mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-09-26 17:02:31 +00:00
c58b261feb
### Summary Partial solution to #1185. Related to #1222. Creates decorator from `chunk_by_title` cleaning brick. Breaks a document into sections based on the presence of Title elements. Also starts a new section under the following conditions: - If metadata changes, indicating a change in section or page or a switch to processing attachments. If `multipage_sections=True`, sections can span pages. `multipage_sections` defaults to True. - If the length of the section exceeds `new_after_n_chars` characters. The default is 1500. The **chunking function does not split individual elements**, so it's possible for a section to exceed that threshold if an individual element if over `new_after_n_chars characters`, which could occur with a long NarrativeText element. Combines sections under these conditions - Sections under `combine_under_n_chars` characters are combined. The default is 500. ### Testing from unstructured.partition.html import partition_html url = "https://understandingwar.org/backgrounder/russian-offensive-campaign-assessment-august-27-2023-0" chunks = partition_html(url=url, chunking_strategy="by_title") for chunk in chunks: print(chunk) print("\n\n" + "-"*80) input()
281 lines
8.5 KiB
Python
281 lines
8.5 KiB
Python
import os
|
|
import pathlib
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
import requests
|
|
|
|
from unstructured.chunking.title import chunk_by_title
|
|
from unstructured.partition.json import partition_json
|
|
from unstructured.partition.md import partition_md
|
|
from unstructured.staging.base import elements_to_json
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
|
|
|
|
def test_partition_md_from_filename():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
elements = partition_md(filename=filename)
|
|
assert "PageBreak" not in [elem.category for elem in elements]
|
|
assert len(elements) > 0
|
|
for element in elements:
|
|
assert element.metadata.filename == "README.md"
|
|
|
|
|
|
def test_partition_md_from_filename_with_metadata_filename():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
elements = partition_md(filename=filename, metadata_filename="test")
|
|
assert "PageBreak" not in [elem.category for elem in elements]
|
|
assert len(elements) > 0
|
|
for element in elements:
|
|
assert element.metadata.filename == "test"
|
|
|
|
|
|
def test_partition_md_from_file():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
elements = partition_md(file=f)
|
|
assert len(elements) > 0
|
|
for element in elements:
|
|
assert element.metadata.filename is None
|
|
|
|
|
|
def test_partition_md_from_file_with_metadata_filename():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
elements = partition_md(file=f, metadata_filename="test")
|
|
assert len(elements) > 0
|
|
assert all(element.metadata.filename == "test" for element in elements)
|
|
|
|
|
|
def test_partition_md_from_text():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
elements = partition_md(text=text)
|
|
assert len(elements) > 0
|
|
for element in elements:
|
|
assert element.metadata.filename is None
|
|
|
|
|
|
class MockResponse:
|
|
def __init__(self, text, status_code, headers={}):
|
|
self.text = text
|
|
self.status_code = status_code
|
|
self.ok = status_code < 300
|
|
self.headers = headers
|
|
|
|
|
|
def test_partition_md_from_url():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
response = MockResponse(
|
|
text=text,
|
|
status_code=200,
|
|
headers={"Content-Type": "text/markdown"},
|
|
)
|
|
with patch.object(requests, "get", return_value=response) as _:
|
|
elements = partition_md(url="https://fake.url")
|
|
|
|
assert len(elements) > 0
|
|
for element in elements:
|
|
assert element.metadata.filename is None
|
|
|
|
|
|
def test_partition_md_from_url_raises_with_bad_status_code():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
response = MockResponse(
|
|
text=text,
|
|
status_code=500,
|
|
headers={"Content-Type": "text/html"},
|
|
)
|
|
with patch.object(requests, "get", return_value=response) as _:
|
|
with pytest.raises(ValueError):
|
|
partition_md(url="https://fake.url")
|
|
|
|
|
|
def test_partition_md_from_url_raises_with_bad_content_type():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
response = MockResponse(
|
|
text=text,
|
|
status_code=200,
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
with patch.object(requests, "get", return_value=response) as _:
|
|
with pytest.raises(ValueError):
|
|
partition_md(url="https://fake.url")
|
|
|
|
|
|
def test_partition_md_raises_with_none_specified():
|
|
with pytest.raises(ValueError):
|
|
partition_md()
|
|
|
|
|
|
def test_partition_md_raises_with_too_many_specified():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
with pytest.raises(ValueError):
|
|
partition_md(filename=filename, text=text)
|
|
|
|
|
|
def test_partition_md_from_filename_exclude_metadata():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
elements = partition_md(filename=filename, include_metadata=False)
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_md_from_file_exclude_metadata():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
elements = partition_md(file=f, include_metadata=False)
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_md_from_text_exclude_metadata():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "README.md")
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
elements = partition_md(text=text, include_metadata=False)
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_md_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.md",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.md.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_md(
|
|
filename=filename,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_md_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.md",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.md.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_md(
|
|
filename=filename,
|
|
metadata_last_modified=expected_last_modification_date,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_md_from_file_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.md",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.md.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_md(
|
|
file=f,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_md_from_file_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.md",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.md.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_md(file=f, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_md_from_text_metadata_date(
|
|
filename="example-docs/README.md",
|
|
):
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
elements = partition_md(
|
|
text=text,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified is None
|
|
|
|
|
|
def test_partition_md_from_text_with_custom_metadata_date(
|
|
filename="example-docs/README.md",
|
|
):
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
elements = partition_md(text=text, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_md_with_json(
|
|
filename="example-docs/README.md",
|
|
):
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
|
|
elements = partition_md(
|
|
text=text,
|
|
)
|
|
test_elements = partition_json(text=elements_to_json(elements))
|
|
|
|
assert len(elements) == len(test_elements)
|
|
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_on_partition_md(
|
|
filename="example-docs/README.md",
|
|
):
|
|
elements = partition_md(filename=filename)
|
|
chunk_elements = partition_md(filename, chunking_strategy="by_title")
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|