Skip to content

Improve parsing to correctly handle spaces #222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
onizet merged 1 commit into from
Jan 22, 2026
Merged

Improve parsing to correctly handle spaces #222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 12 additions & 11 deletions src/Html2OpenXml/Utilities/Converter.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,9 @@ static class Converter
{
Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"left" => JustificationValues.Left,
"left" => JustificationValues.Left,
"right" => JustificationValues.Right,
"center" => JustificationValues.Center,
"justify" => JustificationValues.Both,
Expand All @@ -43,7 +43,7 @@ static class Converter
{
Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"top" => TableVerticalAlignmentValues.Top,
"middle" => TableVerticalAlignmentValues.Center,
Expand All @@ -61,7 +61,7 @@ public static Unit ToFontSize(ReadOnlySpan<char> span)

Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
var unit = loweredValue switch
var unit = loweredValue.Trim() switch
{
"1" or "xx-small" => new Unit(UnitMetric.Point, 10),
"2" or "x-small" => new Unit(UnitMetric.Point, 15),
Expand Down Expand Up @@ -92,7 +92,7 @@ public static Unit ToFontSize(ReadOnlySpan<char> span)

Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"small-caps" => FontVariant.SmallCaps,
"normal" => FontVariant.Normal,
Expand All @@ -106,7 +106,7 @@ public static Unit ToFontSize(ReadOnlySpan<char> span)

Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"italic" or "oblique" => FontStyle.Italic,
"normal" => FontStyle.Normal,
Expand All @@ -120,7 +120,7 @@ public static Unit ToFontSize(ReadOnlySpan<char> span)

Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"700" or "bold" => FontWeight.Bold,
"bolder" => FontWeight.Bolder,
Expand All @@ -135,8 +135,9 @@ public static Unit ToFontSize(ReadOnlySpan<char> span)

// return the first font name
Span<Range> tokens = stackalloc Range[1];
return span.SplitCompositeAttribute(tokens, ',') switch {
1 => span.Slice(tokens[0]).ToString(),
return span.SplitCompositeAttribute(tokens, ',') switch
{
1 => span.Slice(tokens[0]).Trim().ToString(),
_ => null
};
}
Expand All @@ -148,7 +149,7 @@ public static BorderValues ToBorderStyle(ReadOnlySpan<char> span)

Span<char> loweredValue = span.Length <= 128 ? stackalloc char[span.Length] : new char[span.Length];
span.ToLowerInvariant(loweredValue);
return loweredValue switch
return loweredValue.Trim() switch
{
"dotted" => BorderValues.Dotted,
"dashed" => BorderValues.Dashed,
Expand Down Expand Up @@ -177,7 +178,7 @@ public static ICollection<TextDecoration> ToTextDecoration(ReadOnlySpan<char> va
var tokenCount = span.Split(tokens, ' ', StringSplitOptions.RemoveEmptyEntries);
for (int i = 0; i < tokenCount; i++)
{
switch (span.Slice(tokens[i]))
switch (span.Slice(tokens[i]).Trim())
{
case "underline": decorations.Add(TextDecoration.Underline); break;
case "line-through": decorations.Add(TextDecoration.LineThrough); break;
Expand Down
16 changes: 8 additions & 8 deletions test/HtmlToOpenXml.Tests/ElementTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,13 +37,13 @@ public void PhrasingTag_ReturnsRunWithDefaultStyle<T> (string html) where T : Op
public void MultipleStyle_ShouldBeAllApplied ()
{
var elements = converter.Parse(@"<b style=""
font-style:italic;
font-size:12px;
font-family:Verdana;
font-variant:small-caps;
color:white;
text-decoration:wavy line-through double;
background:red;
font-style: italic;
font-size: 12px;
font-family: Verdana;
font-variant: small-caps;
color: white;
text-decoration: wavy line-through double;
background: red;
"">bold with italic style</b>");
Assert.That(elements, Has.Count.EqualTo(1));

Expand All @@ -67,7 +67,7 @@ public void MultipleStyle_ShouldBeAllApplied ()
}
}

[TestCase("<span style='font-style:normal'><span style='font-style:italic'>Italic!</span></span>")]
[TestCase("<span style='font-style: normal'><span style='font-style: italic'>Italic!</span></span>")]
[TestCase("<div style='font-style:italic'><span style='font-style:normal'><span style='font-style:italic'>Italic!</span></span></div>")]
[TestCase("<div id='outer' style='font-style:italic'><div id='inner'>Italic</div></div>")]
public void NestedTagWithStyle_ShouldCascadeParentStyle (string html)
Expand Down