Initialize the Submission data structure

This is the first step towards solving #296. The code added by this
commit is currently *not* put in use in the certification pipeline and
is a partial duplicate of the "checkprcontent" package.

The Submission data structure can collect and run early validation
checks on all information concerning a user's submission (i.e. a GitHub
Pull Request). In its current state, given an api_url (link to a given
PR), it can collect the list of modified files, and extract the
category, organization, chart's name and version, as well as running
basic checks, such as SemVer compatibility of the provided version.

This commit also implements a custom JSON Serializer / Deserializer. The
Submission object can therefore easily be dumped to / read from a file.
Such file can later be an GitHub workflow artifact, populated in a
future "pre-check" job and read in subsequent jobs.

Signed-off-by: Matthias Goerens <[email protected]>

scripts/requirements.txt

@@ -25,6 +25,7 @@ pytest-forked==1.3.0
 pytest-xdist==2.4.0
 PyYAML==6.0.1
 requests==2.26.0
+responses==0.23.1
 retrying==1.3.3
 semantic-version==2.8.5
 semver==2.13.0

scripts/src/checkprcontent/checkpr.py

@@ -113,7 +113,7 @@ def get_file_match_compiled_patterns():
 
     pattern = re.compile(base + r"/.*")
     reportpattern = re.compile(base + r"/report.yaml")
-    tarballpattern = re.compile(base + r"/(.*\.tgz$)")
+    tarballpattern = re.compile(base + r"/(.*\.tgz)")
     return pattern, reportpattern, tarballpattern
 
 

scripts/src/precheck/serializer.py

@@ -0,0 +1,47 @@
+"""Contains the logic to serialize / deserialize a Submission object to / from JSON.
+
+A pair of custom JSONEncoder / JSONDecoder is required due to the fact that the Submission class
+contains nested classes.
+
+"""
+
+import copy
+import json
+
+from precheck import submission
+
+
+class SubmissionEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, submission.Submission):
+            obj_dict = copy.deepcopy(obj.__dict__)
+            obj_dict["chart"] = obj_dict["chart"].__dict__
+            obj_dict["report"] = obj_dict["report"].__dict__
+            obj_dict["source"] = obj_dict["source"].__dict__
+            obj_dict["tarball"] = obj_dict["tarball"].__dict__
+            return obj_dict
+
+        return json.JSONEncoder.default(self, obj)
+
+
+class SubmissionDecoder(json.JSONDecoder):
+    def __init__(self, *args, **kwargs):
+        json.JSONDecoder.__init__(self, object_hook=self.object_hook, *args, **kwargs)
+
+    def object_hook(self, dct):
+        if "chart" in dct:
+            chart_obj = submission.Chart(**dct["chart"])
+            report_obj = submission.Report(**dct["report"])
+            source_obj = submission.Source(**dct["source"])
+            tarball_obj = submission.Tarball(**dct["tarball"])
+
+            to_merge_dct = {
+                "chart": chart_obj,
+                "report": report_obj,
+                "source": source_obj,
+                "tarball": tarball_obj,
+            }
+
+            new_dct = dct | to_merge_dct
+            return submission.Submission(**new_dct)
+        return dct

scripts/src/precheck/serializer_test.py

@@ -0,0 +1,95 @@
+import json
+
+from precheck import serializer
+from precheck import submission
+
+submission_json = """
+{
+    "api_url": "https://api.github.com/repos/openshift-helm-charts/charts/pulls/1",
+    "modified_files": ["charts/partners/acme/awesome/1.42.0/report.yaml"],
+    "chart": {
+        "category": "partners",
+        "organization": "acme",
+        "name": "awesome",
+        "version": "1.42.0"
+    },
+    "report": {
+        "found": true,
+        "signed": false,
+        "path": "charts/partners/acme/awesome/1.42.0/report.yaml"
+    },
+    "source": {
+        "found": false,
+        "path": null
+    },
+    "tarball": {
+        "found": false,
+        "path": null,
+        "provenance": null
+    },
+    "modified_owners": [],
+    "modified_unknown": []
+}
+"""
+
+
+def sanitize_json_string(json_string: str):
+    """Remove the newlines from the JSON string. This is done by
+    loading and dumping the string representation of the JSON object.
+    Goal is to allow comparison with other JSON string.
+    """
+    json_dict = json.loads(json_string)
+    return json.dumps(json_dict)
+
+
+def test_submission_serializer():
+    s = json.loads(submission_json, cls=serializer.SubmissionDecoder)
+
+    assert isinstance(s, submission.Submission)
+    assert (
+        s.api_url == "https://api.github.com/repos/openshift-helm-charts/charts/pulls/1"
+    )
+    assert "charts/partners/acme/awesome/1.42.0/report.yaml" in s.modified_files
+    assert s.chart.category == "partners"
+    assert s.chart.organization == "acme"
+    assert s.chart.name == "awesome"
+    assert s.chart.version == "1.42.0"
+    assert s.report.found
+    assert not s.report.signed
+    assert s.report.path == "charts/partners/acme/awesome/1.42.0/report.yaml"
+    assert not s.source.found
+    assert not s.source.path
+    assert not s.tarball.found
+    assert not s.tarball.path
+    assert not s.tarball.provenance
+
+
+def test_submission_deserializer():
+    s = submission.Submission(
+        api_url="https://api.github.com/repos/openshift-helm-charts/charts/pulls/1",
+        modified_files=["charts/partners/acme/awesome/1.42.0/report.yaml"],
+        chart=submission.Chart(
+            category="partners",
+            organization="acme",
+            name="awesome",
+            version="1.42.0",
+        ),
+        report=submission.Report(
+            found=True,
+            signed=False,
+            path="charts/partners/acme/awesome/1.42.0/report.yaml",
+        ),
+        source=submission.Source(
+            found=False,
+            path=None,
+        ),
+        tarball=submission.Tarball(
+            found=False,
+            path=None,
+            provenance=None,
+        ),
+    )
+
+    assert serializer.SubmissionEncoder().encode(s) == sanitize_json_string(
+        submission_json
+    )