org.apache.lucene.util.automaton.CompiledAutomaton的实例源码

项目:lams    文件FuzzyTermsEnum.java   
/** initialize levenshtein DFAs up to maxdistance,if possible */
private List<CompiledAutomaton> initAutomata(int maxdistance) {
  final List<CompiledAutomaton> runAutomata = dfaAtt.automata();
  //System.out.println("cached automata size: " + runAutomata.size());
  if (runAutomata.size() <= maxdistance &&
      maxdistance <= LevenshteinAutomata.MAXIMUM_SUPPORTED_disTANCE) {
    LevenshteinAutomata builder = 
      new LevenshteinAutomata(UnicodeUtil.newString(termText,realPrefixLength,termText.length - realPrefixLength),transpositions);

    String prefix = UnicodeUtil.newString(termText,realPrefixLength);
    for (int i = runAutomata.size(); i <= maxdistance; i++) {
      Automaton a = builder.toAutomaton(i,prefix);
      //System.out.println("compute automaton n=" + i);
      runAutomata.add(new CompiledAutomaton(a,true,false));
    }
  }
  return runAutomata;
}
项目:lams    文件MultiTerms.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  final List<MultiTermsEnum.TermsEnumIndex> termsEnums = new ArrayList<>();
  for(int i=0;i<subs.length;i++) {
    final TermsEnum termsEnum = subs[i].intersect(compiled,startTerm);
    if (termsEnum != null) {
      termsEnums.add(new MultiTermsEnum.TermsEnumIndex(termsEnum,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:lams    文件Terms.java   
/** Returns a TermsEnum that iterates over all terms that
 *  are accepted by the provided {@link
 *  CompiledAutomaton}.  If the <code>startTerm</code> is
 *  provided then the returned enum will only accept terms
 *  > <code>startTerm</code>,but you still must call
 *  next() first to get to the first term.  Note that the
 *  provided <code>startTerm</code> must be accepted by
 *  the automaton.
 *
 * <p><b>NOTE</b>: the returned TermsEnum cannot
 * seek</p>. */
public TermsEnum intersect(CompiledAutomaton compiled,final BytesRef startTerm) throws IOException {
  // Todo: eventually we Could support seekCeil/Exact on
  // the returned enum,instead of only being able to seek
  // at the start
  if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.norMAL) {
    throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
  }
  if (startTerm == null) {
    return new AutomatonTermsEnum(iterator(null),compiled);
  } else {
    return new AutomatonTermsEnum(iterator(null),compiled) {
      @Override
      protected BytesRef nextSeekTerm(BytesRef term) throws IOException {
        if (term == null) {
          term = startTerm;
        }
        return super.nextSeekTerm(term);
      }
    };
  }
}
项目:search    文件FuzzyTermsEnum.java   
/** initialize levenshtein DFAs up to maxdistance,false));
    }
  }
  return runAutomata;
}
项目:search    文件MultiTerms.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:search    文件Terms.java   
/** Returns a TermsEnum that iterates over all terms that
 *  are accepted by the provided {@link
 *  CompiledAutomaton}.  If the <code>startTerm</code> is
 *  provided then the returned enum will only accept terms
 *  > <code>startTerm</code>,compiled) {
      @Override
      protected BytesRef nextSeekTerm(BytesRef term) throws IOException {
        if (term == null) {
          term = startTerm;
        }
        return super.nextSeekTerm(term);
      }
    };
  }
}
项目:NYBC    文件FuzzyTermsEnum.java   
/** initialize levenshtein DFAs up to maxdistance,if possible */
private List<CompiledAutomaton> initAutomata(int maxdistance) {
  final List<CompiledAutomaton> runAutomata = dfaAtt.automata();
  //System.out.println("cached automata size: " + runAutomata.size());
  if (runAutomata.size() <= maxdistance && 
      maxdistance <= LevenshteinAutomata.MAXIMUM_SUPPORTED_disTANCE) {
    LevenshteinAutomata builder = 
      new LevenshteinAutomata(UnicodeUtil.newString(termText,transpositions);

