lucene-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF GitHub Bot (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (LUCENE-7603) Support Graph Token Streams in QueryBuilder
Date Thu, 29 Dec 2016 19:28:58 GMT

    [ https://issues.apache.org/jira/browse/LUCENE-7603?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15785941#comment-15785941
] 

ASF GitHub Bot commented on LUCENE-7603:
----------------------------------------

Github user mattweber commented on a diff in the pull request:

    https://github.com/apache/lucene-solr/pull/129#discussion_r94171262
  
    --- Diff: lucene/core/src/java/org/apache/lucene/util/graph/GraphTokenStreamFiniteStrings.java
---
    @@ -0,0 +1,294 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *     http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.lucene.util.graph;
    +
    +import java.io.IOException;
    +import java.util.ArrayList;
    +import java.util.HashMap;
    +import java.util.List;
    +import java.util.Map;
    +
    +import org.apache.lucene.analysis.TokenStream;
    +import org.apache.lucene.analysis.tokenattributes.BytesTermAttribute;
    +import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
    +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
    +import org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute;
    +import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
    +import org.apache.lucene.util.BytesRef;
    +import org.apache.lucene.util.IntsRef;
    +import org.apache.lucene.util.automaton.Automaton;
    +import org.apache.lucene.util.automaton.FiniteStringsIterator;
    +import org.apache.lucene.util.automaton.Operations;
    +import org.apache.lucene.util.automaton.Transition;
    +
    +import static org.apache.lucene.util.automaton.Operations.DEFAULT_MAX_DETERMINIZED_STATES;
    +
    +/**
    + * Creates a list of {@link TokenStream} where each stream is the tokens that make up
a finite string in graph token stream.  To do this,
    + * the graph token stream is converted to an {@link Automaton} and from there we use
a {@link FiniteStringsIterator} to collect the various
    + * token streams for each finite string.
    + */
    +public class GraphTokenStreamFiniteStrings {
    +  /* TODO:
    +     Most of this is a combination of code from TermAutomatonQuery and TokenStreamToTermAutomatonQuery.
Would be
    +     good to make this so it could be shared. */
    +  private final Automaton.Builder builder;
    +  Automaton det;
    +  private final Map<BytesRef, Integer> termToID = new HashMap<>();
    +  private final Map<Integer, BytesRef> idToTerm = new HashMap<>();
    +  private int anyTermID = -1;
    +
    +  public GraphTokenStreamFiniteStrings() {
    +    this.builder = new Automaton.Builder();
    +  }
    +
    +  private static class BytesRefArrayTokenStream extends TokenStream {
    +    private final BytesTermAttribute termAtt = addAttribute(BytesTermAttribute.class);
    +    private final BytesRef[] terms;
    +    private int offset;
    +
    +    BytesRefArrayTokenStream(BytesRef[] terms) {
    +      this.terms = terms;
    +      offset = 0;
    +    }
    +
    +    @Override
    +    public boolean incrementToken() throws IOException {
    +      if (offset < terms.length) {
    +        clearAttributes();
    +        termAtt.setBytesRef(terms[offset]);
    +        offset = offset + 1;
    +        return true;
    +      }
    +
    +      return false;
    +    }
    +  }
    +
    +  /**
    +   * Gets the list of finite string token streams from the given input graph token stream.
    +   */
    +  public List<TokenStream> getTokenStreams(final TokenStream in) throws IOException
{
    +    // build automation
    +    build(in);
    +
    +    List<TokenStream> tokenStreams = new ArrayList<>();
    +    final FiniteStringsIterator finiteStrings = new FiniteStringsIterator(det);
    +    for (IntsRef string; (string = finiteStrings.next()) != null; ) {
    +      final BytesRef[] tokens = new BytesRef[string.length];
    +      for (int idx = string.offset, len = string.offset + string.length; idx < len;
idx++) {
    +        tokens[idx - string.offset] = idToTerm.get(string.ints[idx]);
    +      }
    +
    +      tokenStreams.add(new BytesRefArrayTokenStream(tokens));
    +    }
    +
    +    return tokenStreams;
    +  }
    +
    +  private void build(final TokenStream in) throws IOException {
    +    if (det != null) {
    +      throw new IllegalStateException("Automation already built");
    +    }
    +
    +    final TermToBytesRefAttribute termBytesAtt = in.addAttribute(TermToBytesRefAttribute.class);
    +    final PositionIncrementAttribute posIncAtt = in.addAttribute(PositionIncrementAttribute.class);
    +    final PositionLengthAttribute posLengthAtt = in.addAttribute(PositionLengthAttribute.class);
    +    final OffsetAttribute offsetAtt = in.addAttribute(OffsetAttribute.class);
    +
    +    in.reset();
    +
    +    int pos = -1;
    +    int lastPos = 0;
    +    int maxOffset = 0;
    +    int maxPos = -1;
    +    int state = -1;
    +    while (in.incrementToken()) {
    +      int posInc = posIncAtt.getPositionIncrement();
    +      assert pos > -1 || posInc > 0;
    +
    +      if (posInc > 1) {
    --- End diff --
    
    @dsmiley That was actually pulled out of the existing [TokenStreamToTermAutomatonQuery.java](https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/search/TokenStreamToTermAutomatonQuery.java#L77).
 Let me look into it more.


> Support Graph Token Streams in QueryBuilder
> -------------------------------------------
>
>                 Key: LUCENE-7603
>                 URL: https://issues.apache.org/jira/browse/LUCENE-7603
>             Project: Lucene - Core
>          Issue Type: Improvement
>          Components: core/queryparser, core/search
>            Reporter: Matt Weber
>
> With [LUCENE-6664|https://issues.apache.org/jira/browse/LUCENE-6664] we can use multi-term
synonyms query time.  A "graph token stream" will be created which which is nothing more than
using the position length attribute on stacked tokens to indicate how many positions a token
should span.  Currently the position length attribute on tokens is ignored during query parsing.
 This issue will add support for handling these graph token streams inside the QueryBuilder
utility class used by query parsers.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@lucene.apache.org
For additional commands, e-mail: dev-help@lucene.apache.org


Mime
View raw message