scheme-sdk 0.3.6__tar.gz → 0.3.8__tar.gz

{scheme_sdk-0.3.6 → scheme_sdk-0.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scheme_sdk
-Version: 0.3.6
+Version: 0.3.8
 Summary: The Scheme SDK provides connectors for ingesting conversations, messages, and files across communication platforms.
 License:                                  Apache License
                                     Version 2.0, January 2004
@@ -203,6 +203,7 @@ License:                                  Apache License
             WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
             See the License for the specific language governing permissions and
             limitations under the License.
+Requires-Dist: html-sanitizer>=2.6.0
 Requires-Dist: requests>=2.32.5
 Requires-Python: >=3.11
 Project-URL: Homepage, https://www.schemebig.com/

{scheme_sdk-0.3.6 → scheme_sdk-0.3.8}/pyproject.toml

@@ -4,12 +4,13 @@ build-backend = "uv_build"
 
 [project]
 name = "scheme_sdk"
-version = "0.3.6"
+version = "0.3.8"
 description = "The Scheme SDK provides connectors for ingesting conversations, messages, and files across communication platforms."
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.11"
 dependencies = [
+    "html-sanitizer>=2.6.0",
     "requests>=2.32.5",
 ]
 

{scheme_sdk-0.3.6 → scheme_sdk-0.3.8}/src/scheme_sdk/connectors/base/__init__.py

@@ -13,12 +13,17 @@ from .errors import (
     ConnectorRateLimitError,
 )
 from .message import MessageConnector
+from .storage import FileContent, FileMetadata, FolderMetadata, StorageConnector
 
 __all__ = [
     # Base classes
     "BaseConnector",
     "MessageConnector",
+    "StorageConnector",
     "ConnectorContext",
+    "FileMetadata",
+    "FolderMetadata",
+    "FileContent",
     # Exceptions
     "ConnectorError",
     "ConnectorAuthError",

{scheme_sdk-0.3.6 → scheme_sdk-0.3.8}/src/scheme_sdk/connectors/base/message.py

@@ -2,6 +2,7 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from dataclasses import dataclass, field
 from typing import Any, Dict, Iterable, Optional
+from html_sanitizer import Sanitizer
 
 from .base import BaseConnector
 
@@ -11,6 +12,38 @@ class MessageConnector(BaseConnector, ABC):
     Abstract base class for all message connectors.
     """
 
+    _sanitizer_settings = {
+        "tags": {
+            "a",
+            "strong",
+            "em",
+            "p",
+            "ul",
+            "ol",
+            "li",
+            "br",
+            "blockquote",
+            "code",
+            "pre",
+            "span",
+            "sub",
+            "sup",
+            "hr",
+        },
+        "attributes": {"a": {"href", "title", "rel", "target"}},
+        "empty": {"hr", "a", "br"},
+        "separate": {"a", "p", "li", "blockquote", "pre"},
+        "whitespace": {"br"},
+        "add_nofollow": False,
+        "autolink": False,
+        "keep_typographic_whitespace": False,
+    }
+
+    _sanitizer: Sanitizer
+
+    def __init__(self):
+        self._sanitizer = Sanitizer(settings=self._sanitizer_settings)
+
     @abstractmethod
     def fetch_conversations(self) -> Iterable[Dict[str, Any]]:
         """
@@ -85,6 +118,7 @@ class MessageConnector(BaseConnector, ABC):
         """
         ...
 
+    @abstractmethod
     def normalize_message(self, raw_message: Dict[str, Any]) -> Dict[str, Any]:
         """
         Transform a platform-specific message into canonical format.
@@ -100,6 +134,7 @@ class MessageConnector(BaseConnector, ABC):
         """
         ...
 
+    @abstractmethod
     def normalize_conversation(
         self, raw_conversation: Dict[str, Any]
     ) -> Dict[str, Any]:
@@ -134,6 +169,18 @@ class MessageConnector(BaseConnector, ABC):
         self._logger.warning(f"search_messages not implemented for {self.platform}")
         return iter([])
 
+    def _sanitize_html(self, html: str) -> str:
+        """
+        Sanitize HTML content.
+
+        Args:
+            html: HTML content to sanitize
+
+        Returns:
+            Sanitized HTML content
+        """
+        return self._sanitizer.sanitize(html)
+
 
