Skip to content

Strict parsing #2 #92

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 9 commits into from
Sep 26, 2023
Merged

Strict parsing #2 #92

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
649df84
Receive buildOptions in NMT builds and pass on to machine.py
Enkidu93 Sep 14, 2023
2d25a42
Pass buildOptions to SMT --ECL
Enkidu93 Sep 14, 2023
01faccf
Add strict parsing option to SMT build jobs via buildOptions parameter
Enkidu93 Sep 25, 2023
bc3306b
Removed flag logic and added custom exception
Enkidu93 Sep 26, 2023
89ab470
Merge to remove previous changes
Enkidu93 Sep 26, 2023
0cb6f2f
Remove buildOptions-related changes
Enkidu93 Sep 26, 2023
95c4744
Removed mention of buildOptions from tests
Enkidu93 Sep 26, 2023
b41438d
Fix typo
Enkidu93 Sep 26, 2023
2b81130
Merge branch 'master' into strict_parsing_#2
Enkidu93 Sep 26, 2023
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
2 changes: 1 addition & 1 deletion src/SIL.Machine.AspNetCore/Services/ClearMLService.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ public async Task<string> CreateTaskAsync(
+ $" 'trg_lang': '{ConvertLanguageTag(targetLanguageTag)}',\n"
+ $" 'max_steps': {_options.CurrentValue.MaxSteps},\n"
+ $" 'shared_file_uri': '{sharedFileUri}',\n"
+ $" 'clearml': True\n"
+ $" 'clearml': True,\n"
+ "}\n"
+ "run(args)\n";

Expand Down
1 change: 0 additions & 1 deletion src/SIL.Machine.AspNetCore/Services/SmtTransferEngineBuildJob.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,6 @@ CancellationToken cancellationToken
)
{
IDistributedReaderWriterLock rwLock = await _lockFactory.CreateAsync(engineId, cancellationToken);

var tokenizer = new LatinWordTokenizer();
var detokenizer = new LatinWordDetokenizer();
ITrainer? smtModelTrainer = null;
Expand Down
12 changes: 12 additions & 0 deletions src/SIL.Machine/Corpora/CorpusAlignmentException.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
using System;

namespace SIL.Machine.Corpora
{
public class CorpusAlignmentException : Exception
{
public CorpusAlignmentException(string sourceRef, string targetRef)
: base(
$"Invalid format in {sourceRef} and {targetRef}. Mismatched key formats \"{sourceRef}\" and \"{targetRef}\". There may be an extraneous tab, missing ref, or inconsistent use of user-defined refs."
) { }
}
}
41 changes: 34 additions & 7 deletions src/SIL.Machine/Corpora/ParallelTextCorpus.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,18 @@ public IEnumerable<ParallelTextRow> GetRows()
bool trgCompleted = !trgEnumerator.MoveNext();
while (!srcCompleted && !trgCompleted)
{
int compare1 = RowRefComparer.Compare(srcEnumerator.Current.Ref, trgEnumerator.Current.Ref);
int compare1 = 0;
try
{
compare1 = RowRefComparer.Compare(srcEnumerator.Current.Ref, trgEnumerator.Current.Ref);
}
catch (ArgumentException)
{
throw new CorpusAlignmentException(
srcEnumerator.Current.Ref.ToString(),
trgEnumerator.Current.Ref.ToString()
);
}
if (compare1 < 0)
{
if (!AllTargetRows && srcEnumerator.Current.IsInRange)
Expand Down Expand Up @@ -176,9 +187,19 @@ ParallelTextRow row in CreateTargetRows(
int compare2;
do
{
compare2 = alignmentEnumerator.MoveNext()
? RowRefComparer.Compare(srcEnumerator.Current.Ref, alignmentEnumerator.Current.Ref)
: 1;
try
{
compare2 = alignmentEnumerator.MoveNext()
? RowRefComparer.Compare(srcEnumerator.Current.Ref, alignmentEnumerator.Current.Ref)
: 1;
}
catch (ArgumentException)
{
throw new CorpusAlignmentException(
srcEnumerator.Current.Ref.ToString(),
trgEnumerator.Current.Ref.ToString()
);
}
} while (compare2 < 0);

if (
Expand Down Expand Up @@ -378,9 +399,15 @@ private IEnumerable<ParallelTextRow> CreateRows(

private bool CheckSameRefRows(List<TextRow> sameRefRows, TextRow otherRow)
{
if (sameRefRows.Count > 0 && RowRefComparer.Compare(sameRefRows[0].Ref, otherRow.Ref) != 0)
sameRefRows.Clear();

try
{
if (sameRefRows.Count > 0 && RowRefComparer.Compare(sameRefRows[0].Ref, otherRow.Ref) != 0)
sameRefRows.Clear();
}
catch (ArgumentException)
{
throw new CorpusAlignmentException(sameRefRows[0].Ref.ToString(), otherRow.Ref.ToString());
}
return sameRefRows.Count > 0;
}

Expand Down