Spaces:
Sleeping
Sleeping
| """Apply config/course.yaml classification rules to file paths.""" | |
| from __future__ import annotations | |
| import fnmatch | |
| import re | |
| from dataclasses import dataclass | |
| from typing import Optional | |
| class Classification: | |
| kind: str | |
| topic: str | |
| visibility: str | |
| student_access: bool | |
| release_status: str | |
| order: Optional[int] = None | |
| lecture_date: Optional[str] = None | |
| def classify_path(path: str, rules: dict) -> Optional[Classification]: | |
| """Classify a repo-relative POSIX path against the loaded course.yaml rules. | |
| Returns None if no rule matches (caller should record as unmatched diagnostic). | |
| """ | |
| for rule in rules["classification_rules"]: | |
| if not fnmatch.fnmatchcase(path, rule["match"]): | |
| continue | |
| topic_raw = _extract(rule.get("topic_extract"), path) | |
| if topic_raw is None: | |
| topic = "_unknown" | |
| else: | |
| topic = rules.get("topic_name_overrides", {}).get( | |
| topic_raw, _normalize_topic(topic_raw) | |
| ) | |
| order = _extract_int(rule.get("order_extract"), path) | |
| lecture_date = _extract(rule.get("lecture_date_extract"), path) | |
| return Classification( | |
| kind=rule["kind"], | |
| topic=topic, | |
| visibility=rule["visibility"], | |
| student_access=rule["student_access"], | |
| release_status=rule["release_status"], | |
| order=order, | |
| lecture_date=lecture_date, | |
| ) | |
| return None | |
| def _extract(pattern: Optional[str], path: str) -> Optional[str]: | |
| if not pattern: | |
| return None | |
| m = re.search(pattern, path) | |
| return m.group(1) if m else None | |
| def _extract_int(pattern: Optional[str], path: str) -> Optional[int]: | |
| raw = _extract(pattern, path) | |
| return int(raw) if raw is not None else None | |
| def _normalize_topic(raw: str) -> str: | |
| """Single-cap-boundary Camel/Pascal → snake_case lowercase. | |
| Consecutive capitals (e.g., 'URL', 'XMLParser') are NOT handled — | |
| use ``topic_name_overrides`` in course.yaml to map such inputs. | |
| """ | |
| s = re.sub(r"(?<!^)(?=[A-Z])", "_", raw).lower() | |
| return s | |