在 Word 文档中查找文本
本主题扩展了以前的查询，以执行一些有用的任务：在文档中查找一个字符串的所有匹配项。
示例
本示例处理一个 WordprocessingML 文档，在该文档中查找特定文本片断的所有匹配项。 为演示此操作，我们使用一个查询，查找字符串“Hello”。 本示例以本教程中前面的一些示例为基础构建。 下面代码中的注释标识出了这个新查询。
有关创建本示例的源文档的说明，请参见创建源 Office Open XML 文档。
本示例使用 WindowsBase 程序集中的类。 它使用 System.IO.Packaging 命名空间中的类型。
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)
};
// Following is the new query that retrieves all paragraphs
// that have specific text in them.
var helloParagraphs =
from para in paraWithText
where para.Text.Contains("Hello")
select new
{
ParagraphNode = para.ParagraphNode,
StyleName = para.StyleName,
Text = para.Text
};
foreach (var p in helloParagraphs)
Console.WriteLine("StyleName:{0} >{1}<", p.StyleName, p.Text);
}
}
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 (styleRelation IsNot 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 query that retrieves all paragraphs
' that have specific text in them.
Dim helloParagraphs = _
From para In paraWithText _
Where para.Text.Contains("Hello") _
Select New With _
{ _
.ParagraphNode = para.ParagraphNode, _
.StyleName = para.StyleName, _
.Text = para.Text _
}
For Each p In helloParagraphs
Console.WriteLine("StyleName:{0} >{1}<", p.StyleName, p.Text)
Next
End Sub
End Module
此示例产生以下输出：
StyleName:Code > Console.WriteLine("Hello World");<
StyleName:Code >Hello World<
当然，您可以修改搜索条件，使它搜索具有特定样式的行。 下面的查询查找具有“Code”样式的所有空行：
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)
};
// Retrieve all paragraphs that have no text and are styled Code.
var blankCodeParagraphs =
from para in paraWithText
where para.Text == "" && para.StyleName == "Code"
select new
{
ParagraphNode = para.ParagraphNode,
StyleName = para.StyleName,
Text = para.Text
};
foreach (var p in blankCodeParagraphs)
Console.WriteLine("StyleName:{0} >{1}<", p.StyleName, p.Text);
}
}
Imports System.IO.Packaging
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 (styleRelation IsNot 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) _
}
' Retrieve all paragraphs that have no text and are styled Code.
Dim blankCodeParagraphs = _
From para In paraWithText _
Where String.IsNullOrEmpty(para.Text) And para.StyleName.Equals("Code") _
Select New With _
{ _
.ParagraphNode = para.ParagraphNode, _
.StyleName = para.StyleName, _
.Text = para.Text _
}
For Each p In blankCodeParagraphs
Console.WriteLine("StyleName:{0} >{1}<", p.StyleName, p.Text)
Next
End Sub
End Module
此示例产生以下输出：
StyleName:Code ><
当然，可以通过多种方式对此示例进行改进。 例如，可以使用正则表达式来搜索文本，可以循环访问某一特定目录下的所有 Word 文件等等。
请注意，此示例的执行效果与将它编写为一个单个查询几乎同样好。 因为每个查询都以迟缓方式实现，每个查询直到循环到该查询时才生成结果。 有关执行和迟缓计算的更多信息，请参见LINQ to XML 中的延迟执行和迟缓计算。
后续步骤
下一节提供有关 WordprocessingML 文档的更多信息：