Address feedback and fix potential undefined behavior in seqreader.cc

scripts/mask_low_complexity.sh

@@ -13,7 +13,7 @@ set -o pipefail  # Stop on failures in non-final pipeline commands
 
 target="$1"
 
-MASKER="dustmasker"
+MASKER="k2mask"
 if [ -n "$KRAKEN2_PROTEIN_DB" ]; then
   MASKER="segmasker"
 fi
@@ -33,7 +33,7 @@ if [ -d $target ]; then
   done
 elif [ -f $target ]; then
   if [ ! -e "$target.masked" ]; then
-    $MASKER -in $target -outfmt fasta | sed -e '/^>/!s/[a-z]/x/g' > "$target.tmp"
+    $MASKER -in $target -threads 4 -outfmt fasta | sed -e '/^>/!s/[a-z]/x/g' > "$target.tmp"
     mv "$target.tmp" $target
     touch "$target.masked"
   fi

src/CMakeLists.txt

@@ -43,8 +43,8 @@ add_executable(lookup_accession_numbers
         omp_hack.cc
         utilities.cc)
 
-add_executable(dustmasker
-        dustmasker.cc
+add_executable(k2mask
+        k2mask.cc
         seqreader.cc)
 
 target_link_libraries(dustmasker ${ZLIB_LIBRARIES} Threads::Threads)

src/Makefile

@@ -1,10 +1,11 @@
 CXX = g++
-CXXFLAGS = -fopenmp -Wall -std=c++11 -O3
+OMPFLAG ?= -fopenmp
+CXXFLAGS = $(OMPFLAG) -Wall -std=c++11 -O3
 CXXFLAGS += -DLINEAR_PROBING
 
 .PHONY: all clean install
 
-PROGS = estimate_capacity build_db classify dump_table lookup_accession_numbers
+PROGS = estimate_capacity build_db classify dump_table lookup_accession_numbers k2mask
 
 all: $(PROGS)
 
@@ -24,13 +25,13 @@ omp_hack.o: omp_hack.cc omp_hack.h
 reports.o: reports.cc reports.h kraken2_data.h
 aa_translate.o: aa_translate.cc aa_translate.h
 utilities.o: utilities.cc utilities.h
-dustmasker.o: dustmasker.cc gzstream.h threadpool.h
 
 classify.o: classify.cc kraken2_data.h kv_store.h taxonomy.h seqreader.h mmscanner.h compact_hash.h aa_translate.h reports.h utilities.h readcounts.h
 dump_table.o: dump_table.cc compact_hash.h taxonomy.h mmscanner.h kraken2_data.h reports.h
 estimate_capacity.o: estimate_capacity.cc kv_store.h mmscanner.h seqreader.h utilities.h
 build_db.o: build_db.cc taxonomy.h mmscanner.h seqreader.h compact_hash.h kv_store.h kraken2_data.h utilities.h
 lookup_accession_numbers.o: lookup_accession_numbers.cc mmap_file.h utilities.h
+k2mask.o: k2mask.cc gzstream.h threadpool.h
 
 build_db: build_db.o mmap_file.o compact_hash.o taxonomy.o seqreader.o mmscanner.o omp_hack.o utilities.o
 	$(CXX) $(CXXFLAGS) -o $@ $^
@@ -47,5 +48,5 @@ dump_table: dump_table.o mmap_file.o compact_hash.o omp_hack.o taxonomy.o report
 lookup_accession_numbers: lookup_accession_numbers.o mmap_file.o omp_hack.o utilities.o
 	$(CXX) $(CXXFLAGS) -o $@ $^
 
-dustmasker: dustmasker.o seqreader.o
+k2mask: k2mask.o seqreader.o
 	$(CXX) $(CXXFLAGS) -o $@ $^ -lz -pthread