#!/usr/bin/env bash
# 03_ingest_csv_to_parquet.sh — GOLAKE-030.
# Ingests fixtures/csv/workers.csv via /v1/ingest, verifies the parquet
# object lands on storaged and catalogd registers a matching manifest.
# Leaves data in place so 04_query_correctness can SELECT against it.

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-030"
CASE_NAME="Ingest CSV → Parquet → catalog manifest"
CASE_TYPE="integration"
if [ "${1:-}" = "--metadata-only" ]; then return 0 2>/dev/null || exit 0; fi

DATASET="proof_workers"
CSV_FIXTURE="${PROOF_REPO_ROOT}/tests/proof/fixtures/csv/workers.csv"

# Record fixture sha for the evidence chain.
CSV_SHA=$(sha256sum "$CSV_FIXTURE" | awk '{print $1}')
echo "{\"fixture\":\"workers.csv\",\"sha256\":\"$CSV_SHA\"}" \
    > "${PROOF_REPORT_DIR}/raw/outputs/${CASE_ID}_fixture.json"

# Idempotent prelude — schema-drift would 409, but identical-fp is fine.
# We can't easily delete a catalog entry; rely on idempotent re-ingest.
# If a prior run with different csv content registered DATASET, this
# would 409 — which would be a real finding worth surfacing.

# Ingest. /v1/ingest takes ?name=<n> in the query and a multipart form
# with the CSV file under any field name (handler reads the first file).
# proof_post / proof_put set Content-Type + --data which conflict with
# multipart -F; use proof_call for direct curl-arg pass-through.
proof_call "$CASE_ID" "ingest" POST \
    "${PROOF_GATEWAY_URL}/v1/ingest?name=${DATASET}" \
    -F "file=@${CSV_FIXTURE}" >/dev/null

ingest_status=$(proof_status_of "$CASE_ID" "ingest")
proof_assert_eq "$CASE_ID" "ingest → 200" "200" "$ingest_status"

# Halt the rest of the case if ingest didn't succeed — the downstream
# claims would all fail for the same reason, no point recording N
# duplicate failures.
if [ "$ingest_status" != "200" ]; then
    proof_skip "$CASE_ID" "downstream claims skipped — ingest failed" \
        "see raw/http/${CASE_ID}/ingest.body for upstream error"
    return 0 2>/dev/null || exit 0
fi

ingest_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/ingest.body"

# Response shape: {manifest, existing, row_count, parquet_size, parquet_key}.
row_count=$(jq -r '.row_count' "$ingest_body")
proof_assert_eq "$CASE_ID" "ingest reports row_count = 5" "5" "$row_count"

parquet_size=$(jq -r '.parquet_size' "$ingest_body")
proof_assert_gt "$CASE_ID" "parquet_size > 0" "$parquet_size" "0"

parquet_key=$(jq -r '.parquet_key' "$ingest_body")
proof_assert_ne "$CASE_ID" "parquet_key non-empty" "" "$parquet_key"
# Content-addressed keys are datasets/<name>/<fp_hex>.parquet per memory `c1e4113`.
proof_assert_contains "$CASE_ID" "parquet_key is content-addressed under datasets/${DATASET}/" \
    "datasets/${DATASET}/" "$parquet_key"

# Verify the parquet object actually exists on storaged.
proof_get "$CASE_ID" "storage_list" \
    "${PROOF_GATEWAY_URL}/v1/storage/list" >/dev/null
list_body=$(proof_body_of "$CASE_ID" "storage_list")
proof_assert_contains "$CASE_ID" "storaged LIST contains parquet_key" \
    "$parquet_key" "$list_body"

# Verify catalogd has a matching manifest.
proof_get "$CASE_ID" "catalog_manifest" \
    "${PROOF_GATEWAY_URL}/v1/catalog/manifest/${DATASET}" >/dev/null
proof_assert_eq "$CASE_ID" "catalog manifest GET → 200" "200" \
    "$(proof_status_of "$CASE_ID" "catalog_manifest")"
manifest_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/catalog_manifest.body"
manifest_row_count=$(jq -r '.row_count' "$manifest_body")
proof_assert_eq "$CASE_ID" "manifest row_count = 5" "5" "$manifest_row_count"