orc

package module
v0.0.9 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jul 2, 2021 License: MIT Imports: 22 Imported by: 0

README

orc

Build Status code-coverage go-doc

Project Status

This project is still a work in progress.

Current Support

Column Encoding Read Write Go Type
SmallInt, Int, BigInt ✓ int64
Float, Double ✓ float32, float64
String, Char, and VarChar ✓ string
Boolean ✓ bool
TinyInt ✓ byte
Binary ✓ []byte
Decimal ✓ orc.Decimal
Date ✓ orc.Date (time.Time)
Timestamp ✓ time.Time
Struct ✓ orc.Struct (map[string]interface{})
List ✓ []interface{}
Map ✓ []orc.MapEntry
Union ✓ interface{}
  • The writer support is in its late stages, however, I do not recommend using it yet.

Example

r, err := Open("./examples/demo-12-zlib.orc")
if err != nil {
    log.Fatal(err)
}
defer r.Close()

// Create a new Cursor reading the provided columns.
c := r.Select("_col0", "_col1", "_col2")

// Iterate over each stripe in the file.
for c.Stripes() {
    
    // Iterate over each row in the stripe.
    for c.Next() {
          
        // Retrieve a slice of interface values for the current row.
        log.Println(c.Row())
        
    }
   
}

if err := c.Err(); err != nil {
    log.Fatal(err)
}

Documentation

Index

Constants

View Source 
const (
	// MinRepeatSize is the minimum number of repeated values required to use run length encoding.
	MinRepeatSize = 3
	// MaxShortRepeatLength is the maximum run length used for RLEV2IntShortRepeat sequences.
	MaxShortRepeatLength = 10
	// MaxScope is the maximum number of values that can be buffered before being flushed.
	MaxScope = 512
)
View Source 
const (
	MaxRepeatSize = 127 + MinRepeatSize
	MinDelta      = -128
	MaxDelta      = 127
)
View Source 
const (
	// InitialDictionarySize is the initial size used when creating the dictionary.
	InitialDictionarySize = 4096
	// DictionaryEncodingThreshold is the threshold ratio of unique items to the total count of items.
	DictionaryEncodingThreshold = 0.49
)
View Source 
const (
	BufferSize = 64
)
View Source 
const (
	MaxLiteralSize = 128
)
View Source 
const (
	// TimestampBaseSeconds is 1 January 2015, the base value for all timestamp values.
	TimestampBaseSeconds int64 = 1420070400
)

Variables

View Source 
var (
	// Version0_11 is an ORC file version compatible with Hive 0.11.
	Version0_11 = Version{"0.11", 0, 11}
	// Version0_12 is an ORC file version compatible with Hive 0.12.
	Version0_12 = Version{"0.12", 0, 12}
)
View Source 
var (
	ErrEOFUnsignedVInt = errors.New("EOF while reading unsigned vint")
	ErrCorrupt         = errors.New("ORC file is corrupt")
)
View Source 
var (
	CategoryBoolean   = Category{"boolean", true, proto.Type_BOOLEAN.Enum()}
	CategoryByte      = Category{"tinyint", true, proto.Type_BYTE.Enum()}
	CategoryShort     = Category{"smallint", true, proto.Type_SHORT.Enum()}
	CategoryInt       = Category{"int", true, proto.Type_INT.Enum()}
	CategoryLong      = Category{"bigint", true, proto.Type_LONG.Enum()}
	CategoryFloat     = Category{"float", true, proto.Type_FLOAT.Enum()}
	CategoryDouble    = Category{"double", true, proto.Type_DOUBLE.Enum()}
	CategoryString    = Category{"string", true, proto.Type_STRING.Enum()}
	CategoryDate      = Category{"date", true, proto.Type_DATE.Enum()}
	CategoryTimestamp = Category{"timestamp", true, proto.Type_TIMESTAMP.Enum()}
	CategoryBinary    = Category{"binary", true, proto.Type_BINARY.Enum()}
	CategoryDecimal   = Category{"decimal", true, proto.Type_DECIMAL.Enum()}
	CategoryVarchar   = Category{"varchar", true, proto.Type_VARCHAR.Enum()}
	CategoryChar      = Category{"char", true, proto.Type_CHAR.Enum()}
	CategoryList      = Category{"array", false, proto.Type_LIST.Enum()}
	CategoryMap       = Category{"map", false, proto.Type_MAP.Enum()}
	CategoryStruct    = Category{"struct", false, proto.Type_STRUCT.Enum()}
	CategoryUnion     = Category{"uniontype", false, proto.Type_UNION.Enum()}
	Categories        = []Category{
		CategoryBoolean,
		CategoryByte,
		CategoryShort,
		CategoryInt,
		CategoryLong,
		CategoryFloat,
		CategoryDouble,
		CategoryString,
		CategoryDate,
		CategoryTimestamp,
		CategoryBinary,
		CategoryDecimal,
		CategoryVarchar,
		CategoryChar,
		CategoryList,
		CategoryMap,
		CategoryStruct,
		CategoryUnion,
	}
)
View Source 
var (

	// WriterImplementation identifies the writer implementation
	WriterImplementation = uint32(3)
	// WriterVersion identifies the writer version being used.
	WriterVersion = uint32(6)
	// DefaultStripeTargetSize is the size in bytes over which a stripe should be written to the underlying file.
	DefaultStripeTargetSize int64 = 200 * 1024 * 1024
	// DefaultStripeTargetRowCount is the number of rows over which a stripe should be written to the underlying file.
	DefaultStripeTargetRowCount int64 = 1024 * 1024
	// DefaultStripeWriterTimezone is the timezone that writer adds into the stripe footer.
	DefaultStripeWriterTimezone string = "GMT"
	// DefaultCompressionChunkSize is the default size of compression chunks within each stream.
	DefaultCompressionChunkSize uint64 = 256 * 1024
	// DefaultRowIndexStride is the default number of rows between indexes
	DefaultRowIndexStride uint32 = 10000
)

Functions

func NewStringPosition 

func NewStringPosition(value string) *stringPosition

Types

type BaseStatistics 

type BaseStatistics struct {
	*proto.ColumnStatistics
}

func NewBaseStatistics 

func NewBaseStatistics() BaseStatistics

func (BaseStatistics) Add 

func (b BaseStatistics) Add(value interface{})

func (BaseStatistics) Merge 

func (b BaseStatistics) Merge(other ColumnStatistics)

func (BaseStatistics) Statistics 

func (b BaseStatistics) Statistics() *proto.ColumnStatistics

type BaseTreeReader 

type BaseTreeReader struct {
	*BooleanReader
}

BaseTreeReader wraps a *BooleanReader and is used for reading the Present stream in all TreeReader implementations.

