/// <summary>
/// Method to get the documents from loadfile
/// </summary>
/// <param name="correlationId">Correlation id</param>
/// <param name="recordText">record text</param>
/// <param name="documentCtrlNbr">document control number</param>
/// <param name="imageFileList">imagefile list</param>
/// <param name="textFileList">text file list</param>
/// <param name="recordParserLog">recordParser Log</param>
/// <returns>list of DocumentDetail</returns>
public List<DocumentDetail> GetDocuments(string correlationId, string recordText, string documentCtrlNbr,
List<string> textFileList, out JobWorkerLog<LoadFileDocumentParserLogInfo> recordParserLog)
{
recordText.ShouldNotBe(null);
List<DocumentDetail> documentDetailList = new List<DocumentDetail>();
recordParserLog = null;
RVWDocumentBEO document = null;
string missingNativeFile = null;
List<string> missingImageFiles = new List<string>();
bool isMissingContent = false;
List<string> missingContentFiles = new List<string>();
List<string> misMatchedFields = new List<string>();
List<string> misMatchedFieldsMessage = new List<string>();
Int32 importedImagesCount = 0;
#region Parse Record Text
var recordTokenizer = new RecordTokenizer(m_ColumnDelimiter, m_QuoteCharacter);
var fields = recordTokenizer.ParseRecord(recordText);
#endregion
List<RVWDocumentFieldBEO> matchingKeyField = null; //For Overlay
//Get document
document = ConsturctDocument(correlationId, fields, textFileList,
ref matchingKeyField, out missingNativeFile, missingImageFiles, out isMissingContent,
missingContentFiles, misMatchedFields, misMatchedFieldsMessage, out importedImagesCount);
if (m_JobParameter.IsAppend)
{
// Assign DCN
document.DocumentControlNumber = documentCtrlNbr;
//1) Construct Native Set
var nativeSetDocument = GetDocumentForNativeSet(document);
var doc = new DocumentDetail();
doc.CorrelationId = correlationId;
doc.docType = DocumentsetType.NativeSet;
doc.document = nativeSetDocument;
doc.ConversationIndex = document.ConversationIndex;
doc.IsNewDocument = true;
//Add Native Document
documentDetailList.Add(doc);
//2) Construct Image Set
if (m_JobParameter.IsImportImages && !string.IsNullOrEmpty(m_JobParameter.ImageSetId))
{
var imageSetDocument = GetDocumentForImageSet(document, m_JobParameter.ImageSetId);
imageSetDocument.IsImageFilesNotAssociated = !(importedImagesCount > 0 || missingImageFiles.Any());
var docImg = new DocumentDetail();
docImg.CorrelationId = correlationId;
docImg.docType = DocumentsetType.ImageSet;
docImg.document = imageSetDocument;
docImg.IsNewDocument = true;
//Add Image Document
documentDetailList.Add(docImg);
}
}
else
{
//Send original document to Search worker
var doc = new DocumentDetail();
doc.document = document;
doc.ConversationIndex = document.ConversationIndex;
#region Create a unique file name for extracted content file
doc.document.DocumentBinary.FileList.ForEach(x => x.Path = (x.Type.ToLower() == Constants.TEXT_FILE_TYPE.ToLower()) ? string.Format("{0}?id={1}", x.Path, Guid.NewGuid().ToString()) : x.Path);
#endregion
doc.CorrelationId = correlationId;
doc.OverlayMatchingField = matchingKeyField;
doc.document.IsImageFilesNotAssociated = !(importedImagesCount > 0 || missingImageFiles.Any());
documentDetailList.Add(doc);
}
//3) Construct Log
#region Log
var imageMappingKey=string.Empty;
if (m_JobParameter.IsImportImages && m_JobParameter.LoadFile.ImageFile != null)
{
imageMappingKey = fields[m_JobParameter.LoadFile.ImageFile.ImageMatchingFieldId];
}
recordParserLog = ConstructLog(correlationId, true, document.DocumentId,
missingNativeFile, missingImageFiles, isMissingContent, missingContentFiles, importedImagesCount, misMatchedFields, documentCtrlNbr, document.CrossReferenceFieldValue, misMatchedFieldsMessage, imageMappingKey);
#endregion
var firstDoc = documentDetailList.FirstOrDefault();
if (firstDoc != null)
{
firstDoc.document.ImportMessage = recordParserLog.LogInfo.Message;
}
return documentDetailList;
}
protected override void BeginWork()
{
try
{
base.BeginWork();
m_Parameters = GetImportBEO(BootParameters);
m_Parameters.ShouldNotBe(null);
m_LoadFileUri = new Uri(m_Parameters.Locations.First());
m_ColumnDelimiter = (char)m_Parameters.LoadFile.ColumnDelimiter;
m_QuoteCharacter = (char)m_Parameters.LoadFile.QuoteCharacter;
m_NewlineCharacter = (char)m_Parameters.LoadFile.NewlineDelimiter;
m_RecordTokenizer = new RecordTokenizer(m_ColumnDelimiter, m_QuoteCharacter);
m_EncodingType = Encoding.GetEncoding(m_Parameters.LoadFile.EncodingType);
m_IsFirstLineHeader = m_Parameters.LoadFile.IsFirstLineHeader;
var loadFilePath = HttpUtility.UrlDecode(m_LoadFileUri.OriginalString);
ReportToDirector("LoadFileParser works on load file {0}", loadFilePath);
m_StreamReader = new StreamReader(loadFilePath, m_EncodingType);
#region Dataset Detaills
