Question

最终目标是输入一个庞大的txt文件并替换csv文件中给出的所有单词。将在一个新的csv文件旁边创建一个新的txt文件，该文件将计算每个单词的出现次数。

我遇到的问题是将地图数据写入新的csv文件。我得到的数据是不确定的，但是如何将其更改为可读的？

无论我将哪种map.thingie放在data.push字段中，都会出现错误。

var fs = require('fs');
var inputFile='OneLetter.csv';
var parse = require('csv-parse');
var map1 = new Map();
var iterator = map1[Symbol.iterator]();


//This part creates a stream, essentially reads it and creates a list

var parser = parse({delimiter: ';'}, function (err, data) {
    data.forEach(function(line) {
      // create line object out of parsed fields
      var list = map1.set(line) 
     });
        for (let item of iterator) {
    console.log(item)
    };    
});

fs.createReadStream(inputFile).pipe(parser);


//This program writes a CSV file containing data in the data1, data2... fields

let data = [];
let columns = {
        Column1: '# times',
        Column2: 'Original',
        Column3: 'Short'
};

  data.push(['data1',
             'data2',
             'data3'
]); 

var stringify = require('csv-stringify');

stringify(data ,{ delimiter: ';', header: true, columns: columns }, (err, output) => {
  if (err) throw err;
  fs.writeFile('TEST.csv', output, (err) => {
    if (err) throw err;
    console.log('TEST.csv saved.');
  });
});

Working Result:

[ [ 'A', 'A' ], undefined ]
[ [ 'B', 'BE' ], undefined ]
[ [ 'C', 'SEE' ], undefined ]
[ [ 'D', 'IN THE' ], undefined ]
[ [ 'E', 'HE' ], undefined ]
[ [ 'F', 'OF THE' ], undefined ]
[ [ 'G', 'FROM THE' ], undefined ]
[ [ 'H', 'HAS' ], undefined ]
[ [ 'I', 'I' ], undefined ]
[ [ 'J', 'BY WHICH' ], undefined ]
[ [ 'K', 'OUT OF THE' ], undefined ]
[ [ 'L', 'ALL' ], undefined ]
[ [ 'M', 'MORE' ], undefined ]
[ [ 'N', 'NOT' ], undefined ]
[ [ 'O', 'OF' ], undefined ]
[ [ 'P', 'PER' ], undefined ]
[ [ 'Q', 'ON THE' ], undefined ]
[ [ 'R', 'ARE' ], undefined ]
[ [ 'S', 'SEPERATOR' ], undefined ]
[ [ 'T', 'THE' ], undefined ]
[ [ 'U', 'YOU' ], undefined ]
[ [ 'V', 'OF WHICH' ], undefined ]
[ [ 'W', 'WITH' ], undefined ]
[ [ 'X', 'IN WHICH' ], undefined ]
[ [ 'Y', 'YES' ], undefined ]
[ [ 'Z', 'FROM WHICH' ], undefined ]
TEST.csv saved.

非工作结果：

Error: Invalid Record: expect an array or an object, got undefined
    at Stringifier._transform (C:\Program Files\nodejs\node_modules\csv-stringify\lib\index.

Answer 1

我似乎没有看到根据文档在parse方法中进行转换的选项-您需要尝试使用transform使其以您想要的方式工作-因此创建一个并像这样通过它：

const transformer = transform(function(data){
    return replaceEntries(data); // here you call the replacement
});
fs.createReadStream(textFile).pipe(parser).pipe(transformer).pipe(stringify);

需要先准备好变压器

根据您的情况判断，似乎没有记录传递转换函数，并且错误可能来自此。此外，您的代码似乎并没有执行您想要达到的目标，更像是尝试创建新的CSV。

我认为您可能已经从一个奇怪的角度开始了任务，所以我建议您从头开始重做-您需要编写一个程序，按以下顺序执行以下操作：

将CSV文件读取到内存中，并创建替换图或数组
从TXT文件创建可读流
创建转换流并将其可读性管道化
创建可写流并将转换通过管道传递给它

我还建议使用我创建的scramjet框架，这可以使代码更容易理解。

const {StringStream} = require("scramjet");

StringStream
    // here we read the file
    .from(fs.createReadStream('massive.txt'))
    .use(async stream => {
        // here we create replacements
        const replacements = await (
            StringStream.from(fs.createReadStream('massive.txt'))
                .csvParse({header: false})
                // the line below will make sure we're replacing whole words
                .map(([_from, _to]) => ([new RegExp(`\b${_from}\b`, "g"), _to])
                .toArray()
        );

        // here we map all the items in the stream and iterate over all the replacements
        return stream.map(
            chunk => replacements.reduce((s, [_from, _to]) => s.replace(_from, _to), chunk)
        );
    })
    // and here we push the replaced stream to the output file
    .pipe(fs.createWriteStream('massive-file-out.txt');

请检查以.map(([_from, _to]) =>开头的行。我假设您只想在整个单词中替换文本，所以更多R U ready -> Are you ready，而不是Robert -> Areobert-这是此行的目的。

对地图中的数据进行字符串化处理？

1 个答案: