本文整理了Java中org.apache.kylin.common.util.Dictionary类的一些代码示例，展示了Dictionary类的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。Dictionary类的具体详情如下：
包路径：org.apache.kylin.common.util.Dictionary
类名称：Dictionary

Dictionary介绍

[英]A bi-way dictionary that maps from dimension/column values to IDs and vice versa. By storing IDs instead of real values, the size of cube is significantly reduced. - IDs are smallest integers possible for the cardinality of a column, for the purpose of minimal storage space - IDs preserve ordering of values, such that range query can be applied to IDs directly A dictionary once built, is immutable. This allows optimal memory footprint by e.g. flatten the Trie structure into a byte array, replacing node pointers with array offsets.
[中]

代码示例

代码示例来源：origin: apache/kylin

@Override
  public List<ByteArray> reEncodeDictionary(List<ByteArray> value, MeasureDesc measureDesc, Map<TblColRef, Dictionary<String>> oldDicts, Map<TblColRef, Dictionary<String>> newDicts) {
    TblColRef colRef = getRawColumn(measureDesc.getFunction());
    Dictionary<String> sourceDict = oldDicts.get(colRef);
    Dictionary<String> mergedDict = newDicts.get(colRef);
    int valueSize = value.size();
    byte[] newIdBuf = new byte[valueSize * mergedDict.getSizeOfId()];
    int bufOffset = 0;
    for (ByteArray c : value) {
      int oldId = BytesUtil.readUnsigned(c.array(), c.offset(), c.length());
      int newId;
      String v = sourceDict.getValueFromId(oldId);
      if (v == null) {
        newId = mergedDict.nullId();
      } else {
        newId = mergedDict.getIdFromValue(v);
      }
      BytesUtil.writeUnsigned(newId, newIdBuf, bufOffset, mergedDict.getSizeOfId());
      c.reset(newIdBuf, bufOffset, mergedDict.getSizeOfId());
      bufOffset += mergedDict.getSizeOfId();
    }
    return value;
  }
};

代码示例来源：origin: apache/kylin

public List<T> enumeratorValues() {
  List<T> ret = Lists.newArrayListWithExpectedSize(getSize());
  for (int i = getMinId(); i <= getMaxId(); i++) {
    ret.add(getValueFromId(i));
  }
  return ret;
}

代码示例来源：origin: apache/kylin

public static void serialize(Dictionary<?> dict, OutputStream outputStream) {
  try {
    DataOutputStream out = new DataOutputStream(outputStream);
    out.writeUTF(dict.getClass().getName());
    dict.write(out);
    out.flush();
  } catch (IOException e) {
    throw new RuntimeException(e);
  }
}

代码示例来源：origin: apache/kylin

public int getSize() {
  return getMaxId() - getMinId() + 1;
}

代码示例来源：origin: apache/kylin

public ShrunkenDictionary<T> build(ValueSerializer<T> valueSerializer) {
    return new ShrunkenDictionary<>(valueSerializer, fullDict.getMinId(), fullDict.getMaxId(),
        fullDict.getSizeOfId(), fullDict.getSizeOfValue(), valueToIdMap);
  }
}

代码示例来源：origin: apache/kylin

private TupleFilter translateFunctionTupleFilter(BuiltInFunctionTupleFilter builtInFunctionTupleFilter) {
  if (!builtInFunctionTupleFilter.isValid())
    return null;
  TblColRef columnRef = builtInFunctionTupleFilter.getColumn();
  Dictionary<?> dict = dimEncMap.getDictionary(columnRef);
  if (dict == null)
    return null;
  CompareTupleFilter translated = new CompareTupleFilter(builtInFunctionTupleFilter.isReversed() ? FilterOperatorEnum.NOTIN : FilterOperatorEnum.IN);
  translated.addChild(new ColumnTupleFilter(columnRef));
  try {
    int translatedInClauseMaxSize = KylinConfig.getInstanceFromEnv().getTranslatedInClauseMaxSize();
    for (int i = dict.getMinId(); i <= dict.getMaxId(); i++) {
      Object dictVal = dict.getValueFromId(i);
      if ((Boolean) builtInFunctionTupleFilter.invokeFunction(dictVal)) {
        translated.addChild(new ConstantTupleFilter(dictVal));
        if (translated.getChildren().size() > translatedInClauseMaxSize) {
          return null;
        }
      }
    }
    logger.debug("getting a in clause with {} children", translated.getChildren().size());
  } catch (Exception e) {
    logger.debug(e.getMessage());
    return null;
  }
  return translated;
}

