Find and show arabic text in C# and .NET
In today's world of multilingual applications and multilingual documents, it becomes necessary to work with text from various languages, including complex ones like Arabic, hieroglyphic languages, and languages with unique spelling. In this article, we'll look at how to implement searching and displaying Arabic text in C# and .NET using the SautinSoft Document .NET library, a reliable tool that reduces development time and improves accuracy.
The Arabic language has unique properties:
- Text flow is right-to-left.
- Display formats include differences in letter connections and distinctive calligraphy.
- You often need to search, extract, or edit Arabic text in documents or applications.
These features make working with Arabic text challenging without specialized tools.
Input file:
Intermediate files:
Output result:
Complete code
GitHubusing System;
using System.IO;
using System.Collections.Generic;
using SautinSoft.Document;
using System.Drawing;
using System.Drawing.Imaging;
using System.Linq;
using System.Text.RegularExpressions;
namespace Sample
{
class Sample
{
static void Main(string[] args)
{
// Get your free trial key here:
// https://sautinsoft.com/start-for-free/
string searchDir = Path.GetFullPath(@"..\..\..\searching\");
string searchText = "بسبب";
FullTextSearching(searchDir, searchText);
}
/// <summary>
/// This sample shows how to launch full text search in the specific directory for arabic words.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/full-text-searching-in-arabic-hebrew-right-to-left.php
/// </remarks>
public static void FullTextSearching(string searchPath, string searchText)
{
DirectoryInfo searchDir = new DirectoryInfo(searchPath);
List<string> supportedFiles = new List<string>();
// 1. Find theS files to make search.
// Specify to make the search only in *.docx
// including subdirectories.
foreach (string file in Directory.GetFiles(searchDir.FullName, "*.*", SearchOption.AllDirectories))
{
string ext = Path.GetExtension(file).ToLower();
if (ext == ".docx")
supportedFiles.Add(file);
}
// 2. Perform the text search in the each file using a loop.
// We'll search the word "بسبب" in the each and count how many times the file contains it.
Console.WriteLine($"The results for \"{searchText}\":");
int totalFiles = 0, totalMatches = 0;
foreach (string file in supportedFiles)
{
DocumentCore dc = DocumentCore.Load(file);
totalFiles++;
Regex regex = new Regex($"\\b({searchText})\\b", RegexOptions.IgnoreCase);
// Show also subfolder if we aren't in the root folder.
DirectoryInfo dirInfo = new DirectoryInfo(Path.GetDirectoryName(file));
string fileName = String.Empty;
if (dirInfo.FullName.TrimEnd(new char[] { '\\' }) != searchDir.FullName.TrimEnd(new char[] { '\\' }))
fileName = file.Substring(searchPath.Length, file.Length - searchPath.Length);
else
// We are in the root folder.
fileName = Path.GetFileName(file);
int matches = dc.Content.Find(regex).Count();
totalMatches += matches;
Console.WriteLine($"{totalFiles:D3} from {supportedFiles.Count} {fileName} - {matches} matches.");
}
Console.WriteLine($"\nSearching finished. {supportedFiles.Count} file(s) has been processed. Total matches: {totalMatches}.");
Console.WriteLine("Press any key ...");
Console.ReadKey();
}
}
}Imports Microsoft.VisualBasic
Imports System
Imports System.IO
Imports System.Collections.Generic
Imports SautinSoft.Document
Imports System.Drawing
Imports System.Drawing.Imaging
Imports System.Linq
Imports System.Text.RegularExpressions
Namespace Sample
Friend Class Sample
Shared Sub Main(ByVal args() As String)
' Get your free trial key here:
' https://sautinsoft.com/start-for-free/
Dim searchDir As String = Path.GetFullPath("..\..\..\searching\")
Dim searchText As String = "بسبب"
FullTextSearching(searchDir, searchText)
End Sub
''' <summary>
''' This sample shows how to launch full text search in the specific directory for arabic words.
''' </summary>
''' <remarks>
''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/full-text-searching-in-arabic-hebrew-right-to-left.php
''' </remarks>
Public Shared Sub FullTextSearching(ByVal searchPath As String, ByVal searchText As String)
Dim searchDir As New DirectoryInfo(searchPath)
Dim supportedFiles As New List(Of String)()
' 1. Find theS files to make search.
' Specify to make the search only in *.docx
' including subdirectories.
For Each file As String In Directory.GetFiles(searchDir.FullName, "*.*", SearchOption.AllDirectories)
Dim ext As String = Path.GetExtension(file).ToLower()
If ext = ".docx" Then
supportedFiles.Add(file)
End If
Next file
' 2. Perform the text search in the each file using a loop.
' We'll search the word "بسبب" in the each and count how many times the file contains it.
Console.WriteLine($"The results for ""{searchText}"":")
Dim totalFiles As Integer = 0, totalMatches As Integer = 0
For Each file As String In supportedFiles
Dim dc As DocumentCore = DocumentCore.Load(file)
totalFiles += 1
Dim regex As New Regex($"\b({searchText})\b", RegexOptions.IgnoreCase)
' Show also subfolder if we aren't in the root folder.
Dim dirInfo As New DirectoryInfo(Path.GetDirectoryName(file))
Dim fileName As String = String.Empty
If dirInfo.FullName.TrimEnd(New Char() { "\"c }) <> searchDir.FullName.TrimEnd(New Char() { "\"c }) Then
fileName = file.Substring(searchPath.Length, file.Length - searchPath.Length)
Else
' We are in the root folder.
fileName = Path.GetFileName(file)
End If
Dim matches As Integer = dc.Content.Find(regex).Count()
totalMatches += matches
Console.WriteLine($"{totalFiles:D3} from {supportedFiles.Count} {fileName} - {matches} matches.")
Next file
Console.WriteLine($"Searching finished. {supportedFiles.Count} file(s) has been processed. Total matches: {totalMatches}.")
Console.WriteLine("Press any key ...")
Console.ReadKey()
End Sub
End Class
End Namespace
If you need a new code example or have a question: email us at support@sautinsoft.com or ask at Online Chat (right-bottom corner of this page) or use the Form below: