Merge pull request #38 from vbatts/travis

travis: test more go versions

.travis.yml

@@ -1,16 +1,17 @@
 language: go
 go:
   - tip
-  - 1.5.1
+  - 1.x
-  - 1.4.3
+  - 1.8.x
-  - 1.3.3
+  - 1.7.x
+  - 1.6.x
+  - 1.5.x
 
 # let us have pretty, fast Docker-based Travis workers!
 sudo: false
 
 install:
   - go get -d ./...
-  - go get golang.org/x/tools/cmd/vet
 
 script:
   - go test -v ./...

README.md

@@ -1,6 +1,7 @@
 # tar-split
 
 [![Build Status](https://travis-ci.org/vbatts/tar-split.svg?branch=master)](https://travis-ci.org/vbatts/tar-split)
+[![Go Report Card](https://goreportcard.com/badge/github.com/vbatts/tar-split)](https://goreportcard.com/report/github.com/vbatts/tar-split)
 
 Pristinely disassembling a tar archive, and stashing needed raw bytes and offsets to reassemble a validating original archive.
 
@@ -39,7 +40,7 @@ This demonstrates the `tar-split` command and how to assemble a tar archive from
 
 This demonstrates the tar-split integration for docker-1.8. Providing consistent tar archives for the image layer content.
 
-![docker tar-split demo](https://www.youtube.com/upload_thumbnail?v=tV_Dia8E8xw&t=2&ts=1445028436275)
+![docker tar-split demo](https://i.ytimg.com/vi_webp/vh5wyjIOBtc/default.webp)
 [youtube vide of docker layer checksums](https://youtu.be/tV_Dia8E8xw)
 
 ## Caveat
@@ -66,7 +67,7 @@ Do not break the API of stdlib `archive/tar` in our fork (ideally find an upstre
 
 ## Std Version
 
-The version of golang stdlib `archive/tar` is from go1.4.1, and their master branch around [a9dddb53f](https://github.com/golang/go/tree/a9dddb53f).
+The version of golang stdlib `archive/tar` is from go1.6
 It is minimally extended to expose the raw bytes of the TAR, rather than just the marshalled headers and file stream.
 
 

archive/tar/reader.go

@@ -608,11 +608,12 @@ func (tr *Reader) readHeader() *Header {
 	header := tr.hdrBuff[:]
 	copy(header, zeroBlock)
 
-	if _, tr.err = io.ReadFull(tr.r, header); tr.err != nil {
+	if n, err := io.ReadFull(tr.r, header); err != nil {
+		tr.err = err
 		// because it could read some of the block, but reach EOF first
 		if tr.err == io.EOF && tr.RawAccounting {
-			if _, tr.err = tr.rawBytes.Write(header); tr.err != nil {
+			if _, err := tr.rawBytes.Write(header[:n]); err != nil {
-				return nil
+				tr.err = err
 			}
 		}
 		return nil // io.EOF is okay here
@@ -625,11 +626,12 @@ func (tr *Reader) readHeader() *Header {
 
 	// Two blocks of zero bytes marks the end of the archive.
 	if bytes.Equal(header, zeroBlock[0:blockSize]) {
-		if _, tr.err = io.ReadFull(tr.r, header); tr.err != nil {
+		if n, err := io.ReadFull(tr.r, header); err != nil {
+			tr.err = err
 			// because it could read some of the block, but reach EOF first
 			if tr.err == io.EOF && tr.RawAccounting {
-				if _, tr.err = tr.rawBytes.Write(header); tr.err != nil {
+				if _, err := tr.rawBytes.Write(header[:n]); err != nil {
-					return nil
+					tr.err = err
 				}
 			}
 			return nil // io.EOF is okay here

archive/tar/tar_test.go

@@ -94,13 +94,12 @@ func TestRoundTrip(t *testing.T) {
 	var b bytes.Buffer
 	tw := NewWriter(&b)
 	hdr := &Header{
-		Name:    "file.txt",
+		Name: "file.txt",
-		Uid:     1 << 21, // too big for 8 octal digits
+		Uid:  1 << 21, // too big for 8 octal digits
-		Size:    int64(len(data)),
+		Size: int64(len(data)),
-		ModTime: time.Now(),
+		// https://github.com/golang/go/commit/0e3355903d2ebcf5ee9e76096f51ac9a116a9dbb#diff-d7bf2a98d7b57b6ff754ca406f1b7581R105
+		ModTime: time.Now().AddDate(0, 0, 0).Round(1 * time.Second),
 	}
-	// tar only supports second precision.
-	hdr.ModTime = hdr.ModTime.Add(-time.Duration(hdr.ModTime.Nanosecond()) * time.Nanosecond)
 	if err := tw.WriteHeader(hdr); err != nil {
 		t.Fatalf("tw.WriteHeader: %v", err)
 	}

cmd/tar-split/asm.go

@@ -6,7 +6,7 @@ import (
 	"os"
 
 	"github.com/Sirupsen/logrus"
-	"github.com/codegangsta/cli"
+	"github.com/urfave/cli"
 	"github.com/vbatts/tar-split/tar/asm"
 	"github.com/vbatts/tar-split/tar/storage"
 )

cmd/tar-split/checksize.go

@@ -10,7 +10,7 @@ import (
 	"os"
 
