parquet-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jul...@apache.org
Subject parquet-format git commit: PARQUET-450: Fix several typos in Parquet format documentation
Date Fri, 29 Jan 2016 18:30:14 GMT
Repository: parquet-format
Updated Branches:
  refs/heads/master c3682e3b3 -> 2a8f022a4


PARQUET-450: Fix several typos in Parquet format documentation

It also changes parquet.thrift location to conform to maven layout and add a link to it from
README.md

Author: Laurent Goujon <lgoujon@twitter.com>

Closes #36 from laurentgo/update-format-specification and squashes the following commits:

244c119 [Laurent Goujon] Fix several typos/errors in Parquet documentation
90a2be4 [Laurent Goujon] Fix thrift source path to match maven layout


Project: http://git-wip-us.apache.org/repos/asf/parquet-format/repo
Commit: http://git-wip-us.apache.org/repos/asf/parquet-format/commit/2a8f022a
Tree: http://git-wip-us.apache.org/repos/asf/parquet-format/tree/2a8f022a
Diff: http://git-wip-us.apache.org/repos/asf/parquet-format/diff/2a8f022a

Branch: refs/heads/master
Commit: 2a8f022a49555fa7476dbb6804c9771397f8da12
Parents: c3682e3
Author: Laurent Goujon <lgoujon@twitter.com>
Authored: Fri Jan 29 10:30:06 2016 -0800
Committer: Julien Le Dem <julien@dremio.com>
Committed: Fri Jan 29 10:30:06 2016 -0800

----------------------------------------------------------------------
 Encodings.md                   |   2 +-
 README.md                      |  27 +-
 pom.xml                        |   2 +-
 src/main/thrift/parquet.thrift | 573 ++++++++++++++++++++++++++++++++++++
 src/thrift/parquet.thrift      | 573 ------------------------------------
 5 files changed, 589 insertions(+), 588 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/parquet-format/blob/2a8f022a/Encodings.md
----------------------------------------------------------------------
diff --git a/Encodings.md b/Encodings.md
index 42961ba..c4cdf70 100644
--- a/Encodings.md
+++ b/Encodings.md
@@ -53,7 +53,7 @@ using the [RLE/Bit-Packing Hybrid](#RLE) encoding. If the dictionary grows
too b
 or number of distinct values, the encoding will fall back to the plain encoding. The dictionary
page is 
 written first, before the data pages of the column chunk.
 
-Dictionary page format: the entries in the dictionary - in dictionary order - using the [plain](#PLAIN)
enncoding.
+Dictionary page format: the entries in the dictionary - in dictionary order - using the [plain](#PLAIN)
encoding.
 
 Data page format: the bit width used to encode the entry ids stored as 1 byte (max bit width
= 32),
 followed by the values encoded using RLE/Bit packed described above (with the given bit width).

http://git-wip-us.apache.org/repos/asf/parquet-format/blob/2a8f022a/README.md
----------------------------------------------------------------------
diff --git a/README.md b/README.md
index 904bb6a..b0423e6 100644
--- a/README.md
+++ b/README.md
@@ -46,30 +46,30 @@ The `parquet-compatibility` project contains compatibility tests that
can be use
 
 ## Building
 
-Java resources can be build using `mvn package.` The current stable version should always
be available from Maven Central.
+Java resources can be build using `mvn package`. The current stable version should always
be available from Maven Central.
 
 C++ thrift resources can be generated via make.
 
 Thrift can be also code-genned into any other thrift-supported language.
 
 ## Glossary
-  - Block (hdfs block): This means a block in hdfs and the meaning is 
+  - Block (HDFS block): This means a block in HDFS and the meaning is 
     unchanged for describing this file format.  The file format is 
-    designed to work well on top of hdfs.
+    designed to work well on top of HDFS.
 
-  - File: A hdfs file that must include the metadata for the file.
+  - File: A HDFS file that must include the metadata for the file.
     It does not need to actually contain the data.
 
   - Row group: A logical horizontal partitioning of the data into rows.
     There is no physical structure that is guaranteed for a row group.
     A row group consists of a column chunk for each column in the dataset.
 
-  - Column chunk: A chunk of the data for a particular column.  These live
-    in a particular row group and is guaranteed to be contiguous in the file.
+  - Column chunk: A chunk of the data for a particular column.  They live
+    in a particular row group and are guaranteed to be contiguous in the file.
 
   - Page: Column chunks are divided up into pages.  A page is conceptually
     an indivisible unit (in terms of compression and encoding).  There can
-    be multiple page types which is interleaved in a column chunk.
+    be multiple page types which are interleaved in a column chunk.
 
 Hierarchically, a file consists of one or more row groups.  A row group
 contains exactly one column chunk per column.  Column chunks contain one or
@@ -81,7 +81,7 @@ more pages.
   - Encoding/Compression - Page
 
 ## File format
-This file and the thrift definition should be read together to understand the format.
+This file and the [thrift definition](src/main/thrift/parquet.thrift) should be read together
to understand the format.
 
     4-byte magic number "PAR1"
     <Column 1 Chunk 1 + Column Metadata>
@@ -98,13 +98,13 @@ This file and the thrift definition should be read together to understand
the fo
     ...
     <Column N Chunk M + Column Metadata>
     File Metadata
-    4-byte length in bytes of file metadata
+    4-byte length in bytes of file metadata (little endian)
     4-byte magic number "PAR1"
 
 In the above example, there are N columns in this table, split into M row 
 groups.  The file metadata contains the locations of all the column metadata 
 start locations.  More details on what is contained in the metadata can be found 
-in the thrift files.
+in the thrift definition.
 
