npm - markpdfdown - Versions diffs - 0.1.0 - Mend

markpdfdown 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (81) hide show

package/dist/renderer/index.html ADDED Viewed

@@ -0,0 +1,14 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>MarkPDFdown</title>
+    <script type="module" crossorigin src="./assets/index-DeDe7lry.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-CbMlWqbh.css">
+  </head>
+  <body>
+    <div id="root"></div>
+  </body>
+</html>

package/package.json ADDED Viewed

@@ -0,0 +1,156 @@
+{
+  "name": "markpdfdown",
+  "version": "0.1.0",
+  "description": "A high-quality PDF to Markdown tool based on large language model visual recognition.",
+  "author": "MarkPDFdown",
+  "main": "dist/main/index.js",
+  "bin": {
+    "markpdfdown": "./bin/cli.js"
+  },
+  "type": "module",
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "homepage": "https://github.com/markpdfdown/markpdfdown-desktop",
+  "files": [
+    "bin/",
+    "dist/",
+    "src/core/infrastructure/db/migrations/",
+    "src/core/infrastructure/db/schema.prisma"
+  ],
+  "scripts": {
+    "lint": "eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts --fix",
+    "dev": "npm run generate && electron-vite dev",
+    "build": "npm run generate && electron-vite build",
+    "start": "npm run generate && electron-vite preview",
+    "build:mac": "npm run build && electron-builder --mac --x64 --arm64",
+    "build:win": "npm run build && electron-builder --win --x64 --arm64",
+    "build:linux": "npm run build && electron-builder --linux --x64 --arm64",
+    "migrate:dev": "prisma migrate dev --schema=./src/core/infrastructure/db/schema.prisma",
+    "migrate:reset": "prisma migrate reset --schema=./src/core/infrastructure/db/schema.prisma",
+    "generate": "prisma generate --schema=./src/core/infrastructure/db/schema.prisma",
+    "logo": "electron-icon-builder --input=./src/renderer/assets/logo.png --output=./public",
+    "test": "vitest",
+    "test:unit": "vitest run --config vitest.config.ts",
+    "test:renderer": "vitest run --config vitest.config.renderer.ts",
+    "test:watch": "vitest watch",
+    "test:coverage": "vitest run --coverage",
+    "prepare": "husky"
+  },
+  "build": {
+    "appId": "com.markpdfdown.desktop",
+    "productName": "MarkPDFdown",
+    "files": [
+      "dist/**/*",
+      "!**/*.db",
+      "!**/*.d.ts",
+      "!**/*.min.*.map",
+      "!**/{.DS_Store,Thumbs.db}"
+    ],
+    "extraResources": [
+      "node_modules/.prisma/**/*",
+      "node_modules/@prisma/client/**/*",
+      {
+        "from": "src/core/infrastructure/db/migrations",
+        "to": "migrations",
+        "filter": [
+          "**/*.sql"
+        ]
+      }
+    ],
+    "asarUnpack": [
+      "**/*.{node,dll,metal,exp,lib}"
+    ],
+    "directories": {
+      "buildResources": "assets",
+      "output": "release"
+    },
+    "mac": {
+      "category": "public.app-category.productivity",
+      "artifactName": "${productName}-${version}-${arch}.${ext}",
+      "icon": "public/icons/mac/icon.icns"
+    },
+    "win": {
+      "target": "nsis",
+      "artifactName": "${productName}-${version}-${arch}.${ext}",
+      "icon": "public/icons/win/icon.ico"
+    },
+    "nsis": {
+      "artifactName": "${productName}-${version}-${arch}.${ext}",
+      "shortcutName": "${productName}",
+      "uninstallDisplayName": "${productName}",
+      "createDesktopShortcut": true,
+      "allowToChangeInstallationDirectory": true,
+      "oneClick": false
+    },
+    "linux": {
+      "target": "AppImage",
+      "artifactName": "${productName}-${version}-${arch}.${ext}",
+      "icon": "public/icons/png"
+    },
+    "electronDownload": {
+      "mirror": "https://github.com/electron/electron/releases/download/"
+    },
+    "asar": true
+  },
+  "lint-staged": {
+    "*.{js,jsx,cjs,mjs,ts,tsx,cts,mts}": [
+      "eslint --fix",
+      "prettier --write"
+    ],
+    "*.{json,css,md}": [
+      "prettier --write"
+    ]
+  },
+  "dependencies": {
+    "@ant-design/icons": "^5.6.1",
+    "@prisma/client": "^6.5.0",
+    "@types/sharp": "^0.31.1",
+    "antd": "^5.24.4",
+    "electron-is-dev": "^3.0.1",
+    "katex": "^0.16.21",
+    "pdf-lib": "^1.17.1",
+    "pdf-to-png-converter": "^3.11.0",
+    "prismjs": "^1.30.0",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0",
+    "react-i18next": "^16.5.3",
+    "react-markdown": "^10.1.0",
+    "react-router-dom": "^7.3.0",
+    "rehype-katex": "^7.0.1",
+    "rehype-prism-plus": "^2.0.0",
+    "remark-gfm": "^4.0.1",
+    "remark-math": "^6.0.0",
+    "sharp": "^0.34.1",
+    "uuid": "^11.1.0"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.21.0",
+    "@testing-library/jest-dom": "^6.1.5",
+    "@testing-library/react": "^14.0.0",
+    "@testing-library/user-event": "^14.5.1",
+    "@types/react": "^18.2.67",
+    "@types/react-dom": "^18.2.22",
+    "@vitejs/plugin-react": "^4.3.4",
+    "@vitest/coverage-v8": "^2.1.8",
+    "concurrently": "^9.1.2",
+    "electron": "^35.0.2",
+    "electron-builder": "^25.1.8",
+    "electron-icon-builder": "^2.0.1",
+    "electron-vite": "^3.1.0",
+    "eslint": "^9.21.0",
+    "eslint-plugin-react-hooks": "^5.1.0",
+    "eslint-plugin-react-refresh": "^0.4.19",
+    "globals": "^15.15.0",
+    "husky": "^9.1.7",
+    "jsdom": "^25.0.1",
+    "nodemon": "^3.1.9",
+    "prisma": "^6.5.0",
+    "typescript": "~5.7.2",
+    "typescript-eslint": "^8.24.1",
+    "vite": "^6.2.0",
+    "vitest": "^2.1.8",
+    "vitest-mock-extended": "^2.0.2",
+    "wait-on": "^8.0.3"
+  }
+}

