private bool DoSomeWork(Library library, PDFDocument pdf_document, RunningStatistics stats)
{
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF processing loop due to daemon termination");
return(false);
}
// Start rendering the first page so we can do some extraction
try
{
//if (pdf_document.DocumentExists) -- already tested in collection loop above
pdf_document.PDFRenderer.GetOCRText(1);
}
catch (Exception ex)
{
Logging.Error(ex, "There was an exception while requesting the first page to be OCRed while processing document {0}", pdf_document.Fingerprint);
}
StatusManager.Instance.UpdateStatus("AutoSuggestMetadata", "Suggesting metadata", stats.currentdocumentIndex, stats.totalDocumentCount, true);
if (StatusManager.Instance.IsCancelled("AutoSuggestMetadata"))
{
return(false);
}
// Try get the authors and year with the PDF in-file metadata
try
{
PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata while processing document {0}", pdf_document.Fingerprint);
}
// Try looking for the title in the OCR
try
{
PDFMetadataInferenceFromOCR.InferTitleFromOCR(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
// Try suggesting some bibtex from bibtexsearch.com
try
{
PDFMetadataInferenceFromBibTeXSearch.InferBibTeX(pdf_document, false);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
return(true);
}
public void DoMaintenance(Library library, Action callback_after_some_work_done)
{
Stopwatch clk = Stopwatch.StartNew();
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance START");
RunningStatistics stats = new RunningStatistics();
// To recover from a search index fatal failure and re-indexing attempt for very large libraries,
// we're better off processing a limited number of source files as we'll be able to see
// *some* results more quickly and we'll have a working, though yet incomplete,
// index in *reasonable time*.
//
// Reconstructing the entire index will take a *long* time. We grow the index and other meta
// stores a bunch-of-files at a time and then repeat the entire maintenance process until
// we'll be sure to have run out of files to process for sure...
const int MAX_NUMBER_OF_PDF_FILES_TO_PROCESS = 30;
const int MIN_NUMBER_OF_PDF_FILES_TO_PROCESS_PER_ITERATION = 10;
const int MAX_SECONDS_PER_ITERATION = 10 * 60;
long clk_bound = clk.ElapsedMilliseconds + MAX_SECONDS_PER_ITERATION * 1000;
try
{
// If this library is busy, skip it for now
if (Library.IsBusyAddingPDFs || Library.IsBusyRegeneratingTags)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Not daemon processing any library that is busy with adds...");
return;
}
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to application termination");
return;
}
if (Common.Configuration.ConfigurationManager.Instance.ConfigurationRecord.DisableAllBackgroundTasks)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to DisableAllBackgroundTasks");
return;
}
// Check that we have something to do
List <PDFDocument> pdf_documents = library.PDFDocuments;
stats.totalDocumentCount = pdf_documents.Count;
stats.currentdocumentIndex = 0;
stats.documentsProcessedCount = 0;
foreach (PDFDocument pdf_document in pdf_documents)
{
int needs_processing = 0;
stats.currentdocumentIndex++;
// there's nothing to infer from PDF when there's no PDF to process:
if (!pdf_document.DocumentExists)
{
continue;
}
if (PDFMetadataInferenceFromPDFMetadata.NeedsProcessing(pdf_document))
{
needs_processing |= 0x01;
}
if (PDFMetadataInferenceFromOCR.NeedsProcessing(pdf_document))
{
needs_processing |= 0x02;
}
if (PDFMetadataInferenceFromBibTeXSearch.NeedsProcessing(pdf_document))
{
needs_processing |= 0x04;
}
if (needs_processing != 0)
{
pdfs_retry_count.TallyOne(pdf_document.Fingerprint);
int cnt = pdfs_retry_count.GetCount(pdf_document.Fingerprint);
if (!General.IsPowerOfTwo(cnt))
{
needs_processing = 0; // skip this time around
}
#if true
// Reset counter when it has run up to 64 (which means 6 attempts were made up to now).
if (cnt > 64)
{
pdfs_retry_count.ResetTally(pdf_document.Fingerprint);
}
#endif
}
// Previous check calls MAY take some serious time, hence we SHOULD check again whether
// the user decided to exit Qiqqa before we go on and do more time consuming work.
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF fingerprinting loop due to daemon termination");
return;
}
if (needs_processing != 0)
{
if (DoSomeWork(library, pdf_document, stats))
{
stats.documentsProcessedCount++;
}
}
// Limit the number of source files to process before we go and create/update
// a sane (though tiny and incomplete) Lucene search index database so that
// we have some up-to-date results ready whenever the user exits the Qiqqa application
// while this process is still running.
