我试图读取一个大文件一行在一次。我在Quora上找到了一个关于这个主题的问题，但我错过了一些联系，把整个事情联系在一起。
var Lazy=require("lazy");
new Lazy(process.stdin)
.lines
.forEach(
function(line) {
console.log(line.toString());
}
);
process.stdin.resume();
我想要弄清楚的是如何一次从文件中读取一行，而不是像本例中那样读取STDIN。
我试着:
fs.open('./VeryBigFile.csv', 'r', '0666', Process);
function Process(err, fd) {
if (err) throw err;
// DO lazy read
}
但这并不奏效。我知道在必要时我可以使用PHP之类的东西，但我想弄清楚这个问题。
我不认为其他答案会起作用，因为文件比我运行它的服务器的内存大得多。
function createLineReader(fileName){
var EM = require("events").EventEmitter
var ev = new EM()
var stream = require("fs").createReadStream(fileName)
var remainder = null;
stream.on("data",function(data){
if(remainder != null){//append newly received data chunk
var tmp = new Buffer(remainder.length+data.length)
remainder.copy(tmp)
data.copy(tmp,remainder.length)
data = tmp;
}
var start = 0;
for(var i=0; i<data.length; i++){
if(data[i] == 10){ //\n new line
var line = data.slice(start,i)
ev.emit("line", line)
start = i+1;
}
}
if(start<data.length){
remainder = data.slice(start);
}else{
remainder = null;
}
})
stream.on("end",function(){
if(null!=remainder) ev.emit("line",remainder)
})
return ev
}
//---------main---------------
fileName = process.argv[2]
lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
console.log(line.toString())
//console.log("++++++++++++++++++++")
})
另一个解决方案是通过顺序执行器nsynjs运行逻辑。它使用节点readline模块逐行读取文件，并且不使用承诺或递归，因此在大文件上不会失败。下面是代码的样子:
var nsynjs = require('nsynjs');
var textFile = require('./wrappers/nodeReadline').textFile; // this file is part of nsynjs
function process(textFile) {
var fh = new textFile();
fh.open('path/to/file');
var s;
while (typeof(s = fh.readLine(nsynjsCtx).data) != 'undefined')
console.log(s);
fh.close();
}
var ctx = nsynjs.run(process,{},textFile,function () {
console.log('done');
});
上面的代码基于这个示例:https://github.com/amaksr/nsynjs/blob/master/examples/node-readline/index.js
function createLineReader(fileName){
var EM = require("events").EventEmitter
var ev = new EM()
var stream = require("fs").createReadStream(fileName)
var remainder = null;
stream.on("data",function(data){
if(remainder != null){//append newly received data chunk
var tmp = new Buffer(remainder.length+data.length)
remainder.copy(tmp)
data.copy(tmp,remainder.length)
data = tmp;
}
var start = 0;
for(var i=0; i<data.length; i++){
if(data[i] == 10){ //\n new line
var line = data.slice(start,i)
ev.emit("line", line)
start = i+1;
}
}
if(start<data.length){
remainder = data.slice(start);
}else{
remainder = null;
}
})
stream.on("end",function(){
if(null!=remainder) ev.emit("line",remainder)
})
return ev
}
//---------main---------------
fileName = process.argv[2]
lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
console.log(line.toString())
//console.log("++++++++++++++++++++")
})
我对缺乏全面的解决方案感到沮丧，所以我把自己的尝试(git / npm)放在一起。复制粘贴功能列表:
Interactive line processing (callback-based, no loading the entire file into RAM)
Optionally, return all lines in an array (detailed or raw mode)
Interactively interrupt streaming, or perform map/filter like processing
Detect any newline convention (PC/Mac/Linux)
Correct eof / last line treatment
Correct handling of multi-byte UTF-8 characters
Retrieve byte offset and byte length information on per-line basis
Random access, using line-based or byte-based offsets
Automatically map line-offset information, to speed up random access
Zero dependencies
Tests
国家卫生研究院?你决定:-)
我想解决同样的问题，基本上在Perl中是这样的:
while (<>) {
process_line($_);
}
我的用例只是一个独立的脚本，而不是服务器，所以同步就可以了。以下是我的标准:
可以在许多项目中重用的最小同步代码。
不限制文件大小或行数。
不限制线的长度。
能够处理UTF-8的完整Unicode，包括BMP以外的字符。
能够处理*nix和Windows行结束符(老式Mac对我来说不需要)。
行中要包含的行结束字符。
能够处理带有或不带有行尾字符的最后一行。
不要使用node.js发行版中不包含的任何外部库。
这是一个让我在node.js中感受低级脚本类型代码的项目，并决定它作为其他脚本语言(如Perl)的替代品的可行性。
经过惊人的努力和一些错误的开始，这是我提出的代码。它非常快，但没有我预期的那么琐碎:(在GitHub上分叉)
var fs = require('fs'),
StringDecoder = require('string_decoder').StringDecoder,
util = require('util');
function lineByLine(fd) {
var blob = '';
var blobStart = 0;
var blobEnd = 0;
var decoder = new StringDecoder('utf8');
var CHUNK_SIZE = 16384;
var chunk = new Buffer(CHUNK_SIZE);
var eolPos = -1;
var lastChunk = false;
var moreLines = true;
var readMore = true;
// each line
while (moreLines) {
readMore = true;
// append more chunks from the file onto the end of our blob of text until we have an EOL or EOF
while (readMore) {
// do we have a whole line? (with LF)
eolPos = blob.indexOf('\n', blobStart);
if (eolPos !== -1) {
blobEnd = eolPos;
readMore = false;
// do we have the last line? (no LF)
} else if (lastChunk) {
blobEnd = blob.length;
readMore = false;
// otherwise read more
} else {
var bytesRead = fs.readSync(fd, chunk, 0, CHUNK_SIZE, null);
lastChunk = bytesRead !== CHUNK_SIZE;
blob += decoder.write(chunk.slice(0, bytesRead));
}
}
if (blobStart < blob.length) {
processLine(blob.substring(blobStart, blobEnd + 1));
blobStart = blobEnd + 1;
if (blobStart >= CHUNK_SIZE) {
// blobStart is in characters, CHUNK_SIZE is in octets
var freeable = blobStart / CHUNK_SIZE;
// keep blob from growing indefinitely, not as deterministic as I'd like
blob = blob.substring(CHUNK_SIZE);
blobStart -= CHUNK_SIZE;
blobEnd -= CHUNK_SIZE;
}
} else {
moreLines = false;
}
}
}
它可能会被进一步清理，这是试验和错误的结果。
