arrow

package
v7.0.1 Latest Latest
Warning

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

 Go to latest Published: Jul 14, 2022 License: Apache-2.0, BSD-2-Clause, BSD-3-Clause, + 8 more Imports: 19 Imported by: 9

Documentation

Overview

Package arrow provides an implementation of Apache Arrow.

Apache Arrow is a cross-language development platform for in-memory data. It specifies a standardized language-independent columnar memory format for flat and hierarchical data, organized for efficient analytic operations on modern hardware. It also provides computational libraries and zero-copy streaming messaging and inter-process communication.

Basics

The fundamental data structure in Arrow is an Array, which holds a sequence of values of the same type. An array consists of memory holding the data and an additional validity bitmap that indicates if the corresponding entry in the array is valid (not null). If the array has no null entries, it is possible to omit this bitmap.

Example (FixedSizeListArray)

This example shows how to create a FixedSizeList array. The resulting array should be: 

[[0, 1, 2], (null), [3, 4, 5], [6, 7, 8], (null)]

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	lb := array.NewFixedSizeListBuilder(pool, 3, arrow.PrimitiveTypes.Int64)
	defer lb.Release()

	vb := lb.ValueBuilder().(*array.Int64Builder)
	vb.Reserve(10)

	lb.Append(true)
	vb.Append(0)
	vb.Append(1)
	vb.Append(2)

	lb.AppendNull()
	vb.AppendValues([]int64{-1, -1, -1}, nil)

	lb.Append(true)
	vb.Append(3)
	vb.Append(4)
	vb.Append(5)

	lb.Append(true)
	vb.Append(6)
	vb.Append(7)
	vb.Append(8)

	lb.AppendNull()

	arr := lb.NewArray().(*array.FixedSizeList)
	defer arr.Release()

	fmt.Printf("NullN()   = %d\n", arr.NullN())
	fmt.Printf("Len()     = %d\n", arr.Len())
	fmt.Printf("Type()    = %v\n", arr.DataType())
	fmt.Printf("List      = %v\n", arr)

}

Output:

NullN()   = 2
Len()     = 5
Type()    = fixed_size_list<item: int64, nullable>[3]
List      = [[0 1 2] (null) [3 4 5] [6 7 8] (null)]
Example (Float64Slice)

This example shows how one can slice an array. The initial (float64) array is: 

[1, 2, 3, (null), 4, 5]

and the sub-slice is: 

[3, (null), 4]

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	b := array.NewFloat64Builder(pool)
	defer b.Release()

	b.AppendValues(
		[]float64{1, 2, 3, -1, 4, 5},
		[]bool{true, true, true, false, true, true},
	)

	arr := b.NewFloat64Array()
	defer arr.Release()

	fmt.Printf("array = %v\n", arr)

	sli := array.NewSlice(arr, 2, 5).(*array.Float64)
	defer sli.Release()

	fmt.Printf("slice = %v\n", sli)

}

Output:

array = [1 2 3 (null) 4 5]
slice = [3 (null) 4]
Example (Float64Tensor2x5) 
package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
	"github.com/apache/arrow/go/v7/arrow/tensor"
)

func main() {
	pool := memory.NewGoAllocator()

	b := array.NewFloat64Builder(pool)
	defer b.Release()

	raw := []float64{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
	b.AppendValues(raw, nil)

	arr := b.NewFloat64Array()
	defer arr.Release()

	f64 := tensor.NewFloat64(arr.Data(), []int64{2, 5}, nil, []string{"x", "y"})
	defer f64.Release()

	for _, i := range [][]int64{
		{0, 0},
		{0, 1},
		{0, 2},
		{0, 3},
		{0, 4},
		{1, 0},
		{1, 1},
		{1, 2},
		{1, 3},
		{1, 4},
	} {
		fmt.Printf("arr%v = %v\n", i, f64.Value(i))
	}

}

Output:

arr[0 0] = 1
arr[0 1] = 2
arr[0 2] = 3
arr[0 3] = 4
arr[0 4] = 5
arr[1 0] = 6
arr[1 1] = 7
arr[1 2] = 8
arr[1 3] = 9
arr[1 4] = 10
Example (Float64Tensor2x5ColMajor) 
package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
	"github.com/apache/arrow/go/v7/arrow/tensor"
)

func main() {
	pool := memory.NewGoAllocator()

	b := array.NewFloat64Builder(pool)
	defer b.Release()

	raw := []float64{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
	b.AppendValues(raw, nil)

	arr := b.NewFloat64Array()
	defer arr.Release()

	f64 := tensor.NewFloat64(arr.Data(), []int64{2, 5}, []int64{8, 16}, []string{"x", "y"})
	defer f64.Release()

	for _, i := range [][]int64{
		{0, 0},
		{0, 1},
		{0, 2},
		{0, 3},
		{0, 4},
		{1, 0},
		{1, 1},
		{1, 2},
		{1, 3},
		{1, 4},
	} {
		fmt.Printf("arr%v = %v\n", i, f64.Value(i))
	}

}

Output:

arr[0 0] = 1
arr[0 1] = 3
arr[0 2] = 5
arr[0 3] = 7
arr[0 4] = 9
arr[1 0] = 2
arr[1 1] = 4
arr[1 2] = 6
arr[1 3] = 8
arr[1 4] = 10
Example (FromMemory)

This example demonstrates creating an array, sourcing the values and null bitmaps directly from byte slices. The null count is set to UnknownNullCount, instructing the array to calculate the null count from the bitmap when NullN is called. 

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	// create LSB packed bits with the following pattern:
	// 01010011 11000101
	data := memory.NewBufferBytes([]byte{0xca, 0xa3})

	// create LSB packed validity (null) bitmap, where every 4th element is null:
	// 11101110 11101110
	nullBitmap := memory.NewBufferBytes([]byte{0x77, 0x77})

	// Create a boolean array and lazily determine NullN using UnknownNullCount
	bools := array.NewBoolean(16, data, nullBitmap, array.UnknownNullCount)
	defer bools.Release()

	// Show the null count
	fmt.Printf("NullN()  = %d\n", bools.NullN())

	// Enumerate the values.
	n := bools.Len()
	for i := 0; i < n; i++ {
		fmt.Printf("bools[%d] = ", i)
		if bools.IsNull(i) {
			fmt.Println("(null)")
		} else {
			fmt.Printf("%t\n", bools.Value(i))
		}
	}

}

Output:

NullN()  = 4
bools[0] = false
bools[1] = true
bools[2] = false
bools[3] = (null)
bools[4] = false
bools[5] = false
bools[6] = true
bools[7] = (null)
bools[8] = true
bools[9] = true
bools[10] = false
bools[11] = (null)
bools[12] = false
bools[13] = true
bools[14] = false
bools[15] = (null)
Example (ListArray)

This example shows how to create a List array. The resulting array should be: 

[[0, 1, 2], [], [3], [4, 5], [6, 7, 8], [], [9]]

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	lb := array.NewListBuilder(pool, arrow.PrimitiveTypes.Int64)
	defer lb.Release()

	vb := lb.ValueBuilder().(*array.Int64Builder)
	vb.Reserve(10)

	lb.Append(true)
	vb.Append(0)
	vb.Append(1)
	vb.Append(2)

	lb.AppendNull()

	lb.Append(true)
	vb.Append(3)

	lb.Append(true)
	vb.Append(4)
	vb.Append(5)

	lb.Append(true)
	vb.Append(6)
	vb.Append(7)
	vb.Append(8)

	lb.AppendNull()

	lb.Append(true)
	vb.Append(9)

	arr := lb.NewArray().(*array.List)
	defer arr.Release()

	arr.DataType().(*arrow.ListType).SetElemNullable(false)
	fmt.Printf("NullN()   = %d\n", arr.NullN())
	fmt.Printf("Len()     = %d\n", arr.Len())
	fmt.Printf("Offsets() = %v\n", arr.Offsets())
	fmt.Printf("Type()    = %v\n", arr.DataType())

	offsets := arr.Offsets()[1:]

	varr := arr.ListValues().(*array.Int64)

	pos := 0
	for i := 0; i < arr.Len(); i++ {
		if !arr.IsValid(i) {
			fmt.Printf("List[%d]   = (null)\n", i)
			continue
		}
		fmt.Printf("List[%d]   = [", i)
		for j := pos; j < int(offsets[i]); j++ {
			if j != pos {
				fmt.Printf(", ")
			}
			fmt.Printf("%v", varr.Value(j))
		}
		pos = int(offsets[i])
		fmt.Printf("]\n")
	}
	fmt.Printf("List      = %v\n", arr)

}

Output:

