Merge pull request #16 from sansecio/wdg/xxhash

Replace crc32 with xxhash

corediff.go

@@ -8,9 +8,17 @@ import (
 	"log"
 	"os"
 	"path/filepath"
+	"runtime"
+
+	"github.com/gwillem/go-buildversion"
+	"github.com/gwillem/go-selfupdate"
 )
 
-var placeholder = struct{}{}
+var (
+	selfUpdateURL   = fmt.Sprintf("https://sansec.io/downloads/%s-%s/corediff", runtime.GOOS, runtime.GOARCH)
+	placeholder     = struct{}{}
+	corediffVersion = buildversion.String()
+)
 
 func loadDB(path string) hashDB {
 	m := make(hashDB)
@@ -23,7 +31,7 @@ func loadDB(path string) hashDB {
 	defer f.Close()
 	reader := bufio.NewReader(f)
 	for {
-		var b uint32
+		var b uint64
 		err = binary.Read(reader, binary.LittleEndian, &b)
 		if err == io.EOF {
 			break
@@ -187,10 +195,14 @@ func addPath(root string, db hashDB, args *baseArgs) {
 
 func main() {
 
+	if restarted, err := selfupdate.UpdateRestart(selfUpdateURL); restarted || err != nil {
+		logVerbose("Restarted new version", restarted, "with error:", err)
+	}
+
 	args := setup()
 	db := loadDB(args.Database)
 
-	logInfo(boldwhite("Corediff loaded ", len(db), " precomputed hashes. (C) 2020-2023 labs@sansec.io"))
+	logInfo(boldwhite("Corediff ", corediffVersion, " loaded ", len(db), " precomputed hashes. (C) 2020-2023 labs@sansec.io"))
 	logInfo("Using database:", args.Database, "\n")
 
 	if args.Merge {

corediff_test.go

@@ -10,7 +10,7 @@ import (
 	"github.com/stretchr/testify/assert"
 )
 
-func digest(b uint32) string {
+func digest(b uint64) string {
 	return fmt.Sprintf("%x", b)
 }
 
@@ -28,7 +28,7 @@ func Test_hash(t *testing.T) {
 		args []byte
 		want string
 	}{
-		{[]byte("banaan"), "14ac6691"},
+		{[]byte("banaan"), "acfb1ff4438e39f3"},
 	}
 	for _, tt := range tests {
 		t.Run(string(tt.args), func(t *testing.T) {
@@ -42,7 +42,7 @@ func Test_hash(t *testing.T) {
 func Test_vendor_bug(t *testing.T) {
 	db := loadDB("fixture/sample.db")
 	assert.Len(t, db, 238)
-	wantHash := uint32(3333369281)
+	wantHash := uint64(3900178074848893275)
 	if _, ok := db[wantHash]; !ok {
 		t.Error("hash not in db")
 	}

go.mod

@@ -1,22 +1,26 @@
-module github.com/gwillem/magento-corediff
+module github.com/sansecio/corediff
 
 go 1.20
 
 require (
-	github.com/cespare/xxhash/v2 v2.2.0
-	github.com/fatih/color v1.12.0
+	github.com/fatih/color v1.15.0
 	github.com/gobwas/glob v0.2.3
-	github.com/gwillem/urlfilecache v0.0.0-20201121123616-8e4f7e58333d
+	github.com/gwillem/go-buildversion v0.0.0-20230402114832-b1addefa8764
+	github.com/gwillem/go-selfupdate v0.0.0-20230402110315-648e078de292
+	github.com/gwillem/urlfilecache v0.0.0-20230402105623-8ef3b7b67c13
 	github.com/jessevdk/go-flags v1.5.0
-	github.com/stretchr/testify v1.6.1
+	github.com/stretchr/testify v1.8.2
 )
 
 require (
-	github.com/adrg/xdg v0.2.3 // indirect
-	github.com/davecgh/go-spew v1.1.0 // indirect
-	github.com/mattn/go-colorable v0.1.8 // indirect
-	github.com/mattn/go-isatty v0.0.12 // indirect
+	github.com/adrg/xdg v0.4.0 // indirect
+	github.com/cespare/xxhash/v2 v2.2.0 // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.18 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
-	golang.org/x/sys v0.0.0-20210320140829-1e4c9ba3b0c4 // indirect
-	gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c // indirect
+	golang.org/x/sys v0.6.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
+
+//replace github.com/gwillem/go-buildversion => ../go-buildversion

