Merge pull request #21 from par-tec/ioggstream-20

Fix: #20. Refactor test directories

tests/json/bandit_error.json → tests/data/bandit_error.json

@@ -5,7 +5,7 @@
       "reason": "syntax error while parsing AST from file"
     },
     {
-      "filename": "tests/data/py2.py",
+      "filename": "tests/data/python-01/py2.py",
       "reason": "syntax error while parsing AST from file"
     }
   ],
@@ -43,7 +43,7 @@
   "results": [
     {
       "code": "2 \n3 print(randint(0, 10))\n4 \n",
-      "filename": "tests/canary.py",
+      "filename": "tests/data/python-01/canary.py",
       "issue_confidence": "HIGH",
       "issue_severity": "LOW",
       "issue_text": "Standard pseudo-random generators are not suitable for security/cryptographic purposes.",
@@ -57,7 +57,7 @@
     },
     {
       "code": "4 \n5 password = \"secret\"\n6 \n7 a = eval(\"\"\"\n",
-      "filename": "tests/canary.py",
+      "filename": "tests/data/python-01/canary.py",
       "issue_confidence": "MEDIUM",
       "issue_severity": "LOW",
       "issue_text": "Possible hardcoded password: 'secret'",
@@ -72,7 +72,7 @@
     },
     {
       "code": "6 \n7 a = eval(\"\"\"\n8     3 + 2 \\\n9     + randint(0, 10)\n10 \n11 \"\"\")\n12 assert a\n",
-      "filename": "tests/canary.py",
+      "filename": "tests/data/python-01/canary.py",
       "issue_confidence": "HIGH",
       "issue_severity": "MEDIUM",
       "issue_text": "Use of possibly insecure function - consider using safer ast.literal_eval.",
@@ -90,7 +90,7 @@
     },
     {
       "code": "11 \"\"\")\n12 assert a\n",
-      "filename": "tests/canary.py",
+      "filename": "tests/data/python-01/canary.py",
       "issue_confidence": "HIGH",
       "issue_severity": "LOW",
       "issue_text": "Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.",

tests/data/semgrep-01.annotations.json

@@ -0,0 +1,23 @@
+{
+    "name": "Semgrep Comments",
+    "head_sha": "stuff",
+    "completed_at": "2023-11-09T15:29:33.821590Z",
+    "conclusion": "failure",
+    "output": {
+        "title": "Semgrep: ",
+        "summary": "Semgrep statistics: {\n  \"Total_errors\": 1,\n  \"Semgrep_Version\": \"1.34.0\",\n  \"paths_scanned\": 36\n}",
+        "text": "<add --verbose for a list of skipped paths>",
+        "annotations": [
+            {
+                "path": ".github/workflows/test.yml",
+                "start_line": 31,
+                "end_line": 31,
+                "start_column": 114,
+                "end_column": 117,
+                "annotation_level": "warning",
+                "title": "Syntax error",
+                "message": " When parsing a snippet as Bash for metavariable-pattern in rule 'yaml.github-actions.security.curl-eval.curl-eval'"
+            }
+        ]
+    }
+}

tests/test_bandit.py

@@ -4,15 +4,15 @@
 from parse_scripts.util import json_load
 
 TEST_DIR = Path(__file__).parent
-JSON_DIR = TEST_DIR / "json"
+DATA_DIR = TEST_DIR / "data"
 
 
 def test_errors():
-    results = json_load(JSON_DIR / "bandit_error.json")
+    results = json_load(DATA_DIR / "bandit_error.json")
     errors = [bandit.bandit_error(error) for error in results["errors"]]
     assert errors[0]["path"] == "LICENSE"
     assert errors[1] == {
-        "path": "tests/data/py2.py",
+        "path": "tests/data/python-01/py2.py",
         "start_line": 2,
         "end_line": 2,
         "annotation_level": "failure",
@@ -22,13 +22,13 @@ def test_errors():
 
 
 def test_annotations():
-    data = json_load(JSON_DIR / "bandit.json")
+    data = json_load(DATA_DIR / "bandit.json")
     annotations = bandit.bandit_annotations(data)
     assert annotations[0]["path"] == "canary.py"
     assert annotations[0]["start_line"] == 3
 
 
 def test_run_check():
-    data = json_load(JSON_DIR / "bandit.json")
+    data = json_load(DATA_DIR / "bandit.json")
     run_check_body = bandit.bandit_run_check(data)
     assert run_check_body["conclusion"] == "failure"

tests/test_checkov.py

@@ -1,16 +1,24 @@
 from pathlib import Path
 
+import pytest
+
 from parse_scripts import checkov
 from parse_scripts.util import json_load
 
 TEST_DIR = Path(__file__).parent
-JSON_DIR = TEST_DIR / "json"
 DATA_DIR = TEST_DIR / "data"
 
 
-def test_parse():
-    expected_comments = json_load(DATA_DIR / "checkov_input.json")
-    data = json_load(JSON_DIR / "checkov.json")
+@pytest.mark.parametrize(
+    "infile,expected",
+    [
+        (f, f.with_suffix(".annotations.json"))
+        for f in DATA_DIR.glob("checkov-[0-9][0-9].json")
+    ],
+)
+def test_parse(infile, expected):
+    expected_comments = json_load(expected)
+    data = json_load(infile)
     actual_comments = checkov.checkov_results(log=data, github_sha="stuff")
     actual_comments["completed_at"] = "00:00"
     assert expected_comments == actual_comments

tests/test_semgrep.py

@@ -1,37 +1,23 @@
 from pathlib import Path
 
+import pytest
+
 import parse_scripts.semgrep
 from parse_scripts.util import json_load
 
-DATA_DIR = Path(__file__).parent / "json"
-
-expected_results = {
-    "name": "Semgrep Comments",
-    "head_sha": "stuff",
-    "completed_at": "2023-11-09T15:29:33.821590Z",
-    "conclusion": "failure",
-    "output": {
-        "title": "Semgrep: ",
-        "summary": 'Semgrep statistics: {\n  "Total_errors": 1,\n  "Semgrep_Version": "1.34.0",\n  "paths_scanned": 36\n}',
-        "text": "<add --verbose for a list of skipped paths>",
-        "annotations": [
-            {
-                "path": ".github/workflows/test.yml",
-                "start_line": 31,
-                "end_line": 31,
-                "start_column": 114,
-                "end_column": 117,
-                "annotation_level": "warning",
-                "title": "Syntax error",
-                "message": " When parsing a snippet as Bash for metavariable-pattern in rule 'yaml.github-actions.security.curl-eval.curl-eval'",
-            }
-        ],
-    },
-}
+DATA_DIR = Path(__file__).parent / "data"
 
 
-def test_parse_data():
-    data = json_load(DATA_DIR / "semgrep.json")
+@pytest.mark.parametrize(
+    "infile,expected",
+    [
+        (f, f.with_suffix(".annotations.json"))
+        for f in DATA_DIR.glob("semgrep-[0-9][0-9].json")
+    ],
+)
+def test_parse_data(infile, expected):
+    data = json_load(infile)
+    expected_results = json_load(expected)
     actual_results = parse_scripts.semgrep.parse_data(data, "stuff")
     actual_results["completed_at"] = "2023-11-09T15:29:33.821590Z"
     assert expected_results == actual_results