Java Operations.determinize方法代码示例

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
final Automaton toLookupAutomaton(final CharSequence key) throws IOException {
    // TODO: is there a Reader from a CharSequence?
    // Turn tokenstream into automaton:
    Automaton automaton = null;

    try (TokenStream ts = queryAnalyzer.tokenStream("", key.toString())) {
        automaton = getTokenStreamToAutomaton().toAutomaton(ts);
    }

    automaton = replaceSep(automaton);

    // TODO: we can optimize this somewhat by determinizing
    // while we convert

    // This automaton should not blow up during determinize:
    automaton = Operations.determinize(automaton, Integer.MAX_VALUE);
    return automaton;
}
 

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
/**
 * Create a automaton for a given context query this automaton will be used
 * to find the matching paths with the fst
 *
 * @param preserveSep set an additional char (<code>XAnalyzingSuggester.SEP_LABEL</code>) between each context query
 * @param queries list of {@link ContextQuery} defining the lookup context
 *
 * @return Automaton matching the given Query
 */
public static Automaton toAutomaton(boolean preserveSep, Iterable<ContextQuery> queries) {
    Automaton a = Automata.makeEmptyString();

    Automaton gap = Automata.makeChar(ContextMapping.SEPARATOR);
    if (preserveSep) {
        // if separators are preserved the fst contains a SEP_LABEL
        // behind each gap. To have a matching automaton, we need to
        // include the SEP_LABEL in the query as well
        gap = Operations.concatenate(gap, Automata.makeChar(XAnalyzingSuggester.SEP_LABEL));
    }

    for (ContextQuery query : queries) {
        a = Operations.concatenate(Arrays.asList(query.toAutomaton(), gap, a));
    }

    // TODO: should we limit this?  Do any of our ContextQuery impls really create exponential regexps?  GeoQuery looks safe (union
    // of strings).
    return Operations.determinize(a, Integer.MAX_VALUE);
}
 

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
final Automaton toLookupAutomaton(final CharSequence key) throws IOException {
  // TODO: is there a Reader from a CharSequence?
  // Turn tokenstream into automaton:
  Automaton automaton = null;
  TokenStream ts = queryAnalyzer.tokenStream("", key.toString());
  try {
      automaton = getTokenStreamToAutomaton().toAutomaton(ts);
  } finally {
    IOUtils.closeWhileHandlingException(ts);
  }

  automaton = replaceSep(automaton);

  // TODO: we can optimize this somewhat by determinizing
  // while we convert
  automaton = Operations.determinize(automaton, DEFAULT_MAX_DETERMINIZED_STATES);
  return automaton;
}
 

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
@Override
protected Automaton convertAutomaton(Automaton a) {
  if (unicodeAware) {
    // FLORIAN EDIT: get converted Automaton from superclass
    Automaton utf8automaton = new UTF32ToUTF8().convert(super.convertAutomaton(a));
    // This automaton should not blow up during determinize:
    utf8automaton = Operations.determinize(utf8automaton, Integer.MAX_VALUE);
    return utf8automaton;
  } else {
    return super.convertAutomaton(a);
  }
}
 

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
protected Automaton convertAutomaton(Automaton a) {
  if (queryPrefix != null) {
    a = Operations.concatenate(Arrays.asList(queryPrefix, a));
    // This automaton should not blow up during determinize:
    a = Operations.determinize(a, Integer.MAX_VALUE);
  }
  return a;
}
 

import org.apache.lucene.util.automaton.Operations; //导入方法依赖的package包/类
@Override
protected Automaton convertAutomaton(Automaton a) {
  if (unicodeAware) {
    Automaton utf8automaton = new UTF32ToUTF8().convert(a);
    utf8automaton = Operations.determinize(utf8automaton, DEFAULT_MAX_DETERMINIZED_STATES);
    return utf8automaton;
  } else {
    return a;
  }
}