func NewBaseTreeReader 

func NewBaseTreeReader(r io.Reader) BaseTreeReader

NewBaseTreeReader return a new BaseTreeReader from the provided io.Reader.

func (BaseTreeReader) Err 

func (b BaseTreeReader) Err() error

Err returns the last error to occur.

func (BaseTreeReader) IsPresent 

func (b BaseTreeReader) IsPresent() bool

IsPresent returns true if a value is available and is present in the stream.

func (BaseTreeReader) Next 

func (b BaseTreeReader) Next() bool

Next returns the next available value.

type BaseTreeWriter 

type BaseTreeWriter struct {
	// contains filtered or unexported fields
}

BaseTreeWriter is a TreeWriter implementation that writes to the present stream. It is the basis for all other TreeWriter implementations.

func NewBaseTreeWriter 

func NewBaseTreeWriter(category Category, codec CompressionCodec) BaseTreeWriter

NewBaseTreeWriter is a TreeWriter that is embedded in all other TreeWriter implementations.

func (*BaseTreeWriter) AddPositionRecorder 

func (b *BaseTreeWriter) AddPositionRecorder(recorder PositionRecorder)

func (*BaseTreeWriter) AddStream 

func (b *BaseTreeWriter) AddStream(kind *proto.Stream_Kind) Stream

func (*BaseTreeWriter) Close 

func (b *BaseTreeWriter) Close() error

Close flushes the underlying BufferedWriter returning an error if one occurs.

func (*BaseTreeWriter) Flush 

func (b *BaseTreeWriter) Flush() error

Flush flushes the underlying BufferedWriter returning an error if one occurs.

func (*BaseTreeWriter) RecordPositions 

func (b *BaseTreeWriter) RecordPositions()

func (*BaseTreeWriter) RowIndex 

func (b *BaseTreeWriter) RowIndex() *proto.RowIndex

func (*BaseTreeWriter) Statistics 

func (b *BaseTreeWriter) Statistics() ColumnStatistics

func (*BaseTreeWriter) Streams 

func (b *BaseTreeWriter) Streams() []Stream

func (*BaseTreeWriter) Write 

func (b *BaseTreeWriter) Write(i interface{}) error

Write checks whether i is nil and writes an appropriate true or false value to the underlying isPresent stream.

type BinaryTreeReader 

type BinaryTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

BinaryTreeReader is a TreeReader that reads a Binary type column.

func NewBinaryTreeReader 

func NewBinaryTreeReader(present, data, length io.Reader, encoding *proto.ColumnEncoding) (*BinaryTreeReader, error)

func (*BinaryTreeReader) Binary 

func (r *BinaryTreeReader) Binary() []byte

func (*BinaryTreeReader) Err 

func (r *BinaryTreeReader) Err() error

func (*BinaryTreeReader) Next 

func (r *BinaryTreeReader) Next() bool

func (*BinaryTreeReader) Value 

func (r *BinaryTreeReader) Value() interface{}

type BooleanReader 

type BooleanReader struct {
	*RunLengthByteReader
	// contains filtered or unexported fields
}

func NewBooleanReader 

func NewBooleanReader(r io.ByteReader) *BooleanReader

func (*BooleanReader) Bool 

func (b *BooleanReader) Bool() bool

func (*BooleanReader) Err 

func (b *BooleanReader) Err() error

func (*BooleanReader) Next 

func (b *BooleanReader) Next() bool

func (*BooleanReader) Value 

func (b *BooleanReader) Value() interface{}

type BooleanTreeReader 

type BooleanTreeReader struct {
	BaseTreeReader
	*BooleanReader
}

func NewBooleanTreeReader 

func NewBooleanTreeReader(present, data io.Reader, encoding *proto.ColumnEncoding) (*BooleanTreeReader, error)

func (*BooleanTreeReader) Err 

func (b *BooleanTreeReader) Err() error

func (*BooleanTreeReader) Next 

func (b *BooleanTreeReader) Next() bool

func (*BooleanTreeReader) Value 

func (b *BooleanTreeReader) Value() interface{}

type BooleanTreeWriter 

type BooleanTreeWriter struct {
	BaseTreeWriter
	*BooleanWriter
	*BufferedWriter
}

func NewBooleanTreeWriter 

func NewBooleanTreeWriter(category Category, codec CompressionCodec) (*BooleanTreeWriter, error)

func (*BooleanTreeWriter) Close 

func (b *BooleanTreeWriter) Close() error

func (*BooleanTreeWriter) Encoding 

func (b *BooleanTreeWriter) Encoding() *proto.ColumnEncoding

func (*BooleanTreeWriter) Flush 

func (b *BooleanTreeWriter) Flush() error

func (*BooleanTreeWriter) Write 

func (b *BooleanTreeWriter) Write(value interface{}) error

type BooleanWriter 

type BooleanWriter struct {
	*RunLengthByteWriter
	// contains filtered or unexported fields
}

func NewBooleanWriter 

func NewBooleanWriter(w io.ByteWriter) *BooleanWriter

func (*BooleanWriter) Close 

func (b *BooleanWriter) Close() error

func (*BooleanWriter) Flush 

func (b *BooleanWriter) Flush() error

func (*BooleanWriter) WriteBool 

func (b *BooleanWriter) WriteBool(t bool) error

type BucketStatistics 

type BucketStatistics struct {
	BaseStatistics
}

func NewBucketStatistics 

func NewBucketStatistics() *BucketStatistics

type BufferedWriter 

type BufferedWriter struct {
	sync.Mutex
	// contains filtered or unexported fields
}

func NewBufferedWriter 

func NewBufferedWriter(codec CompressionCodec) *BufferedWriter

NewBufferedWriter returns a new BufferedWriter using the provided CompressionCodec.

func (*BufferedWriter) Close 

func (b *BufferedWriter) Close() error

Close flushes any buffered bytes to the underlying writer.

func (*BufferedWriter) Flush 

func (b *BufferedWriter) Flush() error

func (*BufferedWriter) Len 

func (b *BufferedWriter) Len() int

func (*BufferedWriter) Positions 

func (b *BufferedWriter) Positions() []uint64

func (*BufferedWriter) Read 

func (b *BufferedWriter) Read(p []byte) (int, error)

func (*BufferedWriter) Reset 

func (b *BufferedWriter) Reset()

Reset resets the underlying encoded buffer

func (*BufferedWriter) Write 

func (b *BufferedWriter) Write(p []byte) (int, error)

