cmd

Documentation

Index

• type CatCmd
  • func (c CatCmd) Run() error
• type ImportCmd
  • func (c ImportCmd) Run() error
• type MergeCmd
  • func (c MergeCmd) Run() error
• type MetaCmd
  • func (c MetaCmd) Run() error
• type RowCountCmd
  • func (c RowCountCmd) Run() error
• type SchemaCmd
  • func (c SchemaCmd) Run() error
• type SizeCmd
  • func (c SizeCmd) Run() error
• type SplitCmd
  • func (c SplitCmd) Run() error
• type TrunkWriter
• type VersionCmd
  • func (c VersionCmd) Run() error

Types

type CatCmd

type CatCmd struct {
	internal.ReadOption
	Skip         int64   `short:"k" help:"Skip rows before apply other logics." default:"0"`
	SkipPageSize int64   `help:"Page size to skip rows." default:"100000"`
	Limit        uint64  `short:"l" help:"Max number of rows to output, 0 means no limit." default:"0"`
	ReadPageSize int     `help:"Page size to read from Parquet." default:"1000"`
	SampleRatio  float32 `short:"s" help:"Sample ratio (0.0-1.0)." default:"1.0"`
	Format       string  `short:"f" help:"output format (json/jsonl/csv/tsv)" enum:"json,jsonl,csv,tsv" default:"json"`
	NoHeader     bool    `help:"(CSV/TSV only) do not output field name as header" default:"false"`
	URI          string  `arg:"" predictor:"file" help:"URI of Parquet file."`
	FailOnInt96  bool    `help:"fail command if INT96 data type presents." name:"fail-on-int96" default:"false"`
	PargoPrefix  string  `help:"remove this prefix from field names." default:""`
}

CatCmd is a kong command for cat

func (CatCmd) Run

func (c CatCmd) Run() error

Run does actual cat job

type ImportCmd

type ImportCmd struct {
	internal.WriteOption
	Source     string `required:"" short:"s" predictor:"file" help:"Source file name."`
	Format     string `help:"Source file formats (csv/json/jsonl)." short:"f" enum:"csv,json,jsonl" default:"csv"`
	Schema     string `required:"" short:"m" predictor:"file" help:"Schema file name."`
	SkipHeader bool   `help:"Skip first line of CSV files" default:"false"`
	URI        string `arg:"" predictor:"file" help:"URI of Parquet file."`
}

ImportCmd is a kong command for import

func (ImportCmd) Run

func (c ImportCmd) Run() error

Run does actual import job

type MergeCmd

type MergeCmd struct {
	internal.ReadOption
	internal.WriteOption
	ReadPageSize int      `help:"Page size to read from Parquet." default:"1000"`
	Sources      []string `help:"Files to be merged."`
	URI          string   `arg:"" predictor:"file" help:"URI of Parquet file."`
	FailOnInt96  bool     `help:"fail command if INT96 data type presents." name:"fail-on-int96" default:"false"`
}

MergeCmd is a kong command for merge

func (MergeCmd) Run

func (c MergeCmd) Run() error

Run does actual merge job

type MetaCmd

type MetaCmd struct {
	internal.ReadOption
	Base64      bool   `name:"base64" short:"b" help:"Encode min/max value." default:"false"`
	URI         string `arg:"" predictor:"file" help:"URI of Parquet file."`
	FailOnInt96 bool   `help:"fail command if INT96 data type presents." name:"fail-on-int96" default:"false"`
	PargoPrefix string `help:"remove this prefix from field names." default:""`
}

MetaCmd is a kong command for meta

func (MetaCmd) Run

func (c MetaCmd) Run() error

Run does actual meta job

type RowCountCmd

type RowCountCmd struct {
	internal.ReadOption
	URI string `arg:"" predictor:"file" help:"URI of Parquet file."`
}

RowCountCmd is a kong command for rowcount

func (RowCountCmd) Run

func (c RowCountCmd) Run() error

Run does actual rowcount job

type SchemaCmd

type SchemaCmd struct {
	internal.ReadOption
	Format      string `short:"f" help:"Schema format (raw/json/go/csv)." enum:"raw,json,go,csv" default:"json"`
	URI         string `arg:"" predictor:"file" help:"URI of Parquet file."`
	PargoPrefix string `help:"remove this prefix from field names." default:""`
}

SchemaCmd is a kong command for schema

func (SchemaCmd) Run

func (c SchemaCmd) Run() error

Run does actual schema job

type SizeCmd

type SizeCmd struct {
	internal.ReadOption
	Query string `short:"q" help:"Size to query (raw/uncompressed/footer/all)." enum:"raw,uncompressed,footer,all" default:"raw"`
	JSON  bool   `short:"j" help:"Output in JSON format." default:"false"`
	URI   string `arg:"" predictor:"file" help:"URI of Parquet file."`
}

SizeCmd is a kong command for size

func (SizeCmd) Run

func (c SizeCmd) Run() error

Run does actual size job

type SplitCmd

type SplitCmd struct {
	internal.ReadOption
	internal.WriteOption
	ReadPageSize int    `help:"Page size to read from Parquet." default:"1000"`
	URI          string `arg:"" predictor:"file" help:"URI of Parquet file."`
	FileCount    int64  `xor:"RecordCount" help:"Generate this number of result files with potential empty ones"`
	RecordCount  int64  `xor:"FileCount" help:"Result files will have at most this number of records"`
	FailOnInt96  bool   `help:"Fail command if INT96 data type presents." name:"fail-on-int96" default:"false"`
	NameFormat   string `help:"Format to populate target file names" default:"result-%06d.parquet"`
	// contains filtered or unexported fields
}

SplitCmd is a kong command for split

func (SplitCmd) Run

func (c SplitCmd) Run() error

Run does actual split job

type TrunkWriter

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

current writer state

type VersionCmd

type VersionCmd struct {
	JSON      bool `short:"j" help:"Output in JSON format." default:"false"`
	All       bool `short:"a" help:"Output all version details." default:"false"`
	BuildTime bool `short:"b" help:"Output build time." default:"false"`
	Source    bool `short:"s" help:"Source of the executable." default:"false"`
}

VersionCmd is a kong command for version

func (VersionCmd) Run

func (c VersionCmd) Run() error

Run does actual version job