mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-31 01:54:25 +00:00
5eb1466acc
* Apply import sorting ruff . --select I --fix * Remove unnecessary open mode parameter ruff . --select UP015 --fix * Use f-string formatting rather than .format * Remove extraneous parentheses Also use "" instead of str() * Resolve missing trailing commas ruff . --select COM --fix * Rewrite list() and dict() calls using literals ruff . --select C4 --fix * Add () to pytest.fixture, use tuples for parametrize, etc. ruff . --select PT --fix * Simplify code: merge conditionals, context managers ruff . --select SIM --fix * Import without unnecessary alias ruff . --select PLR0402 --fix * Apply formatting via black * Rewrite ValueError somewhat Slightly unrelated to the rest of the PR * Apply formatting to tests via black * Update expected exception message to match 0d81564 * Satisfy E501 line too long in test * Update changelog & version * Add ruff to make tidy and test deps * Run 'make tidy' * Update changelog & version * Update changelog & version * Add ruff to 'check' target Doing so required me to also fix some non-auto-fixable issues. Two of them I fixed with a noqa: SIM115, but especially the one in __init__ may need some attention. That said, that refactor is out of scope of this PR.
22 lines
566 B
Python
22 lines
566 B
Python
from typing import List, Tuple
|
|
|
|
|
|
def mock_sent_tokenize(text: str) -> List[str]:
|
|
sentences = text.split(".")
|
|
return sentences[:-1] if text.endswith(".") else sentences
|
|
|
|
|
|
def mock_word_tokenize(text: str) -> List[str]:
|
|
return text.split(" ")
|
|
|
|
|
|
def mock_pos_tag(text: str) -> List[Tuple[str, str]]:
|
|
tokens = mock_word_tokenize(text)
|
|
pos_tags: List[Tuple[str, str]] = []
|
|
for token in tokens:
|
|
if token.lower() == "ask":
|
|
pos_tags.append((token, "VB"))
|
|
else:
|
|
pos_tags.append((token, ""))
|
|
return pos_tags
|