Github user omalley commented on a diff in the pull request:

    https://github.com/apache/orc/pull/41#discussion_r71378147
  
    --- Diff: c++/include/orc/Reader.hh ---
    @@ -645,7 +645,72 @@ namespace orc {
       };
     
       /**
    -   * The interface for reading ORC files.
    +   * The interface for reading rows in ORC files.
    +   * This is an an abstract class that will subclassed as necessary.
    +   */
    +  class RowReader {
    +  public:
    +    virtual ~RowReader();
    +    /**
    +     * Get the selected type of the rows in the file. The file's row type
    +     * is projected down to just the selected columns. Thus, if the file's
    +     * type is struct<col0:int,col1:double,col2:string> and the selected
    +     * columns are "col0,col2" the selected type would be
    +     * struct<col0:int,col2:string>.
    +     * @return the root type
    +     */
    +    virtual const Type& getSelectedType() const = 0;
    +
    +    /**
    +     * Get the selected columns of the file.
    +     */
    +    virtual const std::vector<bool> getSelectedColumns() const = 0;
    +
    +    /**
    +     * Create a row batch for reading the selected columns of this file.
    +     * @param size the number of rows to read
    +     * @return a new ColumnVectorBatch to read into
    +     */
    +    virtual ORC_UNIQUE_PTR<ColumnVectorBatch> createRowBatch(uint64_t size
    +                                                             ) const = 0;
    +
    +    /**
    +     * Read the next row batch from the current position.
    +     * Caller must look at numElements in the row batch to determine how
    +     * many rows were read.
    +     * @param data the row batch to read into.
    +     * @return true if a non-zero number of rows were read or false if the
    +     *   end of the file was reached.
    +     */
    +    virtual bool next(ColumnVectorBatch& data) = 0;
    +
    +    /**
    +     * Get the row number of the first row in the previously read batch.
    +     * @return the row number of the previous batch.
    +     */
    +    virtual uint64_t getRowNumber() const = 0;
    +
    +    /**
    +     * Seek to a given row.
    +     * @param rowNumber the next row the reader should return
    +     */
    +    virtual void seekToRow(uint64_t rowNumber) = 0;
    +  
    +    /**
    +     * Estimate an upper bound on heap memory allocation by the Reader
    +     * based on the information in the file footer.
    +     * The bound is less tight if only few columns are read or compression 
is
    +     * used.
    +     * @param stripeIx index of the stripe to be read (if not specified,
    +     *        all stripes are considered).
    +     * @return upper bound on memory use
    +     */
    +    virtual uint64_t getMemoryUse(int stripeIx=-1) = 0;
    --- End diff --
    
    This should stay in the reader.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

Reply via email to