代码示例来源：origin: apache/kylin

@Override
public void serialize(Object value, ByteBuffer buf) {
  int id = dict.getIdFromValue(value == null ? null : value.toString(), roundingFlag);
  BytesUtil.writeUnsigned(id, dict.getSizeOfId(), buf);
}

代码示例来源：origin: org.apache.kylin/kylin-job

Dictionary<?> mergedDict = dictMgr.getDictionary(mergedCubeSegment.getDictResPath(col));
  while (sourceDict.getSizeOfValue() > newKeyBuf.length - bufOffset || mergedDict.getSizeOfValue() > newKeyBuf.length - bufOffset) {
    byte[] oldBuf = newKeyBuf;
    newKeyBuf = new byte[2 * newKeyBuf.length];
  int idInMergedDict;
  int size = sourceDict.getValueBytesFromId(idInSourceDict, newKeyBuf, bufOffset);
  if (size < 0) {
    idInMergedDict = mergedDict.nullId();
  } else {
    idInMergedDict = mergedDict.getIdFromValueBytes(newKeyBuf, bufOffset, size);
  BytesUtil.writeUnsigned(idInMergedDict, newKeyBuf, bufOffset, mergedDict.getSizeOfId());
  bufOffset += mergedDict.getSizeOfId();
} else {

代码示例来源：origin: apache/kylin

public boolean isNullId(int id) {
  int nullId = NULL_ID[getSizeOfId()];
  return (nullId & id) == nullId;
}

代码示例来源：origin: apache/kylin

/**
 * Convenient form of <code>getIdFromValue(value, 0)</code>
 */
final public int getIdFromValue(T value) throws IllegalArgumentException {
  return getIdFromValue(value, 0);
}

代码示例来源：origin: apache/kylin

@Override
public Object deserialize(ByteBuffer in) {
  int id = BytesUtil.readUnsigned(in, dict.getSizeOfId());
  return dict.getValueFromId(id);
}

代码示例来源：origin: apache/kylin

buf.append(", ");
  buf.append(s.toString()).append("=>").append(dict.getIdFromValue(s));
logger.debug("Dictionary cardinality: " + dict.getSize());
logger.debug("Dictionary builder class: " + builder.getClass().getName());
logger.debug("Dictionary class: " + dict.getClass().getName());

代码示例来源：origin: apache/kylin

DataOutputStream dos = new DataOutputStream(bos);
shrunkenDict.write(dos);
dShrunkenDict.readFields(dis);
  Assert.assertEquals(dict.getIdFromValue(value), dShrunkenDict.getIdFromValue(value));

代码示例来源：origin: apache/kylin

dict.readFields(in);
  int[] rowIndex = new int[n];
  for (int i = 0; i < n; i++) {
    rowIndex[i] = dict.getIdFromValue(row[i]);

代码示例来源：origin: apache/kylin

@Override
public String[] getRow() {
  int[] rowIndex = rowIndices.get(i);
  String[] row = new String[rowIndex.length];
  for (int x = 0; x < row.length; x++) {
    row[x] = dict.getValueFromId(rowIndex[x]);
  }
  return row;
}

