rarrow

package
v0.34.1 Latest Latest
Warning

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

 Go to latest Published: Oct 12, 2023 License: BSD-3-Clause Imports: 11 Imported by: 0

Documentation

Overview

Package rarrow handles conversion between ROOT and ARROW data models.

Index

Examples

Constants

This section is empty.

Variables

This section is empty.

Functions

func NewFlatTreeWriter added in v0.22.0 

func NewFlatTreeWriter(dir riofs.Directory, name string, schema *arrow.Schema, opts ...rtree.WriteOption) (*flatTreeWriter, error)

NewFlatTreeWriter creates an arrio.Writer that writes ARROW data as a ROOT flat-tree under the provided dir directory.

func NewTable 

func NewTable(t rtree.Tree, opts ...Option) array.Table

NewTable creates a new in-memory Arrow Table from the provided ROOT Tree.

func SchemaFrom 

func SchemaFrom(t rtree.Tree) *arrow.Schema

SchemaFrom returns an Arrow schema from the provided ROOT tree.

Types

type Option 

type Option func(*config)

Option allows to configure how Records and Tables are constructed from input ROOT Trees.

func WithAllocator 

func WithAllocator(mem memory.Allocator) Option

WithAllocator configures an Arrow value to use the specified memory allocator instead of the default Go one.

func WithChunk 

func WithChunk(nentries int64) Option

WithChunk specifies the number of entries to populate Records with.

The default is to populate Records with the whole set of entries the input ROOT Tree contains.

func WithEnd 

func WithEnd(entry int64) Option

WithEnd specifies the last entry (excluded) to read from the input ROOT Tree.

The default (-1) is to read all the entries of the input ROOT Tree.

func WithStart 

func WithStart(entry int64) Option

WithStart specifies the first entry to read from the input ROOT Tree.

type Record 

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

Record is an in-memory Arrow Record backed by a ROOT Tree.

func NewRecord 

func NewRecord(t rtree.Tree, opts ...Option) *Record

NewRecord creates a new in-memory Arrow Record from the provided ROOT Tree.

func (*Record) Column 

func (rec *Record) Column(i int) array.Interface

func (*Record) ColumnName 

func (rec *Record) ColumnName(i int) string

func (*Record) Columns 

func (rec *Record) Columns() []array.Interface

func (*Record) NewSlice 

func (rec *Record) NewSlice(i, j int64) array.Record

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.

func (*Record) NumCols 

func (rec *Record) NumCols() int64

func (*Record) NumRows 

func (rec *Record) NumRows() int64

func (*Record) Release 

func (rec *Record) 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 (*Record) Retain 

func (rec *Record) Retain()

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

func (*Record) Schema 

func (rec *Record) Schema() *arrow.Schema

type RecordReader 

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

RecordReader is an ARROW RecordReader for ROOT Trees.

RecordReader does not materialize more than one record at a time. The number of rows (or entries, in ROOT speak) that record loads can be configured at creation time with the WithChunk function. The default is one entry per record. One can pass -1 to WithChunk to create a record with all entries of the Tree or Chain.

Example 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree)
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [1]
rec[0][two]: [1.1]
rec[0][three]: ["uno"]
rec[1][one]: [2]
rec[1][two]: [2.2]
rec[1][three]: ["dos"]
rec[2][one]: [3]
rec[2][two]: [3.3]
rec[2][three]: ["tres"]
rec[3][one]: [4]
rec[3][two]: [4.4]
rec[3][three]: ["quatro"]
Example (AllTree) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree, rarrow.WithChunk(-1))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [1 2 3 4]
rec[0][two]: [1.1 2.2 3.3 4.4]
rec[0][three]: ["uno" "dos" "tres" "quatro"]
Example (WithChain) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	chain, closer, err := rtree.ChainOf("tree", "../testdata/chain.1.root", "../testdata/chain.2.root")
	if err != nil {
		log.Fatal(err)
	}
	defer func() {
		err = closer()
		if err != nil {
			log.Fatalf("could not close chain: %+v", err)
		}
	}()

