Merge pull request #64 from abdullahwaqar/feature/61-strip-prefixes

feat(utils): Add strip_prefixes function to remove common question prefix

src/harmony/parsing/util/__init__.py

@@ -1,4 +1,4 @@
-'''
+"""
 MIT License
 
 Copyright (c) 2023 Ulster University (https://www.ulster.ac.uk).
@@ -23,5 +23,42 @@
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 
-'''
+"""
 
+from typing import List, Optional
+
+
+def strip_prefixes(question: str, prefixes: Optional[List[str]] = None) -> str:
+    """
+    Strips specified prefixes from a question string if they are present.
+
+    Args:
+        question (str): The question string from which prefixes need to be removed.
+        prefixes (Optional[List[str]]): A list of prefixes to remove from the question.
+                                        If not provided, a default set of common prefixes is used.
+
+    Returns:
+        str: The question string with the prefix removed, if a match is found;
+             otherwise, the original question.
+
+    Example:
+        question = "Have you ever traveled abroad?"
+        result = strip_prefixes(question)
+        # result -> "traveled abroad?"
+    """
+    default_prefixes = [
+        "Have you ever",
+        "Did you ever",
+        "Do you",
+        "Is it true that",
+        "Would you say",
+        "Can you",
+        "Are you aware that",
+        "Do you think",
+    ]
+    prefixes = prefixes or default_prefixes
+
+    for prefix in prefixes:
+        if question.lower().startswith(prefix.lower()):
+            return question[len(prefix) :].strip()
+    return question