You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@parquet.apache.org by ju...@apache.org on 2016/02/19 00:54:35 UTC
[1/3] parquet-cpp git commit: PARQUET-468: Use thirdparty Thrift
compiler to compile parquet.thrift at make time
Repository: parquet-cpp
Updated Branches:
refs/heads/master 17a204555 -> fed331727
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/parquet_types.h
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/parquet_types.h b/src/parquet/thrift/parquet_types.h
deleted file mode 100644
index 466daf4..0000000
--- a/src/parquet/thrift/parquet_types.h
+++ /dev/null
@@ -1,1210 +0,0 @@
-/**
- * Autogenerated by Thrift Compiler (0.9.0)
- *
- * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING
- * @generated
- */
-#ifndef parquet_TYPES_H
-#define parquet_TYPES_H
-
-#include <thrift/Thrift.h>
-#include <thrift/TApplicationException.h>
-#include <thrift/protocol/TProtocol.h>
-#include <thrift/transport/TTransport.h>
-
-
-
-namespace parquet {
-
-struct Type {
- enum type {
- BOOLEAN = 0,
- INT32 = 1,
- INT64 = 2,
- INT96 = 3,
- FLOAT = 4,
- DOUBLE = 5,
- BYTE_ARRAY = 6,
- FIXED_LEN_BYTE_ARRAY = 7
- };
-};
-
-extern const std::map<int, const char*> _Type_VALUES_TO_NAMES;
-
-struct ConvertedType {
- enum type {
- UTF8 = 0,
- MAP = 1,
- MAP_KEY_VALUE = 2,
- LIST = 3,
- ENUM = 4,
- DECIMAL = 5,
- DATE = 6,
- TIME_MILLIS = 7,
- TIMESTAMP_MILLIS = 9,
- UINT_8 = 11,
- UINT_16 = 12,
- UINT_32 = 13,
- UINT_64 = 14,
- INT_8 = 15,
- INT_16 = 16,
- INT_32 = 17,
- INT_64 = 18,
- JSON = 19,
- BSON = 20,
- INTERVAL = 21
- };
-};
-
-extern const std::map<int, const char*> _ConvertedType_VALUES_TO_NAMES;
-
-struct FieldRepetitionType {
- enum type {
- REQUIRED = 0,
- OPTIONAL = 1,
- REPEATED = 2
- };
-};
-
-extern const std::map<int, const char*> _FieldRepetitionType_VALUES_TO_NAMES;
-
-struct Encoding {
- enum type {
- PLAIN = 0,
- PLAIN_DICTIONARY = 2,
- RLE = 3,
- BIT_PACKED = 4,
- DELTA_BINARY_PACKED = 5,
- DELTA_LENGTH_BYTE_ARRAY = 6,
- DELTA_BYTE_ARRAY = 7,
- RLE_DICTIONARY = 8
- };
-};
-
-extern const std::map<int, const char*> _Encoding_VALUES_TO_NAMES;
-
-struct CompressionCodec {
- enum type {
- UNCOMPRESSED = 0,
- SNAPPY = 1,
- GZIP = 2,
- LZO = 3
- };
-};
-
-extern const std::map<int, const char*> _CompressionCodec_VALUES_TO_NAMES;
-
-struct PageType {
- enum type {
- DATA_PAGE = 0,
- INDEX_PAGE = 1,
- DICTIONARY_PAGE = 2,
- DATA_PAGE_V2 = 3
- };
-};
-
-extern const std::map<int, const char*> _PageType_VALUES_TO_NAMES;
-
-typedef struct _Statistics__isset {
- _Statistics__isset() : max(false), min(false), null_count(false), distinct_count(false) {}
- bool max;
- bool min;
- bool null_count;
- bool distinct_count;
-} _Statistics__isset;
-
-class Statistics {
- public:
-
- static const char* ascii_fingerprint; // = "CE004821871820DD79A8FD98BB101F6D";
- static const uint8_t binary_fingerprint[16]; // = {0xCE,0x00,0x48,0x21,0x87,0x18,0x20,0xDD,0x79,0xA8,0xFD,0x98,0xBB,0x10,0x1F,0x6D};
-
- Statistics() : max(), min(), null_count(0), distinct_count(0) {
- }
-
- virtual ~Statistics() throw() {}
-
- std::string max;
- std::string min;
- int64_t null_count;
- int64_t distinct_count;
-
- _Statistics__isset __isset;
-
- void __set_max(const std::string& val) {
- max = val;
- __isset.max = true;
- }
-
- void __set_min(const std::string& val) {
- min = val;
- __isset.min = true;
- }
-
- void __set_null_count(const int64_t val) {
- null_count = val;
- __isset.null_count = true;
- }
-
- void __set_distinct_count(const int64_t val) {
- distinct_count = val;
- __isset.distinct_count = true;
- }
-
- bool operator == (const Statistics & rhs) const
- {
- if (__isset.max != rhs.__isset.max)
- return false;
- else if (__isset.max && !(max == rhs.max))
- return false;
- if (__isset.min != rhs.__isset.min)
- return false;
- else if (__isset.min && !(min == rhs.min))
- return false;
- if (__isset.null_count != rhs.__isset.null_count)
- return false;
- else if (__isset.null_count && !(null_count == rhs.null_count))
- return false;
- if (__isset.distinct_count != rhs.__isset.distinct_count)
- return false;
- else if (__isset.distinct_count && !(distinct_count == rhs.distinct_count))
- return false;
- return true;
- }
- bool operator != (const Statistics &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const Statistics & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(Statistics &a, Statistics &b);
-
-typedef struct _SchemaElement__isset {
- _SchemaElement__isset() : type(false), type_length(false), repetition_type(false), num_children(false), converted_type(false), scale(false), precision(false), field_id(false) {}
- bool type;
- bool type_length;
- bool repetition_type;
- bool num_children;
- bool converted_type;
- bool scale;
- bool precision;
- bool field_id;
-} _SchemaElement__isset;
-
-class SchemaElement {
- public:
-
- static const char* ascii_fingerprint; // = "22DC89BFD9E48E604F01FB8CFDFB8229";
- static const uint8_t binary_fingerprint[16]; // = {0x22,0xDC,0x89,0xBF,0xD9,0xE4,0x8E,0x60,0x4F,0x01,0xFB,0x8C,0xFD,0xFB,0x82,0x29};
-
- SchemaElement() : type((Type::type)0), type_length(0), repetition_type((FieldRepetitionType::type)0), name(), num_children(0), converted_type((ConvertedType::type)0), scale(0), precision(0), field_id(0) {
- }
-
- virtual ~SchemaElement() throw() {}
-
- Type::type type;
- int32_t type_length;
- FieldRepetitionType::type repetition_type;
- std::string name;
- int32_t num_children;
- ConvertedType::type converted_type;
- int32_t scale;
- int32_t precision;
- int32_t field_id;
-
- _SchemaElement__isset __isset;
-
- void __set_type(const Type::type val) {
- type = val;
- __isset.type = true;
- }
-
- void __set_type_length(const int32_t val) {
- type_length = val;
- __isset.type_length = true;
- }
-
- void __set_repetition_type(const FieldRepetitionType::type val) {
- repetition_type = val;
- __isset.repetition_type = true;
- }
-
- void __set_name(const std::string& val) {
- name = val;
- }
-
- void __set_num_children(const int32_t val) {
- num_children = val;
- __isset.num_children = true;
- }
-
- void __set_converted_type(const ConvertedType::type val) {
- converted_type = val;
- __isset.converted_type = true;
- }
-
- void __set_scale(const int32_t val) {
- scale = val;
- __isset.scale = true;
- }
-
- void __set_precision(const int32_t val) {
- precision = val;
- __isset.precision = true;
- }
-
- void __set_field_id(const int32_t val) {
- field_id = val;
- __isset.field_id = true;
- }
-
- bool operator == (const SchemaElement & rhs) const
- {
- if (__isset.type != rhs.__isset.type)
- return false;
- else if (__isset.type && !(type == rhs.type))
- return false;
- if (__isset.type_length != rhs.__isset.type_length)
- return false;
- else if (__isset.type_length && !(type_length == rhs.type_length))
- return false;
- if (__isset.repetition_type != rhs.__isset.repetition_type)
- return false;
- else if (__isset.repetition_type && !(repetition_type == rhs.repetition_type))
- return false;
- if (!(name == rhs.name))
- return false;
- if (__isset.num_children != rhs.__isset.num_children)
- return false;
- else if (__isset.num_children && !(num_children == rhs.num_children))
- return false;
- if (__isset.converted_type != rhs.__isset.converted_type)
- return false;
- else if (__isset.converted_type && !(converted_type == rhs.converted_type))
- return false;
- if (__isset.scale != rhs.__isset.scale)
- return false;
- else if (__isset.scale && !(scale == rhs.scale))
- return false;
- if (__isset.precision != rhs.__isset.precision)
- return false;
- else if (__isset.precision && !(precision == rhs.precision))
- return false;
- if (__isset.field_id != rhs.__isset.field_id)
- return false;
- else if (__isset.field_id && !(field_id == rhs.field_id))
- return false;
- return true;
- }
- bool operator != (const SchemaElement &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const SchemaElement & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(SchemaElement &a, SchemaElement &b);
-
-typedef struct _DataPageHeader__isset {
- _DataPageHeader__isset() : statistics(false) {}
- bool statistics;
-} _DataPageHeader__isset;
-
-class DataPageHeader {
- public:
-
- static const char* ascii_fingerprint; // = "5FC1792B0483E9C984475384165040B1";
- static const uint8_t binary_fingerprint[16]; // = {0x5F,0xC1,0x79,0x2B,0x04,0x83,0xE9,0xC9,0x84,0x47,0x53,0x84,0x16,0x50,0x40,0xB1};
-
- DataPageHeader() : num_values(0), encoding((Encoding::type)0), definition_level_encoding((Encoding::type)0), repetition_level_encoding((Encoding::type)0) {
- }
-
- virtual ~DataPageHeader() throw() {}
-
- int32_t num_values;
- Encoding::type encoding;
- Encoding::type definition_level_encoding;
- Encoding::type repetition_level_encoding;
- Statistics statistics;
-
- _DataPageHeader__isset __isset;
-
- void __set_num_values(const int32_t val) {
- num_values = val;
- }
-
- void __set_encoding(const Encoding::type val) {
- encoding = val;
- }
-
- void __set_definition_level_encoding(const Encoding::type val) {
- definition_level_encoding = val;
- }
-
- void __set_repetition_level_encoding(const Encoding::type val) {
- repetition_level_encoding = val;
- }
-
- void __set_statistics(const Statistics& val) {
- statistics = val;
- __isset.statistics = true;
- }
-
- bool operator == (const DataPageHeader & rhs) const
- {
- if (!(num_values == rhs.num_values))
- return false;
- if (!(encoding == rhs.encoding))
- return false;
- if (!(definition_level_encoding == rhs.definition_level_encoding))
