Amanda Cameron 1fb464235a
chore: Table chunking (#1540)
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>
2023-10-03 09:40:34 -07:00

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