Merge pull request #101 from metabarcoding/push-klzowrsmmnyv

Dynamic Batch Flushing and Build Improvements

.github/workflows/release.yml

@@ -79,7 +79,7 @@ jobs:
             -w /src \
             -e VERSION="${VERSION}" \
             golang:1.26-alpine \
-            sh -c "apk add --no-cache gcc musl-dev zlib-dev make && \
+            sh -c "apk add --no-cache gcc musl-dev zlib-dev zlib-static make && \
                    make LDFLAGS='-linkmode=external -extldflags=-static' obitools"
           mkdir -p artifacts
           tar -czf artifacts/obitools4_${VERSION}_${{ matrix.output_name }}.tar.gz -C build .

pkg/obiiter/distribute.go

@@ -57,34 +57,21 @@ func (dist *IDistribute) Classifier() *obiseq.BioSequenceClassifier {
 }
 
 // Distribute organizes the biosequences from the iterator into batches
-// based on the provided classifier and batch sizes. It returns an
+// based on the provided classifier. It returns an IDistribute instance
-// IDistribute instance that manages the distribution of the sequences.
+// that manages the distribution of the sequences.
 //
-// Parameters:
+// Batches are flushed when either BatchSizeMax() sequences or BatchMem()
-//   - class: A pointer to a BioSequenceClassifier used to classify
+// bytes are accumulated per key, mirroring the RebatchBySize strategy.
-//     the biosequences during distribution.
+func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier) IDistribute {
-//   - sizes: Optional integer values specifying the batch size. If
+	maxCount := obidefault.BatchSizeMax()
-//     no sizes are provided, a default batch size of 5000 is used.
+	maxBytes := obidefault.BatchMem()
-//
-// Returns:
-// An IDistribute instance that contains the outputs of the
-// classified biosequences, a channel for new data notifications,
-// and the classifier used for distribution. The method operates
-// asynchronously, processing the sequences in separate goroutines.
-// It ensures that the outputs are closed and cleaned up once
-// processing is complete.
-func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, sizes ...int) IDistribute {
-	batchsize := obidefault.BatchSize()
 
 	outputs := make(map[int]IBioSequence, 100)
 	slices := make(map[int]*obiseq.BioSequenceSlice, 100)
+	bufBytes := make(map[int]int, 100)
 	orders := make(map[int]int, 100)
 	news := make(chan int)
 
-	if len(sizes) > 0 {
-		batchsize = sizes[0]
-	}
-
 	jobDone := sync.WaitGroup{}
 	lock := sync.Mutex{}
 
@@ -115,6 +102,7 @@ func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, siz
 					slice = &s
 					slices[key] = slice
 					orders[key] = 0
+					bufBytes[key] = 0
 
 					lock.Lock()
 					outputs[key] = MakeIBioSequence()
@@ -123,14 +111,20 @@ func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, siz
 					news <- key
 				}
 
-				*slice = append(*slice, s)
+				sz := s.MemorySize()
-
+				countFull := maxCount > 0 && len(*slice) >= maxCount
-				if len(*slice) == batchsize {
+				memFull := maxBytes > 0 && bufBytes[key]+sz > maxBytes && len(*slice) > 0
+				if countFull || memFull {
 					outputs[key].Push(MakeBioSequenceBatch(source, orders[key], *slice))
 					orders[key]++
 					s := obiseq.MakeBioSequenceSlice()
 					slices[key] = &s
+					slice = &s
+					bufBytes[key] = 0
 				}
+
+				*slice = append(*slice, s)
+				bufBytes[key] += sz
 			}
 		}
 

pkg/obilua/obiseqslice.go

@@ -31,7 +31,8 @@ func obiseqslice2Lua(interpreter *lua.LState,
 }
 
 func newObiSeqSlice(luaState *lua.LState) int {
-	seqslice := obiseq.NewBioSequenceSlice()
+	capacity := luaState.OptInt(1, 0)
+	seqslice := obiseq.NewBioSequenceSlice(capacity)
 	luaState.Push(obiseqslice2Lua(luaState, seqslice))
 	return 1
 }

pkg/obioptions/version.go

@@ -3,7 +3,7 @@ package obioptions
 // Version is automatically updated by the Makefile from version.txt
 // The patch number (third digit) is incremented on each push to the repository
 
-var _Version = "Release 4.4.26"
+var _Version = "Release 4.4.29"
 
 // Version returns the version of the obitools package.
 //

pkg/obiseq/worker.go

@@ -104,11 +104,11 @@ func SeqToSliceWorker(worker SeqWorker,
 			for _, s := range input {
 				r, err := worker(s)
 				if err == nil {
+					if i+len(r) > cap(output) {
+						output = slices.Grow(output[:i], len(r))
+						output = output[:cap(output)]
+					}
 					for _, rs := range r {
-						if i == len(output) {
-							output = slices.Grow(output, cap(output))
-							output = output[:cap(output)]
-						}
 						output[i] = rs
 						i++
 					}

pkg/obitools/obidistribute/distribute.go

@@ -46,8 +46,7 @@ func CLIDistributeSequence(sequences obiiter.IBioSequence) {
 		formater = obiformats.WriteSequencesToFile
 	}
 
-	dispatcher := sequences.Distribute(CLISequenceClassifier(),
+	dispatcher := sequences.Distribute(CLISequenceClassifier())
-		obidefault.BatchSize())
 
 	obiformats.WriterDispatcher(CLIFileNamePattern(),
 		dispatcher, formater, opts...,

version.txt

@@ -1 +1 @@
-4.4.26
+4.4.29