message Stream {
  // if you add new index stream kinds, you need to make sure to update
  // StreamName to ensure it is added to the stripe in the right area
  enum Kind {
    PRESENT = 0;
    DATA = 1;
    LENGTH = 2;
    DICTIONARY_DATA = 3;
    DICTIONARY_COUNT = 4;
    SECONDARY = 5;
    ROW_INDEX = 6;
    BLOOM_FILTER = 7;
    BLOOM_FILTER_UTF8 = 8;
    // Virtual stream kinds to allocate space for encrypted index and data.
    ENCRYPTED_INDEX = 9;
    ENCRYPTED_DATA = 10;

    // stripe statistics streams
    STRIPE_STATISTICS = 100;
    // A virtual stream kind that is used for setting the encryption IV.
    FILE_STATISTICS = 101;
  }
  optional Kind kind = 1;
  optional uint32 column = 2;
  optional uint64 length = 3;
}

message StripeFooter {
  repeated Stream streams = 1;
  repeated ColumnEncoding columns = 2;
  optional string writerTimezone = 3;
  // one for each column encryption variant
  repeated StripeEncryptionVariant encryption = 4;
}

message ColumnEncoding {
  enum Kind {
    DIRECT = 0;
    DICTIONARY = 1;
    DIRECT_V2 = 2;
    DICTIONARY_V2 = 3;
  }
  optional Kind kind = 1;
  optional uint32 dictionarySize = 2;

  // The encoding of the bloom filters for this column:
  //   0 or missing = none or original
  //   1            = ORC-135 (utc for timestamps)
  optional uint32 bloomEncoding = 3;
}

message StripeEncryptionVariant {
  repeated Stream streams = 1;
  repeated ColumnEncoding encoding = 2;
}

message StripeStatistics {
  repeated ColumnStatistics colStats = 1;
}

message Metadata {
  repeated StripeStatistics stripeStats = 1;
}

message Footer {
  optional uint64 headerLength = 1;
  optional uint64 contentLength = 2;
  repeated StripeInformation stripes = 3;
  repeated Type types = 4;
  repeated UserMetadataItem metadata = 5;
  optional uint64 numberOfRows = 6;
  repeated ColumnStatistics statistics = 7;
  optional uint32 rowIndexStride = 8;

  // Each implementation that writes ORC files should register for a code
  // 0 = ORC Java
  // 1 = ORC C++
  // 2 = Presto
  // 3 = Scritchley Go from https://github.com/scritchley/orc
  optional uint32 writer = 9;

  // information about the encryption in this file
  optional Encryption encryption = 10;
  optional CalendarKind calendar = 11;
}

message StripeInformation {
  // the global file offset of the start of the stripe
  optional uint64 offset = 1;
  // the number of bytes of index
  optional uint64 indexLength = 2;
  // the number of bytes of data
  optional uint64 dataLength = 3;
  // the number of bytes in the stripe footer
  optional uint64 footerLength = 4;
  // the number of rows in this stripe
  optional uint64 numberOfRows = 5;
  // If this is present, the reader should use this value for the encryption
  // stripe id for setting the encryption IV. Otherwise, the reader should
  // use one larger than the previous stripe's encryptStripeId.
  // For unmerged ORC files, the first stripe will use 1 and the rest of the
  // stripes won't have it set. For merged files, the stripe information
  // will be copied from their original files and thus the first stripe of
  // each of the input files will reset it to 1.
  // Note that 1 was choosen, because protobuf v3 doesn't serialize
  // primitive types that are the default (eg. 0).
  optional uint64 encryptStripeId = 6;
  // For each encryption variant, the new encrypted local key to use
  // until we find a replacement.
  repeated bytes encryptedLocalKeys = 7;
}

struct FileMetaData {
  /** Version of this file **/
  1: required i32 version
  /** 定义数据表的格式，由一个单根节点的树构成，
  * 按深度优先顺序打平保存到这个 list 里 **/
  2: required list<SchemaElement> schema;
  /** 一共包含的列数 **/
  3: required i64 num_rows
  /** 全部 RowGroups 的 MetaData  **/
  4: required list<RowGroup> row_groups
  /** 可选的 key/value MetaData **/
  5: optional list<KeyValue> key_value_metadata
  /** 写这个 Parquet 文件的签名，格式为
   * <Application> version <App Version> (build <App Build Hash>). */
  6: optional string created_by
  /** 每个 Column 里的值排 min max value 的顺序
  * 由这里的 ColumnOrder 指定 */
  7: optional list<ColumnOrder> column_orders;
  /** 文件使用的加密算法，仅对 footer 为 plaintext 的文件有效 */
  8: optional EncryptionAlgorithm encryption_algorithm
  /** 对文件 footer 加密的 key 的 metadata */ 
  9: optional binary footer_signing_key_metadata
}

