"""DataTools deduplication engine.

Public API
----------
Core:
    deduplicate(df, ...) -> DeduplicationResult
    build_default_strategies(df) -> list[MatchStrategy]

Types:
    Algorithm, SurvivorRule, ColumnMatchStrategy, MatchStrategy
    MatchResult, DeduplicationResult

Normalizers:
    get_normalizer(type) -> Callable
    NormalizerType
    normalize_email, normalize_phone, normalize_name,
    normalize_address, normalize_string

I/O:
    read_file(path, ...) -> DataFrame
    write_file(df, path, ...)
    list_sheets(path) -> list[str]
    detect_encoding, detect_delimiter, detect_header_row

Configuration:
    DeduplicationConfig.from_file(path) -> DeduplicationConfig
    DeduplicationConfig.to_file(path)
"""

from .dedup import (
    Algorithm,
    ColumnMatchStrategy,
    DeduplicationResult,
    MatchResult,
    MatchStrategy,
    SurvivorRule,
    build_default_strategies,
    deduplicate,
)
from .normalizers import (
    NormalizerType,
    get_normalizer,
    normalize_address,
    normalize_email,
    normalize_name,
    normalize_phone,
    normalize_string,
)
from .io import (
    detect_delimiter,
    detect_encoding,
    detect_header_row,
    list_sheets,
    read_file,
    write_file,
)
from .config import (
    ColumnStrategyConfig,
    DeduplicationConfig,
    StrategyConfig,
)

__all__ = [
    # Core
    "deduplicate",
    "build_default_strategies",
    # Types
    "Algorithm",
    "SurvivorRule",
    "ColumnMatchStrategy",
    "MatchStrategy",
    "MatchResult",
    "DeduplicationResult",
    # Normalizers
    "NormalizerType",
    "get_normalizer",
    "normalize_email",
    "normalize_phone",
    "normalize_name",
    "normalize_address",
    "normalize_string",
    # I/O
    "read_file",
    "write_file",
    "list_sheets",
    "detect_encoding",
    "detect_delimiter",
    "detect_header_row",
    # Config
    "DeduplicationConfig",
    "StrategyConfig",
    "ColumnStrategyConfig",
]