"""Convert YAML files to key-path sequences for BEX grammar inference."""

from pathlib import Path
import yaml


def yaml_to_keypath_sequence(data, prefix=""):
    """Convert parsed YAML data to a sequence of key paths (DFS traversal).

    Each leaf (scalar) emits its full key path as a symbol.
    Lists use a generic `[]` marker (no indices).
    Values are NOT included — only key paths.
    """
    seq = []
    if isinstance(data, dict):
        for key, value in data.items():
            path = f"{prefix}.{key}" if prefix else key
            if isinstance(value, (dict, list)):
                seq.extend(yaml_to_keypath_sequence(value, path))
            else:
                seq.append(path)
    elif isinstance(data, list):
        for item in data:
            list_prefix = f"{prefix}[]" if prefix else "[]"
            if isinstance(item, (dict, list)):
                seq.extend(yaml_to_keypath_sequence(item, list_prefix))
            else:
                seq.append(list_prefix)
    return seq


def yaml_file_to_sequence(filepath):
    """Load a YAML file and convert to a key-path sequence."""
    with open(filepath) as f:
        data = yaml.safe_load(f)
    if data is None:
        return []
    return yaml_to_keypath_sequence(data)


def is_vault_file(filepath):
    """Check if a file is an Ansible vault file (encrypted)."""
    try:
        with open(filepath) as f:
            first = f.read(100)
            return '$ANSIBLE_VAULT' in first or first.startswith('!vault |')
    except Exception:
        return False


def collect_all_sequences(root_dir=".", include_vault=False):
    """Collect key-path sequences from all YAML files.

    Returns:
        list of (filepath, sequence) tuples.
    """
    results = []
    for path in sorted(Path(root_dir).rglob("*.yml")):
        parts = path.parts
        if any(d in parts for d in ('node_modules', '.venv', '__pycache__', '.git')):
            continue
        skippable = ('vault.yml' in path.name or 'vault' in path.name)
        if not include_vault and (skippable or is_vault_file(path)):
            continue
        try:
            seq = yaml_file_to_sequence(path)
            if seq:
                results.append((path, seq))
        except Exception as e:
            print(f"  SKIP {path}: {e}")
    return results


def sequences_to_crx(result_list):
    """Run CRX on collected sequences."""
    from .crx import CRX
    sequences = [seq for _, seq in result_list]
    if not sequences:
        return 'ε'
    crx = CRX()
    return crx.infer(sequences)