Files
doczyai-pipelines/fieldExtraction/tests/test_exhibit_chunk_mapping.py
T
Katon Minhas c4e519894b Merged in refactor/one-time-io (pull request #648)
Refactor/one time io

* Delete client work

* Streamline imports

* Fix list class

* Update tests

* Clear code funcs test

* Fix unit tests

* Single read code funcs

* Single-read model

* Single-load embeddings

* Successful E2E test

* update unit tests

* Update importsg

* Reload poetry.lock

* remove old exhibit header function

* Remove aarete_derived generic function

* remove align and format tables

* Remove strings to dict

* references

* Clear code

* Move preprocessing_funcs

* remove keywords

* refactor postprocessing_funcs

* Pass unit test - remove qa_qc directory

* Black and isort

* remove print


Approved-by: Alex Galarce
2025-08-05 20:46:19 +00:00

44 lines
1.1 KiB
Python

from src.investment.preprocessing_funcs import chunk_by_exhibit
def test1():
"""Test non-empty text_dict with empty exhibit_pages."""
text_dict = {"1": "This", "2": "is", "3": "an", "4": "exhibit", "5": "test"}
exhibit_pages = []
assert chunk_by_exhibit(text_dict, exhibit_pages) == {
"1": "1",
"2": "2",
"3": "3",
"4": "4",
"5": "5",
}
def test2():
"""Test when exhibit_pages contains some keys that are also in text_dict."""
text_dict = {"1": "Welcome", "2": "to", "3": "the", "4": "exhibit"}
exhibit_pages = ["1", "2", "4"]
expected_output = {"1": "1", "2": "2", "3": "2", "4": "4"}
assert chunk_by_exhibit(text_dict, exhibit_pages) == expected_output
def test3():
"""Test multiple exhibit pages with transitions between them."""
text_dict = {
"1": "Page 1",
"2": "Page 2",
"3": "Page 3",
"4": "Page 4",
"5": "Page 5",
}
exhibit_pages = ["2", "4"]
expected_output = {"1": "0", "2": "2", "3": "2", "4": "4", "5": "4"}
assert chunk_by_exhibit(text_dict, exhibit_pages) == expected_output
test1()
test2()
test3()