初始化红餐观察库项目

2026-07-19 18:11:08 +08:00
commit c663539548
22 changed files with 1261 additions and 0 deletions
@@ -0,0 +1,75 @@
+PRAGMA journal_mode = WAL;
+PRAGMA foreign_keys = ON;
+
+CREATE TABLE IF NOT EXISTS articles (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    canonical_url TEXT NOT NULL UNIQUE,
+    source TEXT NOT NULL DEFAULT 'hongcan',
+    title TEXT,
+    author TEXT,
+    published_at TEXT,
+    summary TEXT,
+    content TEXT,
+    content_hash TEXT,
+    crawl_status TEXT NOT NULL DEFAULT 'pending',
+    retry_count INTEGER NOT NULL DEFAULT 0,
+    last_error TEXT,
+    discovered_at TEXT NOT NULL,
+    crawled_at TEXT,
+    updated_at TEXT NOT NULL
+);
+
+CREATE INDEX IF NOT EXISTS idx_articles_published_at
+    ON articles(published_at);
+CREATE INDEX IF NOT EXISTS idx_articles_crawl_status
+    ON articles(crawl_status, retry_count);
+CREATE INDEX IF NOT EXISTS idx_articles_content_hash
+    ON articles(content_hash);
+
+CREATE TABLE IF NOT EXISTS crawl_runs (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    started_at TEXT NOT NULL,
+    finished_at TEXT,
+    status TEXT NOT NULL DEFAULT 'running',
+    discovered_count INTEGER NOT NULL DEFAULT 0,
+    inserted_count INTEGER NOT NULL DEFAULT 0,
+    updated_count INTEGER NOT NULL DEFAULT 0,
+    failed_count INTEGER NOT NULL DEFAULT 0,
+    message TEXT
+);
+
+CREATE TABLE IF NOT EXISTS ai_analyses (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    article_id INTEGER NOT NULL,
+    model TEXT NOT NULL,
+    analysis_type TEXT NOT NULL DEFAULT 'editorial',
+    result_json TEXT NOT NULL,
+    content_hash TEXT,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE(article_id, model, analysis_type),
+    FOREIGN KEY(article_id) REFERENCES articles(id) ON DELETE CASCADE
+);
+
+CREATE INDEX IF NOT EXISTS idx_ai_analyses_article
+    ON ai_analyses(article_id, updated_at);
+
+CREATE TABLE IF NOT EXISTS industry_signals (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    signal_date TEXT NOT NULL,
+    title TEXT NOT NULL,
+    summary TEXT NOT NULL,
+    trend TEXT NOT NULL DEFAULT 'emerging',
+    confidence REAL NOT NULL DEFAULT 0.5,
+    implications_json TEXT NOT NULL DEFAULT '[]',
+    article_ids_json TEXT NOT NULL DEFAULT '[]',
+    tags_json TEXT NOT NULL DEFAULT '[]',
+    model TEXT NOT NULL,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE(signal_date, title)
+);
+
+CREATE INDEX IF NOT EXISTS idx_industry_signals_date
+    ON industry_signals(signal_date DESC, confidence DESC);
+