sql-assignment-generator 0.0.12__tar.gz → 0.0.14__tar.gz

{sql_assignment_generator-0.0.12 → sql_assignment_generator-0.0.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql_assignment_generator
-Version: 0.0.12
+Version: 0.0.14
 Summary: This project generates SQL assignments based on common mistakes made by learners.
 Project-URL: Repository, https://github.com/DavidePonzini/sql_assignment_generator
 Project-URL: Documentation, https://sql-assignment-generator.readthedocs.io/en/latest/index.html

{sql_assignment_generator-0.0.12 → sql_assignment_generator-0.0.14}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sql_assignment_generator"
-version = "0.0.12"
+version = "0.0.14"
 authors = [
   { name="Davide Ponzini", email="davide.ponzini95@gmail.com" },
 ]

{sql_assignment_generator-0.0.12 → sql_assignment_generator-0.0.14}/src/sql_assignment_generator/__init__.py

@@ -24,6 +24,8 @@ def generate_assignment(
         *,
         shuffle_exercises: bool = False,
         naming_func: Callable[[SqlErrors, DifficultyLevel], str] = lambda error, difficulty: f'{error.name} - {difficulty.name}',
+        max_dataset_attempts: int = 3,
+        max_exercise_attempts: int = 3,
         max_unique_attempts: int = 3,
         max_workers: int | None = None
     ) -> Assignment:
@@ -39,28 +41,37 @@ def generate_assignment(
         domain (str | None): The domain for the assignments. If None, a random domain will be selected.
         shuffle_exercises (bool): Whether to shuffle exercises to prevent ordering bias (shuffles input order).
         naming_func (Callable[[SqlErrors, DifficultyLevel], str]): Generates exercise titles.
+        max_dataset_attempts (int): Maximum retries for generating a valid dataset before skipping.
+        max_exercise_attempts (int): Maximum retries for generating a valid exercise before skipping.
         max_unique_attempts (int): Maximum retries to avoid duplicate solutions per (error, difficulty).
         max_workers (int | None): Thread pool size. If None, uses ThreadPoolExecutor default.
 
     Returns:
         Assignment: The generated assignment (stable order).
     '''
+    
+    # filter only supported errors
+    supported_errors: list[tuple[SqlErrors, DifficultyLevel]] = []
+    for error, difficulty in errors:
+        if error in ERROR_REQUIREMENTS_MAP:
+            supported_errors.append((error, difficulty))
+        else:
+            dav_tools.messages.warning(f'Skipping unsupported error: {error.name}')
 
-    dav_tools.messages.info(f'Starting assignment generation for {len(errors)} exercises...')
+    if not supported_errors:
+        raise ValueError('No supported errors provided for assignment generation.')
 
     if domain is None:
         domain = random_domain()
 
     if shuffle_exercises:
         random.shuffle(errors)
+    
+
+    dav_tools.messages.info(f'Starting assignment generation for {len(supported_errors)} exercises (out of {len(errors)} requested)')
 
     # convert SqlErrors -> SqlErrorRequirements, keeping difficulty levels
-    requirements: list[tuple[SqlErrors, SqlErrorRequirements, DifficultyLevel]] = []
-    for error, difficulty in errors:
-        if error not in ERROR_REQUIREMENTS_MAP:
-            raise NotImplementedError(f'Error requirements not implemented for error: {error.name}')
-        
-        requirements.append((error, ERROR_REQUIREMENTS_MAP[error], difficulty))
+    requirements: list[tuple[SqlErrors, SqlErrorRequirements, DifficultyLevel]] = [(error, ERROR_REQUIREMENTS_MAP[error], difficulty) for error, difficulty in supported_errors]
 
     # initialize requirements and extra details
     dataset_requirements: list[SchemaConstraint] = []
@@ -75,7 +86,7 @@ def generate_assignment(
     dataset_extra_details = list(set(dataset_extra_details))  # deduplicate details
 
     dav_tools.messages.info(f'Generating dataset for domain: {domain}')
-    dataset = Dataset.generate(domain, dataset_requirements, dataset_extra_details)
+    dataset = Dataset.generate(domain, dataset_requirements, dataset_extra_details, max_attempts=max_dataset_attempts)
 
     generated_solutions_hashes: set[str] = set()
     hashes_lock = threading.Lock()
@@ -98,7 +109,7 @@ def generate_assignment(
 
         for attempt in range(max_unique_attempts):
             try:
-                generated_exercise = Exercise.generate(error, difficulty, constraints, extra_details, dataset=dataset, title=title)
+                generated_exercise = Exercise.generate(error, difficulty, constraints, extra_details, dataset=dataset, title=title, max_attempts=max_exercise_attempts)
             except ExerciseGenerationError:
                 with log_lock:
                     dav_tools.messages.warning(f'{title}: Skipping exercise generation for {error.name} due to validation failures.')
@@ -126,7 +137,7 @@ def generate_assignment(
         return (idx, None)
 
     # Pre-allocate so we can preserve ordering no matter completion order.
-    ordered_results: list[Exercise | None] = [None] * len(errors)
+    ordered_results: list[Exercise | None] = [None] * len(supported_errors)
 
     if max_workers == 1:
         for idx, (error, requirement, difficulty) in enumerate(requirements):
@@ -144,10 +155,10 @@ def generate_assignment(
 
     exercises: list[Exercise] = [ex for ex in ordered_results if ex is not None]
 
-    if len(exercises) < len(errors):
-        dav_tools.messages.warning(f'Finished generating exercises with some failures. Generated {len(exercises)} out of {len(errors)} requested.')
+    if len(exercises) < len(supported_errors):
+        dav_tools.messages.warning(f'Finished generating exercises with some failures. Generated: {len(exercises)}. Unsupported: {len(errors) - len(supported_errors)}. Failed: {len(supported_errors) - len(exercises)}.')
     else:
-        dav_tools.messages.success(f'Successfully generated all {len(exercises)} exercises.')
+        dav_tools.messages.success(f'Successfully generated all {len(exercises)} exercises. Unsupported: {len(errors) - len(supported_errors)}.')
 
     return Assignment(
         dataset=dataset,

{sql_assignment_generator-0.0.12 → sql_assignment_generator-0.0.14}/test.py

@@ -14,6 +14,7 @@ if __name__ == '__main__':
     # change these values as needed
     domain = None
     errors = [
+        (SqlErrors.SYN_22_OMITTING_THE_SEMICOLON, DifficultyLevel.EASY),
         (SqlErrors.SYN_2_AMBIGUOUS_COLUMN, DifficultyLevel.EASY),
     ]*3