add unit tests to check-sum

.github/workflows/ci.yml

@@ -1,4 +1,4 @@
-name: Test Gh publish
+name: Test actions scripts
 on:
   workflow_dispatch:
   pull_request:
@@ -9,13 +9,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.9'
+          python-version: '3.11'
       - name: "Run tests"
         run: |
-            python3 -m pip install uv
+            python3 -m pip install uv pytest rich
             uv run pytest

.github/workflows/test-actions.yml

@@ -23,7 +23,7 @@ jobs:
     environment: test
     steps:
      - name: Checkout Code
-       uses: actions/checkout@v3
+       uses: actions/checkout@v4
 
      - name: Setup Python
        uses: actions/setup-python@v4

checksum/action.yml

@@ -1,18 +1,18 @@
-name: 'Checksum Validator'
-description: 'Validate checksum of packages'
+name: "Checksum Validator"
+description: "Validate checksum of packages"
 inputs:
   checksum-config:
-    description: 'Json config for checksum'
+    description: "Json config for checksum"
     required: true
   temp-dir:
-    description: 'Checkout directory of svn repo'
+    description: "Checkout directory of svn repo"
     required: false
-    default: 'temp-svn-repo'
+    default: "temp-svn-repo"
   repo-path:
-    description: 'Path to the svn repo ex: airflow/providers/'
+    description: "Path to the svn repo ex: airflow/providers/"
     required: true
   repo-url:
-    description: 'URL of the svn repo ex: https://dist.apache.org/repos/dist/release/airflow/'
+    description: "URL of the svn repo ex: https://dist.apache.org/repos/dist/release/airflow/"
     required: true
 
 
@@ -22,7 +22,7 @@ runs:
     - name: Setup Python
       uses: actions/setup-python@v4
       with:
-        python-version: '3.9'
+        python-version: "3.11"
 
     - name: "Check sum validation"
       shell: bash

checksum/checksum_check.py

@@ -7,6 +7,8 @@
 import hashlib
 import json
 import os
+from typing import Any
+
 from rich.console import Console
 
 console = Console(width=400, color_system="standard")
@@ -39,7 +41,7 @@ def validate_checksum(check_sum_files: list[dict[str, str]], algorithm: str):
             )
 
 
-def get_valid_files(algorithm, files) -> list[dict[str, str]]:
+def get_valid_files(algorithm: str, files: list[str]) -> list[dict[str, str]]:
     eligible_files = []
     for file in files:
         if file.endswith(algorithm):
@@ -53,10 +55,12 @@ def get_valid_files(algorithm, files) -> list[dict[str, str]]:
 
 
 if __name__ == "__main__":
-    check_sum_config = json.loads(os.environ.get("CHECK_SUM_CONFIG"))
+    check_sum_config: list[dict[str, Any]] = json.loads(
+        os.environ.get("CHECK_SUM_CONFIG")
+    )
 
     for check in check_sum_config:
-        console.print(f"[blue]Checking {check.get('description')} checksum[/]")
+        console.print(f"[blue]{check.get('description')}[/]")
         valid_files = get_valid_files(check.get("algorithm"), svn_files)
         validate_checksum(valid_files, check.get("algorithm"))
 
@@ -68,4 +72,4 @@ def get_valid_files(algorithm, files) -> list[dict[str, str]]:
             console.print(f"[red]Actual SHA: {invalid.get('actual_sha')}[/]")
         exit(1)
 
-    console.print("[blue]Checksum validation passed[/]")
+    console.print("[blue]Checksum validation passed[/]")

checksum/test_checksum_check.py

@@ -1,17 +1,121 @@
-from unittest.mock import patch, mock_open
-from checksum.checksum_check import get_valid_files, validate_checksum, invalid_checksums
+import os
+from unittest.mock import patch
+from checksum.checksum_check import (
+    get_valid_files,
+    validate_checksum,
+    invalid_checksums,
+)
+import tempfile
+import tarfile
 
-class TestChecksumCheck:
 