 Metadata is written after the data to allow for single pass writing.
 
@@ -139,7 +139,7 @@ by specifying how the primitive types should be interpreted. This keeps
the set
 of primitive types to a minimum and reuses parquet's efficient encodings. For
 example, strings are stored as byte arrays (binary) with a UTF8 annotation.
 These annotations define how to further decode and interpret the data.
-Annotations are stored as a `ConvertedType` in the file metadata and are
+Annotations are stored as `ConvertedType` fields in the file metadata and are
 documented in
 [LogicalTypes.md][logical-types].
 
@@ -165,9 +165,10 @@ nothing else.
 ## Data Pages
 For data pages, the 3 pieces of information are encoded back to back, after the page
 header.  We have the 
- - definition levels data,  
  - repetition levels data, 
+ - definition levels data,  
  - encoded values.
+
 The size of specified in the header is for all 3 pieces combined.
 
 The data for the data page is always required.  The definition and repetition levels
@@ -183,7 +184,7 @@ The supported encodings are described in [Encodings.md](https://github.com/Parqu
 
 ## Column chunks
 Column chunks are composed of pages written back to back.  The pages share a common 
-header and readers can skip over page they are not interested in.  The data for the 
+header and readers can skip over pages they are not interested in.  The data for the 
 page follows the header and can be compressed and/or encoded.  The compression and 
 encoding is specified in the page metadata.
 

http://git-wip-us.apache.org/repos/asf/parquet-format/blob/2a8f022a/pom.xml
----------------------------------------------------------------------
diff --git a/pom.xml b/pom.xml
index 78578b9..d5b3b60 100644
--- a/pom.xml
+++ b/pom.xml
@@ -96,7 +96,7 @@
         <artifactId>maven-thrift-plugin</artifactId>
         <version>0.1.11</version>
         <configuration>
-          <thriftSourceRoot>src/thrift</thriftSourceRoot>
+          <thriftSourceRoot>src/main/thrift</thriftSourceRoot>
         </configuration>
         <executions>
           <execution>