NullN()   = 2
Len()     = 7
Offsets() = [0 3 3 4 6 9 9 10]
Type()    = list<item: int64>
List[0]   = [0, 1, 2]
List[1]   = (null)
List[2]   = [3]
List[3]   = [4, 5]
List[4]   = [6, 7, 8]
List[5]   = (null)
List[6]   = [9]
List      = [[0 1 2] (null) [3] [4 5] [6 7 8] (null) [9]]
Example (MapArray)

This example demonstrates how to create a Map Array. The resulting array should be: 

[{["ab" "cd" "ef" "gh"] [1 2 3 4]} (null) {["ab" "cd" "ef" "gh"] [(null) 2 5 1]}]

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()
	mb := array.NewMapBuilder(pool, arrow.BinaryTypes.String, arrow.PrimitiveTypes.Int16, false)
	defer mb.Release()

	kb := mb.KeyBuilder().(*array.StringBuilder)
	ib := mb.ItemBuilder().(*array.Int16Builder)

	keys := []string{"ab", "cd", "ef", "gh"}

	mb.Append(true)
	kb.AppendValues(keys, nil)
	ib.AppendValues([]int16{1, 2, 3, 4}, nil)

	mb.AppendNull()

	mb.Append(true)
	kb.AppendValues(keys, nil)
	ib.AppendValues([]int16{-1, 2, 5, 1}, []bool{false, true, true, true})

	arr := mb.NewMapArray()
	defer arr.Release()

	fmt.Printf("NullN() = %d\n", arr.NullN())
	fmt.Printf("Len()   = %d\n", arr.Len())

	offsets := arr.Offsets()
	keyArr := arr.Keys().(*array.String)
	itemArr := arr.Items().(*array.Int16)

	for i := 0; i < arr.Len(); i++ {
		if arr.IsNull(i) {
			fmt.Printf("Map[%d] = (null)\n", i)
			continue
		}

		fmt.Printf("Map[%d] = {", i)
		for j := offsets[i]; j < offsets[i+1]; j++ {
			if j != offsets[i] {
				fmt.Printf(", ")
			}
			fmt.Printf("%v => ", keyArr.Value(int(j)))
			if itemArr.IsValid(int(j)) {
				fmt.Printf("%v", itemArr.Value(int(j)))
			} else {
				fmt.Printf("(null)")
			}
		}
		fmt.Printf("}\n")
	}
	fmt.Printf("Map    = %v\n", arr)

}

Output:

NullN() = 1
Len()   = 3
Map[0] = {ab => 1, cd => 2, ef => 3, gh => 4}
Map[1] = (null)
Map[2] = {ab => (null), cd => 2, ef => 5, gh => 1}
Map    = [{["ab" "cd" "ef" "gh"] [1 2 3 4]} (null) {["ab" "cd" "ef" "gh"] [(null) 2 5 1]}]
Example (Minimal)

This example demonstrates how to build an array of int64 values using a builder and Append. Whilst convenient for small arrays, 

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	// Create an allocator.
	pool := memory.NewGoAllocator()

	// Create an int64 array builder.
	builder := array.NewInt64Builder(pool)
	defer builder.Release()

	builder.Append(1)
	builder.Append(2)
	builder.Append(3)
	builder.AppendNull()
	builder.Append(5)
	builder.Append(6)
	builder.Append(7)
	builder.Append(8)

	// Finish building the int64 array and reset the builder.
	ints := builder.NewInt64Array()
	defer ints.Release()

	// Enumerate the values.
	for i, v := range ints.Int64Values() {
		fmt.Printf("ints[%d] = ", i)
		if ints.IsNull(i) {
			fmt.Println("(null)")
		} else {
			fmt.Println(v)
		}
	}
	fmt.Printf("ints = %v\n", ints)

}

Output:

ints[0] = 1
ints[1] = 2
ints[2] = 3
ints[3] = (null)
ints[4] = 5
ints[5] = 6
ints[6] = 7
ints[7] = 8
ints = [1 2 3 (null) 5 6 7 8]
Example (Record) 
package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	schema := arrow.NewSchema(
		[]arrow.Field{
			{Name: "f1-i32", Type: arrow.PrimitiveTypes.Int32},
			{Name: "f2-f64", Type: arrow.PrimitiveTypes.Float64},
		},
		nil,
	)

	b := array.NewRecordBuilder(pool, schema)
	defer b.Release()

	b.Field(0).(*array.Int32Builder).AppendValues([]int32{1, 2, 3, 4, 5, 6}, nil)
	b.Field(0).(*array.Int32Builder).AppendValues([]int32{7, 8, 9, 10}, []bool{true, true, false, true})
	b.Field(1).(*array.Float64Builder).AppendValues([]float64{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}, nil)

	rec := b.NewRecord()
	defer rec.Release()

	for i, col := range rec.Columns() {
		fmt.Printf("column[%d] %q: %v\n", i, rec.ColumnName(i), col)
	}

}

Output:

column[0] "f1-i32": [1 2 3 4 5 6 7 8 (null) 10]
column[1] "f2-f64": [1 2 3 4 5 6 7 8 9 10]
Example (RecordReader) 
package main

import (
	"fmt"
	"log"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	schema := arrow.NewSchema(
		[]arrow.Field{
			{Name: "f1-i32", Type: arrow.PrimitiveTypes.Int32},
			{Name: "f2-f64", Type: arrow.PrimitiveTypes.Float64},
		},
		nil,
	)

	b := array.NewRecordBuilder(pool, schema)
	defer b.Release()

	b.Field(0).(*array.Int32Builder).AppendValues([]int32{1, 2, 3, 4, 5, 6}, nil)
	b.Field(0).(*array.Int32Builder).AppendValues([]int32{7, 8, 9, 10}, []bool{true, true, false, true})
	b.Field(1).(*array.Float64Builder).AppendValues([]float64{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}, nil)

	rec1 := b.NewRecord()
	defer rec1.Release()

	b.Field(0).(*array.Int32Builder).AppendValues([]int32{11, 12, 13, 14, 15, 16, 17, 18, 19, 20}, nil)
	b.Field(1).(*array.Float64Builder).AppendValues([]float64{11, 12, 13, 14, 15, 16, 17, 18, 19, 20}, nil)

	rec2 := b.NewRecord()
	defer rec2.Release()

	itr, err := array.NewRecordReader(schema, []arrow.Record{rec1, rec2})
	if err != nil {
		log.Fatal(err)
	}
	defer itr.Release()

	n := 0
	for itr.Next() {
		rec := itr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%q]: %v\n", n, rec.ColumnName(i), col)
		}
		n++
	}

}

Output:

rec[0]["f1-i32"]: [1 2 3 4 5 6 7 8 (null) 10]
rec[0]["f2-f64"]: [1 2 3 4 5 6 7 8 9 10]
rec[1]["f1-i32"]: [11 12 13 14 15 16 17 18 19 20]
rec[1]["f2-f64"]: [11 12 13 14 15 16 17 18 19 20]
Example (StructArray)

This example shows how to create a Struct array. The resulting array should be: 

[{‘joe’, 1}, {null, 2}, null, {‘mark’, 4}]

package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	dtype := arrow.StructOf([]arrow.Field{
		{Name: "f1", Type: arrow.ListOf(arrow.PrimitiveTypes.Uint8)},
		{Name: "f2", Type: arrow.PrimitiveTypes.Int32},
	}...)

	sb := array.NewStructBuilder(pool, dtype)
	defer sb.Release()

	f1b := sb.FieldBuilder(0).(*array.ListBuilder)
	f1vb := f1b.ValueBuilder().(*array.Uint8Builder)
	f2b := sb.FieldBuilder(1).(*array.Int32Builder)

	sb.Reserve(4)
	f1vb.Reserve(7)
	f2b.Reserve(3)

	sb.Append(true)
	f1b.Append(true)
	f1vb.AppendValues([]byte("joe"), nil)
	f2b.Append(1)

	sb.Append(true)
	f1b.AppendNull()
	f2b.Append(2)

	sb.AppendNull()

	sb.Append(true)
	f1b.Append(true)
	f1vb.AppendValues([]byte("mark"), nil)
	f2b.Append(4)

	arr := sb.NewArray().(*array.Struct)
	defer arr.Release()

	fmt.Printf("NullN() = %d\n", arr.NullN())
	fmt.Printf("Len()   = %d\n", arr.Len())

	list := arr.Field(0).(*array.List)
	offsets := list.Offsets()

	varr := list.ListValues().(*array.Uint8)
	ints := arr.Field(1).(*array.Int32)

	for i := 0; i < arr.Len(); i++ {
		if !arr.IsValid(i) {
			fmt.Printf("Struct[%d] = (null)\n", i)
			continue
		}
		fmt.Printf("Struct[%d] = [", i)
		pos := int(offsets[i])
		switch {
		case list.IsValid(pos):
			fmt.Printf("[")
			for j := offsets[i]; j < offsets[i+1]; j++ {
				if j != offsets[i] {
					fmt.Printf(", ")
				}
				fmt.Printf("%v", string(varr.Value(int(j))))
			}
			fmt.Printf("], ")
		default:
			fmt.Printf("(null), ")
		}
		fmt.Printf("%d]\n", ints.Value(i))
	}

