Java Term.field方法代码示例

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
@CheckForNull
@Override
@SuppressWarnings("StringEquality")
public Void convert(@NonNull final Index.WithTermFrequencies.TermFreq param) throws Stop {
    final Term term = param.getTerm();
    if (fieldName != term.field()) {
        throw new Stop();
    }
    final int docCount = param.getFreq();
    final String encBinName = term.text();
    final String binName = encBinName.substring(
        0,
        encBinName.length() - postfixLen);
    final int dotIndex = binName.lastIndexOf('.');  //NOI18N
    final String pkgName = dotIndex == -1 ? "" : binName.substring(0, dotIndex);    //NOI18N
    final Integer typeCount = typeFreq.get(binName);
    final Integer pkgCount = pkgFreq.get(pkgName);
    typeFreq.put(binName, typeCount == null ? docCount : docCount + typeCount);
    pkgFreq.put(pkgName, pkgCount == null ? docCount : docCount + pkgCount);
    return null;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
@Override
public String convert(Term currentTerm) throws Stop {
    if (fieldName != currentTerm.field()) {
        throw STOP;
    }
    String currentText = currentTerm.text();
    if (all || currentText.startsWith(value)) {
        if (directOnly) {
            int index = currentText.indexOf('.', value.length());    //NOI18N
            if (index>0) {
                currentText = currentText.substring(0,index);
            }
        }
        return currentText;
    }
    return null;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
void reset(FieldInfo fieldInfo) throws IOException {
  //System.out.println("pff.reset te=" + termEnum);
  this.fieldInfo = fieldInfo;
  internedFieldName = fieldInfo.name.intern();
  final Term term = new Term(internedFieldName);
  if (termEnum == null) {
    termEnum = getTermsDict().terms(term);
    seekTermEnum = getTermsDict().terms(term);
    //System.out.println("  term=" + termEnum.term());
  } else {
    getTermsDict().seekEnum(termEnum, term, true);
  }
  skipNext = true;

  unicodeSortOrder = sortTermsByUnicode();

  final Term t = termEnum.term();
  if (t != null && t.field() == internedFieldName) {
    newSuffixStart = 0;
    prevTerm.clear();
    surrogateDance();
  }
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
void seekEnum(SegmentTermEnum enumerator, int indexOffset) throws IOException {
  PagedBytesDataInput input = dataInput.clone();
  
  input.setPosition(indexToDataOffset.get(indexOffset));

  // read the term
  int fieldId = input.readVInt();
  Term field = fields[fieldId];
  Term term = new Term(field.field(), input.readString());

  // read the terminfo
  TermInfo termInfo = new TermInfo();
  termInfo.docFreq = input.readVInt();
  if (termInfo.docFreq >= skipInterval) {
    termInfo.skipOffset = input.readVInt();
  } else {
    termInfo.skipOffset = 0;
  }
  termInfo.freqPointer = input.readVLong();
  termInfo.proxPointer = input.readVLong();

  long pointer = input.readVLong();

  // perform the seek
  enumerator.seek(pointer, ((long) indexOffset * totalIndexInterval) - 1, term, termInfo);
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
public UnionDocsAndPositionsEnum(Bits liveDocs, AtomicReaderContext context, Term[] terms, Map<Term,TermContext> termContexts, TermsEnum termsEnum) throws IOException {
  List<DocsAndPositionsEnum> docsEnums = new LinkedList<>();
  for (int i = 0; i < terms.length; i++) {
    final Term term = terms[i];
    TermState termState = termContexts.get(term).get(context.ord);
    if (termState == null) {
      // Term doesn't exist in reader
      continue;
    }
    termsEnum.seekExact(term.bytes(), termState);
    DocsAndPositionsEnum postings = termsEnum.docsAndPositions(liveDocs, null, DocsEnum.FLAG_NONE);
    if (postings == null) {
      // term does exist, but has no positions
      throw new IllegalStateException("field \"" + term.field() + "\" was indexed without position data; cannot run PhraseQuery (term=" + term.text() + ")");
    }
    cost += postings.cost();
    docsEnums.add(postings);
  }

