ref: move ML stuff

add: .idea to VCS, the refactor guide

.gitignore

@@ -51,7 +51,6 @@ internal/
 !tests/cases/projects/projectOption/**/node_modules
 !tests/cases/projects/NodeModulesSearch/**/*
 !tests/baselines/reference/project/nodeModules*/**/*
-.idea
 yarn.lock
 yarn-error.log
 .parallelperf.*
@@ -78,10 +77,10 @@ node_modules/
 # project specific
 logs/
 __pycache__
-filter/runs
-pred/runs
-pred/checkpoints
-data/
-filter/checkpoints
+ml/filter/runs
+ml/pred/runs
+ml/pred/checkpoints
+ml/data/
+ml/filter/checkpoints
 scripts
 model/

.idea/.gitignore

@@ -0,0 +1,9 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
+dataSources.xml

.idea/cvsa.iml

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="WEB_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.tmp" />
+      <excludeFolder url="file://$MODULE_DIR$/temp" />
+      <excludeFolder url="file://$MODULE_DIR$/tmp" />
+      <excludeFolder url="file://$MODULE_DIR$/ml/data" />
+      <excludeFolder url="file://$MODULE_DIR$/doc" />
+      <excludeFolder url="file://$MODULE_DIR$/ml/filter/checkpoints" />
+      <excludeFolder url="file://$MODULE_DIR$/ml/filter/runs" />
+      <excludeFolder url="file://$MODULE_DIR$/ml/lab/data" />
+      <excludeFolder url="file://$MODULE_DIR$/ml/lab/temp" />
+      <excludeFolder url="file://$MODULE_DIR$/logs" />
+      <excludeFolder url="file://$MODULE_DIR$/model" />
+      <excludeFolder url="file://$MODULE_DIR$/src/db" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,12 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="GrazieInspection" enabled="false" level="GRAMMAR_ERROR" enabled_by_default="false" />
+    <inspection_tool class="LanguageDetectionInspection" enabled="false" level="WARNING" enabled_by_default="false" />
+    <inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
+      <option name="processCode" value="true" />
+      <option name="processLiterals" value="true" />
+      <option name="processComments" value="true" />
+    </inspection_tool>
+  </profile>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/cvsa.iml" filepath="$PROJECT_DIR$/.idea/cvsa.iml" />
+    </modules>
+  </component>
+</project>

.idea/sqldialects.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="SqlDialectMappings">
+    <file url="PROJECT" dialect="PostgreSQL" />
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

README-refactor.md

@@ -0,0 +1,65 @@
+# 项目重构方案
+
+## 目标架构
+采用monorepo结构管理三个独立部分：
+1. `packages/crawler` - 现有爬虫功能
+2. `packages/frontend` - 基于Astro的前端
+3. `packages/backend` - 基于Hono的API后端
+
+## 目录结构调整方案
+
+### 新结构
+```
+.
+├── packages/
+│   ├── crawler/       # 爬虫组件
+│   ├── frontend/      # Astro前端 
+│   ├── backend/       # Hono后端API
+│   └── core/          # 共享代码(未来提取)
+├── docs/              # 文档
+├── scripts/           # 项目脚本
+└── package.json       # 根项目配置
+```
+
+### 具体迁移方案
+
+#### 1. 爬虫部分(crawler)
+保留以下目录/文件：
+- `lib/` (除前端相关)
+- `src/db/raw/` 
+- `src/filterWorker.ts`
+- `src/worker.ts`
+- `test/`
+- `deno.json`
+- `.gitignore`
+
+需要移除：
+- Fresh框架相关文件
+- 前端组件(`components/`)
+- 静态资源(`static/`)
+
+#### 2. 前端部分(frontend)
+全新创建Astro项目，不保留任何现有前端代码
+
+#### 3. 后端部分(backend)
+全新创建Hono项目
+
+#### 4. 共享代码(core)
+未来可从爬虫中提取以下内容到core package：
+- 数据库相关：`lib/db/`
+- 消息队列：`lib/mq/`
+- 网络请求：`lib/net/`
+- 工具函数：`lib/utils/`
+
+## 重构步骤建议
+
+1. 初始化monorepo结构
+2. 迁移爬虫代码到`packages/crawler`
+3. 创建新的Astro项目在`packages/frontend`
+4. 创建新的Hono项目在`packages/backend`
+5. 逐步提取共享代码到`packages/core`
+
+## 注意事项
+- 机器学习相关代码(`pred/`, `filter/`, `lab/`)保持现状
+- 文档(`doc/`)可以迁移到`docs/`目录
+- 需要更新CI/CD流程支持monorepo

