#!/usr/bin/env bash
# File upload, end to end: session -> bytes -> complete -> mapping -> sync.
# Uses the media-streaming CSV of the sample dataset.
set -euo pipefail

: "${TESSERA_API_BASE:?e.g. https://api.staging.tessera.zone/v1}"
: "${TESSERA_API_KEY:?your tsk_test_… key}"
: "${TESSERA_STATE_DIR:=.}"
SAMPLE_URL="${TESSERA_SAMPLE_URL:-https://docs.staging.tessera.zone/downloads/tessera-sample-v1.zip}"
AUTH=(-H "Authorization: Bearer $TESSERA_API_KEY")

curl -sSL "$SAMPLE_URL" -o "$TESSERA_STATE_DIR/sample.zip"
python3 -c 'import sys, zipfile; zipfile.ZipFile(sys.argv[1]).extract("media_streaming.csv", sys.argv[2])' \
  "$TESSERA_STATE_DIR/sample.zip" "$TESSERA_STATE_DIR"

# 1. Create the upload session (a resumable URL, valid for 24 h).
SESSION="$(curl -sS -X POST "$TESSERA_API_BASE/uploads" "${AUTH[@]}" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: docs-file-upload-media" \
  -d '{"filename": "media_streaming.csv", "format": "csv"}')"
UPLOAD_ID="$(printf '%s' "$SESSION" | python3 -c 'import json,sys; print(json.load(sys.stdin)["upload_id"])')"
UPLOAD_URL="$(printf '%s' "$SESSION" | python3 -c 'import json,sys; print(json.load(sys.stdin)["upload_url"])')"

# 2. Send the bytes, then complete (verifies size, fingerprints the object,
#    attaches it to a `file_upload` source, and lands + profiles it).
curl -sS -X PUT "$UPLOAD_URL" --data-binary "@$TESSERA_STATE_DIR/media_streaming.csv" > /dev/null
curl -sS -X POST "$TESSERA_API_BASE/uploads/$UPLOAD_ID:complete" "${AUTH[@]}" > /dev/null
UPLOAD="$(curl -sS "$TESSERA_API_BASE/uploads/$UPLOAD_ID" "${AUTH[@]}")"
SOURCE_ID="$(printf '%s' "$UPLOAD" | python3 -c 'import json,sys; print(json.load(sys.stdin)["source_id"])')"
LANDING_SYNC_ID="$(printf '%s' "$UPLOAD" | python3 -c 'import json,sys; print(json.load(sys.stdin)["sync_id"])')"
echo "upload: $(printf '%s' "$UPLOAD" | python3 -c 'import json,sys; print(json.load(sys.stdin)["status"])')"
for _ in $(seq 1 300); do
  LANDING="$(curl -sS "$TESSERA_API_BASE/syncs/$LANDING_SYNC_ID" "${AUTH[@]}" \
    | python3 -c 'import json,sys; print(json.load(sys.stdin)["status"])')"
  if [ "$LANDING" = "succeeded" ] || [ "$LANDING" = "failed" ]; then break; fi
  sleep 1
done
echo "landing sync: $LANDING"

# 3. Map columns to canonical events, then re-sync to normalize.
curl -sS -X PUT "$TESSERA_API_BASE/sources/$SOURCE_ID/mapping" "${AUTH[@]}" \
  -H "Content-Type: application/json" --data-binary @mapping-media.json > /dev/null
SYNC="$(curl -sS -X POST "$TESSERA_API_BASE/sources/$SOURCE_ID/syncs" "${AUTH[@]}" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: docs-file-upload-media-sync" \
  -d '{"mode": "full"}')"
SYNC_ID="$(printf '%s' "$SYNC" | python3 -c 'import json,sys; print(json.load(sys.stdin)["sync_id"])')"
for _ in $(seq 1 300); do
  SYNC="$(curl -sS "$TESSERA_API_BASE/syncs/$SYNC_ID" "${AUTH[@]}")"
  STATUS="$(printf '%s' "$SYNC" | python3 -c 'import json,sys; print(json.load(sys.stdin)["status"])')"
  if [ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ]; then break; fi
  sleep 1
done
printf '%s' "$SYNC" | python3 -c '
import json, sys
sync = json.load(sys.stdin)
print("sync: %s rows_landed=%s events_normalized=%s rejected=%s"
      % (sync["status"], sync["rows_landed"], sync["events_normalized"], sync["rows_rejected"]))
'