  _queue = new DocsQueue(docsEnums);
  _posList = new IntQueue();
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
/**
 * Create a new FuzzyQuery that will match terms with an edit distance 
 * of at most <code>maxEdits</code> to <code>term</code>.
 * If a <code>prefixLength</code> &gt; 0 is specified, a common prefix
 * of that length is also required.
 * 
 * @param term the term to search for
 * @param maxEdits must be >= 0 and <= {@link LevenshteinAutomata#MAXIMUM_SUPPORTED_DISTANCE}.
 * @param prefixLength length of common (non-fuzzy) prefix
 * @param maxExpansions the maximum number of terms to match. If this number is
 *  greater than {@link BooleanQuery#getMaxClauseCount} when the query is rewritten, 
 *  then the maxClauseCount will be used instead.
 * @param transpositions true if transpositions should be treated as a primitive
 *        edit operation. If this is false, comparisons will implement the classic
 *        Levenshtein algorithm.
 */
public FuzzyQuery(Term term, int maxEdits, int prefixLength, int maxExpansions, boolean transpositions) {
  super(term.field());
  
  if (maxEdits < 0 || maxEdits > LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE) {
    throw new IllegalArgumentException("maxEdits must be between 0 and " + LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE);
  }
  if (prefixLength < 0) {
    throw new IllegalArgumentException("prefixLength cannot be negative.");
  }
  if (maxExpansions <= 0) {
    throw new IllegalArgumentException("maxExpansions must be positive.");
  }
  
  this.term = term;
  this.maxEdits = maxEdits;
  this.prefixLength = prefixLength;
  this.transpositions = transpositions;
  this.maxExpansions = maxExpansions;
  setRewriteMethod(new MultiTermQuery.TopTermsScoringBooleanQueryRewrite(maxExpansions));
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
FreqCollector(
        @NonNull final Term startTerm,
        @NonNull final Map<String,Integer> typeFreqs,
        @NonNull final Map<String,Integer> pkgFreq) {
    this.fieldName = startTerm.field();
    this.typeFreq = typeFreqs;
    this.pkgFreq = pkgFreq;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
public RegexpTermEnum(
        final IndexReader in,
        final String  fieldName,
        final Pattern pattern,
        final String  startPrefix) throws IOException {
    final Term term = new Term(fieldName,startPrefix);
    this.fieldName = term.field();
    this.pattern = pattern;
    this.startPrefix = startPrefix;
    setEnum(in.terms(term));
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
@Override
protected boolean termCompare(Term term) {
    if (fieldName == term.field()) {
        String searchText = term.text();
        if (searchText.startsWith(startPrefix)) {
            return pattern.matcher(term.text()).matches();
        }
    }
    endEnum = true;
    return false;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
@Override
public FieldSelectorResult accept(String fieldName) {
    for (Term t : terms) {
        if (fieldName == t.field()) {
            return FieldSelectorResult.LOAD;
        }
    }
    return FieldSelectorResult.NO_LOAD;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
/**
 * Gets the term at the given position.  For testing.
 * 
 * @param termIndex
 *          the position to read the term from the index.
 * @return the term.
 * @throws IOException If there is a low-level I/O error.
 */
Term getTerm(int termIndex) throws IOException {
  PagedBytesDataInput input = dataInput.clone();
  input.setPosition(indexToDataOffset.get(termIndex));