Write writes the provided byte slice to the underlying buffer. If the desired chunk size is reached, the buffer is compressed

func (*BufferedWriter) WriteByte 

func (b *BufferedWriter) WriteByte(c byte) error

WriteByte writes a byte to the underlying buffer. If the desired chunk size is reached, the buffer is compressed

type ByteTreeReader 

type ByteTreeReader struct {
	BaseTreeReader
	*RunLengthByteReader
}

func NewByteTreeReader 

func NewByteTreeReader(present, data io.Reader, encoding *proto.ColumnEncoding) (*ByteTreeReader, error)

func (*ByteTreeReader) Err 

func (b *ByteTreeReader) Err() error

func (*ByteTreeReader) Next 

func (b *ByteTreeReader) Next() bool

func (*ByteTreeReader) Value 

func (b *ByteTreeReader) Value() interface{}

type Category 

type Category struct {
	// contains filtered or unexported fields
}

func (Category) String 

func (c Category) String() string

type ColumnIterator 

type ColumnIterator interface {
	// Range iterates [from,until)
	Range(from int, until int, f func(int, interface{}) error) error
	// Count returns the total length of the column
	Count() int
}

ColumnIterator ...

type ColumnStatistics 

type ColumnStatistics interface {
	Statistics() *proto.ColumnStatistics
	Add(value interface{})
	Merge(other ColumnStatistics)
	Reset()
}

func NewColumnStatistics 

func NewColumnStatistics(category Category) ColumnStatistics

type CompressionCodec 

type CompressionCodec interface {
	Encoder(w io.Writer) io.WriteCloser
	Decoder(r io.Reader) io.Reader
}

CompressionCodec is an interface that provides methods for creating an Encoder or Decoder of the CompressionCodec implementation.

type CompressionNone 

type CompressionNone struct{}

CompressionNone is a CompressionCodec that implements no compression.

func (CompressionNone) Decoder 

func (c CompressionNone) Decoder(r io.Reader) io.Reader

Decoder implements the CompressionCodec interface.

func (CompressionNone) Encoder 

func (c CompressionNone) Encoder(w io.Writer) io.WriteCloser

Encoder implements the CompressionCodec interface.

type CompressionNoneEncoder 

type CompressionNoneEncoder struct {
	// contains filtered or unexported fields
}

func (CompressionNoneEncoder) Close 

func (c CompressionNoneEncoder) Close() error

func (CompressionNoneEncoder) Flush 

func (c CompressionNoneEncoder) Flush() error

func (CompressionNoneEncoder) Write 

func (c CompressionNoneEncoder) Write(p []byte) (int, error)

type CompressionSnappy 

type CompressionSnappy struct{}

CompressionSnappy implements the CompressionCodec for Snappy compression.

func (CompressionSnappy) Decoder 

func (c CompressionSnappy) Decoder(r io.Reader) io.Reader

Decoder implements the CompressionCodec interface.

func (CompressionSnappy) Encoder 

func (c CompressionSnappy) Encoder(w io.Writer) io.WriteCloser

Encoder implements the CompressionCodec interface. This is currently not implemented.

type CompressionSnappyDecoder 

type CompressionSnappyDecoder struct {
	// contains filtered or unexported fields
}

CompressionSnappyDecoder implements the decoder for CompressionSnappy.

func (*CompressionSnappyDecoder) Read 

func (c *CompressionSnappyDecoder) Read(p []byte) (int, error)

type CompressionSnappyEncoder 

type CompressionSnappyEncoder struct {
	// contains filtered or unexported fields
}

func (*CompressionSnappyEncoder) Close 

func (c *CompressionSnappyEncoder) Close() error

func (*CompressionSnappyEncoder) Write 

func (c *CompressionSnappyEncoder) Write(p []byte) (int, error)

type CompressionZlib 

type CompressionZlib struct {
	Level    int
	Strategy int
}

func (CompressionZlib) Decoder 

func (c CompressionZlib) Decoder(r io.Reader) io.Reader

Decoder implements the CompressionCodec interface.

func (CompressionZlib) Encoder 

func (c CompressionZlib) Encoder(w io.Writer) io.WriteCloser

Encoder implements the CompressionCodec interface. This is currently not implemented.

type CompressionZlibDecoder 

type CompressionZlibDecoder struct {
	// contains filtered or unexported fields
}

CompressionZlibDecoder implements the CompressionCodec for Zlib compression.

func (*CompressionZlibDecoder) Read 

func (c *CompressionZlibDecoder) Read(p []byte) (int, error)

type CompressionZlibEncoder 

type CompressionZlibEncoder struct {
	Level int
	// contains filtered or unexported fields
}

CompressionZlibEncoder implements the CompressionCodec for Zlib compression.

func (*CompressionZlibEncoder) Close 

func (c *CompressionZlibEncoder) Close() error

func (*CompressionZlibEncoder) Write 

func (c *CompressionZlibEncoder) Write(p []byte) (int, error)

type Cursor 

type Cursor struct {
	*Reader
	*Stripe
	// contains filtered or unexported fields
}

Cursor is used for iterating through the stripes and rows within the ORC file.

func (*Cursor) Err 

func (c *Cursor) Err() error

Err returns the last error to have occurred.

func (*Cursor) Next 

func (c *Cursor) Next() bool

Next returns true if another set of records are available.

func (*Cursor) Row 

func (c *Cursor) Row() []interface{}

Row returns the next row of values.

func (*Cursor) RowIndex 

func (c *Cursor) RowIndex(column string) (*proto.RowIndex, error)

RowIndex returns the row index for the provided column from the current strip

func (*Cursor) Scan 

func (c *Cursor) Scan(dest ...interface{}) error

Scan assigns the values returned by the readers to the destination slice.

func (*Cursor) Select 

func (c *Cursor) Select(fields ...string) *Cursor

Select determines the columns that will be read from the ORC file. Only streams for the selected columns will be loaded into memory.

func (*Cursor) SelectStripe 

func (c *Cursor) SelectStripe(n int) error

SelectStripe retrieves the stream information for the specified stripe.

func (*Cursor) Stripes 

func (c *Cursor) Stripes() bool

Stripes prepares the next stripe for reading, returning true once its ready. It returns false if an error occurs whilst preparing the stripe.

type Date 

type Date struct {
	time.Time
}

Date is a date value represented by an underlying time.Time.

type DateTreeReader 

type DateTreeReader struct {
	*IntegerTreeReader
}

DateTreeReader is a TreeReader implementation that can read date column types.

func NewDateTreeReader 

func NewDateTreeReader(present, data io.Reader, encoding *proto.ColumnEncoding) (*DateTreeReader, error)

