✨(backend) Import of documents

We can now import documents in formats .docx and .md.
To do so we added a new container "docspec", which
uses the docspec service to convert
these formats to Blocknote format.

More here: #1567 #1569.

src/backend/core/api/serializers.py

@@ -11,6 +11,7 @@ from django.utils.functional import lazy
 from django.utils.text import slugify
 from django.utils.translation import gettext_lazy as _
 
+from core.services import mime_types
 import magic
 from rest_framework import serializers
 
@@ -18,7 +19,7 @@ from core import choices, enums, models, utils, validators
 from core.services.ai_services import AI_ACTIONS
 from core.services.converter_services import (
     ConversionError,
-    YdocConverter,
+    Converter,
 )
 
 
@@ -164,6 +165,7 @@ class DocumentSerializer(ListDocumentSerializer):
 
     content = serializers.CharField(required=False)
     websocket = serializers.BooleanField(required=False, write_only=True)
+    file = serializers.FileField(required=False, write_only=True, allow_null=True)
 
     class Meta:
         model = models.Document
@@ -180,6 +182,7 @@ class DocumentSerializer(ListDocumentSerializer):
             "deleted_at",
             "depth",
             "excerpt",
+            "file",
             "is_favorite",
             "link_role",
             "link_reach",
@@ -437,7 +440,11 @@ class ServerCreateDocumentSerializer(serializers.Serializer):
             language = user.language or language
 
         try:
-            document_content = YdocConverter().convert(validated_data["content"])
+            document_content = Converter().convert(
+                validated_data["content"],
+                mime_types.MARKDOWN,
+                mime_types.YJS
+            )
         except ConversionError as err:
             raise serializers.ValidationError(
                 {"content": ["Could not convert content"]}

src/backend/core/api/viewsets.py

@@ -46,14 +46,12 @@ from core.api.filters import remove_accents
 from core.services.ai_services import AIService
 from core.services.collaboration_services import CollaborationService
 from core.services.converter_services import (
+    ConversionError,
     ServiceUnavailableError as YProviderServiceUnavailableError,
-)
-from core.services.converter_services import (
     ValidationError as YProviderValidationError,
+    Converter,
 )
-from core.services.converter_services import (
-    YdocConverter,
-)
+from core.services import mime_types
 from core.services.search_indexers import (
     get_document_indexer,
     get_visited_document_ids_of,
@@ -527,6 +525,28 @@ class DocumentViewSet(
                 "IN SHARE ROW EXCLUSIVE MODE;"
             )
 
+        # Remove file from validated_data as it's not a model field
+        # Process it if present
+        uploaded_file = serializer.validated_data.pop("file", None)
+
+        # If a file is uploaded, convert it to Yjs format and set as content
+        if uploaded_file:
+            try:
+                file_content = uploaded_file.read()
+
+                converter = Converter()
+                converted_content = converter.convert(
+                    file_content,
+                    content_type=uploaded_file.content_type,
+                    accept=mime_types.YJS
+                )
+                serializer.validated_data["content"] = converted_content
+                serializer.validated_data["title"] = uploaded_file.name
+            except ConversionError as err:
+                raise drf.exceptions.ValidationError(
+                    {"file": ["Could not convert file content"]}
+                ) from err
+
         obj = models.Document.add_root(
             creator=self.request.user,
             **serializer.validated_data,
@@ -1881,14 +1901,14 @@ class DocumentViewSet(
         if base64_content is not None:
             # Convert using the y-provider service
             try:
-                yprovider = YdocConverter()
+                yprovider = Converter()
                 result = yprovider.convert(
                     base64.b64decode(base64_content),
-                    "application/vnd.yjs.doc",
+                    mime_types.YJS,
                     {
-                        "markdown": "text/markdown",
-                        "html": "text/html",
-                        "json": "application/json",
+                        "markdown": mime_types.MARKDOWN,
+                        "html": mime_types.HTML,
+                        "json": mime_types.JSON,
                     }[content_format],
                 )
                 content = result