DEV: Locale normalizer

app/services/discourse_translator/post_locale_detector.rb

@@ -7,8 +7,9 @@ def self.detect_locale(post)
 
       translator = DiscourseTranslator::Provider::TranslatorProvider.get
       detected_locale = translator.detect!(post)
-      post.update!(locale: detected_locale)
-      detected_locale
+      locale = LocaleNormalizer.normalize_to_i18n(detected_locale)
+      post.update!(locale:)
+      locale
     end
   end
 end

lib/discourse_translator/locale_normalizer.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module DiscourseTranslator
+  class LocaleNormalizer
+    # Normalizes locale string, matching the list of I18n.locales where possible
+    # @param locale [String,Symbol] the locale to normalize
+    # @return [String] the normalized locale
+    def self.normalize_to_i18n(locale)
+      return nil if locale.blank?
+      locale = locale.to_s.gsub("-", "_")
+
+      i18n_pairs.each { |downcased, value| return value if locale.downcase == downcased }
+
+      locale
+    end
+
+    private
+
+    def self.i18n_pairs
+      # they should look like this for the input to match against:
+      # {
+      #   "lowercased" => "actual",
+      #   "en" => "en",
+      #   "zh_cn" => "zh_CN",
+      #   "zh" => "zh_CN",
+      # }
+      @locale_map ||=
+        begin
+          output = {}
+          I18n.available_locales.each do |sym|
+            locale = sym.to_s
+            output[locale.downcase] = locale
+            if locale.include?("_")
+              short = locale.split("_").first
+              output[short] = locale if output[short].blank?
+            end
+          end
+
+          output
+        end
+    end
+  end
+end

spec/lib/locale_normalizer_spec.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+describe DiscourseTranslator::LocaleNormalizer do
+  it "matches input locales to i18n locales" do
+    expect(described_class.normalize_to_i18n("en-GB")).to eq("en_GB")
+    expect(described_class.normalize_to_i18n("en")).to eq("en")
+    expect(described_class.normalize_to_i18n("zh")).to eq("zh_CN")
+    expect(described_class.normalize_to_i18n("tr")).to eq("tr_TR")
+  end
+
+  it "converts dashes to underscores" do
+    expect(described_class.normalize_to_i18n("a-b")).to eq("a_b")
+  end
+end

spec/services/post_locale_detector_spec.rb

@@ -13,14 +13,14 @@
     end
 
     it "calls detect! on the provider with the post" do
-      translator.expects(:detect!).with(post).returns("ja")
-      expect(described_class.detect_locale(post)).to eq("ja")
+      translator.expects(:detect!).with(post).returns("zh")
+      expect(described_class.detect_locale(post)).to eq("zh_CN")
     end
 
     it "updates the post locale with the detected locale" do
-      translator.stubs(:detect!).with(post).returns("ja")
+      translator.stubs(:detect!).with(post).returns("zh")
       expect { described_class.detect_locale(post) }.to change { post.reload.locale }.from(nil).to(
-        "ja",
+        "zh_CN",
       )
     end
   end