from pathlib import Path

from tht.cli.schema_cmd import physical_path


def _extract_lsh_values(dwh, physical, annotations, limit):
    from tht.db.sampling import SkippedColumn, TruncatedColumn, is_text_type
    from tht.mschema.eligibility import effective_eligibility

    values, skipped, truncated = {}, [], []
    for table_name, table in physical.tables.items():
        table_ann = annotations.tables.get(table_name)
        for column_name, column in table.columns.items():
            ann_col = table_ann.columns.get(column_name) if table_ann else None
            if not is_text_type(column.type) or not effective_eligibility(column, ann_col)[0]:
                continue
            try:
                distinct = dwh.distinct_values(table_name, column_name, limit=limit)
            except Exception as exc:
                skipped.append(SkippedColumn(table_name, column_name, f"errore: {exc}"))
                continue
            vals = [str(value) for value in distinct.values if value not in (None, "")]
            if vals:
                values.setdefault(table_name, {})[column_name] = vals
            if distinct.truncated:
                truncated.append(TruncatedColumn(table_name, column_name, len(vals)))
    return values, skipped, truncated


def build_lsh_artifacts(
    cfg, *, dwh=None, verbose: bool = False, physical_file: Path | None = None,
    output_dir: Path | None = None,
):
    """Run the existing LSH extraction/build algorithm and persist its outputs."""
    from tht.adapters.factory import build_dwh
    from tht.cli.schema_cmd import annotations_path
    from tht.lshindex import build_index, save_index
    from tht.mschema.models import Annotations, PhysicalSchema

    phys_file = physical_file or physical_path(cfg)
    if not phys_file.exists():
        raise FileNotFoundError("physical catalog is missing; run schema introspect first")
    physical = PhysicalSchema.from_yaml(phys_file)
    annotations = Annotations.from_yaml(annotations_path(cfg))
    target = dwh if dwh is not None else build_dwh(cfg)
    values, skipped, truncated = _extract_lsh_values(
        target, physical, annotations, cfg.lsh.max_values_per_column
    )
    lsh, minhashes = build_index(values, cfg.lsh, verbose=verbose)
    save_index(
        lsh, minhashes, cfg.lsh, output_dir or (cfg.paths.indexes / "lsh"),
        name=cfg.database.db_schema,
    )
    return minhashes, skipped, truncated, values