public void verify_get_next_job_set_identity()
{
var info = new QueueInfo("test", "", "pdf|docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Id = 1L,
Handle = "FirstHandle",
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice"),
DocumentFormat = new DocumentFormat("office"),
BlobId = new BlobId("soffice.1")
},
DocumentDescriptorId = new DocumentDescriptorId(1),
};
sut.Handle(rm, new TenantId("test"));
rm.Handle = "SecondHandle";
rm.Id = 2L;
//This is typical situation when handle is de-duplicated, because
//and handle is assigned to another document, but the underling blob id is the same.
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
//no need to schedule another job
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
}
public void verify_job_created_with_handle_metadata()
{
var info = new QueueInfo("test", "", "pdf|docx");
QueueHandler sut = new QueueHandler(info, _db);
var customData = new DocumentCustomData()
{
{ "test", "value" },
{ "complex", 42 },
};
StreamReadModel rm = new StreamReadModel()
{
Id = 1L,
Handle = "FirstHandle",
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice"),
DocumentFormat = new DocumentFormat("office"),
BlobId = new BlobId("soffice.1")
},
DocumentDescriptorId = new DocumentDescriptorId(1),
DocumentCustomData = customData,
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Single().HandleCustomData, Is.EquivalentTo(customData));
}
internal bool ShouldCreateJob(StreamReadModel streamElement)
{
//if extensions or mime type are present we need to check belonging in one of them
if (_splittedExtensions.Length > 0 || _splittedMimeTypes.Length > 0)
{
if (!_splittedExtensions.Contains(streamElement.Filename.Extension) && !_splittedMimeTypes.Contains(Core.MimeTypes.GetMimeType(streamElement.Filename)))
{
return(false);
}
}
if (_splittedFormats.Length > 0 && !_splittedFormats.Contains(streamElement.FormatInfo.DocumentFormat.ToString()))
{
return(false);
}
if (!String.IsNullOrEmpty(Pipeline) &&
streamElement.FormatInfo.PipelineId != null &&
!Regex.IsMatch(streamElement.FormatInfo.PipelineId, Pipeline))
{
return(false);
}
//Return only if at least one condition is met.
return(_splittedExtensions.Length > 0 ||
_splittedFormats.Length > 0 ||
_splittedMimeTypes.Length > 0 ||
!String.IsNullOrEmpty(Pipeline));
}
public void verify_pipeline_id_filter()
{
var info = new QueueInfo("test", "tika", "");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice")
}
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0), "pipeline filter is not filtering out unwanted pipeline");
rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("tika"),
DocumentFormat = new DocumentFormat("tika"),
BlobId = new BlobId("tika.1")
}
};
sut.Handle(rm, new TenantId("test"));
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1), "pipeline filter is not filtering in admitted pipeline");
}
public void verify_id_is_opaque_and_not_contains_blob_id()
{
var info = new QueueInfo("test", "", "docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail"),
},
DocumentDescriptorId = new DocumentDescriptorId(1),
Handle = new DocumentHandle("Revision_2"),
};
sut.Handle(rm, new TenantId("test_tenant"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
var job = collection.AsQueryable().Single();
Assert.That(job.BlobId, Is.EqualTo(new BlobId("blob.1")));
Assert.That(job.TenantId, Is.EqualTo(new TenantId("test_tenant")));
Assert.That(job.DocumentDescriptorId, Is.EqualTo(new DocumentDescriptorId(1)));
Assert.That(job.Handle.ToString(), Is.EqualTo(rm.Handle));
Assert.That(job.Id.ToString(), Is.Not.Contains("blob.1"), "Id should not contains internal concempts like blob id");
Assert.That(job.Id.ToString(), Is.Not.Contains("tenant"), "Id should not contains internal concempts like tenant id");
Assert.That(job.Parameters.Keys, Is.Not.Contains(JobKeys.BlobId));
Assert.That(job.Parameters.Keys, Is.Not.Contains(JobKeys.DocumentId));
}
public void verify_job_parameters_contains_mime_type()
{
var info = new QueueInfo("test", "", "docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail"),