NewDateTreeReader returns a new DateTreeReader along with any error that occurs.

func (*DateTreeReader) Date 

func (d *DateTreeReader) Date() Date

Date returns the next date value as a time.Time.

func (*DateTreeReader) Value 

func (d *DateTreeReader) Value() interface{}

Value implements the TreeReader interface.

type DateTreeWriter 

type DateTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

DateTreeWriter is a TreeWriter implementation that writes an Date type column.

func NewDateTreeWriter 

func NewDateTreeWriter(category Category, codec CompressionCodec) (*DateTreeWriter, error)

NewDateTreeWriter returns a new DateTreeWriter.

func (*DateTreeWriter) Close 

func (w *DateTreeWriter) Close() error

Close closes the underlying writers returning an error if one occurs.

func (*DateTreeWriter) Encoding 

func (w *DateTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding used for the DateTreeWriter.

func (*DateTreeWriter) Flush 

func (w *DateTreeWriter) Flush() error

Flush flushes the underlying writers returning an error if one occurs.

func (*DateTreeWriter) Write 

func (w *DateTreeWriter) Write(value interface{}) error

Write writes a value returning an error if one occurs. It accepts a time.Time or a nil value for writing nulls to the stream. Any other types will return an error.

func (*DateTreeWriter) WriteDate 

func (w *DateTreeWriter) WriteDate(date time.Time) error

WriteDate writes an Date value returning an error if one occurs.

type Decimal 

type Decimal struct {
	Int   *big.Int
	Scale int64
}

Decimal is a decimal type.

func NewDecimal 

func NewDecimal(mant *big.Int, scale int64) Decimal

func (Decimal) Float32 

func (d Decimal) Float32() float32

func (Decimal) Float64 

func (d Decimal) Float64() float64

func (Decimal) MarshalJSON 

func (d Decimal) MarshalJSON() ([]byte, error)

MarshalJSON implements the json.Marshaller interface.

func (Decimal) String 

func (d Decimal) String() string

type DecimalTreeReader 

type DecimalTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

DecimalTreeReader is a TreeReader that reads a Decimal type column.

func NewDecimalTreeReader 

func NewDecimalTreeReader(present, data, secondary io.Reader, encoding *proto.ColumnEncoding, precision, scale int) (*DecimalTreeReader, error)

NewDecimalTreeReader returns a new instances of a DecimalTreeReader or an error if one occurs.

func (*DecimalTreeReader) Decimal 

func (d *DecimalTreeReader) Decimal() Decimal

Decimal returns the next decimal value as a float64

func (*DecimalTreeReader) Err 

func (d *DecimalTreeReader) Err() error

Err returns the last error to have occurred.

func (*DecimalTreeReader) Next 

func (d *DecimalTreeReader) Next() bool

Next returns true if a value is available.

func (*DecimalTreeReader) Value 

func (d *DecimalTreeReader) Value() interface{}

Value returns the next decimal value as an interface{}

type Dictionary 

type Dictionary struct {
	// contains filtered or unexported fields
}

Dictionary is a data structure that holds a distinct set of string values.

func NewDictionary 

func NewDictionary(initialCapacity int) *Dictionary

NewDictionary returns a new Dictionary intialised with the provided initialCapacity.

func (*Dictionary) Size 

func (d *Dictionary) Size() int

Size returns the number of values stored in the dictionary.

type DictionaryV2 

type DictionaryV2 struct {
	// contains filtered or unexported fields
}

Dictionary is a data structure that holds a distinct set of string values.

func NewDictionaryV2 

func NewDictionaryV2() *DictionaryV2

NewDictionaryV2 returns a new DictionaryV2 intialised with the provided initialCapacity.

type Double 

type Double float64

Double is ORC double type i.e. a float64.

type Float 

type Float float32

func (Float) MarshalJSON 

func (f Float) MarshalJSON() ([]byte, error)

type FloatTreeReader 

type FloatTreeReader struct {
	BaseTreeReader
	io.Reader
	// contains filtered or unexported fields
}

func NewFloatTreeReader 

func NewFloatTreeReader(bytesPerValue int, present, data io.Reader, encoding *proto.ColumnEncoding) (*FloatTreeReader, error)

func (*FloatTreeReader) Double 

func (r *FloatTreeReader) Double() Double

Double returns the next Double value.

func (*FloatTreeReader) Err 

func (r *FloatTreeReader) Err() error

func (*FloatTreeReader) Float 

func (r *FloatTreeReader) Float() Float

func (*FloatTreeReader) Next 

func (r *FloatTreeReader) Next() bool

func (*FloatTreeReader) Value 

func (r *FloatTreeReader) Value() interface{}

type FloatTreeWriter 

type FloatTreeWriter struct {
	BaseTreeWriter
	*BufferedWriter
	// contains filtered or unexported fields
}

FloatTreeWriter is a TreeWriter that writes to a Float or Double column type.

func NewFloatTreeWriter 

func NewFloatTreeWriter(category Category, codec CompressionCodec, bytesPerValue int) (*FloatTreeWriter, error)

NewFloatTreeWriter returns a new FloatTreeWriter or an error if one occurs.

func (*FloatTreeWriter) Close 

func (f *FloatTreeWriter) Close() error

func (*FloatTreeWriter) Encoding 

func (f *FloatTreeWriter) Encoding() *proto.ColumnEncoding

func (*FloatTreeWriter) Flush 

func (f *FloatTreeWriter) Flush() error

func (*FloatTreeWriter) Write 

func (f *FloatTreeWriter) Write(value interface{}) error

Write writes a float or double value returning an error if one occurs.

func (*FloatTreeWriter) WriteDouble 

func (f *FloatTreeWriter) WriteDouble(value interface{}) error

func (*FloatTreeWriter) WriteFloat 

func (f *FloatTreeWriter) WriteFloat(value interface{}) error

type IntegerReader 

type IntegerReader interface {
	TreeReader
	Int() int64
}

IntegerReader is an interface that provides methods for reading an integer stream that uses V1 or V2 encoding methods.

type IntegerStatistics 

type IntegerStatistics struct {
	BaseStatistics
	// contains filtered or unexported fields
}

func NewIntegerStatistics 

func NewIntegerStatistics() *IntegerStatistics

func (*IntegerStatistics) Add 

func (i *IntegerStatistics) Add(value interface{})

func (*IntegerStatistics) Merge 

func (i *IntegerStatistics) Merge(other ColumnStatistics)

func (*IntegerStatistics) Reset 

func (i *IntegerStatistics) Reset()

func (*IntegerStatistics) Statistics 

func (i *IntegerStatistics) Statistics() *proto.ColumnStatistics

type IntegerTreeReader 

type IntegerTreeReader struct {
	BaseTreeReader
	IntegerReader
}

IntegerTreeReader is a TreeReader that can read Integer type streams.

