"""Deduplication package: MinHash near-dup + semantic paraphrase dedup.

Standard SFT dedup pipeline order:

    exact (caller's responsibility)
        |
        v
    MinHashDeduplicator   - lexical near-dups (formatting variants, edits)
        |
        v
    SemanticDeduplicator  - paraphrases (different wording, same meaning)

Both classes operate on a list[str] and return list[int] of indices to KEEP,
so callers re-index back into their own record list. An optional
`key_fn(idx) -> sortable` controls which member of a duplicate cluster wins
(smaller key wins). Default: smallest original index ("first seen").
"""

from .minhash import MinHashDeduplicator
from .semantic import SemanticDeduplicator
from .templates import find_common_prefixes, strip_template, template_hit_stats

__all__ = [
    "MinHashDeduplicator",
    "SemanticDeduplicator",
    "find_common_prefixes",
    "strip_template",
    "template_hit_stats",
]