cat: better binary display

cmd/zeta/main.go

@@ -53,6 +53,7 @@ type App struct {
 	LsFiles     command.LsFiles     `cmd:"ls-files" help:"Show information about files in the index and the working tree"`
 	HashObject  command.HashObject  `cmd:"hash-object" help:"Compute hash or create object"`
 	MergeFile   command.MergeFile   `cmd:"merge-file" help:"Run a three-way file merge"`
+	Show        command.Show        `cmd:"show" help:"Show various types of objects"`
 	Version     command.Version     `cmd:"version" help:"Display version information"`
 	Debug       bool                `name:"debug" help:"Enable debug mode; analyze timing"`
 }

go.mod

@@ -7,8 +7,8 @@ require (
 	github.com/Netflix/go-expect v0.0.0-20220104043353-73e0943537d2
 	github.com/ProtonMail/go-crypto v1.1.3
 	github.com/aws/aws-sdk-go-v2 v1.32.7
-	github.com/aws/aws-sdk-go-v2/config v1.28.6
-	github.com/aws/aws-sdk-go-v2/credentials v1.17.47
+	github.com/aws/aws-sdk-go-v2/config v1.28.7
+	github.com/aws/aws-sdk-go-v2/credentials v1.17.48
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.71.1
 	github.com/creack/pty v1.1.24
 	github.com/danieljoos/wincred v1.2.2
@@ -43,7 +43,7 @@ require (
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d // indirect
 	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.7 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.21 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.22 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.26 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.26 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.1 // indirect
@@ -52,9 +52,9 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.4.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.7 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.24.7 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.6 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.33.2 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.24.8 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.33.3 // indirect
 	github.com/aws/smithy-go v1.22.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/cloudflare/circl v1.5.0 // indirect