}

Output:

NullN() = 1
Len()   = 4
Struct[0] = [[j, o, e], 1]
Struct[1] = [[], 2]
Struct[2] = (null)
Struct[3] = [[m, a, r, k], 4]
Example (Table) 
package main

import (
	"fmt"

	"github.com/apache/arrow/go/v7/arrow"
	"github.com/apache/arrow/go/v7/arrow/array"
	"github.com/apache/arrow/go/v7/arrow/memory"
)

func main() {
	pool := memory.NewGoAllocator()

	schema := arrow.NewSchema(
		[]arrow.Field{
			{Name: "f1-i32", Type: arrow.PrimitiveTypes.Int32},
			{Name: "f2-f64", Type: arrow.PrimitiveTypes.Float64},
		},
		nil,
	)

	b := array.NewRecordBuilder(pool, schema)
	defer b.Release()

	b.Field(0).(*array.Int32Builder).AppendValues([]int32{1, 2, 3, 4, 5, 6}, nil)
	b.Field(0).(*array.Int32Builder).AppendValues([]int32{7, 8, 9, 10}, []bool{true, true, false, true})
	b.Field(1).(*array.Float64Builder).AppendValues([]float64{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}, nil)

	rec1 := b.NewRecord()
	defer rec1.Release()

	b.Field(0).(*array.Int32Builder).AppendValues([]int32{11, 12, 13, 14, 15, 16, 17, 18, 19, 20}, nil)
	b.Field(1).(*array.Float64Builder).AppendValues([]float64{11, 12, 13, 14, 15, 16, 17, 18, 19, 20}, nil)

	rec2 := b.NewRecord()
	defer rec2.Release()

	tbl := array.NewTableFromRecords(schema, []arrow.Record{rec1, rec2})
	defer tbl.Release()

	tr := array.NewTableReader(tbl, 5)
	defer tr.Release()

	n := 0
	for tr.Next() {
		rec := tr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%q]: %v\n", n, rec.ColumnName(i), col)
		}
		n++
	}

}

Output:

rec[0]["f1-i32"]: [1 2 3 4 5]
rec[0]["f2-f64"]: [1 2 3 4 5]
rec[1]["f1-i32"]: [6 7 8 (null) 10]
rec[1]["f2-f64"]: [6 7 8 9 10]
rec[2]["f1-i32"]: [11 12 13 14 15]
rec[2]["f2-f64"]: [11 12 13 14 15]
rec[3]["f1-i32"]: [16 17 18 19 20]
rec[3]["f2-f64"]: [16 17 18 19 20]

Index

Examples

Constants

View Source 
const (
	// Date32SizeBytes specifies the number of bytes required to store a single Date32 in memory
	Date32SizeBytes = int(unsafe.Sizeof(Date32(0)))
)
View Source 
const (
	// Date64SizeBytes specifies the number of bytes required to store a single Date64 in memory
	Date64SizeBytes = int(unsafe.Sizeof(Date64(0)))
)
View Source 
const (
	// DayTimeIntervalSizeBytes specifies the number of bytes required to store a single DayTimeInterval in memory
	DayTimeIntervalSizeBytes = int(unsafe.Sizeof(DayTimeInterval{}))
)
View Source 
const (
	// Decimal128SizeBytes specifies the number of bytes required to store a single decimal128 in memory
	Decimal128SizeBytes = int(unsafe.Sizeof(decimal128.Num{}))
)
View Source 
const (
	// DurationSizeBytes specifies the number of bytes required to store a single Duration in memory
	DurationSizeBytes = int(unsafe.Sizeof(Duration(0)))
)
View Source 
const (
	// Float16SizeBytes specifies the number of bytes required to store a single float16 in memory
	Float16SizeBytes = int(unsafe.Sizeof(uint16(0)))
)
View Source 
const (
	// Float32SizeBytes specifies the number of bytes required to store a single float32 in memory
	Float32SizeBytes = int(unsafe.Sizeof(float32(0)))
)
View Source 
const (
	// Float64SizeBytes specifies the number of bytes required to store a single float64 in memory
	Float64SizeBytes = int(unsafe.Sizeof(float64(0)))
)
View Source 
const (
	// Int16SizeBytes specifies the number of bytes required to store a single int16 in memory
	Int16SizeBytes = int(unsafe.Sizeof(int16(0)))
)
View Source 
const (
	// Int32SizeBytes specifies the number of bytes required to store a single int32 in memory
	Int32SizeBytes = int(unsafe.Sizeof(int32(0)))
)
View Source 
const (
	// Int64SizeBytes specifies the number of bytes required to store a single int64 in memory
	Int64SizeBytes = int(unsafe.Sizeof(int64(0)))
)
View Source 
const (
	// Int8SizeBytes specifies the number of bytes required to store a single int8 in memory
	Int8SizeBytes = int(unsafe.Sizeof(int8(0)))
)
View Source 
const (
	// MonthDayNanoIntervalSizeBytes specifies the number of bytes required to store a single DayTimeInterval in memory
	MonthDayNanoIntervalSizeBytes = int(unsafe.Sizeof(MonthDayNanoInterval{}))
)
View Source 
const (
	// MonthIntervalSizeBytes specifies the number of bytes required to store a single MonthInterval in memory
	MonthIntervalSizeBytes = int(unsafe.Sizeof(MonthInterval(0)))
)
View Source 
const (
	// Time32SizeBytes specifies the number of bytes required to store a single Time32 in memory
	Time32SizeBytes = int(unsafe.Sizeof(Time32(0)))
)
View Source 
const (
	// Time64SizeBytes specifies the number of bytes required to store a single Time64 in memory
	Time64SizeBytes = int(unsafe.Sizeof(Time64(0)))
)
View Source 
const (
	// TimestampSizeBytes specifies the number of bytes required to store a single Timestamp in memory
	TimestampSizeBytes = int(unsafe.Sizeof(Timestamp(0)))
)
View Source 
const (
	// Uint16SizeBytes specifies the number of bytes required to store a single uint16 in memory
	Uint16SizeBytes = int(unsafe.Sizeof(uint16(0)))
)
View Source 
const (
	// Uint32SizeBytes specifies the number of bytes required to store a single uint32 in memory
	Uint32SizeBytes = int(unsafe.Sizeof(uint32(0)))
)
View Source 
const (
	// Uint64SizeBytes specifies the number of bytes required to store a single uint64 in memory
	Uint64SizeBytes = int(unsafe.Sizeof(uint64(0)))
)
View Source 
const (
	// Uint8SizeBytes specifies the number of bytes required to store a single uint8 in memory
	Uint8SizeBytes = int(unsafe.Sizeof(uint8(0)))
)

Variables

View Source 
var (
	MonthIntervalTraits        monthTraits
	DayTimeIntervalTraits      daytimeTraits
	MonthDayNanoIntervalTraits monthDayNanoTraits
)
View Source 
var (
	Int64Traits     int64Traits
	Uint64Traits    uint64Traits
	Float64Traits   float64Traits
	Int32Traits     int32Traits
	Uint32Traits    uint32Traits
	Float32Traits   float32Traits
	Int16Traits     int16Traits
	Uint16Traits    uint16Traits
	Int8Traits      int8Traits
	Uint8Traits     uint8Traits
	TimestampTraits timestampTraits
	Time32Traits    time32Traits
	Time64Traits    time64Traits
	Date32Traits    date32Traits
	Date64Traits    date64Traits
	DurationTraits  durationTraits
)
View Source 
var (
	BinaryTypes = struct {
		Binary BinaryDataType
		String BinaryDataType
	}{
		Binary: &BinaryType{},
		String: &StringType{},
	}
)
View Source 
var BooleanTraits booleanTraits
View Source 
var Decimal128Traits decimal128Traits

Decimal128 traits

View Source 
var (
	FixedWidthTypes = struct {
		Boolean              FixedWidthDataType
		Date32               FixedWidthDataType
		Date64               FixedWidthDataType
		DayTimeInterval      FixedWidthDataType
		Duration_s           FixedWidthDataType
		Duration_ms          FixedWidthDataType
		Duration_us          FixedWidthDataType
		Duration_ns          FixedWidthDataType
		Float16              FixedWidthDataType
		MonthInterval        FixedWidthDataType
		Time32s              FixedWidthDataType
		Time32ms             FixedWidthDataType
		Time64us             FixedWidthDataType
		Time64ns             FixedWidthDataType
		Timestamp_s          FixedWidthDataType
		Timestamp_ms         FixedWidthDataType
		Timestamp_us         FixedWidthDataType
		Timestamp_ns         FixedWidthDataType
		MonthDayNanoInterval FixedWidthDataType
	}{
		Boolean:              &BooleanType{},
		Date32:               &Date32Type{},
		Date64:               &Date64Type{},
		DayTimeInterval:      &DayTimeIntervalType{},
		Duration_s:           &DurationType{Unit: Second},
		Duration_ms:          &DurationType{Unit: Millisecond},
		Duration_us:          &DurationType{Unit: Microsecond},
		Duration_ns:          &DurationType{Unit: Nanosecond},
		Float16:              &Float16Type{},
		MonthInterval:        &MonthIntervalType{},
		Time32s:              &Time32Type{Unit: Second},
		Time32ms:             &Time32Type{Unit: Millisecond},
		Time64us:             &Time64Type{Unit: Microsecond},
		Time64ns:             &Time64Type{Unit: Nanosecond},
		Timestamp_s:          &TimestampType{Unit: Second, TimeZone: "UTC"},
		Timestamp_ms:         &TimestampType{Unit: Millisecond, TimeZone: "UTC"},
		Timestamp_us:         &TimestampType{Unit: Microsecond, TimeZone: "UTC"},
		Timestamp_ns:         &TimestampType{Unit: Nanosecond, TimeZone: "UTC"},
		MonthDayNanoInterval: &MonthDayNanoIntervalType{},
	}
)
View Source 
var Float16Traits float16Traits

Float16 traits

View Source 
var (
	PrimitiveTypes = struct {
		Int8    DataType
		Int16   DataType
		Int32   DataType
		Int64   DataType
		Uint8   DataType
		Uint16  DataType
		Uint32  DataType
		Uint64  DataType
		Float32 DataType
		Float64 DataType
		Date32  DataType
		Date64  DataType
	}{

		Int8:    &Int8Type{},
		Int16:   &Int16Type{},
		Int32:   &Int32Type{},
		Int64:   &Int64Type{},
		Uint8:   &Uint8Type{},
		Uint16:  &Uint16Type{},
		Uint32:  &Uint32Type{},
		Uint64:  &Uint64Type{},
		Float32: &Float32Type{},
		Float64: &Float64Type{},
		Date32:  &Date32Type{},
		Date64:  &Date64Type{},
	}
)

Functions

func ConvertTimestampValue 

func ConvertTimestampValue(in, out TimeUnit, value int64) int64

func HashType 

func HashType(seed maphash.Seed, dt DataType) uint64

func RegisterExtensionType 

func RegisterExtensionType(typ ExtensionType) error

RegisterExtensionType registers the provided ExtensionType by calling ExtensionName to use as a Key for registrying the type. If a type with the same name is already registered then this will return an error saying so, otherwise it will return nil if successful registering the type. This function is safe to call from multiple goroutines simultaneously.

func TypeEqual 

func TypeEqual(left, right DataType, opts ...TypeEqualOption) bool

TypeEqual checks if two DataType are the same, optionally checking metadata equality for STRUCT types.

func UnregisterExtensionType 

func UnregisterExtensionType(typName string) error

UnregisterExtensionType removes the type with the given name from the registry causing any messages with that type which come in to be expressed with their metadata and underlying type instead of the extension type that isn't known. This function is safe to call from multiple goroutines simultaneously.

Types

type Array 

type Array interface {
	json.Marshaler

	// DataType returns the type metadata for this instance.
	DataType() DataType

	// NullN returns the number of null values in the array.
	NullN() int

	// NullBitmapBytes returns a byte slice of the validity bitmap.
	NullBitmapBytes() []byte

	// IsNull returns true if value at index is null.
	// NOTE: IsNull will panic if NullBitmapBytes is not empty and 0 > i ≥ Len.
	IsNull(i int) bool

	// IsValid returns true if value at index is not null.
	// NOTE: IsValid will panic if NullBitmapBytes is not empty and 0 > i ≥ Len.
	IsValid(i int) bool

	Data() ArrayData

	// Len returns the number of elements in the array.
	Len() int

	// Retain increases the reference count by 1.
	// Retain may be called simultaneously from multiple goroutines.
	Retain()

	// Release decreases the reference count by 1.
	// Release may be called simultaneously from multiple goroutines.
	// When the reference count goes to zero, the memory is freed.
	Release()
}

Array represents an immutable sequence of values using the Arrow in-memory format.

type ArrayData 

type ArrayData interface {
	// Retain increases the reference count by 1, it is safe to call
	// in multiple goroutines simultaneously.
	Retain()
	// Release decreases the reference count by 1, it is safe to call
	// in multiple goroutines simultaneously. Data is removed when reference
	// count is 0.
	Release()
	// DataType returns the current datatype stored in the object.
	DataType() DataType
	// NullN returns the number of nulls for this data instance.
	NullN() int
	// Len returns the length of this data instance
	Len() int
	// Offset returns the offset into the raw buffers where this data begins
	Offset() int
	// Buffers returns the slice of raw data buffers for this data instance. Their
	// meaning depends on the context of the data type.
	Buffers() []*memory.Buffer
	// Children returns the slice of children data instances, only relevant for
	// nested data types. For instance, List data will have a single child containing
	// elements of all the rows and Struct data will contain numfields children which
	// are the arrays for each field of the struct.
	Children() []ArrayData
	// Reset allows reusing this ArrayData object by replacing the data in this ArrayData
	// object without changing the reference count.
	Reset(newtype DataType, newlength int, newbuffers []*memory.Buffer, newchildren []ArrayData, newnulls int, newoffset int)
}

ArrayData is the underlying memory and metadata of an Arrow array, corresponding to the same-named object in the C++ implementation.

The Array interface and subsequent typed objects provide strongly typed accessors which support marshalling and other patterns to the data. This interface allows direct access to the underlying raw byte buffers which allows for manipulating the internal data and casting. For example, one could cast the raw bytes from int64 to float64 like so: 

arrdata := GetMyInt64Data().Data()
newdata := array.NewData(arrow.PrimitiveTypes.Float64, arrdata.Len(),
		arrdata.Buffers(), nil, arrdata.NullN(), arrdata.Offset())
defer newdata.Release()
float64arr := array.NewFloat64Data(newdata)
defer float64arr.Release()

This is also useful in an analytics setting where memory may be reused. For example, if we had a group of operations all returning float64 such as: 

Log(Sqrt(Expr(arr)))

The low-level implementations could have signatures such as: 

func Log(values arrow.ArrayData) arrow.ArrayData

Another example would be a function that consumes one or more memory buffers in an input array and replaces them with newly-allocated data, changing the output data type as well.

type BinaryDataType 

type BinaryDataType interface {
	DataType
	// contains filtered or unexported methods
}

type BinaryType 

type BinaryType struct{}

func (*BinaryType) Fingerprint 

func (t *BinaryType) Fingerprint() string

func (*BinaryType) ID 

func (t *BinaryType) ID() Type

func (*BinaryType) Name 

func (t *BinaryType) Name() string

func (*BinaryType) String 

func (t *BinaryType) String() string

type BooleanType 

type BooleanType struct{}

func (*BooleanType) BitWidth 

func (t *BooleanType) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*BooleanType) Fingerprint 

func (t *BooleanType) Fingerprint() string

func (*BooleanType) ID 

func (t *BooleanType) ID() Type

func (*BooleanType) Name 

func (t *BooleanType) Name() string

func (*BooleanType) String 

func (t *BooleanType) String() string

type Chunked 

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

Chunked manages a collection of primitives arrays as one logical large array.

func NewChunked 

func NewChunked(dtype DataType, chunks []Array) *Chunked

NewChunked returns a new chunked array from the slice of arrays.

NewChunked panics if the chunks do not have the same data type.

func (*Chunked) Chunk 

func (a *Chunked) Chunk(i int) Array

func (*Chunked) Chunks 

func (a *Chunked) Chunks() []Array

func (*Chunked) DataType 

func (a *Chunked) DataType() DataType

func (*Chunked) Len 

func (a *Chunked) Len() int

func (*Chunked) NullN 

func (a *Chunked) NullN() int

func (*Chunked) Release 

func (a *Chunked) Release()

Release decreases the reference count by 1. When the reference count goes to zero, the memory is freed. Release may be called simultaneously from multiple goroutines.

func (*Chunked) Retain 

func (a *Chunked) Retain()

Retain increases the reference count by 1. Retain may be called simultaneously from multiple goroutines.

type Column 

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

Column is an immutable column data structure consisting of a field (type metadata) and a chunked data array.

To get strongly typed data from a Column, you need to iterate the chunks and type assert each individual Array. For example: 

switch column.DataType().ID {
case arrow.INT32:
	for _, c := range column.Data().Chunks() {
		arr := c.(*array.Int32)
		// do something with arr
	}
case arrow.INT64:
	for _, c := range column.Data().Chunks() {
		arr := c.(*array.Int64)
		// do something with arr
	}
case ...
}

func NewColumn 

func NewColumn(field Field, chunks *Chunked) *Column

NewColumn returns a column from a field and a chunked data array.

