onizet · onizet · Sep 28, 2024 · Sep 28, 2024 · Sep 28, 2024 · Sep 30, 2024
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,10 @@
 # Changelog
 
+## 3.3.0
+
+- Rewriting of parsing to use System.Span instead of Regex
+- Set Timeout on remaining Regex to prevent any DoS attack
+=======
 ## 3.2.2
 
 - Supports a feature to disable heading numbering #175

diff --git a/HtmlToOpenXml.sln b/HtmlToOpenXml.sln
@@ -13,34 +13,42 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Demo", "examples\Demo\Demo.
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "HtmlToOpenXml.Tests", "test\HtmlToOpenXml.Tests\HtmlToOpenXml.Tests.csproj", "{CA0A68E0-45A0-4A01-A061-F951D93D6906}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Benchmark", "examples\Benchmark\Benchmark.csproj", "{143A3684-FAEB-43D0-A895-09BE5FDF85F6}"
+EndProject
 Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|Any CPU = Debug|Any CPU
-		Release|Any CPU = Release|Any CPU
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{EF700F30-C9BB-49A6-912C-E3B77857B514}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
-		{EF700F30-C9BB-49A6-912C-E3B77857B514}.Debug|Any CPU.Build.0 = Debug|Any CPU
-		{EF700F30-C9BB-49A6-912C-E3B77857B514}.Release|Any CPU.ActiveCfg = Release|Any CPU
-		{EF700F30-C9BB-49A6-912C-E3B77857B514}.Release|Any CPU.Build.0 = Release|Any CPU
-		{A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
-		{A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Debug|Any CPU.Build.0 = Debug|Any CPU
-		{A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Release|Any CPU.ActiveCfg = Release|Any CPU
-		{A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Release|Any CPU.Build.0 = Release|Any CPU
-		{CA0A68E0-45A0-4A01-A061-F951D93D6906}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
-		{CA0A68E0-45A0-4A01-A061-F951D93D6906}.Debug|Any CPU.Build.0 = Debug|Any CPU
-		{CA0A68E0-45A0-4A01-A061-F951D93D6906}.Release|Any CPU.ActiveCfg = Release|Any CPU
-		{CA0A68E0-45A0-4A01-A061-F951D93D6906}.Release|Any CPU.Build.0 = Release|Any CPU
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-	GlobalSection(NestedProjects) = preSolution
-		{EF700F30-C9BB-49A6-912C-E3B77857B514} = {58520A98-BA53-4BA4-AAE3-786AA21331D6}
-		{A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F} = {84EA02ED-2E97-47D2-992E-32CC104A3A7A}
-		{CA0A68E0-45A0-4A01-A061-F951D93D6906} = {84EA02ED-2E97-47D2-992E-32CC104A3A7A}
-	EndGlobalSection
-	GlobalSection(ExtensibilityGlobals) = postSolution
-		        SolutionGuid = {14EE1026-6507-4295-9FEE-67A55C3849CE}
-	EndGlobalSection
+    GlobalSection(SolutionConfigurationPlatforms) = preSolution
+        Debug|Any CPU = Debug|Any CPU
+        Release|Any CPU = Release|Any CPU
+    EndGlobalSection
+    GlobalSection(ProjectConfigurationPlatforms) = postSolution
+        {EF700F30-C9BB-49A6-912C-E3B77857B514}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+        {EF700F30-C9BB-49A6-912C-E3B77857B514}.Debug|Any CPU.Build.0 = Debug|Any CPU
+        {EF700F30-C9BB-49A6-912C-E3B77857B514}.Release|Any CPU.ActiveCfg = Release|Any CPU
+        {EF700F30-C9BB-49A6-912C-E3B77857B514}.Release|Any CPU.Build.0 = Release|Any CPU
+        {A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+        {A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Debug|Any CPU.Build.0 = Debug|Any CPU
+        {A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Release|Any CPU.ActiveCfg = Release|Any CPU
+        {A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F}.Release|Any CPU.Build.0 = Release|Any CPU
+        {CA0A68E0-45A0-4A01-A061-F951D93D6906}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+        {CA0A68E0-45A0-4A01-A061-F951D93D6906}.Debug|Any CPU.Build.0 = Debug|Any CPU