http://git-wip-us.apache.org/repos/asf/parquet-format/blob/2a8f022a/src/main/thrift/parquet.thrift
----------------------------------------------------------------------
diff --git a/src/main/thrift/parquet.thrift b/src/main/thrift/parquet.thrift
new file mode 100644
index 0000000..d1b305e
--- /dev/null
+++ b/src/main/thrift/parquet.thrift
@@ -0,0 +1,573 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+/**
+ * File format description for the parquet file format
+ */
+namespace cpp parquet
+namespace java org.apache.parquet.format
+
+/**
+ * Types supported by Parquet.  These types are intended to be used in combination
+ * with the encodings to control the on disk storage format.
+ * For example INT16 is not included as a type since a good encoding of INT32
+ * would handle this.
+ */
+enum Type {
+  BOOLEAN = 0;
+  INT32 = 1;
+  INT64 = 2;
+  INT96 = 3;
+  FLOAT = 4;
+  DOUBLE = 5;
+  BYTE_ARRAY = 6;
+  FIXED_LEN_BYTE_ARRAY = 7;
+}
+
+/**
+ * Common types used by frameworks(e.g. hive, pig) using parquet.  This helps map
+ * between types in those frameworks to the base types in parquet.  This is only
+ * metadata and not needed to read or write the data.
+ */
+enum ConvertedType {
+  /** a BYTE_ARRAY actually contains UTF8 encoded chars */
+  UTF8 = 0;
+
+  /** a map is converted as an optional field containing a repeated key/value pair */
+  MAP = 1;
+
+  /** a key/value pair is converted into a group of two fields */
+  MAP_KEY_VALUE = 2;
+
+  /** a list is converted into an optional field containing a repeated field for its
+   * values */
+  LIST = 3;
+
+  /** an enum is converted into a binary field */
+  ENUM = 4;
+
+  /**
+   * A decimal value.
+   *
+   * This may be used to annotate binary or fixed primitive types. The
+   * underlying byte array stores the unscaled value encoded as two's
+   * complement using big-endian byte order (the most significant byte is the
+   * zeroth element). The value of the decimal is the value * 10^{-scale}.
+   *
+   * This must be accompanied by a (maximum) precision and a scale in the
+   * SchemaElement. The precision specifies the number of digits in the decimal
+   * and the scale stores the location of the decimal point. For example 1.23
+   * would have precision 3 (3 total digits) and scale 2 (the decimal point is
+   * 2 digits over).
+   */
+  DECIMAL = 5;
+
+  /**
+   * A Date
+   *
+   * Stored as days since Unix epoch, encoded as the INT32 physical type.
+   *
+   */
+  DATE = 6; 
+
+  /** 
+   * A time 
+   *
+   * The total number of milliseconds since midnight.  The value is stored 
+   * as an INT32 physical type.
+   */
+  TIME_MILLIS = 7;
+
+  /**
+   * A time.
+   *
+   * The total number of microseconds since midnight.  The value is stored as
+   * an INT64 physical type.
+   */
+  TIME_MICROS = 8;
+
+  /**
+   * A date/time combination
+   * 
+   * Date and time recorded as milliseconds since the Unix epoch.  Recorded as
+   * a physical type of INT64.
+   */
+  TIMESTAMP_MILLIS = 9; 
+
+  /**
+   * A date/time combination
+   *
+   * Date and time recorded as microseconds since the Unix epoch.  The value is
+   * stored as an INT64 physical type.
+   */
+  TIMESTAMP_MICROS = 10;
+
+
+  /** 
+   * An unsigned integer value.  
+   * 
+   * The number describes the maximum number of meainful data bits in 
+   * the stored value. 8, 16 and 32 bit values are stored using the 
+   * INT32 physical type.  64 bit values are stored using the INT64
+   * physical type.
+   *
+   */
+  UINT_8 = 11;
+  UINT_16 = 12;
+  UINT_32 = 13;
+  UINT_64 = 14;
+
+  /**
+   * A signed integer value.
+   *
+   * The number describes the maximum number of meainful data bits in
+   * the stored value. 8, 16 and 32 bit values are stored using the
+   * INT32 physical type.  64 bit values are stored using the INT64
+   * physical type.
+   *
+   */
+  INT_8 = 15;
+  INT_16 = 16;
+  INT_32 = 17;
+  INT_64 = 18;
+
+  /** 
+   * An embedded JSON document
+   * 
+   * A JSON document embedded within a single UTF8 column.
+   */
+  JSON = 19;
+
+  /** 
+   * An embedded BSON document
+   * 
+   * A BSON document embedded within a single BINARY column. 
+   */
+  BSON = 20;
+
+  /**
+   * An interval of time
+   * 
+   * This type annotates data stored as a FIXED_LEN_BYTE_ARRAY of length 12
+   * This data is composed of three separate little endian unsigned
+   * integers.  Each stores a component of a duration of time.  The first
+   * integer identifies the number of months associated with the duration,
+   * the second identifies the number of days associated with the duration
+   * and the third identifies the number of milliseconds associated with 
+   * the provided duration.  This duration of time is independent of any
+   * particular timezone or date.
+   */
+  INTERVAL = 21;
+  
+}
+
+/**
+ * Representation of Schemas
+ */
+enum FieldRepetitionType {
+  /** This field is required (can not be null) and each record has exactly 1 value. */
+  REQUIRED = 0;
+
+  /** The field is optional (can be null) and each record has 0 or 1 values. */
+  OPTIONAL = 1;
+
+  /** The field is repeated and can contain 0 or more values */
+  REPEATED = 2;
+}
+
+/**
+ * Statistics per row group and per page
+ * All fields are optional.
+ */
+struct Statistics {
+   /** min and max value of the column, encoded in PLAIN encoding */
+   1: optional binary max;
+   2: optional binary min;
+   /** count of null value in the column */
+   3: optional i64 null_count;
+   /** count of distinct values occurring */
+   4: optional i64 distinct_count;
+}
+
+/**
+ * Represents a element inside a schema definition.
+ *  - if it is a group (inner node) then type is undefined and num_children is defined
+ *  - if it is a primitive type (leaf) then type is defined and num_children is undefined
