v0.0.7 wrap up

.gitignore

@@ -29,6 +29,11 @@ go.work
 /.code
 /dist
 
+# output files
+smash
+smash.exe
+smash.out
+
 # temporary files
 report.json
 analysis.json

docs/demos.md

@@ -3,10 +3,11 @@
 Pre-recorded demos of `smash` in action.
 
 # Examples
+* [v0.0.7-hdd-photos](https://vhs.charm.sh/vhs-4OwN0BJfb3F3CTzGJCFHcs.gif) - `smash`ing an old portable USB HDD of photos & removing duplicates.
 * [v0.0.5-hdd-photos](https://vhs.charm.sh/vhs-7B6XHxXq8VPvZ6AY9FpGIc.gif) - `smash`ing an old portable USB HDD of photos with excluded directories.
 
 # Versions
-
+* [v0.0.7](https://vhs.charm.sh/vhs-5uZbZAvk8Y6eq4dihLppbk.gif) - powered by [VHS](https://vhs.charm.sh)
 * [v0.0.5](https://vhs.charm.sh/vhs-1zSMi9vYpmh0DivoB4E6g4.gif) - powered by [VHS](https://vhs.charm.sh)  
 * [v0.0.4](https://vhs.charm.sh/vhs-tgMXNRqo7UovLRd5iSlgF.gif) - powered by [VHS](https://vhs.charm.sh)
 * [v0.0.3](https://vhs.charm.sh/vhs-1T6pqQivwvPAmudnDpwVQP.gif) - powered by [VHS](https://vhs.charm.sh)

docs/vhs/demo-photos-hdd.tape

@@ -13,7 +13,22 @@ Set WindowBar Colorful
 Set Theme "TokyoNight"
 
 # smash Linux/drivers
-Type "./smash /media/thushan/smash/photos/ --exclude-dir=_uploaded,sort,tmp,events"
+Type "./smash /media/thushan/smash/photos/ --exclude-dir=sort,tmp,events -o report.json"
 Sleep 500ms
 Enter
 Sleep 30s
+Type "clear"
+Sleep 500ms
+Enter
+Type `jq '.analysis.dupes[]|[.location,.path,.filename]|join("/")' report.json`
+Sleep 500ms
+Enter
+Sleep 5s
+Type "clear"
+Sleep 500ms
+Enter
+Type `jq '.analysis.dupes[]|[.location,.path,.filename]|join("/")' report.json | xargs ls -lh`
+Sleep 500ms
+Enter
+Sleep 5s
+

docs/vhs/demo.tape

@@ -13,7 +13,34 @@ Set WindowBar Colorful
 Set Theme "JetBrains Darcula"
 
 # smash Linux/drivers
-Type "./smash ~/linux/drivers"
+Type "./smash ~/linux/drivers --exclude-dir=git -o report.json"
 Sleep 500ms
 Enter
 Sleep 10s
+Type "clear"
+Sleep 500ms
+Enter
+Type `jq '.analysis.dupes[]|[.location,.path,.filename]|join("/")' report.json | xargs wc -l`
+Sleep 500ms
+Enter
+Sleep 5s
+Type `jq '.analysis.dupes[]|[.location,.path,.filename]|join("/")' report.json | xargs rm`
+Sleep 500ms
+Enter
+Sleep 5s
+Type "cd ~/linux/drivers"
+Sleep 500ms
+Enter
+Sleep 2s
+Type "git status -s"
+Sleep 500ms
+Enter
+Sleep 3s
+Type "git reset --hard"
+Sleep 500ms
+Enter
+Sleep 3s
+Type "git status -s"
+Sleep 500ms
+Enter
+Sleep 5s

internal/smash/configuration.go

@@ -39,6 +39,10 @@ func (app *App) printConfiguration() {
 	theme.Println(b.Sprint("Algorithm:   "), theme.ColourConfig(algorithms.Algorithm(f.Algorithm)))
 	theme.Println(b.Sprint("Locations:   "), theme.ColourConfig(strings.Join(app.Locations, ", ")))
 