- return false;
- if (!(repetition_level_encoding == rhs.repetition_level_encoding))
- return false;
- if (__isset.statistics != rhs.__isset.statistics)
- return false;
- else if (__isset.statistics && !(statistics == rhs.statistics))
- return false;
- return true;
- }
- bool operator != (const DataPageHeader &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const DataPageHeader & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(DataPageHeader &a, DataPageHeader &b);
-
-
-class IndexPageHeader {
- public:
-
- static const char* ascii_fingerprint; // = "99914B932BD37A50B983C5E7C90AE93B";
- static const uint8_t binary_fingerprint[16]; // = {0x99,0x91,0x4B,0x93,0x2B,0xD3,0x7A,0x50,0xB9,0x83,0xC5,0xE7,0xC9,0x0A,0xE9,0x3B};
-
- IndexPageHeader() {
- }
-
- virtual ~IndexPageHeader() throw() {}
-
-
- bool operator == (const IndexPageHeader & /* rhs */) const
- {
- return true;
- }
- bool operator != (const IndexPageHeader &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const IndexPageHeader & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(IndexPageHeader &a, IndexPageHeader &b);
-
-typedef struct _DictionaryPageHeader__isset {
- _DictionaryPageHeader__isset() : is_sorted(false) {}
- bool is_sorted;
-} _DictionaryPageHeader__isset;
-
-class DictionaryPageHeader {
- public:
-
- static const char* ascii_fingerprint; // = "B149E4528254D495610C22AE4BD539C5";
- static const uint8_t binary_fingerprint[16]; // = {0xB1,0x49,0xE4,0x52,0x82,0x54,0xD4,0x95,0x61,0x0C,0x22,0xAE,0x4B,0xD5,0x39,0xC5};
-
- DictionaryPageHeader() : num_values(0), encoding((Encoding::type)0), is_sorted(0) {
- }
-
- virtual ~DictionaryPageHeader() throw() {}
-
- int32_t num_values;
- Encoding::type encoding;
- bool is_sorted;
-
- _DictionaryPageHeader__isset __isset;
-
- void __set_num_values(const int32_t val) {
- num_values = val;
- }
-
- void __set_encoding(const Encoding::type val) {
- encoding = val;
- }
-
- void __set_is_sorted(const bool val) {
- is_sorted = val;
- __isset.is_sorted = true;
- }
-
- bool operator == (const DictionaryPageHeader & rhs) const
- {
- if (!(num_values == rhs.num_values))
- return false;
- if (!(encoding == rhs.encoding))
- return false;
- if (__isset.is_sorted != rhs.__isset.is_sorted)
- return false;
- else if (__isset.is_sorted && !(is_sorted == rhs.is_sorted))
- return false;
- return true;
- }
- bool operator != (const DictionaryPageHeader &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const DictionaryPageHeader & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(DictionaryPageHeader &a, DictionaryPageHeader &b);
-
-typedef struct _DataPageHeaderV2__isset {
- _DataPageHeaderV2__isset() : is_compressed(true), statistics(false) {}
- bool is_compressed;
- bool statistics;
-} _DataPageHeaderV2__isset;
-
-class DataPageHeaderV2 {
- public:
-
- static const char* ascii_fingerprint; // = "69FF2F6BD1A443440D5E46ABA5A3A919";
- static const uint8_t binary_fingerprint[16]; // = {0x69,0xFF,0x2F,0x6B,0xD1,0xA4,0x43,0x44,0x0D,0x5E,0x46,0xAB,0xA5,0xA3,0xA9,0x19};
-
- DataPageHeaderV2() : num_values(0), num_nulls(0), num_rows(0), encoding((Encoding::type)0), definition_levels_byte_length(0), repetition_levels_byte_length(0), is_compressed(true) {
- }
-
- virtual ~DataPageHeaderV2() throw() {}
-
- int32_t num_values;
- int32_t num_nulls;
- int32_t num_rows;
- Encoding::type encoding;
- int32_t definition_levels_byte_length;
- int32_t repetition_levels_byte_length;
- bool is_compressed;
- Statistics statistics;
-
- _DataPageHeaderV2__isset __isset;
-
- void __set_num_values(const int32_t val) {
- num_values = val;
- }
-
- void __set_num_nulls(const int32_t val) {
- num_nulls = val;
- }
-
- void __set_num_rows(const int32_t val) {
- num_rows = val;
- }
-
- void __set_encoding(const Encoding::type val) {
- encoding = val;
- }
-
- void __set_definition_levels_byte_length(const int32_t val) {
- definition_levels_byte_length = val;
- }
-
- void __set_repetition_levels_byte_length(const int32_t val) {
- repetition_levels_byte_length = val;
- }
-
- void __set_is_compressed(const bool val) {
- is_compressed = val;
- __isset.is_compressed = true;
- }
-
- void __set_statistics(const Statistics& val) {
- statistics = val;
- __isset.statistics = true;
- }
-
- bool operator == (const DataPageHeaderV2 & rhs) const
- {
- if (!(num_values == rhs.num_values))
- return false;
- if (!(num_nulls == rhs.num_nulls))
- return false;
- if (!(num_rows == rhs.num_rows))
- return false;
- if (!(encoding == rhs.encoding))
- return false;
- if (!(definition_levels_byte_length == rhs.definition_levels_byte_length))
- return false;
- if (!(repetition_levels_byte_length == rhs.repetition_levels_byte_length))
- return false;
- if (__isset.is_compressed != rhs.__isset.is_compressed)
- return false;
- else if (__isset.is_compressed && !(is_compressed == rhs.is_compressed))
- return false;
- if (__isset.statistics != rhs.__isset.statistics)
- return false;
- else if (__isset.statistics && !(statistics == rhs.statistics))
- return false;
- return true;
- }
- bool operator != (const DataPageHeaderV2 &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const DataPageHeaderV2 & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(DataPageHeaderV2 &a, DataPageHeaderV2 &b);
-
-typedef struct _PageHeader__isset {
- _PageHeader__isset() : crc(false), data_page_header(false), index_page_header(false), dictionary_page_header(false), data_page_header_v2(false) {}
- bool crc;
- bool data_page_header;
- bool index_page_header;
- bool dictionary_page_header;
- bool data_page_header_v2;
-} _PageHeader__isset;
-
-class PageHeader {
- public:
-
- static const char* ascii_fingerprint; // = "B5BD2BDF3756C883A58B30B9C9F204A0";
- static const uint8_t binary_fingerprint[16]; // = {0xB5,0xBD,0x2B,0xDF,0x37,0x56,0xC8,0x83,0xA5,0x8B,0x30,0xB9,0xC9,0xF2,0x04,0xA0};
-
- PageHeader() : type((PageType::type)0), uncompressed_page_size(0), compressed_page_size(0), crc(0) {
- }
-
- virtual ~PageHeader() throw() {}
-
- PageType::type type;
- int32_t uncompressed_page_size;
- int32_t compressed_page_size;
- int32_t crc;
- DataPageHeader data_page_header;
- IndexPageHeader index_page_header;
- DictionaryPageHeader dictionary_page_header;
- DataPageHeaderV2 data_page_header_v2;
-
- _PageHeader__isset __isset;
-
- void __set_type(const PageType::type val) {
- type = val;
- }
-
- void __set_uncompressed_page_size(const int32_t val) {
- uncompressed_page_size = val;
- }
-
- void __set_compressed_page_size(const int32_t val) {
- compressed_page_size = val;
- }
-
- void __set_crc(const int32_t val) {
- crc = val;
- __isset.crc = true;
- }
-
- void __set_data_page_header(const DataPageHeader& val) {
- data_page_header = val;
- __isset.data_page_header = true;
- }
-
- void __set_index_page_header(const IndexPageHeader& val) {
- index_page_header = val;
- __isset.index_page_header = true;
- }
-
- void __set_dictionary_page_header(const DictionaryPageHeader& val) {
- dictionary_page_header = val;
- __isset.dictionary_page_header = true;
- }
-
- void __set_data_page_header_v2(const DataPageHeaderV2& val) {
- data_page_header_v2 = val;
- __isset.data_page_header_v2 = true;
- }
-
- bool operator == (const PageHeader & rhs) const
- {
- if (!(type == rhs.type))
- return false;
- if (!(uncompressed_page_size == rhs.uncompressed_page_size))
- return false;
- if (!(compressed_page_size == rhs.compressed_page_size))
- return false;
- if (__isset.crc != rhs.__isset.crc)
- return false;
- else if (__isset.crc && !(crc == rhs.crc))
- return false;
- if (__isset.data_page_header != rhs.__isset.data_page_header)
- return false;
- else if (__isset.data_page_header && !(data_page_header == rhs.data_page_header))
- return false;
- if (__isset.index_page_header != rhs.__isset.index_page_header)
- return false;
- else if (__isset.index_page_header && !(index_page_header == rhs.index_page_header))
- return false;
- if (__isset.dictionary_page_header != rhs.__isset.dictionary_page_header)
- return false;
- else if (__isset.dictionary_page_header && !(dictionary_page_header == rhs.dictionary_page_header))
- return false;
- if (__isset.data_page_header_v2 != rhs.__isset.data_page_header_v2)
- return false;
- else if (__isset.data_page_header_v2 && !(data_page_header_v2 == rhs.data_page_header_v2))
- return false;
- return true;
- }
- bool operator != (const PageHeader &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const PageHeader & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(PageHeader &a, PageHeader &b);
-
-typedef struct _KeyValue__isset {
- _KeyValue__isset() : value(false) {}
- bool value;
-} _KeyValue__isset;
-
-class KeyValue {
- public:
-
- static const char* ascii_fingerprint; // = "5B708A954C550ECA9C1A49D3C5CAFAB9";
- static const uint8_t binary_fingerprint[16]; // = {0x5B,0x70,0x8A,0x95,0x4C,0x55,0x0E,0xCA,0x9C,0x1A,0x49,0xD3,0xC5,0xCA,0xFA,0xB9};
-
- KeyValue() : key(), value() {
- }
-
- virtual ~KeyValue() throw() {}
-
- std::string key;
- std::string value;
-
- _KeyValue__isset __isset;
-
- void __set_key(const std::string& val) {
- key = val;
- }
-
- void __set_value(const std::string& val) {
- value = val;
- __isset.value = true;
- }
-
- bool operator == (const KeyValue & rhs) const
- {
- if (!(key == rhs.key))
- return false;
- if (__isset.value != rhs.__isset.value)
- return false;
- else if (__isset.value && !(value == rhs.value))
- return false;
- return true;
- }
