使用node-stream-zip解析manifest.json报错，寻求替代提取方案

问题背景 #

使用node-stream-zip库读取zip包内的manifest.json时，出现以下错误：

错误信息 : SyntaxError: Unexpected token in JSON at position 0
at JSON.parse ()
at StreamZip.

已验证manifest.json格式正确，但同步读取解析时失败，以下是几种可行的替代提取方法：

前置排查点 #

在更换方法前，先排查两个常见问题：

• BOM头问题：部分JSON文件开头带有UTF-8 BOM（\ufeff），直接toString('utf8')会保留该字符，导致JSON解析失败。可以先去除：

  const content = zip.entryDataSync("manifest.json").toString('utf8').replace(/^\uFEFF/, '');
  const zipDotTxtContents = JSON.parse(content);
  

• entry路径大小写：zip内的文件路径可能区分大小写，确认"manifest.json"的路径和大小写完全匹配。

替代提取方法 #

方法1：改用异步读取entry数据 #

避免同步方法可能的潜在问题，使用异步方式读取：

const getAppInfoFromManifest = async (productId) => {
    return new Promise((resolve, reject) => {
        const zip = new StreamZip({
            file: `./files/package${productId}.zip`,
            storeEntries: true,
        });

        zip.on("ready", () => {
            zip.entryData("manifest.json", (err, data) => {
                if (err) {
                    console.log(`读取manifest失败: ${err}`);
                    return resolve(undefined);
                }
                try {
                    const content = data.toString('utf8').replace(/^\uFEFF/, '');
                    const manifest = JSON.parse(content);
                    zip.close();
                    resolve({
                        appId: manifest?.id,
                        appVersionManifest: manifest?.version
                    });
                } catch (parseErr) {
                    console.log(`解析manifest失败: ${parseErr}`);
                    zip.close();
                    resolve(undefined);
                }
            });
        });

        zip.on("error", (err) => {
            console.log(err);
            console.log(`Manifest Parsing Issue for ${productId}`);
            resolve(undefined);
        });
    });
};

方法2：换用adm-zip库 #

adm-zip是另一个常用的Node.js zip处理库，API更直观：

const AdmZip = require('adm-zip');

const getAppInfoFromManifest = async (productId) => {
    try {
        const zip = new AdmZip(`./files/package${productId}.zip`);
        const manifestContent = zip.readAsText("manifest.json").replace(/^\uFEFF/, '');
        const manifest = JSON.parse(manifestContent);
        return {
            appId: manifest?.id,
            appVersionManifest: manifest?.version
        };
    } catch (err) {
        console.log(err);
        console.log(`Manifest Parsing Issue for ${productId}`);
        return undefined;
    }
};

方法3：先解压文件到临时目录再读取 #

如果zip包不大，可以先解压到临时目录，再直接读取文件：

const fs = require('fs').promises;
const path = require('path');
const AdmZip = require('adm-zip');
const os = require('os');

const getAppInfoFromManifest = async (productId) => {
    const tempDir = path.join(os.tmpdir(), `temp_${productId}`);
    try {
        const zip = new AdmZip(`./files/package${productId}.zip`);
        zip.extractAllTo(tempDir, true);
        
        const manifestPath = path.join(tempDir, "manifest.json");
        const content = await fs.readFile(manifestPath, 'utf8');
        const manifest = JSON.parse(content.replace(/^\uFEFF/, ''));
        
        // 清理临时文件
        await fs.rm(tempDir, { recursive: true, force: true });
        
        return {
            appId: manifest?.id,
            appVersionManifest: manifest?.version
        };
    } catch (err) {
        console.log(err);
        console.log(`Manifest Parsing Issue for ${productId}`);
        // 即使出错也清理临时文件
        await fs.rm(tempDir, { recursive: true, force: true }).catch(() => {});
        return undefined;
    }
};

方法4：使用unzipper库流式处理 #

unzipper支持流式解压，适合处理大文件：

const unzipper = require('unzipper');
const fs = require('fs');

const getAppInfoFromManifest = async (productId) => {
    return new Promise((resolve, reject) => {
        fs.createReadStream(`./files/package${productId}.zip`)
            .pipe(unzipper.Parse())
            .on('entry', async (entry) => {
                if (entry.path === "manifest.json") {
                    let content = '';
                    entry.on('data', (chunk) => content += chunk.toString('utf8'));
                    entry.on('end', () => {
                        try {
                            const manifest = JSON.parse(content.replace(/^\uFEFF/, ''));
                            resolve({
                                appId: manifest?.id,
                                appVersionManifest: manifest?.version
                            });
                        } catch (err) {
                            console.log(`解析manifest失败: ${err}`);
                            resolve(undefined);
                        }
                    });
                } else {
                    entry.autodrain(); // 跳过其他文件
                }
            })
            .on('error', (err) => {
                console.log(err);
                console.log(`Manifest Parsing Issue for ${productId}`);
                resolve(undefined);
            });
    });
};

内容的提问来源于stack exchange，提问作者Jagdish Padeliya