    for (int i = runAutomata.size(); i <= maxdistance; i++) {
      Automaton a = builder.toAutomaton(i);
      //System.out.println("compute automaton n=" + i);
      // constant prefix
      if (realPrefixLength > 0) {
        Automaton prefix = BasicAutomata.makeString(
          UnicodeUtil.newString(termText,realPrefixLength));
        a = Basicoperations.concatenate(prefix,a);
      }
      runAutomata.add(new CompiledAutomaton(a,false));
    }
  }
  return runAutomata;
}
项目:NYBC    文件MultiTerms.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  final List<MultiTermsEnum.TermsEnumIndex> termsEnums = new ArrayList<MultiTermsEnum.TermsEnumIndex>();
  for(int i=0;i<subs.length;i++) {
    final TermsEnum termsEnum = subs[i].intersect(compiled,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:NYBC    文件Terms.java   
/** Returns a TermsEnum that iterates over all terms that
 *  are accepted by the provided {@link
 *  CompiledAutomaton}.  If the <code>startTerm</code> is
 *  provided then the returned enum will only accept terms
 *  > <code>startTerm</code>,compiled) {
      @Override
      protected BytesRef nextSeekTerm(BytesRef term) throws IOException {
        if (term == null) {
          term = startTerm;
        }
        return super.nextSeekTerm(term);
      }
    };
  }
}
项目:read-open-source-code    文件FuzzyTermsEnum.java   
/** initialize levenshtein DFAs up to maxdistance,false));
    }
  }
  return runAutomata;
}
项目:read-open-source-code    文件MultiTerms.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:read-open-source-code    文件Terms.java   
/** Returns a TermsEnum that iterates over all terms that
 *  are accepted by the provided {@link
 *  CompiledAutomaton}.  If the <code>startTerm</code> is
 *  provided then the returned enum will only accept terms
 *  > <code>startTerm</code>,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:Maskana-Gestor-de-Conocimiento    文件FuzzyTermsEnum.java   
/** initialize levenshtein DFAs up to maxdistance,false));
    }
  }
  return runAutomata;
}
项目:Maskana-Gestor-de-Conocimiento    文件MultiTerms.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,i));
    }
  }

  if (termsEnums.size() > 0) {
    return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
  } else {
    return TermsEnum.EMPTY;
  }
}
项目:Maskana-Gestor-de-Conocimiento    文件Terms.java   
/** Returns a TermsEnum that iterates over all terms that
 *  are accepted by the provided {@link
 *  CompiledAutomaton}.  If the <code>startTerm</code> is
 *  provided then the returned enum will only accept terms
 *  > <code>startTerm</code>,compiled) {
      @Override
      protected BytesRef nextSeekTerm(BytesRef term) throws IOException {
        if (term == null) {
          term = startTerm;
        }
        return super.nextSeekTerm(term);
      }
    };
  }
}
项目:lams    文件FieldReader.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.norMAL) {
    throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
  }
  return new IntersectTermsEnum(this,compiled,startTerm);
}
项目:lams    文件FuzzyTermsEnum.java   
/**
 * return an automata-based enum for matching up to editdistance from
 * lastTerm,if possible
 */
protected TermsEnum getAutomatonEnum(int editdistance,BytesRef lastTerm)
    throws IOException {
  final List<CompiledAutomaton> runAutomata = initAutomata(editdistance);
  if (editdistance < runAutomata.size()) {
    //System.out.println("FuzzyTE.getAEnum: ed=" + editdistance + " lastTerm=" + (lastTerm==null ? "null" : lastTerm.utf8ToString()));
    final CompiledAutomaton compiled = runAutomata.get(editdistance);
    return new AutomatonFuzzyTermsEnum(terms.intersect(compiled,lastTerm == null ? null : compiled.floor(lastTerm,new BytesRefBuilder())),runAutomata.subList(0,editdistance + 1).toArray(new CompiledAutomaton[editdistance + 1]));
  } else {
    return null;
  }
}
项目:lams    文件FuzzyTermsEnum.java   
public AutomatonFuzzyTermsEnum(TermsEnum tenum,CompiledAutomaton compiled[]) {
  super(tenum,false);
  this.matchers = new ByteRunAutomaton[compiled.length];
  for (int i = 0; i < compiled.length; i++)
    this.matchers[i] = compiled[i].runAutomaton;
  termRef = new BytesRef(term.text());
}
项目:lams    文件FuzzyTermsEnum.java   
@Override
public void copyTo(AttributeImpl target) {
  final List<CompiledAutomaton> targetAutomata =
    ((LevenshteinAutomataAttribute) target).automata();
  targetAutomata.clear();
  targetAutomata.addAll(automata);
}
项目:lams    文件AutomatonTermsEnum.java   
/**
 * Construct an enumerator based upon an automaton,enumerating the specified
 * field,working on a supplied TermsEnum
 * <p>
 * @lucene.experimental 
 * <p>
 * @param compiled CompiledAutomaton
 */
public AutomatonTermsEnum(TermsEnum tenum,CompiledAutomaton compiled) {
  super(tenum);
  this.finite = compiled.finite;
  this.runAutomaton = compiled.runAutomaton;
  assert this.runAutomaton != null;
  this.commonSuffixRef = compiled.commonSuffixRef;
  this.automaton = compiled.automaton;

