"""Dervish — MCP server.

Provides tools to infer regular expression grammars from example sequences.
Run as: python -m bex.mcp_server
"""

from mcp.server.fastmcp import FastMCP

from .crx import CRX
from .idregex import idregex
from .ensemble import infer_ensemble, _matches

mcp = FastMCP("grammar-inference", log_level="ERROR")


@mcp.tool()
def infer_grammar(
    sequences: list[list[str]],
    method: str = "crx",
    kmax: int = 2,
    N: int = 3,
) -> str:
    """Infer a grammar (regular expression) from example sequences.

    Args:
        sequences: List of sequences, each a list of symbols (strings).
        method: Algorithm to use — 'crx' (fast, deterministic) or 'idregex' (probabilistic, handles noise better).
        kmax: Maximum k for k-ORE inference (iDRegEx only).
        N: Number of EM iterations (iDRegEx only).

    Returns:
        A regular expression string describing the inferred grammar.
    """
    if method == "crx":
        return CRX().infer(sequences)
    elif method == "idregex":
        result = idregex(sequences, kmax=kmax, N=N)
        return result or "∅"
    else:
        raise ValueError(f"Unknown method: {method}. Use 'crx' or 'idregex'.")


@mcp.tool()
def infer_best_grammar(
    sequences: list[list[str]],
    prefer: str = "",
    kmax: int = 2,
    N: int = 3,
) -> str:
    """Infer a compact grammar from example sequences. Use this when you
    have examples of sequential data and want to learn the pattern.

    The grammar compresses N examples into ~100 chars — far fewer tokens
    than passing all examples. Pass the existing sequences, get back a
    pattern you can follow to generate new instances.

    Args:
        sequences: List of sequences, each a list of strings (symbols in
            the order they appear). Example: [["file","copy","command"],
            ["file","template","command"]].
        prefer: Optional — 'crx' for full coverage (accepts all examples),
            'idregex' for minimal core (only what every example shares).
            Default: runs both and picks best by MDL score.
        kmax: Maximum k for iDRegEx k-ORE inference.
        N: Number of EM iterations for iDRegEx.

    Returns:
        A formatted string with the best grammar, scores, and explanation.
        Grammar notation: a.b = a then b, (a+b) = a or b, r? = optional,
        r+ = one or more, r+? = zero or more.
    """
    pref = prefer if prefer else None
    result = infer_ensemble(sequences, kmax=kmax, N=N, prefer=pref)
    if result['best'] is None:
        return f"No grammar found. {result['why']}"
    lines = [f"Best: {result['best']['algorithm']} (MDL {result['best']['mdl_score']})",
             f"Grammar: {result['best']['grammar']}",
             ""]
    if len(result['all']) > 1:
        for r in result['all']:
            m = sum(1 for s in sequences if _matches(r['grammar'], s))
            lines.append(f"  {r['algorithm']:10s}  MDL={r['mdl_score']:>8.2f}  match={m}/{len(sequences)}")
    lines.append("")
    lines.append(f"Why: {result['why']}")
    return "\n".join(lines)


def main():
    mcp.run()


if __name__ == "__main__":
    main()