#!/usr/bin/env bash
set -euo pipefail

repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd -P)"
python="$repo_root/harness/.venv/bin/python"
fixture="$repo_root/harness/tests/fixtures/evidence_authoring/poorly_structured.md"

[[ -x "$python" ]] || { printf 'missing harness virtualenv: %s\n' "$python" >&2; exit 127; }
[[ -f "$fixture" ]] || { printf 'missing authoring fixture: %s\n' "$fixture" >&2; exit 2; }

before_status="$(git -C "$repo_root" status --porcelain)"
temporary_root="$(mktemp -d "${TMPDIR:-/tmp}/thothii-evidence-restructuring.XXXXXXXX")"
trap 'rm -rf -- "$temporary_root"' EXIT HUP INT TERM

# The authoring target is created under mktemp and passed directly to the Python API.
# This runner has no PSD workspace argument or configured external authoring path.
TASK12_WORKSPACE="$temporary_root/workspace" TASK12_FIXTURE="$fixture" \
  PYTHONPATH="$repo_root/harness" "$python" - <<'PY'
import os
import shutil
import subprocess
from pathlib import Path

from tht.evidence import (
    EvidencePreparationError,
    EvidenceRestructurer,
    RestructureCandidate,
    dump_manifest,
    load_curated_tree,
    load_manifest,
    prepare_workspace_evidence,
    validate_workspace_evidence,
)


workspace = Path(os.environ["TASK12_WORKSPACE"]).resolve()
fixture = Path(os.environ["TASK12_FIXTURE"]).resolve()
source_root = workspace / "evidence" / "source"
source_root.mkdir(parents=True)
fixture_target = source_root / "notes" / "poorly-structured.md"
fixture_target.parent.mkdir()
shutil.copyfile(fixture, fixture_target)
independent_target = source_root / "notes" / "independent.md"
independent_target.write_text("La codifica ADT è usata soltanto per il triage.\n", encoding="utf-8")


class FakeRestructurer(EvidenceRestructurer):
    """Hermetic, deterministic substitute for the one-call-per-source Pi boundary."""

    def __init__(self):
        self.requests = []

    def restructure(self, request):
        self.requests.append(request)
        existing = {unit.title: unit.id for unit in request.previous_units}

        def candidate(title, kind, purposes, excerpt, payload, review_items=()):
            return RestructureCandidate.model_validate({
                "schema_version": 1,
                "existing_id": existing.get(title),
                "title": title,
                "kind": kind,
                "purposes": purposes,
                "applies_to": {
                    "concepts": ["fascia pediatrica"],
                    "tables": ["clinical.patient"],
                    "columns": ["clinical.patient.birth_date"],
                },
                "language": "it",
                "supporting_excerpts": [excerpt],
                "review_items": review_items,
                "payload": payload,
            })

        if request.source_file.endswith("independent.md"):
            return (candidate(
                "Codifica ADT", "domain", ["schema_linking"],
                "La codifica ADT è usata soltanto per il triage.",
                {"rule": "Usare ADT solo per il triage."},
            ),)
        return (
            candidate(
                "Fascia pediatrica", "formula", ["sql_generation"],
                "Formula candidata: `CASE WHEN age < 18 THEN 'pediatrica' ELSE 'adulta' END`.",
                {
                    "concept": "fascia pediatrica",
                    "columns": ["clinical.patient.birth_date"],
                    "sql": "CASE WHEN age < 18 THEN 'pediatrica' ELSE 'adulta' END",
                },
            ),
            candidate(
                "Stato dimissione", "enum", ["schema_linking"],
                "Lo stato di dimissione usa i codici: D = dimesso, T = trasferito.",
                {"column": "clinical.episode.discharge_status", "values": {"D": "dimesso", "T": "trasferito"}},
            ),
            candidate(
                "Linea guida dimissione", "reference", ["rewriting"],
                "https://example.test/linee-guida-dimissione",
                {
                    "url": "https://example.test/linee-guida-dimissione",
                    "label": "Linea guida dimissione",
                    "description": "Riferimento clinico per la dimissione.",
                },
            ),
            candidate(
                "Regola età", "domain", ["disambiguation"],
                "La fascia pediatrica riguarda i pazienti con età minore di 18 anni; il testo non chiarisce se l'età debba essere calcolata alla data di ricovero o alla data odierna.",
                {"rule": "La fascia pediatrica comprende i pazienti con meno di 18 anni."},
                [{
                    "code": "ambiguous_source_statement",
                    "message": "La data di calcolo dell'età non è specificata.",
                    "field": "domain.rule",
                }],
            ),
        )


def run_git(*arguments):
    return subprocess.run(["git", *arguments], cwd=workspace, check=True, capture_output=True, text=True)