},
DocumentDescriptorId = new DocumentDescriptorId(1),
};
sut.Handle(rm, new TenantId("test_tenant"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
var job = collection.AsQueryable().Single();
Assert.That(job.BlobId, Is.EqualTo(new BlobId("blob.1")));
Assert.That(job.Parameters[JobKeys.MimeType], Is.EqualTo(MimeTypes.GetMimeTypeByExtension("docx")));
}
public void verify_id_is_opaque_and_not_contains_blob_id()
{
var info = new QueueInfo("test", "", "docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail"),
},
DocumentDescriptorId = new DocumentDescriptorId(1),
Handle = new DocumentHandle("Revision_2"),
};
sut.Handle(rm, new TenantId("test_tenant"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
var job = collection.AsQueryable().Single();
Assert.That(job.BlobId, Is.EqualTo(new BlobId("blob.1")));
Assert.That(job.TenantId, Is.EqualTo(new TenantId("test_tenant")));
Assert.That(job.DocumentDescriptorId, Is.EqualTo(new DocumentDescriptorId(1)));
Assert.That(job.Handle.ToString(), Is.EqualTo(rm.Handle));
Assert.That(job.Id.ToString(), Is.Not.Contains("blob.1"), "Id should not contains internal concempts like blob id");
Assert.That(job.Id.ToString(), Is.Not.Contains("tenant"), "Id should not contains internal concempts like tenant id");
Assert.That(job.Parameters.Keys, Is.Not.Contains(JobKeys.BlobId));
Assert.That(job.Parameters.Keys, Is.Not.Contains(JobKeys.DocumentId));
}
public void verify_should_create_job_mime_extension(String mimetypes, String extensions, String fileName, Boolean expected)
{
QueueInfo sut = new QueueInfo("TEST", extensions : extensions, mimeTypes: mimetypes);
StreamReadModel sr = new StreamReadModel();
sr.Filename = new Core.Model.FileNameWithExtension(fileName);
Assert.That(sut.ShouldCreateJob(sr), Is.EqualTo(expected));
}
public void verify_filtering_on_mime_types()
{
var mimeTypeDocx = MimeTypes.GetMimeTypeByExtension("docx");
var info = new QueueInfo("test", mimeTypes: mimeTypeDocx);
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.pdf"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail")
}
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0));
rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail")
}
};
sut.Handle(rm, new TenantId("test"));
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
}
public void Verify_should_create_job_mime_extension(String mimetypes, String extensions, String fileName, Boolean expected)
{
QueueInfo sut = new QueueInfo("TEST", extensions: extensions, mimeTypes: mimetypes);
StreamReadModel sr = new StreamReadModel();
sr.Filename = new Core.Model.FileNameWithExtension(fileName);
Assert.That(sut.ShouldCreateJob(sr), Is.EqualTo(expected));
}
public void verify_file_extension_on_handler_filter_exact_extension()
{
var info = new QueueInfo("test", "", "pdf|doc");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx")
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0));
}
public void queue_with_only_manual_execution(
String mimetypes,
String extensions,
String pipeline,
String fileName)
{
QueueInfo sut = new QueueInfo("TEST",
extensions: extensions,
mimeTypes: mimetypes,
pipeline : pipeline);
StreamReadModel sr = new StreamReadModel();
sr.Filename = new Core.Model.FileNameWithExtension(fileName);
Assert.That(sut.ShouldCreateJob(sr), Is.EqualTo(false));
}
public void verify_file_extension_on_handler_filter_exact_extension()
{
var info = new QueueInfo("test", "", "pdf|doc");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx")
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0));
}
public void Queue_with_only_manual_execution(
String mimetypes,
String extensions,
String pipeline,
String fileName)
{
QueueInfo sut = new QueueInfo("TEST",
extensions: extensions,
mimeTypes: mimetypes,
pipeline: pipeline);
StreamReadModel sr = new StreamReadModel();
sr.Filename = new Core.Model.FileNameWithExtension(fileName);
Assert.That(sut.ShouldCreateJob(sr), Is.EqualTo(false));
}
/// <summary>
/// Handle a <see cref="StreamReadModel" /> and generates job for the queue
/// if needed.
