From 70f382d5b15c852298a3cb74b8e1a31ff14c83fc Mon Sep 17 00:00:00 2001
From: Adam Djellouli <37275728+djeada@users.noreply.github.com>
Date: Wed, 26 Mar 2025 21:21:53 -0100
Subject: [PATCH] Refactor question utils for enhanced performance,
 readability, and extended functionality while preserving backward
 compatibility (#10551)

---
 scripts/question_utils.py | 82 +++++++++++++++------------------------
 1 file changed, 31 insertions(+), 51 deletions(-)

diff --git a/scripts/question_utils.py b/scripts/question_utils.py
index 765ad91..a51fc33 100644
--- a/scripts/question_utils.py
+++ b/scripts/question_utils.py
@@ -7,66 +7,50 @@ from random import choice
 from typing import List
 import re
 
-p = pathlib.Path(__file__).parent.parent.joinpath("README.md")
+README_PATH = pathlib.Path(__file__).parent.parent / "README.md"
+EXERCISES_PATH = pathlib.Path(__file__).parent.parent / "exercises"
+
+DETAILS_PATTERN = re.compile(r"<details>(.*?)</details>", re.DOTALL)
+SUMMARY_PATTERN = re.compile(r"<summary>(.*?)</summary>", re.DOTALL)
+B_PATTERN = re.compile(r"<b>(.*?)</b>", re.DOTALL)
 
 
-def get_file_list():
-    file_list = ""
-    with open(p, "rb") as f:
-        for line in f.readlines():
-            file_list += line.rstrip().decode()
-    return file_list
+def get_file_content() -> str:
+    with README_PATH.open("r", encoding="utf-8") as f:
+        return f.read()
 
 
-def get_question_list(file_list: List[str]) -> list:
-    file_list = re.findall("<details>(.*?)</details>", file_list)
-    questions_list = []
-    for i in file_list:
-        q = re.findall(r"<summary>(.*?)</summary>", i)[0]
-        questions_list.append(q)
-    return questions_list
+def get_question_list(file_content: str) -> List[str]:
+    details = DETAILS_PATTERN.findall(file_content)
+    return [SUMMARY_PATTERN.search(detail).group(1) for detail in details if SUMMARY_PATTERN.search(detail)]
 
 
-def get_answered_questions(question_list: List[str]) -> list:
-    t = []
-    question_list = re.findall("<details>(.*?)</details>", question_list)
-    for i in question_list:
-        q = re.findall(r"<summary>(.*?)</summary>", i)
-        if q and q[0] == "":
-            continue
-        a = re.findall(r"<b>(.*?)</b>", i)
-        if a and a[0] == "":
-            continue
-        else:
-            t.append(q[0])
-    return t
+def get_answered_questions(file_content: str) -> List[str]:
+    details = DETAILS_PATTERN.findall(file_content)
+    answered = []
+    for detail in details:
+        summary_match = SUMMARY_PATTERN.search(detail)
+        b_match = B_PATTERN.search(detail)
+        if summary_match and b_match and summary_match.group(1).strip() and b_match.group(1).strip():
+            answered.append(summary_match.group(1))
+    return answered
 
 
-def get_answers_count() -> List:
-    """
-    Return [answer_questions,all_questions] ,PASS complete. FAIL incomplete.
-    >>> get_answers_count()
-    [463, 463]
-    """
-    ans_questions = get_answered_questions(get_file_list())
-    len_ans_questions = len(ans_questions)
-    all_questions = get_question_list(get_file_list())
-    len_all_questions = len(all_questions)
-    return [len_ans_questions, len_all_questions]
+def get_answers_count() -> List[int]:
+    file_content = get_file_content()
+    answered = get_answered_questions(file_content)
+    all_questions = get_question_list(file_content)
+    return [len(answered), len(all_questions)]
 
 
 def get_challenges_count() -> int:
-    challenges_path = (
-        pathlib.Path(__file__).parent.parent.joinpath("exercises").glob("*.md")
-    )
-    return len(list(challenges_path))
+    return len(list(EXERCISES_PATH.glob("*.md")))
 
 
-# WIP WAITING FEEDBACK
-def get_random_question(question_list: List[str], with_answer=False):
+def get_random_question(question_list: List[str], with_answer: bool = False) -> str:
     if with_answer:
-        return choice(get_answered_questions(question_list))
-    return choice(get_question_list(question_list))
+        return choice(get_answered_questions(get_file_content()))
+    return choice(get_question_list(get_file_content()))
 
 
 """Use this question_list. Unless you have already opened/worked/need the file, then don't or
@@ -74,7 +58,7 @@ you will end up doing the same thing twice.
 eg:
 #my_dir/main.py
 from scripts import question_utils
-print(question_utils.get_answered_questions(question_utils.question_list)
+print(question_utils.get_answered_questions(question_utils.get_question_list(question_utils.get_file_content()))
 >> 123
  # noqa: E501
 """
@@ -83,7 +67,3 @@ if __name__ == "__main__":
     import doctest
 
     doctest.testmod()
-    # print(get_question_list(get_file_list()))
-    # print(get_answered_questions(get_file_list()))
-    # print(get_random_question(get_file_list(),True))
-    # print(get_random_question(get_file_list(),False))