- bool operator != (const KeyValue &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const KeyValue & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(KeyValue &a, KeyValue &b);
-
-
-class SortingColumn {
- public:
-
- static const char* ascii_fingerprint; // = "F079C2D58A783AD90F9BE05D10DBBC6F";
- static const uint8_t binary_fingerprint[16]; // = {0xF0,0x79,0xC2,0xD5,0x8A,0x78,0x3A,0xD9,0x0F,0x9B,0xE0,0x5D,0x10,0xDB,0xBC,0x6F};
-
- SortingColumn() : column_idx(0), descending(0), nulls_first(0) {
- }
-
- virtual ~SortingColumn() throw() {}
-
- int32_t column_idx;
- bool descending;
- bool nulls_first;
-
- void __set_column_idx(const int32_t val) {
- column_idx = val;
- }
-
- void __set_descending(const bool val) {
- descending = val;
- }
-
- void __set_nulls_first(const bool val) {
- nulls_first = val;
- }
-
- bool operator == (const SortingColumn & rhs) const
- {
- if (!(column_idx == rhs.column_idx))
- return false;
- if (!(descending == rhs.descending))
- return false;
- if (!(nulls_first == rhs.nulls_first))
- return false;
- return true;
- }
- bool operator != (const SortingColumn &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const SortingColumn & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(SortingColumn &a, SortingColumn &b);
-
-
-class PageEncodingStats {
- public:
-
- static const char* ascii_fingerprint; // = "5F1BEE04836FAA3055D3EE2492AE44FB";
- static const uint8_t binary_fingerprint[16]; // = {0x5F,0x1B,0xEE,0x04,0x83,0x6F,0xAA,0x30,0x55,0xD3,0xEE,0x24,0x92,0xAE,0x44,0xFB};
-
- PageEncodingStats() : page_type((PageType::type)0), encoding((Encoding::type)0), count(0) {
- }
-
- virtual ~PageEncodingStats() throw() {}
-
- PageType::type page_type;
- Encoding::type encoding;
- int32_t count;
-
- void __set_page_type(const PageType::type val) {
- page_type = val;
- }
-
- void __set_encoding(const Encoding::type val) {
- encoding = val;
- }
-
- void __set_count(const int32_t val) {
- count = val;
- }
-
- bool operator == (const PageEncodingStats & rhs) const
- {
- if (!(page_type == rhs.page_type))
- return false;
- if (!(encoding == rhs.encoding))
- return false;
- if (!(count == rhs.count))
- return false;
- return true;
- }
- bool operator != (const PageEncodingStats &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const PageEncodingStats & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(PageEncodingStats &a, PageEncodingStats &b);
-
-typedef struct _ColumnMetaData__isset {
- _ColumnMetaData__isset() : key_value_metadata(false), index_page_offset(false), dictionary_page_offset(false), statistics(false), encoding_stats(false) {}
- bool key_value_metadata;
- bool index_page_offset;
- bool dictionary_page_offset;
- bool statistics;
- bool encoding_stats;
-} _ColumnMetaData__isset;
-
-class ColumnMetaData {
- public:
-
- static const char* ascii_fingerprint; // = "AEE7317B6DB9719FE828388D537DBD71";
- static const uint8_t binary_fingerprint[16]; // = {0xAE,0xE7,0x31,0x7B,0x6D,0xB9,0x71,0x9F,0xE8,0x28,0x38,0x8D,0x53,0x7D,0xBD,0x71};
-
- ColumnMetaData() : type((Type::type)0), codec((CompressionCodec::type)0), num_values(0), total_uncompressed_size(0), total_compressed_size(0), data_page_offset(0), index_page_offset(0), dictionary_page_offset(0) {
- }
-
- virtual ~ColumnMetaData() throw() {}
-
- Type::type type;
- std::vector<Encoding::type> encodings;
- std::vector<std::string> path_in_schema;
- CompressionCodec::type codec;
- int64_t num_values;
- int64_t total_uncompressed_size;
- int64_t total_compressed_size;
- std::vector<KeyValue> key_value_metadata;
- int64_t data_page_offset;
- int64_t index_page_offset;
- int64_t dictionary_page_offset;
- Statistics statistics;
- std::vector<PageEncodingStats> encoding_stats;
-
- _ColumnMetaData__isset __isset;
-
- void __set_type(const Type::type val) {
- type = val;
- }
-
- void __set_encodings(const std::vector<Encoding::type> & val) {
- encodings = val;
- }
-
- void __set_path_in_schema(const std::vector<std::string> & val) {
- path_in_schema = val;
- }
-
- void __set_codec(const CompressionCodec::type val) {
- codec = val;
- }
-
- void __set_num_values(const int64_t val) {
- num_values = val;
- }
-
- void __set_total_uncompressed_size(const int64_t val) {
- total_uncompressed_size = val;
- }
-
- void __set_total_compressed_size(const int64_t val) {
- total_compressed_size = val;
- }
-
- void __set_key_value_metadata(const std::vector<KeyValue> & val) {
- key_value_metadata = val;
- __isset.key_value_metadata = true;
- }
-
- void __set_data_page_offset(const int64_t val) {
- data_page_offset = val;
- }
-
- void __set_index_page_offset(const int64_t val) {
- index_page_offset = val;
- __isset.index_page_offset = true;
- }
-
- void __set_dictionary_page_offset(const int64_t val) {
- dictionary_page_offset = val;
- __isset.dictionary_page_offset = true;
- }
-
- void __set_statistics(const Statistics& val) {
- statistics = val;
- __isset.statistics = true;
- }
-
- void __set_encoding_stats(const std::vector<PageEncodingStats> & val) {
- encoding_stats = val;
- __isset.encoding_stats = true;
- }
-
- bool operator == (const ColumnMetaData & rhs) const
- {
- if (!(type == rhs.type))
- return false;
- if (!(encodings == rhs.encodings))
- return false;
- if (!(path_in_schema == rhs.path_in_schema))
- return false;
- if (!(codec == rhs.codec))
- return false;
- if (!(num_values == rhs.num_values))
- return false;
- if (!(total_uncompressed_size == rhs.total_uncompressed_size))
- return false;
- if (!(total_compressed_size == rhs.total_compressed_size))
- return false;
- if (__isset.key_value_metadata != rhs.__isset.key_value_metadata)
- return false;
- else if (__isset.key_value_metadata && !(key_value_metadata == rhs.key_value_metadata))
- return false;
- if (!(data_page_offset == rhs.data_page_offset))
- return false;
- if (__isset.index_page_offset != rhs.__isset.index_page_offset)
- return false;
- else if (__isset.index_page_offset && !(index_page_offset == rhs.index_page_offset))
- return false;
- if (__isset.dictionary_page_offset != rhs.__isset.dictionary_page_offset)
- return false;
- else if (__isset.dictionary_page_offset && !(dictionary_page_offset == rhs.dictionary_page_offset))
- return false;
- if (__isset.statistics != rhs.__isset.statistics)
- return false;
- else if (__isset.statistics && !(statistics == rhs.statistics))
- return false;
- if (__isset.encoding_stats != rhs.__isset.encoding_stats)
- return false;
- else if (__isset.encoding_stats && !(encoding_stats == rhs.encoding_stats))
- return false;
- return true;
- }
- bool operator != (const ColumnMetaData &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const ColumnMetaData & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(ColumnMetaData &a, ColumnMetaData &b);
-
-typedef struct _ColumnChunk__isset {
- _ColumnChunk__isset() : file_path(false), meta_data(false) {}
- bool file_path;
- bool meta_data;
-} _ColumnChunk__isset;
-
-class ColumnChunk {
- public:
-
- static const char* ascii_fingerprint; // = "F9F2DFFF1A7805AEF05AA10B23AF3108";
- static const uint8_t binary_fingerprint[16]; // = {0xF9,0xF2,0xDF,0xFF,0x1A,0x78,0x05,0xAE,0xF0,0x5A,0xA1,0x0B,0x23,0xAF,0x31,0x08};
-
- ColumnChunk() : file_path(), file_offset(0) {
- }
-
- virtual ~ColumnChunk() throw() {}
-
- std::string file_path;
- int64_t file_offset;
- ColumnMetaData meta_data;
-
- _ColumnChunk__isset __isset;
-
- void __set_file_path(const std::string& val) {
- file_path = val;
- __isset.file_path = true;
- }
-
- void __set_file_offset(const int64_t val) {
- file_offset = val;
- }
-
- void __set_meta_data(const ColumnMetaData& val) {
- meta_data = val;
- __isset.meta_data = true;
- }
-
- bool operator == (const ColumnChunk & rhs) const
- {
- if (__isset.file_path != rhs.__isset.file_path)
- return false;
- else if (__isset.file_path && !(file_path == rhs.file_path))
- return false;
- if (!(file_offset == rhs.file_offset))
- return false;
- if (__isset.meta_data != rhs.__isset.meta_data)
- return false;
- else if (__isset.meta_data && !(meta_data == rhs.meta_data))
- return false;
- return true;
- }
- bool operator != (const ColumnChunk &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const ColumnChunk & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(ColumnChunk &a, ColumnChunk &b);
-
-typedef struct _RowGroup__isset {
- _RowGroup__isset() : sorting_columns(false) {}
- bool sorting_columns;
-} _RowGroup__isset;
-
-class RowGroup {
- public:
-
- static const char* ascii_fingerprint; // = "9BCFCB6790B06809B46424957993EDA6";
- static const uint8_t binary_fingerprint[16]; // = {0x9B,0xCF,0xCB,0x67,0x90,0xB0,0x68,0x09,0xB4,0x64,0x24,0x95,0x79,0x93,0xED,0xA6};
-
- RowGroup() : total_byte_size(0), num_rows(0) {
- }
-
- virtual ~RowGroup() throw() {}
-
- std::vector<ColumnChunk> columns;
- int64_t total_byte_size;
- int64_t num_rows;
- std::vector<SortingColumn> sorting_columns;
-
- _RowGroup__isset __isset;
-
- void __set_columns(const std::vector<ColumnChunk> & val) {
- columns = val;
- }
-
- void __set_total_byte_size(const int64_t val) {
- total_byte_size = val;
- }
-
- void __set_num_rows(const int64_t val) {
- num_rows = val;
- }
-
- void __set_sorting_columns(const std::vector<SortingColumn> & val) {
- sorting_columns = val;
- __isset.sorting_columns = true;
- }
-
- bool operator == (const RowGroup & rhs) const
- {
- if (!(columns == rhs.columns))
- return false;
- if (!(total_byte_size == rhs.total_byte_size))
- return false;
