CSV转JSON JavaScript指南

function csvToJson(csv) {
  const lines = csv.trim().split('\n')
  const headers = lines[0].split(',').map(h => h.trim())

  const rows = lines.slice(1)
    .filter(line => line.trim() !== '')
    .map(line => {
      const values = line.split(',')
      return Object.fromEntries(
        headers.map((header, i) => [header, values[i]?.trim()])
      )
    })

  return JSON.stringify(rows, null, 2)
}

const csv = `server,port,region,status
api-gateway,8080,us-east-1,healthy
auth-service,8443,eu-west-1,degraded
payments-api,9090,ap-south-1,healthy`

console.log(csvToJson(csv))
// [
//   { "server": "api-gateway", "port": "8080", "region": "us-east-1", "status": "healthy" },
//   { "server": "auth-service", "port": "8443", "region": "eu-west-1", "status": "degraded" },
//   { "server": "payments-api", "port": "9090", "region": "ap-south-1", "status": "healthy" }
// ]

function coerceValue(val) {
  if (val === undefined || val === '') return null
  if (val === 'true') return true
  if (val === 'false') return false
  if (val === 'null') return null
  const num = Number(val)
  if (!isNaN(num) && val.trim() !== '') return num
  return val
}

function csvToJson(csv, { coerce = false } = {}) {
  const lines = csv.trim().split('\n')
  const headers = lines[0].split(',').map(h => h.trim())

  const rows = lines.slice(1)
    .filter(line => line.trim() !== '')
    .map(line => {
      const values = line.split(',')
      return Object.fromEntries(
        headers.map((header, i) => [
          header,
          coerce ? coerceValue(values[i]?.trim()) : values[i]?.trim()
        ])
      )
    })

  return JSON.stringify(rows, null, 2)
}

const csv = `endpoint,port,max_connections,debug
/api/v2/orders,8443,500,true
/api/v2/health,8080,100,false`

console.log(csvToJson(csv, { coerce: true }))
// [
//   { "endpoint": "/api/v2/orders", "port": 8443, "max_connections": 500, "debug": true },
//   { "endpoint": "/api/v2/health", "port": 8080, "max_connections": 100, "debug": false }
// ]

// 从 CSV 标题→值对构建 Map
const headers = ['server', 'port', 'region']
const values = ['payments-api', '9090', 'ap-south-1']
const rowMap = new Map(headers.map((h, i) => [h, values[i]]))

// Map 不能直接序列化
console.log(JSON.stringify(rowMap))
// "{}"  — 空对象，数据丢失！

// 先转换为普通对象
const rowObj = Object.fromEntries(rowMap)
console.log(JSON.stringify(rowObj, null, 2))
// {
//   "server": "payments-api",
//   "port": "9090",
//   "region": "ap-south-1"
// }

class EmployeeRecord {
  constructor(csvRow) {
    this._rowIndex = csvRow._rowIndex  // 内部字段，不输出到 JSON
    this.employeeId = csvRow.employee_id
    this.name = csvRow.name
    this.hiredAt = new Date(csvRow.hired_date)
    this.salary = Number(csvRow.salary)
  }

  toJSON() {
    // 仅暴露我们希望出现在 JSON 输出中的字段
    return {
      employee_id: this.employeeId,
      name: this.name,
      hired_at: this.hiredAt,  // Date.toJSON() → 自动输出 ISO 字符串
      salary: this.salary,
    }
  }
}

const csvRow = {
  _rowIndex: 42,
  employee_id: 'EMP-2847',
  name: '陈明',
  hired_date: '2024-03-15',
  salary: '128000',
}

const record = new EmployeeRecord(csvRow)
console.log(JSON.stringify(record, null, 2))
// {
//   "employee_id": "EMP-2847",
//   "name": "陈明",
//   "hired_at": "2024-03-15T00:00:00.000Z",
//   "salary": 128000
// }
// 注意：_rowIndex 被排除，salary 为数字，日期为 ISO 格式

const jsonString = '{"employee_id":"EMP-2847","name":"陈明","hired_at":"2024-03-15T00:00:00.000Z","salary":128000}'

const isoDatePattern = /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}/

const parsed = JSON.parse(jsonString, (key, value) => {
  if (typeof value === 'string' && isoDatePattern.test(value)) {
    return new Date(value)
  }
  return value
})

console.log(parsed.hired_at instanceof Date)  // true
console.log(parsed.hired_at.getFullYear())    // 2024

const csv = `endpoint,method,avg_latency_ms,error_rate
/api/v2/orders,POST,342,0.02
/api/v2/health,GET,12,0.00
/api/v2/payments,POST,890,0.15
/api/v2/users,GET,45,0.01`

