dedup

package
v3.0.0 Latest Latest
Warning

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

Go to latest
Published: Feb 27, 2025 License: Apache-2.0 Imports: 20 Imported by: 0

Documentation

Index

Constants

View Source
const (
	BufferMaxMem     = "max-buffer-mem"
	BufferMaxMemHelp = "the maximum bytes of memory allowed for each buffer before overflowing to disk"

	DedupSizeGain     = "min-size-gain"
	DedupSizeGainHelp = `minimum bytes one must earn to perform a deduplication`

	MinIndexDiskFree     = "min-index-disk-free"
	MinIndexDiskFreeHelp = `minimum free space on disk to allow index writing`
)

Variables

This section is empty.

Functions

func NewCmdDedup

func NewCmdDedup() *cobra.Command

Types

type DedupFlags

type DedupFlags struct {
	WarcFileFlags         flag.WarcIteratorFlags
	InputHookFlags        *flag.InputHookFlags
	OutputHookFlags       *flag.OutputHookFlags
	FileWalkerFlags       flag.FileWalkerFlags
	WarcWriterConfigFlags *flag.WarcWriterConfigFlags
	UtilFlags             flag.UtilFlags
	RepairFlags           flag.RepairFlags
	WarcRecordOptionFlags flag.WarcRecordOptionFlags
	IndexFlags            *flag.IndexFlags
	ConcurrencyFlags      flag.ConcurrencyFlags
	ErrorFlags            flag.ErrorFlags
}

func NewDedupFlags

func NewDedupFlags() DedupFlags

func (DedupFlags) AddFlags

func (f DedupFlags) AddFlags(cmd *cobra.Command)

func (DedupFlags) BufferMaxMem

func (f DedupFlags) BufferMaxMem() int64

func (DedupFlags) DedupSizeGain

func (f DedupFlags) DedupSizeGain() int64

func (DedupFlags) MinIndexDiskFree

func (f DedupFlags) MinIndexDiskFree() int64

func (DedupFlags) ToDedupOptions

func (f DedupFlags) ToDedupOptions() (*DedupOptions, error)

type DedupOptions

type DedupOptions struct {
	Paths               []string
	Concurrency         int
	DigestIndex         *index.DigestIndex
	FileIndex           *index.FileIndex
	WarcWriterConfig    *warcwriterconfig.WarcWriterConfig
	MinimumSizeGain     int64
	MinWARCDiskFree     int64
	MinIndexDiskFree    int64
	ContinueOnError     bool
	FileWalker          *filewalker.FileWalker
	WarcRecordOptions   []gowarc.WarcRecordOption
	OpenInputFileHook   hooks.OpenInputFileHook
	CloseInputFileHook  hooks.CloseInputFileHook
	OpenOutputFileHook  hooks.OpenOutputFileHook
	CloseOutputFileHook hooks.CloseOutputFileHook
}

func (*DedupOptions) Complete

func (o *DedupOptions) Complete(cmd *cobra.Command, args []string) error

func (*DedupOptions) Run

func (o *DedupOptions) Run() error

func (*DedupOptions) Validate

func (o *DedupOptions) Validate() error

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL