@liangjiehappy/dsh-plugin-mfgabc 0.0.0-stage → 0.1.0

package/README.md

@@ -1,3 +1,41 @@
-# Temporary Holding Version
+# dsh-plugin-mfgabc
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+mfgabc.com 只读查询插件：标准页、产业带城市、工艺集群、跨境合规、任意站内页。
+
+## 工具
+
+| 工具 | 作用 |
+|---|---|
+| `mfgabc_standard` | 标准号 → 标准页（状态/标题/链接） |
+| `mfgabc_city` | 城市产业带页 |
+| `mfgabc_process` | 工艺集群页（工艺 + 城市） |
+| `mfgabc_compliance` | 跨境合规页（品类 + 国家） |
+| `mfgabc_page` | 任意站内路径查询 |
+
+## 安装
+
+```bash
+dsh plugin --profile web add @liangjiehappy/dsh-plugin-mfgabc
+```
+
+## 配置
+
+```yaml
+- insert:
+    - id: dsh-plugin-mfgabc
+      name: dsh-plugin-mfgabc
+      config:
+        baseUrl: "https://www.mfgabc.com"
+```
+
+## 权限声明
+
+- 只对 `www.mfgabc.com` 发 HTTPS GET
+- 不读写文件、不读凭证、不执行 shell
+- 只读：不提交表单、不登录、不写数据
+
+## 限制
+
+- mfgabc 以静态页为主，工具返回页面状态/标题/链接，不做全文提取
+- 标准页 slug 由标准号规范化生成；个别标准可能 404，工具会如实返回状态码
+- 站点对 AI 训练爬虫有 403 策略；本插件以普通 UA 访问公开页面

package/cordis.patch.yml

@@ -0,0 +1,5 @@
+- insert:
+    - id: dsh-plugin-mfgabc
+      name: "@liangjiehappy/dsh-plugin-mfgabc"
+      config:
+        baseUrl: "https://www.mfgabc.com"

package/lib/core.js

@@ -0,0 +1,57 @@
+// dsh-plugin-mfgabc · 纯函数：站内路径构造与 HTML 解析
+export const DEFAULT_BASE = 'https://www.mfgabc.com'
+
+export function normalizeBase(base) {
+  const b = (base || DEFAULT_BASE).trim().replace(/\/+$/, '')
+  if (!/^https?:\/\//i.test(b)) throw new Error('baseUrl 必须以 http(s):// 开头')
+  return b
+}
+
+export function slugify(s) {
+  return String(s || '')
+    .trim()
+    .toLowerCase()
+    .replace(/[\/\s_.]+/g, '-')
+    .replace(/[^a-z0-9\u4e00-\u9fa5-]+/g, '')
+    .replace(/-+/g, '-')
+    .replace(/^-|-$/g, '')
+}
+
+/** 标准号 → mfgabc 标准页 slug：ISO 4703-1977 → ISO-4703-1977 */
+export function normalizeStandard(no) {
+  return String(no || '')
+    .trim()
+    .toUpperCase()
+    .replace(/[\/\s_]+/g, '-')
+    .replace(/\./g, '-')
+    .replace(/-+/g, '-')
+    .replace(/^-|-$/g, '')
+}
+
+export function buildSiteUrl(base, path) {
+  if (!isSafePath(path)) throw new Error('非法站内路径')
+  return normalizeBase(base) + path
+}
+
+export function isSafePath(path) {
+  if (typeof path !== 'string' || !path.startsWith('/')) return false
+  if (path.includes('..') || path.includes('//')) return false
+  if (/[\s"'<>\\]/.test(path)) return false
+  return path.length <= 512
+}
+
+export function extractTitle(html) {
+  const m = String(html || '').match(/<title[^>]*>([\s\S]*?)<\/title>/i)
+  if (!m) return ''
+  return decodeEntities(m[1]).replace(/\s+/g, ' ').trim().slice(0, 200)
+}
+
+export function decodeEntities(s) {
+  return String(s)
+    .replace(/&amp;/g, '&')
+    .replace(/&lt;/g, '<')
+    .replace(/&gt;/g, '>')
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;|&apos;/g, "'")
+    .replace(/&nbsp;/g, ' ')
+}

