dsh-linked-workspace 0.5.12 → 0.6.0

package/lib/index.js

@@ -16,11 +16,12 @@
  * addresses and workspace paths.
  */
 import { randomUUID } from 'node:crypto'
-import { chmodSync, cpSync, existsSync, mkdirSync, readFileSync, readdirSync, renameSync, rmSync, writeFileSync } from 'node:fs'
+import { chmodSync, cpSync, existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, renameSync, rmSync, writeFileSync } from 'node:fs'
 import { spawn } from 'node:child_process'
 import { mkdir, readdir, stat as fsStat } from 'node:fs/promises'
 import { homedir, tmpdir } from 'node:os'
-import { basename, dirname, isAbsolute, join, posix, resolve, sep } from 'node:path'
+import { basename, dirname, extname, isAbsolute, join, posix, resolve, sep } from 'node:path'
+import { fileURLToPath } from 'node:url'
 import { listHosts, RemoteHost, SshError } from './ssh.js'
 import * as linkedFs from './linked.js'
 import * as git from './git.js'
@@ -1423,6 +1424,129 @@ export function apply(ctx) {
     }
   }
 
+  // ── document bridge (Markdown/PDF/DOCX/XLSX/PPTX) ──────────────────────
+
+  const DOC_MAX_BYTES = 80 * 1024 * 1024
+  const DOC_TOOL = join(dirname(fileURLToPath(import.meta.url)), '..', 'scripts', 'doc_tool.py')
+  const DOC_KIND_BY_EXT = new Map([
+    ['.md', 'markdown'], ['.markdown', 'markdown'],
+    ['.pdf', 'pdf'], ['.docx', 'docx'], ['.xlsx', 'xlsx'], ['.pptx', 'pptx'],
+  ])
+
+  function docKind(path) {
+    return DOC_KIND_BY_EXT.get(extname(String(path || '')).toLowerCase()) || ''
+  }
+
+  function docPython() {
+    return process.env.DSH_OFFICE_PYTHON || process.env.DSH_PYTHON || (process.platform === 'win32' ? 'python' : 'python3')
+  }
+
+  function runDocTool(args, timeoutMs = 120000) {
+    return new Promise((resolvePromise, rejectPromise) => {
+      let child
+      try {
+        child = spawn(docPython(), [DOC_TOOL, ...args], { windowsHide: true })
+      } catch (error) {
+        rejectPromise(new ApiError('DOC_RUNTIME', '需要 Python 3 与文档库：' + (error && error.message ? error.message : error)))
+        return
+      }
+      const out = []
+      const err = []
+      const timer = setTimeout(() => {
+        try { child.kill() } catch { /* already gone */ }
+        rejectPromise(new ApiError('DOC_TIMEOUT', '文档处理超时'))
+      }, timeoutMs)
+      child.stdout.on('data', (chunk) => out.push(chunk))
+      child.stderr.on('data', (chunk) => err.push(chunk))
+      child.on('error', (error) => {
+        clearTimeout(timer)
+        if (error && error.code === 'ENOENT') {
+          rejectPromise(new ApiError('DOC_RUNTIME', '未找到 Python。请安装 Python 3 以及 python-docx / openpyxl / python-pptx / PyMuPDF，或设置 DSH_OFFICE_PYTHON。'))
+        } else {
+          rejectPromise(new ApiError('DOC_RUNTIME', error && error.message ? error.message : String(error)))
+        }
+      })
+      child.on('close', (code) => {
+        clearTimeout(timer)
+        const stdout = Buffer.concat(out).toString('utf8')
+        const stderr = Buffer.concat(err).toString('utf8')
+        let parsed
+        try {
+          parsed = JSON.parse(stdout.trim().split(String.fromCharCode(10)).filter(Boolean).pop() || '{}')
+        } catch {