+ * the nodes are listed in depth first traversal order.
+ */
+struct SchemaElement {
+  /** Data type for this field. Not set if the current element is a non-leaf node */
+  1: optional Type type;
+
+  /** If type is FIXED_LEN_BYTE_ARRAY, this is the byte length of the vales.
+   * Otherwise, if specified, this is the maximum bit length to store any of the values.
+   * (e.g. a low cardinality INT col could have this set to 3).  Note that this is
+   * in the schema, and therefore fixed for the entire file.
+   */
+  2: optional i32 type_length;
+
+  /** repetition of the field. The root of the schema does not have a repetition_type.
+   * All other nodes must have one */
+  3: optional FieldRepetitionType repetition_type;
+
+  /** Name of the field in the schema */
+  4: required string name;
+
+  /** Nested fields.  Since thrift does not support nested fields,
+   * the nesting is flattened to a single list by a depth-first traversal.
+   * The children count is used to construct the nested relationship.
+   * This field is not set when the element is a primitive type
+   */
+  5: optional i32 num_children;
+
+  /** When the schema is the result of a conversion from another model
+   * Used to record the original type to help with cross conversion.
+   */
+  6: optional ConvertedType converted_type;
+
+  /** Used when this column contains decimal data.
+   * See the DECIMAL converted type for more details.
+   */
+  7: optional i32 scale
+  8: optional i32 precision
+
+  /** When the original schema supports field ids, this will save the
+   * original field id in the parquet schema
+   */
+  9: optional i32 field_id;
+
+}
+
+/**
+ * Encodings supported by Parquet.  Not all encodings are valid for all types.  These
+ * enums are also used to specify the encoding of definition and repetition levels.
+ * See the accompanying doc for the details of the more complicated encodings.
+ */
+enum Encoding {
+  /** Default encoding.
+   * BOOLEAN - 1 bit per value. 0 is false; 1 is true.
+   * INT32 - 4 bytes per value.  Stored as little-endian.
+   * INT64 - 8 bytes per value.  Stored as little-endian.
+   * FLOAT - 4 bytes per value.  IEEE. Stored as little-endian.
+   * DOUBLE - 8 bytes per value.  IEEE. Stored as little-endian.
+   * BYTE_ARRAY - 4 byte length stored as little endian, followed by bytes.
+   * FIXED_LEN_BYTE_ARRAY - Just the bytes.
+   */
+  PLAIN = 0;
+
+  /** Group VarInt encoding for INT32/INT64.
+   * This encoding is deprecated. It was never used
+   */
+  //  GROUP_VAR_INT = 1;
+
+  /**
+   * Deprecated: Dictionary encoding. The values in the dictionary are encoded in the
+   * plain type.
+   * in a data page use RLE_DICTIONARY instead.
+   * in a Dictionary page use PLAIN instead
+   */
+  PLAIN_DICTIONARY = 2;
+
+  /** Group packed run length encoding. Usable for definition/reptition levels
+   * encoding and Booleans (on one bit: 0 is false; 1 is true.)
+   */
+  RLE = 3;
+
+  /** Bit packed encoding.  This can only be used if the data has a known max
+   * width.  Usable for definition/repetition levels encoding.
+   */
+  BIT_PACKED = 4;
+
+  /** Delta encoding for integers. This can be used for int columns and works best
+   * on sorted data
+   */
+  DELTA_BINARY_PACKED = 5;
+
+  /** Encoding for byte arrays to separate the length values and the data. The lengths
+   * are encoded using DELTA_BINARY_PACKED
+   */
+  DELTA_LENGTH_BYTE_ARRAY = 6;
+
+  /** Incremental-encoded byte array. Prefix lengths are encoded using DELTA_BINARY_PACKED.
+   * Suffixes are stored as delta length byte arrays.
+   */
+  DELTA_BYTE_ARRAY = 7;
+
+  /** Dictionary encoding: the ids are encoded using the RLE encoding
+   */
+  RLE_DICTIONARY = 8;
+}
+
+/**
+ * Supported compression algorithms.
+ */
+enum CompressionCodec {
+  UNCOMPRESSED = 0;
+  SNAPPY = 1;
+  GZIP = 2;
+  LZO = 3;
+}
+
+enum PageType {
+  DATA_PAGE = 0;
+  INDEX_PAGE = 1;
+  DICTIONARY_PAGE = 2;
+  DATA_PAGE_V2 = 3;
+}
+
+/** Data page header */
+struct DataPageHeader {
+  /** Number of values, including NULLs, in this data page. **/
+  1: required i32 num_values
+
+  /** Encoding used for this data page **/
+  2: required Encoding encoding
+
+  /** Encoding used for definition levels **/
+  3: required Encoding definition_level_encoding;
+
+  /** Encoding used for repetition levels **/
+  4: required Encoding repetition_level_encoding;
+
+  /** Optional statistics for the data in this page**/
+  5: optional Statistics statistics;
+}
+
+struct IndexPageHeader {
+  /** TODO: **/
+}
+
+struct DictionaryPageHeader {
+  /** Number of values in the dictionary **/
+  1: required i32 num_values;
+
+  /** Encoding using this dictionary page **/
+  2: required Encoding encoding
+
+  /** If true, the entries in the dictionary are sorted in ascending order **/
+  3: optional bool is_sorted;
+}
+
+/**
+ * New page format alowing reading levels without decompressing the data
+ * Repetition and definition levels are uncompressed
+ * The remaining section containing the data is compressed if is_compressed is true
+ **/
+struct DataPageHeaderV2 {
+  /** Number of values, including NULLs, in this data page. **/
+  1: required i32 num_values
+  /** Number of NULL values, in this data page.
+      Number of non-null = num_values - num_nulls which is also the number of values in the
data section **/
+  2: required i32 num_nulls
+  /** Number of rows in this data page. which means pages change on record boundaries (r
= 0) **/
+  3: required i32 num_rows
+  /** Encoding used for data in this page **/
+  4: required Encoding encoding
+
+  // repetition levels and definition levels are always using RLE (without size in it)
+
+  /** length of the repetition levels */
+  5: required i32 definition_levels_byte_length;
+  /** length of the definition levels */
+  6: required i32 repetition_levels_byte_length;
