Skip to content

Bug in NParallelTextCorpus #290

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 2 commits into from
Mar 7, 2025
Merged

Bug in NParallelTextCorpus #290

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
120ca7b
Bug in NParallelTextCorpus
Enkidu93 Mar 6, 2025
6234a00
Add unit test
Enkidu93 Mar 7, 2025
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
10 changes: 5 additions & 5 deletions src/SIL.Machine/Corpora/NParallelTextCorpus.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,9 +170,11 @@ NParallelTextRow row in CreateMinRefRows(
minRefIndexes.ToArray(),
nonMinRefIndexes.ToArray(),
sameRefRows,
forceInRange: minRefIndexes
forceInRange: Enumerable
.Range(0, N)
.Select(i =>
anyNonMinEnumeratorsMidRange
minRefIndexes.Contains(i)
&& anyNonMinEnumeratorsMidRange
&& nonMinRefIndexes.All(j =>
!completed[j] && currentRows[j].TextId == currentRows[i].TextId
) //All non-min rows have the same textId as the given min row
Expand Down Expand Up @@ -357,18 +359,16 @@ NParallelTextRow row in CreateRows(rangeInfo, textRows, forceInRange: forceInRan
}
}
textRows = new TextRow[N];
var forceCurrentInRange = new bool[N];
bool rowsHaveContent = false;
foreach (int i in minRefIndexes.Where(i => AllRows[i]).Except(alreadyYielded))
{
TextRow textRow = currentRows[i];
textRows[i] = textRow;
forceCurrentInRange[i] = forceCurrentInRange[i];
rowsHaveContent = true;
}
if (rowsHaveContent)
{
foreach (NParallelTextRow row in CreateRows(rangeInfo, textRows, forceCurrentInRange))
foreach (NParallelTextRow row in CreateRows(rangeInfo, textRows, forceInRange))
{
yield return row;
}
Expand Down
27 changes: 27 additions & 0 deletions tests/SIL.Machine.Tests/Corpora/NParallelTextCorpusTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,33 @@ public void GetRows_ThreeCorpora_SameRefManyToMany()
Assert.That(rows.Length, Is.EqualTo(10));
}

[Test]
public void GetRows_ThreeCorpora_SameRefCorporaOfDifferentSizes()
{
var corpus1 = new DictionaryTextCorpus(
new MemoryText("text1", new[] { TextRow("text1", 2, "source segment 2 .") })
);
var corpus2 = new DictionaryTextCorpus(
new MemoryText(
"text1",
new[]
{
TextRow("text1", 1, "source segment 1 ."),
TextRow("text1", 2, "source segment 2-1 ."),
TextRow("text1", 2, "source segment 2-2 ."),
TextRow("text1", 3, "source segment 3 . ")
}
)
);
var corpus3 = new DictionaryTextCorpus(
new MemoryText("text1", new[] { TextRow("text1", 1, "source segment 1 .") })
);
var nParallelCorpus = new NParallelTextCorpus([corpus1, corpus2, corpus3]) { AllRows = [true, true, true] };
NParallelTextRow[] rows = nParallelCorpus.ToArray();
Assert.That(rows.Length, Is.EqualTo(4), JsonSerializer.Serialize(rows));
Assert.That(rows[0].NRefs[1], Is.EquivalentTo(new object[] { 1 }));
}

private static TextRow TextRow(
string textId,
object rowRef,
Expand Down
Loading