mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 17:41:15 +00:00
3bab9d93e6
**Summary** In preparation for pluggable auto-partitioners simplify metadata as discussed. **Additional Context** - Pluggable auto-partitioners requires partitioners to have a consistent call signature. An arbitrary partitioner provided at runtime needs to have a call signature that is known and consistent. Basically `partition_x(filename, *, file, **kwargs)`. - The current `auto.partition()` is highly coupled to each distinct file-type partitioner, deciding which arguments to forward to each. - This is driven by the existence of "delegating" partitioners, those that convert their file-type and then call a second partitioner to do the actual partitioning. Both the delegating and proxy partitioners are decorated with metadata-post-processing decorators and those decorators are not idempotent. We call the situation where those decorators would run twice "double-decorating". For example, EPUB converts to HTML and calls `partition_html()` and both `partition_epub()` and `partition_html()` are decorated. - The way double-decorating has been avoided in the past is to avoid sending the arguments the metadata decorators are sensitive to to the proxy partitioner. This is very obscure, complex to reason about, error-prone, and just overall not a viable strategy. The better solution is to not decorate delegating partitioners and let the proxy partitioner handle all the metadata. - This first step in preparation for that is part of simplifying the metadata processing by removing unused or unwanted legacy parameters. - `date_from_file_object` is a misnomer because a file-object never contains last-modified data. - It can never produce useful results in the API where last-modified information must be provided by `metadata_last_modified`. - It is an undocumented parameter so not in use. - Using it can produce incorrect metadata.
120 lines
4.2 KiB
Python
120 lines
4.2 KiB
Python
from __future__ import annotations
|
|
|
|
from pytest_mock import MockFixture
|
|
|
|
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 Title
|
|
from unstructured.partition.rst import partition_rst
|
|
|
|
|
|
def test_partition_rst_from_filename():
|
|
elements = partition_rst(example_doc_path("README.rst"))
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filetype == "text/x-rst"
|
|
for element in elements:
|
|
assert element.metadata.filename == "README.rst"
|
|
|
|
|
|
def test_partition_rst_from_filename_returns_uns_elements():
|
|
elements = partition_rst(example_doc_path("README.rst"))
|
|
assert isinstance(elements[0], Title)
|
|
|
|
|
|
def test_partition_rst_from_filename_with_metadata_filename():
|
|
elements = partition_rst(example_doc_path("README.rst"), metadata_filename="test")
|
|
assert all(element.metadata.filename == "test" for element in elements)
|
|
|
|
|
|
def test_partition_rst_from_file():
|
|
with open(example_doc_path("README.rst"), "rb") as f:
|
|
elements = partition_rst(file=f)
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filetype == "text/x-rst"
|
|
for element in elements:
|
|
assert element.metadata.filename is None
|
|
|
|
|
|
def test_partition_rst_from_file_with_metadata_filename():
|
|
with open(example_doc_path("README.rst"), "rb") as f:
|
|
elements = partition_rst(file=f, metadata_filename="test")
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
for element in elements:
|
|
assert element.metadata.filename == "test"
|
|
|
|
|
|
def test_partition_rst_from_filename_exclude_metadata():
|
|
elements = partition_rst(example_doc_path("README.rst"), include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_rst_from_file_exclude_metadata():
|
|
with open(example_doc_path("README.rst"), "rb") as f:
|
|
elements = partition_rst(file=f, include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
# -- .metadata.last_modified ---------------------------------------------------------------------
|
|
|
|
|
|
def test_partition_rst_from_file_path_gets_last_modified_from_filesystem(mocker: MockFixture):
|
|
filesystem_last_modified = "2024-06-14T16:01:29"
|
|
mocker.patch(
|
|
"unstructured.partition.rst.get_last_modified_date", return_value=filesystem_last_modified
|
|
)
|
|
|
|
elements = partition_rst(example_doc_path("README.rst"))
|
|
|
|
assert all(e.metadata.last_modified == filesystem_last_modified for e in elements)
|
|
|
|
|
|
def test_partition_rst_from_file_path_prefers_metadata_last_modified(mocker: MockFixture):
|
|
filesystem_last_modified = "2024-06-14T16:01:29"
|
|
metadata_last_modified = "2020-07-05T09:24:28"
|
|
mocker.patch(
|
|
"unstructured.partition.rst.get_last_modified_date", return_value=filesystem_last_modified
|
|
)
|
|
|
|
elements = partition_rst(
|
|
example_doc_path("README.rst"), metadata_last_modified=metadata_last_modified
|
|
)
|
|
|
|
assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
|
|
|
|
|
|
# ------------------------------------------------------------------------------------------------
|
|
|
|
|
|
def test_partition_rst_with_json():
|
|
elements = partition_rst(example_doc_path("README.rst"))
|
|
assert_round_trips_through_JSON(elements)
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_rst():
|
|
file_path = example_doc_path("README.rst")
|
|
elements = partition_rst(file_path)
|
|
chunk_elements = partition_rst(file_path, chunking_strategy="by_title")
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|
|
|
|
|
|
def test_partition_rst_element_metadata_has_languages():
|
|
elements = partition_rst(example_doc_path("README.rst"))
|
|
assert elements[0].metadata.languages == ["eng"]
|
|
|
|
|
|
def test_partition_rst_respects_detect_language_per_element():
|
|
elements = partition_rst(
|
|
example_doc_path("language-docs/eng_spa_mult.rst"), detect_language_per_element=True
|
|
)
|
|
langs = [element.metadata.languages for element in elements]
|
|
assert langs == [["eng"], ["spa", "eng"], ["eng"], ["eng"], ["spa"]]
|