  // used for path tracking,where each bit is a numbered state.
  visited = new long[runAutomaton.getSize()];

  termComp = getComparator();
}
项目:meltwater-elasticsearch-queries    文件WildcardTermsProducer.java   
private TermsEnum wildcardEnumeration(final IndexReader reader)
        throws IOException {
    Terms terms = MultiFields.getTerms(reader,term.field());
    if(terms == null){
        return null;
    }
    return new AutomatonTermsEnum(
            terms.iterator(),new CompiledAutomaton(
                    WildcardQuery.toAutomaton(term),false,false));
}
项目:search    文件FSTTermsReader.java   
IntersectTermsEnum(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  super();
  //if (TEST) System.out.println("Enum init,startTerm=" + startTerm);
  this.fst = dict;
  this.fstReader = fst.getBytesReader();
  this.fstOutputs = dict.outputs;
  this.fsa = compiled.runAutomaton;
  this.level = -1;
  this.stack = new Frame[16];
  for (int i = 0 ; i < stack.length; i++) {
    this.stack[i] = new Frame();
  }

  Frame frame;
  frame = loadVirtualFrame(newFrame());
  this.leveL++;
  frame = loadFirstFrame(newFrame());
  pushFrame(frame);

  this.Meta = null;
  this.MetaUpto = 1;
  this.decoded = false;
  this.pending = false;

  if (startTerm == null) {
    pending = isAccept(topFrame());
  } else {
    doSeekCeil(startTerm);
    pending = (term == null || !startTerm.equals(term.get())) && isValid(topFrame()) && isAccept(topFrame());
  }
}
项目:search    文件FSTOrdTermsReader.java   
IntersectTermsEnum(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  //if (TEST) System.out.println("Enum init,startTerm=" + startTerm);
  this.fst = index;
  this.fstReader = fst.getBytesReader();
  this.fstOutputs = index.outputs;
  this.fsa = compiled.runAutomaton;
  this.level = -1;
  this.stack = new Frame[16];
  for (int i = 0 ; i < stack.length; i++) {
    this.stack[i] = new Frame();
  }

  Frame frame;
  frame = loadVirtualFrame(newFrame());
  this.leveL++;
  frame = loadFirstFrame(newFrame());
  pushFrame(frame);

  this.decoded = false;
  this.pending = false;

  if (startTerm == null) {
    pending = isAccept(topFrame());
  } else {
    doSeekCeil(startTerm);
    pending = (term == null || !startTerm.equals(term.get())) && isValid(topFrame()) && isAccept(topFrame());
  }
}
项目:search    文件OrdsFieldReader.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,BytesRef startTerm) throws IOException {
  if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.norMAL) {
    throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
  }
  return new OrdsIntersectTermsEnum(this,startTerm);
}
项目:search    文件AssertingAtomicReader.java   
@Override
public TermsEnum intersect(CompiledAutomaton automaton,BytesRef bytes) throws IOException {
  TermsEnum termsEnum = in.intersect(automaton,bytes);
  assert termsEnum != null;
  assert bytes == null || bytes.isValid();
  return new AssertingTermsEnum(termsEnum);
}
项目:search    文件LuceneTestCase.java   
/** 
 * Terms api equivalency 
 */
public void assertTermsEquals(String info,IndexReader leftReader,Terms leftTerms,Terms rightTerms,boolean deep) throws IOException {
  if (leftTerms == null || rightTerms == null) {
    assertNull(info,leftTerms);
    assertNull(info,rightTerms);
    return;
  }
  assertTermsstatisticsEquals(info,leftTerms,rightTerms);
  assertEquals(leftTerms.hasOffsets(),rightTerms.hasOffsets());
  assertEquals(leftTerms.hasPositions(),rightTerms.hasPositions());
  assertEquals(leftTerms.hasPayloads(),rightTerms.hasPayloads());

