SkyJourney
64445322eb
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。
282 lines
8.6 KiB
JavaScript
282 lines
8.6 KiB
JavaScript
import { spawnSync } from "node:child_process";
|
||
import { createHash, randomUUID } from "node:crypto";
|
||
import { mkdir, mkdtemp, readFile, rm, stat } from "node:fs/promises";
|
||
import net from "node:net";
|
||
import os from "node:os";
|
||
import path from "node:path";
|
||
import { fileURLToPath } from "node:url";
|
||
import { defaultExportConfig } from "@md-to-pdf/core";
|
||
import { strFromU8, unzipSync } from "fflate";
|
||
|
||
const scriptDirectory = path.dirname(fileURLToPath(import.meta.url));
|
||
const repositoryRoot = path.resolve(scriptDirectory, "..");
|
||
const composeFile = path.join(scriptDirectory, "compose.yaml");
|
||
const image = process.env.MD_TO_PDF_IMAGE?.trim() || "md-to-pdf:local";
|
||
const fontPackRoot = path.resolve(
|
||
path.join(repositoryRoot, "output", "font-packs", "root")
|
||
);
|
||
const expectedFontPacks = [
|
||
{ id: "mdtp-serif-sc", version: "1.0.0" },
|
||
{ id: "mdtp-sans-sc", version: "1.0.0" },
|
||
{ id: "mdtp-mono", version: "1.0.0" }
|
||
];
|
||
|
||
function assert(condition, message) {
|
||
if (!condition) {
|
||
throw new Error(message);
|
||
}
|
||
}
|
||
|
||
function sha256(content) {
|
||
return createHash("sha256").update(content).digest("hex").toLowerCase();
|
||
}
|
||
|
||
function run(command, args, options = {}) {
|
||
const result = spawnSync(command, args, {
|
||
cwd: repositoryRoot,
|
||
encoding: "utf8",
|
||
stdio: options.capture ? "pipe" : "inherit",
|
||
env: options.env ?? process.env
|
||
});
|
||
if (result.error) {
|
||
throw result.error;
|
||
}
|
||
if (result.status !== 0) {
|
||
throw new Error(
|
||
`${command} ${args.join(" ")} 失败（退出码 ${result.status}）${
|
||
options.capture ? `\n${result.stderr || result.stdout}` : ""
|
||
}`
|
||
);
|
||
}
|
||
return options.capture ? result.stdout.trim() : "";
|
||
}
|
||
|
||
async function freePort() {
|
||
return new Promise((resolve, reject) => {
|
||
const server = net.createServer();
|
||
server.once("error", reject);
|
||
server.listen(0, "127.0.0.1", () => {
|
||
const address = server.address();
|
||
const port =
|
||
typeof address === "object" && address ? address.port : undefined;
|
||
server.close((error) =>
|
||
error || !port
|
||
? reject(error ?? new Error("无法分配端口"))
|
||
: resolve(port)
|
||
);
|
||
});
|
||
});
|
||
}
|
||
|
||
async function waitForHealth(origin) {
|
||
let lastError;
|
||
for (let attempt = 0; attempt < 60; attempt += 1) {
|
||
try {
|
||
const response = await fetch(`${origin}/api/health`);
|
||
if (response.ok && (await response.json()).status === "ok") {
|
||
return;
|
||
}
|
||
} catch (error) {
|
||
lastError = error;
|
||
}
|
||
await new Promise((resolve) => setTimeout(resolve, 1000));
|
||
}
|
||
throw new Error(
|
||
`容器健康检查未就绪${lastError ? `：${String(lastError)}` : ""}`
|
||
);
|
||
}
|
||
|
||
function assertNoFontPackMount(containerId) {
|
||
