13 ppe hostedcom showing in provider (#21)

* add ppe-hosted

* convert non-ascii to ascii

* fix test

bulkvalidate/bulkvalidate.go

@@ -143,7 +143,7 @@ func RunBulkValidation(inputFilePath, outputFilePath string) {
 		if err != nil {
 			log.Printf("Error: %s %s", email, err.Error())
 		}
-		emailResults, err := mailvalidate.ValidateEmail(request)
+		emailResults, err := mailvalidate.ValidateEmail(request, syntaxResults)
 		if err != nil {
 			log.Printf("Error: %s %s", email, err.Error())
 		}

go.mod

@@ -16,4 +16,5 @@ require (
 	github.com/schollz/progressbar/v3 v3.14.6 // indirect
 	golang.org/x/sys v0.23.0 // indirect
 	golang.org/x/term v0.23.0 // indirect
+	golang.org/x/text v0.17.0 // indirect
 )

go.sum

@@ -28,3 +28,5 @@ golang.org/x/sys v0.23.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.22.0/go.mod h1:F3qCibpT5AMpCRfhfT53vVJwhLtIVHhB9XDjfFvnMI4=
 golang.org/x/term v0.23.0 h1:F6D4vR+EHoL9/sWAWgAR1H2DcHr4PareCbAaCo1RpuU=
 golang.org/x/term v0.23.0/go.mod h1:DgV24QBUrK6jhZXl+20l6UWznPlwAHm1Q1mGHtydmSk=
+golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=

internal/cmd/cmd.go

@@ -51,7 +51,7 @@ func VerifyEmail(email string) {
 	request := run.BuildRequest(email)
 	syntaxResults := VerifySyntax(email, false)
 	domainResults := VerifyDomain(syntaxResults.Domain, false)
-	emailResults, err := mailvalidate.ValidateEmail(request)
+	emailResults, err := mailvalidate.ValidateEmail(request, syntaxResults)
 	if err != nil {
 		fmt.Println(err)
 	}

internal/dns/known_email_providers.toml

@@ -101,6 +101,7 @@ domains = [
     ["ondmarc.com", "ondmarc"],
     ["powerspf.com", "power spf"],
     ["pphosted.com", "proofpoint"],
+    ["ppe-hosted.com", "proofpoint"],
     ["redpoints.com", "red points"],
     ["reflexion.net", "sophos"],
     ["res.cisco.com", "cisco"],

internal/run/run.go

@@ -80,8 +80,13 @@ func BuildResponse(emailAddress string, syntax mailvalidate.SyntaxValidation, do
 		Description:  email.Description,
 	}
 
+	cleanEmail := emailAddress
+	if syntax.IsValid {
+		cleanEmail = fmt.Sprintf("%s@%s", syntax.User, syntax.Domain)
+	}
+
 	response := VerifyEmailResponse{
-		Email:         emailAddress,
+		Email:         cleanEmail,
 		IsDeliverable: email.IsDeliverable,
 		Provider:      domain.Provider,
 		Firewall:      domain.Firewall,

internal/syntax/syntax.go

@@ -3,26 +3,44 @@ package syntax
 import (
 	"regexp"
 	"strings"
+	"unicode"
 
 	"golang.org/x/net/publicsuffix"
+	"golang.org/x/text/runes"
+	"golang.org/x/text/transform"
+	"golang.org/x/text/unicode/norm"
 )
 
 var (
 	usernameRegex = regexp.MustCompile(`^[\p{L}\p{N}.!#$%&'+-/=?^_` + "`" + `{|}~]+$`)
 	domainRegex   = regexp.MustCompile(`^[a-zA-Z0-9][a-zA-Z0-9-]{0,61}[a-zA-Z0-9](?:\.[a-zA-Z0-9][a-zA-Z0-9-]{0,61}[a-zA-Z0-9])*$`)
 )
 
-func IsValidEmailSyntax(email string) bool {
+func IsValidEmailSyntax(email string) (bool, string) {
+	normalizedEmail := convertToAscii(email)
+
 	if !isValidEmailFormat(email) {
-		return false
+		return false, ""
 	}
 
 	username, domain, ok := splitEmail(email)
 	if !ok {
-		return false
+		return false, ""
 	}
 
