Skip to content

Fix crash when surrogate pair handling multibyte Unicode characters #361

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
Enkidu93 merged 1 commit into from
Dec 8, 2025
Merged

Fix crash when surrogate pair handling multibyte Unicode characters #361

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
12 changes: 6 additions & 6 deletions src/SIL.Machine/PunctuationAnalysis/TextSegment.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,13 +187,13 @@ public class SurrogatePairString
public SurrogatePairString(string stringValue)
{
_stringValue = stringValue;
IEnumerable<(int SurrogatePairIndex, int StringIndex)> indexPairs = _stringValue
.Select((c, i) => (c, i))
IEnumerable<(int StringIndex, int SurrogatePairIndex)> indexPairs = _stringValue
.Select((c, stringIndex) => (c, stringIndex))
.Where(tup => !char.IsLowSurrogate(tup.c))
.Select((tup, i) => (tup.i, i));
.Select((tup, surrogatePairIndex) => (tup.stringIndex, surrogatePairIndex));
_surrogatePairIndexByStringIndex = new Dictionary<int, int>();
_stringIndexBySurrogatePairIndex = new Dictionary<int, int>();
foreach ((int surrogatePairIndex, int stringIndex) in indexPairs)
foreach ((int stringIndex, int surrogatePairIndex) in indexPairs)
{
_surrogatePairIndexByStringIndex[stringIndex] = surrogatePairIndex;
_stringIndexBySurrogatePairIndex[surrogatePairIndex] = stringIndex;
Expand Down Expand Up @@ -251,11 +251,11 @@ public string Substring(int startSurrogatePairIndex, int length)

public int GetStringIndexForSurrogatePairIndex(int surrogatePairIndex)
{
if (surrogatePairIndex == _surrogatePairIndexByStringIndex.Count)
if (surrogatePairIndex == _stringIndexBySurrogatePairIndex.Count)
{
return _stringValue.Length;
}
return _surrogatePairIndexByStringIndex[surrogatePairIndex];
return _stringIndexBySurrogatePairIndex[surrogatePairIndex];
}
}
}
28 changes: 28 additions & 0 deletions tests/SIL.Machine.Tests/PunctuationAnalysis/QuotationMarkFinderTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,4 +441,32 @@ public void ThatItUsesTheQuoteConventionSet()
)
);
}

[Test]
public void SupportsMultibyteUnicodeCharacters()
{
var quotationMarkFinder = new QuotationMarkFinder(QuoteConventions.Standard);

// [grinning face], [left double quotation mark][grinning face with big eyes][right double quotation mark]
Assert.That(
quotationMarkFinder
.FindAllPotentialQuotationMarksInTextSegment(
new TextSegment.Builder().SetText("\U0001f600, \u201c\U0001f603\u201d").Build()
)
.SequenceEqual(
[
new QuotationMarkStringMatch(
new TextSegment.Builder().SetText("\U0001f600, \u201c\U0001f603\u201d").Build(),
3,
4
),
new QuotationMarkStringMatch(
new TextSegment.Builder().SetText("\U0001f600, \u201c\U0001f603\u201d").Build(),
5,
6
),
]
)
);
}
}
Loading