本主題顯示以不同於來源 XML 的組織結構規劃 XML 的範例。
許多典型的 XML 轉換都包含鏈結的查詢，如此範例中所示。 常見的狀況是，從特定格式的 XML 開始，將中繼結果規劃為匿名型別或具名型別的集合，最後再將結果規劃回完全不同於來源 XML 之組織結構的 XML。
範例
此範例會處理 WordprocessingML 文件，並從 WordprocessingML 文件擷取段落節點。 它也可以識別每個段落的樣式和文字。 最後，此範例會使用不同的組織結構規劃 XML。 此範例在這個教學課程中，會在先前的範例上建置。 進行規劃的新陳述式會在以下程式碼的註解中叫出。
如需建立此範例之來源文件的指示，請參閱建立 Office Open XML 文件來源。
這個範例會使用 WindowsBase 組件的類別。 它會使用 System.IO.Packaging 命名空間中的型別。
public static class LocalExtensions
{
public static string StringConcatenate(this IEnumerable<string> source)
{
StringBuilder sb = new StringBuilder();
foreach (string s in source)
sb.Append(s);
return sb.ToString();
}
public static string StringConcatenate<T>(this IEnumerable<T> source,
Func<T, string> func)
{
StringBuilder sb = new StringBuilder();
foreach (T item in source)
sb.Append(func(item));
return sb.ToString();
}
public static string StringConcatenate(this IEnumerable<string> source, string separator)
{
StringBuilder sb = new StringBuilder();
foreach (string s in source)
sb.Append(s).Append(separator);
return sb.ToString();
}
public static string StringConcatenate<T>(this IEnumerable<T> source,
Func<T, string> func, string separator)
{
StringBuilder sb = new StringBuilder();
foreach (T item in source)
sb.Append(func(item)).Append(separator);
return sb.ToString();
}
}
class Program
{
public static string ParagraphText(XElement e)
{
XNamespace w = e.Name.Namespace;
return e
.Elements(w + "r")
.Elements(w + "t")
.StringConcatenate(element => (string)element);
}
static void Main(string[] args)
{
const string fileName = "SampleDoc.docx";
const string documentRelationshipType =
"https://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument";
const string stylesRelationshipType =
"https://schemas.openxmlformats.org/officeDocument/2006/relationships/styles";
const string wordmlNamespace =
"https://schemas.openxmlformats.org/wordprocessingml/2006/main";
XNamespace w = wordmlNamespace;
XDocument xDoc = null;
XDocument styleDoc = null;
using (Package wdPackage = Package.Open(fileName, FileMode.Open, FileAccess.Read))
{
PackageRelationship docPackageRelationship =
wdPackage.GetRelationshipsByType(documentRelationshipType).FirstOrDefault();
if (docPackageRelationship != null)
{
Uri documentUri = PackUriHelper.ResolvePartUri(new Uri("/", UriKind.Relative),
docPackageRelationship.TargetUri);
PackagePart documentPart = wdPackage.GetPart(documentUri);
// Load the document XML in the part into an XDocument instance.
xDoc = XDocument.Load(XmlReader.Create(documentPart.GetStream()));
// Find the styles part. There will only be one.
PackageRelationship styleRelation =
documentPart.GetRelationshipsByType(stylesRelationshipType).FirstOrDefault();
if (styleRelation != null)
{
Uri styleUri =
PackUriHelper.ResolvePartUri(documentUri, styleRelation.TargetUri);
PackagePart stylePart = wdPackage.GetPart(styleUri);
// Load the style XML in the part into an XDocument instance.
styleDoc = XDocument.Load(XmlReader.Create(stylePart.GetStream()));
}
}
}
string defaultStyle =
(string)(
from style in styleDoc.Root.Elements(w + "style")
where (string)style.Attribute(w + "type") == "paragraph" &&
(string)style.Attribute(w + "default") == "1"
select style
).First().Attribute(w + "styleId");
// Find all paragraphs in the document.
var paragraphs =
from para in xDoc
.Root
.Element(w + "body")
.Descendants(w + "p")
let styleNode = para
.Elements(w + "pPr")
.Elements(w + "pStyle")
.FirstOrDefault()
select new
{
ParagraphNode = para,
StyleName = styleNode != null ?
(string)styleNode.Attribute(w + "val") :
defaultStyle
};
// Retrieve the text of each paragraph.
var paraWithText =
from para in paragraphs
select new
{
ParagraphNode = para.ParagraphNode,
StyleName = para.StyleName,
Text = ParagraphText(para.ParagraphNode)
};
// The following is the new code that projects XML in a new shape.
