mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-07 09:02:59 +00:00

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>
147 lines
4.6 KiB
Python
147 lines
4.6 KiB
Python
from unstructured.chunking.title import chunk_by_title
|
|
from unstructured.documents.elements import Title
|
|
from unstructured.partition.json import partition_json
|
|
from unstructured.partition.org import partition_org
|
|
from unstructured.staging.base import elements_to_json
|
|
|
|
|
|
def test_partition_org_from_filename(filename="example-docs/README.org"):
|
|
elements = partition_org(filename=filename)
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filetype == "text/org"
|
|
|
|
|
|
def test_partition_org_from_filename_with_metadata_filename(filename="example-docs/README.org"):
|
|
elements = partition_org(filename=filename, metadata_filename="test")
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
def test_partition_org_from_file(filename="example-docs/README.org"):
|
|
with open(filename, "rb") as f:
|
|
elements = partition_org(file=f)
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filetype == "text/org"
|
|
|
|
|
|
def test_partition_org_from_file_with_metadata_filename(filename="example-docs/README.org"):
|
|
with open(filename, "rb") as f:
|
|
elements = partition_org(file=f, metadata_filename="test")
|
|
|
|
assert elements[0] == Title("Example Docs")
|
|
assert elements[0].metadata.filename == "test"
|
|
|
|
|
|
def test_partition_org_from_filename_exclude_metadata(filename="example-docs/README.org"):
|
|
elements = partition_org(filename=filename, include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_org_from_file_exclude_metadata(filename="example-docs/README.org"):
|
|
with open(filename, "rb") as f:
|
|
elements = partition_org(file=f, include_metadata=False)
|
|
|
|
for i in range(len(elements)):
|
|
assert elements[i].metadata.to_dict() == {}
|
|
|
|
|
|
def test_partition_org_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.org",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.html.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_org(
|
|
filename=filename,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_org_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.org",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.html.get_last_modified_date",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
elements = partition_org(
|
|
filename=filename,
|
|
metadata_last_modified=expected_last_modification_date,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_org_from_file_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.org",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.html.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_org(
|
|
file=f,
|
|
)
|
|
|
|
assert elements[0].metadata.last_modified == mocked_last_modification_date
|
|
|
|
|
|
def test_partition_org_from_file_with_custom_metadata_date(
|
|
mocker,
|
|
filename="example-docs/README.org",
|
|
):
|
|
mocked_last_modification_date = "2029-07-05T09:24:28"
|
|
expected_last_modification_date = "2020-07-05T09:24:28"
|
|
|
|
mocker.patch(
|
|
"unstructured.partition.html.get_last_modified_date_from_file",
|
|
return_value=mocked_last_modification_date,
|
|
)
|
|
|
|
with open(filename, "rb") as f:
|
|
elements = partition_org(file=f, metadata_last_modified=expected_last_modification_date)
|
|
|
|
assert elements[0].metadata.last_modified == expected_last_modification_date
|
|
|
|
|
|
def test_partition_org_with_json(filename="example-docs/README.org"):
|
|
elements = partition_org(filename=filename)
|
|
test_elements = partition_json(text=elements_to_json(elements))
|
|
|
|
assert elements[0] == test_elements[0]
|
|
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_by_title_on_partition_org(
|
|
filename="example-docs/README.org",
|
|
):
|
|
elements = partition_org(filename=filename)
|
|
chunk_elements = partition_org(filename, chunking_strategy="by_title")
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|