ADLA XMLExtractor无法读取属性？

2 回答

• 1

  问题是 Microsoft.Analytics.Samples.Formats.Xml.XmlDomExtractor 完全忽略了XML命名空间 .

  更好的实现看起来像这样（虽然未经测试）：

  [SqlUserDefinedExtractor(AtomicFileProcessing = true)]
  public class XmlDomExtractorNs : IExtractor
  {
      private string rowPath;
      private SqlMap<string, string> columnPaths;
      private string namespaces;
      private Regex xmlns = new Regex("(?:xmlns:)?(\\S+)\\s*=\\s*([\"']?)(\\S+)\\2");
  
      public XmlDomExtractor(string rowPath, SqlMap<string, string> columnPaths, string namespaces)
      {
          this.rowPath = rowPath;
          this.columnPaths = columnPaths;
          this.namespaces = namespaces;
      }
  
      public override IEnumerable<IRow> Extract(IUnstructuredReader input, IUpdatableRow output)
      {
          IColumn column = output.Schema.FirstOrDefault(col => col.Type != typeof(string));
          if (column != null)
          {
              throw new ArgumentException(string.Format("Column '{0}' must be of type 'string', not '{1}'", column.Name, column.Type.Name));
          }
  
          XmlDocument xmlDocument = new XmlDocument();
          xmlDocument.Load(input.BaseStream);
  
          XmlNamespaceManager nsmgr = new XmlNamespaceManager(xmlDocument.NameTable);
          if (this.namespaces != null)
          {
              foreach (Match nsdef in xmlns.Matches(this.namespaces))
              {
                  string prefix = nsdef.Groups[1].Value;
                  string uri = nsdef.Groups[3].Value;
                  nsmgr.AddNamespace(prefix, uri);
              }
          }
  
          foreach (XmlNode xmlNode in xmlDocument.DocumentElement.SelectNodes(this.rowPath, nsmgr))
          {
              foreach(IColumn col in output.Schema)
              {
                  var explicitColumnMapping = this.columnPaths.FirstOrDefault(columnPath => columnPath.Value == col.Name);
                  XmlNode xml = xmlNode.SelectSingleNode(explicitColumnMapping.Key ?? col.Name, nsmgr);
                  output.Set(explicitColumnMapping.Value ?? col.Name, xml == null ? null : xml.InnerXml);
              }
              yield return output.AsReadOnly();
          }
      }
  }
  

  并像这样使用：

  @e = EXTRACT a string, b string
    FROM @"D:\file.xml"
    USING new Your.Namespace.XmlDomExtractorNs(
      rowPath:"lics:rec",
      columnPaths:new SQL.MAP<string, string> { {"@sTime", "a"} },
      namespaces:"lics=http://the/namespace/of/the/doc"
    );
  
  OUTPUT @e TO "D:/output.csv" USING Outputters.Csv(quoting:false);
  

  namespaces参数将被解析为namespace-prefix和namespace-uri部分，然后将用于驱动XPath查询 . 为方便起见，它支持以下任何值格式：

  • 'xmlns:foo="http://uri/1" xmlns:bar="http://uri/2"'

  • "xmlns:foo='http://uri/1' xmlns:bar='http://uri/2'"

  • "xmlns:foo=http://uri/1 xmlns:bar=http://uri/2"

  • "foo=http://uri/1 bar=http://uri/2"

  所以它可以直接从XML源复制它们，也可以手动创建它们而不用太大惊小怪 .

  由于您使用的XML文档具有默认命名空间，并且XPath要求在表达式中使用您需要的任何命名空间的前缀，因此必须为命名空间URI选择命名空间前缀 . 我选择使用上面的 lics .

  ---

  FWIW，解析名称空间参数的正则表达式分解如下：

  (?:            # non-capturing group
    xmlns:       #   literal "xmlns:"
  )?             # end non-capturing group, make optional
  (\S+)          # GROUP 1 (prefix): any number of non-whitespace characters
  \s*=\s*        # a literal "=" optionally surrounded by whitespace
  (["']?)        # GROUP 2 (delimiter): either single or double quote, optional
  (\S+)          # GROUP 3 (uri): any number of non-whitespace characters
  \2             # whatever was in group 2 to end the namespace URI
  

  回复于 2024-05-03T22:17:14+08:00
• 3

  我可能会使用另一个SQL.MAP来定义命名空间映射的前缀（并且不需要与文档中相同的前缀） .

  我在这里创建了一个功能请求：https://feedback.azure.com/forums/327234-data-lake/suggestions/11675604-add-xml-namespace-support-to-xml-extractor . 请添加您的投票 .

  UPDATE: The XmlDomExtractor now supports XML Namespaces. Use the following USING clause:

  USING new Microsoft.Analytics.Samples.Formats.Xml.XmlDomExtractor(rowPath:"ns:rec",
                       columnPaths:new SQL.MAP<string, string> { {"@sTime", "a"} },
                       namespaceDecls: new SqlMap<string,string>{{"ns","***"}});
  

  回复于 2024-05-03T22:17:14+08:00