package/src/core/infrastructure/db/migrations/20250414154412_/migration.sql ADDED Viewed

@@ -0,0 +1,24 @@
+-- CreateTable
+CREATE TABLE "Provider" (
+    "id" INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
+    "name" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "api_key" TEXT,
+    "base_url" TEXT,
+    "suffix" TEXT,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+-- CreateTable
+CREATE TABLE "Model" (
+    "id" TEXT NOT NULL,
+    "provider" INTEGER NOT NULL,
+    "name" TEXT NOT NULL,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+-- CreateIndex
+CREATE UNIQUE INDEX "Model_id_provider_key" ON "Model"("id", "provider");

package/src/core/infrastructure/db/migrations/20250419090345_/migration.sql ADDED Viewed

@@ -0,0 +1,29 @@
+-- CreateTable
+CREATE TABLE "Task" (
+    "id" TEXT NOT NULL,
+    "filename" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "pages" TEXT NOT NULL,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "model_name" TEXT NOT NULL,
+    "progress" INTEGER NOT NULL DEFAULT 0,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+-- CreateTable
+CREATE TABLE "TaskDetail" (
+    "id" INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
+    "task" TEXT NOT NULL,
+    "page" INTEGER NOT NULL,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+-- CreateIndex
+CREATE UNIQUE INDEX "Task_id_key" ON "Task"("id");

package/src/core/infrastructure/db/migrations/20250419104636_/migration.sql ADDED Viewed

@@ -0,0 +1,47 @@
+/*
+  Warnings:
+  - You are about to alter the column `pages` on the `Task` table. The data in that column could be lost. The data in that column will be cast from `String` to `Int`.
+  - Added the required column `page_range` to the `Task` table without a default value. This is not possible if the table is not empty.
+  - Added the required column `content` to the `TaskDetail` table without a default value. This is not possible if the table is not empty.
+  - Added the required column `page_source` to the `TaskDetail` table without a default value. This is not possible if the table is not empty.
+*/
+-- RedefineTables
+PRAGMA defer_foreign_keys=ON;
+PRAGMA foreign_keys=OFF;
+CREATE TABLE "new_Task" (
+    "id" TEXT NOT NULL,
+    "filename" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "page_range" TEXT NOT NULL,
+    "pages" INTEGER NOT NULL,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "model_name" TEXT NOT NULL,
+    "progress" INTEGER NOT NULL DEFAULT 0,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_Task" ("createdAt", "filename", "id", "model", "model_name", "pages", "progress", "provider", "status", "type", "updatedAt") SELECT "createdAt", "filename", "id", "model", "model_name", "pages", "progress", "provider", "status", "type", "updatedAt" FROM "Task";
+DROP TABLE "Task";
+ALTER TABLE "new_Task" RENAME TO "Task";
+CREATE UNIQUE INDEX "Task_id_key" ON "Task"("id");
+CREATE TABLE "new_TaskDetail" (
+    "id" INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
+    "task" TEXT NOT NULL,
+    "page" INTEGER NOT NULL,
+    "page_source" INTEGER NOT NULL,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "content" TEXT NOT NULL,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_TaskDetail" ("createdAt", "id", "model", "page", "provider", "status", "task", "updatedAt") SELECT "createdAt", "id", "model", "page", "provider", "status", "task", "updatedAt" FROM "TaskDetail";
+DROP TABLE "TaskDetail";
+ALTER TABLE "new_TaskDetail" RENAME TO "TaskDetail";
+PRAGMA foreign_keys=ON;
+PRAGMA defer_foreign_keys=OFF;