+        {CA0A68E0-45A0-4A01-A061-F951D93D6906}.Release|Any CPU.ActiveCfg = Release|Any CPU
+        {CA0A68E0-45A0-4A01-A061-F951D93D6906}.Release|Any CPU.Build.0 = Release|Any CPU
+        {143A3684-FAEB-43D0-A895-09BE5FDF85F6}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+        {143A3684-FAEB-43D0-A895-09BE5FDF85F6}.Debug|Any CPU.Build.0 = Debug|Any CPU
+        {143A3684-FAEB-43D0-A895-09BE5FDF85F6}.Release|Any CPU.ActiveCfg = Release|Any CPU
+        {143A3684-FAEB-43D0-A895-09BE5FDF85F6}.Release|Any CPU.Build.0 = Release|Any CPU
+    EndGlobalSection
+    GlobalSection(SolutionProperties) = preSolution
+        HideSolutionNode = FALSE
+    EndGlobalSection
+    GlobalSection(NestedProjects) = preSolution
+        {EF700F30-C9BB-49A6-912C-E3B77857B514} = {58520A98-BA53-4BA4-AAE3-786AA21331D6}
+        {A1ECC760-B9F7-4A00-AF5F-568B5FD6F09F} = {84EA02ED-2E97-47D2-992E-32CC104A3A7A}
+        {CA0A68E0-45A0-4A01-A061-F951D93D6906} = {84EA02ED-2E97-47D2-992E-32CC104A3A7A}
+        {143A3684-FAEB-43D0-A895-09BE5FDF85F6} = {84EA02ED-2E97-47D2-992E-32CC104A3A7A}
+    EndGlobalSection
+    GlobalSection(ExtensibilityGlobals) = postSolution
+        SolutionGuid = {14EE1026-6507-4295-9FEE-67A55C3849CE}
+        SolutionGuid = {194D4CBE-A20A-4E32-967B-E1BBD3922C29}
+    EndGlobalSection
 EndGlobal
diff --git a/examples/Benchmark/Benchmark.csproj b/examples/Benchmark/Benchmark.csproj
@@ -0,0 +1,21 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFrameworks>net48;net8.0</TargetFrameworks>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+    <SonarQubeExclude>true</SonarQubeExclude>
+    <LangVersion>latest</LangVersion>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="BenchmarkDotnet" Version="0.14.0" />
+    <ProjectReference Include="..\..\src\Html2OpenXml\HtmlToOpenXml.csproj" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <EmbeddedResource Include="*.html" />
+  </ItemGroup>
+
+</Project>
diff --git a/examples/Benchmark/Benchmarks.cs b/examples/Benchmark/Benchmarks.cs
@@ -0,0 +1,35 @@
+using BenchmarkDotNet.Attributes;
+using BenchmarkDotNet.Jobs;
+using DocumentFormat.OpenXml;
+using DocumentFormat.OpenXml.Packaging;
+using DocumentFormat.OpenXml.Wordprocessing;
+using HtmlToOpenXml;
+
+[MemoryDiagnoser]
+[SimpleJob(runtimeMoniker: RuntimeMoniker.Net48)]
+[SimpleJob(runtimeMoniker: RuntimeMoniker.Net80, baseline: true)]
+public class Benchmarks
+{
+    [Benchmark]
+    public async Task ParseWithSpan()
+    {
+        string html = ResourceHelper.GetString("benchmark.html");
+
+        using (MemoryStream generatedDocument = new MemoryStream())
+        using (WordprocessingDocument package = WordprocessingDocument.Create(generatedDocument, WordprocessingDocumentType.Document))
+        {
+            MainDocumentPart? mainPart = package.MainDocumentPart;
+            if (mainPart == null)
+            {
+                mainPart = package.AddMainDocumentPart();
+                new Document(new Body()).Save(mainPart);
+            }
+
+            HtmlConverter converter = new HtmlConverter(mainPart);
+            converter.RenderPreAsTable = true;
+
+            await converter.ParseBody(html);
+            mainPart.Document.Save();
+        }
+    }
+}
diff --git a/examples/Benchmark/Program.cs b/examples/Benchmark/Program.cs
@@ -0,0 +1,3 @@
+using BenchmarkDotNet.Running;
+
+BenchmarkRunner.Run<Benchmarks>();
diff --git a/examples/Benchmark/README.md b/examples/Benchmark/README.md
@@ -0,0 +1,7 @@
+# Benchmarks
+
+How to run the benchmark tool.
+First build the project: `dotnet build -c Release`
+
+Then run the performance test targeting multiple runtimes:
+`dotnet run -c Release -f net8.0 --runtimes net48 net8.0`
diff --git a/examples/Benchmark/ResourceHelper.cs b/examples/Benchmark/ResourceHelper.cs
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2017 Deal Stream sàrl. All rights reserved
+ */
+using System.IO;
+using System.Reflection;
+using System.Resources;
+
+/// <summary>
+/// Helper class to get an embedded resources.
+/// </summary>
+public static class ResourceHelper
+{
+    public static string GetString(string resourceName)
+    {
+        return GetString(typeof(ResourceHelper).GetTypeInfo().Assembly, resourceName);
+    }
+
+    public static string GetString(Assembly assembly, string resourceName)
+    {
+        using (var stream = GetStream(assembly, resourceName))
+        {
+            using (var reader = new StreamReader(stream))
+                return reader.ReadToEnd();
+        }
+    }
+
+    public static Stream GetStream(string resourceName)
+    {
+        return GetStream(typeof(ResourceHelper).GetTypeInfo().Assembly, resourceName);
+    }
+
+    public static Stream GetStream(Assembly assembly, string resourceName)
+    {
+        var stream = assembly.GetManifestResourceStream(assembly.GetName().Name + "." + resourceName);
+        if (stream == null)
+            throw new MissingManifestResourceException($"Requested resource `{resourceName}` was not found in the assembly `{assembly}`.");
+
+        return stream;
+    }
+}
diff --git a/examples/Benchmark/benchmark.html b/examples/Benchmark/benchmark.html
@@ -0,0 +1,124 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Sample HTML Page</title>
+</head>
+<body>
+
+<!-- Header Section -->
+<h1 style="color: blue; text-align: center;">Welcome to My Sample Page</h1>
+
+<!-- Paragraph with styling -->
+<p style="font-family: Arial, 'Times New Roman', sans-serif; font-size: 14px; color: grey;">
+    This is a sample paragraph. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+</p>
+
+<!-- Link with styling -->
+<a href="https://www.example.com" style="text-decoration: none; color: green;">Visit Example</a>
+
+<!-- Image with styling -->
+<img src="https://via.placeholder.com/150" alt="Placeholder Image" style="border: 2px solid black;">
+
+<!-- List with styling -->
+<ul style="list-style-type: square;">
+    <li style="color: red;">Item 1</li>
+    <li style="color: orange;">Item 2</li>
+    <li style="color: yellow;">Item 3</li>
+</ul>
+
+<!-- Table with styling -->
+<table style="width: 100%; border-collapse: collapse;">
+    <tr style="background-color: #f2f2f2;">
+        <th style="border: 1px solid black;">Header 1</th>
+        <th style="border: 1px solid black;">Header 2</th>
+    </tr>
+    <tr>
+        <td style="border: 1px solid black;">Cell 1</td>
+        <td style="border: 1px solid black;">Cell 2</td>
+    </tr>
+    <tr style="background-color: #f2f2f2;">
+        <td style="border: 1px solid black;">Cell 3</td>
+        <td style="border: 1px solid black;">Cell 4</td>
+    </tr>
+</table>
+
+<!-- Form with styling -->
+<form style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ccc;">
+    <label for="name" style="font-weight: bold;">Name:</label>
+    <input type="text" id="name" name="name" style="width: 100%; padding: 10px; margin-top: 5px;">
+
+    <label for="email" style="font-weight: bold; margin-top: 10px; display: block;">Email:</label>
+    <input type="email" id="email" name="email" style="width: 100%; padding: 10px; margin-top: 5px;">
+
+    <button type="submit" style="background-color: blue; color: white; padding: 10px 20px; margin-top: 10px;">Submit</button>
+</form>
+
+<!-- Additional Content to Reach 300 Lines -->
+