// When the user keeps Qiqqa running, this same approach will help us to 'update'
// the search index a bunch of files at a time, so everyone involved will be able
// to see progress happening after losing the index due to some fatal crash or
// forced re-index request.
if ((stats.documentsProcessedCount + 1) % MAX_NUMBER_OF_PDF_FILES_TO_PROCESS == 0)
{
Logging.Debug特("Interupting the MetadataExtractionDaemon PDF fingerprinting loop due to MAX_NUMBER_OF_PDF_FILES_TO_PROCESS reached");
callback_after_some_work_done();
}
// A timeout should only kick in when we have *some* work done already or
// we would have introduced a subtle bug for very large libraries: if the timeout
// is short enough for the library scan to take that long on a slow machine,
// the timeout would, by itself, cause no work to be done, *ever*.
// Hence we require a minimum amount of work done before the timeout condition
// is allowed to fire.
if (clk_bound <= clk.ElapsedMilliseconds && stats.documentsProcessedCount >= MIN_NUMBER_OF_PDF_FILES_TO_PROCESS_PER_ITERATION)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF fingerprinting loop due to MAX_SECONDS_PER_ITERATION: {0} ms consumed", clk.ElapsedMilliseconds);
return;
}
}
}
finally
{
if (0 < stats.documentsProcessedCount)
{
Logging.Debug特("Got {0} items of metadata extraction work done.", stats.documentsProcessedCount);
}
else
{
// nothing to do.
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to no more files to process right now.");
// when there's nothing to do, reset the retry tallying by doing a hard reset:
// the idea here being that delaying any retries on pending items is useless when
// there's nothing to do otherwise.
pdfs_retry_count = new CountingDictionary <string>(); // quickest and cleanest reset is a re-init (+ GarbageCollect of the old dict)
}
Logging.Info("{0}ms were spent to extract metadata", clk.ElapsedMilliseconds);
StatusManager.Instance.ClearStatus("AutoSuggestMetadata");
callback_after_some_work_done();
}
}
public void DoMaintenance(Library library)
{
Stopwatch sw_total = new Stopwatch();
sw_total.Start();
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance START");
// To recover from a search index fatal failure and re-indexing attempt for very large libraries,
// we're better off processing a limited number of source files as we'll be able to see
// *some* results more quickly and we'll have a working, though yet incomplete,
// index in *reasonable time*.
//
// To reconstruct the entire index will take a *long* time. We grow the index and other meta
// stores a bunch-of-files at a time and then repeat the entire maintenance process until
// we'll be sure to have run out of files to process for sure...
const int MAX_NUMBER_OF_PDF_FILES_TO_PROCESS = 10;
const int MAX_SECONDS_PER_ITERATION = 15;
DateTime index_processing_start_time = DateTime.UtcNow;
while (true)
{
// If this library is busy, skip it for now
if (Library.IsBusyAddingPDFs)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Not daemon processing any library that is busy with adds...");
break;
}
if (DateTime.UtcNow.Subtract(index_processing_start_time).TotalSeconds > MAX_SECONDS_PER_ITERATION)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to MAX_SECONDS_PER_ITERATION: {0} seconds consumed", DateTime.UtcNow.Subtract(index_processing_start_time).TotalSeconds);
break;
}
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to application termination");
break;
}
if (Common.Configuration.ConfigurationManager.Instance.ConfigurationRecord.DisableAllBackgroundTasks)
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to DisableAllBackgroundTasks");
break;
}
// Check that we have something to do
List <PDFDocument> pdfs_to_process = new List <PDFDocument>();
{
List <PDFDocument> pdf_documents = library.PDFDocuments;
foreach (PDFDocument pdf_document in pdf_documents)
{
bool needs_processing = false;
if (PDFMetadataInferenceFromPDFMetadata.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (PDFMetadataInferenceFromOCR.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (PDFMetadataInferenceFromBibTeXSearch.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (needs_processing)
{
pdfs_retry_count.TallyOne(pdf_document.Fingerprint);
if (General.IsPowerOfTwo(pdfs_retry_count.GetCount(pdf_document.Fingerprint)))
{
pdfs_to_process.Add(pdf_document);
}
}
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF fingerprinting loop due to daemon termination");
break;
}
// Limit the number of source files to process at once or we won't have recreated
// a sane (though tiny and incomplete) Lucene search index database by the time
// the user exits the Qiqqa application in a minute or so.
// When the user keeps Qiqqa running, this same approach will help us to 'update'
// the search index a bunch of files at a time, so everyone involved will be able
// to see progress happening after losing the index due to some fatal crash or
// forced re-index request.
