mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-03 07:05:20 +00:00
e43cb0e6e0
* add pypandoc dependency * added epub partitioner and file conversion * test for partition_epub * tests for file conversion * add epub to filetype detection * added epub to auto partition * update bricks docs * updated installing docs * changelot and version * add pandoc to dependencies * add pandoc to debian dependencies * linting, linting, linting * typo fix * typo fix * file conversion type hints * more type hints --------- Co-authored-by: qued <64741807+qued@users.noreply.github.com>
24 lines
833 B
Python
24 lines
833 B
Python
import os
|
|
import pathlib
|
|
from unittest.mock import patch
|
|
|
|
import pypandoc
|
|
import pytest
|
|
|
|
from unstructured.file_utils.file_conversion import convert_file_to_text
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
|
|
|
|
def test_convert_file_to_text():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
|
|
html_text = convert_file_to_text(filename, source_format="epub", target_format="html")
|
|
assert html_text.startswith("<p>")
|
|
|
|
|
|
def test_convert_to_file_raises_if_pandoc_not_available():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
|
|
with patch.object(pypandoc, "convert_file", side_effect=FileNotFoundError):
|
|
with pytest.raises(FileNotFoundError):
|
|
convert_file_to_text(filename, source_format="epub", target_format="html")
|