// 第一步：将 CSV 转换为 JSON 字符串
const jsonString = csvToJson(csv, { coerce: true })

// 第二步：解析回 JavaScript 数组
const endpoints = JSON.parse(jsonString)

// 验证为数组
console.log(Array.isArray(endpoints))  // true

// 过滤高延迟端点
const slow = endpoints.filter(ep => ep.avg_latency_ms > 200)
console.log(slow.map(ep => ep.endpoint))
// ["/api/v2/orders", "/api/v2/payments"]

// 解构第一行
const [first, ...rest] = endpoints
console.log(first.endpoint)  // "/api/v2/orders"
console.log(rest.length)     // 3

function safeParse(jsonString) {
  try {
    return { data: JSON.parse(jsonString), error: null }
  } catch (err) {
    return { data: null, error: err.message }
  }
}

// 有效输出
const result = safeParse(csvToJson(csv))
if (result.error) {
  console.error('CSV 转换产生了无效 JSON：', result.error)
} else {
  console.log(`已解析 ${result.data.length} 行`)
}

// 误将原始 CSV 传入 JSON.parse — 这会失败
const bad = safeParse('name,email\n陈明,chenming@nexuslabs.io')
console.log(bad.error)  // "Unexpected token '陈', "name,email"... is not valid JSON"

const jsonString = csvToJson(`employeeId,firstName,hiredDate
EMP-2847,陈明,2024-03-15
EMP-3012,李芳,2023-11-01`, { coerce: false })

const camelToSnake = str => str.replace(/[A-Z]/g, c => '_' + c.toLowerCase())

const employees = JSON.parse(jsonString, function(key, value) {
  // 根值——验证结构
  if (key === '') {
    if (!Array.isArray(value)) throw new Error('Expected JSON array from CSV')
    return value
  }
  // 将驼峰命名的标题键重命名为下划线命名
  if (typeof value === 'object' && value !== null && !Array.isArray(value)) {
    return Object.fromEntries(
      Object.entries(value).map(([k, v]) => [camelToSnake(k), v])
    )
  }
  return value
})

console.log(employees[0])
// { employee_id: 'EMP-2847', first_name: '陈明', hired_date: '2024-03-15' }

import { readFileSync, writeFileSync } from 'node:fs'

function csvToJsonFromFile(inputPath, outputPath) {
  let csvText
  try {
    csvText = readFileSync(inputPath, 'utf8')
  } catch (err) {
    throw new Error(`读取 ${inputPath} 失败：${err.message}`)
  }

  const lines = csvText.trim().split('\n')
  if (lines.length < 2) {
    throw new Error(`${inputPath} 没有数据行（只有 ${lines.length} 行）`)
  }

  const headers = lines[0].split(',').map(h => h.trim())
  const rows = lines.slice(1)
    .filter(line => line.trim() !== '')
    .map(line => {
      const values = line.split(',')
      return Object.fromEntries(headers.map((h, i) => [h, values[i]?.trim()]))
    })

  const jsonOutput = JSON.stringify(rows, null, 2)
  writeFileSync(outputPath, jsonOutput, 'utf8')
  console.log(`已转换 ${rows.length} 行 → ${outputPath}`)
  return rows
}

// 用法
const data = csvToJsonFromFile('inventory.csv', 'inventory.json')
console.log(data[0])
// { sku: "WDG-2847", warehouse: "us-east-1", quantity: "150", ... }

async function fetchCsvAsJson(url) {
  const response = await fetch(url)
  if (!response.ok) {
    throw new Error(`HTTP ${response.status}: ${response.statusText}`)
  }

  const contentType = response.headers.get('content-type') || ''
  if (!contentType.includes('text/csv') && !contentType.includes('text/plain')) {
    console.warn(`意外的 content-type：${contentType}`)
  }

  const csvText = await response.text()
  const lines = csvText.trim().split('\n')
  const headers = lines[0].split(',').map(h => h.trim())
  const rows = lines.slice(1)
    .filter(line => line.trim() !== '')
    .map(line => {
      const values = line.split(',')
      return Object.fromEntries(headers.map((h, i) => [h, values[i]?.trim()]))
    })

  return rows
}

// 示例：从数据提供商获取汇率 CSV
try {
  const rates = await fetchCsvAsJson('https://data.ecb.internal/rates/daily.csv')
  console.log(JSON.stringify(rates.slice(0, 3), null, 2))
  // 以 JSON 形式发送给下游服务
  await fetch('https://api.internal/v2/rates', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ data: rates }),
  })
} catch (err) {
  console.error('汇率同步失败：', err.message)
}

