From d58cd5db871b53942cf44614c6cf6e06a54e6d3b Mon Sep 17 00:00:00 2001
From: "Sergienko.V5" <Sergienko.V5@wildberries.ru>
Date: Sat, 19 Feb 2022 18:24:11 +0300
Subject: [PATCH] fix ValidUTF8

---
 cpd.go  |  8 ++++----
 go.mod  | 14 ++++++++++++++
 go.sum  | 14 ++++++++++++++
 utf8.go |  7 ++++++-
 4 files changed, 38 insertions(+), 5 deletions(-)
 create mode 100644 go.mod
 create mode 100644 go.sum

diff --git a/cpd.go b/cpd.go
index 21af8ae..f33d149 100644
--- a/cpd.go
+++ b/cpd.go
@@ -1,7 +1,7 @@
 //Package cpd - code page detect
 // (c) 2020 softlandia@gmail.com
 package cpd
-
+	
 import (
 	"bufio"
 	"errors"
@@ -61,7 +61,7 @@ func CodepageAutoDetect(b []byte) IDCodePage {
 // support convert only from/to Windows1251/IBM866
 func FileConvertCodepage(fileName string, fromCP, toCP IDCodePage) error {
 	switch {
-	case (fromCP == toCP):
+	case fromCP == toCP:
 		return nil
 	case (fromCP != CP1251) && (fromCP != CP866):
 		return nil
@@ -74,7 +74,7 @@ func FileConvertCodepage(fileName string, fromCP, toCP IDCodePage) error {
 	}
 	defer iFile.Close()
 
-	//TODO need using sytem tmp folder
+	//TODO need using system tmp folder
 	tmpFileName := fileName + "~"
 	oFile, err := os.Create(tmpFileName)
 	if err != nil {
@@ -150,7 +150,7 @@ var (
 	errUnsupportedOutputCodepage = errors.New("cpd: output codepage not support encode")
 )
 
-// NewReader - convertion to UTF-8
+// NewReader - conversion to UTF-8
 // return input reader if input contain less 4 bytes
 // return input reader if input contain ASCII data
 // if cpn[0] exist, then using it as input codepage name
diff --git a/go.mod b/go.mod
new file mode 100644
index 0000000..1ec7935
--- /dev/null
+++ b/go.mod
@@ -0,0 +1,14 @@
+module github.com/softlandia/cpd
+
+go 1.17
+
+require (
+	github.com/stretchr/testify v1.7.0
+	golang.org/x/text v0.3.7
+)
+
+require (
+	github.com/davecgh/go-spew v1.1.0 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c // indirect
+)
diff --git a/go.sum b/go.sum
new file mode 100644
index 0000000..aaea189
--- /dev/null
+++ b/go.sum
@@ -0,0 +1,14 @@
+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/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 v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+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=
diff --git a/utf8.go b/utf8.go
index 3fdbfd0..c2eea4f 100644
--- a/utf8.go
+++ b/utf8.go
@@ -50,7 +50,7 @@ func testUTF8bitPattern(b byte) (int, cp int32) {
 	return 0, 0
 }
 
-//ValidUTF8 - return true if imput slice contain true UTF-8
+//ValidUTF8 - return true if input slice contain true UTF-8
 func ValidUTF8(data []byte) bool {
 	m := len(data)
 	if m <= 1 {
@@ -67,6 +67,11 @@ func ValidUTF8(data []byte) bool {
 		if n == 0 {
 			return false
 		}
+
+		if i+int(n) >= m {
+			break
+		}
+
 		i++
 		var j int32
 		for j = 1; j < n; j++ {