components/Button.tsx

@@ -1,12 +0,0 @@
-import { JSX } from "preact";
-import { IS_BROWSER } from "$fresh/runtime.ts";
-
-export function Button(props: JSX.HTMLAttributes<HTMLButtonElement>) {
-	return (
-		<button
-			{...props}
-			disabled={!IS_BROWSER || props.disabled}
-			class="px-2 py-1 border-gray-500 border-2 rounded bg-white hover:bg-gray-200 transition-colors"
-		/>
-	);
-}

data/filter/1.py

@@ -1,55 +0,0 @@
-import json
-import random
-
-def process_data(input_file, output_file):
-    """
-    从输入文件中读取数据，找出model和human不一致的行，
-    删除"model"键，将"human"键重命名为"label"，
-    然后将处理后的数据添加到输出文件中。
-    在写入之前，它会加载output_file中的所有样本，
-    并使用aid键进行去重过滤。
-
-    Args:
-        input_file (str): 输入文件的路径。
-        output_file (str): 输出文件的路径。
-    """
-
-    # 加载output_file中已有的数据，用于去重
-    existing_data = set()
-    try:
-        with open(output_file, 'r', encoding='utf-8') as f_out:
-            for line in f_out:
-                try:
-                    data = json.loads(line)
-                    existing_data.add(data['aid'])
-                except json.JSONDecodeError:
-                    pass  # 忽略JSON解码错误，继续读取下一行
-    except FileNotFoundError:
-        pass  # 如果文件不存在，则忽略
-
-    with open(input_file, 'r', encoding='utf-8') as f_in, open(output_file, 'a', encoding='utf-8') as f_out:
-        for line in f_in:
-            try:
-                data = json.loads(line)
-
-                if data['model'] != data['human'] or random.random() < 0.2:
-                    if data['aid'] not in existing_data:  # 检查aid是否已存在
-                        del data['model']
-                        data['label'] = data['human']
-                        del data['human']
-                        f_out.write(json.dumps(data, ensure_ascii=False) + '\n')
-                        existing_data.add(data['aid'])  # 将新的aid添加到集合中
-
-            except json.JSONDecodeError as e:
-                print(f"JSON解码错误: {e}")
-                print(f"错误行内容: {line.strip()}")
-            except KeyError as e:
-                print(f"KeyError: 键 '{e}' 不存在")
-                print(f"错误行内容: {line.strip()}")
-
-# 调用函数处理数据
-input_file = 'real_test.jsonl'
-output_file = 'labeled_data.jsonl'
-process_data(input_file, output_file)
-print(f"处理完成，结果已写入 {output_file}")
-

dev.ts

@@ -1,7 +0,0 @@
-#!/usr/bin/env -S deno run -A --watch=static/,routes/
-
-import dev from "$fresh/dev.ts";
-import config from "./fresh.config.ts";
-
-import "$std/dotenv/load.ts";
-await dev(import.meta.url, "./main.ts", config);

fresh.config.ts

@@ -1,6 +0,0 @@
-import { defineConfig } from "$fresh/server.ts";
-import tailwind from "$fresh/plugins/tailwind.ts";
-
-export default defineConfig({
-	plugins: [tailwind()],
-});