 	"github.com/Sirupsen/logrus"
-	"github.com/codegangsta/cli"
+	"github.com/urfave/cli"
 	"github.com/vbatts/tar-split/tar/asm"
 	"github.com/vbatts/tar-split/tar/storage"
 )

cmd/tar-split/disasm.go

@@ -3,10 +3,11 @@ package main
 import (
 	"compress/gzip"
 	"io"
+	"io/ioutil"
 	"os"
 
 	"github.com/Sirupsen/logrus"
-	"github.com/codegangsta/cli"
+	"github.com/urfave/cli"
 	"github.com/vbatts/tar-split/tar/asm"
 	"github.com/vbatts/tar-split/tar/storage"
 )
@@ -48,7 +49,13 @@ func CommandDisasm(c *cli.Context) {
 	if err != nil {
 		logrus.Fatal(err)
 	}
-	i, err := io.Copy(os.Stdout, its)
+	var out io.Writer
+	if c.Bool("no-stdout") {
+		out = ioutil.Discard
+	} else {
+		out = os.Stdout
+	}
+	i, err := io.Copy(out, its)
 	if err != nil {
 		logrus.Fatal(err)
 	}

cmd/tar-split/main.go

@@ -4,7 +4,7 @@ import (
 	"os"
 
 	"github.com/Sirupsen/logrus"
-	"github.com/codegangsta/cli"
+	"github.com/urfave/cli"
 	"github.com/vbatts/tar-split/version"
 )
 
@@ -42,6 +42,10 @@ func main() {
 					Value: "tar-data.json.gz",
 					Usage: "output of disassembled tar stream",
 				},
+				cli.BoolFlag{
+					Name:  "no-stdout",
+					Usage: "do not throughput the stream to STDOUT",
+				},
 			},
 		},
 		{

tar/asm/assemble_test.go

@@ -139,6 +139,8 @@ var testCases = []struct {
 	{"./testdata/longlink.tar.gz", "d9f6babe107b7247953dff6b5b5ae31a3a880add", 20480},
 	{"./testdata/fatlonglink.tar.gz", "8537f03f89aeef537382f8b0bb065d93e03b0be8", 26234880},
 	{"./testdata/iso-8859.tar.gz", "ddafa51cb03c74ec117ab366ee2240d13bba1ec3", 10240},
+	{"./testdata/extranils.tar.gz", "e187b4b3e739deaccc257342f4940f34403dc588", 10648},
+	{"./testdata/notenoughnils.tar.gz", "72f93f41efd95290baa5c174c234f5d4c22ce601", 512},
 }
 
 func TestTarStream(t *testing.T) {

tar_benchmark_test.go

@@ -0,0 +1,84 @@
+package tartest
+
+import (
+	"io"
+	"io/ioutil"
+	"os"
+	"testing"
+
+	upTar "archive/tar"
+
+	ourTar "github.com/vbatts/tar-split/archive/tar"
+)
+
+var testfile = "./archive/tar/testdata/sparse-formats.tar"
+
+func BenchmarkUpstreamTar(b *testing.B) {
+	for n := 0; n < b.N; n++ {
+		fh, err := os.Open(testfile)
+		if err != nil {
+			b.Fatal(err)
+		}
+		tr := upTar.NewReader(fh)
+		for {
+			_, err := tr.Next()
+			if err != nil {
+				if err == io.EOF {
+					break
+				}
+				fh.Close()
+				b.Fatal(err)
+			}
+			io.Copy(ioutil.Discard, tr)
+		}
+		fh.Close()
+	}
+}
+
+func BenchmarkOurTarNoAccounting(b *testing.B) {
+	for n := 0; n < b.N; n++ {
+		fh, err := os.Open(testfile)
+		if err != nil {
+			b.Fatal(err)
+		}
+		tr := ourTar.NewReader(fh)
+		tr.RawAccounting = false // this is default, but explicit here
+		for {
+			_, err := tr.Next()
+			if err != nil {
+				if err == io.EOF {
+					break
+				}
+				fh.Close()
+				b.Fatal(err)
+			}
+			io.Copy(ioutil.Discard, tr)
+		}
+		fh.Close()
+	}
+}
+func BenchmarkOurTarYesAccounting(b *testing.B) {
+	for n := 0; n < b.N; n++ {
+		fh, err := os.Open(testfile)
+		if err != nil {
+			b.Fatal(err)
+		}
+		tr := ourTar.NewReader(fh)
+		tr.RawAccounting = true // This enables mechanics for collecting raw bytes
+		for {
+			_ = tr.RawBytes()
+			_, err := tr.Next()
+			_ = tr.RawBytes()
+			if err != nil {
+				if err == io.EOF {
+					break
+				}
+				fh.Close()
+				b.Fatal(err)
+			}
+			io.Copy(ioutil.Discard, tr)
+			_ = tr.RawBytes()
+		}
+		fh.Close()
+	}
+}

version/version.go

@@ -1,7 +1,7 @@
 package version
 
 // AUTO-GENEREATED. DO NOT EDIT
-// 2016-02-15 09:43:15.919197079 -0500 EST
+// 2016-09-26 19:53:30.825879 -0400 EDT
 
 // VERSION is the generated version from /home/vbatts/src/vb/tar-split/version
-var VERSION = "v0.9.13-19-862ccd05b"
+var VERSION = "v0.10.1-4-gf280282"