From 08ffcd56a3b25b6e22e4e66e18c95adc70179b82 Mon Sep 17 00:00:00 2001
From: Yiheng Wang <68361391+yiheng-wang-nv@users.noreply.github.com>
Date: Thu, 25 Jan 2024 13:28:57 +0800
Subject: [PATCH] Fix weekly cpu test error and add hash check [skip-gpu]
 (#549)

Fixes #548 .

### Description
A few sentences describing the changes proposed in this pull request.

### Status
**Ready**

### Please ensure all the checkboxes:
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Codeformat tests passed locally by running `./runtests.sh
--codeformat`.
- [ ] In-line docstrings updated.
- [ ] Update `version` and `changelog` in `metadata.json` if changing an
existing bundle.
- [ ] Please ensure the naming rules in config files meet our
requirements (please refer to: `CONTRIBUTING.md`).
- [ ] Ensure versions of packages such as `monai`, `pytorch` and `numpy`
are correct in `metadata.json`.
- [ ] Descriptions should be consistent with the content, such as
`eval_metrics` of the provided weights and TorchScript modules.
- [ ] Files larger than 25MB are excluded and replaced by providing
download links in `large_file.yml`.
- [ ] Avoid using path that contains personal information within config
files (such as use `/home/your_name/` for `"bundle_root"`).

Signed-off-by: Yiheng Wang <vennw@nvidia.com>
---
 ci/download_latest_bundle.py | 12 ++++++++++--
 ci/get_bundle_list.py        |  5 ++++-
 ci/utils.py                  |  5 +++++
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/ci/download_latest_bundle.py b/ci/download_latest_bundle.py
index ca5c3f7e..14ea3581 100644
--- a/ci/download_latest_bundle.py
+++ b/ci/download_latest_bundle.py
@@ -14,15 +14,23 @@
 import os
 
 from monai.bundle import download
-from utils import get_latest_version
+from utils import get_checksum, get_hash_func, get_latest_version, get_version_checksum
 
 
 def download_latest_bundle(bundle_name: str, models_path: str, download_path: str):
     model_info_path = os.path.join(models_path, "model_info.json")
     version = get_latest_version(bundle_name=bundle_name, model_info_path=model_info_path)
-
+    checksum = get_version_checksum(bundle_name=bundle_name, version=version, model_info_path=model_info_path)
     download(name=bundle_name, source="monaihosting", version=version, bundle_dir=download_path)
 
+    # verify checksum
+    hash_func = get_hash_func(hash_type="sha1")
+    bundle_zip_name = f"{bundle_name}_v{version}.zip"
+    downloaded_checksum = get_checksum(dst_path=os.path.join(download_path, bundle_zip_name), hash_func=hash_func)
+    if checksum != downloaded_checksum:
+        raise ValueError(f"Checksum of {bundle_zip_name} is not correct.")
+    print(f"Checksum of downloaded bundle {bundle_name} is correct.")
+
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="")
diff --git a/ci/get_bundle_list.py b/ci/get_bundle_list.py
index e49481b7..3e6d5393 100644
--- a/ci/get_bundle_list.py
+++ b/ci/get_bundle_list.py
@@ -14,10 +14,13 @@
 
 from utils import get_sub_folders
 
+# new added bundles should temporarily be added to this list, and remove until they can be downloaded successfully
+EXCLUDE_LIST = ["segmentation_template", "classification_template"]
+
 
 def main(models_path):
     bundle_list = get_sub_folders(root_dir=models_path)
-
+    bundle_list = [b for b in bundle_list if b not in EXCLUDE_LIST]
     print(bundle_list)
 
 
diff --git a/ci/utils.py b/ci/utils.py
index 70432a34..dd35171c 100644
--- a/ci/utils.py
+++ b/ci/utils.py
@@ -123,6 +123,11 @@ def get_latest_version(bundle_name: str, model_info_path: str):
     return sorted(versions)[-1]
 
 
+def get_version_checksum(bundle_name: str, version: str, model_info_path: str):
+    model_info_dict = get_json_dict(model_info_path)
+    return model_info_dict[f"{bundle_name}_v{version}"]["checksum"]
+
+
 def submit_pull_request(model_info_path: str):
     # set required info for a pull request
     branch_name = "auto-update-model-info"