ByteScout PDF Extractor SDK – C# – Load Unicode CSV to DataTable using OLEDB

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – Load Unicode CSV to DataTable using OLEDB

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-Load-Unicode-CSV-to-DataTable-using-OLEDB.pdf

How to load unicode CSV to datatable using OLEDB in C# with ByteScout PDF Extractor SDK

ByteScout PDF Extractor SDK is the SDK that helps developers to extract data from unstructured documents, pdf, images, scanned and electronic forms. Includes AI functions like automatic table detection, automatic table extraction and restructuring, text recognition and text restoration from pdf and scanned documents. Includes PDF to CSV, PDF to XML, PDF to JSON, PDF to searchable PDF functions as well as methods for low level data extraction.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

ConsoleApplication1.NETCore.csproj

      <?xml version="1.0" encoding="utf-8"?>
<Project Sdk="Microsoft.NET.Sdk">
  <PropertyGroup>
    <OutputType>Exe</OutputType>
    <TargetFramework>netcoreapp2.0</TargetFramework>
    <EnableDefaultCompileItems>false</EnableDefaultCompileItems>
    <GenerateAssemblyCompanyAttribute>false</GenerateAssemblyCompanyAttribute>
    <GenerateAssemblyConfigurationAttribute>false</GenerateAssemblyConfigurationAttribute>
    <GenerateAssemblyFileVersionAttribute>false</GenerateAssemblyFileVersionAttribute>
    <GenerateAssemblyInformationalVersionAttribute>false</GenerateAssemblyInformationalVersionAttribute>
    <GenerateAssemblyProductAttribute>false</GenerateAssemblyProductAttribute>
    <GenerateAssemblyTitleAttribute>false</GenerateAssemblyTitleAttribute>
    <GenerateAssemblyVersionAttribute>false</GenerateAssemblyVersionAttribute>
    <GenerateAssemblyCopyrightAttribute>false</GenerateAssemblyCopyrightAttribute>
    <GenerateAssemblyTrademarkAttribute>false</GenerateAssemblyTrademarkAttribute>
    <GenerateAssemblyCultureAttribute>false</GenerateAssemblyCultureAttribute>
    <GenerateAssemblyDescriptionAttribute>false</GenerateAssemblyDescriptionAttribute>
  </PropertyGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
    <None Include="..\..\UnicodeSample.pdf" Link="UnicodeSample.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <ItemGroup>
    <PackageReference Include="Microsoft.Windows.Compatibility" Version="2.0.0" />
  </ItemGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\Bytescout PDF Extractor SDK\netcoreapp2.0\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.PDFExtractor.OCRExtension">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\Bytescout PDF Extractor SDK\netcoreapp2.0\Bytescout.PDFExtractor.OCRExtension.dll</HintPath>
    </Reference>
  </ItemGroup>
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2005.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>8.0.50727</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildBinPath)\Microsoft.CSharp.targets" />
  <!-- To modify your build process, add your task inside one of the targets below and uncomment it. 
       Other similar extension points exist, see Microsoft.Common.targets.
  <Target Name="BeforeBuild">
  </Target>
  <Target Name="AfterBuild">
  </Target>
  -->
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2008.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="3.5">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>9.0.21022</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <OldToolsVersion>2.0</OldToolsVersion>
    <TargetFrameworkVersion>v3.5</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
  <!-- To modify your build process, add your task inside one of the targets below and uncomment it. 
       Other similar extension points exist, see Microsoft.Common.targets.
  <Target Name="BeforeBuild">
  </Target>
  <Target Name="AfterBuild">
  </Target>
  -->
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2010.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="4.0">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>
    </ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <OldToolsVersion>3.5</OldToolsVersion>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Debug|x86'">
    <DebugSymbols>true</DebugSymbols>
    <OutputPath>bin\x86\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <DebugType>full</DebugType>
    <PlatformTarget>x86</PlatformTarget>
    <ErrorReport>prompt</ErrorReport>
    <CodeAnalysisRuleSet>MinimumRecommendedRules.ruleset</CodeAnalysisRuleSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Release|x86'">
    <OutputPath>bin\x86\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <Optimize>true</Optimize>
    <DebugType>pdbonly</DebugType>
    <PlatformTarget>x86</PlatformTarget>
    <ErrorReport>prompt</ErrorReport>
    <CodeAnalysisRuleSet>MinimumRecommendedRules.ruleset</CodeAnalysisRuleSet>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
  <!-- To modify your build process, add your task inside one of the targets below and uncomment it. 
       Other similar extension points exist, see Microsoft.Common.targets.
  <Target Name="BeforeBuild">
  </Target>
  <Target Name="AfterBuild">
  </Target>
  -->
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.cs

      using Bytescout.PDFExtractor;
using System;
using System.Data;
using System.Data.OleDb;
using System.Globalization;
using System.IO;

namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            string inputDocument = Path.GetFullPath(@".\UnicodeSample.pdf");
            string csvFilePath = Path.ChangeExtension(inputDocument, ".csv");
            string csvFileName = Path.GetFileName(csvFilePath);
            string csvDirectory = Path.GetDirectoryName(Path.GetFullPath(csvFilePath));

            // Create Bytescout.PDFExtractor.CSVExtractor instance
            using (CSVExtractor extractor = new CSVExtractor("demo", "demo"))
            {
                extractor.LoadDocumentFromFile(inputDocument);

                extractor.CSVSeparatorSymbol = ",";

                string csvText = extractor.GetCSV();
            
                // Save csv text in UTF-8 encoding without BOM (byte order mark):
                File.WriteAllText(csvFilePath, csvText);
            }

            // Please Note: Target the project to x86 because Microsoft.Jet.OLEDB.4.0 driver is 32-bit only.
            using (OleDbConnection connection = new OleDbConnection($@"Provider=Microsoft.Jet.OLEDB.4.0;Data Source=""{csvDirectory}"";Extended Properties=""Text;FMT=$;HDR=No;CharacterSet=65001"""))
            {
                using (OleDbCommand command = new OleDbCommand({code}quot;select * from [{csvFileName}]", connection))
                {
                    using (OleDbDataAdapter adapter = new OleDbDataAdapter(command))
                    {
                        DataTable table = new DataTable();
                        table.Locale = CultureInfo.CurrentCulture;
                        adapter.Fill(table);

                        Console.WriteLine({code}quot;Loaded {table.Rows.Count} lines.");
                    }
                }
            }

            Console.ReadKey();
        }
    }
}