func NewIntegerTreeReader 

func NewIntegerTreeReader(present, data io.Reader, encoding *proto.ColumnEncoding) (*IntegerTreeReader, error)

NewIntegerTreeReader returns a new IntegerReader or an error if one occurs.

func (*IntegerTreeReader) Err 

func (i *IntegerTreeReader) Err() error

Err implements the TreeReader interface.

func (*IntegerTreeReader) Next 

func (i *IntegerTreeReader) Next() bool

Next implements the TreeReader interface.

func (*IntegerTreeReader) Value 

func (i *IntegerTreeReader) Value() interface{}

Value implements the TreeReader interface.

type IntegerTreeWriter 

type IntegerTreeWriter struct {
	BaseTreeWriter
	IntegerWriter
	*BufferedWriter
	// contains filtered or unexported fields
}

IntegerTreeWriter is a TreeWriter implementation that writes an integer type column.

func NewIntegerTreeWriter 

func NewIntegerTreeWriter(category Category, codec CompressionCodec) (*IntegerTreeWriter, error)

NewIntegerTreeWriter returns a new IntegerTreeWriter.

func (*IntegerTreeWriter) Close 

func (w *IntegerTreeWriter) Close() error

Close closes the underlying writers returning an error if one occurs.

func (*IntegerTreeWriter) Encoding 

func (w *IntegerTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding used for the IntegerTreeWriter.

func (*IntegerTreeWriter) Flush 

func (w *IntegerTreeWriter) Flush() error

Flush flushes the underlying writers returning an error if one occurs.

func (*IntegerTreeWriter) Write 

func (w *IntegerTreeWriter) Write(value interface{}) error

Write writes a value returning an error if one occurs. It accepts any form of integer or a nil value for writing nulls to the stream. Any other types will return an error.

func (*IntegerTreeWriter) WriteInt 

func (w *IntegerTreeWriter) WriteInt(value int64) error

WriteInt writes an integer value returning an error if one occurs.

type IntegerWriter 

type IntegerWriter interface {
	WriteInt(value int64) error
	Close() error
	Flush() error
}

IntegerWriter is an interface implemented by all integer type writers.

type ListTreeReader 

type ListTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

func NewListTreeReader 

func NewListTreeReader(present, length io.Reader, value TreeReader, encoding *proto.ColumnEncoding) (*ListTreeReader, error)

func (*ListTreeReader) Err 

func (r *ListTreeReader) Err() error

func (*ListTreeReader) List 

func (r *ListTreeReader) List() []interface{}

func (*ListTreeReader) Next 

func (r *ListTreeReader) Next() bool

func (*ListTreeReader) Value 

func (r *ListTreeReader) Value() interface{}

type ListTreeWriter 

type ListTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

func NewListTreeWriter 

func NewListTreeWriter(category Category, codec CompressionCodec, child TreeWriter) (*ListTreeWriter, error)

func (*ListTreeWriter) Close 

func (l *ListTreeWriter) Close() error

func (*ListTreeWriter) Encoding 

func (l *ListTreeWriter) Encoding() *proto.ColumnEncoding

func (*ListTreeWriter) Flush 

func (l *ListTreeWriter) Flush() error

func (*ListTreeWriter) Write 

func (l *ListTreeWriter) Write(value interface{}) error

type MapEntry 

type MapEntry struct {
	Key   interface{} `json:"key"`
	Value interface{} `json:"value"`
}

MapEntry is an individual entry in a Map.

type MapTreeReader 

type MapTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

MapTreeReader is a TreeReader that reads from map encoded columns.

func NewMapTreeReader 

func NewMapTreeReader(present, length io.Reader, key, value TreeReader, encoding *proto.ColumnEncoding) (*MapTreeReader, error)

NewMapTreeReader returns a new instance of a MapTreeReader.

func (*MapTreeReader) Map 

func (m *MapTreeReader) Map() []MapEntry

Map returns the next available row of MapEntries.

func (*MapTreeReader) Next 

func (m *MapTreeReader) Next() bool

Next returns true if another row is available.

func (*MapTreeReader) Value 

func (m *MapTreeReader) Value() interface{}

Value implements the TreeReader interface, returning the next available row.

type MapTreeWriter 

type MapTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

func NewMapTreeWriter 

func NewMapTreeWriter(category Category, codec CompressionCodec, keyWriter, valueWriter TreeWriter) (*MapTreeWriter, error)

func (*MapTreeWriter) Close 

func (m *MapTreeWriter) Close() error

func (*MapTreeWriter) Encoding 

func (m *MapTreeWriter) Encoding() *proto.ColumnEncoding

func (*MapTreeWriter) Flush 

func (m *MapTreeWriter) Flush() error

func (*MapTreeWriter) Write 

func (m *MapTreeWriter) Write(value interface{}) error

type PositionRecorder 

type PositionRecorder interface {
	Positions() []uint64
}

type PositionRecorders 

type PositionRecorders []PositionRecorder

func NewPositionRecorders 

func NewPositionRecorders(recorders ...PositionRecorder) PositionRecorders

type RLEEncodingType 

type RLEEncodingType int

RLEEncodingType is a run length encoding type specified within the Apache ORC file documentation: https://orc.apache.org/docs/run-length.html 

const (
	RLEV2IntShortRepeat RLEEncodingType = 0
	RLEV2IntDirect      RLEEncodingType = 1
	RLEV2IntPatchedBase RLEEncodingType = 2
	RLEV2IntDelta       RLEEncodingType = 3
)

func (RLEEncodingType) String 

func (i RLEEncodingType) String() string

type Reader 

type Reader struct {
	// contains filtered or unexported fields
}

func NewReader 

func NewReader(r SizedReaderAt) (*Reader, error)

func Open 

func Open(filepath string) (*Reader, error)

Open opens the file at the provided filepath.

func (*Reader) Close 

func (r *Reader) Close() error

func (*Reader) Metadata 

func (r *Reader) Metadata() *proto.Metadata

func (*Reader) NumRows 

func (r *Reader) NumRows() int

func (*Reader) NumStripes 

func (r *Reader) NumStripes() (int, error)

func (*Reader) Schema 

func (r *Reader) Schema() *TypeDescription

func (*Reader) Select 

func (r *Reader) Select(fields ...string) *Cursor

type RunLengthByteReader 

type RunLengthByteReader struct {
	// contains filtered or unexported fields
}

RunLengthByteReader reads a byte run length encoded stream from ByteReader r.

