mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 09:26:08 +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()
291 lines
9.5 KiB
Python
291 lines
9.5 KiB
Python
import os
|
|
import pathlib
|
|
|
|
import pytest
|
|
|
|
from unstructured.chunking.title import chunk_by_title
|
|
from unstructured.documents.elements import NarrativeText, Title
|
|
from unstructured.partition.json import partition_json
|
|
from unstructured.partition.xml import partition_xml
|
|
from unstructured.staging.base import elements_to_json
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_filename(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
elements = partition_xml(filename=file_path, xml_keep_tags=False)
|
|
|
|
assert elements[0].text == "United States"
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
def test_partition_xml_from_filename_with_metadata_filename():
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", "factbook.xml")
|
|
elements = partition_xml(filename=file_path, xml_keep_tags=False, metadata_filename="test")
|
|
|
|
assert elements[0].text == "United States"
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_file(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with open(file_path) as f:
|
|
elements = partition_xml(file=f, xml_keep_tags=False, metadata_filename=file_path)
|
|
|
|
assert elements[0].text == "United States"
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
def test_partition_xml_from_file_with_metadata_filename():
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", "factbook.xml")
|
|
with open(file_path) as f:
|
|
elements = partition_xml(file=f, xml_keep_tags=False, metadata_filename="test")
|
|
|
|
assert elements[0].text == "United States"
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_file_rb(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with open(file_path, "rb") as f:
|
|
elements = partition_xml(file=f, xml_keep_tags=False, metadata_filename=file_path)
|
|
|
|
assert elements[0].text == "United States"
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_filename_with_tags_default_encoding(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
elements = partition_xml(filename=file_path, xml_keep_tags=True)
|
|
|
|
assert "<leader>Joe Biden</leader>" in elements[0].text
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
def test_partition_xml_from_text_with_tags(filename="example-docs/factbook.xml"):
|
|
with open(filename) as f:
|
|
text = f.read()
|
|
elements = partition_xml(text=text, xml_keep_tags=True, metadata_filename=filename)
|
|
|
|
assert "<leader>Joe Biden</leader>" in elements[0].text
|
|
assert elements[0].metadata.filename == "factbook.xml"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "encoding", "error"),
|
|
[("factbook-utf-16.xml", "utf-8", UnicodeDecodeError)],
|
|
)
|
|
def test_partition_xml_from_filename_with_tags_raises_encoding_error(filename, encoding, error):
|
|
with pytest.raises(error):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
partition_xml(filename=file_path, xml_keep_tags=True, encoding=encoding)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_file_with_tags_default_encoding(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with open(file_path) as f:
|
|
elements = partition_xml(file=f, xml_keep_tags=True, metadata_filename=file_path)
|
|
|
|
assert "<leader>Joe Biden</leader>" in elements[0].text
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_file_rb_with_tags_default_encoding(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with open(file_path, "rb") as f:
|
|
elements = partition_xml(file=f, xml_keep_tags=True, metadata_filename=file_path)
|
|
|
|
assert "<leader>Joe Biden</leader>" in elements[0].text
|
|
assert elements[0].metadata.filename == filename
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "encoding", "error"),
|
|
[("factbook-utf-16.xml", "utf-8", UnicodeDecodeError)],
|
|
)
|
|
def test_partition_xml_from_file_rb_with_tags_raises_encoding_error(filename, encoding, error):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with pytest.raises(error), open(file_path, "rb") as f:
|
|
partition_xml(
|
|
file=f,
|
|
xml_keep_tags=True,
|
|
metadata_filename=file_path,
|
|
encoding=encoding,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_filename_exclude_metadata(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
elements = partition_xml(filename=file_path, xml_keep_tags=False, include_metadata=False)
|
|
|
|
assert elements[0].text == "United States"
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_from_file_exclude_metadata(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
with open(file_path) as f:
|
|
elements = partition_xml(
|
|
file=f,
|
|
xml_keep_tags=False,
|
|
metadata_filename=file_path,
|
|
include_metadata=False,
|
|
)
|
|
|
|
assert elements[0].text == "United States"
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_xml_metadata_date(
|
|
mocker,
|
|
filename="example-docs/factbook.xml",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.xml.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_xml(
|
|
filename=filename,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_xml_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/factbook.xml",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.xml.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_xml(
|
|
filename=filename,
|
|
metadata_last_modified=expected_last_modification_date,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_xml_from_file_metadata_date(
|
|
mocker,
|
|
filename="example-docs/factbook.xml",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.xml.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_xml(
|
|
file=f,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_xml_from_file_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/factbook.xml",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.xml.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_xml(file=f, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"filename",
|
|
["factbook.xml", "factbook-utf-16.xml"],
|
|
)
|
|
def test_partition_xml_with_json(filename):
|
|
file_path = os.path.join(DIRECTORY, "..", "..", "example-docs", filename)
|
|
elements = partition_xml(filename=file_path, xml_keep_tags=False)
|
|
test_elements = partition_json(text=elements_to_json(elements))
|
|
|
|
assert len(elements) == len(test_elements)
|
|
assert elements[0].metadata.page_number == test_elements[0].metadata.page_number
|
|
assert elements[0].metadata.filename == test_elements[0].metadata.filename
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i] == test_elements[i]
|
|
|
|
|
|
def test_partition_xml_with_narrative_line_breaks():
|
|
xml_text = """<xml>
|
|
<parrot>
|
|
<name>Conure</name>
|
|
<description>A conure is a very friendly bird.
|
|
Conures are feathery and like to dance.
|
|
</description>
|
|
</parrot>
|
|
</xml>"""
|
|
|
|
elements = partition_xml(text=xml_text)
|
|
assert elements[0] == Title("Conure")
|
|
assert isinstance(elements[1], NarrativeText)
|
|
assert str(elements[1]).startswith("A conure is a very friendly bird.")
|
|
assert str(elements[1]).strip().endswith("Conures are feathery and like to dance.")
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_xml(
|
|
filename="example-docs/factbook.xml",
|
|
):
|
|
elements = partition_xml(filename=filename)
|
|
chunk_elements = partition_xml(filename, chunking_strategy="by_title")
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|