decomposer: generate deliverable files for Define the normalized ingestion contract and pluggable source-connector interface for SCM, CMS, and other content sources.; Implement a GitHub SCM connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of Markdown, plain-text, and source files with webhook and revision metadata.; Implement a SharePoint CMS connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of PDF, DOCX, and HTML files with webhook and revision metadata.; Implement ingestion orchestration and triggers; Normalize, govern, and publish ingested content to the shared knowledge store.; Add deployment/configuration, tests, and documentation for the ingestion agent.; Validate end-to-end ingestion and downstream content availability.

kab_ingestion/sharepoint.py

@@ -0,0 +1,36 @@
+from __future__ import annotations
+import hashlib
+from datetime import datetime, timezone
+from .models import ACL, Change, IngestionBatch, NormalizedDocument, Provenance, SyncCursor
+
+class SharePointConnector:
+    name = "sharepoint"
+    def __init__(self, graph, secret_provider, config):
+        self.graph, self.secrets, self.config = graph, secret_provider, config
+        self.scope = ":".join(config[x] for x in ('site_id','drive_id')) + ':' + config.get('folder_path','')
+
+    def _headers(self): return {"Authorization": f"Bearer {self.secrets.get(self.config['credential_ref'])}"}
+    def _doc(self, tenant_id, item, event_id=None):
+        body = item.get('text', '')
+        now = datetime.now(timezone.utc)
+        return NormalizedDocument(document_id=f"sharepoint:{item['id']}", tenant_id=tenant_id, title=item['name'], body=body,
+          mime_type=item['mime_type'], source_path=item['web_url'], content_hash=hashlib.sha256(body.encode()).hexdigest(),
+          updated_at=item['last_modified'], acl=ACL(**item.get('acl', {})), provenance=Provenance(connector=self.name,
+          source_uri=item['web_url'], source_id=item['id'], revision_id=item.get('e_tag'), revision_time=item['last_modified'],
+          retrieved_at=now, webhook_event_id=event_id))
+
+    def full(self, tenant_id):
+        items = self.graph.list_files(self.config, self._headers())
+        allowed = set(self.config.get('mime_types', ['application/pdf','application/vnd.openxmlformats-officedocument.wordprocessingml.document','text/html']))
+        docs = [self._doc(tenant_id, x) for x in items if x['mime_type'] in allowed]
+        return IngestionBatch(run_id=hashlib.sha256(self.scope.encode()).hexdigest()[:16], tenant_id=tenant_id, documents=docs,
+          next_cursor=SyncCursor(connector=self.name, scope_fingerprint=self.scope, value=items[-1].get('delta_token') if items else None, version=1, updated_at=datetime.now(timezone.utc)))
+
+    def incremental(self, tenant_id, cursor):
+        items, token = self.graph.delta(self.config, cursor.value if cursor else None, self._headers())
+        docs = [self._doc(tenant_id, x) for x in items if not x.get('deleted')]
+        return IngestionBatch(run_id=hashlib.sha256(self.scope.encode()).hexdigest()[:16], tenant_id=tenant_id, documents=docs,
+          next_cursor=SyncCursor(connector=self.name, scope_fingerprint=self.scope, value=token, version=(cursor.version+1 if cursor else 1), updated_at=datetime.now(timezone.utc)))
+
+    def changes_from_webhook(self, payload):
+        return [Change(path=r['resource'], source_id=r['resource'], revision_id=r.get('resourceData', {}).get('id')) for r in payload.get('value', [])]