Files
doczyai-pipelines/fieldExtraction/tests/test_chunking.py
T
Alex Galarce 53b38ea15c Merged in refactor/split-investment-and-client (pull request #347)
Refactor/split investment and client

* refactor: clean up tests

* Renamed tests/qcqa to tests/qa_qc for consistency

* comment out faulty test - see docstring note at top

* split to client/investment

* add __init__.py to investment and client to avoid mypy confusion

* fix imports

* update imports for consistency across investment module

* move back to one config

* try changing import to relative

* add init.py to src

* try relative import

* try one more sys.path.append

* fix path for client main

* fix imports in file_processing

* make prompts common

* move keywords out to `src`

* move smart_chunking_funcs to `src`

* fix mypy error

* start moving to explicit imports

* remove old keywords and fix imports for keywords and prompts

* change all imports to full paths

* fix unit tests

* add readme for new way of running things

* isort after all that import work

* remove unused sys.path.append from some tests


Approved-by: Katon Minhas
2025-01-08 21:59:47 +00:00

194 lines
5.3 KiB
Python

import pytest
from src.preprocessing_funcs import smart_chunk_ac
test_chunk_dict_term = {
"1": "NA",
"2": "Termination",
"3": "NA",
"4": "NA",
}
test_full_text_term = '\n'.join([v for v in test_chunk_dict_term.values()])
test_late_paid_claims = {
"1": "NA",
"2": "LATE PAYMENT", # try lowercase
"3": "NA",
"4": "NA",
"10": "NA",
"11": "LATE PAID",
"12": "NA",
}
test_full_text_late_paid_claims = '\n'.join([v for v in test_late_paid_claims.values()])
test_keyword_mappings = {
"or_1": {
"methodology": "or",
"keywords": ["kw1", "kw2", "kw3"],
"case_sensitive": False,
},
"or_2": {"methodology": "or", "keywords": ["kw4"], "case_sensitive": False},
"hierarchy_1": {
"methodology": "hierarchy",
"keywords": ["h5", "h6"],
"case_sensitive": False,
},
"cs_or_1": {
"methodology": "or",
"keywords": ["KW1", "kw2", "kw3"],
"case_sensitive": True,
},
"and": {"methodology": "and", "keywords": ["KW1", "KW2"], "case_sensitive": False},
"regex": {
"methodology": "regex",
"regex": r"\b\d{2}-?\d{7}\b",
"case_sensitive": True,
"keywords": ["KW1", "KW2"],
},
}
case_1 = {
"1": "NA",
"2": "kw1",
"3": "NA",
"4": "h6",
"5": "NA",
"6": "kw3",
}
case_2 = {
"1": "NA",
"2": "h6",
"3": "NA",
"4": "kw2",
"10": "NA",
"11": "h5",
"12": "NA",
"15": "kw4",
}
case_3 = {
"1": "NA",
"2": "KW1",
"3": "NA",
"4": "h6",
"5": "NA",
"6": "kw3",
}
case_4 = {
"1": "NA",
"2": "KW1",
"3": "NA",
"4": "KW1KW2",
"5": "NA",
"6": "kw3",
}
case_5 = {
"1": "NA",
"2": "12-3456789",
"3": "987654321",
"4": "Next",
"5": "1234567-89",
"6": "kw3",
}
def test_smart_chunk_term():
assert smart_chunk_ac(text_dict=test_chunk_dict_term,
contract_text=test_full_text_term)["term_group"] == "\n".join(["NA", "Termination", "NA"])
def test_smart_chunk_late_paid():
assert smart_chunk_ac(text_dict=test_late_paid_claims,
contract_text=test_full_text_late_paid_claims)[
"LATE_PAID_CLAIMS_LANGUAGE"
] == "\n".join(["NA", "LATE PAID", "NA"])
def test_or_1():
assert smart_chunk_ac(text_dict=case_1,
contract_text='\n'.join([v for v in case_1.values()]),
keyword_mappings=test_keyword_mappings)[
"or_1"
] == "\n".join(["NA", "kw1", "NA", "NA", "kw3"])
assert smart_chunk_ac(text_dict=case_2,
contract_text='\n'.join([v for v in case_2.values()]),
keyword_mappings=test_keyword_mappings)[
"or_1"
] == "\n".join(["NA", "kw2"])
def test_or_2():
assert smart_chunk_ac(text_dict=case_1,
contract_text='\n'.join([v for v in case_1.values()]),
keyword_mappings=test_keyword_mappings)[
"or_2"
] == "\n".join([])
assert smart_chunk_ac(text_dict=case_2,
contract_text='\n'.join([v for v in case_2.values()]),
keyword_mappings=test_keyword_mappings)[
"or_2"
] == "\n".join(["kw4"])
def test_case_sensitive_or_1():
assert smart_chunk_ac(text_dict=case_1,
contract_text='\n'.join([v for v in case_1.values()]),
keyword_mappings=test_keyword_mappings)[
"cs_or_1"
] == "\n".join(["NA", "kw3"])
assert smart_chunk_ac(text_dict=case_3,
contract_text='\n'.join([v for v in case_3.values()]),
keyword_mappings=test_keyword_mappings)[
"cs_or_1"
] == "\n".join(["NA", "KW1", "NA", "NA", "kw3"])
def test_hierarchy_1():
assert smart_chunk_ac(text_dict=case_1,
contract_text='\n'.join([v for v in case_1.values()]),
keyword_mappings=test_keyword_mappings)[
"hierarchy_1"
] == "\n".join(["NA", "h6", "NA"])
assert smart_chunk_ac(text_dict=case_2,
contract_text='\n'.join([v for v in case_2.values()]),
keyword_mappings=test_keyword_mappings)[
"hierarchy_1"
] == "\n".join(["NA", "h5", "NA"])
def test_and():
assert smart_chunk_ac(text_dict=case_4,
contract_text='\n'.join([v for v in case_4.values()]),
keyword_mappings=test_keyword_mappings)[
"and"
] == "\n".join(["NA", "KW1KW2", "NA"])
def test_regex():
assert smart_chunk_ac(text_dict=case_5,
contract_text='\n'.join([v for v in case_5.values()]),
keyword_mappings=test_keyword_mappings)[
"regex"
] == "\n".join(["NA", "12-3456789", "987654321", "Next"])
def test_undefined_methodology():
with pytest.raises(ValueError):
smart_chunk_ac(
text_dict=case_1,
contract_text='\n'.join([v for v in case_1.values()]),
keyword_mappings={
"e1": {
"methodology": "Not a real methodology",
"keywords": ["NA"],
"case_sensitive": True,
}
},
)