const inspection = JSON.parse(
|
||
run("docker", ["inspect", containerId], { capture: true })
|
||
)[0];
|
||
const mount = inspection.Mounts.find(
|
||
(item) => item.Destination === "/app/.local/font-packs"
|
||
);
|
||
assert(!mount, "Docker 字体包必须来自镜像层，不能依赖运行时挂载");
|
||
}
|
||
|
||
async function exportDocx(origin) {
|
||
const response = await fetch(`${origin}/api/docx`, {
|
||
method: "POST",
|
||
headers: { "content-type": "application/json" },
|
||
body: JSON.stringify({
|
||
markdown:
|
||
"---\ntitle: Docker 内置字体包验收\n---\n\n# Docker 内置字体包验收\n\n这是一段包含行内代码 `const value = 1` 的可编辑中文正文，代码前后不得换行。",
|
||
fileName: "Docker 内置字体包验收.md",
|
||
language: "zh-CN",
|
||
resources: [],
|
||
exportConfig: {
|
||
...defaultExportConfig,
|
||
themeId: "gov-red-standard"
|
||
}
|
||
})
|
||
});
|
||
if (!response.ok) {
|
||
throw new Error(
|
||
`DOCX 导出失败（${response.status}）：${await response.text()}`
|
||
);
|
||
}
|
||
return new Uint8Array(await response.arrayBuffer());
|
||
}
|
||
|
||
const fontPackStatus = await stat(fontPackRoot).catch(() => undefined);
|
||
assert(
|
||
fontPackStatus?.isDirectory(),
|
||
`未找到有效字体包根目录：${fontPackRoot}。请先运行 npm run build:font-pack。`
|
||
);
|
||
const localManifests = await Promise.all(
|
||
expectedFontPacks.map(async (pack) => ({
|
||
...pack,
|
||
content: await readFile(
|
||
path.join(fontPackRoot, pack.id, pack.version, "font-pack.json")
|
||
)
|
||
}))
|
||
);
|
||
const buildEnvironment = {
|
||
...process.env,
|
||
MD_TO_PDF_IMAGE: image
|
||
};
|
||
run(
|
||
"docker",
|
||
["compose", "--file", composeFile, "build", "app"],
|
||
{ env: buildEnvironment }
|
||
);
|
||
run("docker", ["image", "inspect", image], { capture: true });
|
||
const embeddedManifestHashes = {};
|
||
for (const manifest of localManifests) {
|
||
const embeddedHash = run(
|
||
"docker",
|
||
[
|
||
"run",
|
||
"--rm",
|
||
"--entrypoint",
|
||
"sha256sum",
|
||
image,
|
||
`/app/.local/font-packs/${manifest.id}/${manifest.version}/font-pack.json`
|
||
],
|
||
{ capture: true }
|
||
).split(/\s+/u)[0];
|
||
assert(
|
||
embeddedHash === sha256(manifest.content),
|
||
`镜像内字体包清单不一致：${manifest.id}@${manifest.version}`
|
||
);
|
||
embeddedManifestHashes[`${manifest.id}@${manifest.version}`] = embeddedHash;
|
||
}
|
||
|
||
const port = await freePort();
|
||
const projectName = `morphdoc-font-pack-${randomUUID().slice(0, 8)}`;
|
||
const temporaryRoot = await mkdtemp(
|
||
path.join(os.tmpdir(), "morphdoc-docker-font-pack-")
|
||
);
|
||
const themeRoot = path.join(temporaryRoot, "empty-themes");
|
||
await mkdir(themeRoot, { recursive: true });
|
||
const environment = {
|
||
...buildEnvironment,
|
||
MD_TO_PDF_PORT: String(port),
|
||
MD_TO_PDF_THEME_DIR: themeRoot,
|
||
MD_TO_PDF_APP_VERSION: "0.6.2"
|
||
};
|
||
const compose = [
|
||
"compose",
|
||
"--project-name",
|
||
projectName,
|
||
"--file",
|
||
composeFile
|
||
];
|
||
|
||
try {
|
||
run(
|
||
"docker",
|
||
[...compose, "up", "--detach", "--no-build", "--pull", "never"],
|
||
{ env: environment }