func NewRunLengthByteReader 

func NewRunLengthByteReader(r io.ByteReader) *RunLengthByteReader

func (*RunLengthByteReader) Byte 

func (b *RunLengthByteReader) Byte() byte

func (*RunLengthByteReader) Err 

func (b *RunLengthByteReader) Err() error

func (*RunLengthByteReader) Next 

func (b *RunLengthByteReader) Next() bool

func (*RunLengthByteReader) ReadByte 

func (b *RunLengthByteReader) ReadByte() (byte, error)

func (*RunLengthByteReader) Value 

func (b *RunLengthByteReader) Value() interface{}

type RunLengthByteWriter 

type RunLengthByteWriter struct {
	io.ByteWriter
	// contains filtered or unexported fields
}

func NewRunLengthByteWriter 

func NewRunLengthByteWriter(w io.ByteWriter) *RunLengthByteWriter

func (*RunLengthByteWriter) Close 

func (b *RunLengthByteWriter) Close() error

func (*RunLengthByteWriter) Flush 

func (b *RunLengthByteWriter) Flush() error

func (*RunLengthByteWriter) WriteByte 

func (b *RunLengthByteWriter) WriteByte(value byte) error

type RunLengthIntegerReader 

type RunLengthIntegerReader struct {
	// contains filtered or unexported fields
}

func NewRunLengthIntegerReader 

func NewRunLengthIntegerReader(r io.ByteReader, signed bool) *RunLengthIntegerReader

func (*RunLengthIntegerReader) Err 

func (r *RunLengthIntegerReader) Err() error

func (*RunLengthIntegerReader) Int 

func (r *RunLengthIntegerReader) Int() int64

func (*RunLengthIntegerReader) Next 

func (r *RunLengthIntegerReader) Next() bool

func (*RunLengthIntegerReader) ReadByte 

func (r *RunLengthIntegerReader) ReadByte() (byte, error)

func (*RunLengthIntegerReader) Value 

func (r *RunLengthIntegerReader) Value() interface{}

type RunLengthIntegerReaderV2 

type RunLengthIntegerReaderV2 struct {
	// contains filtered or unexported fields
}

func NewRunLengthIntegerReaderV2 

func NewRunLengthIntegerReaderV2(r io.ByteReader, signed bool, skipCorrupt bool) *RunLengthIntegerReaderV2

func (*RunLengthIntegerReaderV2) Err 

func (r *RunLengthIntegerReaderV2) Err() error

func (*RunLengthIntegerReaderV2) Int 

func (r *RunLengthIntegerReaderV2) Int() int64

func (*RunLengthIntegerReaderV2) Next 

func (r *RunLengthIntegerReaderV2) Next() bool

func (*RunLengthIntegerReaderV2) ReadByte 

func (r *RunLengthIntegerReaderV2) ReadByte() (byte, error)

func (*RunLengthIntegerReaderV2) Value 

func (r *RunLengthIntegerReaderV2) Value() interface{}

type RunLengthIntegerWriter 

type RunLengthIntegerWriter struct {
	// contains filtered or unexported fields
}

func NewRunLengthIntegerWriter 

func NewRunLengthIntegerWriter(w io.ByteWriter, signed bool) *RunLengthIntegerWriter

func (*RunLengthIntegerWriter) Close 

func (w *RunLengthIntegerWriter) Close() error

func (*RunLengthIntegerWriter) Flush 

func (w *RunLengthIntegerWriter) Flush() error

func (*RunLengthIntegerWriter) WriteInt 

func (w *RunLengthIntegerWriter) WriteInt(value int64) error

type RunLengthIntegerWriterV2 

type RunLengthIntegerWriterV2 struct {
	// contains filtered or unexported fields
}

func NewRunLengthIntegerWriterV2 

func NewRunLengthIntegerWriterV2(w io.ByteWriter, signed bool) *RunLengthIntegerWriterV2

func (*RunLengthIntegerWriterV2) Close 

func (i *RunLengthIntegerWriterV2) Close() error

func (*RunLengthIntegerWriterV2) Flush 

func (i *RunLengthIntegerWriterV2) Flush() error

func (*RunLengthIntegerWriterV2) WriteInt 

func (i *RunLengthIntegerWriterV2) WriteInt(val int64) error

type SizedReaderAt 

type SizedReaderAt interface {
	io.ReaderAt
	Size() int64
}

type Stream 

type Stream struct {
	// contains filtered or unexported fields
}

Stream is an individual stream for the TreeWriter.

func (Stream) Positions 

func (s Stream) Positions() []uint64

type StringDictionaryTreeReader 

type StringDictionaryTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

func NewStringDictionaryTreeReader 

func NewStringDictionaryTreeReader(present, data, length, dictionary io.Reader, encoding *proto.ColumnEncoding) (*StringDictionaryTreeReader, error)

func (*StringDictionaryTreeReader) Err 

func (s *StringDictionaryTreeReader) Err() error

func (*StringDictionaryTreeReader) Next 

func (s *StringDictionaryTreeReader) Next() bool

func (*StringDictionaryTreeReader) String 

func (s *StringDictionaryTreeReader) String() string

func (*StringDictionaryTreeReader) Value 

func (s *StringDictionaryTreeReader) Value() interface{}

type StringDirectTreeReader 

type StringDirectTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

StringDirectTreeReader is a StringTreeReader implementation that can read direct encoded string type columns.

func NewStringDirectTreeReader 

func NewStringDirectTreeReader(present, data, length io.Reader, kind proto.ColumnEncoding_Kind) (*StringDirectTreeReader, error)

func (*StringDirectTreeReader) Err 

func (s *StringDirectTreeReader) Err() error

func (*StringDirectTreeReader) Next 

func (s *StringDirectTreeReader) Next() bool

func (*StringDirectTreeReader) String 

func (s *StringDirectTreeReader) String() string

func (*StringDirectTreeReader) Value 

func (s *StringDirectTreeReader) Value() interface{}

type StringStatistics 

type StringStatistics struct {
	BaseStatistics
	// contains filtered or unexported fields
}

func NewStringStatistics 

func NewStringStatistics() *StringStatistics

func (*StringStatistics) Add 

func (s *StringStatistics) Add(value interface{})

func (*StringStatistics) Merge 

func (s *StringStatistics) Merge(other ColumnStatistics)

func (*StringStatistics) Reset 

func (s *StringStatistics) Reset()

func (*StringStatistics) Statistics 

func (s *StringStatistics) Statistics() *proto.ColumnStatistics

type StringTreeReader 

type StringTreeReader interface {
	TreeReader
	String() string
}

IntegerReader is an interface that provides methods for reading a string stream.

