mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-23 16:20:30 +00:00
fae5f8fdde
* added filetype detection for odt * add function for partition odt documents * add odt files to auto * changelog and version * docs and readme * update installation docs * skip tests if not supported or in docker * import pytest * fix docs typos
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
import os
|
|
import pathlib
|
|
|
|
import pypandoc
|
|
import pytest
|
|
|
|
from unstructured.documents.elements import Title
|
|
from unstructured.partition.odt import partition_odt
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
EXAMPLE_DOCS_DIRECTORY = os.path.join(DIRECTORY, "..", "..", "example-docs")
|
|
|
|
odt_not_supported = "odt" not in pypandoc.get_pandoc_formats()[0]
|
|
is_in_docker = os.path.exists("/.dockerenv")
|
|
|
|
|
|
@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
|
|
@pytest.mark.skipif(odt_not_supported, reason="odt not supported in this version of pypandoc.")
|
|
def test_partition_odt_from_filename():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
elements = partition_odt(filename=filename)
|
|
assert elements == [Title("Lorem ipsum dolor sit amet.")]
|
|
|
|
|
|
@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
|
|
@pytest.mark.skipif(odt_not_supported, reason="odt not supported in this version of pypandoc.")
|
|
def test_partition_odt_from_file():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(file=f)
|
|
|
|
assert elements == [Title("Lorem ipsum dolor sit amet.")]
|