go.sum

@@ -16,12 +16,12 @@ github.com/aws/aws-sdk-go-v2 v1.32.7 h1:ky5o35oENWi0JYWUZkB7WYvVPP+bcRF5/Iq7JWSb
 github.com/aws/aws-sdk-go-v2 v1.32.7/go.mod h1:P5WJBrYqqbWVaOxgH0X/FYYD47/nooaPOZPlQdmiN2U=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.7 h1:lL7IfaFzngfx0ZwUGOZdsFFnQ5uLvR0hWqqhyE7Q9M8=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.7/go.mod h1:QraP0UcVlQJsmHfioCrveWOC1nbiWUl3ej08h4mXWoc=
-github.com/aws/aws-sdk-go-v2/config v1.28.6 h1:D89IKtGrs/I3QXOLNTH93NJYtDhm8SYa9Q5CsPShmyo=
-github.com/aws/aws-sdk-go-v2/config v1.28.6/go.mod h1:GDzxJ5wyyFSCoLkS+UhGB0dArhb9mI+Co4dHtoTxbko=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.47 h1:48bA+3/fCdi2yAwVt+3COvmatZ6jUDNkDTIsqDiMUdw=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.47/go.mod h1:+KdckOejLW3Ks3b0E3b5rHsr2f9yuORBum0WPnE5o5w=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.21 h1:AmoU1pziydclFT/xRV+xXE/Vb8fttJCLRPv8oAkprc0=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.21/go.mod h1:AjUdLYe4Tgs6kpH4Bv7uMZo7pottoyHMn4eTcIcneaY=
+github.com/aws/aws-sdk-go-v2/config v1.28.7 h1:GduUnoTXlhkgnxTD93g1nv4tVPILbdNQOzav+Wpg7AE=
+github.com/aws/aws-sdk-go-v2/config v1.28.7/go.mod h1:vZGX6GVkIE8uECSUHB6MWAUsd4ZcG2Yq/dMa4refR3M=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.48 h1:IYdLD1qTJ0zanRavulofmqut4afs45mOWEI+MzZtTfQ=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.48/go.mod h1:tOscxHN3CGmuX9idQ3+qbkzrjVIx32lqDSU1/0d/qXs=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.22 h1:kqOrpojG71DxJm/KDPO+Z/y1phm1JlC8/iT+5XRmAn8=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.22/go.mod h1:NtSFajXVVL8TA2QNngagVZmUtXciyrHOt7xgz4faS/M=
 github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.26 h1:I/5wmGMffY4happ8NOCuIUEWGUvvFp5NSeQcXl9RHcI=
 github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.26/go.mod h1:FR8f4turZtNy6baO0KJ5FJUmXH/cSkI9fOngs0yl6mA=
 github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.26 h1:zXFLuEuMMUOvEARXFUVJdfqZ4bvvSgdGRq/ATcrQxzM=
@@ -40,12 +40,12 @@ github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.7 h1:Hi0KGbrnr57bEH
 github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.7/go.mod h1:wKNgWgExdjjrm4qvfbTorkvocEstaoDl4WCvGfeCy9c=
 github.com/aws/aws-sdk-go-v2/service/s3 v1.71.1 h1:aOVVZJgWbaH+EJYPvEgkNhCEbXXvH7+oML36oaPK3zE=
 github.com/aws/aws-sdk-go-v2/service/s3 v1.71.1/go.mod h1:r+xl5yzMk9083rMR+sJ5TYj9Tihvf/l1oxzZXDgGj2Q=
-github.com/aws/aws-sdk-go-v2/service/sso v1.24.7 h1:rLnYAfXQ3YAccocshIH5mzNNwZBkBo+bP6EhIxak6Hw=
-github.com/aws/aws-sdk-go-v2/service/sso v1.24.7/go.mod h1:ZHtuQJ6t9A/+YDuxOLnbryAmITtr8UysSny3qcyvJTc=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.6 h1:JnhTZR3PiYDNKlXy50/pNeix9aGMo6lLpXwJ1mw8MD4=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.6/go.mod h1:URronUEGfXZN1VpdktPSD1EkAL9mfrV+2F4sjH38qOY=
-github.com/aws/aws-sdk-go-v2/service/sts v1.33.2 h1:s4074ZO1Hk8qv65GqNXqDjmkf4HSQqJukaLuuW0TpDA=
-github.com/aws/aws-sdk-go-v2/service/sts v1.33.2/go.mod h1:mVggCnIWoM09jP71Wh+ea7+5gAp53q+49wDFs1SW5z8=
+github.com/aws/aws-sdk-go-v2/service/sso v1.24.8 h1:CvuUmnXI7ebaUAhbJcDy9YQx8wHR69eZ9I7q5hszt/g=
+github.com/aws/aws-sdk-go-v2/service/sso v1.24.8/go.mod h1:XDeGv1opzwm8ubxddF0cgqkZWsyOtw4lr6dxwmb6YQg=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.7 h1:F2rBfNAL5UyswqoeWv9zs74N/NanhK16ydHW1pahX6E=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.7/go.mod h1:JfyQ0g2JG8+Krq0EuZNnRwX0mU0HrwY/tG6JNfcqh4k=
+github.com/aws/aws-sdk-go-v2/service/sts v1.33.3 h1:Xgv/hyNgvLda/M9l9qxXc4UFSgppnRczLxlMs5Ae/QY=
+github.com/aws/aws-sdk-go-v2/service/sts v1.33.3/go.mod h1:5Gn+d+VaaRgsjewpMvGazt0WfcFO+Md4wLOuBfGR9Bc=
 github.com/aws/smithy-go v1.22.1 h1:/HPHZQ0g7f4eUeK6HKglFz8uwVfZKgoI25rb/J+dnro=
 github.com/aws/smithy-go v1.22.1/go.mod h1:irrKGvNn1InZwb2d7fkIRNucdfwR8R+Ts3wxYa/cJHg=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=

modules/diferenco/text.go

@@ -94,17 +94,37 @@ func readRawText(r io.Reader, size int) (string, error) {
 	return unsafe.String(unsafe.SliceData(content), len(content)), nil
 }
 
-func ReadUnifiedText(r io.Reader, size int64, textConv bool) (content string, charset string, err error) {
+func ReadUnifiedText(r io.Reader, size int64, textconv bool) (content string, charset string, err error) {
 	if size > MAX_DIFF_SIZE {
 		return "", "", ErrNonTextContent
 	}
-	if textConv {
+	if textconv {
 		return readUnifiedText(r)
 	}
 	content, err = readRawText(r, int(size))
 	return content, UTF8, err
 }
 
