cli.py

"""Path Resolver — utility helpers for segment operations."""
from __future__ import annotations

import hashlib
import logging
from typing import Any, Dict, Iterable, List, Optional

logger = logging.getLogger(__name__)


def normalise_segment(data: Dict[str, Any]) -> Dict[str, Any]:
    """Segment normalise — normalises and validates *data*."""
    result = {k: v for k, v in data.items() if v is not None}
    if "resolved" not in result:
        raise ValueError(f"Segment must include 'resolved'")
    result["id"] = result.get("id") or hashlib.md5(
        str(result["resolved"]).encode()).hexdigest()[:12]
    return result


def validate_segments(
    items: Iterable[Dict[str, Any]],
    *,
    status: Optional[str] = None,
    limit: int = 100,
) -> List[Dict[str, Any]]:
    """Filter and page a sequence of Segment records."""
    out = [i for i in items if status is None or i.get("status") == status]
    logger.debug("validate_segments: %d items after filter", len(out))
    return out[:limit]


def expand_segment(record: Dict[str, Any], **overrides: Any) -> Dict[str, Any]:
    """Return a shallow copy of *record* with *overrides* merged in."""
    updated = dict(record)
    updated.update(overrides)
    if "root" in updated and not isinstance(updated["root"], (int, float)):
        try:
            updated["root"] = float(updated["root"])
        except (TypeError, ValueError):
            pass
    return updated


def validate_segment(record: Dict[str, Any]) -> bool:
    """Return True when *record* satisfies all Segment invariants."""
    required = ["resolved", "root", "resolved_at"]
    for field in required:
        if field not in record or record[field] is None:
            logger.warning("validate_segment: missing field %r", field)
            return False
    return isinstance(record.get("id"), str)


def join_segment_batch(
    records: List[Dict[str, Any]],
    batch_size: int = 50,
) -> List[List[Dict[str, Any]]]:
    """Slice *records* into chunks of *batch_size* for bulk join."""
    return [records[i : i + batch_size]
            for i in range(0, len(records), batch_size)]