  TermsEnum leftTermsEnum = leftTerms.iterator(null);
  TermsEnum rightTermsEnum = rightTerms.iterator(null);
  assertTermsEnumEquals(info,leftReader,leftTermsEnum,rightTermsEnum,true);

  assertTermsSeekingEquals(info,rightTerms);

  if (deep) {
    int numIntersections = atLeast(3);
    for (int i = 0; i < numIntersections; i++) {
      String re = AutomatonTestUtil.randomregexp(random());
      CompiledAutomaton automaton = new CompiledAutomaton(new RegExp(re,RegExp.NONE).toAutomaton());
      if (automaton.type == CompiledAutomaton.AUTOMATON_TYPE.norMAL) {
        // Todo: test start term too
        TermsEnum leftIntersection = leftTerms.intersect(automaton,null);
        TermsEnum rightIntersection = rightTerms.intersect(automaton,null);
        assertTermsEnumEquals(info,leftIntersection,rightIntersection,rarely());
      }
    }
  }
}
项目:search    文件FieldReader.java   
@Override
public TermsEnum intersect(CompiledAutomaton compiled,startTerm);
}
项目:search    文件FuzzyTermsEnum.java   
/**
 * return an automata-based enum for matching up to editdistance from
 * lastTerm,editdistance + 1).toArray(new CompiledAutomaton[editdistance + 1]));
  } else {
    return null;
  }
}
项目:search    文件FuzzyTermsEnum.java   
public AutomatonFuzzyTermsEnum(TermsEnum tenum,false);
  this.matchers = new ByteRunAutomaton[compiled.length];
  for (int i = 0; i < compiled.length; i++)
    this.matchers[i] = compiled[i].runAutomaton;
  termRef = new BytesRef(term.text());
}
项目:search    文件FuzzyTermsEnum.java   
@Override
public void copyTo(AttributeImpl target) {
  final List<CompiledAutomaton> targetAutomata =
    ((LevenshteinAutomataAttribute) target).automata();
  targetAutomata.clear();
  targetAutomata.addAll(automata);
}
项目:search    文件AutomatonTermsEnum.java   
/**
 * Construct an enumerator based upon an automaton,where each bit is a numbered state.
  visited = new long[runAutomaton.getSize()];

  termComp = getComparator();
}
项目:search    文件TestBlockPostingsFormat3.java   
public void assertTerms(Terms leftTerms,boolean deep) throws Exception {
  if (leftTerms == null || rightTerms == null) {
    assertNull(leftTerms);
    assertNull(rightTerms);
    return;
  }
  assertTermsstatistics(leftTerms,rightTerms);

  // NOTE: we don't assert hasOffsets/hasPositions/hasPayloads because they are allowed to be different

  TermsEnum leftTermsEnum = leftTerms.iterator(null);
  TermsEnum rightTermsEnum = rightTerms.iterator(null);
  assertTermsEnum(leftTermsEnum,true);

  assertTermsSeeking(leftTerms,null);
        assertTermsEnum(leftIntersection,rarely());
      }
    }
  }
}
项目:search    文件TestTermsEnum.java   
private boolean accepts(CompiledAutomaton c,BytesRef b) {
  int state = c.runAutomaton.getinitialState();
  for(int idx=0;idx<b.length;idx++) {
    assertTrue(state != -1);
    state = c.runAutomaton.step(state,b.bytes[b.offset+idx] & 0xff);
  }
  return c.runAutomaton.isAccept(state);
}
项目:NYBC    文件AssertingAtomicReader.java   
@Override
public TermsEnum intersect(CompiledAutomaton automaton,BytesRef bytes) throws IOException {
  TermsEnum termsEnum = super.intersect(automaton,bytes);
  assert termsEnum != null;
  assert bytes == null || bytes.isValid();
  return new AssertingTermsEnum(termsEnum);
}

相关文章

买水果
比较全面的redis工具类
gson 反序列化到多态子类
java 版本的 mb_strwidth
JAVA 反转字符串的最快方法,大概比StringBuffer.reverse()性...
com.google.gson.internal.bind.ArrayTypeAdapter的实例源码...