config/config.exs

@@ -885,7 +885,8 @@
 config :pleroma, :argos_translate,
   command_argos_translate: "argos-translate",
   command_argospm: "argospm",
-  default_language: "en"
+  fallback_language: "en",
+  strip_html: true
 
 # Import environment specific config. This must remain at the bottom
 # of this file so it overrides the configuration defined above.

docs/docs/configuration/cheatsheet.md

@@ -1143,6 +1143,9 @@ Translations are available at `/api/v1/statuses/:id/translations/:language`, whe
 
 ### `:argos_translate`
 
+[Argos Translate](https://github.com/argosopentech/argos-translate) is the library used by Libre Translate and can run as a command line tool. It's more basic than Libre Translate as it doesn't provide a way to properly handle html or language detection.
+
 - `:command_argos_translate` - command for `argos-translate`. Can be the command if it's in your PATH, or the full path to the file  (default: `argos-translate`).
 - `:command_argospm` - command for `argospm`. Can be the command if it's in your PATH, or the full path to the file (default: `argospm`).
-- `:default_language` - When no language is provided to translate from, this language will be used. Must be a two letter langage code from a language you have installed (default: `en`).
+- `:fallback_language` - When no language is provided to translate from, this language will be used. Must be a two letter langage code from a language you have installed (default: `en`).
+- `:strip_html` - Strip html from the post before translating the text (default: `true`).

lib/pleroma/akkoma/translators/argos_translate.ex

@@ -11,8 +11,8 @@ defp argospm do
     Config.get([:argos_translate, :command_argospm])
   end
 
-  defp default_language do
-    Config.get([:argos_translate, :default_language])
+  defp fallback_language do
+    Config.get([:argos_translate, :fallback_language])
   end
 
   defp safe_languages() do
@@ -63,19 +63,45 @@ defp safe_translate(string, from_language, to_language) do
     end
   end
 
+  defp clean_string(string, true) do
+    string
+    |> String.replace("<p>", "\n")
+    |> String.replace("</p>", "\n")
+    |> String.replace("<br>", "\n")
+    |> String.replace("<br/>", "\n")
+    |> String.replace("<li>", "\n")
+    |> Pleroma.HTML.strip_tags()
+    |> HtmlEntities.decode()
+  end
+
+  defp clean_string(string, _), do: string
+
+  defp htmlify_response(string, true) do
+    string
+    |> HtmlEntities.encode()
+    |> String.replace("\n", "<br/>")
+  end
+
+  defp htmlify_response(string, _), do: string
+
   @impl Pleroma.Akkoma.Translator
   def translate(string, from_language, to_language) do
+    strip_html = Config.get([:argos_translate, :strip_html])
     # Akkoma's Pleroma-fe expects us to detect the source language automatically.
     # Argos-translate doesn't have that option (yet?)
     #     see <https://github.com/argosopentech/argos-translate/issues/9>
-    # For now we choose a default source language from settings.
+    # For now we choose a fallback source language from settings.
     # Afterwards people get the option to overwrite the source language from a dropdown.
-    from_language = from_language || default_language()
-    to_language = to_language || default_language()
+    from_language = from_language || fallback_language()
+    to_language = to_language || fallback_language()
+    # Argos Translate doesn't properly translate HTML (yet?)
+    # For now we give admins the option to strip the html before translating
+    # Note that we have to add some html back to the response afterwards
+    string = clean_string(string, strip_html)
 
     with {translated, 0} <-
            safe_translate(string, from_language, to_language) do
-      {:ok, from_language, translated}
+      {:ok, from_language, translated |> htmlify_response(strip_html)}
     else
       {response, _} -> {:error, "ArgosTranslate failed to translate (#{response})"}
     end

test/pleroma/akkoma/translators/argos_translate_test.exs

@@ -63,4 +63,39 @@ test "it returns a proper error when the executable can't be found" do
     assert {:error, "ArgosTranslate failed to translate" <> _} =
              ArgosTranslate.translate("blabla", "nl", "en")
   end
+
+  test "it can strip html" do
+    content =
+      ~s[<p>What&#39;s up my fellow fedizens?</p><p>So anyway</p><ul><li><a class="hashtag" data-tag="cofe" href="https://suya.space/tag/cofe">#cofe</a></li><li><a class="hashtag" data-tag="suya" href="https://cofe.space/tag/suya">#Suya</a></li></ul><p>ammiright!<br/>:ablobfoxhyper:</p>]
+
+    stripped_content =
+      "\nWhat's up my fellow fedizens?\n\nSo anyway\n\n#cofe\n#Suya\nammiright!\n:ablobfoxhyper:\n"
+
+    expected_response_strip_html =
+      "<br/>What&#39;s up my fellow fedizens?<br/><br/>So anyway<br/><br/>#cofe<br/>#Suya<br/>ammiright!<br/>:ablobfoxhyper:<br/>"
+
+    response_strip_html =
+      with_mock System, [:passthrough],
+        cmd: fn "argos-translate_test",
+                ["--from-lang", _, "--to-lang", _, ^stripped_content],
+                _ ->
+          {stripped_content, 0}
+        end do
+        ArgosTranslate.translate(content, "nl", "en")
+      end
+
+    clear_config([:argos_translate, :strip_html], false)
+
+    response_no_strip_html =
+      with_mock System, [:passthrough],
+        cmd: fn "argos-translate_test", ["--from-lang", _, "--to-lang", _, string], _ ->
+          {string, 0}
+        end do
+        ArgosTranslate.translate(content, "nl", "en")
+      end
+
+    assert {:ok, "nl", content} == response_no_strip_html
+
+    assert {:ok, "nl", expected_response_strip_html} == response_strip_html
+  end
 end