from datetime import datetime

from sqlalchemy import (
    BigInteger,
    DateTime,
    ForeignKey,
    Index,
    Integer,
    Text,
    UniqueConstraint,
)
from sqlalchemy.orm import Mapped, mapped_column

from scribe.models import Base
from scribe.models.base import TimestampMixin

# The classification vocabulary (note 2786). `unclassified` is the default and
# THE todo state; every other status is a judgment, stamped with who made it.
SHAPE_STATUSES = ("canonical", "instance", "variant", "exempt", "unclassified")
SHAPE_CLASSIFIERS = ("agent", "audit", "hook", "mechanical", "import")


class CodeShape(Base, TimestampMixin):
    """One extracted code shape and its classification against canon (#2787).

    The accounting half of the pattern system (governing note 2786): the
    snippet library records CANON (small); this ledger accounts for EVERY
    shape the coverage extractor finds in a bound repo (total). A row's
    status says how the shape relates to canon — it IS a snippet's reference
    (`canonical`), conforms to one (`instance` — snippet_id may point at
    another project's snippet, so family canon counts), departs deliberately
    (`variant`, with the why in `reason`), was judged one-off (`exempt`,
    a recorded judgment rather than silence), or awaits judgment
    (`unclassified` — the todo).

    Identity is (project, repo_key, path, symbol, kind) — kind is part of it
    because one file can define `.foo` (css) and `foo` (sym) as distinct
    shapes. A rename therefore reads as vanish + new row: accepted for v1,
    because chasing renames needs content identity the extractor doesn't
    have. `vanished_at` keeps the history instead of deleting it.

    snippet_id is SET NULL on snippet deletion: the classification's target
    is gone but the judgment happened; the sync pass (step 2) re-files such
    rows as unclassified so they rejoin the todo instead of dangling.
    """

    __tablename__ = "code_shapes"
    __table_args__ = (
        UniqueConstraint(
            "project_id", "repo_key", "path", "symbol", "kind",
            name="uq_code_shapes_identity",
        ),
        Index("ix_code_shapes_project_status", "project_id", "status"),
        Index("ix_code_shapes_snippet", "snippet_id"),
    )

    id: Mapped[int] = mapped_column(primary_key=True)
    project_id: Mapped[int] = mapped_column(
        Integer, ForeignKey("projects.id", ondelete="CASCADE"), nullable=False
    )
    repo_key: Mapped[str] = mapped_column(Text, nullable=False)
    path: Mapped[str] = mapped_column(Text, nullable=False)
    symbol: Mapped[str] = mapped_column(Text, nullable=False)
    kind: Mapped[str] = mapped_column(Text, nullable=False)  # "css" | "sym"
    status: Mapped[str] = mapped_column(Text, nullable=False, default="unclassified")
    snippet_id: Mapped[int | None] = mapped_column(
        BigInteger, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
    )
    reason: Mapped[str | None] = mapped_column(Text, nullable=True)
    classified_by: Mapped[str | None] = mapped_column(Text, nullable=True)
    classified_at: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), nullable=True
    )
    first_seen_commit: Mapped[str] = mapped_column(Text, default="")
    last_seen_commit: Mapped[str] = mapped_column(Text, default="")
    vanished_at: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), nullable=True
    )

    def to_dict(self) -> dict:
        return {
            "id": self.id,
            "project_id": self.project_id,
            "repo_key": self.repo_key,
            "path": self.path,
            "symbol": self.symbol,
            "kind": self.kind,
            "status": self.status,
            "snippet_id": self.snippet_id,
            "reason": self.reason,
            "classified_by": self.classified_by,
            "classified_at": self.classified_at.isoformat() if self.classified_at else None,
            "first_seen_commit": self.first_seen_commit,
            "last_seen_commit": self.last_seen_commit,
            "vanished_at": self.vanished_at.isoformat() if self.vanished_at else None,
            "created_at": self.created_at.isoformat(),
            "updated_at": self.updated_at.isoformat(),
        }