Improve naming of prefilter merging stages

soedinglab · Aug 12, 2019 · 5047bdc · 5047bdc
1 parent 67c04ae
commit 5047bdc
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 11 deletions.
diff --git a/src/commons/DBWriter.cpp b/src/commons/DBWriter.cpp
@@ -609,7 +609,7 @@ void DBWriter::mergeResults(const char *outFileName, const char *outFileNameInde
 
     DBWriter::sortIndex(indexFileNames[0], outFileNameIndex, lexicographicOrder);
     FileUtil::remove(indexFileNames[0]);
-    Debug(Debug::INFO) << "Time for merging files: " << timer.lap() << "\n";
+    Debug(Debug::INFO) << "Time for merging into " << outFileName << " by mergeResults: " << timer.lap() << "\n";
 }
 
 void DBWriter::mergeIndex(const char** indexFilenames, unsigned int fileCount, const std::vector<size_t> &dataSizes) {
@@ -721,14 +721,15 @@ void DBWriter::mergeFilePair(const std::vector<std::pair<std::string, std::strin
     }
     delete[] files;
 
-    Debug(Debug::INFO) << "Merge file " << fileNames[0].first << " and " << fileNames[0].second << "\n";
+    Debug(Debug::INFO) << "Will merge " << fileNames.size() << " files into " << fileNames[0].first << " and into " << fileNames[0].second << "\n";
     DBReader<unsigned int> reader1(fileNames[0].first.c_str(), fileNames[0].second.c_str(), 1,
                                    DBReader<unsigned int>::USE_INDEX);
     reader1.open(DBReader<unsigned int>::NOSORT);
     unsigned int *seqLen1 = reader1.getSeqLens();
     DBReader<unsigned int>::Index *index1 = reader1.getIndex();
 
     for (size_t i = 1; i < fileNames.size(); i++) {
+        Debug(Debug::INFO) << "Adding files " << fileNames[i].first << " and " << fileNames[i].second << " to the merge \n";
         DBReader<unsigned int> reader2(fileNames[i].first.c_str(), fileNames[i].second.c_str(), 1,
                                        DBReader<unsigned int>::USE_INDEX);
         reader2.open(DBReader<unsigned int>::NOSORT);

diff --git a/src/commons/Parameters.h b/src/commons/Parameters.h
@@ -303,7 +303,7 @@ class Parameters {
     bool   diagonalScoring;              // switch diagonal scoring
     int    exactKmerMatching;            // only exact k-mer matching
     int    maskMode;                     // mask low complex areas
-    int    maskLowerCaseMode;            // maske lowercase letters in prefilter and kmermatchers
+    int    maskLowerCaseMode;            // mask lowercase letters in prefilter and kmermatchers
 
     int    minDiagScoreThr;              // min diagonal score
     int    spacedKmer;                   // Spaced Kmers

diff --git a/src/prefiltering/Prefiltering.cpp b/src/prefiltering/Prefiltering.cpp
@@ -387,7 +387,7 @@ void Prefiltering::setupSplit(DBReader<unsigned int>& tdbr, const int alphabetSi
     }
 }
 
-void Prefiltering::mergeOutput(const std::string &outDB, const std::string &outDBIndex,
+void Prefiltering::mergeTargetSplits(const std::string &outDB, const std::string &outDBIndex,
                                const std::vector<std::pair<std::string, std::string>> &filenames) {
     Timer timer;
     if (filenames.size() < 2) {
@@ -444,7 +444,7 @@ void Prefiltering::mergeOutput(const std::string &outDB, const std::string &outD
 
     DBReader<unsigned int>::removeDb(tmpDb.first);
 
-    Debug(Debug::INFO) << "\nTime for merging results: " << timer.lap() << "\n";
+    Debug(Debug::INFO) << "\nTime for merging into " << outDB << " by mergeTargetSplits: " << timer.lap() << "\n";
 }
 
 
@@ -598,7 +598,7 @@ void Prefiltering::runMpiSplits(const std::string &resultDB, const std::string &
 
         if (splitFiles.size() > 0) {
             // merge output databases
-            mergeFiles(resultDB, resultDBIndex, splitFiles);
+            mergePrefilterSplits(resultDB, resultDBIndex, splitFiles);
         } else {
             Debug(Debug::ERROR) << "Aborting. No results were computed!\n";
             EXIT(EXIT_FAILURE);
@@ -642,7 +642,7 @@ int Prefiltering::runSplits(const std::string &resultDB, const std::string &resu
             }
         }
         if (splitFiles.size() > 0) {
-            mergeFiles(resultDB, resultDBIndex, splitFiles);
+            mergePrefilterSplits(resultDB, resultDBIndex, splitFiles);
             hasResult = true;
         }
     } else if (splitProcessCount == 1) {
@@ -921,10 +921,10 @@ BaseMatrix *Prefiltering::getSubstitutionMatrix(const ScoreMatrixFile &scoringMa
     return subMat;
 }
 
-void Prefiltering::mergeFiles(const std::string &outDB, const std::string &outDBIndex,
+void Prefiltering::mergePrefilterSplits(const std::string &outDB, const std::string &outDBIndex,
                               const std::vector<std::pair<std::string, std::string>> &splitFiles) {
     if (splitMode == Parameters::TARGET_DB_SPLIT) {
-        mergeOutput(outDB, outDBIndex, splitFiles);
+        mergeTargetSplits(outDB, outDBIndex, splitFiles);
     } else if (splitMode == Parameters::QUERY_DB_SPLIT) {
         DBWriter::mergeResults(outDB, outDBIndex, splitFiles);
     }

diff --git a/src/prefiltering/Prefiltering.h b/src/prefiltering/Prefiltering.h
@@ -36,7 +36,7 @@ class Prefiltering {
     int runSplits(const std::string &resultDB, const std::string &resultDBIndex, size_t fromSplit, size_t splitProcessCount, bool merge);
 
     // merge file
-    void mergeFiles(const std::string &outDb, const std::string &outDBIndex,
+    void mergePrefilterSplits(const std::string &outDb, const std::string &outDBIndex,
                     const std::vector<std::pair<std::string, std::string>> &splitFiles);
 
     // get substitution matrix
@@ -125,7 +125,7 @@ class Prefiltering {
     void printStatistics(const statistics_t &stats, std::list<int> **reslens,
                          unsigned int resLensSize, size_t empty, size_t maxResults);
 
-    void mergeOutput(const std::string &outDb, const std::string &outDBIndex,
+    void mergeTargetSplits(const std::string &outDb, const std::string &outDBIndex,
                      const std::vector<std::pair<std::string, std::string>> &filenames);
 
     bool isSameQTDB();