ES-262914-How to find and remove the long text in Word document

Find-and-Replace/Find-And-Remove-LongText/.NET/Find-And-Remove-LongText.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.14.36930.0 d17.14
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Find-And-Remove-LongText", "Find-And-Remove-LongText\Find-And-Remove-LongText.csproj", "{E7831400-4839-7597-D279-1825650F1DB7}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{E7831400-4839-7597-D279-1825650F1DB7}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{E7831400-4839-7597-D279-1825650F1DB7}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{E7831400-4839-7597-D279-1825650F1DB7}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{E7831400-4839-7597-D279-1825650F1DB7}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {9A56DF1A-9E81-4559-B4B8-B1018E6490C8}
+	EndGlobalSection
+EndGlobal

Find-and-Replace/Find-And-Remove-LongText/.NET/Find-And-Remove-LongText/Find-And-Remove-LongText.csproj

@@ -0,0 +1,22 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+    <PropertyGroup>
+        <OutputType>Exe</OutputType>
+        <TargetFramework>net8.0</TargetFramework>
+		<RootNamespace>Find-And-Remove-LongText</RootNamespace>
+        <ImplicitUsings>enable</ImplicitUsings>
+        <Nullable>enable</Nullable>
+    </PropertyGroup>
+
+    <ItemGroup>
+      <PackageReference Include="Syncfusion.DocIORenderer.Net.Core" Version="*" />
+    </ItemGroup>
+	<ItemGroup>
+    <None Update="Data\Input.docx">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+   </ItemGroup>
+</Project>

Find-and-Replace/Find-And-Remove-LongText/.NET/Find-And-Remove-LongText/Output/.gitkeep

@@ -0,0 +1 @@
+

Find-and-Replace/Find-And-Remove-LongText/.NET/Find-And-Remove-LongText/Program.cs

@@ -0,0 +1,131 @@
+using Syncfusion.DocIO;
+using Syncfusion.DocIO.DLS;
+using Syncfusion.DocIORenderer;
+using Syncfusion.Pdf;
+using System.IO;
+
+
+namespace Find_And_Remove_LongText
+{
+    class Program
+    {
+        // Set text length to be remove from the document
+        static int requiredLongTextLength = 300;
+
+        static void Main(string[] args)
+        {
+            // Open an existing word document 
+            using (FileStream inputFileStream = new FileStream(Path.GetFullPath(@"../../../Data/Input.docx"), FileMode.Open))
+            {
+                //Loads an existing Word document.
+                using (WordDocument wordDocument = new WordDocument(inputFileStream, FormatType.Docx))
+                {
+                    // Remove long texts
+                    CheckAndRemoveLongText(wordDocument);
+                    //Creates an instance of DocIORenderer.
+                    using (DocIORenderer renderer = new DocIORenderer())
+                    {
+                        //Converts Word document into PDF document.
+                        using (PdfDocument pdfDocument = renderer.ConvertToPDF(wordDocument))
+                        {
+                            //Saves the PDF file to file system.    
+                            using (FileStream outputStream = new FileStream(Path.GetFullPath(@"..\..\..\Output\WordToPDF.pdf"), FileMode.Create, FileAccess.ReadWrite, FileShare.ReadWrite))
+                            {
+                                pdfDocument.Save(outputStream);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+        private static void CheckAndRemoveLongText(WordDocument document)
+        {
+            List<Entity> paragraphs = document.FindAllItemsByProperty(EntityType.Paragraph, null, null);
+            foreach (Entity paragraph in paragraphs) 
+            {
+                WParagraph wParagraph = paragraph as WParagraph;
+                IterateParagraph(wParagraph.Items);
+            }
+        }
+        private static void IterateTextBody(WTextBody textBody)
+        {
+            //Iterates through each of the child items of WTextBody
+            for (int i = 0; i < textBody.ChildEntities.Count; i++)
+            {
+                //IEntity is the basic unit in DocIO DOM. 
+                //Accesses the body items (should be either paragraph, table or block content control) as IEntity
+                IEntity bodyItemEntity = textBody.ChildEntities[i];
+                //A Text body has 3 types of elements - Paragraph, Table and Block Content Control
+                //Decides the element type by using EntityType
+                switch (bodyItemEntity.EntityType)
+                {
+                    case EntityType.Paragraph:
+                        WParagraph paragraph = bodyItemEntity as WParagraph;
+                        //Processes the paragraph contents
+                        //Iterates through the paragraph's DOM
+                        IterateParagraph(paragraph.Items);
+                        break;
+                    case EntityType.Table:
+                        //Table is a collection of rows and cells
+                        //Iterates through table's DOM
+                        IterateTable(bodyItemEntity as WTable);
+                        break;
+                    case EntityType.BlockContentControl:
+                        BlockContentControl blockContentControl = bodyItemEntity as BlockContentControl;
+                        //Iterates to the body items of Block Content Control.
+                        IterateTextBody(blockContentControl.TextBody);
+                        break;
+                }
+            }
+        }
+        private static void IterateTable(WTable table)
+        {
+            //Iterates the row collection in a table
+            foreach (WTableRow row in table.Rows)
+            {
+                //Iterates the cell collection in a table row
+                foreach (WTableCell cell in row.Cells)
+                {
+                    //Table cell is derived from (also a) TextBody
+                    //Reusing the code meant for iterating TextBody
+                    IterateTextBody(cell);
+                }
+            }
+        }
+        private static void IterateParagraph(ParagraphItemCollection paraItems)
+        {
+            for (int i = 0; i < paraItems.Count; i++)
+            {
+                Entity entity = paraItems[i];
+                //A paragraph can have child elements such as text, image, hyperlink, symbols, etc.,
+                //Decides the element type by using EntityType
+                switch (entity.EntityType)
+                {
+                    case EntityType.TextRange:
+                        WTextRange textRange = entity as WTextRange;
+                        //Find and remove the long text in Word document.
+                        if (textRange.Text.Length >= requiredLongTextLength)
+                        {
+                            (entity as WTextRange).Text = string.Empty;
+                        }
+                        break;
+                    case EntityType.TextBox:
+                        //Iterates to the body items of textbox.
+                        WTextBox textBox = entity as WTextBox;
+                        IterateTextBody(textBox.TextBoxBody);
+                        break;
+                    case EntityType.Shape:
+                        //Iterates to the body items of shape.
+                        Shape shape = entity as Shape;
+                        IterateTextBody(shape.TextBody);
+                        break;
+                    case EntityType.InlineContentControl:
+                        //Iterates to the paragraph items of inline content control.
+                        InlineContentControl inlineContentControl = entity as InlineContentControl;
+                        IterateParagraph(inlineContentControl.ParagraphItems);
+                        break;
+                }
+            }
+        }
+    }
+}