+
+  /**  whether the values are compressed.
+  Which means the section of the page between
+  definition_levels_byte_length + repetition_levels_byte_length + 1 and compressed_page_size
(included)
+  is compressed with the compression_codec.
+  If missing it is considered compressed */
+  7: optional bool is_compressed = 1;
+
+  /** optional statistics for this column chunk */
+  8: optional Statistics statistics;
+}
+
+struct PageHeader {
+  /** the type of the page: indicates which of the *_header fields is set **/
+  1: required PageType type
+
+  /** Uncompressed page size in bytes (not including this header) **/
+  2: required i32 uncompressed_page_size
+
+  /** Compressed page size in bytes (not including this header) **/
+  3: required i32 compressed_page_size
+
+  /** 32bit crc for the data below. This allows for disabling checksumming in HDFS
+   *  if only a few pages needs to be read
+   **/
+  4: optional i32 crc
+
+  // Headers for page specific data.  One only will be set.
+  5: optional DataPageHeader data_page_header;
+  6: optional IndexPageHeader index_page_header;
+  7: optional DictionaryPageHeader dictionary_page_header;
+  8: optional DataPageHeaderV2 data_page_header_v2;
+}
+
+/**
+ * Wrapper struct to store key values
+ */
+ struct KeyValue {
+  1: required string key
+  2: optional string value
+}
+
+/**
+ * Wrapper struct to specify sort order
+ */
+struct SortingColumn {
+  /** The column index (in this row group) **/
+  1: required i32 column_idx
+
+  /** If true, indicates this column is sorted in descending order. **/
+  2: required bool descending
+
+  /** If true, nulls will come before non-null values, otherwise,
+   * nulls go at the end. */
+  3: required bool nulls_first
+}
+
+/**
+ * statistics of a given page type and encoding
+ */
+struct PageEncodingStats {
+
+  /** the page type (data/dic/...) **/
+  1: required PageType page_type;
+
+  /** encoding of the page **/
+  2: required Encoding encoding;
+
+  /** number of pages of this type with this encoding **/
+  3: required i32 count;
+
+}
+
+/**
+ * Description for column metadata
+ */
+struct ColumnMetaData {
+  /** Type of this column **/
+  1: required Type type
+
+  /** Set of all encodings used for this column. The purpose is to validate
+   * whether we can decode those pages. **/
+  2: required list<Encoding> encodings
+
+  /** Path in schema **/
+  3: required list<string> path_in_schema
+
+  /** Compression codec **/
+  4: required CompressionCodec codec
+
+  /** Number of values in this column **/
+  5: required i64 num_values
+
+  /** total byte size of all uncompressed pages in this column chunk (including the headers)
**/
+  6: required i64 total_uncompressed_size
+
+  /** total byte size of all compressed pages in this column chunk (including the headers)
**/
+  7: required i64 total_compressed_size
+
+  /** Optional key/value metadata **/
+  8: optional list<KeyValue> key_value_metadata
+
+  /** Byte offset from beginning of file to first data page **/
+  9: required i64 data_page_offset
+
+  /** Byte offset from beginning of file to root index page **/
+  10: optional i64 index_page_offset
+
+  /** Byte offset from the beginning of file to first (only) dictionary page **/
+  11: optional i64 dictionary_page_offset
+
+  /** optional statistics for this column chunk */
+  12: optional Statistics statistics;
+
+  /** Set of all encodings used for pages in this column chunk.
+   * This information can be used to determine if all data pages are
+   * dictionary encoded for example **/
+  13: optional list<PageEncodingStats> encoding_stats;
+}
+
+struct ColumnChunk {
+  /** File where column data is stored.  If not set, assumed to be same file as
+    * metadata.  This path is relative to the current file.
+    **/
+  1: optional string file_path
+
+  /** Byte offset in file_path to the ColumnMetaData **/
+  2: required i64 file_offset
+
+  /** Column metadata for this chunk. This is the same content as what is at
+   * file_path/file_offset.  Having it here has it replicated in the file
+   * metadata.
+   **/
+  3: optional ColumnMetaData meta_data
+}
+
+struct RowGroup {
+  /** Metadata for each column chunk in this row group.
+   * This list must have the same order as the SchemaElement list in FileMetaData.
+   **/
+  1: required list<ColumnChunk> columns
+
+  /** Total byte size of all the uncompressed column data in this row group **/
+  2: required i64 total_byte_size
+
+  /** Number of rows in this row group **/
+  3: required i64 num_rows
+
+  /** If set, specifies a sort ordering of the rows in this RowGroup.
+   * The sorting columns can be a subset of all the columns.
+   */
+  4: optional list<SortingColumn> sorting_columns
+}
+
+/**
+ * Description for file metadata
+ */
+struct FileMetaData {
+  /** Version of this file **/
+  1: required i32 version
+
+  /** Parquet schema for this file.  This schema contains metadata for all the columns.
+   * The schema is represented as a tree with a single root.  The nodes of the tree
+   * are flattened to a list by doing a depth-first traversal.
+   * The column metadata contains the path in the schema for that column which can be
+   * used to map columns to nodes in the schema.
+   * The first element is the root **/
+  2: required list<SchemaElement> schema;
+
+  /** Number of rows in this file **/
+  3: required i64 num_rows
+
+  /** Row groups in this file **/
+  4: required list<RowGroup> row_groups
+
+  /** Optional key/value metadata **/
+  5: optional list<KeyValue> key_value_metadata
+
+  /** String for application that wrote this file.  This should be in the format
+   * <Application> version <App Version> (build <App Build Hash>).
+   * e.g. impala version 1.0 (build 6cf94d29b2b7115df4de2c06e2ab4326d721eb55)
+   **/
+  6: optional string created_by
+}
+