go.sum

@@ -1,31 +1,47 @@
-github.com/adrg/xdg v0.2.3 h1:GxXngdYxNDkoUvZXjNJGwqZxWXi43MKbOOlA/00qZi4=
-github.com/adrg/xdg v0.2.3/go.mod h1:7I2hH/IT30IsupOpKZ5ue7/qNi3CoKzD6tL3HwpaRMQ=
+github.com/adrg/xdg v0.4.0 h1:RzRqFcjH4nE5C6oTAxhBtoE2IRyjBSa62SCbyPidvls=
+github.com/adrg/xdg v0.4.0/go.mod h1:N6ag73EX4wyxeaoeHctc1mas01KZgsj5tYiAIwqJE/E=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/fatih/color v1.12.0 h1:mRhaKNwANqRgUBGKmnI5ZxEk7QXmjQeCcuYFMX2bfcc=
-github.com/fatih/color v1.12.0/go.mod h1:ELkj/draVOlAH/xkhN6mQ50Qd0MPOk5AAr3maGEBuJM=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/fatih/color v1.15.0 h1:kOqh6YHBtK8aywxGerMG2Eq3H6Qgoqeo13Bk2Mv/nBs=
+github.com/fatih/color v1.15.0/go.mod h1:0h5ZqXfHYED7Bhv2ZJamyIOUej9KtShiJESRwBDUSsw=
 github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
 github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
-github.com/gwillem/urlfilecache v0.0.0-20201121123616-8e4f7e58333d h1:SUYp/bOtCvpddj20LJRLoU/YFnoQhXLGG3S+Ro8uWP0=
-github.com/gwillem/urlfilecache v0.0.0-20201121123616-8e4f7e58333d/go.mod h1:wcspENTUwvMi317k0q22DWfx6hIXAlEjz5LO6pjJWQ0=
+github.com/gwillem/go-buildversion v0.0.0-20230402113215-08d191152cc5 h1:tMpRA020WZ+HsqrRFiflnC0Pj9gseMrG8jWimXw9WWQ=
+github.com/gwillem/go-buildversion v0.0.0-20230402113215-08d191152cc5/go.mod h1:mT3drjAmZ/WgzCwPqf270xC9absLnjSMbDSPXPRiGk8=
+github.com/gwillem/go-buildversion v0.0.0-20230402114832-b1addefa8764 h1:GL/gS9rv5F1oBgQwbT+pl0HefNbDZLjbcWmDNT/pUOU=
+github.com/gwillem/go-buildversion v0.0.0-20230402114832-b1addefa8764/go.mod h1:yf2A6rXn1ptErQTutA0vpEDZJG6E0b/aUnMnXelY5tU=
+github.com/gwillem/go-selfupdate v0.0.0-20230402110315-648e078de292 h1:AoF/jIYBBxpLJkyf204k6ArAFDFVKitkcOGnyYuWHco=
+github.com/gwillem/go-selfupdate v0.0.0-20230402110315-648e078de292/go.mod h1:Zv9vnDD/HDN/WCidxG2QdCEDtYIaIeUTX9yHspWZfEM=
+github.com/gwillem/urlfilecache v0.0.0-20230402105623-8ef3b7b67c13 h1:Kuu6BZRS1uaSatweU/S5pWKkwt+QFCMb2QjJrWcvTWA=
+github.com/gwillem/urlfilecache v0.0.0-20230402105623-8ef3b7b67c13/go.mod h1:vEuNDp+GXXq7N5Anwiu1f4VQ08IGuSTGs/PaFCEno/U=
 github.com/jessevdk/go-flags v1.5.0 h1:1jKYvbxEjfUl0fmqTCOfonvskHHXMjBySTLW4y9LFvc=
 github.com/jessevdk/go-flags v1.5.0/go.mod h1:Fw0T6WPc1dYxT4mKEZRfG5kJhaTDP9pj1c2EWnYs/m4=
-github.com/mattn/go-colorable v0.1.8 h1:c1ghPdyEDarC70ftn0y+A/Ee++9zz8ljHG1b13eJ0s8=
-github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
-github.com/mattn/go-isatty v0.0.12 h1:wuysRhFDzyxgEmMf5xjvJ2M9dZoWAXNNr5LSBS7uHXY=
-github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
+github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
+github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
+github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mattn/go-isatty v0.0.18 h1:DOKFKCQ7FNG2L1rbrmstDN4QVRdS89Nkh85u68Uwp98=
+github.com/mattn/go-isatty v0.0.18/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
-github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
-github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
-golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210320140829-1e4c9ba3b0c4 h1:EZ2mChiOa8udjfp6rRmswTbtZN/QzUQp4ptM4rnjHvc=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.2 h1:+h33VjcLVPDHtOdpUCuF+7gSuG3yGIftsP1YvFihtJ8=
+github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 golang.org/x/sys v0.0.0-20210320140829-1e4c9ba3b0c4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20211025201205-69cdffdb9359/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220209214540-3681064d5158/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0 h1:MVltZSvRTcU2ljQOhs94SXPftV6DCNnZViHeQps87pQ=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

helpers.go

@@ -3,12 +3,12 @@ package main
 import (
 	"bytes"
 	"fmt"
-	"hash/crc32"
 	"os"
 	"path/filepath"
 	"regexp"
 	"strings"
 
+	"github.com/cespare/xxhash/v2"
 	"github.com/gobwas/glob"
 )
 
@@ -78,11 +78,11 @@ func check(err error) {
 	}
 }
 
-func hash(b []byte) uint32 {
-	return crc32.ChecksumIEEE(b)
+func hash(b []byte) uint64 {
+	return xxhash.Sum64(b)
 }
 
-func pathHash(p string) uint32 {
+func pathHash(p string) uint64 {
 	return hash([]byte("path:" + p))
 }
 

needle_test.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"fmt"
+	"testing"
+)
+
+func Test_Needle(t *testing.T) {
+
+	needles := []string{
+		"path:app/code/Magedelight/GeoIp/Controller/Adminhtml/Currencymapping/Delete.php",
+	}
+	dbpath := "m2.db"
+
+	db := loadDB(dbpath)
+	fmt.Println("Loaded entries:", len(db))
+
+	for k, _ := range db {
+		fmt.Println("first entry", k)
+		break
+	}
+
+	for _, needle := range needles {
+		checksum := hash([]byte(needle))
+		hash := fmt.Sprintf("%x", checksum)
+		_, ok := db[checksum]
+		fmt.Println(ok, hash)
+	}
+}

setup.go

@@ -11,7 +11,7 @@ import (
 )
 
 type (
-	hashDB map[uint32]struct{}
+	hashDB map[uint64]struct{}
 
 	walkStats struct {
 		totalFiles          int
@@ -121,7 +121,7 @@ func setup() *baseArgs {
 			fmt.Println("Can't merge without given --database file")
 			os.Exit(1)
 		}
-		fmt.Println("Downloading default hash database from", hashDBURL)
+		// fmt.Println("Using default hash database from", hashDBURL)
 		args.Database = urlfilecache.ToPath(hashDBURL)
 	}