detect: skip binary files with --no-git (#810)

detect/detect.go

@@ -15,6 +15,7 @@ import (
 
 	"github.com/fatih/semgroup"
 	"github.com/gitleaks/go-gitdiff/gitdiff"
+	"github.com/h2non/filetype"
 	"github.com/rs/zerolog/log"
 	"github.com/spf13/viper"
 )
@@ -322,6 +323,15 @@ func (d *Detector) DetectFiles(source string) ([]report.Finding, error) {
 			if err != nil {
 				return err
 			}
+
+			mimetype, err := filetype.Match(b)
+			if err != nil {
+				return err
+			}
+			if mimetype.MIME.Type == "application" {
+				return nil // skip binary files
+			}
+
 			fragment := Fragment{
 				Raw:      string(b),
 				FilePath: p,

go.mod

@@ -14,6 +14,7 @@ require (
 require (
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/fsnotify/fsnotify v1.4.9 // indirect
+	github.com/h2non/filetype v1.1.3 // indirect
 	github.com/hashicorp/hcl v1.0.0 // indirect
 	github.com/inconshreveable/mousetrap v1.0.0 // indirect
 	github.com/magiconair/properties v1.8.5 // indirect

go.sum

@@ -143,6 +143,8 @@ github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5m
 github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
 github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
+github.com/h2non/filetype v1.1.3 h1:FKkx9QbD7HR/zjK1Ia5XiBsq9zdLi5Kf3zGyFTAFkGg=
+github.com/h2non/filetype v1.1.3/go.mod h1:319b3zT68BvV+WRj7cwy856M2ehB3HqNOt6sy1HndBY=
 github.com/hashicorp/consul/api v1.1.0/go.mod h1:VmuI/Lkw1nC05EYQWNKwWGbkg+FbDBtguAZLlVdkD9Q=
 github.com/hashicorp/consul/sdk v0.1.1/go.mod h1:VKf9jXwCTEY1QZP2MOLRhb5i/I/ssyNV1vwHyQBF0x8=
 github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=