refactor test aftifacts for increased readability

tests/__init__.py

@@ -1,4 +1,5 @@
 import os
+import json
 
 from karton.core import Task
 from karton.core.test import KartonTestCase, TestResource
@@ -9,69 +10,37 @@
 class ClassifierTestCase(KartonTestCase):
     karton_class = Classifier
 
-    def _single_file_test(
-            self, name, content, tag,
-            kind=None, platform=None, extension=None, stage="recognized"
-    ):
-        sample = TestResource(name, content)
-        task = Task({
-            "type": "sample",
-            "kind": "raw"
-        }, payload={
-            "sample": sample,
-            "extraction_level": 999
-        })
-        results = self.run_task(task)
-        if kind is None:
-            self.assertTasksEqual(results, [])
-        else:
-            expected_headers = {
-                "origin": "karton.classifier",
-                "type": "sample",
-                "stage": stage,
-                "quality": "high",
-                "kind": kind
-            }
-            if platform:
-                expected_headers["platform"] = platform
-            if extension:
-                expected_headers["extension"] = extension
-
-            payload = {
-                "sample": sample,
-                "extraction_level": 999,
-            }
-            if tag:
-                payload["tags"] = [tag]
-
-            self.assertTasksEqual(results, [Task(expected_headers, payload)])
-
     def test_works_as_expected(self):
+        self.maxDiff = None
         for testcase in os.listdir("tests/testdata"):
+            print(testcase)
+            if not testcase.endswith('.json'):
+                continue
+
+            testcase_config = testcase
+            testcase_content = testcase_config.replace('.json', '')
+
             with self.subTest(testcase):
-                with open(f"tests/testdata/{testcase}", "rb") as f:
+                with open(f"tests/testdata/{testcase_config}", "rb") as f:
+                    expected = json.load(f)
+                with open(f"tests/testdata/{testcase_content}", "rb") as f:
                     content = f.read()
-                expected_tag, file_name = testcase.split("-", 1)
-                tag_elements = expected_tag.split(":")
-
-                # "misc" prefix is added only for mwdb compatibility
-                if tag_elements[0] == "misc":
-                    tag_elements = tag_elements[1:]
 
-                headers = {
-                    "kind": tag_elements[0],
-                    'stage': "recognized",
+                sample = TestResource(testcase_content, content)
+                task = Task({
+                    "type": "sample",
+                    "kind": "raw"
+                }, payload={
+                    "sample": sample,
+                    "extraction_level": 999,
+                })
+
+                payload = {
+                    "sample": sample,
+                    "extraction_level": 999,
                 }
-                if len(tag_elements) > 1:
-                    if tag_elements[0] == "archive":
-                        headers["extension"] = tag_elements[1]
-                    elif tag_elements[0] == "unknown":
-                        expected_tag = None
-                        headers['stage'] = "unrecognized"
-                    else:
-                        headers["platform"] = tag_elements[1]
-                        if len(tag_elements) > 2:
-                            headers["extension"] = tag_elements[2]
-                self._single_file_test(
-                    file_name, content, expected_tag, **headers
-                )
+                if expected.get("payload"):
+                    payload.update(expected["payload"])
+
+                res = self.run_task(task)
+                self.assertTasksEqual(res, [Task(expected["headers"], payload)])

tests/testdata/archive:7z-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "7z",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:7z"
+        ]
+    }
+}

tests/testdata/archive:ace-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "ace",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:ace"
+        ]
+    }
+}

tests/testdata/archive:bz2-sample.bz2.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "bz2",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:bz2"
+        ]
+    }
+}

tests/testdata/archive:cab-sample.cab.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "cab",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:cab"
+        ]
+    }
+}

tests/testdata/archive:cab-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "cab",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:cab"
+        ]
+    }
+}

tests/testdata/archive:gz-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "gz",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:gz"
+        ]
+    }
+}

tests/testdata/archive:iso-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "iso",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:iso"
+        ]
+    }
+}

tests/testdata/archive:lz-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "lz",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:lz"
+        ]
+    }
+}

tests/testdata/archive:rar-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "rar",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:rar"
+        ]
+    }
+}

tests/testdata/archive:tar-sample.tar.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "tar",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:tar"
+        ]
+    }
+}

tests/testdata/archive:udf-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "udf",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:udf"
+        ]
+    }
+}

tests/testdata/archive:xz-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "xz",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:xz"
+        ]
+    }
+}

tests/testdata/archive:zip-sample.json

@@ -0,0 +1,15 @@
+{
+    "headers": {
+        "extension": "zip",
+        "kind": "archive",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample"
+    },
+    "payload": {
+        "tags": [
+            "archive:zip"
+        ]
+    }
+}

tests/testdata/document:win32:doc-12a_a.doc.json

@@ -0,0 +1,16 @@
+{
+    "headers": {
+        "extension": "doc",
+        "kind": "document",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample",
+        "platform": "win32"
+    },
+    "payload": {
+        "tags": [
+            "document:win32:doc"
+        ]
+    }
+}

tests/testdata/document:win32:docx-EngWhiteKen3081.doc.json

@@ -0,0 +1,16 @@
+{
+    "headers": {
+        "extension": "docx",
+        "kind": "document",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample",
+        "platform": "win32"
+    },
+    "payload": {
+        "tags": [
+            "document:win32:docx"
+        ]
+    }
+}

tests/testdata/document:win32:pdf-Doc-6235300-202005.json

@@ -0,0 +1,16 @@
+{
+    "headers": {
+        "extension": "pdf",
+        "kind": "document",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample",
+        "platform": "win32"
+    },
+    "payload": {
+        "tags": [
+            "document:win32:pdf"
+        ]
+    }
+}

tests/testdata/document:win32:rtf-document.doc.json

@@ -0,0 +1,16 @@
+{
+    "headers": {
+        "extension": "rtf",
+        "kind": "document",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample",
+        "platform": "win32"
+    },
+    "payload": {
+        "tags": [
+            "document:win32:rtf"
+        ]
+    }
+}

tests/testdata/document:win32:xls-faktura_82.xls.json

@@ -0,0 +1,16 @@
+{
+    "headers": {
+        "extension": "xls",
+        "kind": "document",
+        "origin": "karton.classifier",
+        "quality": "high",
+        "stage": "recognized",
+        "type": "sample",
+        "platform": "win32"
+    },
+    "payload": {
+        "tags": [
+            "document:win32:xls"
+        ]
+    }
+}