+	if !f.HideOutput && f.OutputFile != "" {
+		theme.Println(b.Sprint("Output:      "), theme.ColourConfig(f.OutputFile), "(json)")
+	}
+
 	if len(f.ExcludeDir) > 0 || len(f.ExcludeFile) > 0 {
 		theme.StyleBold.Println("Excluded")
 		if len(f.ExcludeDir) > 0 {

internal/smash/export.go

@@ -41,18 +41,23 @@ type ReportTopFilesSummary struct {
 }
 type ReportFiles struct {
 	Fails []ReportFailSummary      `json:"fails"`
-	Empty []ReportFileSummary      `json:"empty"`
+	Empty []ReportFileBaseSummary  `json:"empty"`
 	Dupes []ReportDuplicateSummary `json:"dupes"`
 }
 
 type ReportFailSummary struct {
 	Filename string `json:"filename"`
 	Error    string `json:"error"`
 }
-type ReportFileSummary struct {
+
+type ReportFileBaseSummary struct {
 	Filename string `json:"filename"`
 	Location string `json:"location"`
 	Path     string `json:"path"`
+}
+
+type ReportFileSummary struct {
+	ReportFileBaseSummary
 	Hash     string `json:"hash"`
 	Size     uint64 `json:"size"`
 	FullHash bool   `json:"fullHash"`
@@ -116,19 +121,23 @@ func getHostName() string {
 	if host, err := os.Hostname(); err == nil {
 		return host
 	}
-	return "Unknown"
+	return "Classified"
 }
 
 func summariseRunAnalysis(session *AppSession) ReportFiles {
 
+	fails := summariseSmashFails(session.Fails)
+	empty := summariseEmptyFiles(session.Empty.Files)
+	dupes := transformDupes(session.Dupes)
+
 	return ReportFiles{
-		Fails: summariseSmashedFails(session.Fails),
-		Empty: summariseSmashedFiles(session.Empty.Files),
-		Dupes: transformDupes(session.Dupes),
+		Fails: fails,
+		Empty: empty,
+		Dupes: dupes,
 	}
 }
 
-func summariseSmashedFails(fails *xsync.MapOf[string, error]) []ReportFailSummary {
+func summariseSmashFails(fails *xsync.MapOf[string, error]) []ReportFailSummary {
 	summary := make([]ReportFailSummary, fails.Size())
 	var index = 0
 	fails.Range(func(key string, value error) bool {
@@ -147,16 +156,24 @@ func transformDupes(duplicates *xsync.MapOf[string, *DuplicateFiles]) []ReportDu
 	var index = 0
 	duplicates.Range(func(hash string, dupe *DuplicateFiles) bool {
 		root := dupe.Files[0]
+		rest := dupe.Files[1:]
 		dupes[index] = ReportDuplicateSummary{
 			ReportFileSummary: summariseSmashedFile(root),
-			Duplicates:        summariseSmashedFiles(dupe.Files),
+			Duplicates:        summariseSmashedFiles(rest),
 		}
 		index++
 		return true
 	})
 	return dupes
 }
 
+func summariseEmptyFiles(files []File) []ReportFileBaseSummary {
+	summary := make([]ReportFileBaseSummary, len(files))
+	for i, file := range files {
+		summary[i] = summariseSmashedFile(file).ReportFileBaseSummary
+	}
+	return summary
+}
 func summariseSmashedFiles(files []File) []ReportFileSummary {
 	summary := make([]ReportFileSummary, len(files))
 	for i, file := range files {
@@ -166,9 +183,11 @@ func summariseSmashedFiles(files []File) []ReportFileSummary {
 }
 func summariseSmashedFile(file File) ReportFileSummary {
 	return ReportFileSummary{
-		Filename: file.Filename,
-		Location: file.Location,
-		Path:     filepath.Dir(file.Path),
+		ReportFileBaseSummary: ReportFileBaseSummary{
+			Filename: file.Filename,
+			Location: file.Location,
+			Path:     filepath.Dir(file.Path),
+		},
 		Hash:     file.Hash,
 		Size:     file.FileSize,
 		FullHash: file.FullHash,

readme.md

@@ -13,14 +13,13 @@ Tool to `smash` through to find duplicate files efficiently by slicing a file (o
 and computing a hash using a fast non-cryptographic algorithm such as [xxhash](https://xxhash.com/) or [murmur3](https://en.wikipedia.org/wiki/MurmurHash).
 
 <p align="center">
- <img src="https://vhs.charm.sh/vhs-1zSMi9vYpmh0DivoB4E6g4.gif" alt="Made with VHS"><br/>
+ <img src="https://vhs.charm.sh/vhs-5uZbZAvk8Y6eq4dihLppbk.gif" alt="Made with VHS"><br/>
     <sub>
         <sup>Find duplicates in the <a href="https://github.com/torvalds/linux">linux/drivers</a> source tree with <code>smash</code> (see our <a href="docs/demos.md">🍿 other demos</a>). Made with <a href="https://vhs.charm.sh" target="_blank">vhs</a>!</sup>
     </sub>
 </p>
 
-`smash` has a read-only view of the underlying filesystem and only reports duplicates - currently, we do not remove 
-duplicates and instead leave that for you to do via the output. We also don't support symlinks or NT Junction Points (Windows Symlinks) and ignore them.
+`smash` has a read-only view of the underlying filesystem, outputs empty and duplicate files into a json report that you can use a tool like [jq](https://github.com/jqlang/jq) to operate on. See examples below or [this vhs tape](https://vhs.charm.sh/vhs-4OwN0BJfb3F3CTzGJCFHcs.gif).
 
