fix seq validation introduced in v2.7.0. fix #439

Author: shenwei356

CHANGELOG.md

@@ -1,3 +1,9 @@
+- [SeqKit v2.7.1](https://github.com/shenwei356/seqkit/releases/tag/v2.7.1) - 2024-01-31
+[![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.7.1/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.7.1)
+    - `seqkit seq/locate/fish/watch`:
+        - Removing the flag `-V/--validate-seq-length`. Now the whole sequence will be checked if `-v/--validate-seq` is given.
+    - `seqkit amplicon`:
+        - Fix the speed problem, introduced in v2.7.0. [#439](https://github.com/shenwei356/seqkit/issues/439).
 - [SeqKit v2.7.0](https://github.com/shenwei356/seqkit/releases/tag/v2.7.0) - 2024-01-31
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.7.0/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.7.0)
     - `seqkit`:

go.mod

@@ -20,7 +20,7 @@ require (
 	github.com/mattn/go-isatty v0.0.16
 	github.com/mitchellh/go-homedir v1.1.0
 	github.com/pkg/errors v0.9.1
-	github.com/shenwei356/bio v0.12.1
+	github.com/shenwei356/bio v0.13.0
 	github.com/shenwei356/breader v0.3.2
 	github.com/shenwei356/bwt v0.6.1
 	github.com/shenwei356/go-logging v0.0.0-20171012171522-c6b9702d88ba

go.sum

@@ -123,8 +123,8 @@ github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/f
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/ruudk/golang-pdf417 v0.0.0-20181029194003-1af4ab5afa58/go.mod h1:6lfFZQK844Gfx8o5WFuvpxWRwnSoipWe/p622j1v06w=
 github.com/ruudk/golang-pdf417 v0.0.0-20201230142125-a7e3863a1245/go.mod h1:pQAZKsJ8yyVxGRWYNEm9oFB8ieLgKFnamEyDmSA0BRk=
-github.com/shenwei356/bio v0.12.1 h1:RAABmg9XVOEaPXqcNx7gLK710FN007a+v9SXho3P6GU=
-github.com/shenwei356/bio v0.12.1/go.mod h1:JjWavkWha/UzK0K7dqTVuzkHEBgGNad9yC1hv0YJrG0=
+github.com/shenwei356/bio v0.13.0 h1:PtgC6pJyBcSR7S16qjn6dW1mISAmsFakaBgh0uI+aFY=
+github.com/shenwei356/bio v0.13.0/go.mod h1:JjWavkWha/UzK0K7dqTVuzkHEBgGNad9yC1hv0YJrG0=
 github.com/shenwei356/breader v0.3.2 h1:GLy2clIMck6FdTwj8WLnmhv0PW/7Pp+Wcx7TVEHG0ks=
 github.com/shenwei356/breader v0.3.2/go.mod h1:BimwolkMTIr/O4iX7xXtjEB1z5y39G+8I5Tsm9guC3E=
 github.com/shenwei356/bwt v0.6.1 h1:BDS1nhhIxiC284OKtLBUgy+U5L/7WrvT/ehOExB/DSA=

seqkit/cmd/fish.go

@@ -154,11 +154,8 @@ Attention:
 		alnParams := parseAlnParams(flagAlnParams)
 
 		validateSeq := getFlagBool(cmd, "validate-seq")
-		validateSeqLength := getFlagValidateSeqLength(cmd, "validate-seq-length")
 
 		seq.ValidateSeq = validateSeq
-		seq.ValidateWholeSeq = false
-		seq.ValidSeqLengthThreshold = validateSeqLength
 		seq.ValidSeqThreads = config.Threads
 
 		if !(alphabet == nil || alphabet == seq.Unlimit) {
@@ -360,7 +357,6 @@ func init() {
 	fishCmd.Flags().BoolP("print-desc", "D", false, "print full sequence header")
 	fishCmd.Flags().BoolP("print-aln", "g", false, "print sequence alignments")
 	fishCmd.Flags().BoolP("invert", "i", false, "print out references not matching with any query")
-	fishCmd.Flags().IntP("validate-seq-length", "V", 10000, "length of sequence to validate (0 for whole seq)")
 	fishCmd.Flags().Float64P("min-qual", "q", 5.0, "minimum mapping quality")
 }
 