-    def test_get_valid_files(self):
-        files = [
-            'apache-airflow-2.10.3-source.tar.gz.sha512',
-            'apache_airflow-2.10.3-py3-none-any.whl.asc',
-            'apache_airflow-2.10.3-py3-none-any.whl.sha512',
-            'apache_airflow-2.10.3.tar.gz'
-        ]
-        valida_files = get_valid_files('sha512', files)
-        assert valida_files == [{'sha_file': 'apache-airflow-2.10.3-source.tar.gz.sha512', 'check_file': 'apache-airflow-2.10.3-source.tar.gz'}, {'sha_file': 'apache_airflow-2.10.3-py3-none-any.whl.sha512', 'check_file': 'apache_airflow-2.10.3-py3-none-any.whl'}]
 
 
+def test_get_valid_files_sha512():
+    files = [
+        "apache-airflow-2.10.3-source.tar.gz.sha512",
+        "apache_airflow-2.10.3-py3-none-any.whl.asc",
+        "apache_airflow-2.10.3-py3-none-any.whl.sha512",
+        "apache_airflow-2.10.3.tar.gz",
+    ]
+    valida_files = get_valid_files("sha512", files)
+    assert valida_files == [
+        {
+            "sha_file": "apache-airflow-2.10.3-source.tar.gz.sha512",
+            "check_file": "apache-airflow-2.10.3-source.tar.gz",
+        },
+        {
+            "sha_file": "apache_airflow-2.10.3-py3-none-any.whl.sha512",
+            "check_file": "apache_airflow-2.10.3-py3-none-any.whl",
+        },
+    ]
 
+def test_get_valid_files_with_sha256():
+    files = [
+        "apache-airflow-2.10.3-source.tar.gz.sha256",
+        "apache_airflow-2.10.3-py3-none-any.whl.asc",
+        "apache_airflow-2.10.3-py3-none-any.whl.sha256",
+        "apache_airflow-2.10.3.tar.gz",
+    ]
+    valida_files = get_valid_files("sha256", files)
+    assert valida_files == [
+        {
+            "sha_file": "apache-airflow-2.10.3-source.tar.gz.sha256",
+            "check_file": "apache-airflow-2.10.3-source.tar.gz",
+        },
+        {
+            "sha_file": "apache_airflow-2.10.3-py3-none-any.whl.sha256",
+            "check_file": "apache_airflow-2.10.3-py3-none-any.whl",
+        },
+    ]
+
+@patch("hashlib.file_digest")
+def test_validate_checksum(mock_file_digest):
+    mock_file_digest.return_value.hexdigest.return_value = "bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd"
+
+    invalid_checksums.clear()
+    temp_dir = tempfile.TemporaryDirectory()
+    temp_file = tempfile.NamedTemporaryFile()
+    os.chdir(temp_dir.name)
+
+    with open(temp_file.name, "wb") as temp_data:
+        temp_data.write(b"some random data")
+
+    with open(
+        temp_dir.name + "/apache-airflow-2.10.3-source.tar.gz.sha512", "wb"
+    ) as temp_file:
+        temp_file.write(
+            b"bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd apache-airflow-2.10.3-source.tar.gz"
+        )
+    tar = tarfile.open(
+        temp_dir.name + "/apache-airflow-2.10.3-source.tar.gz", "w:gz"
+    )
+    tar.add(temp_file.name)
+    tar.close()
+
+    check_sum_files = [
+        {
+            "sha_file": "apache-airflow-2.10.3-source.tar.gz.sha512",
+            "check_file": "apache-airflow-2.10.3-source.tar.gz",
+        }
+    ]
+    validate_checksum(check_sum_files, "sha512")
+    assert invalid_checksums == []
+
+@patch("hashlib.file_digest")
+def test_validate_checksum_invalid(mock_file_digest):
+    mock_file_digest.return_value.hexdigest.return_value = "bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd12"
+    invalid_checksums.clear()
+    temp_dir = tempfile.TemporaryDirectory()
+    temp_file = tempfile.NamedTemporaryFile()
+    os.chdir(temp_dir.name)
+
+    with open(temp_file.name, "wb") as temp_data:
+        temp_data.write(b"some random data")
+
+    with open(
+        temp_dir.name + "/apache-airflow-2.10.3-source.tar.gz.sha512", "wb"
+    ) as temp_file:
+        temp_file.write(
+            b"bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd apache-airflow-2.10.3-source.tar.gz"
+        )
+    tar = tarfile.open(
+        temp_dir.name + "/apache-airflow-2.10.3-source.tar.gz", "w:gz"
+    )
+    tar.add(temp_file.name)
+    tar.close()
+
+    check_sum_files = [
+        {
+            "sha_file": "apache-airflow-2.10.3-source.tar.gz.sha512",
+            "check_file": "apache-airflow-2.10.3-source.tar.gz",
+        }
+    ]
+    validate_checksum(check_sum_files, "sha512")
+    assert invalid_checksums == [
+        {
+            "file": "apache-airflow-2.10.3-source.tar.gz.sha512",
+            "expected_sha": "bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd",
+            "actual_sha": "bbc759357eb1980e7f80ba0b016e9ed02120e26fcd008129b5777baf8086208c45e170e3c98cf35bd96a246d59484bde3220a897e5e6a7f688a69a40bcd451bd12",
+        }
+    ]

