refactor(ocr): extract _validate_zip_entry to utils.py so ZIP Slip test runs in CI

_validate_zip_entry has no ML-stack dependency; importing it via main.py
pulled in surya/torch and caused the test to be skipped in CI. Moving it
to utils.py (fastapi only) and adding fastapi to the CI lightweight install
lets test_zipslip_still_anchors_under_custom_tmpdir run on every push.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ocr-service/main.py

@@ -27,6 +27,7 @@ from engines import kraken as kraken_engine
 from engines import surya as surya_engine
 from models import OcrBlock, OcrRequest
 from preprocessing import preprocess_page
+from utils import _validate_zip_entry
 
 TRAINING_TOKEN = os.environ.get("TRAINING_TOKEN", "")
 KRAKEN_MODEL_PATH = os.environ.get("KRAKEN_MODEL_PATH", "/app/models/german_kurrent.mlmodel")
@@ -291,14 +292,6 @@ def _check_training_token(x_training_token: str | None) -> None:
         raise HTTPException(status_code=403, detail="Invalid or missing X-Training-Token")
 
 
-def _validate_zip_entry(name: str, extract_dir: str) -> None:
-    """Reject ZIP Slip attacks: path traversal and absolute paths."""
-    if os.path.isabs(name) or name.startswith(".."):
-        raise HTTPException(status_code=400, detail=f"Unsafe ZIP entry: {name}")
-    resolved = os.path.realpath(os.path.join(extract_dir, name))
-    if not resolved.startswith(os.path.realpath(extract_dir)):
-        raise HTTPException(status_code=400, detail=f"ZIP Slip detected: {name}")
-
 
 def _rotate_backups(model_path: str, keep: int = 3) -> None:
     """Keep only the last `keep` timestamped backups of the model."""