/// </summary>
/// <param name="streamElement"></param>
/// <param name="tenantId"></param>
/// <param name="forceReSchedule"></param>
public void Handle(
StreamReadModel streamElement,
TenantId tenantId,
Boolean forceReSchedule = false)
{
if (_info.ShouldCreateJob(streamElement))
{
if (!forceReSchedule)
{
//look for already existing job with the same blobid, there is no need to re-queue again
//because if a job with the same blobid was already fired for this queue there is no need
//to re-issue
var existing = _collection.Find(
Builders< QueuedJob>.Filter.And(
Builders< QueuedJob>.Filter.Eq(j => j.BlobId, streamElement.FormatInfo.BlobId),
Builders<QueuedJob>.Filter.Eq(j => j.TenantId, tenantId)
)
).Count() > 0;
if (existing) return;
}
if (Logger.IsDebugEnabled) Logger.DebugFormat("Create queue for readmodel stream id {0} and queue {1}", streamElement.Id, _info.Name);
QueuedJob job = new QueuedJob();
var id = new QueuedJobId(Guid.NewGuid().ToString());
job.Id = id;
job.SchedulingTimestamp = DateTime.Now;
job.StreamId = streamElement.Id;
job.TenantId = tenantId;
job.DocumentDescriptorId = streamElement.DocumentDescriptorId;
job.BlobId = streamElement.FormatInfo.BlobId;
job.Handle = new DocumentHandle( streamElement.Handle);
job.Parameters = new Dictionary<string, string>();
job.Parameters.Add(JobKeys.FileExtension, streamElement.Filename.Extension);
job.Parameters.Add(JobKeys.Format, streamElement.FormatInfo.DocumentFormat);
job.Parameters.Add(JobKeys.FileName, streamElement.Filename);
job.Parameters.Add(JobKeys.TenantId, tenantId);
job.Parameters.Add(JobKeys.MimeType, MimeTypes.GetMimeType(streamElement.Filename));
job.HandleCustomData = streamElement.DocumentCustomData;
if (_info.Parameters != null)
{
foreach (var parameter in _info.Parameters)
{
job.Parameters.Add(parameter.Key, parameter.Value);
}
}
_collection.InsertOne(job);
}
}
public FeedForStreamReadModel(StreamReadModel original)
{
Id = original.Id;
Handle = original.Handle;
EventType = original.EventType;
EventTypeDesc = original.EventType.ToString();
if (original.FormatInfo != null)
{
DocumentFormat = original.FormatInfo.DocumentFormat;
}
if (original.Filename != null)
{
FileName = original.Filename;
MimeType = MimeTypes.GetMimeType(original.Filename);
}
}
public FeedForStreamReadModel(StreamReadModel original)
{
Id = original.Id;
Handle = original.Handle;
EventType = original.EventType;
EventTypeDesc = original.EventType.ToString();
if (original.FormatInfo != null)
{
DocumentFormat = original.FormatInfo.DocumentFormat;
}
if (original.Filename != null)
{
FileName = original.Filename;
MimeType = MimeTypes.GetMimeType(original.Filename);
}
}
private static void HandleStreamToCreateJob(
QueueHandler sut,
String tenant = "test",
Dictionary <String, Object> customData = null)
{
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("tika"),
DocumentFormat = new DocumentFormat("tika"),
BlobId = new BlobId("tika." + lastBlobId++)
},
DocumentCustomData = new DocumentCustomData(customData ?? new Dictionary <String, Object>()),
};
sut.Handle(rm, new TenantId(tenant));
}
public void On(DocumentDescriptorHasNewAttachment e)
{
var attachmentDescriptor = _documentDescriptorReadModel.AllUnsorted.SingleOrDefault(d => d.Documents.Contains(e.Attachment));
if (attachmentDescriptor == null)
{
return;
}
var streamReadModel = new StreamReadModel()
{
Id = GetNewId(),
Handle = e.Attachment,
DocumentDescriptorId = attachmentDescriptor.Id,
EventType = HandleStreamEventTypes.DocumentHasNewAttachment,
};
streamReadModel.AddEventData(StreamReadModelEventDataKeys.ChildHandle, e.Attachment);
_streamReadModelCollection.Insert(e, streamReadModel);
}
public void Verify_file_extension_permitted()