# 将 CSV 管道到 Node.js 内联脚本
cat servers.csv | node -e "
  const lines = require('fs').readFileSync('/dev/stdin','utf8').trim().split('\n');
  const h = lines[0].split(',');
  const rows = lines.slice(1).map(l => Object.fromEntries(h.map((k,i) => [k.trim(), l.split(',')[i]?.trim()])));
  console.log(JSON.stringify(rows, null, 2));
"

# Miller 是结构化数据的瑞士军刀
# 安装：brew install miller (macOS) 或 apt install miller (Debian/Ubuntu)
mlr --icsv --ojson cat inventory.csv

# 转换时过滤行
mlr --icsv --ojson filter '$quantity > 100' inventory.csv

# 选择特定列
mlr --icsv --ojson cut -f sku,warehouse,quantity inventory.csv

# 全局安装
npm install -g csvtojson

# 转换文件
csvtojson servers.csv > servers.json

# 从标准输入管道
cat exports/q1-metrics.csv | csvtojson > q1-metrics.json

npm install papaparse

import Papa from 'papaparse'

const csv = `product,description,price,in_stock
"小部件，大号","一个带有 ""额外"" 功能的优质部件",29.99,true
螺栓套件,标准 M8 螺栓套件,4.50,true
"密封圈套装","包含密封圈、封条和 O 形圈",12.75,false`

const { data, errors, meta } = Papa.parse(csv, {
  header: true,
  dynamicTyping: true,     // 自动转换数字和布尔值
  skipEmptyLines: true,
  transformHeader: h => h.trim().toLowerCase().replace(/\s+/g, '_'),
})

if (errors.length > 0) {
  console.error('解析错误：', errors)
}

console.log(JSON.stringify(data, null, 2))
// [
//   {
//     "product": "小部件，大号",
//     "description": "一个带有 \"额外\" 功能的优质部件",
//     "price": 29.99,
//     "in_stock": true
//   },
//   ...
// ]
console.log(`已解析 ${data.length} 行，分隔符："${meta.delimiter}"`)

npm install cli-highlight

import { highlight } from 'cli-highlight'

// 将 CSV 转换为 JSON 数组后
const jsonOutput = JSON.stringify(rows, null, 2)

// 带语法高亮打印
console.log(highlight(jsonOutput, { language: 'json' }))
// 键、字符串、数字和布尔值各自获得不同颜色

import { createReadStream, createWriteStream } from 'node:fs'
import { parse } from 'csv-parse'
import { Transform } from 'node:stream'
import { pipeline } from 'node:stream/promises'

// 将每个 CSV 行对象转换为 JSON 行
const toNdjson = new Transform({
  objectMode: true,
  transform(record, encoding, callback) {
    callback(null, JSON.stringify(record) + '\n')
  },
})

await pipeline(
  createReadStream('telemetry-2026-03.csv'),
  parse({
    columns: true,       // 使用第一行作为标题
    skip_empty_lines: true,
    trim: true,
    cast: true,          // 自动转换数字和布尔值
  }),
  toNdjson,
  createWriteStream('telemetry-2026-03.ndjson')
)

console.log('流式转换完成')
// 输出文件中每行是一个 JSON 对象：
// {"timestamp":"2026-03-15T08:22:00Z","service":"gateway","latency_ms":42,"status":200}
// {"timestamp":"2026-03-15T08:22:01Z","service":"auth","latency_ms":156,"status":401}
// ...

import Papa from 'papaparse'
import { createReadStream } from 'node:fs'

let rowCount = 0
const errors = []

const fileStream = createReadStream('warehouse-inventory.csv')

Papa.parse(fileStream, {
  header: true,
  dynamicTyping: true,
  step(result) {
    // 每次处理一行——内存占用恒定
    rowCount++
    if (result.data.quantity === 0) {
      errors.push(`第 ${rowCount} 行：${result.data.sku} 缺货`)
    }
  },
  complete() {
    console.log(`已处理 ${rowCount} 行`)
    if (errors.length > 0) {
      console.log(`发现问题：${errors.length} 个`)
      errors.forEach(e => console.log(`  ${e}`))
    }
  },
  error(err) {
    console.error('解析失败：', err.message)
  },
})