mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-06-27 02:30:08 +00:00
a9b9b873b1
* first pass at partition_tsv * working tests * create constants for tests and debug `make test` failure * make check and tidy * undo changes for testing locally * update changelog and version * fix bricks.rst * refactor if statements * make tidy * fix README and change try/except to if/else * update changelog and version * fix\ docstring
34 lines
1.3 KiB
Python
34 lines
1.3 KiB
Python
from test_unstructured.partition.test_constants import EXPECTED_TABLE, EXPECTED_TEXT
|
|
from unstructured.cleaners.core import clean_extra_whitespace
|
|
from unstructured.documents.elements import Table
|
|
from unstructured.partition.csv import partition_csv
|
|
|
|
EXPECTED_FILETYPE = "text/csv"
|
|
|
|
|
|
def test_partition_csv_from_filename(filename="example-docs/stanley-cups.csv"):
|
|
elements = partition_csv(filename=filename)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert elements[0].metadata.text_as_html == EXPECTED_TABLE
|
|
assert elements[0].metadata.filetype == EXPECTED_FILETYPE
|
|
|
|
|
|
def test_partition_csv_from_file(filename="example-docs/stanley-cups.csv"):
|
|
with open(filename, "rb") as f:
|
|
elements = partition_csv(file=f)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.text_as_html == EXPECTED_TABLE
|
|
assert elements[0].metadata.filetype == EXPECTED_FILETYPE
|
|
|
|
|
|
def test_partition_csv_can_exclude_metadata(filename="example-docs/stanley-cups.csv"):
|
|
elements = partition_csv(filename=filename, include_metadata=False)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.text_as_html is None
|
|
assert elements[0].metadata.filetype is None
|