m_Parameters.DatasetId.ShouldBeGreaterThan(0);
m_Dataset = DataSetBO.GetDataSetDetailForDataSetId(m_Parameters.DatasetId);
var matterDetails = MatterDAO.GetMatterDetails(m_Parameters.MatterId.ToString());
matterDetails.ShouldNotBe(null);
m_Dataset.Matter = matterDetails;
var searchServerDetails = ServerDAO.GetSearchServer(matterDetails.SearchServer.Id);
searchServerDetails.ShouldNotBe(null);
m_Dataset.Matter.SearchServer = searchServerDetails;
m_DatasetPath = m_Dataset.CompressedFileExtractionLocation;
#endregion
if (m_Parameters != null &&
m_Parameters.IsImportImages &&
m_Parameters.LoadFile.ImageFile != null &&
m_Parameters.LoadFile.ImageFile.ImageExtractionOption == LoadFileImageExtractionOption.HelperFile)
{
var imageHelperFileName = m_Parameters.LoadFile.ImageFile.HelperFileName;
ReportToDirector("LoadFileParser uses image helper file {0}", imageHelperFileName);
_imageHelperFileParser = new HelperFileParser(this, imageHelperFileName);
}
if (m_Parameters != null &&
m_Parameters.LoadFile.ContentFile != null &&
m_Parameters.LoadFile.ContentFile.TextExtractionOption == LoadFileTextExtractionOption.HelperFile)
{
var contentHelperFileName = m_Parameters.LoadFile.ContentFile.HelperFileName;
ReportToDirector("LoadFileParser uses content (text) helper file {0}", contentHelperFileName);
TextHelperFile = new HelperFile(this, contentHelperFileName);
}
if (null != m_Parameters &&
null != m_Parameters.LoadFile &&
null != m_Parameters.LoadFile.ContentFile &&
null != m_Parameters.LoadFile.ContentFile.LoadFileContentField)
{
m_ContentFieldNumber = Convert.ToInt32(m_Parameters.LoadFile.ContentFile.LoadFileContentField);
}
_uniqueThreadString = Guid.NewGuid().ToString().Replace("-", "").ToUpper();
SetMessageBatchSize(m_Parameters);
}
catch (Exception ex)
{
//Send log to Log Pipe
LogMessage(false, Constants.ParserFailureMessageOnInitialize);
ex.Trace();
ReportToDirector("Exception in LoadFileParser.BeginWork", ex.ToDebugString());
throw;
}
}
protected override void BeginWork()
{
try
{
base.BeginWork();
m_Parameters = GetImportBEO(BootParameters);
m_Parameters.ShouldNotBe(null);
m_LoadFileUri = new Uri(m_Parameters.Locations.First());
m_ColumnDelimiter = (char) m_Parameters.LoadFile.ColumnDelimiter;
m_QuoteCharacter = (char) m_Parameters.LoadFile.QuoteCharacter;
m_NewlineCharacter = (char) m_Parameters.LoadFile.NewlineDelimiter;
m_RecordTokenizer = new RecordTokenizer(m_ColumnDelimiter, m_QuoteCharacter);
m_EncodingType = Encoding.GetEncoding(m_Parameters.LoadFile.EncodingType);
m_IsFirstLineHeader = m_Parameters.LoadFile.IsFirstLineHeader;
var loadFilePath = HttpUtility.UrlDecode(m_LoadFileUri.OriginalString);
ReportToDirector("LoadFileParser works on load file {0}", loadFilePath);
m_StreamReader = new StreamReader(loadFilePath, m_EncodingType);
#region Dataset Detaills
m_Parameters.DatasetId.ShouldBeGreaterThan(0);
m_Dataset = DataSetBO.GetDataSetDetailForDataSetId(m_Parameters.DatasetId);
var matterDetails = MatterDAO.GetMatterDetails(m_Parameters.MatterId.ToString());
matterDetails.ShouldNotBe(null);
m_Dataset.Matter = matterDetails;
var searchServerDetails = ServerDAO.GetSearchServer(matterDetails.SearchServer.Id);
searchServerDetails.ShouldNotBe(null);
m_Dataset.Matter.SearchServer = searchServerDetails;
m_DatasetPath = m_Dataset.CompressedFileExtractionLocation;
#endregion
if (m_Parameters != null &&
m_Parameters.IsImportImages &&
m_Parameters.LoadFile.ImageFile != null &&
m_Parameters.LoadFile.ImageFile.ImageExtractionOption == LoadFileImageExtractionOption.HelperFile)
{
var imageHelperFileName = m_Parameters.LoadFile.ImageFile.HelperFileName;
ReportToDirector("LoadFileParser uses image helper file {0}", imageHelperFileName);
_imageHelperFileParser =new HelperFileParser(this,imageHelperFileName);
}
if (m_Parameters != null &&
m_Parameters.LoadFile.ContentFile != null &&
m_Parameters.LoadFile.ContentFile.TextExtractionOption == LoadFileTextExtractionOption.HelperFile)
{
var contentHelperFileName = m_Parameters.LoadFile.ContentFile.HelperFileName;
ReportToDirector("LoadFileParser uses content (text) helper file {0}", contentHelperFileName);
TextHelperFile = new HelperFile(this, contentHelperFileName);
}
if (null != m_Parameters &&
null != m_Parameters.LoadFile &&
null != m_Parameters.LoadFile.ContentFile &&
null != m_Parameters.LoadFile.ContentFile.LoadFileContentField)
{
m_ContentFieldNumber = Convert.ToInt32(m_Parameters.LoadFile.ContentFile.LoadFileContentField);
}
_uniqueThreadString = Guid.NewGuid().ToString().Replace("-", "").ToUpper();
SetMessageBatchSize(m_Parameters);
}
catch (Exception ex)
{
//Send log to Log Pipe
LogMessage(false, Constants.ParserFailureMessageOnInitialize);
ex.Trace();
ReportToDirector("Exception in LoadFileParser.BeginWork", ex.ToDebugString());
throw;
}
}
