使用parquetjs 创建parquet 文件

parquetjs 是纯js 的parquet 文件创建以及读取工具，以下是一个简单的使用

参考代码

var parquet = require('parquetjs');

 

var schema = new parquet.ParquetSchema({

    name: { type: 'UTF8' },

    quantity: { type: 'INT64' },

    price: { type: 'DOUBLE' },

    date: { type: 'TIMESTAMP_MILLIS' },

    in_stock: { type: 'BOOLEAN' }

});

 

 

 

// append a few rows to the file

let write = async function () {

    var writer = await parquet.ParquetWriter.openFile(schema, 'fruits.parquet');

    await writer.appendRow({ name: 'apples', quantity: 10, price: 2.5, date: new Date(), in_stock: true });

    await writer.appendRow({ name: 'oranges', quantity: 10, price: 2.5, date: new Date(), in_stock: true });

    await writer.close();

}

 

 

let read = async function () {

    let reader = await parquet.ParquetReader.openFile('fruits.parquet');

    // create a new cursor

    let cursor = reader.getCursor();

    // read all records from the file and print them

    let record = null;

    while (record = await cursor.next()) {

        console.log(record);

    }

}

write().then(()=>{

    read()

})

 

参考资料

https://github.com/ironSource/parquetjs
https://parquet.apache.org/documentation/latest/