- if (!(num_rows == rhs.num_rows))
- return false;
- if (__isset.sorting_columns != rhs.__isset.sorting_columns)
- return false;
- else if (__isset.sorting_columns && !(sorting_columns == rhs.sorting_columns))
- return false;
- return true;
- }
- bool operator != (const RowGroup &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const RowGroup & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(RowGroup &a, RowGroup &b);
-
-typedef struct _FileMetaData__isset {
- _FileMetaData__isset() : key_value_metadata(false), created_by(false) {}
- bool key_value_metadata;
- bool created_by;
-} _FileMetaData__isset;
-
-class FileMetaData {
- public:
-
- static const char* ascii_fingerprint; // = "D76119B1A4F2B4F404F095255FBDBD9A";
- static const uint8_t binary_fingerprint[16]; // = {0xD7,0x61,0x19,0xB1,0xA4,0xF2,0xB4,0xF4,0x04,0xF0,0x95,0x25,0x5F,0xBD,0xBD,0x9A};
-
- FileMetaData() : version(0), num_rows(0), created_by() {
- }
-
- virtual ~FileMetaData() throw() {}
-
- int32_t version;
- std::vector<SchemaElement> schema;
- int64_t num_rows;
- std::vector<RowGroup> row_groups;
- std::vector<KeyValue> key_value_metadata;
- std::string created_by;
-
- _FileMetaData__isset __isset;
-
- void __set_version(const int32_t val) {
- version = val;
- }
-
- void __set_schema(const std::vector<SchemaElement> & val) {
- schema = val;
- }
-
- void __set_num_rows(const int64_t val) {
- num_rows = val;
- }
-
- void __set_row_groups(const std::vector<RowGroup> & val) {
- row_groups = val;
- }
-
- void __set_key_value_metadata(const std::vector<KeyValue> & val) {
- key_value_metadata = val;
- __isset.key_value_metadata = true;
- }
-
- void __set_created_by(const std::string& val) {
- created_by = val;
- __isset.created_by = true;
- }
-
- bool operator == (const FileMetaData & rhs) const
- {
- if (!(version == rhs.version))
- return false;
- if (!(schema == rhs.schema))
- return false;
- if (!(num_rows == rhs.num_rows))
- return false;
- if (!(row_groups == rhs.row_groups))
- return false;
- if (__isset.key_value_metadata != rhs.__isset.key_value_metadata)
- return false;
- else if (__isset.key_value_metadata && !(key_value_metadata == rhs.key_value_metadata))
- return false;
- if (__isset.created_by != rhs.__isset.created_by)
- return false;
- else if (__isset.created_by && !(created_by == rhs.created_by))
- return false;
- return true;
- }
- bool operator != (const FileMetaData &rhs) const {
- return !(*this == rhs);
- }
-
- bool operator < (const FileMetaData & ) const;
-
- uint32_t read(::apache::thrift::protocol::TProtocol* iprot);
- uint32_t write(::apache::thrift::protocol::TProtocol* oprot) const;
-
-};
-
-void swap(FileMetaData &a, FileMetaData &b);
-
-} // namespace
-
-#endif
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/thirdparty/build_thirdparty.sh
----------------------------------------------------------------------
diff --git a/thirdparty/build_thirdparty.sh b/thirdparty/build_thirdparty.sh
index 5e5fca4..2a4a2dc 100755
--- a/thirdparty/build_thirdparty.sh
+++ b/thirdparty/build_thirdparty.sh
@@ -98,6 +98,8 @@ if [ -n "$F_ALL" -o -n "$F_THRIFT" ]; then
# such a way that ./configure can find them
cd $TP_DIR/$THRIFT_BASEDIR
./configure CXXFLAGS='-fPIC' --without-qt4 --without-c_glib --without-csharp --without-java --without-erlang --without-nodejs --without-lua --without-python --without-perl --without-php --without-php_extension --without-ruby --without-haskell --without-go --without-d --with-cpp --prefix=$PREFIX
+
+ # This must be removed with Thrift 0.9.3, but required for Thrift 0.9.1
make clean
make install
fi
[3/3] parquet-cpp git commit: PARQUET-468: Use thirdparty Thrift
compiler to compile parquet.thrift at make time
Posted by ju...@apache.org.
PARQUET-468: Use thirdparty Thrift compiler to compile parquet.thrift at make time
This also adds a `#define` working around the googletest incompatibility described in PARQUET-470.
Author: Wes McKinney <we...@apache.org>
Closes #55 from wesm/PARQUET-468 and squashes the following commits:
e0338df [Wes McKinney] Auto-generate Thrift C++ bindings from environment Thrift compiler. Add #define workaround for Thrift >= 0.9.2 std::tuple conflict with googletest
Project: http://git-wip-us.apache.org/repos/asf/parquet-cpp/repo
Commit: http://git-wip-us.apache.org/repos/asf/parquet-cpp/commit/fed33172
Tree: http://git-wip-us.apache.org/repos/asf/parquet-cpp/tree/fed33172
Diff: http://git-wip-us.apache.org/repos/asf/parquet-cpp/diff/fed33172
Branch: refs/heads/master
Commit: fed3317274ccab4bb544a2baa0d120a875630a05
Parents: 17a2045
Author: Wes McKinney <we...@apache.org>
Authored: Thu Feb 18 15:54:32 2016 -0800
Committer: Julien Le Dem <ju...@dremio.com>
Committed: Thu Feb 18 15:54:32 2016 -0800
----------------------------------------------------------------------
CMakeLists.txt | 11 +
ci/before_script_travis.sh | 2 +-
parquet-format/parquet.thrift | 556 ------
src/parquet/column/column-reader-test.cc | 4 +-
src/parquet/schema/schema-converter-test.cc | 4 +-
src/parquet/thrift/.gitignore | 2 +
src/parquet/thrift/CMakeLists.txt | 30 +-
src/parquet/thrift/parquet.thrift | 556 ++++++
src/parquet/thrift/parquet_constants.cpp | 17 -
src/parquet/thrift/parquet_constants.h | 24 -
src/parquet/thrift/parquet_types.cpp | 2188 ----------------------
src/parquet/thrift/parquet_types.h | 1210 ------------
thirdparty/build_thirdparty.sh | 2 +
13 files changed, 598 insertions(+), 4008 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/CMakeLists.txt
----------------------------------------------------------------------
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 62182c4..c853993 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -111,6 +111,17 @@ function(ADD_PARQUET_TEST REL_TEST_NAME)
# This test has a corresponding .cc file, set it up as an executable.
set(TEST_PATH "${EXECUTABLE_OUTPUT_PATH}/${TEST_NAME}")
add_executable(${TEST_NAME} "${REL_TEST_NAME}.cc")
+
+ if(APPLE)
+ # On OS X / Thrift >= 0.9.2, tr1/tuple.h is not in libc++
+ SET_TARGET_PROPERTIES(${TEST_NAME} PROPERTIES COMPILE_FLAGS
+ -DGTEST_USE_OWN_TR1_TUPLE=1)
+ else()
+ # Linux, for Thrift >= 0.9.2
+ SET_TARGET_PROPERTIES(${TEST_NAME} PROPERTIES COMPILE_FLAGS
+ -DGTEST_USE_OWN_TR1_TUPLE=0)
+ endif()
+
target_link_libraries(${TEST_NAME} ${PARQUET_TEST_LINK_LIBS})
else()
# No executable, just invoke the test (probably a script) directly.
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/ci/before_script_travis.sh
----------------------------------------------------------------------
diff --git a/ci/before_script_travis.sh b/ci/before_script_travis.sh
index c467c67..aec40ed 100755
--- a/ci/before_script_travis.sh
+++ b/ci/before_script_travis.sh
@@ -5,7 +5,7 @@ cp -r $TRAVIS_BUILD_DIR/thirdparty .
./thirdparty/download_thirdparty.sh
if [ $TRAVIS_OS_NAME == "osx" ]; then
- brew update -q
+ brew update > /dev/null
brew install thrift
else
# Use a C++11 compiler on Linux
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/parquet-format/parquet.thrift
----------------------------------------------------------------------
diff --git a/parquet-format/parquet.thrift b/parquet-format/parquet.thrift
deleted file mode 100644
index 7544cf3..0000000
--- a/parquet-format/parquet.thrift
+++ /dev/null
@@ -1,556 +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 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;
- // RESERVED = 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;
- // RESERVED = 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 {
- 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-cpp/blob/fed33172/src/parquet/column/column-reader-test.cc
----------------------------------------------------------------------
diff --git a/src/parquet/column/column-reader-test.cc b/src/parquet/column/column-reader-test.cc
index c2c0aa3..828ef31 100644
--- a/src/parquet/column/column-reader-test.cc
+++ b/src/parquet/column/column-reader-test.cc
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+#include <gtest/gtest.h>
+
#include <algorithm>
#include <cstdint>
#include <cstdlib>
@@ -22,8 +24,6 @@
#include <string>
#include <vector>
-#include <gtest/gtest.h>
-
#include "parquet/types.h"
#include "parquet/column/page.h"
#include "parquet/column/reader.h"
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/schema/schema-converter-test.cc
----------------------------------------------------------------------
diff --git a/src/parquet/schema/schema-converter-test.cc b/src/parquet/schema/schema-converter-test.cc
index 93cfd24..64ca817 100644
--- a/src/parquet/schema/schema-converter-test.cc
+++ b/src/parquet/schema/schema-converter-test.cc
@@ -15,13 +15,13 @@
// specific language governing permissions and limitations
// under the License.
+#include <gtest/gtest.h>
+
#include <cstdlib>
#include <memory>
#include <string>
#include <vector>
-#include <gtest/gtest.h>
-
#include "parquet/exception.h"
#include "parquet/schema/converter.h"
#include "parquet/schema/test-util.h"
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/.gitignore
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/.gitignore b/src/parquet/thrift/.gitignore
new file mode 100644
index 0000000..0695270
--- /dev/null
+++ b/src/parquet/thrift/.gitignore
@@ -0,0 +1,2 @@
+parquet_constants.*
+parquet_types.*
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/CMakeLists.txt
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/CMakeLists.txt b/src/parquet/thrift/CMakeLists.txt