 The name comes from a prototype tool called SmartHash (written many years ago in C/ASM that's now lost in source & 
 too hard to modernise) which operated on a similar concept (with CRC32 then later MD5).
@@ -48,25 +47,26 @@ $ go install github.com/thushan/smash@latest
 ```
 Usage:
   smash [flags] [locations-to-smash]
-  
+
 Flags:
       --algorithm algorithm    Algorithm to use to hash files. Supported: xxhash, murmur3, md5, sha512, sha256 (full list, see readme) (default xxhash)
       --base strings           Base directories to use for comparison Eg. --base=/c/dos,/c/dos/run/,/run/dos/run
-      --disable-slicing        Disable slicing & hash the full file instead
       --disable-autotext       Disable detecting text-files to opt for a full hash for those
       --disable-meta           Disable storing of meta-data to improve hashing mismatches
+      --disable-slicing        Disable slicing & hash the full file instead
       --exclude-dir strings    Directories to exclude separated by comma Eg. --exclude-dir=.git,.idea
       --exclude-file strings   Files to exclude separated by comma Eg. --exclude-file=.gitignore,*.csv
   -h, --help                   help for smash
       --ignore-empty           Ignore empty/zero byte files (default true)
       --ignore-hidden          Ignore hidden files & folders Eg. files/folders starting with '.' (default true)
       --ignore-system          Ignore system files & folders Eg. '$MFT', '.Trash' (default true)
   -p, --max-threads int        Maximum threads to utilise (default 16)
-  -w, --max-workers int        Maximum workers to utilise when smashing (default 8)
+  -w, --max-workers int        Maximum workers to utilise when smashing (default 16)
       --nerd-stats             Show nerd stats
+      --no-output              Disable report output
       --no-progress            Disable progress updates
       --no-top-list            Hides top x duplicates list
-  -o, --output-file string     Export as JSON
+  -o, --output-file string     Export analysis as JSON (generated automatically otherwise)
       --profile                Enable Go Profiler - see localhost:1984/debug/pprof
       --progress-update int    Update progress every x seconds (default 5)
       --show-duplicates        Show full list of duplicates
@@ -84,18 +84,30 @@ Examples are given in Unix format, but apply to Windows as well.
 
 ### Basic
 
-To check for duplicates in a single path (Eg. `~/media/photos`)
+To check for duplicates in a single path (Eg. `~/media/photos`) & output report to `report.json`
 
 ```bash
-$ ./smash ~/media/photos
+$ ./smash ~/media/photos -o report.json
+```
+
+You can then look at `report.json` with [jq](https://github.com/jqlang/jq) to check duplicates:
+
+```bash 
+$ jq '.analysis.dupes[]|[.location,.path,.filename]|join("/")' report.json | xargs wc -l
 ```
 
 ### Show Empty Files
 
 By default, `smash` ignores empty files but can report on them with the `--ignore-empty=false` argument:
 
 ```bash
-$ ./smash ~/media/photos --ignore-empty=false
+$ ./smash ~/media/photos --ignore-empty=false -o report.json
+```
+
+You can then look at `report.json` with [jq](https://github.com/jqlang/jq) to check empty files:
+
+```bash 
+$ jq '.analysis.empty[]|[.location,.path,.filename]|join("/")' report.json | xargs wc -l
 ```
 
 ### Show Top 50 Duplicates
@@ -155,6 +167,7 @@ $ ./smash --algorithm:murmur3 ~/media/photos
 
 This project was possible thanks to the following projects or folks.
 
+* [@jqlang/jq](https://github.com/jqlang/jq) - without `jq` we'd be a bit lost!
 * [@wader/fq](https://github.com/wader/fq) - countless nights of inspecting binary blobs!
 * [@cespare/xxhash](https://github.com/cespare/xxhash) - xxhash implementation
 * [@spaolacci/murmur3](https://github.com/spaolacci/murmur3) - murmur3 implementation
@@ -164,7 +177,7 @@ This project was possible thanks to the following projects or folks.
 * [@golangci/golangci-lint](https://github.com/golangci/golangci-lint) - Go Linter
 * [@dkorunic/betteralign](https://github.com/dkorunic/betteralign) - Go alignment checker
 
-Testers - MarkB, JarredT, BenW, DencilW, JayT, ASV, TimW, RyanW, WilliamH
+Testers - MarkB, JarredT, BenW, DencilW, JayT, ASV, TimW, RyanW, WilliamH, SpencerB, EmadA, ChrisE, AngelaB
 
 # Licence