package/src/core/infrastructure/db/migrations/20260121154536_add_worker_fields/migration.sql ADDED Viewed

@@ -0,0 +1,50 @@
+-- RedefineTables
+PRAGMA defer_foreign_keys=ON;
+PRAGMA foreign_keys=OFF;
+CREATE TABLE "new_Task" (
+    "id" TEXT NOT NULL,
+    "filename" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "page_range" TEXT NOT NULL,
+    "pages" INTEGER NOT NULL DEFAULT 0,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "model_name" TEXT NOT NULL,
+    "progress" INTEGER NOT NULL DEFAULT 0,
+    "status" INTEGER NOT NULL DEFAULT 1,
+    "completed_count" INTEGER NOT NULL DEFAULT 0,
+    "failed_count" INTEGER NOT NULL DEFAULT 0,
+    "worker_id" TEXT,
+    "merged_path" TEXT,
+    "error" TEXT,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_Task" ("createdAt", "filename", "id", "model", "model_name", "page_range", "pages", "progress", "provider", "status", "type", "updatedAt") SELECT "createdAt", "filename", "id", "model", "model_name", "page_range", "pages", "progress", "provider", "status", "type", "updatedAt" FROM "Task";
+DROP TABLE "Task";
+ALTER TABLE "new_Task" RENAME TO "Task";
+CREATE UNIQUE INDEX "Task_id_key" ON "Task"("id");
+CREATE INDEX "Task_status_idx" ON "Task"("status");
+CREATE INDEX "Task_status_updatedAt_idx" ON "Task"("status", "updatedAt");
+CREATE TABLE "new_TaskDetail" (
+    "id" INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
+    "task" TEXT NOT NULL,
+    "page" INTEGER NOT NULL,
+    "page_source" INTEGER NOT NULL,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "worker_id" TEXT,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "content" TEXT NOT NULL DEFAULT '',
+    "error" TEXT,
+    "retry_count" INTEGER NOT NULL DEFAULT 0,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_TaskDetail" ("content", "createdAt", "id", "model", "page", "page_source", "provider", "status", "task", "updatedAt") SELECT "content", "createdAt", "id", "model", "page", "page_source", "provider", "status", "task", "updatedAt" FROM "TaskDetail";
+DROP TABLE "TaskDetail";
+ALTER TABLE "new_TaskDetail" RENAME TO "TaskDetail";
+CREATE INDEX "TaskDetail_task_status_idx" ON "TaskDetail"("task", "status");
+CREATE INDEX "TaskDetail_task_page_idx" ON "TaskDetail"("task", "page");
+PRAGMA foreign_keys=ON;
+PRAGMA defer_foreign_keys=OFF;

package/src/core/infrastructure/db/migrations/20260124014806_/migration.sql ADDED Viewed

