Alex Galarce
47a01e13f0
New Prompt Method (starting with contract effective date) * add todos for Siddhant * moved effective date prompts to prompts.py and added docstring and type hints * moved effective date prompts to prompts.py and added docstring and type hints * fixed conflict Co-authored-by: Alex Galarce <agalarce@aarete.com> * modified contract effective date logic in existing smart chunking * Merged main into chore/contract_effective_date * updated extract_text_from_delimiters function and unit tests for it * Merge remote-tracking branch 'origin/main' into chore/contract_effective_date * added comments to preprocessing_funcs * preprocessing_funcs.py edited online with Bitbucket * utils.py edited online with Bitbucket * add debug line * add NA handling into fix_date_formatting() * add debug print statements * worked on review comments * fixed date checking * fixed date checking and added unit tests * Merged main into chore/contract_effective_date * added logic to handle case when smart chunking returns empty context for effective date * added comments to file_processing.py * optimized imports and removed a TODO * Merged main into chore/contract_effective_date * made prompt changes for effective date * keywords.py edited online with Bitbucket * Removed excess print statements Approved-by: Katon Minhas
52 lines
2.8 KiB
Python
52 lines
2.8 KiB
Python
import pytest
|
|
from enums.delimiters import Delimiter
|
|
from ac_funcs import extract_text_from_delimiters
|
|
|
|
|
|
class TestExtractTextFromDelimiters:
|
|
# Test case for valid inputs
|
|
|
|
def test_pipe_delimiter_match_first_position(self):
|
|
raw_text = "Here is the answer |this is a pipe answer| and |more text.|"
|
|
result = extract_text_from_delimiters(raw_text,delimiter=Delimiter.PIPE,match_index=0)
|
|
assert result == "this is a pipe answer"
|
|
|
|
def test_pipe_delimiter_match_last_position(self):
|
|
raw_text = "Here is the answer |this is a pipe answer| and |more text.|"
|
|
result = extract_text_from_delimiters(raw_text,delimiter=Delimiter.PIPE,match_index=-1)
|
|
assert result == "more text."
|
|
|
|
def test_pipe_delimiter_match_any_position(self):
|
|
raw_text = "|Here| is the answer |this is a pipe answer| and |more text.|"
|
|
result = extract_text_from_delimiters(raw_text,delimiter=Delimiter.PIPE,match_index=1)
|
|
assert result == "this is a pipe answer"
|
|
|
|
def test_backtick_delimiter_match_first_position(self):
|
|
raw_text = "Here is the answer `this is a backtick answer` and `more text.`"
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.BACKTICK, match_index=0)
|
|
assert result == "this is a backtick answer"
|
|
|
|
def test_backtick_delimiter_match_last_position(self):
|
|
raw_text = "Here is the answer `this is a backtick answer` and `more text.`"
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.BACKTICK, match_index=-1)
|
|
assert result == "more text."
|
|
|
|
def test_backtick_delimiter_match_any_position(self):
|
|
raw_text = "`Here` is the answer `this` is a `backtick answer` and `more text.`"
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.BACKTICK, match_index=2)
|
|
assert result == "backtick answer"
|
|
|
|
def test_triple_backtick_delimiter_match_first_position(self):
|
|
raw_text = "Here is the answer ```this is a triple backtick answer``` and more text."
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.TRIPLE_BACKTICK, match_index=0)
|
|
assert result == "this is a triple backtick answer"
|
|
|
|
def test_triple_backtick_delimiter_match_last_position(self):
|
|
raw_text = "Here is the answer ```this``` is a ```triple``` backtick ```answer``` and more text."
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.TRIPLE_BACKTICK, match_index=-1)
|
|
assert result == "answer"
|
|
|
|
def test_triple_backtick_delimiter_match_any_position(self):
|
|
raw_text = "```Here``` is the answer ```this is a triple backtick answer``` and ```more text.```"
|
|
result = extract_text_from_delimiters(raw_text, delimiter=Delimiter.TRIPLE_BACKTICK, match_index=1)
|
|
assert result == "this is a triple backtick answer" |