index 30150ca..29b8ef8 100644
--- a/src/parquet/thrift/CMakeLists.txt
+++ b/src/parquet/thrift/CMakeLists.txt
@@ -15,20 +15,34 @@
# specific language governing permissions and limitations
# under the License.
-add_library(parquet_thrift STATIC
+set(THRIFT_SRCS
parquet_constants.cpp
- parquet_types.cpp
+ parquet_types.cpp)
+
+add_library(parquet_thrift STATIC
+ ${THRIFT_SRCS}
)
+
set_target_properties(parquet_thrift
PROPERTIES
LIBRARY_OUTPUT_DIRECTORY "${BUILD_OUTPUT_ROOT_DIRECTORY}")
+set_source_files_properties(${THRIFT_SRCS} PROPERTIES GENERATED TRUE)
+
+# List of thrift output targets
+set(OUTPUT_DIR ${CMAKE_SOURCE_DIR}/src/parquet/thrift)
+set(THRIFT_OUTPUT_FILES "${OUTPUT_DIR}/parquet_types.cpp")
+set(THRIFT_OUTPUT_FILES ${THRIFT_OUTPUT_FILES} "${OUTPUT_DIR}/parquet_types.h")
+set(THRIFT_OUTPUT_FILES ${THRIFT_OUTPUT_FILES} "${OUTPUT_DIR}/parquet_constants.cpp")
+set(THRIFT_OUTPUT_FILES ${THRIFT_OUTPUT_FILES} "${OUTPUT_DIR}/parquet_constants.h")
+get_filename_component(ABS_PARQUET_THRIFT parquet.thrift ABSOLUTE)
-# Headers: thrift
-install(FILES
- parquet_types.h
- parquet_constants.h
- util.h
- DESTINATION include/parquet/thrift)
+add_custom_command(
+ OUTPUT ${THRIFT_OUTPUT_FILES}
+ COMMAND ${THRIFT_COMPILER} --gen cpp -out ${OUTPUT_DIR} ${CMAKE_CURRENT_SOURCE_DIR}/parquet.thrift
+ DEPENDS ${ABS_PARQUET_THRIFT}
+ COMMENT "Running thrift compiler on parquet.thrift"
+ VERBATIM
+)
ADD_PARQUET_TEST(serializer-test)
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/parquet.thrift
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/parquet.thrift b/src/parquet/thrift/parquet.thrift
new file mode 100644
index 0000000..7544cf3
--- /dev/null
+++ b/src/parquet/thrift/parquet.thrift
@@ -0,0 +1,556 @@
+/**
+ * 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 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;
+ // RESERVED = 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;
+ // RESERVED = 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 {
+ 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-cpp/blob/fed33172/src/parquet/thrift/parquet_constants.cpp
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/parquet_constants.cpp b/src/parquet/thrift/parquet_constants.cpp
deleted file mode 100644
index caa5af6..0000000
--- a/src/parquet/thrift/parquet_constants.cpp
+++ /dev/null
@@ -1,17 +0,0 @@
-/**
- * Autogenerated by Thrift Compiler (0.9.0)
- *
- * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING
- * @generated
- */
-#include "parquet_constants.h"
-
-namespace parquet {
-
-const parquetConstants g_parquet_constants;
-
-parquetConstants::parquetConstants() {
-}
-
-} // namespace
-
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/parquet_constants.h
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/parquet_constants.h b/src/parquet/thrift/parquet_constants.h
deleted file mode 100644
index 71d6f58..0000000
--- a/src/parquet/thrift/parquet_constants.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/**
- * Autogenerated by Thrift Compiler (0.9.0)
- *
- * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING
- * @generated
- */
-#ifndef parquet_CONSTANTS_H
-#define parquet_CONSTANTS_H
-
-#include "parquet_types.h"
-
-namespace parquet {
-
-class parquetConstants {
- public:
- parquetConstants();
-
-};
-
-extern const parquetConstants g_parquet_constants;
-
-} // namespace
-
-#endif
[2/3] parquet-cpp git commit: PARQUET-468: Use thirdparty Thrift
compiler to compile parquet.thrift at make time
Posted by ju...@apache.org.
http://git-wip-us.apache.org/repos/asf/parquet-cpp/blob/fed33172/src/parquet/thrift/parquet_types.cpp
----------------------------------------------------------------------
diff --git a/src/parquet/thrift/parquet_types.cpp b/src/parquet/thrift/parquet_types.cpp
deleted file mode 100644
index 8834e3e..0000000
--- a/src/parquet/thrift/parquet_types.cpp
+++ /dev/null
@@ -1,2188 +0,0 @@
-/**
- * Autogenerated by Thrift Compiler (0.9.0)
- *
- * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING
- * @generated
- */
-#include "parquet_types.h"
-
-#include <algorithm>
-
-namespace parquet {
-
-int _kTypeValues[] = {
- Type::BOOLEAN,
- Type::INT32,
- Type::INT64,
- Type::INT96,
- Type::FLOAT,
- Type::DOUBLE,
- Type::BYTE_ARRAY,
- Type::FIXED_LEN_BYTE_ARRAY
-};
-const char* _kTypeNames[] = {
- "BOOLEAN",
- "INT32",
- "INT64",
- "INT96",
- "FLOAT",
- "DOUBLE",
- "BYTE_ARRAY",
- "FIXED_LEN_BYTE_ARRAY"
-};
-const std::map<int, const char*> _Type_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(8, _kTypeValues, _kTypeNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-int _kConvertedTypeValues[] = {
- ConvertedType::UTF8,
- ConvertedType::MAP,
- ConvertedType::MAP_KEY_VALUE,
- ConvertedType::LIST,
- ConvertedType::ENUM,
- ConvertedType::DECIMAL,
- ConvertedType::DATE,
- ConvertedType::TIME_MILLIS,
- ConvertedType::TIMESTAMP_MILLIS,
- ConvertedType::UINT_8,
- ConvertedType::UINT_16,
- ConvertedType::UINT_32,
- ConvertedType::UINT_64,
- ConvertedType::INT_8,
- ConvertedType::INT_16,
- ConvertedType::INT_32,
- ConvertedType::INT_64,
- ConvertedType::JSON,
- ConvertedType::BSON,
- ConvertedType::INTERVAL
-};
-const char* _kConvertedTypeNames[] = {
- "UTF8",
- "MAP",
- "MAP_KEY_VALUE",
- "LIST",
- "ENUM",
- "DECIMAL",
- "DATE",
- "TIME_MILLIS",
- "TIMESTAMP_MILLIS",
- "UINT_8",
- "UINT_16",
- "UINT_32",
- "UINT_64",
- "INT_8",
- "INT_16",
- "INT_32",
- "INT_64",
- "JSON",
- "BSON",
- "INTERVAL"
-};
-const std::map<int, const char*> _ConvertedType_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(20, _kConvertedTypeValues, _kConvertedTypeNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-int _kFieldRepetitionTypeValues[] = {
- FieldRepetitionType::REQUIRED,
- FieldRepetitionType::OPTIONAL,
- FieldRepetitionType::REPEATED
-};
-const char* _kFieldRepetitionTypeNames[] = {
- "REQUIRED",
- "OPTIONAL",
- "REPEATED"
-};
-const std::map<int, const char*> _FieldRepetitionType_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(3, _kFieldRepetitionTypeValues, _kFieldRepetitionTypeNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-int _kEncodingValues[] = {
- Encoding::PLAIN,
- Encoding::PLAIN_DICTIONARY,
- Encoding::RLE,
- Encoding::BIT_PACKED,
- Encoding::DELTA_BINARY_PACKED,
- Encoding::DELTA_LENGTH_BYTE_ARRAY,
- Encoding::DELTA_BYTE_ARRAY,
- Encoding::RLE_DICTIONARY
-};
-const char* _kEncodingNames[] = {
- "PLAIN",
- "PLAIN_DICTIONARY",
- "RLE",
- "BIT_PACKED",
- "DELTA_BINARY_PACKED",
- "DELTA_LENGTH_BYTE_ARRAY",
- "DELTA_BYTE_ARRAY",
- "RLE_DICTIONARY"
-};
-const std::map<int, const char*> _Encoding_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(8, _kEncodingValues, _kEncodingNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-int _kCompressionCodecValues[] = {
- CompressionCodec::UNCOMPRESSED,
- CompressionCodec::SNAPPY,
- CompressionCodec::GZIP,
- CompressionCodec::LZO
-};
-const char* _kCompressionCodecNames[] = {
- "UNCOMPRESSED",
- "SNAPPY",
- "GZIP",
- "LZO"
-};
-const std::map<int, const char*> _CompressionCodec_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(4, _kCompressionCodecValues, _kCompressionCodecNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-int _kPageTypeValues[] = {
- PageType::DATA_PAGE,
- PageType::INDEX_PAGE,
- PageType::DICTIONARY_PAGE,
- PageType::DATA_PAGE_V2
-};
-const char* _kPageTypeNames[] = {
- "DATA_PAGE",
- "INDEX_PAGE",
- "DICTIONARY_PAGE",
- "DATA_PAGE_V2"
-};
-const std::map<int, const char*> _PageType_VALUES_TO_NAMES(::apache::thrift::TEnumIterator(4, _kPageTypeValues, _kPageTypeNames), ::apache::thrift::TEnumIterator(-1, NULL, NULL));
-
-const char* Statistics::ascii_fingerprint = "CE004821871820DD79A8FD98BB101F6D";
-const uint8_t Statistics::binary_fingerprint[16] = {0xCE,0x00,0x48,0x21,0x87,0x18,0x20,0xDD,0x79,0xA8,0xFD,0x98,0xBB,0x10,0x1F,0x6D};
-
-uint32_t Statistics::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readBinary(this->max);
- this->__isset.max = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readBinary(this->min);
- this->__isset.min = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->null_count);
- this->__isset.null_count = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->distinct_count);
- this->__isset.distinct_count = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- return xfer;
-}
-
-uint32_t Statistics::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("Statistics");
-
- if (this->__isset.max) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("max", ::apache::thrift::protocol::T_STRING, 1);
- xfer += oprot->writeBinary(this->max);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.min) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("min", ::apache::thrift::protocol::T_STRING, 2);
- xfer += oprot->writeBinary(this->min);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.null_count) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("null_count", ::apache::thrift::protocol::T_I64, 3);
- xfer += oprot->writeI64(this->null_count);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.distinct_count) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("distinct_count", ::apache::thrift::protocol::T_I64, 4);
- xfer += oprot->writeI64(this->distinct_count);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(Statistics &a, Statistics &b) {
- using ::std::swap;
- swap(a.max, b.max);
- swap(a.min, b.min);
- swap(a.null_count, b.null_count);
- swap(a.distinct_count, b.distinct_count);
- swap(a.__isset, b.__isset);
-}
-
-const char* SchemaElement::ascii_fingerprint = "22DC89BFD9E48E604F01FB8CFDFB8229";
-const uint8_t SchemaElement::binary_fingerprint[16] = {0x22,0xDC,0x89,0xBF,0xD9,0xE4,0x8E,0x60,0x4F,0x01,0xFB,0x8C,0xFD,0xFB,0x82,0x29};
-
-uint32_t SchemaElement::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_name = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast0;
- xfer += iprot->readI32(ecast0);
- this->type = (Type::type)ecast0;
- this->__isset.type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->type_length);
- this->__isset.type_length = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast1;
- xfer += iprot->readI32(ecast1);
- this->repetition_type = (FieldRepetitionType::type)ecast1;
- this->__isset.repetition_type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readString(this->name);
- isset_name = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_children);
- this->__isset.num_children = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 6:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast2;
- xfer += iprot->readI32(ecast2);
- this->converted_type = (ConvertedType::type)ecast2;
- this->__isset.converted_type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 7:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->scale);
- this->__isset.scale = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 8:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->precision);
- this->__isset.precision = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 9:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->field_id);
- this->__isset.field_id = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_name)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t SchemaElement::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("SchemaElement");
-
- if (this->__isset.type) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("type", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32((int32_t)this->type);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.type_length) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("type_length", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32(this->type_length);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.repetition_type) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("repetition_type", ::apache::thrift::protocol::T_I32, 3);
- xfer += oprot->writeI32((int32_t)this->repetition_type);
- xfer += oprot->writeFieldEnd();
- }
- ++fcnt;
- xfer += oprot->writeFieldBegin("name", ::apache::thrift::protocol::T_STRING, 4);
- xfer += oprot->writeString(this->name);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.num_children) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_children", ::apache::thrift::protocol::T_I32, 5);
- xfer += oprot->writeI32(this->num_children);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.converted_type) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("converted_type", ::apache::thrift::protocol::T_I32, 6);
- xfer += oprot->writeI32((int32_t)this->converted_type);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.scale) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("scale", ::apache::thrift::protocol::T_I32, 7);