@@ -0,0 +1,55 @@
+-- RedefineTables
+PRAGMA defer_foreign_keys=ON;
+PRAGMA foreign_keys=OFF;
+CREATE TABLE "new_Task" (
+    "id" TEXT NOT NULL,
+    "filename" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "page_range" TEXT NOT NULL,
+    "pages" INTEGER NOT NULL DEFAULT 0,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "model_name" TEXT NOT NULL,
+    "progress" INTEGER NOT NULL DEFAULT 0,
+    "status" INTEGER NOT NULL DEFAULT -1,
+    "completed_count" INTEGER NOT NULL DEFAULT 0,
+    "failed_count" INTEGER NOT NULL DEFAULT 0,
+    "worker_id" TEXT,
+    "merged_path" TEXT,
+    "error" TEXT,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_Task" ("completed_count", "createdAt", "error", "failed_count", "filename", "id", "merged_path", "model", "model_name", "page_range", "pages", "progress", "provider", "status", "type", "updatedAt", "worker_id") SELECT "completed_count", "createdAt", "error", "failed_count", "filename", "id", "merged_path", "model", "model_name", "page_range", "pages", "progress", "provider", "status", "type", "updatedAt", "worker_id" FROM "Task";
+DROP TABLE "Task";
+ALTER TABLE "new_Task" RENAME TO "Task";
+CREATE UNIQUE INDEX "Task_id_key" ON "Task"("id");
+CREATE INDEX "Task_status_idx" ON "Task"("status");
+CREATE INDEX "Task_status_updatedAt_idx" ON "Task"("status", "updatedAt");
+CREATE TABLE "new_TaskDetail" (
+    "id" INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
+    "task" TEXT NOT NULL,
+    "page" INTEGER NOT NULL,
+    "page_source" INTEGER NOT NULL,
+    "status" INTEGER NOT NULL DEFAULT 0,
+    "worker_id" TEXT,
+    "provider" INTEGER NOT NULL,
+    "model" TEXT NOT NULL,
+    "content" TEXT NOT NULL DEFAULT '',
+    "error" TEXT,
+    "retry_count" INTEGER NOT NULL DEFAULT 0,
+    "input_tokens" INTEGER NOT NULL DEFAULT 0,
+    "output_tokens" INTEGER NOT NULL DEFAULT 0,
+    "conversion_time" INTEGER NOT NULL DEFAULT 0,
+    "started_at" DATETIME,
+    "completed_at" DATETIME,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+INSERT INTO "new_TaskDetail" ("content", "createdAt", "error", "id", "model", "page", "page_source", "provider", "retry_count", "status", "task", "updatedAt", "worker_id") SELECT "content", "createdAt", "error", "id", "model", "page", "page_source", "provider", "retry_count", "status", "task", "updatedAt", "worker_id" FROM "TaskDetail";
+DROP TABLE "TaskDetail";
+ALTER TABLE "new_TaskDetail" RENAME TO "TaskDetail";
+CREATE INDEX "TaskDetail_task_status_idx" ON "TaskDetail"("task", "status");
+CREATE INDEX "TaskDetail_task_page_idx" ON "TaskDetail"("task", "page");
+PRAGMA foreign_keys=ON;
+PRAGMA defer_foreign_keys=OFF;

package/src/core/infrastructure/db/migrations/migration_lock.toml ADDED Viewed

@@ -0,0 +1,3 @@
+# Please do not edit this file manually
+# It should be added in your version-control system (e.g., Git)
+provider = "sqlite"

package/src/core/infrastructure/db/schema.prisma ADDED Viewed

@@ -0,0 +1,104 @@
+// This is your Prisma schema file,
+// learn more about it in the docs: https://pris.ly/d/prisma-schema
+// Looking for ways to speed up your queries, or scale easily with your serverless or edge functions?
+// Try Prisma Accelerate: https://pris.ly/cli/accelerate-init
+generator client {
+  provider = "prisma-client-js"
+}
+datasource db {
+  provider = "sqlite"
+  url      = env("DATABASE_URL")
+}
+model Provider {
+  id        Int      @id @default(autoincrement())
+  name      String
+  type      String
+  api_key   String?
+  base_url  String?
+  suffix    String?
+  status    Int      @default(0)
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+}
+model Model {
+  id        String
+  provider  Int
+  name      String
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+  @@unique([id, provider])
+}
+model Task {
+  id         String   @unique
+  filename   String
+  type       String
+  page_range String
+  pages      Int      @default(0)
+  provider   Int
+  model      String
+  model_name String
+  // 进度和状态
+  progress        Int     @default(0)   // 0-100
+  status          Int     @default(-1)  // TaskStatus (CREATED)
+  completed_count Int     @default(0)   // 已完成页面数
+  failed_count    Int     @default(0)   // 失败页面数
+  // Worker 追踪
+  worker_id String? // 当前处理的 worker ID
+  // 结果和错误
+  merged_path String? // 合并后的文件路径
+  error       String? // 错误信息
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+  @@index([status])
+  @@index([status, updatedAt])
+}
+model TaskDetail {
+  id          Int    @id @default(autoincrement())
+  task        String // 关联 Task.id
+  page        Int    // 当前页码 (1-based)
+  page_source Int    // 原始 PDF 页码
+  // 状态和处理
+  status    Int     @default(0) // PageStatus
+  worker_id String? // 当前处理的 worker ID
+  // LLM 配置
+  provider Int
+  model    String
+  // 结果和错误
+  content     String  @default("") // 转换后的 Markdown
+  error       String? // 错误信息
+  retry_count Int     @default(0) // 重试次数
+  // 成本追踪
+  input_tokens    Int      @default(0)
+  output_tokens   Int      @default(0)
+  // 性能指标
+  conversion_time Int      @default(0)
+  started_at      DateTime?
+  completed_at    DateTime?
+  // 注意：不存储 image_path，图片路径通过 ImagePathUtil.getPath(task, page) 动态计算
+  // 格式：{tempDir}/{taskId}/page-{page}.png
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+  @@index([task, status])
+  @@index([task, page])
+}