feat: separate contents, abstract and body evidence

backend/wisegrade/knowledge_pages.py

@@ -36,18 +36,33 @@ def page_image_path(db, doc: KnowledgeDocument, page: int) -> Path | None:
     return path if path and path.is_relative_to(root) and path.is_file() else None
 
 
-def page_links(db, document_id: int | None, page: int | None) -> dict[str, str | None]:
+def page_links(db, document_id: int | None, page: int | None) -> dict:
+    """Stable citation links plus the page type, so callers can label the source."""
+    empty = {"url": None, "image_url": None, "page_type": None, "section": None}
     if not document_id or not page:
-        return {"url": None, "image_url": None}
+        return empty
     doc = db.get(KnowledgeDocument, document_id)
     if not doc:
-        return {"url": None, "image_url": None}
+        return empty
     record = db.get(KnowledgePage, (document_id, page))
     if not record:
-        return {"url": None, "image_url": None}
+        return empty
     return {"url": text_url(document_id, page),
-            "image_url": image_url(document_id, page) if page_image_path(db, doc, page) else None}
+            "image_url": image_url(document_id, page) if page_image_path(db, doc, page) else None,
+            "page_type": record.page_type or "unknown",
+            "section": record.section or ""}
 
 
-def evidence_links(db, evidence) -> dict[str, str | None]:
+def evidence_links(db, evidence) -> dict:
     return page_links(db, evidence.document_id, evidence.page)
+
+
+def page_types(db, document_ids) -> dict[int, str]:
+    """Page type per page of the given documents, for labelling citations in bulk."""
+    from sqlalchemy import select as _select
+    ids = [item for item in dict.fromkeys(document_ids or []) if item]
+    if not ids:
+        return {}
+    rows = db.execute(_select(KnowledgePage.document_id, KnowledgePage.page, KnowledgePage.page_type)
+                      .where(KnowledgePage.document_id.in_(ids))).all()
+    return {(document_id, page): (page_type or "unknown") for document_id, page, page_type in rows}