http://git-wip-us.apache.org/repos/asf/parquet-format/blob/2a8f022a/src/thrift/parquet.thrift
----------------------------------------------------------------------
diff --git a/src/thrift/parquet.thrift b/src/thrift/parquet.thrift
deleted file mode 100644
index d1b305e..0000000
--- a/src/thrift/parquet.thrift
+++ /dev/null
@@ -1,573 +0,0 @@
-/**
- * Licensed to the Apache Software Foundation (ASF) under one
- * or more contributor license agreements.  See the NOTICE file
- * distributed with this work for additional information
- * regarding copyright ownership.  The ASF licenses this file
- * to you under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance
- * with the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing,
- * software distributed under the License is distributed on an
- * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
- * KIND, either express or implied.  See the License for the
- * specific language governing permissions and limitations
- * under the License.
- */
-
-/**
- * File format description for the parquet file format
- */
-namespace cpp parquet
-namespace java org.apache.parquet.format
-
-/**
- * Types supported by Parquet.  These types are intended to be used in combination
- * with the encodings to control the on disk storage format.
- * For example INT16 is not included as a type since a good encoding of INT32
- * would handle this.
- */
-enum Type {
-  BOOLEAN = 0;
-  INT32 = 1;
-  INT64 = 2;
-  INT96 = 3;
-  FLOAT = 4;
-  DOUBLE = 5;
-  BYTE_ARRAY = 6;
-  FIXED_LEN_BYTE_ARRAY = 7;
-}
-
-/**
- * Common types used by frameworks(e.g. hive, pig) using parquet.  This helps map
- * between types in those frameworks to the base types in parquet.  This is only
- * metadata and not needed to read or write the data.
- */
-enum ConvertedType {
-  /** a BYTE_ARRAY actually contains UTF8 encoded chars */
-  UTF8 = 0;
-
-  /** a map is converted as an optional field containing a repeated key/value pair */
-  MAP = 1;
-
-  /** a key/value pair is converted into a group of two fields */
-  MAP_KEY_VALUE = 2;
-
-  /** a list is converted into an optional field containing a repeated field for its
-   * values */
-  LIST = 3;
-
-  /** an enum is converted into a binary field */
-  ENUM = 4;
-
-  /**
-   * A decimal value.
-   *
-   * This may be used to annotate binary or fixed primitive types. The
-   * underlying byte array stores the unscaled value encoded as two's
-   * complement using big-endian byte order (the most significant byte is the
-   * zeroth element). The value of the decimal is the value * 10^{-scale}.
-   *
-   * This must be accompanied by a (maximum) precision and a scale in the
-   * SchemaElement. The precision specifies the number of digits in the decimal
-   * and the scale stores the location of the decimal point. For example 1.23
-   * would have precision 3 (3 total digits) and scale 2 (the decimal point is
-   * 2 digits over).
-   */
-  DECIMAL = 5;
-
-  /**
-   * A Date
-   *
-   * Stored as days since Unix epoch, encoded as the INT32 physical type.
-   *
-   */
-  DATE = 6; 
-
-  /** 
-   * A time 
-   *
-   * The total number of milliseconds since midnight.  The value is stored 
-   * as an INT32 physical type.
-   */
-  TIME_MILLIS = 7;
-
-  /**
-   * A time.
-   *
-   * The total number of microseconds since midnight.  The value is stored as
-   * an INT64 physical type.
-   */
-  TIME_MICROS = 8;
-
-  /**
-   * A date/time combination
-   * 
-   * Date and time recorded as milliseconds since the Unix epoch.  Recorded as
-   * a physical type of INT64.
-   */
-  TIMESTAMP_MILLIS = 9; 
-
-  /**
-   * A date/time combination
-   *
-   * Date and time recorded as microseconds since the Unix epoch.  The value is
-   * stored as an INT64 physical type.
-   */
-  TIMESTAMP_MICROS = 10;
-
-
-  /** 
-   * An unsigned integer value.  
-   * 
-   * The number describes the maximum number of meainful data bits in 
-   * the stored value. 8, 16 and 32 bit values are stored using the 
-   * INT32 physical type.  64 bit values are stored using the INT64
-   * physical type.
-   *
-   */
-  UINT_8 = 11;
-  UINT_16 = 12;
-  UINT_32 = 13;
-  UINT_64 = 14;
-
-  /**
-   * A signed integer value.
-   *
-   * The number describes the maximum number of meainful data bits in
-   * the stored value. 8, 16 and 32 bit values are stored using the
-   * INT32 physical type.  64 bit values are stored using the INT64
-   * physical type.
-   *
-   */
-  INT_8 = 15;
-  INT_16 = 16;
-  INT_32 = 17;
-  INT_64 = 18;
-
-  /** 
-   * An embedded JSON document
-   * 
-   * A JSON document embedded within a single UTF8 column.
-   */
-  JSON = 19;
-
-  /** 
-   * An embedded BSON document
-   * 
-   * A BSON document embedded within a single BINARY column. 
-   */
-  BSON = 20;
-
-  /**
-   * An interval of time
-   * 
-   * This type annotates data stored as a FIXED_LEN_BYTE_ARRAY of length 12
-   * This data is composed of three separate little endian unsigned
-   * integers.  Each stores a component of a duration of time.  The first
-   * integer identifies the number of months associated with the duration,
-   * the second identifies the number of days associated with the duration
-   * and the third identifies the number of milliseconds associated with 
-   * the provided duration.  This duration of time is independent of any
-   * particular timezone or date.
-   */
-  INTERVAL = 21;
-  
-}
-
-/**
- * Representation of Schemas
- */
-enum FieldRepetitionType {
-  /** This field is required (can not be null) and each record has exactly 1 value. */
-  REQUIRED = 0;
-
-  /** The field is optional (can be null) and each record has 0 or 1 values. */
-  OPTIONAL = 1;
-
-  /** The field is repeated and can contain 0 or more values */
-  REPEATED = 2;
-}
-
-/**
- * Statistics per row group and per page
- * All fields are optional.
- */
-struct Statistics {
-   /** min and max value of the column, encoded in PLAIN encoding */
-   1: optional binary max;
-   2: optional binary min;
-   /** count of null value in the column */