seqkit/cmd/locate.go

@@ -70,8 +70,6 @@ Attentions:
 		outFile := config.OutFile
 		seq.AlphabetGuessSeqLengthThreshold = config.AlphabetGuessSeqLength
 		seq.ValidateSeq = true
-		seq.ValidateWholeSeq = false
-		seq.ValidSeqLengthThreshold = getFlagValidateSeqLength(cmd, "validate-seq-length")
 		seq.ValidSeqThreads = config.Threads
 		seq.ComplementThreads = config.Threads
 		quiet := config.Quiet
@@ -988,7 +986,6 @@ func init() {
 	locateCmd.Flags().BoolP("use-fmi", "F", false, "use FM-index for much faster search of lots of sequence patterns")
 	locateCmd.Flags().BoolP("ignore-case", "i", false, "ignore case")
 	locateCmd.Flags().BoolP("only-positive-strand", "P", false, "only search on positive strand")
-	locateCmd.Flags().IntP("validate-seq-length", "V", 10000, "length of sequence to validate (0 for whole seq)")
 	locateCmd.Flags().BoolP("non-greedy", "G", false, "non-greedy mode, faster but may miss motifs overlapping with others")
 	locateCmd.Flags().BoolP("gtf", "", false, "output in GTF format")
 	locateCmd.Flags().BoolP("bed", "", false, "output in BED6 format")

seqkit/cmd/seq.go

@@ -74,7 +74,6 @@ var seqCmd = &cobra.Command{
 		rna2dna := getFlagBool(cmd, "rna2dna")
 		color := getFlagBool(cmd, "color")
 		validateSeq := getFlagBool(cmd, "validate-seq")
-		validateSeqLength := getFlagValidateSeqLength(cmd, "validate-seq-length")
 		minLen := getFlagInt(cmd, "min-len")
 		maxLen := getFlagInt(cmd, "max-len")
 		qBase := getFlagPositiveInt(cmd, "qual-ascii-base")
@@ -112,8 +111,6 @@ var seqCmd = &cobra.Command{
 		}
 
 		seq.ValidateSeq = validateSeq
-		seq.ValidateWholeSeq = false
-		seq.ValidSeqLengthThreshold = validateSeqLength
 		seq.ValidSeqThreads = config.Threads
 		seq.ComplementThreads = config.Threads
 
@@ -446,7 +443,6 @@ func init() {
 	seqCmd.Flags().BoolP("rna2dna", "", false, "RNA to DNA")
 	seqCmd.Flags().BoolP("color", "k", false, "colorize sequences - to be piped into \"less -R\"")
 	seqCmd.Flags().BoolP("validate-seq", "v", false, "validate bases according to the alphabet")
-	seqCmd.Flags().IntP("validate-seq-length", "V", 10000, "length of sequence to validate (0 for whole seq)")
 	seqCmd.Flags().IntP("min-len", "m", -1, "only print sequences longer than or equal to the minimum length (-1 for no limit)")
 	seqCmd.Flags().IntP("max-len", "M", -1, "only print sequences shorter than or equal to the maximum length (-1 for no limit)")
 	seqCmd.Flags().IntP("qual-ascii-base", "b", 33, "ASCII BASE, 33 for Phred+33")

seqkit/cmd/version.go

@@ -29,7 +29,7 @@ import (
 )
 
 // VERSION of seqkit
-const VERSION = "2.7.0"
+const VERSION = "2.7.1"
 
 // versionCmd represents the version command
 var versionCmd = &cobra.Command{

seqkit/cmd/watch.go

@@ -73,7 +73,6 @@ var watchCmd = &cobra.Command{
 		_ = logMode
 		fieldsText := getFlagString(cmd, "fields")
 		validateSeq := getFlagBool(cmd, "validate-seq")
-		validateSeqLength := getFlagValidateSeqLength(cmd, "validate-seq-length")
 		qBase := getFlagPositiveInt(cmd, "qual-ascii-base")
 		_ = qBase
 
@@ -148,8 +147,6 @@ var watchCmd = &cobra.Command{
 		}
 
 		seq.ValidateSeq = validateSeq
-		seq.ValidateWholeSeq = false
-		seq.ValidSeqLengthThreshold = validateSeqLength
 		seq.ValidSeqThreads = config.Threads
 		seq.ComplementThreads = config.Threads
 
@@ -285,7 +282,6 @@ func init() {
 	watchCmd.Flags().BoolP("pass", "x", false, "pass through mode (write input to stdout)")
 	watchCmd.Flags().BoolP("log", "L", false, "log10(x+1) transform numeric values")
 	watchCmd.Flags().StringP("fields", "f", "ReadLen", "target fields, available values: ReadLen, MeanQual, GC, GCSkew")
-	watchCmd.Flags().IntP("validate-seq-length", "V", 10000, "length of sequence to validate (0 for whole seq)")
 	watchCmd.Flags().IntP("qual-ascii-base", "b", 33, "ASCII BASE, 33 for Phred+33")
 	watchCmd.Flags().IntP("bins", "B", -1, "number of histogram bins")
 	watchCmd.Flags().IntP("print-freq", "p", -1, "print/report after this many records (-1 for print after EOF)")