com.sindicetech.siren.search.node.NodeRegexpQuery Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of siren-core Show documentation
SIREn core module
The newest version!
/**
 * Copyright (c) 2014, Sindice Limited. All Rights Reserved.
 *
 * This file is part of the SIREn project.
 *
 * SIREn is a free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, either version 3 of
 * the License, or (at your option) any later version.
 *
 * SIREn is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public
 * License along with this program. If not, see .
 */
package com.sindicetech.siren.search.node;

import org.apache.lucene.index.Term;
import org.apache.lucene.search.RegexpQuery;
import org.apache.lucene.util.ToStringUtils;
import org.apache.lucene.util.automaton.Automaton;
import org.apache.lucene.util.automaton.AutomatonProvider;
import org.apache.lucene.util.automaton.RegExp;

import java.io.IOException;

/**
 * A {@link DatatypedNodeQuery} that provides a fast regular expression matching
 * based on the {@link org.apache.lucene.util.automaton} package.
 *
 * 
 *
 * 

 * Comparisons are fast
 * 
The term dictionary is enumerated in an intelligent way, to avoid
 * comparisons. See {@link NodeAutomatonQuery} for more details.
 * 
 *
 * 
 *
 * The supported syntax is documented in the {@link RegExp} class.
 * Note this might be different than other regular expression implementations.
 * For some alternatives with different syntax, look under the sandbox.
 *
 * 

 *
 * Note this query can be slow, as it needs to iterate over many terms. In order
 * to prevent extremely slow RegexpQueries, a Regexp term should not start with
 * the expression .*
 *
 * 
 Code taken from {@link RegexpQuery} and adapted for SIREn.
 */
public class NodeRegexpQuery extends NodeAutomatonQuery {
  /**
   * A provider that provides no named automata
   */
  private static AutomatonProvider defaultProvider = new AutomatonProvider() {
    public Automaton getAutomaton(final String name) throws IOException {
      return null;
    }
  };

  /**
   * Constructs a query for terms matching term.
   * 

   * By default, all regular expression features are enabled.
   * 
   *
   * @param term regular expression.
   */
  public NodeRegexpQuery(final Term term) {
    this(term, RegExp.ALL);
  }

  /**
   * Constructs a query for terms matching term.
   *
   * @param term regular expression.
   * @param flags optional RegExp features from {@link RegExp}
   */
  public NodeRegexpQuery(final Term term, final int flags) {
    this(term, flags, defaultProvider);
  }

  /**
   * Constructs a query for terms matching term.
   *
   * @param term regular expression.
   * @param flags optional RegExp features from {@link RegExp}
   * @param provider custom AutomatonProvider for named automata
   */
  public NodeRegexpQuery(final Term term, final int flags, final AutomatonProvider provider) {
    super(term, new RegExp(term.text(), flags).toAutomaton(provider));
  }

  /** Prints a user-readable version of this query. */
  @Override
  public String toString(final String field) {
    final StringBuilder buffer = new StringBuilder();
    buffer.append('/');
    buffer.append(term.text());
    buffer.append('/');
    buffer.append(ToStringUtils.boost(this.getBoost()));
    return this.wrapToStringWithDatatype(buffer).toString();
  }

}