core

Documentation

Index

• func ApplyAction(action Action, keep models.FileInfo, dup models.FileInfo, backupDir string) error
• func ApplyKeepStrategy(group models.DuplicateGroup, strategy string) (keep models.FileInfo, toRemove []models.FileInfo)
• func BuildReport(allFiles []models.FileInfo, groups []models.DuplicateGroup, scanPath string) models.Report
• func CountHardLinks(files []models.FileInfo) int
• func DeleteFile(path string) error
• func ExportCSV(report models.Report, path string) error
• func ExportHTML(report models.Report, path string) error
• func ExportJSON(report models.Report, path string) error
• func FindDuplicates(files []models.FileInfo, workers int) []models.DuplicateGroup
• func FormatSize(bytes int64) string
• func GroupByHash(annotated []AnnotatedFile) map[string][]models.FileInfo
• func GroupBySize(files []models.FileInfo) map[int64][]models.FileInfo
• func HashBlake3(path string) (string, error)
• func HashSHA256(path string) (string, error)
• func ImportJSON(path string) (models.Report, error)
• func MoveToBackup(dup, backupDir string) error
• func PlatformName() string
• func ReplaceWithHardLink(keep, dup string) error
• func ReplaceWithSoftLink(keep, dup string) error
• func Scan(cfg ScanConfig) ([]models.FileInfo, error)
• func SortGroupsByCount(groups []models.DuplicateGroup)
• func SortGroupsByPath(groups []models.DuplicateGroup)
• func SortGroupsBySize(groups []models.DuplicateGroup)
• type Action
• type AnnotatedFile
  • func AnnotateFiles(files []models.FileInfo, algorithm string, workers int) []AnnotatedFile
• type HashResult
  • func HashPipeline(paths []string, algorithm string, workers int) []HashResult
• type ScanConfig

Functions

func ApplyAction

func ApplyAction(action Action, keep models.FileInfo, dup models.FileInfo, backupDir string) error

ApplyAction performs the given action on a duplicate file.

func ApplyKeepStrategy

func ApplyKeepStrategy(group models.DuplicateGroup, strategy string) (keep models.FileInfo, toRemove []models.FileInfo)

ApplyKeepStrategy selects which file to keep and which to remove.

func BuildReport

func BuildReport(allFiles []models.FileInfo, groups []models.DuplicateGroup, scanPath string) models.Report

BuildReport creates a Report from the scan results.

func CountHardLinks

func CountHardLinks(files []models.FileInfo) int

CountHardLinks returns the number of files that are already hard-linked.

func DeleteFile

func DeleteFile(path string) error

DeleteFile removes a single file.

func ExportCSV

func ExportCSV(report models.Report, path string) error

ExportCSV writes a Report to a CSV file, one row per file.

func ExportHTML

func ExportHTML(report models.Report, path string) error

ExportHTML writes a Report to a styled HTML file.

func ExportJSON

func ExportJSON(report models.Report, path string) error

ExportJSON writes a Report to a JSON file.

func FindDuplicates

func FindDuplicates(files []models.FileInfo, workers int) []models.DuplicateGroup

FindDuplicates runs the full two-stage dedup pipeline: size grouping → Blake3 → SHA256 verification → duplicate groups.

func FormatSize

func FormatSize(bytes int64) string

FormatSize returns a human-readable file size string.

func GroupByHash

func GroupByHash(annotated []AnnotatedFile) map[string][]models.FileInfo

GroupByHash groups annotated files by their hash, returning only groups with 2+ files.

func GroupBySize

func GroupBySize(files []models.FileInfo) map[int64][]models.FileInfo

GroupBySize groups files by their size, returning only groups with 2+ files.

func HashBlake3

func HashBlake3(path string) (string, error)

HashBlake3 computes the Blake3 hash of a file.

func HashSHA256

func HashSHA256(path string) (string, error)

HashSHA256 computes the SHA256 hash of a file.

func ImportJSON

func ImportJSON(path string) (models.Report, error)

ImportJSON reads a Report from a JSON file.

func MoveToBackup

func MoveToBackup(dup, backupDir string) error

MoveToBackup moves a duplicate file to a backup directory, preserving structure.

func PlatformName

func PlatformName() string

PlatformName returns a human-readable name for the current OS/arch.

func ReplaceWithHardLink

func ReplaceWithHardLink(keep, dup string) error

ReplaceWithHardLink replaces dup with a hard link to keep.

func ReplaceWithSoftLink

func ReplaceWithSoftLink(keep, dup string) error

ReplaceWithSoftLink replaces dup with a symbolic link to keep.

func Scan

func Scan(cfg ScanConfig) ([]models.FileInfo, error)

Scan discovers files using filepath.WalkDir for better performance, applies filters, and returns a list of FileInfo.

func SortGroupsByCount

func SortGroupsByCount(groups []models.DuplicateGroup)

SortGroupsByCount sorts groups by number of copies descending.

func SortGroupsByPath

func SortGroupsByPath(groups []models.DuplicateGroup)

SortGroupsByPath sorts groups alphabetically by first file path.

func SortGroupsBySize

func SortGroupsBySize(groups []models.DuplicateGroup)

SortGroupsBySize sorts groups by file size descending (default).

Types

type Action

type Action int

Action represents a file operation to perform.

const (
	ActionNone Action = iota
	ActionDelete
	ActionHardLink
	ActionSoftLink
	ActionBackup
)

type AnnotatedFile

type AnnotatedFile struct {
	File models.FileInfo
	Hash string
}

AnnotatedFile pairs a models.FileInfo with a hash result.

func AnnotateFiles

func AnnotateFiles(files []models.FileInfo, algorithm string, workers int) []AnnotatedFile

AnnotateFiles adds hashes to file infos concurrently.

type HashResult

type HashResult struct {
	Path string
	Hash string
	Err  error
}

HashResult is a single file hash result.

func HashPipeline

func HashPipeline(paths []string, algorithm string, workers int) []HashResult

HashPipeline hashes a list of files concurrently using the given algorithm. algorithm: "blake3" or "sha256"

type ScanConfig

type ScanConfig struct {
	Path         string
	Recursive    bool
	MinSize      int64
	MaxSize      int64
	Exclude      []string
	ExcludeRegex []string
	ExcludeDir   []string
	Workers      int
	OnProgress   func(stats models.ScanStats)
}

ScanConfig holds options for the file scanner.