	rr := rarrow.NewRecordReader(chain, rarrow.WithStart(10), rarrow.WithEnd(20))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][evt]: {["beg-010"] [10] [[10 10 10 10 10 10 10 10 10 10]] [0] [[]] ["std-010"] [[]] [[]] ["end-010"]}
rec[1][evt]: {["beg-011"] [11] [[11 11 11 11 11 11 11 11 11 11]] [1] [[11]] ["std-011"] [[11]] [["vec-011"]] ["end-011"]}
rec[2][evt]: {["beg-012"] [12] [[12 12 12 12 12 12 12 12 12 12]] [2] [[12 12]] ["std-012"] [[12 12]] [["vec-012" "vec-012"]] ["end-012"]}
rec[3][evt]: {["beg-013"] [13] [[13 13 13 13 13 13 13 13 13 13]] [3] [[13 13 13]] ["std-013"] [[13 13 13]] [["vec-013" "vec-013" "vec-013"]] ["end-013"]}
rec[4][evt]: {["beg-014"] [14] [[14 14 14 14 14 14 14 14 14 14]] [4] [[14 14 14 14]] ["std-014"] [[14 14 14 14]] [["vec-014" "vec-014" "vec-014" "vec-014"]] ["end-014"]}
rec[5][evt]: {["beg-015"] [15] [[15 15 15 15 15 15 15 15 15 15]] [5] [[15 15 15 15 15]] ["std-015"] [[15 15 15 15 15]] [["vec-015" "vec-015" "vec-015" "vec-015" "vec-015"]] ["end-015"]}
rec[6][evt]: {["beg-016"] [16] [[16 16 16 16 16 16 16 16 16 16]] [6] [[16 16 16 16 16 16]] ["std-016"] [[16 16 16 16 16 16]] [["vec-016" "vec-016" "vec-016" "vec-016" "vec-016" "vec-016"]] ["end-016"]}
rec[7][evt]: {["beg-017"] [17] [[17 17 17 17 17 17 17 17 17 17]] [7] [[17 17 17 17 17 17 17]] ["std-017"] [[17 17 17 17 17 17 17]] [["vec-017" "vec-017" "vec-017" "vec-017" "vec-017" "vec-017" "vec-017"]] ["end-017"]}
rec[8][evt]: {["beg-018"] [18] [[18 18 18 18 18 18 18 18 18 18]] [8] [[18 18 18 18 18 18 18 18]] ["std-018"] [[18 18 18 18 18 18 18 18]] [["vec-018" "vec-018" "vec-018" "vec-018" "vec-018" "vec-018" "vec-018" "vec-018"]] ["end-018"]}
rec[9][evt]: {["beg-019"] [19] [[19 19 19 19 19 19 19 19 19 19]] [9] [[19 19 19 19 19 19 19 19 19]] ["std-019"] [[19 19 19 19 19 19 19 19 19]] [["vec-019" "vec-019" "vec-019" "vec-019" "vec-019" "vec-019" "vec-019" "vec-019" "vec-019"]] ["end-019"]}
Example (WithChunk) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree, rarrow.WithChunk(3))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [1 2 3]
rec[0][two]: [1.1 2.2 3.3]
rec[0][three]: ["uno" "dos" "tres"]
rec[1][one]: [4]
rec[1][two]: [4.4]
rec[1][three]: ["quatro"]
Example (WithEnd) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree, rarrow.WithEnd(2))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [1]
rec[0][two]: [1.1]
rec[0][three]: ["uno"]
rec[1][one]: [2]
rec[1][two]: [2.2]
rec[1][three]: ["dos"]
Example (WithStart) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree, rarrow.WithStart(1))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [2]
rec[0][two]: [2.2]
rec[0][three]: ["dos"]
rec[1][one]: [3]
rec[1][two]: [3.3]
rec[1][three]: ["tres"]
rec[2][one]: [4]
rec[2][two]: [4.4]
rec[2][three]: ["quatro"]
Example (WithStartEnd) 
package main

import (
	"fmt"
	"log"

	"go-hep.org/x/hep/groot"
	"go-hep.org/x/hep/groot/rarrow"
	"go-hep.org/x/hep/groot/riofs"
	"go-hep.org/x/hep/groot/rtree"
)

func main() {
	f, err := groot.Open("../testdata/simple.root")
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	o, err := riofs.Dir(f).Get("tree")
	if err != nil {
		log.Fatal(err)
	}

	tree := o.(rtree.Tree)

	rr := rarrow.NewRecordReader(tree, rarrow.WithStart(1), rarrow.WithEnd(2))
	defer rr.Release()

	recs := 0
	for rr.Next() {
		rec := rr.Record()
		for i, col := range rec.Columns() {
			fmt.Printf("rec[%d][%s]: %v\n", recs, rec.Schema().Field(i).Name, col)
		}
		recs++
	}

}

Output:

rec[0][one]: [2]
rec[0][two]: [2.2]
rec[0][three]: ["dos"]

func NewRecordReader 

func NewRecordReader(tree rtree.Tree, opts ...Option) *RecordReader

NewRecordReader creates a new ARROW RecordReader from the provided ROOT Tree.

func (*RecordReader) Next 

func (r *RecordReader) Next() bool

func (*RecordReader) Record 

func (r *RecordReader) Record() array.Record

func (*RecordReader) Release 

func (r *RecordReader) 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 (*RecordReader) Retain 

func (r *RecordReader) Retain()

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

func (*RecordReader) Schema 

func (r *RecordReader) Schema() *arrow.Schema

Source Files

View all Source files

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.