- xfer += oprot->writeI32(this->scale);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.precision) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("precision", ::apache::thrift::protocol::T_I32, 8);
- xfer += oprot->writeI32(this->precision);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.field_id) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("field_id", ::apache::thrift::protocol::T_I32, 9);
- xfer += oprot->writeI32(this->field_id);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(SchemaElement &a, SchemaElement &b) {
- using ::std::swap;
- swap(a.type, b.type);
- swap(a.type_length, b.type_length);
- swap(a.repetition_type, b.repetition_type);
- swap(a.name, b.name);
- swap(a.num_children, b.num_children);
- swap(a.converted_type, b.converted_type);
- swap(a.scale, b.scale);
- swap(a.precision, b.precision);
- swap(a.field_id, b.field_id);
- swap(a.__isset, b.__isset);
-}
-
-const char* DataPageHeader::ascii_fingerprint = "5FC1792B0483E9C984475384165040B1";
-const uint8_t DataPageHeader::binary_fingerprint[16] = {0x5F,0xC1,0x79,0x2B,0x04,0x83,0xE9,0xC9,0x84,0x47,0x53,0x84,0x16,0x50,0x40,0xB1};
-
-uint32_t DataPageHeader::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_num_values = false;
- bool isset_encoding = false;
- bool isset_definition_level_encoding = false;
- bool isset_repetition_level_encoding = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_values);
- isset_num_values = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast3;
- xfer += iprot->readI32(ecast3);
- this->encoding = (Encoding::type)ecast3;
- isset_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast4;
- xfer += iprot->readI32(ecast4);
- this->definition_level_encoding = (Encoding::type)ecast4;
- isset_definition_level_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast5;
- xfer += iprot->readI32(ecast5);
- this->repetition_level_encoding = (Encoding::type)ecast5;
- isset_repetition_level_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->statistics.read(iprot);
- this->__isset.statistics = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_num_values)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_definition_level_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_repetition_level_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t DataPageHeader::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("DataPageHeader");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_values", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32(this->num_values);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("encoding", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32((int32_t)this->encoding);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("definition_level_encoding", ::apache::thrift::protocol::T_I32, 3);
- xfer += oprot->writeI32((int32_t)this->definition_level_encoding);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("repetition_level_encoding", ::apache::thrift::protocol::T_I32, 4);
- xfer += oprot->writeI32((int32_t)this->repetition_level_encoding);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.statistics) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("statistics", ::apache::thrift::protocol::T_STRUCT, 5);
- xfer += this->statistics.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(DataPageHeader &a, DataPageHeader &b) {
- using ::std::swap;
- swap(a.num_values, b.num_values);
- swap(a.encoding, b.encoding);
- swap(a.definition_level_encoding, b.definition_level_encoding);
- swap(a.repetition_level_encoding, b.repetition_level_encoding);
- swap(a.statistics, b.statistics);
- swap(a.__isset, b.__isset);
-}
-
-const char* IndexPageHeader::ascii_fingerprint = "99914B932BD37A50B983C5E7C90AE93B";
-const uint8_t IndexPageHeader::binary_fingerprint[16] = {0x99,0x91,0x4B,0x93,0x2B,0xD3,0x7A,0x50,0xB9,0x83,0xC5,0xE7,0xC9,0x0A,0xE9,0x3B};
-
-uint32_t IndexPageHeader::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- xfer += iprot->skip(ftype);
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- return xfer;
-}
-
-uint32_t IndexPageHeader::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("IndexPageHeader");
-
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(IndexPageHeader &a, IndexPageHeader &b) {
- using ::std::swap;
- (void) a;
- (void) b;
-}
-
-const char* DictionaryPageHeader::ascii_fingerprint = "B149E4528254D495610C22AE4BD539C5";
-const uint8_t DictionaryPageHeader::binary_fingerprint[16] = {0xB1,0x49,0xE4,0x52,0x82,0x54,0xD4,0x95,0x61,0x0C,0x22,0xAE,0x4B,0xD5,0x39,0xC5};
-
-uint32_t DictionaryPageHeader::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_num_values = false;
- bool isset_encoding = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_values);
- isset_num_values = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast6;
- xfer += iprot->readI32(ecast6);
- this->encoding = (Encoding::type)ecast6;
- isset_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_BOOL) {
- xfer += iprot->readBool(this->is_sorted);
- this->__isset.is_sorted = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_num_values)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t DictionaryPageHeader::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("DictionaryPageHeader");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_values", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32(this->num_values);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("encoding", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32((int32_t)this->encoding);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.is_sorted) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("is_sorted", ::apache::thrift::protocol::T_BOOL, 3);
- xfer += oprot->writeBool(this->is_sorted);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(DictionaryPageHeader &a, DictionaryPageHeader &b) {
- using ::std::swap;
- swap(a.num_values, b.num_values);
- swap(a.encoding, b.encoding);
- swap(a.is_sorted, b.is_sorted);
- swap(a.__isset, b.__isset);
-}
-
-const char* DataPageHeaderV2::ascii_fingerprint = "69FF2F6BD1A443440D5E46ABA5A3A919";
-const uint8_t DataPageHeaderV2::binary_fingerprint[16] = {0x69,0xFF,0x2F,0x6B,0xD1,0xA4,0x43,0x44,0x0D,0x5E,0x46,0xAB,0xA5,0xA3,0xA9,0x19};
-
-uint32_t DataPageHeaderV2::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_num_values = false;
- bool isset_num_nulls = false;
- bool isset_num_rows = false;
- bool isset_encoding = false;
- bool isset_definition_levels_byte_length = false;
- bool isset_repetition_levels_byte_length = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_values);
- isset_num_values = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_nulls);
- isset_num_nulls = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->num_rows);
- isset_num_rows = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast7;
- xfer += iprot->readI32(ecast7);
- this->encoding = (Encoding::type)ecast7;
- isset_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->definition_levels_byte_length);
- isset_definition_levels_byte_length = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 6:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->repetition_levels_byte_length);
- isset_repetition_levels_byte_length = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 7:
- if (ftype == ::apache::thrift::protocol::T_BOOL) {
- xfer += iprot->readBool(this->is_compressed);
- this->__isset.is_compressed = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 8:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->statistics.read(iprot);
- this->__isset.statistics = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_num_values)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_num_nulls)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_num_rows)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_definition_levels_byte_length)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_repetition_levels_byte_length)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t DataPageHeaderV2::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("DataPageHeaderV2");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_values", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32(this->num_values);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_nulls", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32(this->num_nulls);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_rows", ::apache::thrift::protocol::T_I32, 3);
- xfer += oprot->writeI32(this->num_rows);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("encoding", ::apache::thrift::protocol::T_I32, 4);
- xfer += oprot->writeI32((int32_t)this->encoding);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("definition_levels_byte_length", ::apache::thrift::protocol::T_I32, 5);
- xfer += oprot->writeI32(this->definition_levels_byte_length);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("repetition_levels_byte_length", ::apache::thrift::protocol::T_I32, 6);
- xfer += oprot->writeI32(this->repetition_levels_byte_length);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.is_compressed) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("is_compressed", ::apache::thrift::protocol::T_BOOL, 7);
- xfer += oprot->writeBool(this->is_compressed);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.statistics) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("statistics", ::apache::thrift::protocol::T_STRUCT, 8);
- xfer += this->statistics.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(DataPageHeaderV2 &a, DataPageHeaderV2 &b) {
- using ::std::swap;
- swap(a.num_values, b.num_values);
- swap(a.num_nulls, b.num_nulls);
- swap(a.num_rows, b.num_rows);
- swap(a.encoding, b.encoding);
- swap(a.definition_levels_byte_length, b.definition_levels_byte_length);
- swap(a.repetition_levels_byte_length, b.repetition_levels_byte_length);
- swap(a.is_compressed, b.is_compressed);
- swap(a.statistics, b.statistics);
- swap(a.__isset, b.__isset);
-}
-
-const char* PageHeader::ascii_fingerprint = "B5BD2BDF3756C883A58B30B9C9F204A0";
-const uint8_t PageHeader::binary_fingerprint[16] = {0xB5,0xBD,0x2B,0xDF,0x37,0x56,0xC8,0x83,0xA5,0x8B,0x30,0xB9,0xC9,0xF2,0x04,0xA0};
-
-uint32_t PageHeader::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_type = false;
- bool isset_uncompressed_page_size = false;
- bool isset_compressed_page_size = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast8;
- xfer += iprot->readI32(ecast8);
- this->type = (PageType::type)ecast8;
- isset_type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->uncompressed_page_size);
- isset_uncompressed_page_size = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->compressed_page_size);
- isset_compressed_page_size = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->crc);
- this->__isset.crc = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->data_page_header.read(iprot);
- this->__isset.data_page_header = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 6:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->index_page_header.read(iprot);
- this->__isset.index_page_header = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 7:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->dictionary_page_header.read(iprot);
- this->__isset.dictionary_page_header = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 8:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->data_page_header_v2.read(iprot);
- this->__isset.data_page_header_v2 = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_type)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_uncompressed_page_size)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_compressed_page_size)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t PageHeader::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("PageHeader");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("type", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32((int32_t)this->type);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("uncompressed_page_size", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32(this->uncompressed_page_size);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("compressed_page_size", ::apache::thrift::protocol::T_I32, 3);
- xfer += oprot->writeI32(this->compressed_page_size);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.crc) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("crc", ::apache::thrift::protocol::T_I32, 4);
