Skip to content

Collapse nested character markup to single level (BL-16387) #8019

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

Open
StephenMcConnel wants to merge 3 commits into
base: master
Choose a base branch
from
+108 −2
Open

Collapse nested character markup to single level (BL-16387) #8019

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4ffb167
Collapse nested character markup to single level (BL-16387)
StephenMcConnel Jun 30, 2026
6da1954
Collapse nested markup with surrounding text; leave nested <sup> alon…
StephenMcConnel Jul 8, 2026
ae6ff79
Fix ticket number typo in comment: BL-16378 -> BL-16387
StephenMcConnel Jul 8, 2026
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
34 changes: 32 additions & 2 deletions src/BloomExe/Book/Book.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2628,7 +2628,13 @@ var chunk in text.InnerXml.Split(

/// <summary>
/// Convert old &lt;b&gt; and &lt;i&gt; to &lt;strong&gt; and &lt;em&gt; respectively.
/// Also remove instances like &lt;/b&gt;&lt;b&gt; altogether since such markup is redundant.
/// Remove instances like &lt;/b&gt;&lt;b&gt; altogether since such markup is redundant.
/// Cleanup instances like &lt;strong&gt;&lt;strong&gt;...&lt;/strong&gt;&lt;/strong&gt; to just &lt;strong&gt;...&lt;/strong&gt;.
/// Remove empty character markup like &lt;strong&gt;&lt;/strong&gt;, and seemingly empty markup that contains
/// only zero-width characters.
/// Doubled (nested) markup is handled only to one level, but that should be enough since Bloom can't
/// introduce such markup on its own. Handling general nested markup would require more than regular
/// expressions to handle properly.
/// </summary>
public static void UpdateCharacterStyleMarkup(HtmlDom bookDOM)
{
Expand Down Expand Up @@ -2667,19 +2673,43 @@ public static void UpdateCharacterStyleMarkup(HtmlDom bookDOM)
"<strong>$1</strong>",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
if (inner.IndexOf("<b>", StringComparison.OrdinalIgnoreCase) >= 0) // handle one level of nesting
inner = Regex.Replace(
inner,
@"<b>(.*?)</b>",
"<strong>$1</strong>",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
inner = Regex.Replace(
inner,
@"<i>(.*?)</i>",
"<em>$1</em>",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
if (inner.IndexOf("<i>", StringComparison.OrdinalIgnoreCase) >= 0) // handle one level of nesting
inner = Regex.Replace(
inner,
@"<i>(.*?)</i>",
"<em>$1</em>",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
// Replace doubled (nested) markup with single markup. This shouldn't happen, but it
// has been seen in the wild, possibly as a result of pasting text. (BL-16387)
// Only one level of nesting is handled, but that should (almost always) be enough.
inner = Regex.Replace(
inner,
@"<(strong|em|u)>([^<>]*)<\1>([^<>]*)</\1>([^<>]*)</\1>",
"<$1>$2$3$4</$1>",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
Comment thread
greptile-apps[bot] marked this conversation as resolved.
// Remove empty (or essentially empty) character markup tags. (BL-16387)
// strong em sup u, empty or zero-width characters in between are all considered empty.
// \u200B = zero-width space, \u200C = zero-width non-joiner, \u200D = zero-width joiner
inner = Regex.Replace(
inner,
@"<(strong|em|sup|u)>(\u200B|\u200C|\u200D)*</\1>",
""
"",
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase
);
if (inner != para.InnerXml)
para.InnerXml = inner;
Expand Down
76 changes: 76 additions & 0 deletions src/BloomTests/Book/BookTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3179,6 +3179,82 @@ public void UpdateCharacterStyleMarkup_LeavesPlainTextUnchanged()
);
}

[Test]
public void UpdateCharacterStyleMarkup_ReducesNestingOfSameTags()
{
var dom = new HtmlDom(
"<html><body><div class='bloom-editable'><p><b>some <b style='color:red'>text</b> here</b></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom);
Assert.That(
GetFirstEditableParagraph(dom).InnerXml,
Is.EqualTo("<strong>some text here</strong>")
);
var dom1 = new HtmlDom(
"<html><body><div class='bloom-editable'><p><i><i style='color:red'>text</i></i></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom1);
Assert.That(GetFirstEditableParagraph(dom1).InnerXml, Is.EqualTo("<em>text</em>"));
var dom2 = new HtmlDom(
"<html><body><div class='bloom-editable'><p><sup><sup style='color:red'>text</sup></sup></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom2);
// <sup> does have a nesting effect, so we don't collapse them. We just remove the attributes from the inner tag.
Assert.That(
GetFirstEditableParagraph(dom2).InnerXml,
Is.EqualTo("<sup><sup>text</sup></sup>")
);
var dom3 = new HtmlDom(
"<html><body><div class='bloom-editable'><p>This is <u><u style='color:red'>some text.</u></u></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom3);
Assert.That(
GetFirstEditableParagraph(dom3).InnerXml,
Is.EqualTo("This is <u>some text.</u>")
);
}
Comment thread
greptile-apps[bot] marked this conversation as resolved.

[Test]
public void UpdateCharacterStyleMarkup_HandlesMultipleTags()
{
var dom = new HtmlDom(
"<html><body><div class='bloom-editable'><p><b>text</b>, <b><i>more text</i></b> and <i><b>yet more.</b></i></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom);
Assert.That(
GetFirstEditableParagraph(dom).InnerXml,
Is.EqualTo(
"<strong>text</strong>, <strong><em>more text</em></strong> and <em><strong>yet more.</strong></em>"
)
);
var dom1 = new HtmlDom(
"<html><body><div class='bloom-editable'><p><i><i>text</i></i> with <i><i>more text</i></i></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom1);
Assert.That(
GetFirstEditableParagraph(dom1).InnerXml,
Is.EqualTo("<em>text</em> with <em>more text</em>")
);
var dom2 = new HtmlDom(
"<html><body><div class='bloom-editable'><p><sup>number</sup> of <sup style='color:red'>text</sup> with <sup>xyz</sup></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom2);
Assert.That(
GetFirstEditableParagraph(dom2).InnerXml,
Is.EqualTo("<sup>number</sup> of <sup>text</sup> with <sup>xyz</sup>")
);
var dom3 = new HtmlDom(
"<html><body><div class='bloom-editable'><p>This is <b><b>some text.</b></b> x <b>More stuff</b> of <b>sorts</b></p></div></body></html>"
);
Bloom.Book.Book.UpdateCharacterStyleMarkup(dom3);
Assert.That(
GetFirstEditableParagraph(dom3).InnerXml,
Is.EqualTo(
"This is <strong>some text.</strong> x <strong>More stuff</strong> of <strong>sorts</strong>"
)
);
}

[Test]
public void BringBookUpToDate_FixesDuplicateAudioIds_SentenceRecording()
{
Expand Down