libpod/container_internal: Split locale at the first dot, etc.

We're going to feed this into Go's BCP 47 language parser.  Language
tags have the form [1]:

  language
  ["-" script]
  ["-" region]
  *("-" variant)
  *("-" extension)
  ["-" privateuse]

and locales have the form [2]:

  [language[_territory][.codeset][@modifier]]

The modifier is useful for collation, but Go's language-based API
[3] does not provide a way for us to supply it.  This code converts
our locale to a BCP 47 language by stripping the dot and later and
replacing the first underscore, if any, with a hyphen.  This will
avoid errors like [4]:

  WARN[0000] failed to parse language "en_US.UTF-8": language: tag is not well-formed

when feeding language.Parse(...).

[1]: https://tools.ietf.org/html/bcp47#section-2.1
[2]: http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap08.html#tag_08_02
[3]: https://github.com/golang/go/issues/25340
[4]: https://github.com/containers/libpod/issues/2494

Signed-off-by: W. Trevor King <wking@tremily.us>

2 files changed, 61 insertions, 7 deletions

diff --git a/libpod/container_internal.go b/libpod/container_internal.go
index 08945c410..d86062e38 100644
--- a/libpod/container_internal.go
+++ b/libpod/container_internal.go
@@ -34,8 +34,8 @@ const (
 )
 
 var (
-	// localeToLanguage maps from locale values to language tags.
-	localeToLanguage = map[string]string{
+	// localeToLanguageMap maps from locale values to language tags.
+	localeToLanguageMap = map[string]string{
 		"":      "und-u-va-posix",
 		"c":     "und-u-va-posix",
 		"posix": "und-u-va-posix",
@@ -1281,6 +1281,16 @@ func (c *Container) saveSpec(spec *spec.Spec) error {
 	return nil
 }
 
+// localeToLanguage translates POSIX locale strings to BCP 47 language tags.
+func localeToLanguage(locale string) string {
+	locale = strings.Replace(strings.SplitN(locale, ".", 2)[0], "_", "-", 1)
+	langString, ok := localeToLanguageMap[strings.ToLower(locale)]
+	if !ok {
+		langString = locale
+	}
+	return langString
+}
+
 // Warning: precreate hooks may alter 'config' in place.
 func (c *Container) setupOCIHooks(ctx context.Context, config *spec.Spec) (extensionStageHooks map[string][]spec.Hook, err error) {
 	var locale string
@@ -1296,11 +1306,7 @@ func (c *Container) setupOCIHooks(ctx context.Context, config *spec.Spec) (exten
 		}
 	}
 
-	langString, ok := localeToLanguage[strings.ToLower(locale)]
-	if !ok {
-		langString = locale
-	}
-
+	langString := localeToLanguage(locale)
 	lang, err := language.Parse(langString)
 	if err != nil {
 		logrus.Warnf("failed to parse language %q: %s", langString, err)
diff --git a/libpod/container_internal_test.go b/libpod/container_internal_test.go
index f1e2b70a7..1654af929 100644
--- a/libpod/container_internal_test.go
+++ b/libpod/container_internal_test.go
@@ -17,6 +17,54 @@ import (
 // hookPath is the path to an example hook executable.
 var hookPath string
 
+func TestLocaleToLanguage(t *testing.T) {
+	for _, testCase := range []struct {
+		locale   string
+		language string
+	}{
+		{
+			locale:   "",
+			language: "und-u-va-posix",
+		},
+		{
+			locale:   "C",
+			language: "und-u-va-posix",
+		},
+		{
+			locale:   "POSIX",
+			language: "und-u-va-posix",
+		},
+		{
+			locale:   "c",
+			language: "und-u-va-posix",
+		},
+		{
+			locale:   "en",
+			language: "en",
+		},
+		{
+			locale:   "en_US",
+			language: "en-US",
+		},
+		{
+			locale:   "en.UTF-8",
+			language: "en",
+		},
+		{
+			locale:   "en_US.UTF-8",
+			language: "en-US",
+		},
+		{
+			locale:   "does-not-exist",
+			language: "does-not-exist",
+		},
+	} {
+		t.Run(testCase.locale, func(t *testing.T) {
+			assert.Equal(t, testCase.language, localeToLanguage(testCase.locale))
+		})
+	}
+}
+
 func TestPostDeleteHooks(t *testing.T) {
 	ctx := context.Background()
 	dir, err := ioutil.TempDir("", "libpod_test_")