NewColumn panics if the field's data type is inconsistent with the data type of the chunked data array.

func NewColumnFromArr 

func NewColumnFromArr(field Field, arr Array) Column

NewColumnFromArr is a convenience function to create a column from a field and a non-chunked array.

This provides a simple mechanism for bypassing the middle step of constructing a Chunked array of one and then releasing it because of the ref counting.

func (*Column) Data 

func (col *Column) Data() *Chunked

func (*Column) DataType 

func (col *Column) DataType() DataType

func (*Column) Field 

func (col *Column) Field() Field

func (*Column) Len 

func (col *Column) Len() int

func (*Column) Name 

func (col *Column) Name() string

func (*Column) NullN 

func (col *Column) NullN() int

func (*Column) Release 

func (col *Column) Release()

Release decreases the reference count by 1. When the reference count goes to zero, the memory is freed. Release may be called simultaneously from multiple goroutines.

func (*Column) Retain 

func (col *Column) Retain()

Retain increases the reference count by 1. Retain may be called simultaneously from multiple goroutines.

type DataType 

type DataType interface {
	ID() Type
	// Name is name of the data type.
	Name() string
	Fingerprint() string
}

DataType is the representation of an Arrow type.

type Date32 

type Date32 int32

func Date32FromTime 

func Date32FromTime(t time.Time) Date32

Date32FromTime returns a Date32 value from a time object

func (Date32) ToTime 

func (d Date32) ToTime() time.Time

type Date32Type 

type Date32Type struct{}

func (*Date32Type) BitWidth 

func (t *Date32Type) BitWidth() int

func (*Date32Type) Fingerprint 

func (t *Date32Type) Fingerprint() string

func (*Date32Type) ID 

func (t *Date32Type) ID() Type

func (*Date32Type) Name 

func (t *Date32Type) Name() string

func (*Date32Type) String 

func (t *Date32Type) String() string

type Date64 

type Date64 int64

func Date64FromTime 

func Date64FromTime(t time.Time) Date64

Date64FromTime returns a Date64 value from a time object

func (Date64) ToTime 

func (d Date64) ToTime() time.Time

type Date64Type 

type Date64Type struct{}

func (*Date64Type) BitWidth 

func (t *Date64Type) BitWidth() int

func (*Date64Type) Fingerprint 

func (t *Date64Type) Fingerprint() string

func (*Date64Type) ID 

func (t *Date64Type) ID() Type

func (*Date64Type) Name 

func (t *Date64Type) Name() string

func (*Date64Type) String 

func (t *Date64Type) String() string

type DayTimeInterval 

type DayTimeInterval struct {
	Days         int32 `json:"days"`
	Milliseconds int32 `json:"milliseconds"`
}

DayTimeInterval represents a number of days and milliseconds (fraction of day).

type DayTimeIntervalType 

type DayTimeIntervalType struct{}

DayTimeIntervalType is encoded as a pair of 32-bit signed integer, representing a number of days and milliseconds (fraction of day).

func (*DayTimeIntervalType) BitWidth 

func (t *DayTimeIntervalType) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*DayTimeIntervalType) Fingerprint 

func (*DayTimeIntervalType) Fingerprint() string

func (*DayTimeIntervalType) ID 

func (*DayTimeIntervalType) ID() Type

func (*DayTimeIntervalType) Name 

func (*DayTimeIntervalType) Name() string

func (*DayTimeIntervalType) String 

func (*DayTimeIntervalType) String() string

type Decimal128Type 

type Decimal128Type struct {
	Precision int32
	Scale     int32
}

Decimal128Type represents a fixed-size 128-bit decimal type.

func (*Decimal128Type) BitWidth 

func (*Decimal128Type) BitWidth() int

func (*Decimal128Type) Fingerprint 

func (t *Decimal128Type) Fingerprint() string

func (*Decimal128Type) ID 

func (*Decimal128Type) ID() Type

func (*Decimal128Type) Name 

func (*Decimal128Type) Name() string

func (*Decimal128Type) String 

func (t *Decimal128Type) String() string

type Duration 

type Duration int64

type DurationType 

type DurationType struct {
	Unit TimeUnit
}

DurationType is encoded as a 64-bit signed integer, representing an amount of elapsed time without any relation to a calendar artifact.

func (*DurationType) BitWidth 

func (*DurationType) BitWidth() int

func (*DurationType) Fingerprint 

func (t *DurationType) Fingerprint() string

func (*DurationType) ID 

func (*DurationType) ID() Type

func (*DurationType) Name 

func (*DurationType) Name() string

func (*DurationType) String 

func (t *DurationType) String() string

type ExtensionBase 

type ExtensionBase struct {
	// Storage is the underlying storage type
	Storage DataType
}

ExtensionBase is the base struct for user-defined Extension Types which must be embedded in any user-defined types like so: 

type UserDefinedType struct {
    arrow.ExtensionBase
    // any other data
}

func (*ExtensionBase) Fields 

func (e *ExtensionBase) Fields() []Field

func (*ExtensionBase) Fingerprint 

func (e *ExtensionBase) Fingerprint() string

func (*ExtensionBase) ID 

func (*ExtensionBase) ID() Type

ID always returns arrow.EXTENSION and should not be overridden

func (*ExtensionBase) Name 

func (*ExtensionBase) Name() string

Name should always return "extension" and should not be overridden

func (*ExtensionBase) StorageType 

func (e *ExtensionBase) StorageType() DataType

StorageType returns the underlying storage type and exists so that functions written against the ExtensionType interface can access the storage type.

func (*ExtensionBase) String 

func (e *ExtensionBase) String() string

String by default will return "extension_type<storage=storage_type>" by can be overridden to customize what is printed out when printing this extension type.

type ExtensionType 

type ExtensionType interface {
	DataType
	// ArrayType should return the reflect.TypeOf(ExtensionArrayType{}) where the
	// ExtensionArrayType is a type that implements the array.ExtensionArray interface.
	// Such a type must also embed the array.ExtensionArrayBase in it. This will be used
	// when creating arrays of this ExtensionType by using reflect.New
	ArrayType() reflect.Type
	// ExtensionName is what will be used when registering / unregistering this extension
	// type. Multiple user-defined types can be defined with a parameterized ExtensionType
	// as long as the parameter is used in the ExtensionName to distinguish the instances
	// in the global Extension Type registry.
	// The return from this is also what will be placed in the metadata for IPC communication
	// under the key ARROW:extension:name
	ExtensionName() string
	// StorageType returns the underlying storage type which is used by this extension
	// type. It is already implemented by the ExtensionBase struct and thus does not need
	// to be re-implemented by a user-defined type.
	StorageType() DataType
	// ExtensionEquals is used to tell whether two ExtensionType instances are equal types.
	ExtensionEquals(ExtensionType) bool
	// Serialize should produce any extra metadata necessary for initializing an instance of
	// this user-defined type. Not all user-defined types require this and it is valid to return
	// nil from this function or an empty slice. This is used for the IPC format and will be
	// added to metadata for IPC communication under the key ARROW:extension:metadata
	// This should be implemented such that it is valid to be called by multiple goroutines
	// concurrently.
	Serialize() string
	// Deserialize is called when reading in extension arrays and types via the IPC format
	// in order to construct an instance of the appropriate extension type. The data passed in
	// is pulled from the ARROW:extension:metadata key and may be nil or an empty slice.
	// If the storage type is incorrect or something else is invalid with the data this should
	// return nil and an appropriate error.
	Deserialize(storageType DataType, data string) (ExtensionType, error)
	// contains filtered or unexported methods
}

ExtensionType is an interface for handling user-defined types. They must be DataTypes and must embed arrow.ExtensionBase in them in order to work properly ensuring that they always have the expected base behavior.

