Memory span

.github/workflows/publish_nuget.yml

@@ -0,0 +1,38 @@
+# This workflow will build, pack and deploy the solution on Nuget
+
+name: 'publish_nuget.yml'
+
+on:
+  push:
+    tags:
+      - '[0-9]+.[0-9]+'
+    branches:
+      - master
+
+jobs:
+  publish:
+    if: startsWith(github.ref, 'refs/tags/') && github.ref_type == 'tag' && github.ref_name != ''
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ensure tag is on master
+        run: |
+          TAG_COMMIT=$(git rev-list -n 1 ${{ github.ref_name }})
+          if ! git merge-base --is-ancestor $TAG_COMMIT origin/master; then
+            echo "Tag is not on master branch. Skipping publish."
+            exit 1
+          fi
+      - name: Setup .NET 8.
+        uses: actions/setup-dotnet@v4
+        with:
+          dotnet-version: '8.0.x'
+      - name: Build
+        run: dotnet build --configuration Release
+      - name: Pack
+        run: dotnet pack src/Html2OpenXml/HtmlToOpenXml.csproj --configuration Release --output ./nupkg
+      - name: Push nuget to NuGet.org
+        run: dotnet nuget push ./nupkg/*.nupkg --api-key $NUGET_API_KEY -s https://api.nuget.org/v3/index.json
+        env:
+          NUGET_API_KEY: ${{ secrets.NUGET_API_KEY }}
+      - name: Create Release and Upload Artifact to Release
+        run: gh release create ${{github.ref_name}} -t "Release ${{github.ref_name}}" *.nupkg --generate-notes --draft

.vscode/settings.json

@@ -1,9 +1,9 @@
 {
-    "omnisharp.organizeImportsOnFormat": true,
     "dotnet.completion.showCompletionItemsFromUnimportedNamespaces": false,
     "coverage-gutters.coverageFileNames":[
         "coverage.info"
     ],
     "coverage-gutters.showGutterCoverage": false,
-    "coverage-gutters.showLineCoverage": true
+    "coverage-gutters.showLineCoverage": true,
+    "dotnet.formatting.organizeImportsOnFormat": true
 }

CHANGELOG.md

@@ -1,5 +1,55 @@
 # Changelog
 
+## 3.3.0
+
+- Rewriting of parsing to use System.Span instead of Regex
+- Set Timeout on remaining Regex to prevent any DoS attack
+
+## 3.2.8
+
+- Fix a fatal crash when trying to convert multiple images #215
+- New feature to allow to reference external image instead of embedding them #216
+- Fix a potential issue on image streams that are disposed too early.
+- Support table col with percentage width #206
+
+## 3.2.7
+
+- Fix handling Uri with an anchor #209
+- New option DefaultStyles.NumberedHeadingStyle to support an alternate heading style #210
+
+## 3.2.6
+
+(wrong packaging, same code as 3.2.5)
+
+## 3.2.5
+
+- Fix a crash with the new whitespace handling introduced in 3.2.3 #191
+- Fix crash when the html contains 2 images with identical source path #193
+- Support margin auto for table alignment #194
+- Fix handling whitespace between runs #195
+- Whitelist more mime-types as specified by the IANA standard #196
+- Support EMF file #196
+- Correct handling of `figcaption` (allow nested phrasings) #197
+- Numbering list now supports type attribute `<ol type="1|a|A|i|I">` #198
+- Always restart nested numbering list #198
+- Fix table borders being removed even when the specified word table style has borders #199
+- Defensive code when download image stream is truncated #201
+- Table inside list is constrained to not exceed page margin #202
+- Table now supports width:auto for auto-fit content #202
+
+## 3.2.4
+
+- Fix a crash with the new whitespace handling introduced in 3.2.3 #191
+- Table inside list must be aligned with the list item #192
+
+## 3.2.3
+
+- Improve support of table alignment #187
+- Fix a crash if a span is empty
+- Heading with only digits should not be considered as a numbering #189
+- Fix whitespaces inserted between spans #179 and #185
+- Support percentage size (typically width:100%) for img node #188
+
 ## 3.2.2
 
 - Supports a feature to disable heading numbering #175

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

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>

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();
+        }
+    }
+}

examples/Benchmark/Program.cs

@@ -0,0 +1,3 @@
+using BenchmarkDotNet.Running;
+
+BenchmarkRunner.Run<Benchmarks>();

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`

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;
+    }
+}