if (pdfs_to_process.Count >= MAX_NUMBER_OF_PDF_FILES_TO_PROCESS)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF fingerprinting loop due to MAX_NUMBER_OF_PDF_FILES_TO_PROCESS reached");
break;
}
}
if (0 < pdfs_to_process.Count)
{
Logging.Debug特("Got {0} items of metadata extraction work", pdfs_to_process.Count);
}
}
// Get each of our guys to start rendering their first pages so we can do some extraction
foreach (PDFDocument pdf_document in pdfs_to_process)
{
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon PDF processing loop due to daemon termination");
break;
}
try
{
if (pdf_document.DocumentExists)
{
pdf_document.PDFRenderer.GetOCRText(1);
}
}
catch (Exception ex)
{
Logging.Error(ex, "There was an exception while requesting the first page to be OCRed");
}
}
// See if there is any completed OCR to work with
if (0 < pdfs_to_process.Count)
{
StatusManager.Instance.ClearCancelled("AutoSuggestMetadata");
}
for (int i = 0; i < pdfs_to_process.Count; ++i)
{
StatusManager.Instance.UpdateStatusBusy("AutoSuggestMetadata", "Suggesting metadata", i, pdfs_to_process.Count, true);
if (StatusManager.Instance.IsCancelled("AutoSuggestMetadata"))
{
break;
}
if (Utilities.Shutdownable.ShutdownableManager.Instance.IsShuttingDown)
{
Logging.Debug特("Breaking out of MetadataExtractionDaemon metadata suggesting loop due to daemon termination");
break;
}
PDFDocument pdf_document = pdfs_to_process[i];
// Try get the authors and year with the PDF in-file metadata
try
{
PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata while processing document {0}", pdf_document.Fingerprint);
}
// Try looking for the title in the OCR
try
{
PDFMetadataInferenceFromOCR.InferTitleFromOCR(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
// Try suggesting some bibtex from bibtexsearch.com
try
{
PDFMetadataInferenceFromBibTeXSearch.InferBibTeX(pdf_document, false);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
}
if (0 < pdfs_to_process.Count)
{
Logging.Info("It took a total of {0}ms to extract metadata", sw_total.ElapsedMilliseconds);
StatusManager.Instance.ClearStatus("AutoSuggestMetadata");
}
else
{
Logging.Debug特("MetadataExtractionDaemon::DoMaintenance: Breaking out of outer processing loop due to no more files to process (count = {0})", pdfs_to_process.Count);
break;
}
}
}
public void DoMaintenance(Library library, Daemon daemon)
{
Stopwatch sw_total = new Stopwatch();
sw_total.Start();
// Check that we have something to do
List <PDFDocument> pdfs_to_process = new List <PDFDocument>();
{
List <PDFDocument> pdf_documents = library.PDFDocuments;
foreach (PDFDocument pdf_document in pdf_documents)
{
bool needs_processing = false;
if (PDFMetadataInferenceFromPDFMetadata.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (PDFMetadataInferenceFromOCR.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (PDFMetadataInferenceFromBibTeXSearch.NeedsProcessing(pdf_document))
{
needs_processing = true;
}
if (needs_processing)
{
pdfs_retry_count.TallyOne(pdf_document.Fingerprint);
if (General.IsPowerOfTwo(pdfs_retry_count.GetCount(pdf_document.Fingerprint)))
{
pdfs_to_process.Add(pdf_document);
}
}
}
if (0 < pdfs_to_process.Count)
{
Logging.Debug("Got {0} items of metadata extraction work", pdfs_to_process.Count);
}
}
// Get each of our guys to start rendering their first pages so we can do some extraction
foreach (PDFDocument pdf_document in pdfs_to_process)
{
if (!daemon.StillRunning)
{
break;
}
try
{
if (pdf_document.DocumentExists)
{
pdf_document.PDFRenderer.GetOCRText(1);
}
}
catch (Exception ex)
{
Logging.Error(ex, "There was an exception while requesting the first page to be OCRed");
}
}
// See if there is any completed OCR to work with
if (0 < pdfs_to_process.Count)
{
StatusManager.Instance.ClearCancelled("AutoSuggestMetadata");
}
for (int i = 0; i < pdfs_to_process.Count; ++i)
{
StatusManager.Instance.UpdateStatusBusy("AutoSuggestMetadata", "Suggesting metadata", i, pdfs_to_process.Count, true);
if (StatusManager.Instance.IsCancelled("AutoSuggestMetadata"))
{
break;
}
if (!daemon.StillRunning)
{
break;
}
PDFDocument pdf_document = pdfs_to_process[i];
// Try get the authors and year with the PDF in-file metadata
try
{
PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromPDFMetadata.InferFromPDFMetadata while processing document {0}", pdf_document.Fingerprint);
}
// Try looking for the title in the OCR
try
{
PDFMetadataInferenceFromOCR.InferTitleFromOCR(pdf_document);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
// Try suggesting some bibtex from bibtexsearch.com
try
{
PDFMetadataInferenceFromBibTeXSearch.InferBibTeX(pdf_document, false);
}
catch (Exception ex)
{
Logging.Warn(ex, "Problem in PDFMetadataInferenceFromOCR.InferTitleFromOCR while processing document {0}", pdf_document.Fingerprint);
}
}
if (0 < pdfs_to_process.Count)
{
Logging.Info("It took a total of {0}ms to extract metadata", sw_total.ElapsedMilliseconds);
StatusManager.Instance.ClearStatus("AutoSuggestMetadata");
}
}
