fix: resolve pre-existing test failures and improve coverage (#833)

tests/test_basic.py

@@ -29,10 +29,14 @@
     validate_recommendation_inputs,
     parse_skills,
     score_single_project,
-    WEIGHT_LEVEL,
-    WEIGHT_INTEREST,
-    WEIGHT_TIME,
+    SCORING_WEIGHTS,
+    VALID_LEVELS,
+    VALID_TIME_AVAILABILITY,
 )
+
+WEIGHT_LEVEL    = SCORING_WEIGHTS["level"]
+WEIGHT_INTEREST = SCORING_WEIGHTS["interest"]
+WEIGHT_TIME     = SCORING_WEIGHTS["time"]
 from app import app, internal_server_error
 
 

utils/recommender.py

@@ -29,6 +29,24 @@
 }
 
 def parse_skills(skills_string):
+    """
+    Convert a raw skills string into a normalized lowercase list.
+    Accepts either a JSON array (e.g. '["Python","React"]') or a
+    comma-separated string (e.g. "JS, HTML5, CSS3").
+
+    Example:
+        '["Python","React"]' -> ["python", "react"]
+        "JS, HTML5, CSS3"   -> ["javascript", "html", "css"]
+    """
+    stripped = skills_string.strip()
+    if stripped.startswith("["):
+        try:
+            parsed = json.loads(stripped)
+            if isinstance(parsed, list):
+                raw_skills = [str(s).strip().lower() for s in parsed if str(s).strip()]
+                return [SKILL_ALIASES.get(skill, skill) for skill in raw_skills]
+        except (json.JSONDecodeError, ValueError):
+            pass
     raw_skills = [
         s.strip().lower()
         for s in skills_string.split(",")
@@ -103,15 +121,27 @@ def ml_similarity_score(project, user_skills, level, interest, time_availability
     return _cosine_similarity(user_vector, project_vector)
 
 def score_single_project(project, user_skills, level, interest, time_availability):
+    TIME_RANKS = ["low", "medium", "high"]
+
+    user_time    = time_availability.strip().lower()
+    project_time = project.get("time", "").strip().lower()
+
+    # If the project needs more time than the user has, exclude it.
+    if project_time not in TIME_RANKS or user_time not in TIME_RANKS:
+        return 0
+    if TIME_RANKS.index(project_time) > TIME_RANKS.index(user_time):
+        return 0
+
     score = 0
 
     # Compare user's skills against the project's required skills
     project_skills = [SKILL_ALIASES.get(s.lower(), s.lower()) for s in project.get("skills", [])]
-    # Count how many user skills overlap with the
-    # skills required by the current project.
     matched_skills = sum(1 for skill in user_skills if skill in project_skills)
-
-    score += matched_skills * SCORING_WEIGHTS["skill"]
+    if project_skills:
+        coverage = matched_skills / len(project_skills)
+        score += matched_skills * SCORING_WEIGHTS["skill"] * coverage
+    else:
+        score += matched_skills * SCORING_WEIGHTS["skill"]
 
     if project.get("level", "").lower() == level.lower():
         score += SCORING_WEIGHTS["level"]
@@ -131,8 +161,7 @@ def score_single_project(project, user_skills, level, interest, time_availabilit
 def get_recommendations(skills_string, level, interest, time_availability):
     user_skills = parse_skills(skills_string)
     all_projects = load_all_projects()
-
-    scored = []
+    scored_projects = []
     for project in all_projects:
         rule_score = score_single_project(
             project,
@@ -141,7 +170,6 @@ def get_recommendations(skills_string, level, interest, time_availability):
             interest,
             time_availability,
         )
-
         similarity_score = ml_similarity_score(
             project,
             user_skills,
@@ -150,21 +178,20 @@ def get_recommendations(skills_string, level, interest, time_availability):
             time_availability,
             all_projects,
         )
-
-    # Sort projects in descending order so the
-    # most relevant recommendations appear first.
-    scored_projects.sort(key=lambda item: (item["score"], item["project"].get("id", 0)), reverse=True)
         final_score = rule_score + similarity_score
-
         if final_score > 0:
             scored_projects.append({
                 "project": project,
                 "score": final_score,
             })
+    # Sort projects in descending order so the
+    # most relevant recommendations appear first.
+    scored_projects.sort(key=lambda item: (item["score"], item["project"].get("id", 0)), reverse=True)
+    return [item["project"] for item in scored_projects[:MAX_RESULTS]]
 
-    scored_projects.sort(key=lambda item: item["score"], reverse=True)
+VALID_LEVELS = ["beginner", "intermediate", "advanced"]
+VALID_TIME_AVAILABILITY = ["low", "medium", "high"]
 
-    return [item["project"] for item in scored_projects[:MAX_RESULTS]]
 
 def validate_recommendation_inputs(skills, level, interest, time_availability):
     errors = []
@@ -179,8 +206,8 @@ def validate_recommendation_inputs(skills, level, interest, time_availability):
     elif level.strip().lower() not in VALID_LEVELS:
         errors.append("Invalid experience level. Choose Beginner, Intermediate, or Advanced.")
 
-    if not interest or not isinstance(interest, str) or interest.strip().lower() not in VALID_INTERESTS:
-        errors.append("Please select a valid area of interest.")
+    if not interest or not isinstance(interest, str) or not interest.strip():
+        errors.append("Please select an area of interest.")
 
     if not time_availability or not time_availability.strip():
         errors.append("Please select your time availability.")