ran ruff format via uv

nextcloud_mcp_server/client/unstructured_client.py

@@ -81,7 +81,11 @@ class UnstructuredClient:
 
         # Prepare the multipart form data
         files = {
-            "files": (filename, io.BytesIO(content), content_type or "application/octet-stream")
+            "files": (
+                filename,
+                io.BytesIO(content),
+                content_type or "application/octet-stream",
+            )
         }
 
         # Prepare the request data
@@ -132,7 +136,7 @@ class UnstructuredClient:
                     "element_types": element_types,
                     "strategy": strategy,
                     "languages": languages,
-                    "parsing_method": "unstructured_api"
+                    "parsing_method": "unstructured_api",
                 }
 
                 logger.debug(
@@ -144,7 +148,9 @@ class UnstructuredClient:
 
         except httpx.HTTPError as e:
             logger.error(f"HTTP error calling Unstructured API: {e}")
-            raise Exception(f"Failed to parse document via Unstructured API: {str(e)}") from e
+            raise Exception(
+                f"Failed to parse document via Unstructured API: {str(e)}"
+            ) from e
         except Exception as e:
             logger.error(f"Unexpected error parsing document: {e}")
             raise Exception(f"Failed to parse document: {str(e)}") from e

nextcloud_mcp_server/config.py

@@ -116,7 +116,9 @@ def get_unstructured_languages() -> list[str]:
     languages = [lang.strip() for lang in languages_str.split(",") if lang.strip()]
 
     if not languages:
-        logging.warning("No languages specified in UNSTRUCTURED_LANGUAGES. Using default: eng,deu")
+        logging.warning(
+            "No languages specified in UNSTRUCTURED_LANGUAGES. Using default: eng,deu"
+        )
         return ["eng", "deu"]
 
     return languages

nextcloud_mcp_server/server/webdav.py

@@ -3,7 +3,10 @@ import logging
 from mcp.server.fastmcp import Context, FastMCP
 
 from nextcloud_mcp_server.client import NextcloudClient
-from nextcloud_mcp_server.utils.document_parser import is_parseable_document, parse_document
+from nextcloud_mcp_server.utils.document_parser import (
+    is_parseable_document,
+    parse_document,
+)
 from nextcloud_mcp_server.config import is_unstructured_parsing_enabled
 
 logger = logging.getLogger(__name__)
@@ -62,7 +65,7 @@ def configure_webdav_tools(mcp: FastMCP):
         content, content_type = await client.webdav.read_file(path)
 
         # Check if this is a parseable document (PDF, DOCX, etc.)
-        if (is_unstructured_parsing_enabled() and is_parseable_document(content_type)):
+        if is_unstructured_parsing_enabled() and is_parseable_document(content_type):
             try:
                 logger.info(f"Parsing document '{path}' of type '{content_type}'")
                 parsed_text, metadata = await parse_document(

nextcloud_mcp_server/utils/document_parser.py

@@ -35,6 +35,7 @@ PARSEABLE_MIME_TYPES = {
     "image/bmp": "image",
 }
 
+
 def is_parseable_document(content_type: Optional[str]) -> bool:
     """Check if a document type can be parsed.
 
@@ -51,10 +52,9 @@ def is_parseable_document(content_type: Optional[str]) -> bool:
     base_content_type = content_type.split(";")[0].strip().lower()
     return base_content_type in PARSEABLE_MIME_TYPES
 
+
 async def parse_document(
-    content: bytes,
+    content: bytes, content_type: Optional[str], filename: Optional[str] = None
-    content_type: Optional[str],
-    filename: Optional[str] = None
 ) -> Tuple[str, dict]:
     """Parse a document using the Unstructured API.
 
@@ -75,7 +75,9 @@ async def parse_document(
     if not is_parseable_document(content_type):
         raise ValueError(f"Document type '{content_type}' is not supported for parsing")
 
-    base_content_type = content_type.split(";")[0].strip().lower() if content_type else ""
+    base_content_type = (
+        content_type.split(";")[0].strip().lower() if content_type else ""
+    )
     doc_type = PARSEABLE_MIME_TYPES.get(base_content_type, "unknown")
 
     logger.debug(f"Parsing document of type '{doc_type}' (MIME: {content_type})")
@@ -84,7 +86,10 @@ async def parse_document(
     if is_unstructured_parsing_enabled():
         logger.debug("Using Unstructured API for parsing")
         try:
-            from nextcloud_mcp_server.client.unstructured_client import UnstructuredClient
+            from nextcloud_mcp_server.client.unstructured_client import (
+                UnstructuredClient,
+            )
+
             client = UnstructuredClient()
             # The client will automatically use environment configuration
             # (UNSTRUCTURED_STRATEGY and UNSTRUCTURED_LANGUAGES)
@@ -97,6 +102,7 @@ async def parse_document(
             logger.error(f"Unstructured API parsing failed: {e}")
             # If unstructured parsing fails, return base64 as fallback
             import base64
+
             parsed_text = f"Document could not be parsed. Base64 content: {base64.b64encode(content).decode('ascii')[:200]}..."
             metadata = {
                 "document_type": doc_type,
@@ -104,18 +110,21 @@ async def parse_document(
                 "element_count": 0,
                 "text_length": len(parsed_text),
                 "parsing_method": "fallback_base64",
-                "error": str(e)
+                "error": str(e),
             }
             return parsed_text, metadata
     else:
-        logger.debug("Unstructured parsing is disabled, returning base64 encoded content as fallback")
+        logger.debug(
+            "Unstructured parsing is disabled, returning base64 encoded content as fallback"
+        )
         import base64
+
         parsed_text = f"Document could not be parsed. Base64 content: {base64.b64encode(content).decode('ascii')[:200]}..."
         metadata = {
             "document_type": doc_type,
             "mime_type": content_type,
             "element_count": 0,
             "text_length": len(parsed_text),
-            "parsing_method": "fallback_base64"
+            "parsing_method": "fallback_base64",
         }
         return parsed_text, metadata