Files
MorphDoc/packages/docx-engine/tests/pandoc-converter.test.ts
T
SkyJourney 64445322eb release: 发布 v0.6.2 DOCX 真实文档修复
新增能力:将 DOCX 发布验收拆分为四套独立 140,支持真实语料冻结、指纹复用、失败与基础设施错误独立统计,并为表格换行、全 JSON 围栏、代码连续性和长文档分页建立通用门禁。

问题修复:冻结 Paged.js 分片前的逻辑表格列轨并传递打印几何,统一 Markdown 表格换行、代码、段落与 OOXML 翻译;改进 PDF 文本流排序、语义块映射、颜色与栅格比较,消除窄字符重叠和跨行范围符号误报。

兼容与部署:版本统一为 0.6.2;正式 Docker 镜像内置固定 Chromium、Pandoc 3.9.0.2 和 Serif/Sans/Mono 字体;Desktop NSIS 与 ZIP 继续直接内置字体,无需系统字体安装。

验证结果:合成基线与长庆严格 280/280,M4N 140/140;健康数据残余误报 6/115(5.22%),均核查为重复表头自动对齐/取样误报且基础设施错误为 0。全项目测试、类型检查、生产构建和 git diff --check 通过;正式 Docker、NSIS、ZIP、离线镜像、部署包、清单及 SHA-256 均已生成并校验。
2026-08-26 10:50:20 +08:00

