[pytx] Implement FileContent class

python-threatexchange/threatexchange/content_type/content_base.py

@@ -10,7 +10,7 @@
 from enum import Enum, auto
 import typing as t
 
-from threatexchange import common
+import common
 
 
 class ContentType:
@@ -21,8 +21,8 @@ def get_name(cls) -> str:
 
     @classmethod
     def extract_additional_content(
-        cls, content_arg: str
-    ) -> t.List[t.Tuple[t.Type["ContentType"], str]]:
+        cls, content_in_file: Path, available_content: t.Sequence[t.Type["ContentType"]]
+    ) -> t.Dict[t.Type["ContentType"], t.List[Path]]:
         """
         Post-process/download content to find additional components
 
@@ -32,7 +32,7 @@ def extract_additional_content(
         * Photo => run OCR and extract text
         * Video => break out photo thumbnail, close caption text, audio
         """
-        return []
+        return {}
 
 
 class RotationType(Enum):

python-threatexchange/threatexchange/content_type/file_content.py

@@ -0,0 +1,30 @@
+import typing as t
+from content_base import ContentType
+from photo import PhotoContent
+from video import VideoContent
+
+class FileContent(ContentType):
+    """
+    Content representing a file. Determines if a file is a photo or video based on file extension.
+    """
+
+    VALID_PHOTO_EXTENSIONS = {".jpg", ".jpeg", ".png", ".gif"}
+    VALID_VIDEO_EXTENSIONS = {".mp4", ".avi", ".mov", ".mkv"}
+
+    def __init__(self, file_name: str):
+        self.file_name = file_name
+
+    @classmethod
+    def get_name(cls) -> str:
+        return "File"
+
+    def get_content_type_from_filename(self) -> t.Type[ContentType]:
+        """
+        Determines content type based on file extension.
+        """
+        if any(self.file_name.endswith(ext) for ext in self.VALID_PHOTO_EXTENSIONS):
+            return PhotoContent
+        elif any(self.file_name.endswith(ext) for ext in self.VALID_VIDEO_EXTENSIONS):
+            return VideoContent
+        else:
+            raise ValueError(f"Unknown content type for file: {self.file_name}")

python-threatexchange/threatexchange/tests/test_file_content_type.py

@@ -0,0 +1,20 @@
+import unittest
+from threatexchange.content_type.photo import PhotoContent
+from threatexchange.content_type.video import VideoContent
+from threatexchange.content_type.file_content import FileContent
+
+class TestFileContentType(unittest.TestCase):
+    def test_photo_detection(self):
+        file_content = FileContent("file.jpg")
+        content_type = file_content.get_content_type_from_filename()
+        self.assertEqual(content_type, PhotoContent)
+
+    def test_video_detection(self):
+        file_content = FileContent("file.mp4")
+        content_type = file_content.get_content_type_from_filename()
+        self.assertEqual(content_type, VideoContent)
+
+    def test_unknown_file_type(self):
+        file_content = FileContent("file.txt")
+        with self.assertRaises(ValueError):
+            file_content.get_content_type_from_filename()