|
||
);
|
||
const containerId = run(
|
||
"docker",
|
||
[...compose, "ps", "--quiet", "app"],
|
||
{ capture: true, env: environment }
|
||
);
|
||
assert(containerId, "未创建 Docker 字体包验收容器");
|
||
assertNoFontPackMount(containerId);
|
||
const origin = `http://127.0.0.1:${port}`;
|
||
await waitForHealth(origin);
|
||
|
||
const capabilityResponse = await fetch(`${origin}/api/docx/capability`);
|
||
const capability = await capabilityResponse.json();
|
||
assert(
|
||
capabilityResponse.ok &&
|
||
capability.status === "available" &&
|
||
capability.detectedVersion === "3.9.0.2",
|
||
`DOCX capability 无效：${JSON.stringify(capability)}`
|
||
);
|
||
|
||
const cssResponse = await fetch(
|
||
`${origin}/api/themes/gov-red-standard/css`
|
||
);
|
||
const css = await cssResponse.text();
|
||
assert(cssResponse.ok, "主题 CSS 请求失败");
|
||
assert(css.includes("md-to-pdf-font-packs:"), "主题 CSS 缺少字体包标记");
|
||
for (const pack of expectedFontPacks) {
|
||
assert(
|
||
css.includes(`${pack.id}@${pack.version}`),
|
||
`Docker 内置字体包未进入主题 CSS：${pack.id}@${pack.version}`
|
||
);
|
||
}
|
||
const assetPath = css.match(
|
||
/(\/api\/font-packs\/[^"'()\s]+\/web\?v=[a-f0-9]+)/u
|
||
)?.[1];
|
||
assert(assetPath, "Docker 内置字体包 CSS 缺少受控 WOFF2 地址");
|
||
const assetResponse = await fetch(`${origin}${assetPath}`);
|
||
assert(assetResponse.ok, "Docker 内置字体包 WOFF2 请求失败");
|
||
assert(
|
||
assetResponse.headers.get("content-type")?.includes("font/woff2"),
|
||
"Docker 内置字体包 WOFF2 MIME 无效"
|
||
);
|
||
assert(
|
||
assetResponse.headers.get("cache-control")?.includes("immutable"),
|
||
"Docker 内置字体包 WOFF2 缓存策略无效"
|
||
);
|
||
|
||
const docx = await exportDocx(origin);
|
||
const entries = unzipSync(docx);
|
||
const fontParts = Object.keys(entries).filter((entry) =>
|
||
entry.startsWith("word/fonts/")
|
||
);
|
||
assert(fontParts.length >= 2, `DOCX 字体部件不足：${fontParts.length}`);
|
||
const fontTable = strFromU8(entries["word/fontTable.xml"]);
|
||
assert(fontTable.includes("MdTP Serif SC"), "字体包未进入 DOCX 字体表");
|
||
assert(fontTable.includes("MdTP Mono"), "等宽字体包未进入 DOCX 字体表");
|
||
const documentXml = strFromU8(entries["word/document.xml"]);
|
||
const inlineCodeParagraph = documentXml
|
||
.match(/<w:p(?:\s[^>]*)?>[\s\S]*?<\/w:p>/gu)
|
||
?.find(
|
||
(paragraph) =>
|
||
paragraph.includes("这是一段包含行内代码") &&
|
||
paragraph.includes("const value = 1") &&
|
||
paragraph.includes("代码前后不得换行")
|
||
);
|
||
assert(inlineCodeParagraph, "行内代码及前后正文未保持在同一 Word 段落");
|
||
|
||
process.stdout.write(
|
||
`${JSON.stringify(
|
||
{
|
||
image,
|
||
embeddedManifestSha256: embeddedManifestHashes,
|
||
runtimeFontPackMount: false,
|
||
fontPackAvailable: true,
|
||
pandocVersion: capability.detectedVersion,
|
||
docxFontParts: fontParts.length
|
||
},
|
||
null,
|
||
2
|
||
)}\n`
|
||
);
|
||
} finally {
|
||
run(
|
||
"docker",
|
||
[...compose, "down", "--remove-orphans", "--timeout", "5"],
|
||
{ env: environment }
|
||
);
|
||
await rm(temporaryRoot, { recursive: true, force: true });
|
||
}
|