mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-17 14:05:54 +00:00
0584e1d031
Carrying `skip_infer_table_types` to `infer_table_structure` in
partition flow. Now PPT/X, DOC/X, etc. Table elements should not have a
`text_as_html` field.
Note: I've continued to exclude this var from partitioners that go
through html flow, I think if we've already got the html it doesn't make
sense to carry the infer variable along, since we're not 'infer-ing' the
html table in these cases.
TODO:
✅ add unit tests
---------
Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com>
Co-authored-by: amanda103 <amanda103@users.noreply.github.com>
224 lines
7.1 KiB
Python
224 lines
7.1 KiB
Python
import os
|
|
import pathlib
|
|
|
|
import pytest
|
|
|
|
from test_unstructured.unit_utils import assert_round_trips_through_JSON, example_doc_path
|
|
from unstructured.chunking.title import chunk_by_title
|
|
from unstructured.documents.elements import Table, TableChunk, Title
|
|
from unstructured.partition.odt import partition_odt
|
|
from unstructured.partition.utils.constants import UNSTRUCTURED_INCLUDE_DEBUG_METADATA
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
EXAMPLE_DOCS_DIRECTORY = os.path.join(DIRECTORY, "..", "..", "..", "example-docs")
|
|
|
|
|
|
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."),
|
|
Table(
|
|
text="\nHeader row Mon Wed"
|
|
" Fri\nColor Blue"
|
|
" Red Green\nTime 1pm"
|
|
" 2pm 3pm\nLeader "
|
|
"Sarah Mark Ryan",
|
|
),
|
|
]
|
|
for element in elements:
|
|
assert element.metadata.filename == "fake.odt"
|
|
if UNSTRUCTURED_INCLUDE_DEBUG_METADATA:
|
|
assert {element.metadata.detection_origin for element in elements} == {
|
|
"docx",
|
|
} # this file is processed by docx backend
|
|
|
|
|
|
def test_partition_odt_from_filename_with_metadata_filename():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
elements = partition_odt(filename=filename, metadata_filename="test")
|
|
assert all(element.metadata.filename == "test" for element in elements)
|
|
|
|
|
|
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."),
|
|
Table(
|
|
text="\nHeader row Mon Wed"
|
|
" Fri\nColor Blue"
|
|
" Red Green\nTime 1pm"
|
|
" 2pm 3pm\nLeader "
|
|
"Sarah Mark Ryan",
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"infer_table_structure",
|
|
[
|
|
True,
|
|
False,
|
|
],
|
|
)
|
|
def test_partition_odt_infer_table_structure(infer_table_structure):
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(file=f, infer_table_structure=infer_table_structure)
|
|
table_element_has_text_as_html_field = (
|
|
hasattr(elements[1].metadata, "text_as_html")
|
|
and elements[1].metadata.text_as_html is not None
|
|
)
|
|
assert table_element_has_text_as_html_field == infer_table_structure
|
|
|
|
|
|
def test_partition_odt_from_file_with_metadata_filename():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(file=f, metadata_filename="test")
|
|
|
|
assert all(element.metadata.filename == "test" for element in elements)
|
|
|
|
|
|
def test_partition_odt_from_filename_exclude_metadata():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
elements = partition_odt(filename=filename, include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_odt_from_file_exclude_metadata():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(file=f, include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_odt_metadata_date(
|
|
mocker,
|
|
filename="example-docs/fake.odt",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.odt.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_odt(
|
|
filename=filename,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_odt_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/fake.odt",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.odt.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_odt(
|
|
filename=filename,
|
|
metadata_last_modified=expected_last_modification_date,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_odt_from_file_metadata_date(
|
|
mocker,
|
|
filename="example-docs/fake.odt",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.odt.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(
|
|
file=f,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_odt_from_file_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/fake.odt",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.odt.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_odt(file=f, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_odt_with_json():
|
|
elements = partition_odt(example_doc_path("fake.odt"), include_metadata=True)
|
|
assert_round_trips_through_JSON(elements)
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_odt(
|
|
filename="example-docs/fake.odt",
|
|
):
|
|
elements = partition_odt(filename=filename)
|
|
chunk_elements = partition_odt(filename, chunking_strategy="by_title")
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_odt_non_default():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake.odt")
|
|
elements = partition_odt(filename=filename)
|
|
chunk_elements = partition_odt(
|
|
filename,
|
|
chunking_strategy="by_title",
|
|
max_characters=7,
|
|
combine_text_under_n_chars=5,
|
|
)
|
|
chunks = chunk_by_title(
|
|
elements,
|
|
max_characters=7,
|
|
combine_text_under_n_chars=5,
|
|
)
|
|
for chunk in chunk_elements:
|
|
if isinstance(chunk, TableChunk):
|
|
assert len(chunk.text) <= 7
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|
|
|
|
|
|
def test_partition_odt_element_metadata_has_languages():
|
|
filename = "example-docs/fake.odt"
|
|
elements = partition_odt(filename=filename)
|
|
assert elements[0].metadata.languages == ["eng"]
|
|
|
|
|
|
def test_partition_odt_respects_detect_language_per_element():
|
|
filename = "example-docs/language-docs/eng_spa_mult.odt"
|
|
elements = partition_odt(filename=filename, detect_language_per_element=True)
|
|
langs = [element.metadata.languages for element in elements]
|
|
assert langs == [["eng"], ["spa", "eng"], ["eng"], ["eng"], ["spa"]]
|