我正在使用以下XML输出器来基于CSV数据编写xml文件。
public override void Output(IRow input, IUnstructuredWriter output)
{
IColumn badColumn = input.Schema.FirstOrDefault(col => col.Type != typeof(string));
if (badColumn != null)
{
throw new ArgumentException(string.Format("Column '{0}' must be of type 'string', not '{1}'", badColumn.Name, badColumn.Type.Name));
}
using (var writer = XmlWriter.Create(output.BaseStream, this.fragmentSettings))
{
writer.WriteStartElement(this.rowPath);
foreach (IColumn col in input.Schema)
{
var value = input.Get<string>(col.Name);
if (value != null)
{
// Skip null values in order to distinguish them from empty strings
writer.WriteElementString(this.columnPaths[col.Name] ?? col.Name, value);
}
}
}
}
它工作得非常好,作业完全没有任何错误但是,在预览和下载文件时还有另一个额外的字符,导致读取的xml文件失败。我尝试使用片段级别和Auto作为一致性级别。
我获得的样本输出是
并且2个标签之间的额外字符在读取文件时导致问题。
答案 0 :(得分:0)
我通过明确提供编码设置以及使用以下代码结束标记来解决问题
private XmlWriterSettings fragmentSettings = new XmlWriterSettings
{
ConformanceLevel = ConformanceLevel.Auto,
Encoding = Encoding.UTF8
};
public override void Output(IRow input, IUnstructuredWriter output)
{
IColumn badColumn = input.Schema.FirstOrDefault(col => col.Type != typeof(string));
if (badColumn != null)
{
throw new ArgumentException(string.Format("Column '{0}' must be of type 'string', not '{1}'", badColumn.Name, badColumn.Type.Name));
}
using (var writer = XmlWriter.Create(output.BaseStream, this.fragmentSettings))
{
writer.WriteStartElement(this.rowPath);
foreach (IColumn col in input.Schema)
{
var value = input.Get<string>(col.Name);
if (value != null)
{
// Skip null values in order to distinguish them from empty strings
writer.WriteElementString(this.columnPaths[col.Name] ?? col.Name, value);
}
}
writer.WriteEndElement(); //explicit closing tag for stream
}
}
这将输出格式良好的XML,可以使用任何xml读取器轻松读取。