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus magna felis sollicitudin mauris.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Integer in mauris eu nibh euismod gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue, eros est euismod turpis, id tincidunt sapien risus a quam.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Maecenas fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis, neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing sapien, sed malesuada diam lacus eget erat.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Cras mollis scelerisque nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis, molestie eu, feugiat in, orci. In hac habitasse platea dictumst.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Fusce convallis, mauris imperdiet gravida bibendum, nisl turpis suscipit mauris, sed placerat ipsum ligula sed magna. Maecenas nisl est, ultrices nec, congue eget, auctor vitae, massa.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Fusce luctus vestibulum augue ut aliquet. Nunc sagittis dictum nisi. Sed id blandit purus. Proin quis orci. Quisque convallis libero in sapien pharetra tincidunt.
+</p>
+
+<!-- Additional lines of paragraph to reach 300 lines -->
+
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus magna felis sollicitudin mauris.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Integer in mauris eu nibh euismod gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue, eros est euismod turpis, id tincidunt sapien risus a quam.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Maecenas fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis, neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing sapien, sed malesuada diam lacus eget erat.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Cras mollis scelerisque nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis, molestie eu, feugiat in, orci. In hac habitasse platea dictumst.
+</p>
+<p style="font-family: Arial, sans-serif; font-size: 14px; color: grey;">
+    Fusce convallis, mauris imperdiet gravida bibendum, nisl turpis suscipit mauris, sed placerat ipsum ligula sed magna. Maecenas nisl est, ultrices nec, congue eget, auctor vitae, massa.
+</p>
+<p style="font-family: Arial, 'Times New Roman', sans-serif; font-size: 14px; color: grey;">
+    Fusce luctus vestibulum augue ut aliquet. Nunc sagittis dictum nisi. Sed id blandit purus. Proin quis orci. Quisque convallis libero in sapien pharetra tincidunt.
+</p>
+
+</body>
+</html>
diff --git a/examples/Demo/Demo.csproj b/examples/Demo/Demo.csproj
@@ -3,6 +3,7 @@
   <PropertyGroup>
     <TargetFramework>net8.0</TargetFramework>
     <OutputType>Exe</OutputType>
+    <SonarQubeExclude>true</SonarQubeExclude>
   </PropertyGroup>
 
   <ItemGroup>

diff --git a/examples/Demo/Program.cs b/examples/Demo/Program.cs
@@ -24,7 +24,7 @@ static async Task Main(string[] args)
                 // instead of creating it from scratch.
                 using (var buffer = ResourceHelper.GetStream("Resources.template.docx"))
                 {
-                    buffer.CopyTo(generatedDocument);
+                    await buffer.CopyToAsync(generatedDocument);
                 }
 
                 generatedDocument.Position = 0L;
@@ -47,7 +47,7 @@ static async Task Main(string[] args)
                     AssertThatOpenXmlDocumentIsValid(package);
                 }
 
-                File.WriteAllBytes(filename, generatedDocument.ToArray());
+                await File.WriteAllBytesAsync(filename, generatedDocument.ToArray());
             }
 
             Process.Start(new ProcessStartInfo(filename) { UseShellExecute = true });
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		using BenchmarkDotNet.Running;

		BenchmarkRunner.Run<Benchmarks>();