{
var info = new QueueInfo("test", "", "pdf|docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice"),
DocumentFormat = new DocumentFormat("office"),
BlobId = new BlobId("soffice.1")
}
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection <QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
}
public void verify_job_parameters_contains_mime_type()
{
var info = new QueueInfo("test", "", "docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail"),
},
DocumentDescriptorId = new DocumentDescriptorId(1),
};
sut.Handle(rm, new TenantId("test_tenant"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
var job = collection.AsQueryable().Single();
Assert.That(job.BlobId, Is.EqualTo(new BlobId("blob.1")));
Assert.That(job.Parameters[JobKeys.MimeType], Is.EqualTo(MimeTypes.GetMimeTypeByExtension("docx")));
}
internal bool ShouldCreateJob(StreamReadModel streamElement)
{
//if extensions or mime type are present we need to check belonging in one of them
if (_splittedExtensions.Length > 0 || _splittedMimeTypes.Length > 0)
{
if (!_splittedExtensions.Contains(streamElement.Filename.Extension) && !_splittedMimeTypes.Contains(Core.MimeTypes.GetMimeType(streamElement.Filename)))
{
return false;
}
}
if (_splittedFormats.Length > 0 && !_splittedFormats.Contains(streamElement.FormatInfo.DocumentFormat.ToString()))
return false;
if (!String.IsNullOrEmpty(Pipeline) &&
streamElement.FormatInfo.PipelineId != null &&
!Regex.IsMatch(streamElement.FormatInfo.PipelineId, Pipeline))
return false;
//Return only if at least one condition is met.
return _splittedExtensions.Length > 0 ||
_splittedFormats.Length > 0 ||
_splittedMimeTypes.Length > 0 ||
!String.IsNullOrEmpty(Pipeline);
}
/// <summary>
/// Handle a <see cref="StreamReadModel" /> and generates job for the queue
/// if needed.
/// </summary>
/// <param name="streamElement"></param>
/// <param name="tenantId"></param>
/// <param name="forceReSchedule"></param>
public QueuedJobId Handle(
StreamReadModel streamElement,
TenantId tenantId,
Boolean forceReSchedule = false)
{
if (_info.ShouldCreateJob(streamElement))
{
if (!forceReSchedule)
{
//look for already existing job with the same blobid, there is no need to re-queue again
//because if a job with the same blobid was already fired for this queue there is no need
//to re-issue
var existing = _collection.Find(
Builders <QueuedJob> .Filter.And(
Builders <QueuedJob> .Filter.Eq(j => j.BlobId, streamElement.FormatInfo.BlobId),
Builders <QueuedJob> .Filter.Eq(j => j.TenantId, tenantId)
)
).Count() > 0;
if (existing)
{
return(null);
}
}
if (Logger.IsInfoEnabled)
{
Logger.Info($"Queue {_info.Name} CREATE JOB to process {streamElement.Describe()}");
}
QueuedJob job = new QueuedJob();
job.Id = new QueuedJobId(Guid.NewGuid().ToString());
job.SchedulingTimestamp = DateTime.Now;
job.StreamId = streamElement.Id;
job.TenantId = tenantId;
job.DocumentDescriptorId = streamElement.DocumentDescriptorId;
job.BlobId = streamElement.FormatInfo.BlobId;
job.Handle = new DocumentHandle(streamElement.Handle);
job.Parameters = new Dictionary <string, string>();
job.Parameters.Add(JobKeys.FileExtension, streamElement.Filename.Extension);
job.Parameters.Add(JobKeys.Format, streamElement.FormatInfo.DocumentFormat);
job.Parameters.Add(JobKeys.FileName, streamElement.Filename);
job.Parameters.Add(JobKeys.TenantId, tenantId);
job.Parameters.Add(JobKeys.MimeType, MimeTypes.GetMimeType(streamElement.Filename));
job.Parameters.Add(JobKeys.PipelineId, streamElement.FormatInfo?.PipelineId?.ToString());
if (forceReSchedule)
{
job.Parameters.Add(JobKeys.Force, "true");
}
job.HandleCustomData = streamElement.DocumentCustomData;
if (_info.Parameters != null)
{
