Java CSV填充在压缩后更改为字节数组

所以我从前端收到一个CSV文件，我需要将其压缩并存储到MySql数据库中。问题是，在我将文件解压缩回来后，它被修改了，不再具有CSV结构（我使用ZIP进行压缩，但我也尝试过gzip）。例如，这是压缩前的文件

header1,header2,header3,header4,header5
val,val2,val3,val4,val5
val6,val7,val8,val9,val10

header1,header2,header3,header4,header5val1,val2,val3,val4,val5val6,val7,val8.val9.val10

@Throws(Exception::class)
fun compressFile(file : ByteArray) : ByteArray {
   val baos = ByteArrayOutputStream()
   val zos = ZipOutputStream(baos)
   val entry = ZipEntry("data.csv")
   entry.size = file.size.toLong()
   zos.putNextEntry(entry)
   zos.write(file)
   zos.closeEntry()
   zos.close()
   return baos.toByteArray()
}

@Throws(Exception::class)
fun decompressFile(file : ByteArray): ByteArray {
   if (file.isEmpty()) return file
   val gis = ZipInputStream(ByteArrayInputStream(file))
   gis.nextEntry
   val bf = BufferedReader(InputStreamReader(gis, "UTF-8"))
   var outStr = ""
   var line: String
   while (bf.readLine().also { line = it ?: "" } != null) {
       outStr += line
   }
   gis.close()
   bf.close()
   return outStr.toByteArray()
}

这是解压缩后的文件

header1,header2,header3,header4,header5
val,val2,val3,val4,val5
val6,val7,val8,val9,val10

header1,header2,header3,header4,header5val1,val2,val3,val4,val5val6,val7,val8.val9.val10

@Throws(Exception::class)
fun compressFile(file : ByteArray) : ByteArray {
   val baos = ByteArrayOutputStream()
   val zos = ZipOutputStream(baos)
   val entry = ZipEntry("data.csv")
   entry.size = file.size.toLong()
   zos.putNextEntry(entry)
   zos.write(file)
   zos.closeEntry()
   zos.close()
   return baos.toByteArray()
}

@Throws(Exception::class)
fun decompressFile(file : ByteArray): ByteArray {
   if (file.isEmpty()) return file
   val gis = ZipInputStream(ByteArrayInputStream(file))
   gis.nextEntry
   val bf = BufferedReader(InputStreamReader(gis, "UTF-8"))
   var outStr = ""
   var line: String
   while (bf.readLine().also { line = it ?: "" } != null) {
       outStr += line
   }
   gis.close()
   bf.close()
   return outStr.toByteArray()
}

我需要将解压缩后的文件发送到python时间序列分析服务，它无法正确解析它

我直接将文件作为字节数组进行压缩/解压缩，我确信压缩是问题所在，因为我尝试存储和获取未压缩的CSV，它工作正常。 提前谢谢

下面是用于压缩的代码

header1,header2,header3,header4,header5
val,val2,val3,val4,val5
val6,val7,val8,val9,val10

header1,header2,header3,header4,header5val1,val2,val3,val4,val5val6,val7,val8.val9.val10

@Throws(Exception::class)
fun compressFile(file : ByteArray) : ByteArray {
   val baos = ByteArrayOutputStream()
   val zos = ZipOutputStream(baos)
   val entry = ZipEntry("data.csv")
   entry.size = file.size.toLong()
   zos.putNextEntry(entry)
   zos.write(file)
   zos.closeEntry()
   zos.close()
   return baos.toByteArray()
}

@Throws(Exception::class)
fun decompressFile(file : ByteArray): ByteArray {
   if (file.isEmpty()) return file
   val gis = ZipInputStream(ByteArrayInputStream(file))
   gis.nextEntry
   val bf = BufferedReader(InputStreamReader(gis, "UTF-8"))
   var outStr = ""
   var line: String
   while (bf.readLine().also { line = it ?: "" } != null) {
       outStr += line
   }
   gis.close()
   bf.close()
   return outStr.toByteArray()
}

下面是用于解压缩的代码

header1,header2,header3,header4,header5
val,val2,val3,val4,val5
val6,val7,val8,val9,val10

header1,header2,header3,header4,header5val1,val2,val3,val4,val5val6,val7,val8.val9.val10

@Throws(Exception::class)
fun compressFile(file : ByteArray) : ByteArray {
   val baos = ByteArrayOutputStream()
   val zos = ZipOutputStream(baos)
   val entry = ZipEntry("data.csv")
   entry.size = file.size.toLong()
   zos.putNextEntry(entry)
   zos.write(file)
   zos.closeEntry()
   zos.close()
   return baos.toByteArray()
}

@Throws(Exception::class)
fun decompressFile(file : ByteArray): ByteArray {
   if (file.isEmpty()) return file
   val gis = ZipInputStream(ByteArrayInputStream(file))
   gis.nextEntry
   val bf = BufferedReader(InputStreamReader(gis, "UTF-8"))
   var outStr = ""
   var line: String
   while (bf.readLine().also { line = it ?: "" } != null) {
       outStr += line
   }
   gis.close()
   bf.close()
   return outStr.toByteArray()
}

---

我认为，您丢失了NL字符，因为BufferedReader.readLine（）只读取最后一行而不读取新行。也就是说，您合并了Line1Line2，但跳过了它们之间的新行

您不应该通过bufferedreader读取流，您需要读取整个内容，包括新行字符，请参阅

---

另请参见相关的感谢！它可以工作，不知道readLine跳过NL转义，还有@gidds，也谢谢你，非常好的资源。