+func NewUnifiedReaderEx(r io.Reader, textconv bool) (io.Reader, string, error) {
+	sniffBytes, err := streamio.ReadMax(r, sniffLen)
+	if err != nil {
+		return nil, "", err
+	}
+	reader := io.MultiReader(bytes.NewReader(sniffBytes), r)
+	if !textconv {
+		if bytes.IndexByte(sniffBytes, 0) != -1 {
+			return reader, BINARY, nil
+		}
+		return reader, UTF8, nil
+	}
+	charset := detectCharset(sniffBytes)
+	// binary or UTF-8 not need convert
+	if charset == BINARY || strings.EqualFold(charset, UTF8) {
+		return reader, charset, nil
+	}
+	return chardet.NewReader(reader, charset), charset, nil
+}
+
 func NewUnifiedReader(r io.Reader) (io.Reader, error) {
 	sniffBytes, err := streamio.ReadMax(r, sniffLen)
 	if err != nil {

modules/streamio/bytes.go

@@ -36,7 +36,7 @@ func PutByteSlice(buf *[]byte) {
 }
 
 // GetBytesBuffer returns a *bytes.Buffer that is managed by a sync.Pool.
-// Returns a buffer that is resetted and ready for use.
+// Returns a buffer that is reset and ready for use.
 //
 // After use, the *bytes.Buffer should be put back into the sync.Pool
 // by calling PutBytesBuffer.

modules/streamio/sync.go

@@ -13,7 +13,7 @@ var bufioReader = sync.Pool{
 }
 
 // GetBufioReader returns a *bufio.Reader that is managed by a sync.Pool.
-// Returns a bufio.Reader that is resetted with reader and ready for use.
+// Returns a bufio.Reader that is reset with reader and ready for use.
 //
 // After use, the *bufio.Reader should be put back into the sync.Pool
 // by calling PutBufioReader.
@@ -39,7 +39,7 @@ var bufferWriter = sync.Pool{
 }
 
 // GetBufferWriter returns a *bufio.Writer that is managed by a sync.Pool.
-// Returns a bufio.Writer that is resetted with writer and ready for use.
+// Returns a bufio.Writer that is reset with writer and ready for use.
 //
 // After use, the *bufio.Writer should be put back into the sync.Pool
 // by calling PutBufferWriter.

modules/streamio/zlib.go

@@ -35,7 +35,7 @@ type ZLibReader struct {
 }
 
 // GetZlibReader returns a ZLibReader that is managed by a sync.Pool.
-// Returns a ZLibReader that is resetted using a dictionary that is
+// Returns a ZLibReader that is reset using a dictionary that is
 // also managed by a sync.Pool.
 //
 // After use, the ZLibReader should be put back into the sync.Pool
@@ -58,7 +58,7 @@ func PutZlibReader(z *ZLibReader) {
 }
 
 // GetZlibWriter returns a *zlib.Writer that is managed by a sync.Pool.
-// Returns a writer that is resetted with w and ready for use.
+// Returns a writer that is reset with w and ready for use.
 //
 // After use, the *zlib.Writer should be put back into the sync.Pool
 // by calling PutZlibWriter.

modules/streamio/zstd.go

@@ -31,7 +31,7 @@ type ZstdDecoder struct {
 }
 
 // GetZstdReader returns a ZstdDecoder that is managed by a sync.Pool.
-// Returns a ZLibReader that is resetted using a dictionary that is
+// Returns a ZLibReader that is reset using a dictionary that is
 // also managed by a sync.Pool.
 //
 // After use, the ZstdDecoder should be put back into the sync.Pool
@@ -55,7 +55,7 @@ type ZstdEncoder struct {
 }
 
 // GetZstdWriter returns a *ztsd.Encoder that is managed by a sync.Pool.
-// Returns a writer that is resetted with w and ready for use.
+// Returns a writer that is reset with w and ready for use.
 //
 // After use, the *ztsd.Encoder  should be put back into the sync.Pool
 // by calling PutZstdWriter.

