Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Handle graphics images and VHD disk images #60

Merged
merged 4 commits into from
Jun 15, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions karton/classifier/classifier.py
Original file line number Diff line number Diff line change
Expand Up @@ -300,6 +300,27 @@ def zip_has_mac_app() -> bool:
)
return sample_class

# Various graphics/image file formats
image_assoc = {
"gif": ["GIF image data"],
"jpg": ["JPEG image data"],
"png": ["PNG image data"],
}

for ext, patterns in image_assoc.items():
if any(pattern in magic for pattern in patterns):
sample_class.update({"kind": "misc", "extension": ext})
return sample_class

if extension in image_assoc.keys():
sample_class.update({"kind": "misc", "extension": ext})
return sample_class

# Is Disk image?
if magic.startswith("Microsoft Disk Image") or extension == "vhd":
sample_class.update({"kind": "archive", "extension": "vhd"})
return sample_class

# Windows scripts (per extension)
script_extensions = [
"vbs",
Expand Down
69 changes: 69 additions & 0 deletions tests/test_classifier_misc.py
Original file line number Diff line number Diff line change
Expand Up @@ -73,3 +73,72 @@ def test_process_misc_csv(self):
},
)
self.assertTasksEqual(res, [expected])

def test_process_misc_gif(self):
resource = mock_resource("misc.gif")
magic = self.magic_from_content(resource.content, mime=False)
res = self.run_task(mock_task(resource))

expected = Task(
headers={
"type": "sample",
"stage": "recognized",
"origin": "karton.classifier",
"quality": "high",
"kind": "misc",
"extension": "gif",
"mime": ANY,
},
payload={
"sample": resource,
"tags": ["misc:gif"],
"magic": magic,
},
)
self.assertTasksEqual(res, [expected])

def test_process_misc_jpg(self):
resource = mock_resource("misc.jpg")
magic = self.magic_from_content(resource.content, mime=False)
res = self.run_task(mock_task(resource))

expected = Task(
headers={
"type": "sample",
"stage": "recognized",
"origin": "karton.classifier",
"quality": "high",
"kind": "misc",
"extension": "jpg",
"mime": ANY,
},
payload={
"sample": resource,
"tags": ["misc:jpg"],
"magic": magic,
},
)
self.assertTasksEqual(res, [expected])

def test_process_misc_png(self):
resource = mock_resource("misc.png")
magic = self.magic_from_content(resource.content, mime=False)
res = self.run_task(mock_task(resource))

expected = Task(
headers={
"type": "sample",
"stage": "recognized",
"origin": "karton.classifier",
"quality": "high",
"kind": "misc",
"extension": "png",
"mime": ANY,
},
payload={
"sample": resource,
"tags": ["misc:png"],
"magic": magic,
},
)
self.assertTasksEqual(res, [expected])
Loading