func NewStringTreeReader 

func NewStringTreeReader(present, data, length, dictionary io.Reader, encoding *proto.ColumnEncoding) (StringTreeReader, error)

NewStringTreeReader returns a StringTreeReader implementation along with any error that occurs.s

type StringTreeWriter 

type StringTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

StringTreeWriter is a TreeWriter implementation that writes to a string type column. It dynamically selects the most appropriate encoding format between direct and dictionary encoding based on the cardinality of the values up to the first call to Flush.

func NewStringTreeWriter 

func NewStringTreeWriter(category Category, codec CompressionCodec) (*StringTreeWriter, error)

NewStringTreeWriter returns a new StringTreeWriter or an error if one occurs.

func (*StringTreeWriter) Close 

func (s *StringTreeWriter) Close() error

Close closes the underlying writes returning an error if one occurs.

func (*StringTreeWriter) Encoding 

func (s *StringTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding for the writer, either DICTIONARY_V2 or DIRECT_V2.

func (*StringTreeWriter) Flush 

func (s *StringTreeWriter) Flush() error

func (*StringTreeWriter) Write 

func (s *StringTreeWriter) Write(value interface{}) error

Write writes the provided value to the underlying writers. It returns an error if the value is not a string type or if an error occurs during writing.

func (*StringTreeWriter) WriteString 

func (s *StringTreeWriter) WriteString(value string) error

WriteString writes a string value to the StringTreeWriter returning an error if one occurs.

type Stripe 

type Stripe struct {
	*proto.StripeInformation
	// contains filtered or unexported fields
}

func NewStripe 

func NewStripe(info *proto.StripeInformation, included ...int) *Stripe

func (*Stripe) FromReader 

func (s *Stripe) FromReader(r *Reader) error

type Struct 

type Struct map[string]interface{}

type StructTreeReader 

type StructTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

func NewStructTreeReader 

func NewStructTreeReader(present io.Reader, children map[string]TreeReader) (*StructTreeReader, error)

func (*StructTreeReader) Err 

func (s *StructTreeReader) Err() error

func (*StructTreeReader) Next 

func (s *StructTreeReader) Next() bool

func (*StructTreeReader) Struct 

func (s *StructTreeReader) Struct() Struct

func (*StructTreeReader) Value 

func (s *StructTreeReader) Value() interface{}

type StructTreeWriter 

type StructTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

StructTreeWriter is a TreeWriter implementation that can write a struct column type.

func NewStructTreeWriter 

func NewStructTreeWriter(category Category, codec CompressionCodec, children []TreeWriter) (*StructTreeWriter, error)

NewStructTreeWriter returns a StructTreeWriter using the provided io.Writer and children TreeWriters. It additionally returns an error if one occurs.

func (*StructTreeWriter) Close 

func (s *StructTreeWriter) Close() error

Close closes the StructTreeWriter and its child TreeWriters returning an error if one occurs.

func (*StructTreeWriter) Encoding 

func (s *StructTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding for the StructTreeWriter.

func (*StructTreeWriter) Flush 

func (s *StructTreeWriter) Flush() error

Flush flushes the StructTreeWriter and its child TreeWriters returning an error if one occurs.

func (*StructTreeWriter) RecordPositions 

func (s *StructTreeWriter) RecordPositions()

func (*StructTreeWriter) Write 

func (s *StructTreeWriter) Write(value interface{}) error

Write writes a value to the underlying child TreeWriters. It returns an error if one occurs.

type TimestampStatistics 

type TimestampStatistics struct {
	BaseStatistics
	// contains filtered or unexported fields
}

func NewTimestampStatistics 

func NewTimestampStatistics() *TimestampStatistics

func (*TimestampStatistics) Add 

func (i *TimestampStatistics) Add(value interface{})

func (*TimestampStatistics) Merge 

func (i *TimestampStatistics) Merge(other ColumnStatistics)

func (*TimestampStatistics) Reset 

func (i *TimestampStatistics) Reset()

func (*TimestampStatistics) Statistics 

func (i *TimestampStatistics) Statistics() *proto.ColumnStatistics

type TimestampTreeReader 

type TimestampTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

TimestampTreeReader is a TreeReader implementation that reads timestamp type columns.

func NewTimestampTreeReader 

func NewTimestampTreeReader(present, data, secondary io.Reader, encoding *proto.ColumnEncoding) (*TimestampTreeReader, error)

NewTimestampTreeReader returns a new TimestampTreeReader along with any error that occurs.

func (*TimestampTreeReader) Err 

func (t *TimestampTreeReader) Err() error

Err implements the TreeReader interface.

func (*TimestampTreeReader) Next 

func (t *TimestampTreeReader) Next() bool

Next implements the TreeReader interface.

func (*TimestampTreeReader) Timestamp 

func (t *TimestampTreeReader) Timestamp() time.Time

ValueTimestamp returns the next timestamp value.

func (*TimestampTreeReader) Value 

func (t *TimestampTreeReader) Value() interface{}

Value implements the TreeReader interface.

type TimestampTreeWriter 

type TimestampTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

TimestampTreeWriter is a TreeWriter implementation that writes an Timestamp type column.

func NewTimestampTreeWriter 

func NewTimestampTreeWriter(category Category, codec CompressionCodec) (*TimestampTreeWriter, error)

NewTimestampTreeWriter returns a new TimestampTreeWriter.

func (*TimestampTreeWriter) Close 

func (w *TimestampTreeWriter) Close() error

Close closes the underlying writers returning an error if one occurs.

func (*TimestampTreeWriter) Encoding 

func (w *TimestampTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding used for the TimestampTreeWriter.

func (*TimestampTreeWriter) Flush 

func (w *TimestampTreeWriter) Flush() error

Flush flushes the underlying writers returning an error if one occurs.

func (*TimestampTreeWriter) Write 

func (w *TimestampTreeWriter) Write(value interface{}) error

Write writes a value returning an error if one occurs. It accepts any form of Timestamp or a nil value for writing nulls to the stream. Any other types will return an error.

func (*TimestampTreeWriter) WriteTimestamp 

func (w *TimestampTreeWriter) WriteTimestamp(value time.Time) error

WriteTimestamp writes an Timestamp value returning an error if one occurs.

type TimestampWriter 

type TimestampWriter interface {
	WriteTimestamp(value time.Time) error
	Close() error
	Flush() error
}