The arrow.ExtensionBase that needs to be embedded implements the DataType interface leaving the remaining functions having to be implemented by the actual user-defined type in order to be handled properly.

func GetExtensionType 

func GetExtensionType(typName string) ExtensionType

GetExtensionType retrieves and returns the extension type of the given name from the global extension type registry. If the type isn't found it will return nil. This function is safe to call from multiple goroutines concurrently.

type Field 

type Field struct {
	Name     string   // Field name
	Type     DataType // The field's data type
	Nullable bool     // Fields can be nullable
	Metadata Metadata // The field's metadata, if any
}

func (Field) Equal 

func (f Field) Equal(o Field) bool

func (Field) Fingerprint 

func (f Field) Fingerprint() string

func (Field) HasMetadata 

func (f Field) HasMetadata() bool

func (Field) String 

func (f Field) String() string

type FixedSizeBinaryType 

type FixedSizeBinaryType struct {
	ByteWidth int
}

func (*FixedSizeBinaryType) BitWidth 

func (t *FixedSizeBinaryType) BitWidth() int

func (*FixedSizeBinaryType) Fingerprint 

func (t *FixedSizeBinaryType) Fingerprint() string

func (*FixedSizeBinaryType) ID 

func (*FixedSizeBinaryType) ID() Type

func (*FixedSizeBinaryType) Name 

func (*FixedSizeBinaryType) Name() string

func (*FixedSizeBinaryType) String 

func (t *FixedSizeBinaryType) String() string

type FixedSizeListType 

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

FixedSizeListType describes a nested type in which each array slot contains a fixed-size sequence of values, all having the same relative type.

func FixedSizeListOf 

func FixedSizeListOf(n int32, t DataType) *FixedSizeListType

FixedSizeListOf returns the list type with element type t. For example, if t represents int32, FixedSizeListOf(10, t) represents [10]int32.

FixedSizeListOf panics if t is nil or invalid. FixedSizeListOf panics if n is <= 0. NullableElem defaults to true

func FixedSizeListOfField 

func FixedSizeListOfField(n int32, f Field) *FixedSizeListType

func FixedSizeListOfNonNullable 

func FixedSizeListOfNonNullable(n int32, t DataType) *FixedSizeListType

FixedSizeListOfNonNullable is like FixedSizeListOf but NullableElem defaults to false indicating that the child type should be marked as non-nullable.

func (*FixedSizeListType) Elem 

func (t *FixedSizeListType) Elem() DataType

Elem returns the FixedSizeListType's element type.

func (*FixedSizeListType) ElemField 

func (t *FixedSizeListType) ElemField() Field

func (*FixedSizeListType) Fields 

func (t *FixedSizeListType) Fields() []Field

func (*FixedSizeListType) Fingerprint 

func (t *FixedSizeListType) Fingerprint() string

func (*FixedSizeListType) ID 

func (*FixedSizeListType) ID() Type

func (*FixedSizeListType) Len 

func (t *FixedSizeListType) Len() int32

Len returns the FixedSizeListType's size.

func (*FixedSizeListType) Name 

func (*FixedSizeListType) Name() string

func (*FixedSizeListType) String 

func (t *FixedSizeListType) String() string

type FixedWidthDataType 

type FixedWidthDataType interface {
	DataType
	// BitWidth returns the number of bits required to store a single element of this data type in memory.
	BitWidth() int
}

FixedWidthDataType is the representation of an Arrow type that requires a fixed number of bits in memory for each element.

type Float16Type 

type Float16Type struct{}

Float16Type represents a floating point value encoded with a 16-bit precision.

func (*Float16Type) BitWidth 

func (t *Float16Type) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*Float16Type) Fingerprint 

func (t *Float16Type) Fingerprint() string

func (*Float16Type) ID 

func (t *Float16Type) ID() Type

func (*Float16Type) Name 

func (t *Float16Type) Name() string

func (*Float16Type) String 

func (t *Float16Type) String() string

type Float32Type 

type Float32Type struct{}

func (*Float32Type) BitWidth 

func (t *Float32Type) BitWidth() int

func (*Float32Type) Fingerprint 

func (t *Float32Type) Fingerprint() string

func (*Float32Type) ID 

func (t *Float32Type) ID() Type

func (*Float32Type) Name 

func (t *Float32Type) Name() string

func (*Float32Type) String 

func (t *Float32Type) String() string

type Float64Type 

type Float64Type struct{}

func (*Float64Type) BitWidth 

func (t *Float64Type) BitWidth() int

func (*Float64Type) Fingerprint 

func (t *Float64Type) Fingerprint() string

func (*Float64Type) ID 

func (t *Float64Type) ID() Type

func (*Float64Type) Name 

func (t *Float64Type) Name() string

func (*Float64Type) String 

func (t *Float64Type) String() string

type Int16Type 

type Int16Type struct{}

func (*Int16Type) BitWidth 

func (t *Int16Type) BitWidth() int

func (*Int16Type) Fingerprint 

func (t *Int16Type) Fingerprint() string

func (*Int16Type) ID 

func (t *Int16Type) ID() Type

func (*Int16Type) Name 

func (t *Int16Type) Name() string

func (*Int16Type) String 

func (t *Int16Type) String() string

type Int32Type 

type Int32Type struct{}

func (*Int32Type) BitWidth 

func (t *Int32Type) BitWidth() int

func (*Int32Type) Fingerprint 

func (t *Int32Type) Fingerprint() string

func (*Int32Type) ID 

func (t *Int32Type) ID() Type

func (*Int32Type) Name 

func (t *Int32Type) Name() string

func (*Int32Type) String 

func (t *Int32Type) String() string

type Int64Type 

type Int64Type struct{}

func (*Int64Type) BitWidth 

func (t *Int64Type) BitWidth() int

func (*Int64Type) Fingerprint 

func (t *Int64Type) Fingerprint() string

func (*Int64Type) ID 

func (t *Int64Type) ID() Type

func (*Int64Type) Name 

func (t *Int64Type) Name() string

func (*Int64Type) String 

func (t *Int64Type) String() string

type Int8Type 

type Int8Type struct{}

func (*Int8Type) BitWidth 

func (t *Int8Type) BitWidth() int

func (*Int8Type) Fingerprint 

func (t *Int8Type) Fingerprint() string

func (*Int8Type) ID 

func (t *Int8Type) ID() Type

func (*Int8Type) Name 

func (t *Int8Type) Name() string

func (*Int8Type) String 

func (t *Int8Type) String() string

type ListType 

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

ListType describes a nested type in which each array slot contains a variable-size sequence of values, all having the same relative type.

func ListOf 

func ListOf(t DataType) *ListType

ListOf returns the list type with element type t. For example, if t represents int32, ListOf(t) represents []int32.

ListOf panics if t is nil or invalid. NullableElem defaults to true

func ListOfField 

func ListOfField(f Field) *ListType

func ListOfNonNullable 

func ListOfNonNullable(t DataType) *ListType

ListOfNonNullable is like ListOf but NullableElem defaults to false, indicating that the child type should be marked as non-nullable.

func (*ListType) Elem 

func (t *ListType) Elem() DataType

Elem returns the ListType's element type.

func (*ListType) ElemField 

func (t *ListType) ElemField() Field

func (*ListType) Fields 

func (t *ListType) Fields() []Field

func (*ListType) Fingerprint 

func (t *ListType) Fingerprint() string

func (*ListType) ID 

func (*ListType) ID() Type

func (*ListType) Name 

func (*ListType) Name() string

func (*ListType) SetElemMetadata 

func (t *ListType) SetElemMetadata(md Metadata)

func (*ListType) SetElemNullable 

func (t *ListType) SetElemNullable(n bool)

func (*ListType) String 

func (t *ListType) String() string

type MapType 

type MapType struct {
	KeysSorted bool
	// contains filtered or unexported fields
}

func MapOf 

func MapOf(key, item DataType) *MapType

func (*MapType) Fields 

func (t *MapType) Fields() []Field

func (*MapType) Fingerprint 

func (t *MapType) Fingerprint() string

func (*MapType) ID 

func (*MapType) ID() Type

func (*MapType) ItemField 

func (t *MapType) ItemField() Field

func (*MapType) ItemType 

func (t *MapType) ItemType() DataType

func (*MapType) KeyField 

func (t *MapType) KeyField() Field

func (*MapType) KeyType 

func (t *MapType) KeyType() DataType

func (*MapType) Name 

func (*MapType) Name() string

func (*MapType) SetItemNullable 

func (t *MapType) SetItemNullable(nullable bool)

func (*MapType) String 

func (t *MapType) String() string

func (*MapType) ValueField 

func (t *MapType) ValueField() Field

func (*MapType) ValueType 

func (t *MapType) ValueType() *StructType

type Metadata 

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

func MetadataFrom 

func MetadataFrom(kv map[string]string) Metadata

func NewMetadata 

func NewMetadata(keys, values []string) Metadata

func (Metadata) Equal 

func (md Metadata) Equal(rhs Metadata) bool

func (Metadata) FindKey 

func (md Metadata) FindKey(k string) int

FindKey returns the index of the key-value pair with the provided key name, or -1 if such a key does not exist.

func (Metadata) Keys 

func (md Metadata) Keys() []string

func (Metadata) Len 

func (md Metadata) Len() int

func (Metadata) String 

func (md Metadata) String() string

func (Metadata) Values 

func (md Metadata) Values() []string

type MonthDayNanoInterval 

type MonthDayNanoInterval struct {
	Months      int32 `json:"months"`
	Days        int32 `json:"days"`
	Nanoseconds int64 `json:"nanoseconds"`
}

MonthDayNanoInterval represents a number of months, days and nanoseconds (fraction of day).

