ordinalMap, rewrittenToQuery, rewrittenFromQuery, searcher.getTopReaderContext().id());
            } else {
                globalOrdinalsWithScoreCollector = new GlobalOrdinalsWithScoreCollector.NoScore(joinField, ordinalMap, valueCount, min, max);
                break;
            }
        default:
            throw new IllegalArgumentException(String.format(Locale.ROOT, "Score mode %s isn't supported.", scoreMode));
    }
    searcher.search(rewrittenFromQuery, globalOrdinalsWithScoreCollector);
    return new GlobalOrdinalsWithScoreQuery(globalOrdinalsWithScoreCollector, scoreMode, joinField, ordinalMap, rewrittenToQuery, rewrittenFromQuery, min, max, searcher.getTopReaderContext().id());
}