Merge pull request #135 from dingedi/feature/add-html-translation

Feature/add html translation

README.md

@@ -12,6 +12,9 @@ Free and Open Source Machine Translation API, entirely self-hosted. Unlike other
 
 ## API Examples
 
+
+### Plain Text
+
 Request:
 
 ```javascript
@@ -36,6 +39,33 @@ Response:
 }
 ```
 
+### HTML
+
+Request:
+
+```javascript
+const res = await fetch("https://libretranslate.com/translate", {
+	method: "POST",
+	body: JSON.stringify({
+		q: '<a href="#" class="green">Hello!</a>',
+		source: "en",
+		target: "es",
+		format: "html"
+	}),
+	headers: { "Content-Type": "application/json" }
+});
+
+console.log(await res.json());
+```
+
+Response:
+
+```javascript
+{
+    "translatedText": "<a href\"#='class=\"green\"'>¡Hola!</a>"
+}
+```
+
 ## Install and Run
 
 You can run your own API server in just a few lines of setup!
@@ -136,7 +166,6 @@ You can pass application arguments directly to Gunicorn via:
 gunicorn --bind 0.0.0.0:5000 'wsgi:app(api_keys=True)'
 ```
 
-
 ## Manage API Keys
 
 LibreTranslate supports per-user limit quotas, e.g. you can issue API keys to users so that they can enjoy higher requests limits per minute (if you also set `--req-limit`). By default all users are rate-limited based on `--req-limit`, but passing an optional `api_key` parameter to the REST endpoints allows a user to enjoy higher request limits.

app/app.py

@@ -10,6 +10,7 @@ from app.language import detect_languages, transliterate
 
 from .api_keys import Database
 
+from translatehtml import translate_html
 
 def get_json_dict(request):
     d = request.get_json()
@@ -262,6 +263,18 @@ def create_app(args):
               example: es
             required: true
             description: Target language code
+          - in: formData
+            name: format
+            schema:
+              type: string
+              enum: [text, html]
+              default: text
+              example: text
+            required: false
+            description: >
+              Format of source text:
+               * `text` - Plain text
+               * `html` - HTML markup
           - in: formData
             name: api_key
             schema:
@@ -323,10 +336,12 @@ def create_app(args):
             q = json.get("q")
             source_lang = json.get("source")
             target_lang = json.get("target")
+            text_format = json.get("format")
         else:
             q = request.values.get("q")
             source_lang = request.values.get("source")
             target_lang = request.values.get("target")
+            text_format = request.values.get("format")
 
         if not q:
             abort(400, description="Invalid request: missing q parameter")
@@ -396,14 +411,25 @@ def create_app(args):
         if tgt_lang is None:
             abort(400, description="%s is not supported" % target_lang)
 
+        if not text_format:
+            text_format = "text"
+
+        if text_format not in ["text", "html"]:
+            abort(400, description="%s format is not supported" % text_format)
+
+
         try:
             if batch:
                 results = []
                 for idx, text in enumerate(q):
                   translator = src_langs[idx].get_translation(tgt_lang)
-                  results.append(translator.translate(
+
-                                transliterate(text, target_lang=source_langs[idx])
+                  if text_format == "html":
-                                ))
+                    translated_text = str(translate_html(translator, transliterate(text, target_lang=source_langs[idx])))
+                  else:
+                    translated_text = translator.translate(transliterate(text, target_lang=source_langs[idx]))
+
+                  results.append(translated_text)
                 return jsonify(
                     {
                         "translatedText": results
@@ -411,11 +437,14 @@ def create_app(args):
                 )
             else:
                 translator = src_langs[0].get_translation(tgt_lang)
+
+                if text_format == "html":
+                    translated_text = str(translate_html(translator, transliterate(q, target_lang=source_langs[0])))
+                else:
+                    translated_text = translator.translate(transliterate(q, target_lang=source_langs[0]))
                 return jsonify(
                     {
-                        "translatedText": translator.translate(
+                        "translatedText": translated_text
-                            transliterate(q, target_lang=source_langs[0])
-                        )
                     }
                 )
         except Exception as e:

requirements.txt

@@ -11,3 +11,4 @@ morfessor==2.0.6
 polyglot==16.7.4
 appdirs==1.4.4
 APScheduler==3.7.0
+translatehtml==1.5.1