#!/bin/bash
# =============================================
# 国内服务器：全链路管道 M2 → M3 → M4 → M5 → M6 → 日报
# =============================================
# 用法：./scripts/pipeline.sh
# 前提：domestic_sync.sh 已完成
# =============================================
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_DIR="$(dirname "$SCRIPT_DIR")"

cd "$PROJECT_DIR"

echo "[$(date)] ═══ 全链路管道开始 ═══"

# 加载 .env
export $(grep -v '^#' .env | grep -v '^$' | xargs 2>/dev/null || true)

# ── M2: 正文提取 ──
echo "[$(date)] [M2] 正文提取..."
.venv/bin/python3 -c "
from extractor.pipeline import process_all_sources
stats = process_all_sources()
print(f'M2: {stats[\"total_articles\"]} 篇, {stats[\"elapsed_sec\"]:.0f}s')
"

# ── M3: 去重 ──
echo "[$(date)] [M3] 三层去重..."
.venv/bin/python3 -c "
from dedup.pipeline import dedup_all_sources
stats = dedup_all_sources()
print(f'M3: 唯一 {stats[\"unique\"]}/重复 {stats[\"duplicate\"]}, {stats[\"elapsed_sec\"]:.0f}s')
"

# ── M4: 翻译+事件 ──
echo "[$(date)] [M4] 翻译+事件抽取..."
.venv/bin/python3 -c "
from llm.pipeline import translate_all_deduped
stats = translate_all_deduped()
print(f'M4: {stats[\"success\"]}/{stats[\"total\"]} 篇, {stats[\"elapsed_sec\"]:.0f}s')
"

# ── M5: 向量生成 ──
echo "[$(date)] [M5] 向量生成..."
.venv/bin/python3 -c "
from embedding.pipeline import embed_all_events
stats = embed_all_events()
print(f'M5: {stats[\"success\"]}/{stats[\"total\"]} 篇, {stats[\"elapsed_sec\"]:.0f}s')
"

# ── M6: Qdrant 入库 ──
echo "[$(date)] [M6] Qdrant 入库..."
.venv/bin/python3 -c "
from vectorstore.pipeline import ingest_all_embeddings
stats = ingest_all_embeddings()
print(f'M6: {stats[\"ingested\"]}/{stats[\"total\"]} 条, {stats[\"elapsed_sec\"]:.0f}s')
"

# ── 日报 ──
echo "[$(date)] [日报] 生成日报（结构化入库）..."
.venv/bin/python3 -c "
from scheduler.reporter import generate_report
report_id = generate_report()
print(f'日报: report_id={report_id}' if report_id is not None else '日报: 无数据/失败')
"

echo "[$(date)] ═══ 全链路管道完成 ✅ ═══"