TimestampWriter is an interface implemented by all Timestamp type writers.

type TreeReader 

type TreeReader interface {
	Next() bool
	Value() interface{}
	Err() error
}

TreeReader is an interface that provides methods for reading an individual stream.

type TreeWriter 

type TreeWriter interface {
	// Encoding returns the column encoding used for the TreeWriter.
	Encoding() *proto.ColumnEncoding
	// Write writes the interface value i to the TreeWriter, it returns an error
	// if i is of an unexpected type or if an error occurs whilst writing to
	// the underlying stream.
	Write(i interface{}) error
	// Close flushes the remaining data and closes the writer.
	Close() error
	// Flush flushes any outstanding data to the underlying writer.
	Flush() error
	// Streams returns a slice of streams for the TreeWriter.
	Streams() []Stream
	// RowIndex returns the RowIndex for the writer.
	RowIndex() *proto.RowIndex
	// RecordPositions
	RecordPositions()
	// Statistics
	Statistics() ColumnStatistics
}

TreeWriter is an interface for writing to a stream.

type TypeDescription 

type TypeDescription struct {
	// contains filtered or unexported fields
}

func NewTypeDescription 

func NewTypeDescription(fns ...TypeDescriptionTransformFunc) (*TypeDescription, error)

func ParseSchema 

func ParseSchema(schema string) (*TypeDescription, error)

func (*TypeDescription) Columns 

func (t *TypeDescription) Columns() []string

func (*TypeDescription) GetField 

func (t *TypeDescription) GetField(fieldName string) (*TypeDescription, error)

func (*TypeDescription) MarshalJSON 

func (t *TypeDescription) MarshalJSON() ([]byte, error)

MarshalJSON returns a json encoded byte slice of t.

func (*TypeDescription) String 

func (t *TypeDescription) String() string

func (*TypeDescription) ToJSON 

func (t *TypeDescription) ToJSON() string

ToJSON returns a json encoded string of t.

func (*TypeDescription) Type 

func (t *TypeDescription) Type() *proto.Type

func (*TypeDescription) Types 

func (t *TypeDescription) Types() []*proto.Type

type TypeDescriptionTransformFunc 

type TypeDescriptionTransformFunc func(t *TypeDescription) error

func AddChild 

func AddChild(fns ...TypeDescriptionTransformFunc) TypeDescriptionTransformFunc

func AddField 

func AddField(field string, fns ...TypeDescriptionTransformFunc) TypeDescriptionTransformFunc

func AddUnionChild 

func AddUnionChild(fns ...TypeDescriptionTransformFunc) TypeDescriptionTransformFunc

func SetCategory 

func SetCategory(category Category) TypeDescriptionTransformFunc

type UnionTreeReader 

type UnionTreeReader struct {
	BaseTreeReader
	// contains filtered or unexported fields
}

UnionTreeReader is a TreeReader that reads a Union type column.

func NewUnionTreeReader 

func NewUnionTreeReader(present, data io.Reader, children []TreeReader) (*UnionTreeReader, error)

NewUnionTreeReader returns a new instance of a UnionTreeReader or an error if one occurs.

func (*UnionTreeReader) Err 

func (u *UnionTreeReader) Err() error

Err returns the last error to have occurred.

func (*UnionTreeReader) Next 

func (u *UnionTreeReader) Next() bool

Next returns true if another value is available.

func (*UnionTreeReader) Value 

func (u *UnionTreeReader) Value() interface{}

Value returns the next value as an interface{}.

type UnionTreeWriter 

type UnionTreeWriter struct {
	BaseTreeWriter
	// contains filtered or unexported fields
}

UnionTreeWriter is a TreeWriter implementation that can write a unionvalue column type.

func NewUnionTreeWriter 

func NewUnionTreeWriter(category Category, codec CompressionCodec, children []TreeWriter) (*UnionTreeWriter, error)

NewUnionTreeWriter returns a UnionTreeWriter using the provided io.Writer and children TreeWriters. It additionally returns an error if one occurs.

func (*UnionTreeWriter) Close 

func (s *UnionTreeWriter) Close() error

Close closes the UnionTreeWriter and its child TreeWriters returning an error if one occurs.

func (*UnionTreeWriter) Encoding 

func (s *UnionTreeWriter) Encoding() *proto.ColumnEncoding

Encoding returns the column encoding for the UnionTreeWriter.

func (*UnionTreeWriter) Flush 

func (s *UnionTreeWriter) Flush() error

Flush flushes the UnionTreeWriter and its child TreeWriters returning an error if one occurs.

func (*UnionTreeWriter) RecordPositions 

func (s *UnionTreeWriter) RecordPositions()

func (*UnionTreeWriter) Write 

func (s *UnionTreeWriter) Write(value interface{}) error

func (*UnionTreeWriter) WriteUnion 

func (s *UnionTreeWriter) WriteUnion(value UnionValue) error

Write writes a value to the underlying child TreeWriters. It returns an error if one occurs.

type UnionValue 

type UnionValue struct {
	Tag   int         `json:"tag"`
	Value interface{} `json:"value"`
}

type Version 

type Version struct {
	// contains filtered or unexported fields
}

Version is the version of the ORC file.

type Writer 

type Writer struct {
	// contains filtered or unexported fields
}

func NewWriter 

func NewWriter(w io.Writer, fns ...WriterConfigFunc) (*Writer, error)

NewWriter returns a new ORC file writer that writes to the provided io.Writer.

func (*Writer) Close 

func (w *Writer) Close() error

func (*Writer) Flush 

func (w *Writer) Flush() error

Flush the current stripe to the underlying Writer

func (*Writer) Schema 

func (w *Writer) Schema() *TypeDescription

func (*Writer) Write 

func (w *Writer) Write(values ...interface{}) error

func (*Writer) WriteColumns 

func (w *Writer) WriteColumns(ColumnIterators []ColumnIterator) error

WriteColumns writes stripes by columns Allows only non nested struct

type WriterConfigFunc 

type WriterConfigFunc func(w *Writer) error

func AddUserMetadata 

func AddUserMetadata(name string, value []byte) WriterConfigFunc

func SetCompression 

func SetCompression(codec CompressionCodec) WriterConfigFunc

func SetSchema 

func SetSchema(schema *TypeDescription) WriterConfigFunc

func SetStripeTargetSize 

func SetStripeTargetSize(stripeTargetSize int64) WriterConfigFunc

Source Files

View all Source files

Directories

Path Synopsis
Package proto is a generated protocol buffer package.
 Package proto is a generated protocol buffer package.
tools
orc2csv

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.