Page History

public abstract class IntermediateDataFormat<T> {
  protected volatile T data;
  public int hashCode() {
    return data.hashCode();
  }

  /**
   * SetGet one row of data.
 If validate is*
 set to true,* the@return data- isOne validated
row of data, *represented againstin the schema.internal/native format of
   *
   * @param data - A single rowthe ofintermediate data toformat be movedimplementation.
   */
  public voidT setDatagetData(T data) {
    this.data =return data;
  }
  /**
   * GetSet one row of data.
 If validate *
is set to *true, @returnthe -data Oneis rowvalidated
 of data, represented* inagainst the internal/native format ofschema.
   *
   * @param data - A single therow intermediateof data formatto implementationbe moved.
   */
  public void setData(T getData(data) {
    this.data return= data;
  }
  /**
   * Get one row of data as CSV text.
 Use SqoopDataUtils *
for reading and *writing
 @return - String* representinginto the datasqoop inspecified CSV, accordingtext toformat thefor "FROM" schema.
   * No schema conversion is done on textData, to keep it as "high performance" option.
   */
  public abstract String getTextData();
  /**
   * Set one row of data as CSV.
   *
   */
  public abstract void setTextData(String text);
  /**
   * Get one row of data as an Object array.
   *each {@link #ColumnType} field in the row
   * Why a "native" internal format and then return CSV text too?
   * Imagine a connector that moves data from a system that stores data as a
   * serialization format called FooFormat. If I also need the data to be
   * written into HDFS as FooFormat, the additional cycles burnt in converting
   * the FooFormat to text and back is useless - so using the sqoop specified
   * CSV text format saves those extra cycles
   * <p/>
   * Most fast access mechanisms, like mysqldump or pgsqldump write the data
   * out as CSV, and most often the source data is also represented as CSV
   * - so having a minimal CSV support is mandated for all IDF, so we can easily read the
   * data out as text and write as text.
   * <p/>
   * @return - String representing the data in CSV text format.
   */
  public abstract String getCSVTextData();
  /**
   * Set one row of data as CSV.
   *
   */
  public abstract void setCSVTextData(String csvText);
  /**
   * Get one row of data as an Object array. Sqoop uses defined object representation
   * for each column type. For instance org.joda.time to represent date.Use SqoopDataUtils
   * for reading and writing into the sqoop specified object format
   * for each {@link #ColumnType} field in the row
   * </p>
   * @return - String representing the data as an Object array
   * If FROM and TO schema exist, we will use SchemaMatcher to get the data according to "TO" schema
   */
  public abstract Object[] getObjectData();
  /**
   * Set one row of data as an Object array.
   *
   */
  public abstract void setObjectData(Object[] data);
  /**
   * Set the schema for serializing/de-serializing  data.
   *
   * @param schema - the schema used for serializing/de-serializing  data
   */
  public abstract void setSchema(Schema schema);
  /**
   * Serialize the fields of this object to <code>out</code>.
   *
   * @param out <code>DataOuput</code> to serialize this object into.
   * @throws IOException
   */
  public abstract void write(DataOutput out) throws IOException;
  /**
   * Deserialize the fields of this object from <code>in</code>.
   *
   * <p>For efficiency, implementations should attempt to re-use storage in the
   * existing object where possible.</p>
   *
   * @param in <code>DataInput</code> to deseriablize this object from.
   * @throws IOException
   */
  public abstract void read(DataInput in) throws IOException;
}

/**
 * Schema represents the data fields that are transferred between {@link #From} and {@link #To}
 */
public class Schema {
  /**
   * Name of the schema, usually a table name.
   */
  private String name;
  /**
   * Optional note.
   */
  private String note;
  /**
   * Creation date.
   */
  private Date creationDate;
  /**
   * Columns associated with the schema.
   */
  private List<Column> columns;
  /**
   * Helper set for quick column name lookups.
   */
  private Set<String> columNames;

/**
 * All {@link #Column} types supported by Sqoop.
 */
public enum ColumnType {
  ARRAY,
  BINARY,
  BIT,
  DATE,
  DATE_TIME,
  DECIMAL,
  ENUM,
  FIXED_POINT,
  FLOATING_POINT,
  MAP,
  SET,
  TEXT,
  TIME,
  UNKNOWN,
  ;
}