fresh.gen.ts

@@ -1,27 +0,0 @@
-// DO NOT EDIT. This file is generated by Fresh.
-// This file SHOULD be checked into source version control.
-// This file is automatically updated during development when running `dev.ts`.
-
-import * as $_404 from "./routes/_404.tsx";
-import * as $_app from "./routes/_app.tsx";
-import * as $api_joke from "./routes/api/joke.ts";
-import * as $greet_name_ from "./routes/greet/[name].tsx";
-import * as $index from "./routes/index.tsx";
-import * as $Counter from "./islands/Counter.tsx";
-import type { Manifest } from "$fresh/server.ts";
-
-const manifest = {
-	routes: {
-		"./routes/_404.tsx": $_404,
-		"./routes/_app.tsx": $_app,
-		"./routes/api/joke.ts": $api_joke,
-		"./routes/greet/[name].tsx": $greet_name_,
-		"./routes/index.tsx": $index,
-	},
-	islands: {
-		"./islands/Counter.tsx": $Counter,
-	},
-	baseUrl: import.meta.url,
-} satisfies Manifest;
-
-export default manifest;

islands/Counter.tsx

@@ -1,16 +0,0 @@
-import type { Signal } from "@preact/signals";
-import { Button } from "../components/Button.tsx";
-
-interface CounterProps {
-	count: Signal<number>;
-}
-
-export default function Counter(props: CounterProps) {
-	return (
-		<div class="flex gap-8 py-6">
-			<Button onClick={() => props.count.value -= 1}>-1</Button>
-			<p class="text-3xl tabular-nums">{props.count}</p>
-			<Button onClick={() => props.count.value += 1}>+1</Button>
-		</div>
-	);
-}

main.ts

@@ -1,13 +0,0 @@
-/// <reference no-default-lib="true" />
-/// <reference lib="dom" />
-/// <reference lib="dom.iterable" />
-/// <reference lib="dom.asynciterable" />
-/// <reference lib="deno.ns" />
-
-import "$std/dotenv/load.ts";
-
-import { start } from "$fresh/server.ts";
-import manifest from "./fresh.gen.ts";
-import config from "./fresh.config.ts";
-
-await start(manifest, config);

routes/_404.tsx

@@ -1,27 +0,0 @@
-import { Head } from "$fresh/runtime.ts";
-
-export default function Error404() {
-	return (
-		<>
-			<Head>
-				<title>404 - Page not found</title>
-			</Head>
-			<div class="px-4 py-8 mx-auto bg-[#86efac]">
-				<div class="max-w-screen-md mx-auto flex flex-col items-center justify-center">
-					<img
-						class="my-6"
-						src="/logo.svg"
-						width="128"
-						height="128"
-						alt="the Fresh logo: a sliced lemon dripping with juice"
-					/>
-					<h1 class="text-4xl font-bold">404 - Page not found</h1>
-					<p class="my-4">
-						The page you were looking for doesn't exist.
-					</p>
-					<a href="/" class="underline">Go back home</a>
-				</div>
-			</div>
-		</>
-	);
-}

routes/_app.tsx

@@ -1,16 +0,0 @@
-import { type PageProps } from "$fresh/server.ts";
-export default function App({ Component }: PageProps) {
-	return (
-		<html>
-			<head>
-				<meta charset="utf-8" />
-				<meta name="viewport" content="width=device-width, initial-scale=1.0" />
-				<title>cvsa</title>
-				<link rel="stylesheet" href="/styles.css" />
-			</head>
-			<body>
-				<Component />
-			</body>
-		</html>
-	);
-}