package/lib/index.js

@@ -0,0 +1,100 @@
+// dsh-plugin-mfgabc · mfgabc.com 只读页面查询
+import { defineTool } from '@deepseek-ai/dsh-tools'
+import {
+  DEFAULT_BASE, normalizeBase, normalizeStandard, slugify,
+  buildSiteUrl, isSafePath, extractTitle,
+} from './core.js'
+
+export const name = 'dsh-plugin-mfgabc'
+export const inject = ['tools']
+
+const text = (value) => [{ type: 'text', text: JSON.stringify(value, null, 2) }]
+const headers = { 'user-agent': 'dsh-plugin-mfgabc/0.1', accept: 'text/html' }
+
+export function apply(ctx, config = {}) {
+  const base = normalizeBase(config.baseUrl)
+
+  async function fetchPage(path, signal) {
+    const url = buildSiteUrl(base, path)
+    const r = await fetch(url, { headers, signal, redirect: 'follow' })
+    const html = await r.text()
+    return {
+      ok: r.ok,
+      status: r.status,
+      url: r.url || url,
+      title: extractTitle(html),
+    }
+  }
+
+  ctx.tools.register(defineTool({
+    name: 'mfgabc_standard',
+    description: '查 mfgabc.com 标准页：给标准号（如 ISO 4703-1977、GB/T 9114-2010），返回页面状态、标题与官方链接。',
+    parameters: {
+      number: { type: 'string', required: true, description: '标准号，如“ISO 4703-1977”' },
+    },
+    output: { schema: { type: 'json' }, render: (_a, v) => text(v) },
+    isConcurrencySafe: () => true,
+    async execute(args, exec) {
+      const slug = normalizeStandard(args.number)
+      return { slug, ...(await fetchPage(`/standards/s/${slug}/`, exec.signal)) }
+    },
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'mfgabc_city',
+    description: '查 mfgabc.com 产业带城市页（如 dongguan、shenzhen）。',
+    parameters: {
+      city: { type: 'string', required: true, description: '城市英文 slug，如 dongguan' },
+    },
+    output: { schema: { type: 'json' }, render: (_a, v) => text(v) },
+    isConcurrencySafe: () => true,
+    async execute(args, exec) {
+      const slug = slugify(args.city)
+      return { city: slug, ...(await fetchPage(`/cities/${slug}/`, exec.signal)) }
+    },
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'mfgabc_process',
+    description: '查 mfgabc.com 工艺集群页（城市 + 工艺，如 dongguan + stamping-die）。',
+    parameters: {
+      process: { type: 'string', required: true, description: '工艺 slug，如 stamping-die' },
+      city: { type: 'string', required: true, description: '城市 slug，如 dongguan' },
+    },
+    output: { schema: { type: 'json' }, render: (_a, v) => text(v) },
+    isConcurrencySafe: () => true,
+    async execute(args, exec) {
+      const p = slugify(args.process), c = slugify(args.city)
+      return { process: p, city: c, ...(await fetchPage(`/guide/clusters/${p}/${c}/`, exec.signal)) }
+    },
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'mfgabc_compliance',
+    description: '查 mfgabc.com 跨境合规页（品类 + 国家，如 plastic-products + singapore）。',
+    parameters: {
+      category: { type: 'string', required: true, description: '品类 slug，如 plastic-products' },
+      country: { type: 'string', required: true, description: '国家 slug，如 singapore' },
+    },
+    output: { schema: { type: 'json' }, render: (_a, v) => text(v) },
+    isConcurrencySafe: () => true,
+    async execute(args, exec) {
+      const cat = slugify(args.category), c = slugify(args.country)
+      return { category: cat, country: c, ...(await fetchPage(`/compliance/${cat}-${c}/`, exec.signal)) }
+    },
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'mfgabc_page',
+    description: '取 mfgabc.com 任意站内页面的状态、标题与最终链接（用于标准/材料/指南等已知路径）。',
+    parameters: {
+      path: { type: 'string', required: true, description: '站内路径，以 / 开头，如 /standards/' },
+    },
+    output: { schema: { type: 'json' }, render: (_a, v) => text(v) },
+    isConcurrencySafe: () => true,
+    async execute(args, exec) {
+      if (!isSafePath(args.path)) throw new Error('path 必须是站内绝对路径（以 / 开头，不含 .. 或 //）')
+      return fetchPage(args.path, exec.signal)
+    },
+  }))
+}

package/package.json

@@ -1,6 +1,37 @@
 {
   "name": "@liangjiehappy/dsh-plugin-mfgabc",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.0",
+  "description": "mfgabc.com 制造业内容查询：标准页、产业带城市、工艺集群、跨境合规。只访问 www.mfgabc.com。",
+  "type": "module",
+  "main": "lib/index.js",
+  "files": [
+    "lib",
+    "cordis.patch.yml",
+    "README.md"
+  ],
+  "dsh": {
+    "bundle": {
+      "patch": "./cordis.patch.yml"
+    }
+  },
+  "engines": {
+    "dsh": ">=0.2.0"
+  },
+  "peerDependencies": {
+    "@deepseek-ai/cordis": "*",
+    "@deepseek-ai/dsh-tools": "*"
+  },
+  "keywords": [
+    "deepseek-harness",
+    "dsh",
+    "dsh-plugin",
+    "mfgabc",
+    "manufacturing",
+    "standards",
+    "supply-chain"
+  ],
+  "license": "MIT",
+  "scripts": {
+    "test": "node --test"
+  }
+}