mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-03 07:05:20 +00:00
1fb464235a
This change is adding to our `add_chunking_strategy` logic so that we are able to chunk Table elements' `text` and `text_as_html` params. In order to keep the functionality under the same `by_title` chunking strategy we have renamed the `combine_under_n_chars` to `max_characters`. It functions the same way for the combining elements under Title's, as well as specifying a chunk size (in chars) for TableChunk elements. *renaming the variable to `max_characters` will also reflect the 'hard max' we will implement for large elements in followup PRs Additionally -> some lint changes snuck in when I ran `make tidy` hence the minor changes in unrelated files :) TODO: ✅ add unit tests --> note: added where I could to unit tests! Some unit tests I just clarified that the chunking strategy was now 'by_title' because we don't have a file example that has Table elements to test the 'by_num_characters' chunking strategy ✅ update changelog To manually test: ``` In [1]: filename="example-docs/example-10k.html" In [2]: from unstructured.chunking.title import chunk_table_element In [3]: from unstructured.partition.auto import partition In [4]: elements = partition(filename) # element at -2 happens to be a Table, and we'll get chunks of char size 4 here In [5]: chunks = chunk_table_element(elements[-2], 4) # examine text and text_as_html params ln [6]: for c in chunks: print(c.text) print(c.metadata.text_as_html) ``` --------- Co-authored-by: Yao You <theyaoyou@gmail.com>
208 lines
7.2 KiB
Python
208 lines
7.2 KiB
Python
from tempfile import SpooledTemporaryFile
|
|
|
|
import pytest
|
|
|
|
from test_unstructured.partition.test_constants import (
|
|
EXPECTED_TABLE,
|
|
EXPECTED_TABLE_WITH_EMOJI,
|
|
EXPECTED_TEXT,
|
|
EXPECTED_TEXT_WITH_EMOJI,
|
|
)
|
|
from unstructured.chunking.title import chunk_by_title
|
|
from unstructured.cleaners.core import clean_extra_whitespace
|
|
from unstructured.documents.elements import Table
|
|
from unstructured.partition.csv import partition_csv
|
|
from unstructured.partition.json import partition_json
|
|
from unstructured.staging.base import elements_to_json
|
|
|
|
EXPECTED_FILETYPE = "text/csv"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "expected_text", "expected_table"),
|
|
[
|
|
("stanley-cups.csv", EXPECTED_TEXT, EXPECTED_TABLE),
|
|
("stanley-cups-with-emoji.csv", EXPECTED_TEXT_WITH_EMOJI, EXPECTED_TABLE_WITH_EMOJI),
|
|
],
|
|
)
|
|
def test_partition_csv_from_filename(filename, expected_text, expected_table):
|
|
f_path = f"example-docs/{filename}"
|
|
elements = partition_csv(filename=f_path)
|
|
|
|
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
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
def test_partition_csv_from_filename_with_metadata_filename(
|
|
filename="example-docs/stanley-cups.csv",
|
|
):
|
|
elements = partition_csv(filename=filename, metadata_filename="test")
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "expected_text", "expected_table"),
|
|
[
|
|
("stanley-cups.csv", EXPECTED_TEXT, EXPECTED_TABLE),
|
|
("stanley-cups-with-emoji.csv", EXPECTED_TEXT_WITH_EMOJI, EXPECTED_TABLE_WITH_EMOJI),
|
|
],
|
|
)
|
|
def test_partition_csv_from_file(filename, expected_text, expected_table):
|
|
f_path = f"example-docs/{filename}"
|
|
with open(f_path, "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
|
|
assert elements[0].metadata.filename is None
|
|
|
|
|
|
def test_partition_csv_from_file_with_metadata_filename(filename="example-docs/stanley-cups.csv"):
|
|
with open(filename, "rb") as f:
|
|
elements = partition_csv(file=f, metadata_filename="test")
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
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
|
|
assert elements[0].metadata.filename is None
|
|
|
|
|
|
def test_partition_csv_metadata_date(mocker, filename="example-docs/stanley-cups.csv"):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
mocker.patch(
|
|
"unstructured.partition.csv.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
elements = partition_csv(filename=filename)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_csv_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/stanley-cups.csv",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.csv.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_csv(
|
|
filename=filename,
|
|
metadata_last_modified=expected_last_modification_date,
|
|
)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_csv_from_file_metadata_date(
|
|
mocker,
|
|
filename="example-docs/stanley-cups.csv",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.csv.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
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.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_csv_from_file_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/stanley-cups.csv",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.csv.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_csv(file=f, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_csv_from_file_without_metadata(
|
|
mocker,
|
|
filename="example-docs/stanley-cups.csv",
|
|
):
|
|
"""Test partition_csv() with file that are not possible to get last modified date"""
|
|
|
|
with open(filename, "rb") as f:
|
|
sf = SpooledTemporaryFile()
|
|
sf.write(f.read())
|
|
sf.seek(0)
|
|
elements = partition_csv(file=sf)
|
|
|
|
assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
|
|
assert isinstance(elements[0], Table)
|
|
assert elements[0].metadata.last_modified is None
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "expected_text", "expected_table"),
|
|
[
|
|
("stanley-cups.csv", EXPECTED_TEXT, EXPECTED_TABLE),
|
|
("stanley-cups-with-emoji.csv", EXPECTED_TEXT_WITH_EMOJI, EXPECTED_TABLE_WITH_EMOJI),
|
|
],
|
|
)
|
|
def test_partition_csv_with_json(filename, expected_text, expected_table):
|
|
f_path = f"example-docs/{filename}"
|
|
elements = partition_csv(filename=f_path)
|
|
test_elements = partition_json(text=elements_to_json(elements))
|
|
|
|
assert len(elements) == len(test_elements)
|
|
assert clean_extra_whitespace(elements[0].text) == clean_extra_whitespace(test_elements[0].text)
|
|
assert elements[0].metadata.text_as_html == test_elements[0].metadata.text_as_html
|
|
assert elements[0].metadata.filename == test_elements[0].metadata.filename
|
|
for i in range(len(elements)):
|
|
assert elements[i] == test_elements[i]
|
|
|
|
|
|
def test_add_chunking_strategy_to_partition_csv_non_default():
|
|
filename = "example-docs/stanley-cups.csv"
|
|
|
|
elements = partition_csv(filename=filename)
|
|
chunk_elements = partition_csv(
|
|
filename,
|
|
chunking_strategy="by_title",
|
|
max_characters=9,
|
|
combine_text_under_n_chars=0,
|
|
)
|
|
chunks = chunk_by_title(elements, max_characters=9, combine_text_under_n_chars=0)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|