modules/zeta/object/commit.go

@@ -313,6 +313,17 @@ func (c *Commit) Root(ctx context.Context) (*Tree, error) {
 	return resolveTree(ctx, c.b, c.Tree)
 }
 
+// File returns the file with the specified "path" in the commit and a
+// nil error if the file exists. If the file does not exist, it returns
+// a nil file and the ErrFileNotFound error.
+func (c *Commit) File(ctx context.Context, path string) (*File, error) {
+	tree, err := c.Root(ctx)
+	if err != nil {
+		return nil, err
+	}
+	return tree.File(ctx, path)
+}
+
 // StatsContext returns the stats of a commit. Error will be return if context
 // expires. Provided context must be non-nil.
 func (c *Commit) StatsContext(ctx context.Context, m noder.Matcher, opts *PatchOptions) (FileStats, error) {

modules/zeta/object/patch.go

@@ -8,6 +8,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"path"
 	"strconv"
 	"strings"
 
@@ -21,14 +22,28 @@ var (
 
 type PatchOptions struct {
 	Algorithm diferenco.Algorithm
-	TextConv  bool
+	Textconv  bool
 	Match     func(string) bool
 }
 
 func sizeOverflow(f *File) bool {
 	return f != nil && f.Size > diferenco.MAX_DIFF_SIZE
 }
 
+func PathRenameCombine(from, to string) string {
+	fromPaths := strings.Split(from, "/")
+	toPaths := strings.Split(to, "/")
+	n := min(len(fromPaths), len(toPaths))
+	i := 0
+	for i < n && fromPaths[i] == toPaths[i] {
+		i++
+	}
+	if i == 0 {
+		return fmt.Sprintf("%s => %s", from, to)
+	}
+	return fmt.Sprintf("%s/{%s => %s}", path.Join(fromPaths[0:i]...), path.Join(fromPaths[i:]...), path.Join(toPaths[i:]...))
+}
+
 func fileStatName(from, to *File) string {
 	if from == nil {
 		// New File is created.
@@ -40,7 +55,7 @@ func fileStatName(from, to *File) string {
 	}
 	if from.Path != to.Path {
 		// File is renamed.
-		return fmt.Sprintf("%s => %s", from.Path, to.Path)
+		return PathRenameCombine(from.Path, to.Path)
 	}
 	return from.Path
 }
@@ -63,14 +78,14 @@ func fileStatWithContext(ctx context.Context, opts *PatchOptions, c *Change) (*F
 	if sizeOverflow(from) || sizeOverflow(to) {
 		return s, nil
 	}
-	fromContent, err := from.UnifiedText(ctx, opts.TextConv)
+	fromContent, err := from.UnifiedText(ctx, opts.Textconv)
 	if plumbing.IsNoSuchObject(err) || err == diferenco.ErrNonTextContent {
 		return s, nil
 	}
 	if err != nil {
 		return nil, err
 	}
-	toContent, err := to.UnifiedText(ctx, opts.TextConv)
+	toContent, err := to.UnifiedText(ctx, opts.Textconv)
 	if plumbing.IsNoSuchObject(err) || err == diferenco.ErrNonTextContent {
 		return s, nil
 	}
@@ -121,14 +136,14 @@ func filePatchWithContext(ctx context.Context, opts *PatchOptions, c *Change) (*
 	if sizeOverflow(from) || sizeOverflow(to) {
 		return &diferenco.Unified{From: from.asFile(), To: to.asFile(), IsBinary: true}, nil
 	}
-	fromContent, err := from.UnifiedText(ctx, opts.TextConv)
+	fromContent, err := from.UnifiedText(ctx, opts.Textconv)
 	if plumbing.IsNoSuchObject(err) || err == diferenco.ErrNonTextContent {
 		return &diferenco.Unified{From: from.asFile(), To: to.asFile(), IsBinary: true}, nil
 	}
 	if err != nil {
 		return nil, err
 	}
-	toContent, err := to.UnifiedText(ctx, opts.TextConv)
+	toContent, err := to.UnifiedText(ctx, opts.Textconv)
 	if plumbing.IsNoSuchObject(err) || err == diferenco.ErrNonTextContent {
 		return &diferenco.Unified{From: from.asFile(), To: to.asFile(), IsBinary: true}, nil
 	}

