解决Scala中使用AWS SDK将JSON字符串上传至S3内容异常的问题

import com.amazonaws.services.s3.AmazonS3Client
import com.amazonaws.auth.BasicAWSCredentials
import com.amazonaws.ClientConfiguration
import org.apache.spark.sql.SparkSession // 假设Spark环境

// 假设 amazonS3Client, bucketName, objectKey 已初始化
// val amazonS3Client: AmazonS3Client = ...
// val bucketName: String = "your-bucket-name"
// val objectKey: String = "your-object-key.json"

// 示例数据生成
val spark = SparkSession.builder().appName("S3UploadTest").master("local[*]").getOrCreate()
import spark.implicits._
val data = Seq(("id1", "name1"), ("id2", "name2")).toDF("id", "name")
val JSONdata = data.toJSON

var JSONstring: String = JSONdata.collect().mkString("[", ",", "]") // 将Dataset[String]转换为单个JSON数组字符串

try {
    println(JSONstring) // 打印出有效的JSON数据
    println(JSONstring.getClass) // 显示 "class java.lang.String"
    // 导致问题的方法调用
    val result = amazonS3Client.putObject(bucketName, objectKey, JSONstring)
    println("Result ETag: " + result.getETag())
} catch {
    case e: Exception => println("Error: " + e.getMessage())
}

import com.amazonaws.services.s3.AmazonS3Client
import com.amazonaws.services.s3.model.{ObjectMetadata, PutObjectRequest}
import com.amazonaws.auth.BasicAWSCredentials
import com.amazonaws.ClientConfiguration
import java.io.ByteArrayInputStream
import java.nio.charset.StandardCharsets
import org.apache.spark.sql.SparkSession

// 假设 amazonS3Client, bucketName, objectKey 已初始化
// val amazonS3Client: AmazonS3Client = new AmazonS3Client(new BasicAWSCredentials("YOUR_ACCESS_KEY", "YOUR_SECRET_KEY"))
// val bucketName: String = "your-bucket-name"
// val objectKey: String = "your-object-key.json"

// 示例数据生成 (与原问题保持一致，但优化了JSONstring的生成)
val spark = SparkSession.builder().appName("S3UploadFix").master("local[*]").getOrCreate()
import spark.implicits._
val data = Seq(("id1", "name1", 25), ("id2", "name2", 30)).toDF("id", "name", "age")
val JSONdata = data.toJSON // Dataset[String]

// 将Dataset[String]转换为单个JSON数组字符串
// collectAsList() 或 collect() 后再mkString是常见的做法
val JSONstring: String = JSONdata.collect().mkString("[", ",", "]")

try {
    println(s"准备上传的JSON数据:\n$JSONstring")
    println(s"JSON数据类型: ${JSONstring.getClass}")

    // 1. 将JSON字符串转换为字节数组
    val bytes = JSONstring.getBytes(StandardCharsets.UTF_8)

    // 2. 将字节数组转换为输入流
    val inputStream = new ByteArrayInputStream(bytes)

    // 3. 创建ObjectMetadata对象，设置内容长度和内容类型
    val metadata = new ObjectMetadata()
    metadata.setContentLength(bytes.length)
    metadata.setContentType("application/json") // 明确指定内容类型为JSON

    // 4. 构建PutObjectRequest
    val putObjectRequest = new PutObjectRequest(bucketName, objectKey, inputStream, metadata)

    // 5. 执行上传
    val result = amazonS3Client.putObject(putObjectRequest)
    println("S3上传成功！")
    println("ETag: " + result.getETag())
    println("版本ID: " + result.getVersionId()) // 如果S3桶开启了版本控制

    // 重要的资源清理：关闭InputStream
    inputStream.close()

} catch {
    case e: Exception => println(s"S3上传失败！错误信息: ${e.getMessage}")
    e.printStackTrace() // 打印完整的堆栈跟踪以便调试
} finally {
    spark.stop() // 关闭SparkSession
}