fake = FakeRestructurer()
first = prepare_workspace_evidence(workspace, restructurer=fake, git_status=lambda _: ())
assert first.model_calls == 2 and len(first.created) == 5
documents = load_curated_tree(workspace / "evidence" / "curated")
assert {document.kind for document in documents} == {"domain", "enum", "formula", "reference"}
assert len({document.id for document in documents}) == 5
assert {document.provenance.source_file for document in documents} == {
    "source/notes/poorly-structured.md", "source/notes/independent.md",
}
manifest = load_manifest(workspace / "evidence" / "manifest.yaml")
assert not set(manifest.sources["source/notes/poorly-structured.md"].units).intersection(
    manifest.sources["source/notes/independent.md"].units
)
assert "unresolved_review_item" in {finding.code for finding in validate_workspace_evidence(workspace).findings}

run_git("init", "-q")
run_git("config", "user.email", "acceptance@example.test")
run_git("config", "user.name", "Acceptance")
run_git("add", "evidence")
run_git("commit", "-qm", "baseline human-reviewed curated evidence")
baseline_formula = run_git("show", "HEAD:evidence/curated/formula/fascia-pediatrica.md").stdout
fixture_target.write_text(fixture_target.read_text(encoding="utf-8") + "\nNota revisionata.\n", encoding="utf-8")
second = prepare_workspace_evidence(workspace, restructurer=fake)
assert second.model_calls == 1 and second.changed == ("source/notes/poorly-structured.md",)
changed_paths = set(run_git("diff", "--name-only").stdout.splitlines())
assert "evidence/manifest.yaml" in changed_paths
assert "evidence/curated/formula/fascia-pediatrica.md" in changed_paths
assert run_git("show", "HEAD:evidence/curated/formula/fascia-pediatrica.md").stdout == baseline_formula
run_git("add", "evidence")
run_git("commit", "-qm", "proposed fake restructuring")

snapshot = {
    path.relative_to(workspace): path.read_bytes()
    for path in (workspace / "evidence").rglob("*") if path.is_file()
}
no_op = prepare_workspace_evidence(workspace, restructurer=fake)
assert no_op.model_calls == 0 and no_op.changed == ()
assert snapshot == {
    path.relative_to(workspace): path.read_bytes()
    for path in (workspace / "evidence").rglob("*") if path.is_file()
}

curated_path = workspace / "evidence" / "curated" / "formula" / "fascia-pediatrica.md"
curated_path.write_text(curated_path.read_text(encoding="utf-8") + "\n", encoding="utf-8")
try:
    prepare_workspace_evidence(workspace, restructurer=fake)
except EvidencePreparationError as failure:
    assert failure.code == "authoring_worktree_dirty"
else:
    raise AssertionError("dirty curated state was not refused")
run_git("checkout", "--", "evidence/curated")

manifest_path = workspace / "evidence" / "manifest.yaml"
manifest_path.write_text(
    manifest_path.read_text(encoding="utf-8").replace("evidence-authoring-v1", "evidence-authoring-v2"),
    encoding="utf-8",
)
run_git("add", "evidence/manifest.yaml")
run_git("commit", "-qm", "incompatible authoring pipeline")
incompatible = manifest_path.read_bytes()
try:
    prepare_workspace_evidence(workspace, restructurer=fake)
except EvidencePreparationError as failure:
    assert failure.code == "pipeline_upgrade_required"
else:
    raise AssertionError("incompatible pipeline version was not refused")
assert manifest_path.read_bytes() == incompatible
upgrade = prepare_workspace_evidence(workspace, restructurer=fake, upgrade=True)
assert upgrade.model_calls == 2 and set(upgrade.changed) == {
    "source/notes/independent.md", "source/notes/poorly-structured.md",
}

manifest = load_manifest(manifest_path).model_copy(update={"orphans": ("evidence:fascia-pediatrica",)})
manifest_path.write_text(dump_manifest(manifest), encoding="utf-8")
assert "orphaned_unit" in {finding.code for finding in validate_workspace_evidence(workspace).findings}

print("PASS hermetic fake-restructurer: split, review, Git recovery/diff, no-op, dirty, upgrade, orphan")
print("PASS isolation: only a temporary workspace was supplied; no external PSD path was read or written")
PY

(
  cd "$repo_root/harness"
  .venv/bin/pytest -q \
    tests/test_evidence_restructuring_fixture.py \
    tests/test_evidence_candidate_publication.py \
    tests/test_evidence_authoring.py \
    tests/test_evidence_canonical.py \
    tests/test_evidence_pi_restructurer.py \
    tests/test_evidence_evaluation.py \
    tests/test_evidence_formula_migration.py \
    tests/test_evidence_facade_contract.py \
    tests/test_corpus_chunk.py \
    tests/test_corpus_pipeline.py \
    tests/test_qdrant_vector_store.py \
    tests/l0/test_qdrant_bm25_inference.py
)

after_status="$(git -C "$repo_root" status --porcelain)"
[[ "$before_status" == "$after_status" ]] || {
  printf 'acceptance runner unexpectedly changed the ThothII worktree\n' >&2
  exit 1
}
printf 'PASS evidence restructuring automated acceptance\n'