✨Export pdf / docx front side

.github/workflows/impress.yml

@@ -206,10 +206,11 @@ jobs:
       - name: Install development dependencies
         run: pip install --user .[dev]
 
-      - name: Install gettext (required to compile messages)
+      - name: Install gettext (required to compile messages) and MIME support
         run: |
           sudo apt-get update
-          sudo apt-get install -y gettext pandoc
+          sudo apt-get install -y gettext pandoc shared-mime-info
+          sudo wget https://svn.apache.org/repos/asf/httpd/httpd/trunk/docs/conf/mime.types -O /etc/mime.types
 
       - name: Generate a MO file from strings extracted from the project
         run: python manage.py compilemessages

CHANGELOG.md

@@ -17,6 +17,10 @@ and this project adheres to
 - 💄(frontend) add filtering to left panel #475
 - ✨(frontend) new share modal ui #489
 - ✨(frontend) add favorite feature #515
+- 🏷️(backend) add content-type to uploaded files #552
+- ✨(frontend) export pdf docx front side #537
+- 📝(documentation) Documentation about self-hosted installation #530
+- ✨(helm) helm versioning #530
 
 ## Changed
 

Dockerfile

@@ -72,10 +72,11 @@ RUN apk add \
   gettext \
   gdk-pixbuf \
   libffi-dev \
-  pandoc \
   pango \
   shared-mime-info
 
+RUN wget https://svn.apache.org/repos/asf/httpd/httpd/trunk/docs/conf/mime.types -O /etc/mime.types
+
 # Copy entrypoint
 COPY ./docker/files/usr/local/bin/entrypoint /usr/local/bin/entrypoint
 

src/backend/core/api/viewsets.py

@@ -2,6 +2,7 @@
 # pylint: disable=too-many-lines
 
 import logging
+import mimetypes
 import re
 import uuid
 from urllib.parse import urlparse
@@ -604,8 +605,19 @@ def attachment_upload(self, request, *args, **kwargs):
         extension = serializer.validated_data["expected_extension"]
         key = f"{document.key_base}/{ATTACHMENTS_FOLDER:s}/{file_id!s}.{extension:s}"
 
+        # Determine the content type of the file
+        file = serializer.validated_data["file"]
+        content_type, _ = mimetypes.guess_type(file.name)
+
+        # Fallback if MIME type cannot be determined
+        if not content_type:
+            content_type = "application/octet-stream"
+
         # Prepare metadata for storage
-        extra_args = {"Metadata": {"owner": str(request.user.id)}}
+        extra_args = {
+            "Metadata": {"owner": str(request.user.id)},
+            "ContentType": content_type,
+        }
         if serializer.validated_data["is_unsafe"]:
             extra_args["Metadata"]["is_unsafe"] = "true"
 
@@ -936,40 +948,6 @@ def perform_create(self, serializer):
             role=models.RoleChoices.OWNER,
         )
 
-    @drf.decorators.action(
-        detail=True,
-        methods=["post"],
-        url_path="generate-document",
-        permission_classes=[permissions.AccessPermission],
-    )
-    # pylint: disable=unused-argument
-    def generate_document(self, request, pk=None):
-        """
-        Generate and return a document for this template around the
-        body passed as argument.
-
-        2 types of body are accepted:
-        - HTML: body_type = "html"
-        - Markdown: body_type = "markdown"
-
-        2 types of documents can be generated:
-        - PDF: format = "pdf"
-        - Docx: format = "docx"
-        """
-        serializer = serializers.DocumentGenerationSerializer(data=request.data)
-
-        if not serializer.is_valid():
-            return drf.response.Response(
-                serializer.errors, status=drf.status.HTTP_400_BAD_REQUEST
-            )
-
-        body = serializer.validated_data["body"]
-        body_type = serializer.validated_data["body_type"]
-        export_format = serializer.validated_data["format"]
-
-        template = self.get_object()
-        return template.generate_document(body, body_type, export_format)
-
 
 class TemplateAccessViewSet(
     ResourceAccessViewsetMixin,

src/backend/core/models.py

@@ -4,11 +4,8 @@
 
 import hashlib
 import smtplib
-import tempfile
-import textwrap
 import uuid
 from datetime import timedelta
-from io import BytesIO
 from logging import getLogger
 
 from django.conf import settings
@@ -20,19 +17,12 @@
 from django.core.files.storage import default_storage
 from django.core.mail import send_mail
 from django.db import models
-from django.http import FileResponse
-from django.template.base import Template as DjangoTemplate
-from django.template.context import Context
 from django.template.loader import render_to_string
-from django.utils import html, timezone
+from django.utils import timezone
 from django.utils.functional import cached_property, lazy
 from django.utils.translation import get_language, override
 from django.utils.translation import gettext_lazy as _
 
-import frontmatter
-import markdown
-import pypandoc
-import weasyprint
 from botocore.exceptions import ClientError
 from timezone_field import TimeZoneField
 
@@ -754,107 +744,6 @@ def get_abilities(self, user):
             "retrieve": can_get,
         }
 
