✨ Import of documents

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to
 ### Added 
 
 - ✨(frontend) integrate configurable Waffle #1795
+- ✨ Import of documents #1609
 
 ### Changed
 

Makefile

@@ -213,6 +213,7 @@ logs: ## display app-dev logs (follow mode)
 .PHONY: logs
 
 run-backend: ## Start only the backend application and all needed services
+	@$(COMPOSE) up --force-recreate -d docspec
 	@$(COMPOSE) up --force-recreate -d celery-dev
 	@$(COMPOSE) up --force-recreate -d y-provider-development
 	@$(COMPOSE) up --force-recreate -d nginx

bin/Tiltfile

@@ -8,6 +8,7 @@ docker_build(
     dockerfile='../Dockerfile',
     only=['./src/backend', './src/mail', './docker'],
     target = 'backend-production',
+    build_args={'DOCKER_USER': '1000:1000'},
     live_update=[
         sync('../src/backend', '/app'),
         run(
@@ -23,6 +24,7 @@ docker_build(
     dockerfile='../src/frontend/servers/y-provider/Dockerfile',
     only=['./src/frontend/', './docker/', './.dockerignore'],
     target = 'y-provider',
+    build_args={'DOCKER_USER': '1000:1000'},
     live_update=[
         sync('../src/frontend/servers/y-provider/src', '/home/frontend/servers/y-provider/src'),
     ]
@@ -34,6 +36,7 @@ docker_build(
     dockerfile='../src/frontend/Dockerfile',
     only=['./src/frontend', './docker', './.dockerignore'],
     target = 'impress',
+    build_args={'DOCKER_USER': '1000:1000'},
     live_update=[
         sync('../src/frontend', '/home/frontend'),
     ]

compose.yml

@@ -231,6 +231,11 @@ services:
         condition: service_healthy
         restart: true
 
+  docspec:
+    image: ghcr.io/docspecio/api:2.6.3
+    ports:
+      - "4000:4000"
+
 networks:
   lasuite:
     name: lasuite-network

docs/env.md

@@ -32,6 +32,8 @@ These are the environment variables you can set for the `impress-backend` contai
 | CONVERSION_API_ENDPOINT                         | Conversion API endpoint                                                                                                                                                    | convert                                                                 |
 | CONVERSION_API_SECURE                           | Require secure conversion api                                                                                                                                              | false                                                                   |
 | CONVERSION_API_TIMEOUT                          | Conversion api timeout                                                                                                                                                     | 30                                                                      |
+| CONVERSION_FILE_MAX_SIZE                        | The file max size allowed when uploaded to convert it                                                                                                                      | 20971520 (20MB)                                                         |
+| CONVERSION_FILE_EXTENSIONS_ALLOWED              | Extension list managed by the conversion service                                                                                                                           | [".docx", ".md"]
 | CRISP_WEBSITE_ID                                | Crisp website id for support                                                                                                                                               |                                                                         |
 | DB_ENGINE                                       | Engine to use for database connections                                                                                                                                     | django.db.backends.postgresql_psycopg2                                  |
 | DB_HOST                                         | Host of the database                                                                                                                                                       | localhost                                                               |
@@ -58,6 +60,7 @@ These are the environment variables you can set for the `impress-backend` contai
 | DJANGO_EMAIL_USE_TLS                            | Use tls for email host connection                                                                                                                                          | false                                                                   |
 | DJANGO_SECRET_KEY                               | Secret key                                                                                                                                                                 |                                                                         |
 | DJANGO_SERVER_TO_SERVER_API_TOKENS              |                                                                                                                                                                            | []                                                                      |
+| DOCSPEC_API_URL                               | URL to endpoint of DocSpec conversion API    |            |
 | DOCUMENT_IMAGE_MAX_SIZE                         | Maximum size of document in bytes                                                                                                                                          | 10485760                                                                |
 | FRONTEND_CSS_URL                                | To add a external css file to the app                                                                                                                                      |                                                                         |
 | FRONTEND_JS_URL                                | To add a external js file to the app                                                                                                                                      |                                                                         |

env.d/development/common

@@ -76,6 +76,8 @@ DJANGO_SERVER_TO_SERVER_API_TOKENS=server-api-token
 Y_PROVIDER_API_BASE_URL=http://y-provider-development:4444/api/
 Y_PROVIDER_API_KEY=yprovider-api-key
 