- xfer += oprot->writeI32(this->crc);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.data_page_header) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("data_page_header", ::apache::thrift::protocol::T_STRUCT, 5);
- xfer += this->data_page_header.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.index_page_header) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("index_page_header", ::apache::thrift::protocol::T_STRUCT, 6);
- xfer += this->index_page_header.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.dictionary_page_header) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("dictionary_page_header", ::apache::thrift::protocol::T_STRUCT, 7);
- xfer += this->dictionary_page_header.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.data_page_header_v2) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("data_page_header_v2", ::apache::thrift::protocol::T_STRUCT, 8);
- xfer += this->data_page_header_v2.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(PageHeader &a, PageHeader &b) {
- using ::std::swap;
- swap(a.type, b.type);
- swap(a.uncompressed_page_size, b.uncompressed_page_size);
- swap(a.compressed_page_size, b.compressed_page_size);
- swap(a.crc, b.crc);
- swap(a.data_page_header, b.data_page_header);
- swap(a.index_page_header, b.index_page_header);
- swap(a.dictionary_page_header, b.dictionary_page_header);
- swap(a.data_page_header_v2, b.data_page_header_v2);
- swap(a.__isset, b.__isset);
-}
-
-const char* KeyValue::ascii_fingerprint = "5B708A954C550ECA9C1A49D3C5CAFAB9";
-const uint8_t KeyValue::binary_fingerprint[16] = {0x5B,0x70,0x8A,0x95,0x4C,0x55,0x0E,0xCA,0x9C,0x1A,0x49,0xD3,0xC5,0xCA,0xFA,0xB9};
-
-uint32_t KeyValue::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_key = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readString(this->key);
- isset_key = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readString(this->value);
- this->__isset.value = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_key)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t KeyValue::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("KeyValue");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("key", ::apache::thrift::protocol::T_STRING, 1);
- xfer += oprot->writeString(this->key);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.value) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("value", ::apache::thrift::protocol::T_STRING, 2);
- xfer += oprot->writeString(this->value);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(KeyValue &a, KeyValue &b) {
- using ::std::swap;
- swap(a.key, b.key);
- swap(a.value, b.value);
- swap(a.__isset, b.__isset);
-}
-
-const char* SortingColumn::ascii_fingerprint = "F079C2D58A783AD90F9BE05D10DBBC6F";
-const uint8_t SortingColumn::binary_fingerprint[16] = {0xF0,0x79,0xC2,0xD5,0x8A,0x78,0x3A,0xD9,0x0F,0x9B,0xE0,0x5D,0x10,0xDB,0xBC,0x6F};
-
-uint32_t SortingColumn::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_column_idx = false;
- bool isset_descending = false;
- bool isset_nulls_first = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->column_idx);
- isset_column_idx = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_BOOL) {
- xfer += iprot->readBool(this->descending);
- isset_descending = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_BOOL) {
- xfer += iprot->readBool(this->nulls_first);
- isset_nulls_first = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_column_idx)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_descending)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_nulls_first)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t SortingColumn::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("SortingColumn");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("column_idx", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32(this->column_idx);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("descending", ::apache::thrift::protocol::T_BOOL, 2);
- xfer += oprot->writeBool(this->descending);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("nulls_first", ::apache::thrift::protocol::T_BOOL, 3);
- xfer += oprot->writeBool(this->nulls_first);
- xfer += oprot->writeFieldEnd();
-
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(SortingColumn &a, SortingColumn &b) {
- using ::std::swap;
- swap(a.column_idx, b.column_idx);
- swap(a.descending, b.descending);
- swap(a.nulls_first, b.nulls_first);
-}
-
-const char* PageEncodingStats::ascii_fingerprint = "5F1BEE04836FAA3055D3EE2492AE44FB";
-const uint8_t PageEncodingStats::binary_fingerprint[16] = {0x5F,0x1B,0xEE,0x04,0x83,0x6F,0xAA,0x30,0x55,0xD3,0xEE,0x24,0x92,0xAE,0x44,0xFB};
-
-uint32_t PageEncodingStats::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_page_type = false;
- bool isset_encoding = false;
- bool isset_count = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast9;
- xfer += iprot->readI32(ecast9);
- this->page_type = (PageType::type)ecast9;
- isset_page_type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast10;
- xfer += iprot->readI32(ecast10);
- this->encoding = (Encoding::type)ecast10;
- isset_encoding = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->count);
- isset_count = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_page_type)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_encoding)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_count)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t PageEncodingStats::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("PageEncodingStats");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("page_type", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32((int32_t)this->page_type);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("encoding", ::apache::thrift::protocol::T_I32, 2);
- xfer += oprot->writeI32((int32_t)this->encoding);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("count", ::apache::thrift::protocol::T_I32, 3);
- xfer += oprot->writeI32(this->count);
- xfer += oprot->writeFieldEnd();
-
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(PageEncodingStats &a, PageEncodingStats &b) {
- using ::std::swap;
- swap(a.page_type, b.page_type);
- swap(a.encoding, b.encoding);
- swap(a.count, b.count);
-}
-
-const char* ColumnMetaData::ascii_fingerprint = "AEE7317B6DB9719FE828388D537DBD71";
-const uint8_t ColumnMetaData::binary_fingerprint[16] = {0xAE,0xE7,0x31,0x7B,0x6D,0xB9,0x71,0x9F,0xE8,0x28,0x38,0x8D,0x53,0x7D,0xBD,0x71};
-
-uint32_t ColumnMetaData::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_type = false;
- bool isset_encodings = false;
- bool isset_path_in_schema = false;
- bool isset_codec = false;
- bool isset_num_values = false;
- bool isset_total_uncompressed_size = false;
- bool isset_total_compressed_size = false;
- bool isset_data_page_offset = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast11;
- xfer += iprot->readI32(ecast11);
- this->type = (Type::type)ecast11;
- isset_type = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->encodings.clear();
- uint32_t _size12;
- ::apache::thrift::protocol::TType _etype15;
- xfer += iprot->readListBegin(_etype15, _size12);
- this->encodings.resize(_size12);
- uint32_t _i16;
- for (_i16 = 0; _i16 < _size12; ++_i16)
- {
- int32_t ecast17;
- xfer += iprot->readI32(ecast17);
- this->encodings[_i16] = (Encoding::type)ecast17;
- }
- xfer += iprot->readListEnd();
- }
- isset_encodings = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->path_in_schema.clear();
- uint32_t _size18;
- ::apache::thrift::protocol::TType _etype21;
- xfer += iprot->readListBegin(_etype21, _size18);
- this->path_in_schema.resize(_size18);
- uint32_t _i22;
- for (_i22 = 0; _i22 < _size18; ++_i22)
- {
- xfer += iprot->readString(this->path_in_schema[_i22]);
- }
- xfer += iprot->readListEnd();
- }
- isset_path_in_schema = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- int32_t ecast23;
- xfer += iprot->readI32(ecast23);
- this->codec = (CompressionCodec::type)ecast23;
- isset_codec = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->num_values);
- isset_num_values = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 6:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->total_uncompressed_size);
- isset_total_uncompressed_size = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 7:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->total_compressed_size);
- isset_total_compressed_size = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 8:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->key_value_metadata.clear();
- uint32_t _size24;
- ::apache::thrift::protocol::TType _etype27;
- xfer += iprot->readListBegin(_etype27, _size24);
- this->key_value_metadata.resize(_size24);
- uint32_t _i28;
- for (_i28 = 0; _i28 < _size24; ++_i28)
- {
- xfer += this->key_value_metadata[_i28].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- this->__isset.key_value_metadata = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 9:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->data_page_offset);
- isset_data_page_offset = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 10:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->index_page_offset);
- this->__isset.index_page_offset = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 11:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->dictionary_page_offset);
- this->__isset.dictionary_page_offset = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 12:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->statistics.read(iprot);
- this->__isset.statistics = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 13:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->encoding_stats.clear();
- uint32_t _size29;
- ::apache::thrift::protocol::TType _etype32;
- xfer += iprot->readListBegin(_etype32, _size29);
- this->encoding_stats.resize(_size29);
- uint32_t _i33;
- for (_i33 = 0; _i33 < _size29; ++_i33)
- {
- xfer += this->encoding_stats[_i33].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- this->__isset.encoding_stats = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_type)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_encodings)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_path_in_schema)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_codec)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_num_values)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_total_uncompressed_size)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_total_compressed_size)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_data_page_offset)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t ColumnMetaData::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("ColumnMetaData");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("type", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32((int32_t)this->type);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("encodings", ::apache::thrift::protocol::T_LIST, 2);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_I32, static_cast<uint32_t>(this->encodings.size()));
- std::vector<Encoding::type> ::const_iterator _iter34;
- for (_iter34 = this->encodings.begin(); _iter34 != this->encodings.end(); ++_iter34)
- {
- xfer += oprot->writeI32((int32_t)(*_iter34));
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("path_in_schema", ::apache::thrift::protocol::T_LIST, 3);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRING, static_cast<uint32_t>(this->path_in_schema.size()));
- std::vector<std::string> ::const_iterator _iter35;
- for (_iter35 = this->path_in_schema.begin(); _iter35 != this->path_in_schema.end(); ++_iter35)
- {
- xfer += oprot->writeString((*_iter35));
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("codec", ::apache::thrift::protocol::T_I32, 4);
- xfer += oprot->writeI32((int32_t)this->codec);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_values", ::apache::thrift::protocol::T_I64, 5);
- xfer += oprot->writeI64(this->num_values);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("total_uncompressed_size", ::apache::thrift::protocol::T_I64, 6);
- xfer += oprot->writeI64(this->total_uncompressed_size);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("total_compressed_size", ::apache::thrift::protocol::T_I64, 7);
- xfer += oprot->writeI64(this->total_compressed_size);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.key_value_metadata) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("key_value_metadata", ::apache::thrift::protocol::T_LIST, 8);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->key_value_metadata.size()));
