#!/usr/bin/env bash
# 02_catalog_manifest.sh — GOLAKE-020 + GOLAKE-021 + GOLAKE-022.
# Catalog register idempotency + manifest read + list inclusion +
# schema-drift 409 (the ADR-020 contract). Uses a synthetic manifest
# referencing a fake parquet object so we don't depend on prior ingest.

set -uo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "${SCRIPT_DIR}/../lib/env.sh"
source "${SCRIPT_DIR}/../lib/http.sh"
source "${SCRIPT_DIR}/../lib/assert.sh"

CASE_ID="GOLAKE-020-022"
CASE_NAME="Catalog manifest — register idempotent + drift 409"
CASE_TYPE="integration"
if [ "${1:-}" = "--metadata-only" ]; then return 0 2>/dev/null || exit 0; fi

# Fresh-each-run name so the existing=false assertion is meaningful.
# Catalog dataset_id is deterministic UUIDv5 from name; reusing the
# same name across runs would always show existing=true on second run.
NAME="proof_catalog_${PROOF_RUN_ID}"
FP_A="sha256:proof_test_fp_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
FP_B="sha256:proof_test_fp_bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"

reg_body() {
    local name="$1" fp="$2"
    cat <<JSON
{
  "name": "${name}",
  "schema_fingerprint": "${fp}",
  "objects": [{"key": "datasets/${name}/${fp}.parquet", "size": 1024}],
  "row_count": 5
}
JSON
}

# Fresh register.
proof_post "$CASE_ID" "register_first" \
    "${PROOF_GATEWAY_URL}/v1/catalog/register" \
    "application/json" "$(reg_body "$NAME" "$FP_A")" >/dev/null
proof_assert_eq "$CASE_ID" "first register → 200" "200" \
    "$(proof_status_of "$CASE_ID" "register_first")"

first_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/register_first.body"
existing_first=$(jq -r '.existing' "$first_body")
proof_assert_eq "$CASE_ID" "first register existing=false" \
    "false" "$existing_first"
dataset_id_first=$(jq -r '.manifest.dataset_id' "$first_body")
proof_assert_ne "$CASE_ID" "first register dataset_id non-empty" "" "$dataset_id_first"

# Manifest read matches what was registered.
proof_get "$CASE_ID" "manifest_read" \
    "${PROOF_GATEWAY_URL}/v1/catalog/manifest/${NAME}" >/dev/null
proof_assert_eq "$CASE_ID" "manifest read → 200" "200" \
    "$(proof_status_of "$CASE_ID" "manifest_read")"
read_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/manifest_read.body"
read_fp=$(jq -r '.schema_fingerprint' "$read_body")
proof_assert_eq "$CASE_ID" "manifest schema_fingerprint matches" \
    "$FP_A" "$read_fp"
read_id=$(jq -r '.dataset_id' "$read_body")
proof_assert_eq "$CASE_ID" "manifest dataset_id matches" \
    "$dataset_id_first" "$read_id"

# List contains the dataset.
proof_get "$CASE_ID" "list" \
    "${PROOF_GATEWAY_URL}/v1/catalog/list" >/dev/null
proof_assert_eq "$CASE_ID" "list → 200" "200" \
    "$(proof_status_of "$CASE_ID" "list")"
list_body=$(proof_body_of "$CASE_ID" "list")
proof_assert_contains "$CASE_ID" "list contains dataset_id" \
    "$dataset_id_first" "$list_body"

# Idempotent re-register with same name+fp → existing=true, dataset_id stable.
proof_post "$CASE_ID" "register_second" \
    "${PROOF_GATEWAY_URL}/v1/catalog/register" \
    "application/json" "$(reg_body "$NAME" "$FP_A")" >/dev/null
proof_assert_eq "$CASE_ID" "second register → 200" "200" \
    "$(proof_status_of "$CASE_ID" "register_second")"
second_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/register_second.body"
existing_second=$(jq -r '.existing' "$second_body")
proof_assert_eq "$CASE_ID" "second register existing=true (idempotent)" \
    "true" "$existing_second"
dataset_id_second=$(jq -r '.manifest.dataset_id' "$second_body")
proof_assert_eq "$CASE_ID" "dataset_id stable across re-register" \
    "$dataset_id_first" "$dataset_id_second"

# Schema drift — different fp on same name → 409 (ADR-020).
proof_post "$CASE_ID" "register_drift" \
    "${PROOF_GATEWAY_URL}/v1/catalog/register" \
    "application/json" "$(reg_body "$NAME" "$FP_B")" >/dev/null
proof_assert_eq "$CASE_ID" "drift register → 409 (ADR-020)" "409" \
    "$(proof_status_of "$CASE_ID" "register_drift")"