mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-06-27 02:30:08 +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>
22 lines
753 B
Python
22 lines
753 B
Python
import os
|
|
import pathlib
|
|
|
|
from unstructured.partition.epub import partition_epub
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
|
|
|
|
def test_partition_epub_from_filename():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
|
|
elements = partition_epub(filename=filename)
|
|
assert len(elements) > 0
|
|
assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
|
|
|
|
|
|
def test_partition_epub_from_file():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_epub(file=f)
|
|
assert len(elements) > 0
|
|
assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
|