/** RowGroup MetaData **/
struct RowGroup {
  /** 每个 Column Chunk 的 Metadata，按 FileMetaData 里 schema 的顺序排列 */
  1: required list<ColumnChunk> columns
  /** RowGroup 下所有未压缩数据的总字节数 **/
  2: required i64 total_byte_size
  /** RowGroup 下总的数据行数 **/
  3: required i64 num_rows
  /** 如果设置了按该顺序对 RowGroup 下所有行排序，用来排序的列是所有列中的一部分 */
  4: optional list<SortingColumn> sorting_columns
  /** RowGroup 里第一个 Page 开始的地方和文件开头之间的 offset **/
  5: optional i64 file_offset
  /** RowGroup 下所有压缩数据的总字节数 **/
  6: optional i64 total_compressed_size
  /** RowGroup 的序号 **/
  7: optional i16 ordinal
}

struct ColumnChunk {
  /** ColumnChunk 所在的文件，如果为空表示与 FileMetaData 在同一个问题件 **/
  1: optional string file_path
  /** ColumnMetaData 开头到文件开头的 offset **/
  2: required i64 file_offset
  /** ColumnChunk 的列元信息 */
  3: optional ColumnMetaData meta_data
  /** OffsetIndex 在文件里的 offset **/
  4: optional i64 offset_index_offset
  /** OffsetIndex 的大小，单位字节 **/
  5: optional i32 offset_index_length
  /** ColumnIndex 在文件里的 offset **/
  6: optional i64 column_index_offset
  /** ColumnIndex 的大小，单位字节 **/
  7: optional i32 column_index_length
  /** 加密列的加密元信息 **/
  8: optional ColumnCryptoMetaData crypto_metadata
  /** ColumnChunk 列元数据加密后的结果 **/
  9: optional binary encrypted_column_metadata
}

struct ColumnMetaData {
  /** 列的类型 **/
  1: required Type type
  /** 该列的所有编码方式 **/
  2: required list<Encoding> encodings
  /** Path in schema **/
  3: required list<string> path_in_schema
  /** 压缩方式 **/
  4: required CompressionCodec codec
  /** 该列 value 的数量 **/
  5: required i64 num_values
  /** 该 ColumnChunk 所有未压缩的数据大小 (包括 headers) **/
  6: required i64 total_uncompressed_size
  /** 该 ColumnChunk 所有压缩的数据大小 (including the headers) **/
  7: required i64 total_compressed_size
  /** 可选的 key/value metadata **/
  8: optional list<KeyValue> key_value_metadata
  /** 从文件开头到第一个 data page 之间的 offset **/
  9: required i64 data_page_offset
  /** 从文件开头到 Footer 的 index page 之间的 offset **/
  10: optional i64 index_page_offset
  /** 从文件开头到唯一的一个 dictionary page 之间的 offset **/
  11: optional i64 dictionary_page_offset
  /** 该 ColumnChunk 的列统计信息 */
  12: optional Statistics statistics;
  /** 该 ColumnChunk 下所有 page 用到的编码方式 **/
  13: optional list<PageEncodingStats> encoding_stats;
  /** 从文件开头到 bloom filter 的数据之间的 offset **/
  14: optional i64 bloom_filter_offset;
  /** bloom filter 数据的字节大小 **/
  15: optional i32 bloom_filter_length;
  /**
   * Optional statistics to help estimate total memory when converted to in-memory
   * representations. The histograms contained in these statistics can
   * also be useful in some cases for more fine-grained nullability/list length
   * filter pushdown.
   */
  16: optional SizeStatistics size_statistics;
}