 @dataclass
 class Conversation:

scheme_sdk-0.3.8/src/scheme_sdk/connectors/base/storage.py

@@ -0,0 +1,159 @@
+"""
+SeedVault Connector SDK - Storage Connector Interfaces
+
+This module defines the base interface for storage connectors (e.g. Drive,
+OneDrive, Dropbox). Storage connectors provide file and folder metadata,
+search capabilities, and content export.
+"""
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Any, Dict, Iterable, Optional
+
+from .base import BaseConnector
+
+
+class StorageConnector(BaseConnector, ABC):
+    """
+    Abstract base class for all storage connectors.
+    """
+
+    @abstractmethod
+    def list_root_items(self) -> Iterable[Dict[str, Any]]:
+        """
+        List items at the storage root.
+
+        Yields:
+            Dict: Raw file or folder objects from the platform API.
+        """
+        ...
+
+    @abstractmethod
+    def list_children(self, folder_id: str) -> Iterable[Dict[str, Any]]:
+        """
+        List child items within a folder.
+
+        Args:
+            folder_id: Unique identifier of the parent folder.
+
+        Yields:
+            Dict: Raw file or folder objects from the platform API.
+        """
+        ...
+
+    @abstractmethod
+    def get_item(self, item_id: str) -> Dict[str, Any]:
+        """
+        Fetch a single file or folder by ID.
+
+        Args:
+            item_id: Unique identifier of the item.
+
+        Returns:
+            Dict: Raw file or folder object from the platform API.
+        """
+        ...
+
+    @abstractmethod
+    def search_items(
+        self, query: str, folder_id: Optional[str] = None, limit: int = 100
+    ) -> Iterable[Dict[str, Any]]:
+        """
+        Search for files or folders by query string.
+
+        Args:
+            query: Search query (platform-specific syntax).
+            folder_id: Optional folder scope for the search.
+            limit: Maximum number of results.
+
+        Yields:
+            Dict: Raw file or folder objects from the platform API.
+        """
+        ...
+
+    @abstractmethod
+    def fetch_content(self, file_id: str) -> Dict[str, Any]:
+        """
+        Fetch file content by file ID.
+
+        Args:
+            file_id: Unique identifier of the file.
+
+        Returns:
+            Dict: Raw content payload from the platform API.
+            Expected keys may include:
+            - content_bytes: bytes
+            - content_text: str
+            - mime_type: str
+            - size: int
+            - checksum: str
+            - encoding: str
+        """
+        ...
+
+    @abstractmethod
+    def normalize_file(self, raw_file: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        Transform a platform-specific file into canonical format.
+
+        Args:
+            raw_file: Raw file object from the platform API.
+
+        Returns:
+            Normalized file dictionary in canonical format.
+        """
+        ...
+
+    @abstractmethod
+    def normalize_folder(self, raw_folder: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        Transform a platform-specific folder into canonical format.
+
+        Args:
+            raw_folder: Raw folder object from the platform API.
+
+        Returns:
+            Normalized folder dictionary in canonical format.
+        """
+        ...
+
+
+@dataclass
+class FileMetadata:
+    id: str
+    name: str
+    path: Optional[str] = None
+    mime_type: Optional[str] = None
+    size: Optional[int] = None
+    modified_at: Optional[datetime] = None
+    created_at: Optional[datetime] = None
+    checksum: Optional[str] = None
+    direct_link: Optional[str] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class FolderMetadata:
+    id: str
+    name: str
+    path: Optional[str] = None
+    parent_id: Optional[str] = None
+    created_at: Optional[datetime] = None
+    modified_at: Optional[datetime] = None
+    item_count: Optional[int] = None
+    direct_link: Optional[str] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class FileContent:
+    file_id: str
+    name: Optional[str] = None
+    mime_type: Optional[str] = None
+    size: Optional[int] = None
+    content_bytes: Optional[bytes] = None
+    content_text: Optional[str] = None
+    checksum: Optional[str] = None
+    encoding: Optional[str] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)

{scheme_sdk-0.3.6 → scheme_sdk-0.3.8}/src/scheme_sdk/connectors/outlook.py

@@ -4,6 +4,12 @@ from typing import Any, Dict, List, Optional
 
 import requests
 
+from pprint import pprint as pp
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
 from .base import MessageConnector
 
 
@@ -14,6 +20,7 @@ class OutlookConnector(MessageConnector):
     _backoff_cap_seconds = 30
 
     def __init__(self, token: str):
+        super().__init__()
         self.token = token
         self.base = "https://graph.microsoft.com/v1.0"
 
@@ -118,7 +125,7 @@ class OutlookConnector(MessageConnector):
         return {
             "title": message["subject"],
             "platform": self.platform,
-            "text": message["body"]["content"],
+            "text": self._sanitize_html(message["body"]["content"]),
             "direct_link": message["webLink"],
             "metadata": {
                 "platform_conversation_id": message["conversationId"],
@@ -212,3 +219,11 @@ class OutlookConnector(MessageConnector):
             next_params = None  # nextLink already includes the query string
 
         return items
+
+
+if __name__ == "__main__":
+    connector = OutlookConnector(os.getenv("OUTLOOK_TOKEN"))
+    conversations = connector.fetch_conversations(top=1)
+    pp(conversations)
+    messages = connector.fetch_messages(conversations[0]["id"])
+    pp(messages)