Organize submission archive downloaded from Gradescope using student’s names

gradescope-organizer.py

#!/usr/bin/env python3

import itertools
import os
import unicodedata

# pip3 install -U PyYAML
import yaml

# Windows disallows the following characters in filenames: "*/:<>?\|
# as well as anything between U+0000 and U+001F.
# Additionally we disallow these to prevent ambiguity: .&()
FORBIDDEN_CHARS = set('"&()*./:<>?\\|')
# Windows disallows these filenames because they map to I/O ports.
# Any program trying to use these filenames may freeze or behave strangely.
# We need to prevent students from naming themselves such for security reasons.
FORBIDDEN_NAMES = {'aux', 'com1', 'com2', 'com3', 'com4', 'com5', 'com6', 'com7', 'com8', 'com9', 'con', 'lpt1', 'lpt2', 'lpt3', 'lpt4', 'lpt5', 'lpt6', 'lpt7', 'lpt8', 'lpt9', 'nul', 'prn'}


def main() -> None:
    print('Loading submission_metadata.yml... ', end='', flush=True)
    with open('submission_metadata.yml', encoding='UTF-8') as f:
        data = dict(yaml.safe_load(f))
    print(f'{len(data)} submissions loaded.')

    print('Creating renaming plan... ', end='', flush=True)
    #
    # This list comprehension one-liner creates a name map from submission ID to actual submitter's name.
    #
    # 1. If a submitter's name contains FORBIDDEN_CHARS or anything between U+0000 and U+001F, replace them with '_'.
    # 2. If a submission has multiple submitters, combine their names into one name with ' & '.
    # 3. If the resulting name is FORBIDDEN_NAMES or have case-insensitive duplicates, append with ' (1)', ' (2)', etc.
    #
    renaming_plan = sorted((id, names if len(submissions) == 1 and names_fold not in FORBIDDEN_NAMES else f'{names} ({names_idx + 1})') for names_fold, submissions in itertools.groupby(sorted((names_fold, id, names) for id, submission in data.items() for names in [' & '.join(''.join('_' if c < ' ' or c in FORBIDDEN_CHARS else c for c in name) for submitters in submission[':submitters'] for name in [unicodedata.normalize('NFC', str(submitters[':name'] or id))])] for names_fold, id in [(unicodedata.normalize('NFKD', unicodedata.normalize('NFKD', unicodedata.normalize('NFD', names).casefold()).casefold()), str(id))]), lambda x: x[0]) for submissions in [list(submissions)] for names_idx, (_, id, names) in enumerate(submissions))
    print('Done.', flush=True)

    for move_from, move_to in renaming_plan:
        print(f'{move_from} -> {move_to}', end='')
        try:
            os.rename(move_from, move_to)
        except FileNotFoundError:
            print(' (skipped)')
        except Exception as e:
            print(f' (failed: {e})')
        else:
            print()


if __name__ == '__main__':
    main()

quicklook-autograder.py

#!/usr/bin/env python3

from __future__ import annotations
import sys
import os
import pickle
from typing import Any, Optional

# pip3 install -U rich
import rich.box
import rich.console
import rich.table
from rich.markup import escape

# pip3 install -U PyYAML
import yaml


def failure_filter(tests: list[dict[str, Any]]) -> list[dict[str, Any]]:
    return [test for test in tests if test['status'] != 'passed']


def main(argv: list[str]) -> None:
    if 'MANPAGER' not in os.environ and 'PAGER' not in os.environ:
        os.environ['PAGER'] = 'less -c -r'
    console = rich.console.Console(highlight=False)
    if len(argv) == 0:
        skip_to_name: Optional[str] = None
    else:
        skip_to_name = ' '.join(argv).strip('/')
    messages: list[rich.console.RenderableType] = []
    try:
        with console.status('Loading [blue]submission_metadata.yml.cache[/]...'):
            with open('submission_metadata.yml.cache', 'rb') as f:
                data = dict(pickle.load(f))
        messages.append(f'Loaded [blue]{len(data)}[/] submissions from [blue]submission_metadata.yml.cache[/].')
    except FileNotFoundError:
        with console.status('Loading [blue]submission_metadata.yml[/]...'):
            with open('submission_metadata.yml', encoding='UTF-8') as f:
                data = dict(yaml.safe_load(f))
        messages.append(f'Loaded [blue]{len(data)}[/] submissions from [blue]submission_metadata.yml[/].')
        with console.status('Saving to [blue]submission_metadata.yml.cache[/]...'):
            with open('submission_metadata.yml.cache', 'wb') as f:
                pickle.dump(data, f)
    submissions = list(data.items())
    missing_tests = [(submission_id, submission) for submission_id, submission in submissions if not submission[':results'].get('tests')]
    if len(missing_tests) != 0:
        messages.append('')
        messages.append('[red]These submissions have tests missing:[/]')
        table = rich.table.Table(box=None, padding=0)
        table.add_column(width=4)
        table.add_column('Submission ID', no_wrap=True)
        table.add_column(width=1)
        table.add_column('Submitter')
        for submission_id, submission in missing_tests:
            table.add_row(None, escape(submission_id), None, '[grey46], [/]'.join(f'[blue]{escape(str(submitter[":name"]))}[/]' for submitter in submission[':submitters']))
        messages.append(table)
        messages.append('')
    start_idx = 0
    for i, (submission_id, submission) in enumerate(submissions):
        if skip_to_name is not None and skip_to_name not in (str(submitter[':name']) for submitter in submission[':submitters']):
            continue
        if skip_to_name is not None:
            start_idx = i
            messages.append(f'Skip to name: [blue]{escape(skip_to_name)}[/]')
            skip_to_name = None
    if skip_to_name is None:
        del submissions[:start_idx]
    else:
        messages.append(f'Can’t skip to name: [red]{escape(skip_to_name)}[/]')
        submissions = []
    for i, (submission_id, submission) in enumerate(submissions):
        with console.pager(styles=True, links=True):
            if len(messages) != 0:
                for message in messages:
                    console.print(message)
                messages = []
            console.rule(f'[blue]{start_idx + i + 1}[/][grey46] / [/]{len(submissions) + start_idx}')
            table = rich.table.Table(box=None, padding=0, show_header=False)
            table.add_column(no_wrap=True, style='bold grey0')
            table.add_column()
            table.add_row('Submission ID: ', escape(submission_id))
            table.add_row('Submitter: ', '[grey46], [/]'.join(f'[blue]{escape(str(submitter[":name"]))}[/]' for submitter in submission[':submitters']))
            tests = submission[':results'].get('tests', [])
            failed_tests = failure_filter(tests)
            if len(failed_tests) == 0:
                table.add_row('Tests: ', f'[green]All {len(tests)} tests passed.[/]')
            else:
                for test in failed_tests:
                    table.add_row('Failed Test: ', f'[red]{escape(str(test["name"]))}[/]')
                    if test['output']:
                        table.add_row(None, escape(str(test['output']).lstrip('\n').rstrip()))
            console.print(table)
            console.rule(f'[blue]{start_idx + i + 1}[/][grey46] / [/]{len(submissions) + start_idx}')
            console.print('Press [blue]Q[/] to proceed...')
    for message in messages:
        console.print(message)


if __name__ == '__main__':
    main(sys.argv[1:])