mirror of
https://github.com/freedomofpress/dangerzone.git
synced 2025-04-28 18:02:38 +02:00
69c2a02d81
Remove timeouts due to several reasons: 1. Lost purpose: after implementing the containers page streaming the only subprocess we have left is LibreOffice. So don't have such a big risk of commands hanging (the original reason for timeouts). 2. Little benefit: predicting execution time is generically unsolvable computer science problem. Ultimately we were guessing an arbitrary time based on the number of pages and the document size. As a guess we made it pretty lax (30s per page or MB). A document hanging for this long will probably lead to user frustration in any case and the user may be compelled to abort the conversion. 3. Technical Challenges with non-blocking timeout: there have been several technical challenges in keeping timeouts that we've made effort to accommodate. A significant one was having to do non-blocking read to ensure we could timeout when reading conversion stream (and then used here) Fixes #687
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
import platform
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from dangerzone.isolation_provider.container import Container
|
|
from dangerzone.logic import DangerzoneCore
|
|
|
|
|
|
# TODO: Perform an equivalent test on Qubes.
|
|
# NOTE: We skip running this test on Windows/MacOS, because our current CI cannot run
|
|
# Docker in these platforms. It's not a problem anyways, because the result should be
|
|
# the same in all container-based platforms.
|
|
@pytest.mark.skipif(platform.system() != "Linux", reason="Container-specific")
|
|
def test_ocr_ommisions() -> None:
|
|
# Create the command that will list all the installed languages in the container
|
|
# image.
|
|
runtime = Container.get_runtime()
|
|
command = [
|
|
runtime,
|
|
"run",
|
|
Container.CONTAINER_NAME,
|
|
"find",
|
|
"/usr/share/tessdata/",
|
|
"-name",
|
|
"*.traineddata",
|
|
]
|
|
|
|
# Run the command, strip any extra whitespace, and remove the following first line
|
|
# from the result:
|
|
#
|
|
# List of available languages in "/usr/share/tessdata/" ...
|
|
installed_langs_filenames = (
|
|
subprocess.run(command, text=True, check=True, stdout=subprocess.PIPE)
|
|
.stdout.strip()
|
|
.split("\n")
|
|
)
|
|
installed_langs = set(
|
|
[
|
|
Path(filename).name.split(".traineddata")[0]
|
|
for filename in installed_langs_filenames
|
|
]
|
|
)
|
|
|
|
# Remove the "osd" and "equ" languages from the list of installed languages, since
|
|
# they are not an actual language. Read more in:
|
|
# https://pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/
|
|
installed_langs -= {"osd", "equ"}
|
|
|
|
# Grab the languages that Dangerzone offers to the user through the GUI/CLI.
|
|
offered_langs = set(DangerzoneCore(Container()).ocr_languages.values())
|
|
|
|
# Ensure that both the installed languages and the ones we offer to the user are the
|
|
# same.
|
|
assert installed_langs == offered_langs
|