从nodejs readline正确查找字节范围答案

【问题标题】：Finding byte range correctly from nodejs readline从nodejs readline正确查找字节范围
【发布时间】：2021-01-05 15:06:18
【问题描述】：

我正在使用 node js 的 readline 读取一个大的 csv 文件。我想找出我正确读取了多少字节。或块的字节位置。 readline 正在计算第一行的换行符，但我猜其他人没有，所以这有点使整个字节范围错误。有人可以帮忙吗？另外，告诉这是否是正确的方法？另外，假设我读完后可以知道字节位置是什么，比如说 100 行。

const fs = require("fs");
const readline = require("readline");

const csvfile = "csv-file.csv";

// stream
let stream1 = fs.createReadStream(csvfile);

// Stream 2 to read only the specific bytes
//let stream2 = fs.createReadStream(csvfile, { start: 97, end: 174 });
let rl = readline.createInterface({
    input: stream1,
    terminal: false,
  });

var lines = 0;
var byterange = []
var startingByte = 0;
var totalBytesInThisBlock = 0;

// Print those specific bytes and see if it's working as expected.
// stream2.on('data', (data) => {
//     console.log(data.toString('utf8'));
// });
// stream2.on('end', ()=>{});

rl.on('line', (input) => {
//console.log(input);
lines++;
totalBytesInThisBlock += Buffer.byteLength(input);
console.log("total bytes till line "+lines +" and adding "+Buffer.byteLength(input)+" now : " + totalBytesInThisBlock);

//Making blocks of 4 lines i.e. starting byte of 1st line starting byte to 4th line ending byte
// 5th line starting byte to ending byte of 8th line and so on.
if(lines%4==0) {
byterange.push("bytes="+startingByte+"-"+(totalBytesInThisBlock+startingByte));
startingByte+=totalBytesInThisBlock+1;
totalBytesInThisBlock=0;
}
});

rl.on('close', () => {
console.log("lines read : " + lines);
console.log(byterange);

//Total bytes in file
var filedata = fs.readFileSync(csvfile);
console.log(Buffer.byteLength(filedata));
});

【问题讨论】：

标签： javascript node.js readline

【解决方案1】：

我犯的范围计算错误是：

你好世界 0 10 这是示例行。 11. 50

换行时我没有添加一个。所以0-10是1，next不能是10到50，应该是11-50

var lines = 0;
var byterange = []
var startingByte = 0;
var totalBytesInThisBlock = 0;
var lastByteLength = 0;
var byteCursor = -1;
var lastCursor = -1;

rl.on('line', (input) => {
//console.log(input);
lines++;
byteCursor++;
lastByteLength = Buffer.byteLength(input);
byteCursor += lastByteLength;
//console.log("total bytes till line "+lines +" and adding "+Buffer.byteLength(input)+" now : " + totalBytesInThisBlock);

//Making blocks of 4 lines i.e. starting byte of 1st line starting byte to 4th line ending byte
// 5th line starting byte to ending byte of 8th line and so on.
if(byteCursor-startingByte>400) {
    lastCursor = byteCursor;
    console.log("bytes="+startingByte+"-"+byteCursor);
    startingByte = byteCursor+1;
//byterange.push("bytes="+startingByte+"-"+(lastByteLength+startingByte));
//startingByte+=lastByteLength+1;
//totalBytesInThisBlock=0;
}
});

这里 byteCursor 完成了这项工作。

【讨论】：