type MonthDayNanoIntervalType 

type MonthDayNanoIntervalType struct{}

MonthDayNanoIntervalType is encoded as two signed 32-bit integers representing a number of months and a number of days, followed by a 64-bit integer representing the number of nanoseconds since midnight for fractions of a day.

func (*MonthDayNanoIntervalType) BitWidth 

func (*MonthDayNanoIntervalType) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*MonthDayNanoIntervalType) Fingerprint 

func (*MonthDayNanoIntervalType) Fingerprint() string

func (*MonthDayNanoIntervalType) ID 

func (*MonthDayNanoIntervalType) ID() Type

func (*MonthDayNanoIntervalType) Name 

func (*MonthDayNanoIntervalType) Name() string

func (*MonthDayNanoIntervalType) String 

func (*MonthDayNanoIntervalType) String() string

type MonthInterval 

type MonthInterval int32

MonthInterval represents a number of months.

func (MonthInterval) MarshalJSON 

func (m MonthInterval) MarshalJSON() ([]byte, error)

func (*MonthInterval) UnmarshalJSON 

func (m *MonthInterval) UnmarshalJSON(data []byte) error

type MonthIntervalType 

type MonthIntervalType struct{}

MonthIntervalType is encoded as a 32-bit signed integer, representing a number of months.

func (*MonthIntervalType) BitWidth 

func (t *MonthIntervalType) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*MonthIntervalType) Fingerprint 

func (*MonthIntervalType) Fingerprint() string

func (*MonthIntervalType) ID 

func (*MonthIntervalType) ID() Type

func (*MonthIntervalType) Name 

func (*MonthIntervalType) Name() string

func (*MonthIntervalType) String 

func (*MonthIntervalType) String() string

type NestedType 

type NestedType interface {
	DataType
	Fields() []Field
}

type NullType 

type NullType struct{}

NullType describes a degenerate array, with zero physical storage. 

var (
	Null *NullType
)

func (*NullType) Fingerprint 

func (*NullType) Fingerprint() string

func (*NullType) ID 

func (*NullType) ID() Type

func (*NullType) Name 

func (*NullType) Name() string

func (*NullType) String 

func (*NullType) String() string

type Record 

type Record interface {
	json.Marshaler

	Release()
	Retain()

	Schema() *Schema

	NumRows() int64
	NumCols() int64

	Columns() []Array
	Column(i int) Array
	ColumnName(i int) string

	// NewSlice constructs a zero-copy slice of the record with the indicated
	// indices i and j, corresponding to array[i:j].
	// The returned record must be Release()'d after use.
	//
	// NewSlice panics if the slice is outside the valid range of the record array.
	// NewSlice panics if j < i.
	NewSlice(i, j int64) Record
}

Record is a collection of equal-length arrays matching a particular Schema. Also known as a RecordBatch in the spec and in some implementations.

It is also possible to construct a Table from a collection of Records that all have the same schema.

type Schema 

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

Schema is a sequence of Field values, describing the columns of a table or a record batch.

func NewSchema 

func NewSchema(fields []Field, metadata *Metadata) *Schema

NewSchema returns a new Schema value from the slice of fields and metadata.

NewSchema panics if there is a field with an invalid DataType.

func (*Schema) Equal 

func (sc *Schema) Equal(o *Schema) bool

Equal returns whether two schema are equal. Equal does not compare the metadata.

func (*Schema) Field 

func (sc *Schema) Field(i int) Field

func (*Schema) FieldIndices 

func (sc *Schema) FieldIndices(n string) []int

FieldIndices returns the indices of the named field or nil.

func (*Schema) Fields 

func (sc *Schema) Fields() []Field

func (*Schema) FieldsByName 

func (sc *Schema) FieldsByName(n string) ([]Field, bool)

func (*Schema) Fingerprint 

func (s *Schema) Fingerprint() string

func (*Schema) HasField 

func (sc *Schema) HasField(n string) bool

func (*Schema) HasMetadata 

func (sc *Schema) HasMetadata() bool

func (*Schema) Metadata 

func (sc *Schema) Metadata() Metadata

func (*Schema) String 

func (s *Schema) String() string

type StringType 

type StringType struct{}

func (*StringType) Fingerprint 

func (t *StringType) Fingerprint() string

func (*StringType) ID 

func (t *StringType) ID() Type

func (*StringType) Name 

func (t *StringType) Name() string

func (*StringType) String 

func (t *StringType) String() string

type StructType 

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

StructType describes a nested type parameterized by an ordered sequence of relative types, called its fields.

func StructOf 

func StructOf(fs ...Field) *StructType

StructOf returns the struct type with fields fs.

StructOf panics if there are duplicated fields. StructOf panics if there is a field with an invalid DataType.

func (*StructType) Field 

func (t *StructType) Field(i int) Field

func (*StructType) FieldByName 

func (t *StructType) FieldByName(name string) (Field, bool)

func (*StructType) FieldIdx 

func (t *StructType) FieldIdx(name string) (int, bool)

func (*StructType) Fields 

func (t *StructType) Fields() []Field

func (*StructType) Fingerprint 

func (t *StructType) Fingerprint() string

func (*StructType) ID 

func (*StructType) ID() Type

func (*StructType) Name 

func (*StructType) Name() string

func (*StructType) String 

func (t *StructType) String() string

type Table 

type Table interface {
	Schema() *Schema
	NumRows() int64
	NumCols() int64
	Column(i int) *Column

	Retain()
	Release()
}

Table represents a logical sequence of chunked arrays of equal length. It is similar to a Record except that the columns are ChunkedArrays instead, allowing for a Table to be built up by chunks progressively whereas the columns in a single Record are always each a single contiguous array.

type Time32 

type Time32 int32

func Time32FromString 

func Time32FromString(val string, unit TimeUnit) (Time32, error)

Time32FromString parses a string to return a Time32 value in the given unit, unit needs to be only seconds or milliseconds and the string should be in the form of HH:MM or HH:MM:SS[.zzz] where the fractions of a second are optional.

func (Time32) ToTime 

func (t Time32) ToTime(unit TimeUnit) time.Time

type Time32Type 

type Time32Type struct {
	Unit TimeUnit
}

Time32Type is encoded as a 32-bit signed integer, representing either seconds or milliseconds since midnight.

func (*Time32Type) BitWidth 

func (*Time32Type) BitWidth() int

func (*Time32Type) Fingerprint 

func (t *Time32Type) Fingerprint() string

func (*Time32Type) ID 

func (*Time32Type) ID() Type

func (*Time32Type) Name 

func (*Time32Type) Name() string

func (*Time32Type) String 

func (t *Time32Type) String() string

type Time64 

type Time64 int64

func Time64FromString 

func Time64FromString(val string, unit TimeUnit) (Time64, error)

Time64FromString parses a string to return a Time64 value in the given unit, unit needs to be only microseconds or nanoseconds and the string should be in the form of HH:MM or HH:MM:SS[.zzzzzzzzz] where the fractions of a second are optional.

func (Time64) ToTime 

func (t Time64) ToTime(unit TimeUnit) time.Time

type Time64Type 

type Time64Type struct {
	Unit TimeUnit
}

Time64Type is encoded as a 64-bit signed integer, representing either microseconds or nanoseconds since midnight.

func (*Time64Type) BitWidth 

func (*Time64Type) BitWidth() int

func (*Time64Type) Fingerprint 

func (t *Time64Type) Fingerprint() string

func (*Time64Type) ID 

func (*Time64Type) ID() Type

func (*Time64Type) Name 

func (*Time64Type) Name() string

func (*Time64Type) String 

func (t *Time64Type) String() string

type TimeUnit 

type TimeUnit int
const (
	Second TimeUnit = iota
	Millisecond
	Microsecond
	Nanosecond
)

func (TimeUnit) Multiplier 

func (u TimeUnit) Multiplier() time.Duration

func (TimeUnit) String 

func (u TimeUnit) String() string

type Timestamp 

type Timestamp int64

func TimestampFromString 

func TimestampFromString(val string, unit TimeUnit) (Timestamp, error)

TimestampFromString parses a string and returns a timestamp for the given unit level.

The timestamp should be in one of the following forms, [T] can be either T or a space, and [.zzzzzzzzz] can be either left out or up to 9 digits of fractions of a second. 