  // read the term
  int fieldId = input.readVInt();
  Term field = fields[fieldId];
  return new Term(field.field(), input.readString());
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
/**
 * Adds a term to the end of the query phrase.
 * The relative position of the term within the phrase is specified explicitly.
 * This allows e.g. phrases with more than one term at the same position
 * or phrases with gaps (e.g. in connection with stopwords).
 * 
 */
public void add(Term term, int position) {
  if (terms.size() == 0) {
    field = term.field();
  } else if (!term.field().equals(field)) {
    throw new IllegalArgumentException("All phrase terms must be in the same field: " + term);
  }

  terms.add(term);
  positions.add(Integer.valueOf(position));
  if (position > maxPosition) maxPosition = position;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
PackageFilter(final @NonNull Term startTerm, final boolean directOnly) {
    this.fieldName = startTerm.field();
    this.value = startTerm.text();
    this.directOnly = directOnly;
    this.all = value.length() == 0;
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
static Term deepCopyOf(Term other) {
  return new Term(other.field(), BytesRef.deepCopyOf(other.bytes()));
}
 

import org.apache.lucene.index.Term; //导入方法依赖的package包/类
/**
 * Loads the segment information at segment load time.
 * 
 * @param indexEnum
 *          the term enum.
 * @param indexDivisor
 *          the index divisor.
 * @param tiiFileLength
 *          the size of the tii file, used to approximate the size of the
 *          buffer.
 * @param totalIndexInterval
 *          the total index interval.
 */
TermInfosReaderIndex(SegmentTermEnum indexEnum, int indexDivisor, long tiiFileLength, int totalIndexInterval) throws IOException {
  this.totalIndexInterval = totalIndexInterval;
  indexSize = 1 + ((int) indexEnum.size - 1) / indexDivisor;
  skipInterval = indexEnum.skipInterval;
  // this is only an inital size, it will be GCed once the build is complete
  long initialSize = (long) (tiiFileLength * 1.5) / indexDivisor;
  PagedBytes dataPagedBytes = new PagedBytes(estimatePageBits(initialSize));
  PagedBytesDataOutput dataOutput = dataPagedBytes.getDataOutput();

  final int bitEstimate = 1+MathUtil.log(tiiFileLength, 2);
  GrowableWriter indexToTerms = new GrowableWriter(bitEstimate, indexSize, PackedInts.DEFAULT);

  String currentField = null;
  List<String> fieldStrs = new ArrayList<>();
  int fieldCounter = -1;
  for (int i = 0; indexEnum.next(); i++) {
    Term term = indexEnum.term();
    if (currentField == null || !currentField.equals(term.field())) {
      currentField = term.field();
      fieldStrs.add(currentField);
      fieldCounter++;
    }
    TermInfo termInfo = indexEnum.termInfo();
    indexToTerms.set(i, dataOutput.getPosition());
    dataOutput.writeVInt(fieldCounter);
    dataOutput.writeString(term.text());
    dataOutput.writeVInt(termInfo.docFreq);
    if (termInfo.docFreq >= skipInterval) {
      dataOutput.writeVInt(termInfo.skipOffset);
    }
    dataOutput.writeVLong(termInfo.freqPointer);
    dataOutput.writeVLong(termInfo.proxPointer);
    dataOutput.writeVLong(indexEnum.indexPointer);
    for (int j = 1; j < indexDivisor; j++) {
      if (!indexEnum.next()) {
        break;
      }
    }
  }

  fields = new Term[fieldStrs.size()];
  for (int i = 0; i < fields.length; i++) {
    fields[i] = new Term(fieldStrs.get(i));
  }
  
  dataPagedBytes.freeze(true);
  dataInput = dataPagedBytes.getDataInput();
  indexToDataOffset = indexToTerms.getMutable();

  long ramBytesUsed = RamUsageEstimator.shallowSizeOf(fields);
  ramBytesUsed += RamUsageEstimator.shallowSizeOf(dataInput);
  ramBytesUsed += fields.length * RamUsageEstimator.shallowSizeOfInstance(Term.class);
  ramBytesUsed += dataPagedBytes.ramBytesUsed();
  ramBytesUsed += indexToDataOffset.ramBytesUsed();
  this.ramBytesUsed = ramBytesUsed;
}