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

fieldExtraction/tests/string_utils_test.py

@@ -0,0 +1,53 @@
+import pytest
+
+from src.enums.delimiters import Delimiter
+from src.utils.string_utils 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"