- std::vector<KeyValue> ::const_iterator _iter36;
- for (_iter36 = this->key_value_metadata.begin(); _iter36 != this->key_value_metadata.end(); ++_iter36)
- {
- xfer += (*_iter36).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
- }
- ++fcnt;
- xfer += oprot->writeFieldBegin("data_page_offset", ::apache::thrift::protocol::T_I64, 9);
- xfer += oprot->writeI64(this->data_page_offset);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.index_page_offset) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("index_page_offset", ::apache::thrift::protocol::T_I64, 10);
- xfer += oprot->writeI64(this->index_page_offset);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.dictionary_page_offset) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("dictionary_page_offset", ::apache::thrift::protocol::T_I64, 11);
- xfer += oprot->writeI64(this->dictionary_page_offset);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.statistics) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("statistics", ::apache::thrift::protocol::T_STRUCT, 12);
- xfer += this->statistics.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.encoding_stats) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("encoding_stats", ::apache::thrift::protocol::T_LIST, 13);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->encoding_stats.size()));
- std::vector<PageEncodingStats> ::const_iterator _iter37;
- for (_iter37 = this->encoding_stats.begin(); _iter37 != this->encoding_stats.end(); ++_iter37)
- {
- xfer += (*_iter37).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(ColumnMetaData &a, ColumnMetaData &b) {
- using ::std::swap;
- swap(a.type, b.type);
- swap(a.encodings, b.encodings);
- swap(a.path_in_schema, b.path_in_schema);
- swap(a.codec, b.codec);
- swap(a.num_values, b.num_values);
- swap(a.total_uncompressed_size, b.total_uncompressed_size);
- swap(a.total_compressed_size, b.total_compressed_size);
- swap(a.key_value_metadata, b.key_value_metadata);
- swap(a.data_page_offset, b.data_page_offset);
- swap(a.index_page_offset, b.index_page_offset);
- swap(a.dictionary_page_offset, b.dictionary_page_offset);
- swap(a.statistics, b.statistics);
- swap(a.encoding_stats, b.encoding_stats);
- swap(a.__isset, b.__isset);
-}
-
-const char* ColumnChunk::ascii_fingerprint = "F9F2DFFF1A7805AEF05AA10B23AF3108";
-const uint8_t ColumnChunk::binary_fingerprint[16] = {0xF9,0xF2,0xDF,0xFF,0x1A,0x78,0x05,0xAE,0xF0,0x5A,0xA1,0x0B,0x23,0xAF,0x31,0x08};
-
-uint32_t ColumnChunk::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_file_offset = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readString(this->file_path);
- this->__isset.file_path = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->file_offset);
- isset_file_offset = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_STRUCT) {
- xfer += this->meta_data.read(iprot);
- this->__isset.meta_data = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_file_offset)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t ColumnChunk::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("ColumnChunk");
-
- if (this->__isset.file_path) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("file_path", ::apache::thrift::protocol::T_STRING, 1);
- xfer += oprot->writeString(this->file_path);
- xfer += oprot->writeFieldEnd();
- }
- ++fcnt;
- xfer += oprot->writeFieldBegin("file_offset", ::apache::thrift::protocol::T_I64, 2);
- xfer += oprot->writeI64(this->file_offset);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.meta_data) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("meta_data", ::apache::thrift::protocol::T_STRUCT, 3);
- xfer += this->meta_data.write(oprot);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(ColumnChunk &a, ColumnChunk &b) {
- using ::std::swap;
- swap(a.file_path, b.file_path);
- swap(a.file_offset, b.file_offset);
- swap(a.meta_data, b.meta_data);
- swap(a.__isset, b.__isset);
-}
-
-const char* RowGroup::ascii_fingerprint = "9BCFCB6790B06809B46424957993EDA6";
-const uint8_t RowGroup::binary_fingerprint[16] = {0x9B,0xCF,0xCB,0x67,0x90,0xB0,0x68,0x09,0xB4,0x64,0x24,0x95,0x79,0x93,0xED,0xA6};
-
-uint32_t RowGroup::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_columns = false;
- bool isset_total_byte_size = false;
- bool isset_num_rows = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->columns.clear();
- uint32_t _size38;
- ::apache::thrift::protocol::TType _etype41;
- xfer += iprot->readListBegin(_etype41, _size38);
- this->columns.resize(_size38);
- uint32_t _i42;
- for (_i42 = 0; _i42 < _size38; ++_i42)
- {
- xfer += this->columns[_i42].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- isset_columns = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->total_byte_size);
- isset_total_byte_size = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->num_rows);
- isset_num_rows = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->sorting_columns.clear();
- uint32_t _size43;
- ::apache::thrift::protocol::TType _etype46;
- xfer += iprot->readListBegin(_etype46, _size43);
- this->sorting_columns.resize(_size43);
- uint32_t _i47;
- for (_i47 = 0; _i47 < _size43; ++_i47)
- {
- xfer += this->sorting_columns[_i47].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- this->__isset.sorting_columns = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_columns)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_total_byte_size)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_num_rows)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t RowGroup::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("RowGroup");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("columns", ::apache::thrift::protocol::T_LIST, 1);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->columns.size()));
- std::vector<ColumnChunk> ::const_iterator _iter48;
- for (_iter48 = this->columns.begin(); _iter48 != this->columns.end(); ++_iter48)
- {
- xfer += (*_iter48).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("total_byte_size", ::apache::thrift::protocol::T_I64, 2);
- xfer += oprot->writeI64(this->total_byte_size);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_rows", ::apache::thrift::protocol::T_I64, 3);
- xfer += oprot->writeI64(this->num_rows);
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.sorting_columns) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("sorting_columns", ::apache::thrift::protocol::T_LIST, 4);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->sorting_columns.size()));
- std::vector<SortingColumn> ::const_iterator _iter49;
- for (_iter49 = this->sorting_columns.begin(); _iter49 != this->sorting_columns.end(); ++_iter49)
- {
- xfer += (*_iter49).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(RowGroup &a, RowGroup &b) {
- using ::std::swap;
- swap(a.columns, b.columns);
- swap(a.total_byte_size, b.total_byte_size);
- swap(a.num_rows, b.num_rows);
- swap(a.sorting_columns, b.sorting_columns);
- swap(a.__isset, b.__isset);
-}
-
-const char* FileMetaData::ascii_fingerprint = "D76119B1A4F2B4F404F095255FBDBD9A";
-const uint8_t FileMetaData::binary_fingerprint[16] = {0xD7,0x61,0x19,0xB1,0xA4,0xF2,0xB4,0xF4,0x04,0xF0,0x95,0x25,0x5F,0xBD,0xBD,0x9A};
-
-uint32_t FileMetaData::read(::apache::thrift::protocol::TProtocol* iprot) {
-
- uint32_t xfer = 0;
- std::string fname;
- ::apache::thrift::protocol::TType ftype;
- int16_t fid;
-
- xfer += iprot->readStructBegin(fname);
-
- using ::apache::thrift::protocol::TProtocolException;
-
- bool isset_version = false;
- bool isset_schema = false;
- bool isset_num_rows = false;
- bool isset_row_groups = false;
-
- while (true)
- {
- xfer += iprot->readFieldBegin(fname, ftype, fid);
- if (ftype == ::apache::thrift::protocol::T_STOP) {
- break;
- }
- switch (fid)
- {
- case 1:
- if (ftype == ::apache::thrift::protocol::T_I32) {
- xfer += iprot->readI32(this->version);
- isset_version = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 2:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->schema.clear();
- uint32_t _size50;
- ::apache::thrift::protocol::TType _etype53;
- xfer += iprot->readListBegin(_etype53, _size50);
- this->schema.resize(_size50);
- uint32_t _i54;
- for (_i54 = 0; _i54 < _size50; ++_i54)
- {
- xfer += this->schema[_i54].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- isset_schema = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 3:
- if (ftype == ::apache::thrift::protocol::T_I64) {
- xfer += iprot->readI64(this->num_rows);
- isset_num_rows = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 4:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->row_groups.clear();
- uint32_t _size55;
- ::apache::thrift::protocol::TType _etype58;
- xfer += iprot->readListBegin(_etype58, _size55);
- this->row_groups.resize(_size55);
- uint32_t _i59;
- for (_i59 = 0; _i59 < _size55; ++_i59)
- {
- xfer += this->row_groups[_i59].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- isset_row_groups = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 5:
- if (ftype == ::apache::thrift::protocol::T_LIST) {
- {
- this->key_value_metadata.clear();
- uint32_t _size60;
- ::apache::thrift::protocol::TType _etype63;
- xfer += iprot->readListBegin(_etype63, _size60);
- this->key_value_metadata.resize(_size60);
- uint32_t _i64;
- for (_i64 = 0; _i64 < _size60; ++_i64)
- {
- xfer += this->key_value_metadata[_i64].read(iprot);
- }
- xfer += iprot->readListEnd();
- }
- this->__isset.key_value_metadata = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- case 6:
- if (ftype == ::apache::thrift::protocol::T_STRING) {
- xfer += iprot->readString(this->created_by);
- this->__isset.created_by = true;
- } else {
- xfer += iprot->skip(ftype);
- }
- break;
- default:
- xfer += iprot->skip(ftype);
- break;
- }
- xfer += iprot->readFieldEnd();
- }
-
- xfer += iprot->readStructEnd();
-
- if (!isset_version)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_schema)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_num_rows)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- if (!isset_row_groups)
- throw TProtocolException(TProtocolException::INVALID_DATA);
- return xfer;
-}
-
-uint32_t FileMetaData::write(::apache::thrift::protocol::TProtocol* oprot) const {
- uint32_t xfer = 0;
- uint32_t fcnt = 0;
- xfer += oprot->writeStructBegin("FileMetaData");
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("version", ::apache::thrift::protocol::T_I32, 1);
- xfer += oprot->writeI32(this->version);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("schema", ::apache::thrift::protocol::T_LIST, 2);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->schema.size()));
- std::vector<SchemaElement> ::const_iterator _iter65;
- for (_iter65 = this->schema.begin(); _iter65 != this->schema.end(); ++_iter65)
- {
- xfer += (*_iter65).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("num_rows", ::apache::thrift::protocol::T_I64, 3);
- xfer += oprot->writeI64(this->num_rows);
- xfer += oprot->writeFieldEnd();
-
- ++fcnt;
- xfer += oprot->writeFieldBegin("row_groups", ::apache::thrift::protocol::T_LIST, 4);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->row_groups.size()));
- std::vector<RowGroup> ::const_iterator _iter66;
- for (_iter66 = this->row_groups.begin(); _iter66 != this->row_groups.end(); ++_iter66)
- {
- xfer += (*_iter66).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
-
- if (this->__isset.key_value_metadata) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("key_value_metadata", ::apache::thrift::protocol::T_LIST, 5);
- {
- xfer += oprot->writeListBegin(::apache::thrift::protocol::T_STRUCT, static_cast<uint32_t>(this->key_value_metadata.size()));
- std::vector<KeyValue> ::const_iterator _iter67;
- for (_iter67 = this->key_value_metadata.begin(); _iter67 != this->key_value_metadata.end(); ++_iter67)
- {
- xfer += (*_iter67).write(oprot);
- }
- xfer += oprot->writeListEnd();
- }
- xfer += oprot->writeFieldEnd();
- }
- if (this->__isset.created_by) {
- ++fcnt;
- xfer += oprot->writeFieldBegin("created_by", ::apache::thrift::protocol::T_STRING, 6);
- xfer += oprot->writeString(this->created_by);
- xfer += oprot->writeFieldEnd();
- }
- xfer += oprot->writeFieldStop();
- xfer += oprot->writeStructEnd();
- return xfer;
-}
-
-void swap(FileMetaData &a, FileMetaData &b) {
- using ::std::swap;
- swap(a.version, b.version);
- swap(a.schema, b.schema);
- swap(a.num_rows, b.num_rows);
- swap(a.row_groups, b.row_groups);
- swap(a.key_value_metadata, b.key_value_metadata);
- swap(a.created_by, b.created_by);
- swap(a.__isset, b.__isset);
-}
-
-} // namespace