-    def generate_pdf(self, body_html, metadata):
-        """
-        Generate and return a pdf document wrapped around the current template
-        """
-        document_html = weasyprint.HTML(
-            string=DjangoTemplate(self.code).render(
-                Context({"body": html.format_html(body_html), **metadata})
-            )
-        )
-        css = weasyprint.CSS(
-            string=self.css,
-            font_config=weasyprint.text.fonts.FontConfiguration(),
-        )
-
-        pdf_content = document_html.write_pdf(stylesheets=[css], zoom=1)
-        response = FileResponse(BytesIO(pdf_content), content_type="application/pdf")
-        response["Content-Disposition"] = f"attachment; filename={self.title}.pdf"
-
-        return response
-
-    def generate_word(self, body_html, metadata):
-        """
-        Generate and return a docx document wrapped around the current template
-        """
-        template_string = DjangoTemplate(self.code).render(
-            Context({"body": html.format_html(body_html), **metadata})
-        )
-
-        html_string = f"""
-        <!DOCTYPE html>
-        <html>
-        <head>
-            <style>
-                {self.css}
-            </style>
-        </head>
-        <body>
-            {template_string}
-        </body>
-        </html>
-        """
-
-        reference_docx = "core/static/reference.docx"
-        output = BytesIO()
-
-        # Convert the HTML to a temporary docx file
-        with tempfile.NamedTemporaryFile(suffix=".docx", prefix="docx_") as tmp_file:
-            output_path = tmp_file.name
-
-            pypandoc.convert_text(
-                html_string,
-                "docx",
-                format="html",
-                outputfile=output_path,
-                extra_args=["--reference-doc", reference_docx],
-            )
-
-            # Create a BytesIO object to store the output of the temporary docx file
-            with open(output_path, "rb") as f:
-                output = BytesIO(f.read())
-
-        # Ensure the pointer is at the beginning
-        output.seek(0)
-
-        response = FileResponse(
-            output,
-            content_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        )
-        response["Content-Disposition"] = f"attachment; filename={self.title}.docx"
-
-        return response
-
-    def generate_document(self, body, body_type, export_format):
-        """
-        Generate and return a document for this template around the
-        body passed as argument.
-
-        2 types of body are accepted:
-        - HTML: body_type = "html"
-        - Markdown: body_type = "markdown"
-
-        2 types of documents can be generated:
-        - PDF: export_format = "pdf"
-        - Docx: export_format = "docx"
-        """
-        document = frontmatter.loads(body)
-        metadata = document.metadata
-        strip_body = document.content.strip()
-
-        if body_type == "html":
-            body_html = strip_body
-        else:
-            body_html = (
-                markdown.markdown(textwrap.dedent(strip_body)) if strip_body else ""
-            )
-
-        if export_format == "pdf":
-            return self.generate_pdf(body_html, metadata)
-
-        return self.generate_word(body_html, metadata)
-
 
 class TemplateAccess(BaseAccess):
     """Relation model to give access to a template for a user or a team with a role."""

src/backend/core/tests/documents/test_api_documents_attachment_upload.py

@@ -64,12 +64,22 @@ def test_api_documents_attachment_upload_anonymous_success():
     assert response.status_code == 201
 
     pattern = re.compile(rf"^/media/{document.id!s}/attachments/(.*)\.png")
-    match = pattern.search(response.json()["file"])
+    file_path = response.json()["file"]
+    match = pattern.search(file_path)
     file_id = match.group(1)
 
     # Validate that file_id is a valid UUID
     uuid.UUID(file_id)
 
+    # Now, check the metadata of the uploaded file
+    key = file_path.replace("/media", "")
+    file_head = default_storage.connection.meta.client.head_object(
+        Bucket=default_storage.bucket_name, Key=key
+    )
+
+    assert file_head["Metadata"] == {"owner": "None"}
+    assert file_head["ContentType"] == "image/png"
+
 
 @pytest.mark.parametrize(
     "reach, role",
@@ -206,6 +216,7 @@ def test_api_documents_attachment_upload_success(via, role, mock_user_teams):
         Bucket=default_storage.bucket_name, Key=key
     )
     assert file_head["Metadata"] == {"owner": str(user.id)}
+    assert file_head["ContentType"] == "image/png"
 
 
 def test_api_documents_attachment_upload_invalid(client):
@@ -247,16 +258,18 @@ def test_api_documents_attachment_upload_size_limit_exceeded(settings):
 
 
 @pytest.mark.parametrize(
-    "name,content,extension",
+    "name,content,extension,content_type",
     [
-        ("test.exe", b"text", "exe"),
-        ("test", b"text", "txt"),
-        ("test.aaaaaa", b"test", "txt"),
-        ("test.txt", PIXEL, "txt"),
-        ("test.py", b"#!/usr/bin/python", "py"),
+        ("test.exe", b"text", "exe", "application/x-msdownload"),
+        ("test", b"text", "txt", "application/octet-stream"),
+        ("test.aaaaaa", b"test", "txt", "application/octet-stream"),
+        ("test.txt", PIXEL, "txt", "text/plain"),
+        ("test.py", b"#!/usr/bin/python", "py", "text/x-python"),
     ],
 )
-def test_api_documents_attachment_upload_fix_extension(name, content, extension):
+def test_api_documents_attachment_upload_fix_extension(
+    name, content, extension, content_type
+):
     """
     A file with no extension or a wrong extension is accepted and the extension
     is corrected in storage.
@@ -287,6 +300,7 @@ def test_api_documents_attachment_upload_fix_extension(name, content, extension)
         Bucket=default_storage.bucket_name, Key=key
     )
     assert file_head["Metadata"] == {"owner": str(user.id), "is_unsafe": "true"}
+    assert file_head["ContentType"] == content_type
 
 
 def test_api_documents_attachment_upload_empty_file():
@@ -335,3 +349,4 @@ def test_api_documents_attachment_upload_unsafe():
         Bucket=default_storage.bucket_name, Key=key
     )
     assert file_head["Metadata"] == {"owner": str(user.id), "is_unsafe": "true"}
+    assert file_head["ContentType"] == "application/x-msdownload"