From 3e3f84a00e6b427500eb2d87ca781ea75553ecba Mon Sep 17 00:00:00 2001
From: ZdenekSrotyr <zdenek.srotyr@keboola.com>
Date: Wed, 8 Apr 2026 07:04:40 +0200
Subject: [PATCH] feat: dynamic login providers + profiler auto-trigger +
 refresh endpoint

---
 app/api/catalog.py | 24 ++++++++++++++++++++++++
 app/api/sync.py    | 30 ++++++++++++++++++++++++++++++
 app/web/router.py  | 17 ++++++++++++++---
 3 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/app/api/catalog.py b/app/api/catalog.py
index 5f4e482..0d8d582 100644
--- a/app/api/catalog.py
+++ b/app/api/catalog.py
@@ -96,3 +96,27 @@ async def get_metric(
         return content
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Error parsing metric: {e}")
+
+
+@router.post("/profile/{table_name}/refresh")
+async def refresh_profile(
+    table_name: str,
+    user: dict = Depends(get_current_user),
+    conn: duckdb.DuckDBPyConnection = Depends(_get_db),
+):
+    """Re-generate profile for a table on demand."""
+    from src.profiler import profile_table, TableInfo
+
+    data_dir = _get_data_dir()
+    extracts_dir = data_dir / "extracts"
+    candidates = list(extracts_dir.rglob(f"data/{table_name}.parquet"))
+    if not candidates:
+        raise HTTPException(status_code=404, detail=f"No parquet for '{table_name}'")
+
+    try:
+        table_info = TableInfo(name=table_name, table_id=table_name)
+        profile = profile_table(table_info, candidates[0], [], {}, {})
+        ProfileRepository(conn).save(table_name, profile)
+        return {"status": "ok", "table": table_name, "columns": len(profile.get("columns", {}))}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Profile failed: {e}")
diff --git a/app/api/sync.py b/app/api/sync.py
index 7c55981..4fb26a8 100644
--- a/app/api/sync.py
+++ b/app/api/sync.py
@@ -122,6 +122,36 @@ print(json.dumps(result))
         views = orch.rebuild()
         print(f"[SYNC] Orchestrator rebuild: {{{', '.join(f'{k}: {len(v)}' for k, v in views.items())}}}", file=_sys.stderr, flush=True)
 
+        # Auto-profile synced tables (best-effort, don't fail sync on profile error)
+        try:
+            from src.profiler import profile_table, TableInfo
+            from src.repositories.profiles import ProfileRepository
+
+            data_dir = Path(os.environ.get("DATA_DIR", "./data"))
+            extracts_dir = data_dir / "extracts"
+
+            sys_conn = get_system_db()
+            try:
+                profile_repo = ProfileRepository(sys_conn)
+                profiled = 0
+                for source_name, table_names in views.items():
+                    for table_name in table_names[:10]:  # Limit per sync
+                        pq_path = extracts_dir / source_name / "data" / f"{table_name}.parquet"
+                        if not pq_path.exists():
+                            continue
+                        try:
+                            table_info = TableInfo(name=table_name, table_id=table_name)
+                            profile = profile_table(table_info, pq_path, [], {}, {})
+                            profile_repo.save(table_name, profile)
+                            profiled += 1
+                        except Exception as pe:
+                            print(f"[SYNC] Profile {table_name}: {pe}", file=_sys.stderr, flush=True)
+                print(f"[SYNC] Profiled {profiled} tables", file=_sys.stderr, flush=True)
+            finally:
+                sys_conn.close()
+        except Exception as e:
+            print(f"[SYNC] Profiler skipped: {e}", file=_sys.stderr, flush=True)
+
     except subprocess.TimeoutExpired:
         print("[SYNC] Extractor timed out after 1800s", file=_sys.stderr, flush=True)
     except Exception as e:
diff --git a/app/web/router.py b/app/web/router.py
index c1d62cc..a51f19f 100644
--- a/app/web/router.py
+++ b/app/web/router.py
@@ -151,9 +151,20 @@ async def index(request: Request, user: Optional[dict] = Depends(get_optional_us
 
 @router.get("/login", response_class=HTMLResponse)
 async def login_page(request: Request):
-    providers = [
-        {"name": "google", "display_name": "Google", "icon": "google"},
-    ]
+    providers = []
+    try:
+        from app.auth.providers.google import is_available as google_available
+        if google_available():
+            providers.append({"name": "google", "display_name": "Google", "icon": "google"})
+    except Exception:
+        pass
+    providers.append({"name": "password", "display_name": "Email & Password", "icon": "key"})
+    try:
+        from app.auth.providers.email import is_available as email_available
+        if email_available():
+            providers.append({"name": "email", "display_name": "Email Link", "icon": "mail"})
+    except Exception:
+        pass
     ctx = _build_context(request, providers=providers)
     return templates.TemplateResponse(request, "login.html", ctx)