248 lines
6.5 KiB
TypeScript

import {
copyFile,
mkdtemp,
rm,
writeFile
} from "node:fs/promises";
import { existsSync } from "node:fs";
import os from "node:os";
import path from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import {
defaultExportConfig,
type PreparedDocxMedia,
type ThemeManifest
} from "@md-to-pdf/core";
import type { DocxThemeTokenSet } from "@md-to-pdf/docx-theme-engine";
import {
PandocDocxConversionError,
PandocDocxConverter,
type PandocProcessRunner,
type PandocRuntimeProvider
} from "../src/index.js";
import { createTestBaselineReference } from "./reference-test-fixture.js";
function theme(): ThemeManifest {
return {
manifestVersion: 1,
id: "test-theme",
name: "测试主题",
version: "1.0.0",
description: "测试",
author: "测试",
license: "内部许可",
entry: "theme.css",
domPreset: "generic",
defaultFontSize: "16px",
supportedFeatures: [],
category: "general",
compatibleProfiles: [],
docxStyle: { preset: "technical" },
bundled: true
};
}
const emptyMedia: PreparedDocxMedia = {
resources: [],
echartsErrors: [],
mermaidErrors: [],
warnings: [],
totalBytes: 0
};
const themeTokens: DocxThemeTokenSet = {
schemaVersion: 1,
themeId: "test-theme",
themeFingerprint: "c".repeat(64),
mode: "auto-with-overrides",
basePreset: "technical",
slots: [],
diagnostics: []
};
function input() {
return {
markdown: "# 测试",
fileName: "测试.md",
language: "zh-CN",
exportConfig: defaultExportConfig,
theme: theme(),
themeTokens,
fonts: [],
metadata: {
title: "测试",
author: "测试人",
subject: "",
keywords: [],
language: "zh-CN"
},
semanticDocument: {
schemaVersion: 1,
titlePolicy: {
metadataTitle: "suppress",
firstBodyHeading: "keep"
},
regions: []
},
media: emptyMedia
};
}
function argumentAfter(arguments_: readonly string[], name: string) {
const index = arguments_.indexOf(name);
if (index < 0 || !arguments_[index + 1]) {
throw new Error(`缺少参数 ${name}`);
}
return arguments_[index + 1]!;
}
describe("Pandoc DOCX 转换器", () => {
let temporaryRoot: string;
const baseline = createTestBaselineReference();
const runtime: PandocRuntimeProvider = {
async getExecutablePath() {
return "pandoc";
},
async getDefaultReferenceDocx() {
return baseline;
}
};
beforeEach(async () => {
temporaryRoot = await mkdtemp(
path.join(os.tmpdir(), "docx-converter-test-")
);
});
afterEach(async () => {
await rm(temporaryRoot, { recursive: true, force: true });
});
it("使用固定参数转换、校验并清理请求级临时目录", async () => {
let requestDirectory = "";
const runner = vi.fn<PandocProcessRunner>(
async (_executable, arguments_, options) => {
requestDirectory = options.cwd!;
expect(arguments_).toContain("--lua-filter");
expect(arguments_).toContain("--data-dir");
expect(arguments_).toContain("--resource-path");
expect(argumentAfter(arguments_, "--from")).toBe(
"commonmark_x-yaml_metadata_block+pipe_tables+footnotes+task_lists+tex_math_dollars+raw_html"
);
expect(
options.env?.MD_TO_PDF_DOCX_MEDIA_MAP
).toContain("media-map.json");
expect(
options.env?.MD_TO_PDF_DOCX_STRUCTURE_PLAN
).toContain("structure-plan.json");
const structurePlan = JSON.parse(
await import("node:fs/promises").then(({ readFile }) =>
readFile(
options.env!.MD_TO_PDF_DOCX_STRUCTURE_PLAN!,
"utf8"
)
)
);
expect(structurePlan.titlePolicy.metadataTitle).toBe(
"suppress"
);
await copyFile(
argumentAfter(arguments_, "--reference-doc"),
argumentAfter(arguments_, "--output")
);
return {
outcome: "completed",
exitCode: 0,
stdout: new Uint8Array(),
stderr: ""
};
}
);
const converter = new PandocDocxConverter({
runtime,
runner,
temporaryRoot
});
const result = await converter.convert(input());
expect(result.docx.byteLength).toBeGreaterThan(0);
expect(result.validation.partCount).toBeGreaterThan(8);
expect(runner).toHaveBeenCalledTimes(1);
expect(existsSync(requestDirectory)).toBe(false);
});
it("超时和无效输出均返回稳定错误并清理目录", async () => {
let timeoutDirectory = "";
const timeoutRunner = vi.fn<PandocProcessRunner>(
async (_executable, _arguments, options) => {
timeoutDirectory = options.cwd!;
return {
outcome: "timeout",
exitCode: null,
stdout: new Uint8Array(),
stderr: ""
};
}
);
await expect(
new PandocDocxConverter({
runtime,
runner: timeoutRunner,
temporaryRoot
}).convert(input())
).rejects.toMatchObject({
code: "DOCX_RENDER_TIMEOUT"
} satisfies Partial<PandocDocxConversionError>);
expect(existsSync(timeoutDirectory)).toBe(false);
const invalidRunner = vi.fn<PandocProcessRunner>(
async (_executable, arguments_) => {
await writeFile(
argumentAfter(arguments_, "--output"),
"not a docx"
);
return {
outcome: "completed",
exitCode: 0,
stdout: new Uint8Array(),
stderr: ""
};
}
);
await expect(
new PandocDocxConverter({
runtime,
runner: invalidRunner,
temporaryRoot
}).convert(input())
).rejects.toMatchObject({
code: "DOCX_OUTPUT_INVALID"
} satisfies Partial<PandocDocxConversionError>);
});
it("进程失败时保留内部诊断但保持稳定的对外错误", async () => {
const failedRunner = vi.fn<PandocProcessRunner>(async () => ({
outcome: "completed",
exitCode: 64,
stdout: new Uint8Array(),
stderr: "pandoc: 媒体映射失败"
}));
await expect(
new PandocDocxConverter({
runtime,
runner: failedRunner,
temporaryRoot
}).convert(input())
).rejects.toMatchObject({
code: "DOCX_GENERATION_FAILED",
message: "Pandoc 未能生成 DOCX",
diagnostics: {
outcome: "completed",
exitCode: 64,
stderr: "pandoc: 媒体映射失败"
}
} satisfies Partial<PandocDocxConversionError>);
});
});