+          parsed = null
+        }
+        if (code !== 0 || !parsed || parsed.ok !== true) {
+          const message = (parsed && parsed.error) || stderr.trim() || ('文档处理失败（退出码 ' + code + '）')
+          rejectPromise(new ApiError('DOC_FAILED', String(message).slice(0, 800)))
+          return
+        }
+        resolvePromise(parsed.data)
+      })
+    })
+  }
+
+  async function docTarget(params) {
+    if (params.linkedId || params.workspaceId) {
+      const scope = await requireScope(params)
+      const target = scopeTarget(scope, params.path)
+      return { remote: true, scope, path: target }
+    }
+    const raw = typeof params.path === 'string' ? params.path.trim() : ''
+    if (raw === '' || !isAbsolute(raw)) throw new ApiError('BAD_REQUEST', '本地路径必须是绝对路径')
+    return { remote: false, path: resolve(raw) }
+  }
+
+  async function readDocBytes(target, current) {
+    if (!current.remote) {
+      const info = await fsStat(current.path)
+      if (!info.isFile()) throw new ApiError('FS_NOT_DIR', '只能打开文件')
+      if (info.size > DOC_MAX_BYTES) throw new ApiError('DOC_TOO_LARGE', '文档超过 80 MB')
+      return { data: readFileSync(current.path), mtime: info.mtimeMs, size: info.size }
+    }
+    const stat = await current.scope.remote.stat(current.path)
+    if (stat.type !== 'file') throw new ApiError('FS_NOT_DIR', '只能打开文件')
+    if (stat.size > DOC_MAX_BYTES) throw new ApiError('DOC_TOO_LARGE', '文档超过 80 MB')
+    const read = await current.scope.remote.readFile(current.path, { maxBytes: DOC_MAX_BYTES })
+    return { data: read.data, mtime: stat.mtime, size: stat.size }
+  }
+
+  async function writeDocBytes(target, data) {
+    if (!target.remote) {
+      await mkdir(dirname(target.path), { recursive: true })
+      const temp = target.path + '.' + randomUUID() + '.tmp'
+      writeFileSync(temp, data)
+      try { renameSync(temp, target.path) } catch (error) { rmSync(temp, { force: true }); throw error }
+      const info = await fsStat(target.path)
+      return { path: target.path, size: info.size, mtime: info.mtimeMs }
+    }
+    const result = await target.scope.remote.writeFileAtomic(target.path, data)
+    return { path: target.path, size: result.size, mtime: result.mtime }
+  }
+
+  async function makeDocTemp() {
+    const directory = mkdtempSync(join(tmpdir(), 'dsh-doc-'))
+    return {
+      dir: directory,
+      file(name) { return join(directory, name) },
+      cleanup() { try { rmSync(directory, { recursive: true, force: true }) } catch { /* best effort */ } },
+    }
+  }
+
+  function assertDocKind(path, expected) {
+    const kind = docKind(path)
+    if (kind === '') throw new ApiError('DOC_UNSUPPORTED', '仅支持 Markdown、PDF、DOCX、XLSX、PPTX')
+    if (expected && expected !== kind) throw new ApiError('DOC_UNSUPPORTED', '文件类型与请求不一致')
+    return kind
+  }
+
+  async function docStat(target) {
+    if (!target.remote) {
+      try { const info = await fsStat(target.path); return info } catch { return null }
+    }
+    try { return await target.scope.remote.stat(target.path) } catch { return null }
+  }
+
   // ── method table ─────────────────────────────────────────────────────────
 
