Merged in task/unit-tests-investment-and-client (pull request #354)

Task/unit tests investment and client

* move io_utils.py

* add __init__.py

* refactor: move string_funcs and update import paths to use utils namespace

* rename string_funcs to string_utils

* move and rename table_utils.py

* refactor: rename claude_funcs to llm_utils in multiple files

* update unit tests

* added unit tests for src/string_utils.py

* added unit tests for src/table_utils.py

* added unit tests for src/llm_utils.py

* added unit tests for src/io_utils.py

* Merge branch 'main' into task/unit-tests-investment-and-client; TODO: fix unit tests

* Unit tests to fix

* fix unit tests

* fix invalid references

* add unit tests for preprocessing_funcs.py

* move pytest-mock to test dependencies

* Merge remote-tracking branch 'origin/main' into task/unit-tests-investment-and-client

* add tests/string_utils_test.py

* removed filename parameters for a few functions

* save postprocessing_funcs_test midway

* save postprocessing_funcs_test

* postprocessing_funcs unit tests complete

* Merge branch 'main' into task/unit-tests-investment-and-client


Approved-by: Katon Minhas

fieldExtraction/tests/string_utils_test.py

@@ -5,10 +5,9 @@ import src.utils.llm_utils as llm_utils
 import numpy as np
 import pandas as pd
 
-
 from src.enums.delimiters import Delimiter
 
-class TestExtractTextFromDelimiters:
+class TestStringUtils:
     @pytest.mark.parametrize("raw_text, delimiter, match_index, expected", [
         ("Here is the answer |this is a pipe answer| and |more text.|", Delimiter.PIPE, 0, "this is a pipe answer"),
         ("Here is the answer |this is a pipe answer| and |more text.|", Delimiter.PIPE, -1, "more text."),
@@ -24,7 +23,6 @@ class TestExtractTextFromDelimiters:
         result = extract_text_from_delimiters(raw_text, delimiter, match_index)
         assert result == expected
 
-class TestJsonParsingSearch:
     @pytest.mark.parametrize("response_text, field_list, expected", [
         ('{"name": "John", "age": "30", "city": "New York"}', ["name", "age", "city"], {"name": "John", "age": "30", "city": "New York"}),
         ('{"name": "John", "city": "New York"}', ["name", "age", "city"], {"name": "John", "city": "New York"}),
@@ -36,7 +34,6 @@ class TestJsonParsingSearch:
     def test_json_parsing_search(self, response_text, field_list, expected):
         assert json_parsing_search(response_text, field_list) == expected
 
-class TestSecondaryStringToDict:
     @pytest.fixture
     def mock_invoke_claude(self, mocker):
         return mocker.patch.object(llm_utils, 'invoke_claude')
@@ -79,7 +76,6 @@ class TestSecondaryStringToDict:
         assert result == {}
         mock_invoke_claude.assert_called_once()
 
-class TestPrimaryStringToDict:
     @pytest.fixture
     def mock_secondary_string_to_dict(self, mocker):
         return mocker.patch.object(utils.string_utils, "secondary_string_to_dict")
@@ -164,7 +160,6 @@ class TestPrimaryStringToDict:
         assert result == expected_output
         assert mock_secondary_string_to_dict.call_count == 4
 
-class TestContainsReimbursement:
     @pytest.mark.parametrize("text, page, expected", [
         ({"1": "This page contains a 10% reimbursement schedule.", "2": "No relevant content here."}, "1", True),
         ({"1": "This page has no relevant content.", "2": "Still no relevant content here."}, "1", False),
@@ -184,7 +179,6 @@ class TestContainsReimbursement:
         captured = capsys.readouterr()
         assert "contains_reimbursement - Invalid data type" in captured.out
 
-class TestIsEmpty:
     @pytest.mark.parametrize("value, expected", [
         (None, True),
         ("", True),
@@ -199,4 +193,4 @@ class TestIsEmpty:
     ])
     def test_is_empty(self, value, expected):
         result = is_empty(value)
-        assert result == expected
+        assert result == expected