-   3: optional i64 null_count;
-   /** count of distinct values occurring */
-   4: optional i64 distinct_count;
-}
-
-/**
- * Represents a element inside a schema definition.
- *  - if it is a group (inner node) then type is undefined and num_children is defined
- *  - if it is a primitive type (leaf) then type is defined and num_children is undefined
- * the nodes are listed in depth first traversal order.
- */
-struct SchemaElement {
-  /** Data type for this field. Not set if the current element is a non-leaf node */
-  1: optional Type type;
-
-  /** If type is FIXED_LEN_BYTE_ARRAY, this is the byte length of the vales.
-   * Otherwise, if specified, this is the maximum bit length to store any of the values.
-   * (e.g. a low cardinality INT col could have this set to 3).  Note that this is
-   * in the schema, and therefore fixed for the entire file.
-   */
-  2: optional i32 type_length;
-
-  /** repetition of the field. The root of the schema does not have a repetition_type.
-   * All other nodes must have one */
-  3: optional FieldRepetitionType repetition_type;
-
-  /** Name of the field in the schema */
-  4: required string name;
-
-  /** Nested fields.  Since thrift does not support nested fields,
-   * the nesting is flattened to a single list by a depth-first traversal.
-   * The children count is used to construct the nested relationship.
-   * This field is not set when the element is a primitive type
-   */
-  5: optional i32 num_children;
-
-  /** When the schema is the result of a conversion from another model
-   * Used to record the original type to help with cross conversion.
-   */
-  6: optional ConvertedType converted_type;
-
-  /** Used when this column contains decimal data.
-   * See the DECIMAL converted type for more details.
-   */
-  7: optional i32 scale
-  8: optional i32 precision
-
-  /** When the original schema supports field ids, this will save the
-   * original field id in the parquet schema
-   */
-  9: optional i32 field_id;
-
-}
-
-/**
- * Encodings supported by Parquet.  Not all encodings are valid for all types.  These
- * enums are also used to specify the encoding of definition and repetition levels.
- * See the accompanying doc for the details of the more complicated encodings.
- */
-enum Encoding {
-  /** Default encoding.
-   * BOOLEAN - 1 bit per value. 0 is false; 1 is true.
-   * INT32 - 4 bytes per value.  Stored as little-endian.
-   * INT64 - 8 bytes per value.  Stored as little-endian.
-   * FLOAT - 4 bytes per value.  IEEE. Stored as little-endian.
-   * DOUBLE - 8 bytes per value.  IEEE. Stored as little-endian.
-   * BYTE_ARRAY - 4 byte length stored as little endian, followed by bytes.
-   * FIXED_LEN_BYTE_ARRAY - Just the bytes.
-   */
-  PLAIN = 0;
-
-  /** Group VarInt encoding for INT32/INT64.
-   * This encoding is deprecated. It was never used
-   */
-  //  GROUP_VAR_INT = 1;
-
-  /**
-   * Deprecated: Dictionary encoding. The values in the dictionary are encoded in the
-   * plain type.
-   * in a data page use RLE_DICTIONARY instead.
-   * in a Dictionary page use PLAIN instead
-   */
-  PLAIN_DICTIONARY = 2;
-
-  /** Group packed run length encoding. Usable for definition/reptition levels
-   * encoding and Booleans (on one bit: 0 is false; 1 is true.)
-   */
-  RLE = 3;
-
-  /** Bit packed encoding.  This can only be used if the data has a known max
-   * width.  Usable for definition/repetition levels encoding.
-   */
-  BIT_PACKED = 4;
-
-  /** Delta encoding for integers. This can be used for int columns and works best
-   * on sorted data
-   */
-  DELTA_BINARY_PACKED = 5;
-
-  /** Encoding for byte arrays to separate the length values and the data. The lengths
-   * are encoded using DELTA_BINARY_PACKED
-   */
-  DELTA_LENGTH_BYTE_ARRAY = 6;
-
-  /** Incremental-encoded byte array. Prefix lengths are encoded using DELTA_BINARY_PACKED.
-   * Suffixes are stored as delta length byte arrays.
-   */
-  DELTA_BYTE_ARRAY = 7;
-
-  /** Dictionary encoding: the ids are encoded using the RLE encoding
-   */
-  RLE_DICTIONARY = 8;
-}
-
-/**
- * Supported compression algorithms.
- */
-enum CompressionCodec {
-  UNCOMPRESSED = 0;
-  SNAPPY = 1;
-  GZIP = 2;
-  LZO = 3;
-}
-
-enum PageType {
-  DATA_PAGE = 0;
-  INDEX_PAGE = 1;
-  DICTIONARY_PAGE = 2;
-  DATA_PAGE_V2 = 3;
-}
-
-/** Data page header */
-struct DataPageHeader {
-  /** Number of values, including NULLs, in this data page. **/
-  1: required i32 num_values
-
-  /** Encoding used for this data page **/
-  2: required Encoding encoding
-
-  /** Encoding used for definition levels **/
-  3: required Encoding definition_level_encoding;
-
-  /** Encoding used for repetition levels **/
-  4: required Encoding repetition_level_encoding;
-
-  /** Optional statistics for the data in this page**/
-  5: optional Statistics statistics;
-}
-
-struct IndexPageHeader {
-  /** TODO: **/
-}
-
-struct DictionaryPageHeader {
-  /** Number of values in the dictionary **/
-  1: required i32 num_values;
-
-  /** Encoding using this dictionary page **/
-  2: required Encoding encoding
-
-  /** If true, the entries in the dictionary are sorted in ascending order **/
-  3: optional bool is_sorted;
-}
-
-/**
- * New page format alowing reading levels without decompressing the data
- * Repetition and definition levels are uncompressed
- * The remaining section containing the data is compressed if is_compressed is true
- **/
-struct DataPageHeaderV2 {
-  /** Number of values, including NULLs, in this data page. **/
-  1: required i32 num_values
-  /** Number of NULL values, in this data page.
-      Number of non-null = num_values - num_nulls which is also the number of values in the
data section **/
-  2: required i32 num_nulls
-  /** Number of rows in this data page. which means pages change on record boundaries (r
= 0) **/
-  3: required i32 num_rows
-  /** Encoding used for data in this page **/
-  4: required Encoding encoding
-
-  // repetition levels and definition levels are always using RLE (without size in it)