routes/api/joke.ts

@@ -1,21 +0,0 @@
-import { FreshContext } from "$fresh/server.ts";
-
-// Jokes courtesy of https://punsandoneliners.com/randomness/programmer-jokes/
-const JOKES = [
-	"Why do Java developers often wear glasses? They can't C#.",
-	"A SQL query walks into a bar, goes up to two tables and says “can I join you?”",
-	"Wasn't hard to crack Forrest Gump's password. 1forrest1.",
-	"I love pressing the F5 key. It's refreshing.",
-	"Called IT support and a chap from Australia came to fix my network connection.  I asked “Do you come from a LAN down under?”",
-	"There are 10 types of people in the world. Those who understand binary and those who don't.",
-	"Why are assembly programmers often wet? They work below C level.",
-	"My favourite computer based band is the Black IPs.",
-	"What programme do you use to predict the music tastes of former US presidential candidates? An Al Gore Rhythm.",
-	"An SEO expert walked into a bar, pub, inn, tavern, hostelry, public house.",
-];
-
-export const handler = (_req: Request, _ctx: FreshContext): Response => {
-	const randomIndex = Math.floor(Math.random() * JOKES.length);
-	const body = JOKES[randomIndex];
-	return new Response(body);
-};

routes/greet/[name].tsx

@@ -1,5 +0,0 @@
-import { PageProps } from "$fresh/server.ts";
-
-export default function Greet(props: PageProps) {
-	return <div>Hello {props.params.name}</div>;
-}

routes/index.tsx

@@ -1,25 +0,0 @@
-import { useSignal } from "@preact/signals";
-import Counter from "../islands/Counter.tsx";
-
-export default function Home() {
-	const count = useSignal(3);
-	return (
-		<div class="px-4 py-8 mx-auto bg-[#86efac]">
-			<div class="max-w-screen-md mx-auto flex flex-col items-center justify-center">
-				<img
-					class="my-6"
-					src="/logo.svg"
-					width="128"
-					height="128"
-					alt="the Fresh logo: a sliced lemon dripping with juice"
-				/>
-				<h1 class="text-4xl font-bold">Welcome to Fresh</h1>
-				<p class="my-4">
-					Try updating this message in the
-					<code class="mx-2">./routes/index.tsx</code> file, and refresh.
-				</p>
-				<Counter count={count} />
-			</div>
-		</div>
-	);
-}

static/logo.svg

@@ -1,6 +0,0 @@
-<svg width="40" height="40" fill="none" xmlns="http://www.w3.org/2000/svg">
-  <path d="M34.092 8.845C38.929 20.652 34.092 27 30 30.5c1 3.5-2.986 4.222-4.5 2.5-4.457 1.537-13.512 1.487-20-5C2 24.5 4.73 16.714 14 11.5c8-4.5 16-7 20.092-2.655Z" fill="#FFDB1E"/>
-  <path d="M14 11.5c6.848-4.497 15.025-6.38 18.368-3.47C37.5 12.5 21.5 22.612 15.5 25c-6.5 2.587-3 8.5-6.5 8.5-3 0-2.5-4-5.183-7.75C2.232 23.535 6.16 16.648 14 11.5Z" fill="#fff" stroke="#FFDB1E"/>
-  <path d="M28.535 8.772c4.645 1.25-.365 5.695-4.303 8.536-3.732 2.692-6.606 4.21-7.923 4.83-.366.173-1.617-2.252-1.617-1 0 .417-.7 2.238-.934 2.326-1.365.512-4.223 1.29-5.835 1.29-3.491 0-1.923-4.754 3.014-9.122.892-.789 1.478-.645 2.283-.645-.537-.773-.534-.917.403-1.546C17.79 10.64 23 8.77 25.212 8.42c.366.014.82.35.82.629.41-.14 2.095-.388 2.503-.278Z" fill="#FFE600"/>
-  <path d="M14.297 16.49c.985-.747 1.644-1.01 2.099-2.526.566.121.841-.08 1.29-.701.324.466 1.657.608 2.453.701-.715.451-1.057.852-1.452 2.106-1.464-.611-3.167-.302-4.39.42Z" fill="#fff"/>
-</svg>

static/styles.css

@@ -1,3 +0,0 @@
-@tailwind base;
-@tailwind components;
-@tailwind utilities;

tailwind.config.ts

@@ -1,7 +0,0 @@
-import { type Config } from "tailwindcss";
-
-export default {
-	content: [
-		"{routes,islands,components}/**/*.{ts,tsx,js,jsx}",
-	],
-} satisfies Config;