+DOCSPEC_API_URL=http://docspec:4000/conversion
+
 # Theme customization
 THEME_CUSTOMIZATION_CACHE_TIMEOUT=15
 

env.d/development/common.e2e

@@ -6,4 +6,4 @@ Y_PROVIDER_API_BASE_URL=http://y-provider:4444/api/
 
 # Throttle
 API_DOCUMENT_THROTTLE_RATE=1000/min
-API_CONFIG_THROTTLE_RATE=1000/min
+API_CONFIG_THROTTLE_RATE=1000/min

src/backend/core/api/serializers.py

@@ -4,6 +4,7 @@
 import binascii
 import mimetypes
 from base64 import b64decode
+from os.path import splitext
 
 from django.conf import settings
 from django.db.models import Q
@@ -15,10 +16,11 @@
 from rest_framework import serializers
 
 from core import choices, enums, models, utils, validators
+from core.services import mime_types
 from core.services.ai_services import AI_ACTIONS
 from core.services.converter_services import (
     ConversionError,
-    YdocConverter,
+    Converter,
 )
 
 
@@ -164,6 +166,9 @@ 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, max_length=255
+    )
 
     class Meta:
         model = models.Document
@@ -180,6 +185,7 @@ class Meta:
             "deleted_at",
             "depth",
             "excerpt",
+            "file",
             "is_favorite",
             "link_role",
             "link_reach",
@@ -249,6 +255,30 @@ def validate_content(self, value):
 
         return value
 
+    def validate_file(self, file):
+        """Add file size and type constraints as defined in settings."""
+        if not file:
+            return None
+
+        # Validate file size
+        if file.size > settings.CONVERSION_FILE_MAX_SIZE:
+            max_size = settings.CONVERSION_FILE_MAX_SIZE // (1024 * 1024)
+            raise serializers.ValidationError(
+                f"File size exceeds the maximum limit of {max_size:d} MB."
+            )
+
+        _name, extension = splitext(file.name)
+
+        if extension.lower() not in settings.CONVERSION_FILE_EXTENSIONS_ALLOWED:
+            raise serializers.ValidationError(
+                (
+                    f"File extension {extension} is not allowed. Allowed extensions"
+                    f" are: {settings.CONVERSION_FILE_EXTENSIONS_ALLOWED}."
+                )
+            )
+
+        return file
+
     def save(self, **kwargs):
         """
         Process the content field to extract attachment keys and update the document's
@@ -437,7 +467,9 @@ def create(self, validated_data):
             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

@@ -43,16 +43,18 @@
 
 from core import authentication, choices, enums, models
 from core.api.filters import remove_accents
+from core.services import mime_types
 from core.services.ai_services import AIService
 from core.services.collaboration_services import CollaborationService
 from core.services.converter_services import (
-    ServiceUnavailableError as YProviderServiceUnavailableError,
+    ConversionError,
+    Converter,
 )
 from core.services.converter_services import (
-    ValidationError as YProviderValidationError,
+    ServiceUnavailableError as YProviderServiceUnavailableError,
 )
 from core.services.converter_services import (
-    YdocConverter,
+    ValidationError as YProviderValidationError,
 )
 from core.services.search_indexers import (
     get_document_indexer,
@@ -527,6 +529,28 @@ def perform_create(self, serializer):
                 "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 +1905,14 @@ def content(self, request, pk=None):
         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
@@ -2316,6 +2340,8 @@ def get(self, request):
             "AI_FEATURE_ENABLED",
             "COLLABORATION_WS_URL",
             "COLLABORATION_WS_NOT_CONNECTED_READY_ONLY",
+            "CONVERSION_FILE_EXTENSIONS_ALLOWED",
+            "CONVERSION_FILE_MAX_SIZE",
             "CRISP_WEBSITE_ID",
             "ENVIRONMENT",
             "FRONTEND_CSS_URL",

src/backend/core/services/converter_services.py

@@ -1,11 +1,17 @@
 """Y-Provider API services."""
 
+import logging
+import typing
 from base64 import b64encode
 
 from django.conf import settings
 
 import requests
 
+from core.services import mime_types
+
+logger = logging.getLogger(__name__)
+
 
 class ConversionError(Exception):
     """Base exception for conversion-related errors."""
@@ -19,8 +25,81 @@ class ServiceUnavailableError(ConversionError):
     """Raised when the conversion service is unavailable."""
 
