Skip to content

Fix faulty edge-case logic in NParallelTextCorpus #295

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
johnml1135 merged 1 commit into from
Mar 17, 2025
Merged

Fix faulty edge-case logic in NParallelTextCorpus #295

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
6 changes: 3 additions & 3 deletions src/SIL.Machine/Corpora/NParallelTextCorpus.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,9 +71,9 @@ public override IEnumerable<NParallelTextRow> GetRows(IEnumerable<string> textId
}
}

private static bool AllInRangeHaveSegments(IList<TextRow> rows)
private static bool AllRangesAreNewRanges(IList<TextRow> rows)
{
return rows.All(r => (r.IsInRange && !r.IsEmpty) || (!r.IsInRange));
return rows.All(r => r.IsRangeStart || !r.IsInRange);
}

private IList<int> MinRefIndexes(IList<object> refs)
Expand Down Expand Up @@ -211,7 +211,7 @@ NParallelTextRow row in CreateMinRefRows(
{
if (
rangeInfo.IsInRange
&& AllInRangeHaveSegments(currentRows.Where((r, i) => !completed[i]).ToArray())
&& AllRangesAreNewRanges(currentRows.Where((r, i) => !completed[i]).ToArray())
)
{
yield return rangeInfo.CreateRow();
Expand Down
55 changes: 55 additions & 0 deletions tests/SIL.Machine.Tests/Corpora/ParallelTextCorpusTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -599,6 +599,61 @@ public void GetRows_AdjacentRangesDifferentTexts()
Assert.That(rows[1].TargetSegment, Is.EqualTo("target segment 3 . target segment 4 .".Split()));
}

[Test]
public void GetRows_AdjacentRangesBothTexts_EmptyTargetSegments()
{
var sourceCorpus = new DictionaryTextCorpus(
new MemoryText(
"text1",
new[]
{
TextRow(
"text1",
1,
"source segment 1 . source segment 2 .",
TextRowFlags.InRange | TextRowFlags.RangeStart
),
TextRow("text1", 2, flags: TextRowFlags.InRange),
TextRow(
"text1",
3,
"source segment 3 . source segment 4 .",
TextRowFlags.InRange | TextRowFlags.RangeStart
),
TextRow("text1", 4, flags: TextRowFlags.InRange)
}
)
);
var targetCorpus = new DictionaryTextCorpus(
new MemoryText(
"text1",
new[]
{
TextRow("text1", 1, flags: TextRowFlags.InRange | TextRowFlags.RangeStart),
TextRow("text1", 2, flags: TextRowFlags.InRange),
TextRow("text1", 3, flags: TextRowFlags.InRange | TextRowFlags.RangeStart),
TextRow("text1", 4, flags: TextRowFlags.InRange)
}
)
);

var parallelCorpus = new ParallelTextCorpus(sourceCorpus, targetCorpus)
{
AllSourceRows = true,
AllTargetRows = false
};
ParallelTextRow[] rows = parallelCorpus.ToArray();
Assert.That(rows.Length, Is.EqualTo(2));
Assert.That(rows[0].SourceRefs, Is.EqualTo(new[] { 1, 2 }));
Assert.That(rows[0].TargetRefs, Is.EqualTo(new[] { 1, 2 }));
Assert.That(rows[0].SourceSegment, Is.EqualTo("source segment 1 . source segment 2 .".Split()));
Assert.That(rows[0].TargetSegment, Is.Empty);
Assert.That(rows[1].SourceRefs, Is.EqualTo(new[] { 3, 4 }));
Assert.That(rows[1].TargetRefs, Is.EqualTo(new[] { 3, 4 }));
Assert.That(rows[1].SourceSegment, Is.EqualTo("source segment 3 . source segment 4 .".Split()));
Assert.That(rows[1].TargetSegment, Is.Empty);
}

[Test]
public void GetRows_AllSourceRows()
{
Expand Down
Loading