   const methods = {
@@ -1606,6 +1730,136 @@ export function apply(ctx) {
       return { path: target, size: info.size, mtime: info.mtime }
     },
 
+    async 'docs.read'(params = {}) {
+      const target = await docTarget(params)
+      const kind = assertDocKind(target.path)
+      const current = await readDocBytes(target, target)
+      if (kind === 'markdown') {
+        if (looksBinary(current.data)) throw new ApiError('DOC_BINARY', 'Markdown 文件包含二进制内容')
+        return { kind, path: target.path, text: decodeUtf8(current.data), size: current.size, mtime: current.mtime }
+      }
+      const temp = await makeDocTemp()
+      try {
+        const input = temp.file('input.' + (kind === 'markdown' ? 'md' : kind))
+        writeFileSync(input, current.data)
+        const data = await runDocTool(['read', '--kind', kind, '--file', input])
+        return { ...data, path: target.path, size: current.size, mtime: current.mtime }
+      } finally {
+        temp.cleanup()
+      }
+    },
+
+    async 'docs.write'(params = {}) {
+      const target = await docTarget(params)
+      const kind = assertDocKind(target.path)
+      const data = params.data
+      if (!data || typeof data !== 'object') throw new ApiError('BAD_REQUEST', '缺少文档数据')
+      if (typeof params.expectedMtime === 'number' && params.expectedMtime > 0) {
+        const current = await docStat(target)
+        if (current && Math.floor(current.mtime / 1000) !== Math.floor(params.expectedMtime / 1000)) {
+          throw new ApiError('CONFLICT', '文件已被修改，请重新加载后再保存')
+        }
+      }
+      if (kind === 'markdown') {
+        if (typeof data.text !== 'string') throw new ApiError('BAD_REQUEST', 'Markdown 内容无效')
+        const written = await writeDocBytes(target, Buffer.from(data.text, 'utf8'))
+        return { kind, ...written }
+      }
+      const current = await readDocBytes(target, target)
+      const temp = await makeDocTemp()
+      try {
+        const source = temp.file('source.' + kind)
+        const spec = temp.file('data.json')
+        const output = temp.file('output.' + kind)
+        writeFileSync(source, current.data)
+        writeFileSync(spec, JSON.stringify(data))
+        await runDocTool(['write', '--kind', kind, '--file', source, '--data', spec, '--out', output])
+        const written = await writeDocBytes(target, readFileSync(output))
+        return { kind, ...written }
+      } finally {
+        temp.cleanup()
+      }
+    },
+
+    async 'docs.create'(params = {}) {
+      const target = await docTarget(params)
+      const kind = assertDocKind(target.path, params.kind)
+      const existing = await docStat(target)
+      if (existing) throw new ApiError('FS_EXISTS', '目标文件已存在')
+      const temp = await makeDocTemp()
+      try {
+        const cliKind = kind === 'markdown' ? 'md' : kind
+        const output = temp.file('new.' + cliKind)
+        await runDocTool(['create', '--kind', cliKind, '--out', output])
+        const written = await writeDocBytes(target, readFileSync(output))
+        return { kind, ...written }
+      } finally {
+        temp.cleanup()
+      }
+    },
+
+    async 'docs.mdPreview'(params = {}) {
+      const target = await docTarget(params)
+      assertDocKind(target.path, 'markdown')
+      let text = typeof params.text === 'string' ? params.text : null
+      if (text === null) {
+        const current = await readDocBytes(target, target)
+        text = decodeUtf8(current.data)
+      }
+      const temp = await makeDocTemp()
+      try {
+        const input = temp.file('preview.md')
+        writeFileSync(input, text, 'utf8')
+        const data = await runDocTool(['md-preview', '--file', input])
+        return data
+      } finally {
+        temp.cleanup()
+      }
+    },
+
+    async 'docs.mdPdf'(params = {}) {
+      const target = await docTarget(params)
+      assertDocKind(target.path, 'markdown')
+      let text = typeof params.text === 'string' ? params.text : null
+      if (text === null) {
+        const current = await readDocBytes(target, target)
+        text = decodeUtf8(current.data)
+      }
+      const extension = extname(target.path)
+      const base = target.path.slice(0, -extension.length)
+      let outputPath = base + '.pdf'
+      if (target.remote) {
+        const directory = posix.dirname(outputPath)
+        let candidate = outputPath
+        let index = 1
+        while (await target.scope.remote.stat(candidate).catch(() => null)) {
+          candidate = posix.join(directory, posix.basename(base) + '-' + index + '.pdf')
+          index += 1
+        }
+        outputPath = candidate
+      } else {
+        const directory = dirname(outputPath)
+        let candidate = outputPath
+        let index = 1
+        while (existsSync(candidate)) {
+          candidate = join(directory, basename(base) + '-' + index + '.pdf')
+          index += 1
+        }
+        outputPath = candidate
+      }
+      const temp = await makeDocTemp()
+      try {
+        const input = temp.file('export.md')
+        const output = temp.file('export.pdf')
+        writeFileSync(input, text, 'utf8')
+        await runDocTool(['md-pdf', '--file', input, '--out', output], 180000)
+        const written = await writeDocBytes({ ...target, path: outputPath }, readFileSync(output))
+        return { kind: 'pdf', ...written }
+      } finally {
+        temp.cleanup()
+      }
+    },
+
     async 'fs.stat'(params = {}) {
       const scope = await requireScope(params)
       const target = scopeTarget(scope, params.path)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-linked-workspace",
-  "version": "0.5.12",
+  "version": "0.6.0",
   "description": "Linked local ⇄ remote workspaces and SSH-backed remote directories for DeepSeek Harness: theme-aware split editor, file-type icons, and an agent tool that edits remote files directly.",
   "type": "module",
   "main": "lib/index.js",
@@ -22,7 +22,8 @@
     "LICENSE",
     "README.en.md",
     "docs/API.md",
-    "docs/VERIFY.md"
+    "docs/VERIFY.md",
+    "scripts/doc_tool.py"
   ],
   "keywords": [
     "deepseek-harness",