使用JavaScript使用UTF-8(例如希腊语)编码将JSON导出为CSV或Excel

Question

我试图导出并下载JSON对象到CSV文件,我有希腊字符的问题.我的代码有效; 它并不完美,但它确实有效.

问题是希腊字符看起来像垃圾.

这是我现有的代码:

function downloadJsonToCsv(jsonObject) {
    var array = typeof jsonObject != "object" ? JSON.parse(jsonObject) : jsonObject;

    if (array == null) {
        return; // No data found on the jsonObject
    }

    var str = "";

    for (var i = 0; i < array.length; i++) {
        var line = "";

        for (var index in array[i]) {
            line += array[i][index] + ";"; // Set delimiter
        }

        // Here is an example where you would wrap the values in double quotes
        // for (var index in array[i]) {
        //    line += '"' + array[i][index] + '",';
        // }

        line.slice(0,line.Length-1); 

        str += line + "\r\n";
    }

    window.open("data:text/csv;charset=utf-8," + encodeURI(str));
}

我有两个问题.

1. 如何使用正确的希腊语字符导出此CSV文件？
2. 如何以Excel格式而非CSV格式导出此数据？

Answer 1

导出为CSV

导出为具有非ASCII字符的CSV需要在文件前加上字节顺序标记也称为BOM.在你的代码更改

var str = "";

至:

var str = "\uFEFF";

您需要一个现代版本的Excel来识别BOM.正如这篇有用的StackOverflow文章所述,Excel 2003及更早版本不会正确地遵循 BOM.我只能在Windows上访问Excel 2003,所以我暂时无法对此进行测试,但是它的记录非常清楚.

遗憾的是,Excel 2011 for the Macintosh在这个意义上并不是一个"现代Excel".令人高兴的是,Google表格做了正确的事情.

直接导出到Excel

这是下面代码的jsFiddle实现.它生成一个 SpreadsheetXml文档.这种方法的好处是你可能会非常棘手......添加公式并做更多特定于Excel的事情.

// Test script to generate a file from JavaScript such
// that MS Excel will honor non-ASCII characters.

testJson = [
    {
        "name": "Tony Peña",
        "city": "New York",
        "country": "United States",
        "birthdate": "1978-03-15",
        "amount": 42

    },
    {
        "name": "??????? Thessaloniki",
        "city": "Athens",
        "country": "Greece",
        "birthdate": "1987-11-23",
        "amount": 42
    }
];

// Simple type mapping; dates can be hard
// and I would prefer to simply use `datevalue`
// ... you could even add the formula in here.
testTypes = {
    "name": "String",
    "city": "String",
    "country": "String",
    "birthdate": "String",
    "amount": "Number"
};

emitXmlHeader = function () {
    var headerRow =  '<ss:Row>\n';
    for (var colName in testTypes) {
        headerRow += '  <ss:Cell>\n';
        headerRow += '    <ss:Data ss:Type="String">';
        headerRow += colName + '</ss:Data>\n';
        headerRow += '  </ss:Cell>\n';        
    }
    headerRow += '</ss:Row>\n';    
    return '<?xml version="1.0"?>\n' +
           '<ss:Workbook xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet">\n' +
           '<ss:Worksheet ss:Name="Sheet1">\n' +
           '<ss:Table>\n\n' + headerRow;
};

emitXmlFooter = function() {
    return '\n</ss:Table>\n' +
           '</ss:Worksheet>\n' +
           '</ss:Workbook>\n';
};

jsonToSsXml = function (jsonObject) {
    var row;
    var col;
    var xml;
    var data = typeof jsonObject != "object" 
             ? JSON.parse(jsonObject) 
             : jsonObject;

    xml = emitXmlHeader();

    for (row = 0; row < data.length; row++) {
        xml += '<ss:Row>\n';

        for (col in data[row]) {
            xml += '  <ss:Cell>\n';
            xml += '    <ss:Data ss:Type="' + testTypes[col]  + '">';
            xml += data[row][col] + '</ss:Data>\n';
            xml += '  </ss:Cell>\n';
        }

        xml += '</ss:Row>\n';
    }

    xml += emitXmlFooter();
    return xml;  
};

console.log(jsonToSsXml(testJson));

这将生成下面的XML文档.如果此XML保存在名为test.xls的文件中,则Excel应识别此项并使用正确的编码将其打开.

<?xml version="1.0"?>
<ss:Workbook xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet">
<ss:Worksheet ss:Name="Sheet1">
<ss:Table>

<ss:Row>
  <ss:Cell>
    <ss:Data ss:Type="String">name</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">city</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">country</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">birthdate</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">amount</ss:Data>
  </ss:Cell>
</ss:Row>

<ss:Row>
  <ss:Cell>
    <ss:Data ss:Type="String">Tony Peña</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">New York</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">United States</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">1978-03-15</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="Number">42</ss:Data>
  </ss:Cell>
</ss:Row>
<ss:Row>
  <ss:Cell>
    <ss:Data ss:Type="String">??????? Thessaloniki</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">Athens</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">Greece</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="String">1987-11-23</ss:Data>
  </ss:Cell>
  <ss:Cell>
    <ss:Data ss:Type="Number">42</ss:Data>
  </ss:Cell>
</ss:Row>

</ss:Table>
</ss:Worksheet>
</ss:Workbook>

但是,我必须承认,如果可能的话,我强烈倾向于做这个服务器端.我过去使用Python库openpyxl来做这件事,而且非常简单.大多数服务器端语言都有一个生成Excel文件的库,它们应该提供比字符串连接更好的构造.

无论如何,请参阅此MSDN博客了解基础知识.这篇StackOverflow文章提供了各种其他选项的优缺点.

Answer 2

要使Excel读取Unicode CSV文件,您必须添加字节顺序标记作为csv中的第一个字符串.这可以通过JavaScript在代码中添加以下行来完成:

line="\ufeff"+line