	 YYYY-MM-DD
	 YYYY-MM-DD[T]HH
  YYYY-MM-DD[T]HH:MM
  YYYY-MM-DD[T]HH:MM:SS[.zzzzzzzz]

func (Timestamp) ToTime 

func (t Timestamp) ToTime(unit TimeUnit) time.Time

type TimestampType 

type TimestampType struct {
	Unit     TimeUnit
	TimeZone string
}

TimestampType is encoded as a 64-bit signed integer since the UNIX epoch (2017-01-01T00:00:00Z). The zero-value is a nanosecond and time zone neutral. Time zone neutral can be considered UTC without having "UTC" as a time zone.

func (*TimestampType) BitWidth 

func (*TimestampType) BitWidth() int

BitWidth returns the number of bits required to store a single element of this data type in memory.

func (*TimestampType) Fingerprint 

func (t *TimestampType) Fingerprint() string

func (*TimestampType) ID 

func (*TimestampType) ID() Type

func (*TimestampType) Name 

func (*TimestampType) Name() string

func (*TimestampType) String 

func (t *TimestampType) String() string

type Type 

type Type int

Type is a logical type. They can be expressed as either a primitive physical type (bytes or bits of some fixed size), a nested type consisting of other data types, or another data type (e.g. a timestamp encoded as an int64) 

const (
	// NULL type having no physical storage
	NULL Type = iota

	// BOOL is a 1 bit, LSB bit-packed ordering
	BOOL

	// UINT8 is an Unsigned 8-bit little-endian integer
	UINT8

	// INT8 is a Signed 8-bit little-endian integer
	INT8

	// UINT16 is an Unsigned 16-bit little-endian integer
	UINT16

	// INT16 is a Signed 16-bit little-endian integer
	INT16

	// UINT32 is an Unsigned 32-bit little-endian integer
	UINT32

	// INT32 is a Signed 32-bit little-endian integer
	INT32

	// UINT64 is an Unsigned 64-bit little-endian integer
	UINT64

	// INT64 is a Signed 64-bit little-endian integer
	INT64

	// FLOAT16 is a 2-byte floating point value
	FLOAT16

	// FLOAT32 is a 4-byte floating point value
	FLOAT32

	// FLOAT64 is an 8-byte floating point value
	FLOAT64

	// STRING is a UTF8 variable-length string
	STRING

	// BINARY is a Variable-length byte type (no guarantee of UTF8-ness)
	BINARY

	// FIXED_SIZE_BINARY is a binary where each value occupies the same number of bytes
	FIXED_SIZE_BINARY

	// DATE32 is int32 days since the UNIX epoch
	DATE32

	// DATE64 is int64 milliseconds since the UNIX epoch
	DATE64

	// TIMESTAMP is an exact timestamp encoded with int64 since UNIX epoch
	// Default unit millisecond
	TIMESTAMP

	// TIME32 is a signed 32-bit integer, representing either seconds or
	// milliseconds since midnight
	TIME32

	// TIME64 is a signed 64-bit integer, representing either microseconds or
	// nanoseconds since midnight
	TIME64

	// INTERVAL_MONTHS is YEAR_MONTH interval in SQL style
	INTERVAL_MONTHS

	// INTERVAL_DAY_TIME is DAY_TIME in SQL Style
	INTERVAL_DAY_TIME

	// DECIMAL128 is a precision- and scale-based decimal type. Storage type depends on the
	// parameters.
	DECIMAL128

	// DECIMAL256 is a precision and scale based decimal type, with 256 bit max. not yet implemented
	DECIMAL256

	// LIST is a list of some logical data type
	LIST

	// STRUCT of logical types
	STRUCT

	// SPARSE_UNION of logical types. not yet implemented
	SPARSE_UNION

	// DENSE_UNION of logical types. not yet implemented
	DENSE_UNION

	// DICTIONARY aka Category type
	DICTIONARY

	// MAP is a repeated struct logical type
	MAP

	// Custom data type, implemented by user
	EXTENSION

	// Fixed size list of some logical type
	FIXED_SIZE_LIST

	// Measure of elapsed time in either seconds, milliseconds, microseconds
	// or nanoseconds.
	DURATION

	// like STRING, but 64-bit offsets. not yet implemented
	LARGE_STRING

	// like BINARY but with 64-bit offsets, not yet implemented
	LARGE_BINARY

	// like LIST but with 64-bit offsets. not yet implmented
	LARGE_LIST

	// calendar interval with three fields
	INTERVAL_MONTH_DAY_NANO

	// INTERVAL could be any of the interval types, kept to avoid breaking anyone
	// after switching to individual type ids for the interval types that were using
	// it when calling MakeFromData or NewBuilder
	//
	// Deprecated and will be removed in the next major version release
	INTERVAL

	// Alias to ensure we do not break any consumers
	DECIMAL = DECIMAL128
)

func (Type) String 

func (i Type) String() string

type TypeEqualOption 

type TypeEqualOption func(*typeEqualsConfig)

TypeEqualOption is a functional option type used for configuring type equality checks.

func CheckMetadata 

func CheckMetadata() TypeEqualOption

CheckMetadata is an option for TypeEqual that allows checking for metadata equality besides type equality. It only makes sense for STRUCT type.

type Uint16Type 

type Uint16Type struct{}

func (*Uint16Type) BitWidth 

func (t *Uint16Type) BitWidth() int

func (*Uint16Type) Fingerprint 

func (t *Uint16Type) Fingerprint() string

func (*Uint16Type) ID 

func (t *Uint16Type) ID() Type

func (*Uint16Type) Name 

func (t *Uint16Type) Name() string

func (*Uint16Type) String 

func (t *Uint16Type) String() string

type Uint32Type 

type Uint32Type struct{}

func (*Uint32Type) BitWidth 

func (t *Uint32Type) BitWidth() int

func (*Uint32Type) Fingerprint 

func (t *Uint32Type) Fingerprint() string

func (*Uint32Type) ID 

func (t *Uint32Type) ID() Type

func (*Uint32Type) Name 

func (t *Uint32Type) Name() string

func (*Uint32Type) String 

func (t *Uint32Type) String() string

type Uint64Type 

type Uint64Type struct{}

func (*Uint64Type) BitWidth 

func (t *Uint64Type) BitWidth() int

func (*Uint64Type) Fingerprint 

func (t *Uint64Type) Fingerprint() string

func (*Uint64Type) ID 

func (t *Uint64Type) ID() Type

func (*Uint64Type) Name 

func (t *Uint64Type) Name() string

func (*Uint64Type) String 

func (t *Uint64Type) String() string

type Uint8Type 

type Uint8Type struct{}

func (*Uint8Type) BitWidth 

func (t *Uint8Type) BitWidth() int

func (*Uint8Type) Fingerprint 

func (t *Uint8Type) Fingerprint() string

func (*Uint8Type) ID 

func (t *Uint8Type) ID() Type

func (*Uint8Type) Name 

func (t *Uint8Type) Name() string

func (*Uint8Type) String 

func (t *Uint8Type) String() string

Source Files

View all Source files

Directories

Path Synopsis
_examples
helloworld
_tools
tmpl
Package array provides implementations of various Arrow array types.
 Package array provides implementations of various Arrow array types.
Package arrio exposes functions to manipulate records, exposing and using interfaces not unlike the ones defined in the stdlib io package.
 Package arrio exposes functions to manipulate records, exposing and using interfaces not unlike the ones defined in the stdlib io package.
Package csv reads CSV files and presents the extracted data as records, also writes data as record into CSV files
 Package csv reads CSV files and presents the extracted data as records, also writes data as record into CSV files
internal
arrdata
Package arrdata exports arrays and records data ready to be used for tests.
 Package arrdata exports arrays and records data ready to be used for tests.
arrjson
Package arrjson provides types and functions to encode and decode ARROW types and data to and from JSON files.
 Package arrjson provides types and functions to encode and decode ARROW types and data to and from JSON files.
cpu
Package cpu implements processor feature detection used by the Go standard library.
 Package cpu implements processor feature detection used by the Go standard library.
debug
Package debug provides APIs for conditional runtime assertions and debug logging.
 Package debug provides APIs for conditional runtime assertions and debug logging.
flatbuf
flight_integration
flight_integration/cmd/arrow-flight-integration-client
Client for use with Arrow Flight Integration tests via archery
 Client for use with Arrow Flight Integration tests via archery
flight_integration/cmd/arrow-flight-integration-server
testing/gen
testing/tools
testing/types
Package types contains user-defined types for use in the tests for the arrow package
 Package types contains user-defined types for use in the tests for the arrow package
ipc
cmd/arrow-cat
Command arrow-cat displays the content of an Arrow stream or file.
 Command arrow-cat displays the content of an Arrow stream or file.
cmd/arrow-file-to-stream
cmd/arrow-json-integration-test
cmd/arrow-ls
Command arrow-ls displays the listing of an Arrow file.
 Command arrow-ls displays the listing of an Arrow file.
cmd/arrow-stream-to-file
Package math provides optimized mathematical functions for processing Arrow arrays.
 Package math provides optimized mathematical functions for processing Arrow arrays.
Package memory provides support for allocating and manipulating memory at a low level.
 Package memory provides support for allocating and manipulating memory at a low level.
Package tensor provides types that implement n-dimensional arrays.
 Package tensor provides types that implement n-dimensional arrays.

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.