-	return isValidUsername(username) && isValidDomain(domain)
+	return isValidUsername(username) && isValidDomain(domain), normalizedEmail
+}
+
+func GetEmailUserAndDomain(email string) (string, string, bool) {
+	if strings.TrimSpace(email) != email {
+		return "", "", false
+	}
+	user, domain, ok := splitEmail(email)
+	if !isValidUsername(user) || !isValidDomain(domain) {
+		return "", "", false
+	}
+
+	return user, domain, ok
 }
 
 func isValidEmailFormat(email string) bool {
@@ -90,14 +108,17 @@ func isValidTLD(tld string) bool {
 	return icann
 }
 
-func GetEmailUserAndDomain(email string) (string, string, bool) {
-	if strings.TrimSpace(email) != email {
-		return "", "", false
-	}
-	user, domain, ok := splitEmail(email)
-	if !isValidUsername(user) || !isValidDomain(domain) {
-		return "", "", false
+func convertToAscii(input string) string {
+	t := transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC)
+	result, _, _ := transform.String(t, input)
+
+	// Step 2: Remove any remaining non-ASCII characters
+	ascii := make([]rune, 0, len(result))
+	for _, r := range result {
+		if r <= unicode.MaxASCII {
+			ascii = append(ascii, r)
+		}
 	}
 
-	return user, domain, ok
+	return string(ascii)
 }

internal/syntax/syntax_test.go

@@ -35,7 +35,7 @@ func TestIsValidEmailSyntax(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			if got := IsValidEmailSyntax(tt.email); got != tt.want {
+			if got, _ := IsValidEmailSyntax(tt.email); got != tt.want {
 				t.Errorf("IsValidEmailSyntax(%q) = %v, want %v", tt.email, got, tt.want)
 			}
 		})

mailvalidate/validation.go

@@ -52,12 +52,12 @@ type SyntaxValidation struct {
 
 func ValidateEmailSyntax(email string) SyntaxValidation {
 	var results SyntaxValidation
-	ok := syntax.IsValidEmailSyntax(email)
+	ok, cleanEmail := syntax.IsValidEmailSyntax(email)
 	if !ok {
 		return results
 	}
 
-	user, domain, ok := syntax.GetEmailUserAndDomain(email)
+	user, domain, ok := syntax.GetEmailUserAndDomain(cleanEmail)
 	if !ok {
 		return results
 	}
@@ -121,11 +121,14 @@ func ValidateDomainWithCustomKnownProviders(validationRequest EmailValidationReq
 	return results, nil
 }
 
-func ValidateEmail(validationRequest EmailValidationRequest) (EmailValidation, error) {
+func ValidateEmail(validationRequest EmailValidationRequest, emailSyntaxResults SyntaxValidation) (EmailValidation, error) {
 	var results EmailValidation
 	if err := validateRequest(&validationRequest); err != nil {
 		return results, errors.Wrap(err, "Invalid request")
 	}
+	if !emailSyntaxResults.IsValid {
+		return results, fmt.Errorf("Invalid email address")
+	}
 
 	freeEmails, err := GetFreeEmailList()
 	if err != nil {
@@ -137,20 +140,22 @@ func ValidateEmail(validationRequest EmailValidationRequest) (EmailValidation, e
 		log.Fatal(err)
 	}
 
-	isFreeEmail, err := IsFreeEmailCheck(validationRequest.Email, freeEmails)
+	email := fmt.Sprintf("%s@%s", emailSyntaxResults.User, emailSyntaxResults.Domain)
+
+	isFreeEmail, err := IsFreeEmailCheck(email, freeEmails)
 	if err != nil {
 		return results, errors.Wrap(err, "Error executing free email check")
 	}
 	results.IsFreeAccount = isFreeEmail
 
-	isRoleAccount, err := IsRoleAccountCheck(validationRequest.Email, roleAccounts)
+	isRoleAccount, err := IsRoleAccountCheck(email, roleAccounts)
 	if err != nil {
 		return results, errors.Wrap(err, "Error executing role account check")
 	}
 	results.IsRoleAccount = isRoleAccount
 
 	isVerified, smtpValidation, err := mailserver.VerifyEmailAddress(
-		validationRequest.Email,
+		email,
 		validationRequest.FromDomain,
 		validationRequest.FromEmail,
 		validationRequest.Dns,