modules/zeta/object/patch_test.go

@@ -0,0 +1,30 @@
+package object
+
+import (
+	"fmt"
+	"os"
+	"testing"
+)
+
+func TestPathRenameCombine(t *testing.T) {
+	pp := []struct {
+		A, B string
+	}{
+		{
+			"a.txt",
+			"b.txt",
+		},
+		{
+			"pkg/command/command_merge_file.go",
+			"pkg/command/merge.go",
+		},
+		{
+			"pkg/command/command_merge_file.go",
+			"pkg/merge.go",
+		},
+	}
+	for _, i := range pp {
+		d := PathRenameCombine(i.A, i.B)
+		fmt.Fprintf(os.Stderr, "%s => %s|%s\n", i.A, i.B, d)
+	}
+}

modules/zeta/object/tree.go

@@ -571,6 +571,16 @@ func resolveTree(ctx context.Context, b Backend, h plumbing.Hash) (*Tree, error)
 	return t, nil
 }
 
+// File returns the hash of the file identified by the `path` argument.
+// The path is interpreted as relative to the tree receiver.
+func (t *Tree) File(ctx context.Context, path string) (*File, error) {
+	e, err := t.FindEntry(ctx, path)
+	if err != nil {
+		return nil, &ErrEntryNotFound{entry: path}
+	}
+	return newFile(e.Name, path, e.Mode, e.Hash, e.Size, t.b), nil
+}
+
 // Diff returns a list of changes between this tree and the provided one
 func (t *Tree) Diff(to *Tree, m noder.Matcher) (Changes, error) {
 	return t.DiffContext(context.Background(), to, m)

pkg/command/command_cat.go

@@ -10,13 +10,15 @@ import (
 )
 
 type Cat struct {
-	Hash        string `arg:"" name:"object" help:"The name of the object to show"`
-	WriteMax    int64  `name:"max" short:"m" optional:"" help:"Blob output size limit; use 0 for unlimited. Units: KB, MB, GB, K, M, G" default:"20m" type:"size"`
+	Object      string `arg:"" name:"object" help:"The name of the object to show"`
 	T           bool   `name:"type" short:"t" help:"Show object type"`
 	DisplaySize bool   `name:":" short:"s" help:"Show object size"`
 	JSON        bool   `name:"json" short:"j" help:"Returns data as JSON; limited to commits, trees, fragments, and tags"`
-	Textconv    bool   `name:"textconv" help:"Output text as Unicode; blobs only"`
+	Textconv    bool   `name:"textconv" help:"Converting text to Unicode"`
+	Direct      bool   `name:"direct" help:"View files directly"`
 	Verify      bool   `name:"verify" help:"Verify object hash"`
+	Limit       int64  `name:"limit" short:"L" help:"Omits blobs larger than n bytes or units. n may be zero. supported units: KB,MB,GB,K,M,G" default:"-1" type:"size"`
+	Output      string `name:"output" help:"Output to a specific file instead of stdout" placeholder:"<file>"`
 }
 
 func (c *Cat) Run(g *Globals) error {
@@ -30,12 +32,14 @@ func (c *Cat) Run(g *Globals) error {
 	}
 	defer r.Close()
 	return r.Cat(context.Background(), &zeta.CatOptions{
-		Hash:        c.Hash,
-		SizeMax:     c.WriteMax,
-		Type:        c.T,
-		DisplaySize: c.DisplaySize,
-		Textconv:    c.Textconv,
-		FormatJSON:  c.JSON,
-		Verify:      c.Verify,
+		Object:    c.Object,
+		Limit:     c.Limit,
+		Type:      c.T,
+		PrintSize: c.DisplaySize,
+		Textconv:  c.Textconv,
+		Direct:    c.Direct,
+		PrintJSON: c.JSON,
+		Verify:    c.Verify,
+		Output:    c.Output,
 	})
 }