publish-config.yml

@@ -3,7 +3,7 @@ project:
   description: 'Example project for publishing to PyPI'
 publisher:
   name: providers
-  url: 'https://dist.apache.org/repos/dist/release/airflow/'
+  url: 'https://dist.apache.org/repos/dist/dev/airflow'
   path: airflow/providers/
 checks:
   svn:

signature/signature_check.py

@@ -6,6 +6,8 @@
 #     "python-gnupg",
 # ]
 # ///
+from typing import Any
+
 import gnupg
 import requests
 from rich.console import Console
@@ -21,7 +23,7 @@
 invalid_signature_files = []
 
 
-def download_keys(key_url):
+def download_keys(key_url: str):
     response = requests.get(key_url)
     if response.status_code != 200:
         console.print(
@@ -33,8 +35,9 @@ def download_keys(key_url):
         key_file.write(response.text)
 
 
-def validate_signature_with_gpg(signature_check):
+def validate_signature_with_gpg(signature_check: dict[str, Any]):
     key_url = signature_check.get("keys")
+
     download_keys(key_url)
     gpg = gnupg.GPG()
     with open(temp_signature_key_file_path, "rb") as key_file:
@@ -55,7 +58,9 @@ def validate_signature_with_gpg(signature_check):
 
 
 if __name__ == "__main__":
-    signature_check_config = json.loads(os.environ.get("SIGNATURE_CHECK_CONFIG"))
+    signature_check_config: list[dict[str, Any]] = json.loads(
+        os.environ.get("SIGNATURE_CHECK_CONFIG")
+    )
 
     for check in signature_check_config:
         console.print(f"[blue]{check.get('description')}[/]")
@@ -69,4 +74,4 @@ def validate_signature_with_gpg(signature_check):
             )
         exit(1)
 
-    console.print("[blue]All signatures are valid[/]")
+    console.print("[blue]All signatures are valid[/]")

svn/svn_check.py

@@ -1,12 +1,16 @@
 # /// script
-# requires-python = ">=3.9"
+# requires-python = ">=3.11"
 # dependencies = [
 #     "rich",
 # ]
 # ///
+from __future__ import annotations
+
 import json
 import os
 import re
+from typing import Any
+
 from rich.console import Console
 
 console = Console(width=400, color_system="standard")
@@ -17,7 +21,7 @@
 unknown_file_extensions = []
 
 
-def check_with_regex(file_to_check, pattern, check_type):
+def check_with_regex(file_to_check: str, pattern: str, check_type: str) -> bool | None:
     match = re.match(pattern, file_to_check)
 
     if check_type == "extension":
@@ -27,7 +31,9 @@ def check_with_regex(file_to_check, pattern, check_type):
         return match and match.group(1) in file_to_check
 
 
-def check_files_with_identifiers(identifiers, all_files, check_type):
+def check_files_with_identifiers(
+    identifiers: list[dict[str, Any]], all_files: list[str], check_type: str
+):
     all_files_copy = all_files.copy()
 
     for identifier in identifiers:
@@ -48,7 +54,9 @@ def check_files_with_identifiers(identifiers, all_files, check_type):
 
 
 if __name__ == "__main__":
-    svn_check_config = json.loads(os.environ.get("SVN_CHECK_CONFIG"))
+    svn_check_config: list[dict[str, Any]] = json.loads(
+        os.environ.get("SVN_CHECK_CONFIG")
+    )
 
     for check in svn_check_config:
         console.print(f"[blue]{check.get('description')}[/]")