 
+class ConverterProtocol(typing.Protocol):
+    """Protocol for converter classes."""
+
+    def convert(self, data, content_type, accept):
+        """Convert content from one format to another."""
+
+
+class Converter:
+    """Orchestrates conversion between different formats using specialized converters."""
+
+    docspec: ConverterProtocol
+    ydoc: ConverterProtocol
+
+    def __init__(self):
+        self.docspec = DocSpecConverter()
+        self.ydoc = YdocConverter()
+
+    def convert(self, data, content_type, accept):
+        """Convert input into other formats using external microservices."""
+
+        if content_type == mime_types.DOCX and accept == mime_types.YJS:
+            blocknote_data = self.docspec.convert(
+                data, mime_types.DOCX, mime_types.BLOCKNOTE
+            )
+            return self.ydoc.convert(
+                blocknote_data, mime_types.BLOCKNOTE, mime_types.YJS
+            )
+
+        return self.ydoc.convert(data, content_type, accept)
+
+
+class DocSpecConverter:
+    """Service class for DocSpec conversion-related operations."""
+
+    def _request(self, url, data, content_type):
+        """Make a request to the DocSpec API."""
+
+        response = requests.post(
+            url,
+            headers={"Accept": mime_types.BLOCKNOTE},
+            files={"file": ("document.docx", data, content_type)},
+            timeout=settings.CONVERSION_API_TIMEOUT,
+            verify=settings.CONVERSION_API_SECURE,
+        )
+        if not response.ok:
+            logger.error(
+                "DocSpec API error: url=%s, status=%d, response=%s",
+                url,
+                response.status_code,
+                response.text[:200] if response.text else "empty",
+            )
+        response.raise_for_status()
+        return response
+
+    def convert(self, data, content_type, accept):
+        """Convert a Document to BlockNote."""
+        if not data:
+            raise ValidationError("Input data cannot be empty")
+
+        if content_type != mime_types.DOCX or accept != mime_types.BLOCKNOTE:
+            raise ValidationError(
+                f"Conversion from {content_type} to {accept} is not supported."
+            )
+
+        try:
+            return self._request(settings.DOCSPEC_API_URL, data, content_type).content
+        except requests.RequestException as err:
+            logger.exception("DocSpec service error: url=%s", settings.DOCSPEC_API_URL)
+            raise ServiceUnavailableError(
+                "Failed to connect to DocSpec conversion service",
+            ) from err
+
+
 class YdocConverter:
-    """Service class for conversion-related operations."""
+    """Service class for YDoc conversion-related operations."""
 
     @property
     def auth_header(self):
@@ -41,32 +120,34 @@ def _request(self, url, data, content_type, accept):
             timeout=settings.CONVERSION_API_TIMEOUT,
             verify=settings.CONVERSION_API_SECURE,
         )
+        if not response.ok:
+            logger.error(
+                "Y-Provider API error: url=%s, status=%d, response=%s",
+                url,
+                response.status_code,
+                response.text[:200] if response.text else "empty",
+            )
         response.raise_for_status()
         return response
 
-    def convert(
-        self, text, content_type="text/markdown", accept="application/vnd.yjs.doc"
-    ):
+    def convert(self, data, content_type=mime_types.MARKDOWN, accept=mime_types.YJS):
         """Convert a Markdown text into our internal format using an external microservice."""
 
-        if not text:
-            raise ValidationError("Input text cannot be empty")
+        if not data:
+            raise ValidationError("Input data cannot be empty")
 
+        url = f"{settings.Y_PROVIDER_API_BASE_URL}{settings.CONVERSION_API_ENDPOINT}/"
         try:
-            response = self._request(
-                f"{settings.Y_PROVIDER_API_BASE_URL}{settings.CONVERSION_API_ENDPOINT}/",
-                text,
-                content_type,
-                accept,
-            )
-            if accept == "application/vnd.yjs.doc":
+            response = self._request(url, data, content_type, accept)
+            if accept == mime_types.YJS:
                 return b64encode(response.content).decode("utf-8")
-            if accept in {"text/markdown", "text/html"}:
+            if accept in {mime_types.MARKDOWN, "text/html"}:
                 return response.text
-            if accept == "application/json":
+            if accept == mime_types.JSON:
                 return response.json()
             raise ValidationError("Unsupported format")
         except requests.RequestException as err:
+            logger.exception("Y-Provider service error: url=%s", url)
             raise ServiceUnavailableError(
-                "Failed to connect to conversion service",
+                f"Failed to connect to YDoc conversion service {content_type}, {accept}",
             ) from err