only update sha on changes (#850)

* only update sha on changes

* handle git hash of functions

* comment git_hash function

* pre-commit

* ignore another warning

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Author: scottgigante-immunai

.github/workflows/update_website_content.yml

@@ -23,7 +23,7 @@ jobs:
     steps:
     - uses: actions/checkout@v3
       with:
-        fetch-depth: 1
+        fetch-depth: 0
         path: openproblems
 
     - name: Checkout website repo

openproblems/api/hash.py

@@ -32,12 +32,20 @@ def get_module(fun):
     return fun.__module__
 
 
-def git_hash(file):
-    """Get the git commit hash associated with a file."""
-    return _run(
-        ["git", "log", "-n", "1", "--pretty=format:%H", "--", file],
-        cwd=os.path.dirname(__file__),
-    )
+def git_hash(obj):
+    """Get the git commit hash associated with the latest change to a file."""
+    if isinstance(obj, str) and os.path.isfile(obj):
+        # if it's a file, run git log to get the hash
+        return _run(
+            ["git", "log", "-n", "1", "--pretty=format:%H", "--", obj],
+            cwd=os.path.dirname(__file__),
+        )
+    elif hasattr(obj, "__file__"):
+        # if it's a module, get the associated file
+        return git_hash(obj.__file__)
+    elif callable(obj):
+        # if it's a function, get the associated module
+        return git_hash(importlib.import_module(get_module(obj)))
 
 
 def docker_token(image_name):

pytest.ini

@@ -13,4 +13,5 @@ filterwarnings =
     ignore:`Model\.state_updates` will be removed in a future version\.:UserWarning
     ignore:Tensorflow not installed. ParametricUMAP will be unavailable:ImportWarning
     ignore:Deprecated call to `pkg_resources\.declare_namespace:DeprecationWarning
+    ignore:pkg_resources is deprecated as an API:DeprecationWarning
     always:Container failed with AssertionError\. Retrying [0-9]* more time:RuntimeWarning

test/test_core_cli.py

@@ -1,7 +1,9 @@
 from openproblems.api.hash import docker_labels_from_api
+from openproblems.api.hash import git_hash
 from openproblems.api.main import main
 from openproblems.api.utils import print_output
 
+import importlib
 import numpy as np
 import openproblems
 import os
@@ -159,6 +161,20 @@ def test_hash_docker_api():
     assert labels["bio.openproblems.build"] in ["github_actions", "local"]
 
 
+@parameterized.parameterized.expand(
+    [
+        (openproblems.tasks.label_projection.datasets.zebrafish_labs,),
+        (openproblems.tasks.label_projection.methods.knn_classifier_log_cp10k,),
+    ],
+    name_func=utils.name.name_test,
+)
+def test_git_hash(func):
+    h1 = git_hash(func)
+    module = importlib.import_module(func.__wrapped__.__module__)
+    assert git_hash(module) == h1
+    assert git_hash(module.__file__) == h1
+
+
 @parameterized.parameterized.expand(
     [
         (dataset, method, metric)

workflow/parse_metadata.py

@@ -1,5 +1,6 @@
 import json
 import openproblems
+import openproblems.api.hash
 import pathlib
 import re
 import sys
@@ -27,7 +28,7 @@ def get_task_description(task):
 def write_task_json(task, outdir: pathlib.Path):
     data = {
         "task_id": openproblems.utils.get_member_id(task),
-        "commit_sha": workflow_utils.get_sha(),
+        "commit_sha": openproblems.api.hash.git_hash(task),
         "task_name": task._task_name,
         "task_summary": task._task_summary,
         "task_description": get_task_description(task),
@@ -43,7 +44,7 @@ def _write_function_json(task, outdir: pathlib.Path, functions, function_type: s
         function.metadata.update(
             {
                 "task_id": openproblems.utils.get_member_id(task),
-                "commit_sha": workflow_utils.get_sha(),
+                "commit_sha": openproblems.api.hash.git_hash(function),
                 f"{function_type}_id": openproblems.utils.get_member_id(function),
                 "implementation_url": (
                     "https://github.com/openproblems-bio/openproblems/"