foreach (var parameter in _info.Parameters)
{
job.Parameters.Add(parameter.Key, parameter.Value);
}
}
_collection.InsertOne(job);
return(job.Id);
}
else
{
if (Logger.IsDebugEnabled)
{
Logger.Debug($"Queue {_info.Name} do not need to process {streamElement.Describe()}");
}
}
return(null);
}
private static void HandleStreamToCreateJob(
QueueHandler sut,
String tenant = "test",
Dictionary<String, Object> customData = null)
{
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("tika"),
DocumentFormat = new DocumentFormat("tika"),
BlobId = new BlobId("tika." + lastBlobId++)
},
DocumentCustomData = new DocumentCustomData(customData ?? new Dictionary<String,Object>()),
};
sut.Handle(rm, new TenantId(tenant));
}
public void verify_job_created_with_handle_metadata()
{
var info = new QueueInfo("test", "", "pdf|docx");
QueueHandler sut = new QueueHandler(info, _db);
var customData = new DocumentCustomData()
{
{"test" , "value"},
{"complex" , 42},
};
StreamReadModel rm = new StreamReadModel()
{
Id = 1L,
Handle = "FirstHandle",
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice"),
DocumentFormat = new DocumentFormat("office"),
BlobId = new BlobId("soffice.1")
},
DocumentDescriptorId = new DocumentDescriptorId(1),
DocumentCustomData = customData,
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Single().HandleCustomData, Is.EquivalentTo(customData));
}
public void verify_get_next_job_set_identity()
{
var info = new QueueInfo("test", "", "pdf|docx");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Id = 1L,
Handle = "FirstHandle",
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice"),
DocumentFormat = new DocumentFormat("office"),
BlobId = new BlobId("soffice.1")
},
DocumentDescriptorId = new DocumentDescriptorId(1),
};
sut.Handle(rm, new TenantId("test"));
rm.Handle = "SecondHandle";
rm.Id = 2L;
//This is typical situation when handle is de-duplicated, because
//and handle is assigned to another document, but the underling blob id is the same.
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
//no need to schedule another job
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
}
public void verify_pipeline_id_filter()
{
var info = new QueueInfo("test", "tika", "");
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
EventType = HandleStreamEventTypes.DocumentHasNewFormat,
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("soffice")
}
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0), "pipeline filter is not filtering out unwanted pipeline");
rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
PipelineId = new PipelineId("tika"),
DocumentFormat = new DocumentFormat("tika"),
BlobId = new BlobId("tika.1")
}
};
sut.Handle(rm, new TenantId("test"));
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1), "pipeline filter is not filtering in admitted pipeline");
}
public void verify_filtering_on_mime_types()
{
var mimeTypeDocx = MimeTypes.GetMimeTypeByExtension("docx");
var info = new QueueInfo("test", mimeTypes: mimeTypeDocx);
QueueHandler sut = new QueueHandler(info, _db);
StreamReadModel rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.pdf"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail")
}
};
sut.Handle(rm, new TenantId("test"));
var collection = _db.GetCollection<QueuedJob>("queue.test");
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(0));
rm = new StreamReadModel()
{
Filename = new FileNameWithExtension("test.docx"),
FormatInfo = new FormatInfo()
{
DocumentFormat = new DocumentFormat("thumb.small"),
BlobId = new BlobId("blob.1"),
PipelineId = new PipelineId("thumbnail")
}
};
sut.Handle(rm, new TenantId("test"));
Assert.That(collection.AsQueryable().Count(), Is.EqualTo(1));
}