代码示例来源：origin: apache/kylin

private void saveDictionaryInfo(CubeSegment cubeSeg, TblColRef col, DictionaryInfo dictInfo)
    throws IOException {
  if (dictInfo == null)
    return;
  // work on copy instead of cached objects
  CubeInstance cubeCopy = cubeSeg.getCubeInstance().latestCopyForWrite(); // get a latest copy
  CubeSegment segCopy = cubeCopy.getSegmentById(cubeSeg.getUuid());
  Dictionary<?> dict = dictInfo.getDictionaryObject();
  segCopy.putDictResPath(col, dictInfo.getResourcePath());
  segCopy.getRowkeyStats().add(new Object[] { col.getIdentity(), dict.getSize(), dict.getSizeOfId() });
  CubeUpdate update = new CubeUpdate(cubeCopy);
  update.setToUpdateSegs(segCopy);
  updateCube(update);
}

代码示例来源：origin: apache/kylin

/**
 * Returns the ID integer of given value. In case of not found
 * <p>
 * - if roundingFlag=0, throw IllegalArgumentException; <br>
 * - if roundingFlag<0, the closest smaller ID integer if exist; <br>
 * - if roundingFlag>0, the closest bigger ID integer if exist. <br>
 * <p>
 * The implementation often has cache, thus faster than the byte[] version getIdFromValueBytes()
 * 
 * @throws IllegalArgumentException
 *             if value is not found in dictionary and rounding is off;
 *             or if rounding cannot find a smaller or bigger ID
 */
final public int getIdFromValue(T value, int roundingFlag) throws IllegalArgumentException {
  if (isNullObjectForm(value))
    return nullId();
  int id = getIdFromValueImpl(value, roundingFlag);
  if (id == -1) {
    throw new IllegalArgumentException("Value : " + value + " not exists");
  }
  return id;
}

代码示例来源：origin: apache/kylin

void writeData(DataOutput out) throws IOException {
  out.writeInt(rowIndices.size());
  if (rowIndices.size() > 0) {
    int n = rowIndices.get(0).length;
    out.writeInt(n);
    if (this.useDictionary == true) {
      dict.write(out);
      for (int i = 0; i < rowIndices.size(); i++) {
        int[] row = rowIndices.get(i);
        for (int j = 0; j < n; j++) {
          out.writeInt(row[j]);
        }
      }
    } else {
      for (int i = 0; i < rowIndices.size(); i++) {
        int[] row = rowIndices.get(i);
        for (int j = 0; j < n; j++) {
          // NULL_STR is tricky, but we don't want to break the current snapshots
          out.writeUTF(dict.getValueFromId(row[j]) == null ? NULL_STR : dict.getValueFromId(row[j]));
        }
      }
    }
  }
}

代码示例来源：origin: apache/kylin

@Override
public boolean moveNext() throws IOException {
  String minValue = null;
  int curDictIndex = 0;
  // multi-merge dictionary forest
  for (int i = 0; i < dictionaryList.size(); i++) {
    Dictionary<String> dict = dictionaryList.get(i);
    if (dict == null)
      continue;
    int curKey = curKeys.get(i);
    if (curKey > dict.getMaxId())
      continue;
    String curValue = dict.getValueFromId(curKey);
    if (minValue == null || dataType.compare(minValue, curValue) > 0) {
      minValue = curValue;
      curDictIndex = i;
    }
  }
  if (minValue == null) {
    curValue = null;
    return false;
  }
  curValue = minValue;
  curKeys.set(curDictIndex, curKeys.get(curDictIndex) + 1);
  return true;
}

代码示例来源：origin: org.apache.kylin/kylin-dictionary

@Override
public boolean moveNext() throws IOException {
  if (curDictIndex < dictionaryList.size() && curKey <= curDict.getMaxId()) {
    byte[] buffer = new byte[curDict.getSizeOfValue()];
    int size = curDict.getValueBytesFromId(curKey, buffer, 0);
    curValue = Bytes.copy(buffer, 0, size);
    if (++curKey > curDict.getMaxId()) {
      if (++curDictIndex < dictionaryList.size()) {
        curDict = dictionaryList.get(curDictIndex);
        curKey = curDict.getMinId();
      }
    }
    return true;
  }
  curValue = null;
  return false;
}