xmlreader与xmlwriter里的几个坑与解决方案
Posted zhanglb163
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了xmlreader与xmlwriter里的几个坑与解决方案相关的知识，希望对你有一定的参考价值。
加载超过100M的xml文件时（可能不是很常见），XmlDocument这种全部加载到内存里的模式就有点不友好了，耗时长、内存高。
这时用xmlreader就会有自行车换超跑的感觉，但其间遇到几个坑，记录一下。
先看源码，包括dom和sax两种模式的读取和写入
DOM模式：
1 /// <summary>
2 /// dom模式创建xml文件
3 /// </summary>
4 /// <param name="path"></param>
5 public void CreateXml_Dom(string path)
6 {
7 XmlDocument xmlDocw = new XmlDocument();
8 //xml头
9 var xmldecl = xmlDocw.CreateXmlDeclaration("1.0", "utf-8", null);
10 var root = xmlDocw.CreateElement("root");
11 root.SetAttribute("Name", "李四");
12 var test = xmlDocw.CreateElement("test");
13 root.AppendChild(test);
14
15 xmlDocw.AppendChild(xmldecl);
16 xmlDocw.AppendChild(root);
17 xmlDocw.Save(path);
18
19 //可以通过xmlreader读数据后生成节点
20 //var node = xmlDocw.ReadNode(rdr);
21 //root.AppendChild(node);
22 //或者读取outerxml后作为innerxml写入
23 //string str = rdr.ReadOuterXml();
24 //root.InnerXml = str;
25 }
26
27 /// <summary>
28 /// dom模式读取xml
29 /// </summary>
30 /// <param name="path"></param>
31 public void ReadXml_Dom(string path)
32 {
33 XmlDocument xmlDocr = new XmlDocument();
34 xmlDocr.Load(path);
35 var root = xmlDocr.DocumentElement;
36 string str = root.GetAttribute("Name");
37 Console.WriteLine(str);
38 }
SAX（simple API for XML）模式：几种错误也都用注释标注出来了
1 /// <summary>
2 /// xmlwriter创建xml文件
3 /// </summary>
4 /// <param name="path"></param>
5 public void CreateXml_Sax(string path)
6 {
7 //filestream没问题
8 //FileStream stream = new FileStream(path,FileMode.Create);
9 //会出现编码一直是utf-16问题
10 //StringBuilder stream = new StringBuilder();
11 MemoryStream stream = new MemoryStream();
12 XmlWriterSettings settings = new XmlWriterSettings();
13 //Encoding.UTF8这个会报错,字节顺序标记
14 settings.Encoding = new UTF8Encoding(false);
15 XmlWriter xw = XmlWriter.Create(stream, settings);
16 //XmlTextWriter xw = new XmlTextWriter(stream, new UTF8Encoding(false));
17
18 //写入声明
19 xw.WriteStartDocument();
20
21 xw.WriteStartElement("root");
22 xw.WriteAttributeString("Name", "张三");
23 //可以通过xmlreader读数据后直接写入
24 //xw.WriteNode(rdr);
25 xw.WriteStartElement("test");
26 xw.WriteEndElement();
27
28 xw.WriteEndElement();
29
30 xw.WriteEndDocument();
31 xw.Close();
32
33 string xmlstr = Encoding.UTF8.GetString(stream.ToArray());
34 stream.Close();
35 XmlDocument xmlDocw = new XmlDocument();
36 xmlDocw.LoadXml(xmlstr);
37 xmlDocw.Save(path);
38 }
39
40 /// <summary>
41 /// xmlreader读取xml
42 /// </summary>
43 /// <param name="path"></param>
44 public void ReadXml_Sax(string path)
45 {
46 XmlDocument xmlDocw = new XmlDocument();
47 XmlReaderSettings rsettings = new XmlReaderSettings();
48 rsettings.IgnoreComments = true;
49 rsettings.IgnoreWhitespace = false;
50 rsettings.CheckCharacters = false;
51 //默认的xmlreader不读取内容中的回车换行
52 //(XmlReader rdr = XmlReader.Create(path,rsettings))
53 using (XmlTextReader rdr = new XmlTextReader(path))
54 {
55 rdr.WhitespaceHandling = WhitespaceHandling.Significant;
56 string eleName = "";
57 while (rdr.Read())
58 {
59 if (rdr.NodeType == XmlNodeType.Element)
60 {
61 //节点名称
62 eleName = rdr.Name;
63 //节点深度
64 int dp = rdr.Depth;
65 //是否空节点，表示<elememt/> 不是<element></element>
66 bool needend = rdr.IsEmptyElement;
67 for (int i = 0; i < rdr.AttributeCount; i++)
68 {
69 rdr.MoveToAttribute(i);
70 Console.WriteLine(rdr.Name+":"+rdr.Value);
71 }
72 //可以直接读取节点所有的数据.可以用readNode读取
73 //rdr.EOF判定，不然会跳过节点
74 //rdr.ReadOuterXml();
75 }
76 else if (rdr.NodeType == XmlNodeType.EndElement)
77 {
78 eleName = rdr.Name;
79 }
80