XElement root = new XElement("Root",
from p in paraWithText
select new XElement("Paragraph",
new XElement("StyleName", p.StyleName),
new XElement("Text", p.Text)
)
);
Console.WriteLine(root);
}
}
Imports <xmlns:w="https://schemas.openxmlformats.org/wordprocessingml/2006/main">
Module Module1
<System.Runtime.CompilerServices.Extension()> _
Public Function StringConcatenate(ByVal source As IEnumerable(Of String)) As String
Dim sb As StringBuilder = New StringBuilder()
For Each s As String In source
sb.Append(s)
Next
Return sb.ToString()
End Function
<System.Runtime.CompilerServices.Extension()> _
Public Function StringConcatenate(Of T)(ByVal source As IEnumerable(Of T), _
ByVal func As Func(Of T, String)) As String
Dim sb As StringBuilder = New StringBuilder()
For Each item As T In source
sb.Append(func(item))
Next
Return sb.ToString()
End Function
<System.Runtime.CompilerServices.Extension()> _
Public Function StringConcatenate(Of T)(ByVal source As IEnumerable(Of T), _
ByVal separator As String) As String
Dim sb As StringBuilder = New StringBuilder()
For Each s As T In source
sb.Append(s).Append(separator)
Next
Return sb.ToString()
End Function
<System.Runtime.CompilerServices.Extension()> _
Public Function StringConcatenate(Of T)(ByVal source As IEnumerable(Of T), _
ByVal func As Func(Of T, String), ByVal separator As String) As String
Dim sb As StringBuilder = New StringBuilder()
For Each item As T In source
sb.Append(func(item)).Append(separator)
Next
Return sb.ToString()
End Function
Public Function ParagraphText(ByVal e As XElement) As String
Dim w As XNamespace = e.Name.Namespace
Return (e.<w:r>.<w:t>).StringConcatenate(Function(element) CStr(element))
End Function
' Following function is required because VB does not support short circuit evaluation
Private Function GetStyleOfParagraph(ByVal styleNode As XElement, _
ByVal defaultStyle As String) As String
If (styleNode Is Nothing) Then
Return defaultStyle
Else
Return styleNode.@w:val
End If
End Function
Sub Main()
Dim fileName = "SampleDoc.docx"
Dim documentRelationshipType = _
"https://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument"
Dim stylesRelationshipType = _
"https://schemas.openxmlformats.org/officeDocument/2006/relationships/styles"
Dim wordmlNamespace = _
"https://schemas.openxmlformats.org/wordprocessingml/2006/main"
Dim xDoc As XDocument = Nothing
Dim styleDoc As XDocument = Nothing
Using wdPackage As Package = Package.Open(fileName, FileMode.Open, FileAccess.Read)
Dim docPackageRelationship As PackageRelationship = _
wdPackage.GetRelationshipsByType(documentRelationshipType).FirstOrDefault()
If (docPackageRelationship IsNot Nothing) Then
Dim documentUri As Uri = PackUriHelper.ResolvePartUri(New Uri("/", UriKind.Relative), _
docPackageRelationship.TargetUri)
Dim documentPart As PackagePart = wdPackage.GetPart(documentUri)
' Load the document XML in the part into an XDocument instance.
xDoc = XDocument.Load(XmlReader.Create(documentPart.GetStream()))
' Find the styles part. There will only be one.
Dim styleRelation As PackageRelationship = _
documentPart.GetRelationshipsByType(stylesRelationshipType).FirstOrDefault()
If (Not (styleRelation Is Nothing)) Then
Dim styleUri As Uri = _
PackUriHelper.ResolvePartUri(documentUri, styleRelation.TargetUri)
Dim stylePart As PackagePart = wdPackage.GetPart(styleUri)
' Load the style XML in the part into an XDocument instance.
styleDoc = XDocument.Load(XmlReader.Create(stylePart.GetStream()))
End If
End If
End Using
Dim defaultStyle As String = _
( _
From style In styleDoc.Root.<w:style> _
Where style.@w:type = "paragraph" And _
style.@w:default = "1" _
Select style _
).First().@w:styleId
' Find all paragraphs in the document.
Dim paragraphs = _
From para In xDoc.Root.<w:body>...<w:p> _
Let styleNode As XElement = para.<w:pPr>.<w:pStyle>.FirstOrDefault _
Select New With { _
.ParagraphNode = para, _
.StyleName = GetStyleOfParagraph(styleNode, defaultStyle) _
}
' Retrieve the text of each paragraph.
Dim paraWithText = _
From para In paragraphs _
Select New With { _
.ParagraphNode = para.ParagraphNode, _
.StyleName = para.StyleName, _
.Text = ParagraphText(para.ParagraphNode) _
}
' Following is the new code that projects XML in a new shape
Dim root As XElement = _
<Root>
<%= _
From p In paraWithText _
Select _
<Paragraph>
<StyleName><%= p.StyleName %></StyleName>
<Text><%= p.Text %></Text>
</Paragraph> _
%>
</Root>
Console.WriteLine(root)
End Sub
End Module
這個範例產生下列輸出：
<Root>
<Paragraph>
<StyleName>Heading1</StyleName>
<Text>Parsing WordprocessingML with LINQ to XML</Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text></Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text>The following example prints to the console.</Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text></Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text>using System;</Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text></Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text>class Program {</Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text> public static void (string[] args) {</Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text> Console.WriteLine("Hello World");</Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text> }</Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text>}</Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text></Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text>This example produces the following output:</Text>
</Paragraph>
<Paragraph>
<StyleName>Normal</StyleName>
<Text></Text>
</Paragraph>
<Paragraph>
<StyleName>Code</StyleName>
<Text>Hello World</Text>
</Paragraph>
</Root>
後續步驟
在下一個範例中，我們會在 Word 文件中進行查詢以尋找所有文字：