-
-  /** length of the repetition levels */
-  5: required i32 definition_levels_byte_length;
-  /** length of the definition levels */
-  6: required i32 repetition_levels_byte_length;
-
-  /**  whether the values are compressed.
-  Which means the section of the page between
-  definition_levels_byte_length + repetition_levels_byte_length + 1 and compressed_page_size
(included)
-  is compressed with the compression_codec.
-  If missing it is considered compressed */
-  7: optional bool is_compressed = 1;
-
-  /** optional statistics for this column chunk */
-  8: optional Statistics statistics;
-}
-
-struct PageHeader {
-  /** the type of the page: indicates which of the *_header fields is set **/
-  1: required PageType type
-
-  /** Uncompressed page size in bytes (not including this header) **/
-  2: required i32 uncompressed_page_size
-
-  /** Compressed page size in bytes (not including this header) **/
-  3: required i32 compressed_page_size
-
-  /** 32bit crc for the data below. This allows for disabling checksumming in HDFS
-   *  if only a few pages needs to be read
-   **/
-  4: optional i32 crc
-
-  // Headers for page specific data.  One only will be set.
-  5: optional DataPageHeader data_page_header;
-  6: optional IndexPageHeader index_page_header;
-  7: optional DictionaryPageHeader dictionary_page_header;
-  8: optional DataPageHeaderV2 data_page_header_v2;
-}
-
-/**
- * Wrapper struct to store key values
- */
- struct KeyValue {
-  1: required string key
-  2: optional string value
-}
-
-/**
- * Wrapper struct to specify sort order
- */
-struct SortingColumn {
-  /** The column index (in this row group) **/
-  1: required i32 column_idx
-
-  /** If true, indicates this column is sorted in descending order. **/
-  2: required bool descending
-
-  /** If true, nulls will come before non-null values, otherwise,
-   * nulls go at the end. */
-  3: required bool nulls_first
-}
-
-/**
- * statistics of a given page type and encoding
- */
-struct PageEncodingStats {
-
-  /** the page type (data/dic/...) **/
-  1: required PageType page_type;
-
-  /** encoding of the page **/
-  2: required Encoding encoding;
-
-  /** number of pages of this type with this encoding **/
-  3: required i32 count;
-
-}
-
-/**
- * Description for column metadata
- */
-struct ColumnMetaData {
-  /** Type of this column **/
-  1: required Type type
-
-  /** Set of all encodings used for this column. The purpose is to validate
-   * whether we can decode those pages. **/
-  2: required list<Encoding> encodings
-
-  /** Path in schema **/
-  3: required list<string> path_in_schema
-
-  /** Compression codec **/
-  4: required CompressionCodec codec
-
-  /** Number of values in this column **/
-  5: required i64 num_values
-
-  /** total byte size of all uncompressed pages in this column chunk (including the headers)
**/
-  6: required i64 total_uncompressed_size
-
-  /** total byte size of all compressed pages in this column chunk (including the headers)
**/
-  7: required i64 total_compressed_size
-
-  /** Optional key/value metadata **/
-  8: optional list<KeyValue> key_value_metadata
-
-  /** Byte offset from beginning of file to first data page **/
-  9: required i64 data_page_offset
-
-  /** Byte offset from beginning of file to root index page **/
-  10: optional i64 index_page_offset
-
-  /** Byte offset from the beginning of file to first (only) dictionary page **/
-  11: optional i64 dictionary_page_offset
-
-  /** optional statistics for this column chunk */
-  12: optional Statistics statistics;
-
-  /** Set of all encodings used for pages in this column chunk.
-   * This information can be used to determine if all data pages are
-   * dictionary encoded for example **/
-  13: optional list<PageEncodingStats> encoding_stats;
-}
-
-struct ColumnChunk {
-  /** File where column data is stored.  If not set, assumed to be same file as
-    * metadata.  This path is relative to the current file.
-    **/
-  1: optional string file_path
-
-  /** Byte offset in file_path to the ColumnMetaData **/
-  2: required i64 file_offset
-
-  /** Column metadata for this chunk. This is the same content as what is at
-   * file_path/file_offset.  Having it here has it replicated in the file
-   * metadata.
-   **/
-  3: optional ColumnMetaData meta_data
-}
-
-struct RowGroup {
-  /** Metadata for each column chunk in this row group.
-   * This list must have the same order as the SchemaElement list in FileMetaData.
-   **/
-  1: required list<ColumnChunk> columns
-
-  /** Total byte size of all the uncompressed column data in this row group **/
-  2: required i64 total_byte_size
-
-  /** Number of rows in this row group **/
-  3: required i64 num_rows
-
-  /** If set, specifies a sort ordering of the rows in this RowGroup.
-   * The sorting columns can be a subset of all the columns.
-   */
-  4: optional list<SortingColumn> sorting_columns
-}
-
-/**
- * Description for file metadata
- */
-struct FileMetaData {
-  /** Version of this file **/
-  1: required i32 version
-
-  /** Parquet schema for this file.  This schema contains metadata for all the columns.
-   * The schema is represented as a tree with a single root.  The nodes of the tree
-   * are flattened to a list by doing a depth-first traversal.
-   * The column metadata contains the path in the schema for that column which can be
-   * used to map columns to nodes in the schema.
-   * The first element is the root **/
-  2: required list<SchemaElement> schema;
-
-  /** Number of rows in this file **/
-  3: required i64 num_rows
-
-  /** Row groups in this file **/
-  4: required list<RowGroup> row_groups
-
-  /** Optional key/value metadata **/
-  5: optional list<KeyValue> key_value_metadata
-
-  /** String for application that wrote this file.  This should be in the format
-   * <Application> version <App Version> (build <App Build Hash>).
-   * e.g. impala version 1.0 (build 6cf94d29b2b7115df4de2c06e2ab4326d721eb55)
-   **/
-  6: optional string created_by
-}
-


Mime
View raw message