v0.4.1

CHANGES.md

@@ -1,3 +1,5 @@
+- v0.4.1
+    - Better writing and reading performance
 - v0.4.0
     - **Binary serialization format changed.**
     - new command `unikmer sort`: sort binary files

README.md

@@ -113,7 +113,7 @@ optionally compressed in gzip format with extension of `.unik`.
 ![A.muciniphila-ATCC_BAA-835.fasta.gz.cr.tsv.png](testdata/A.muciniphila-ATCC_BAA-835.fasta.gz.cr.tsv.png)
 
 label           |encoded-kmer<sup>a</sup>|gzip-compressed<sup>b</sup>|compact-format<sup>c</sup>|sorted<sup>d</sup>|comment
-:---------------|:-----------------------|:--------------------------|:-------------------------|:-----------------|:------------------------------------------------------
+:---------------|:----------------------:|:-------------------------:|:------------------------:|:----------------:|:------------------------------------------------------
 `plain`         |                        |                           |                          |                  |plain text
 `plain.gz`      |                        |✔                          |                          |                  |gzipped plain text
 `.unik`         |✔                       |✔                          |                          |                  |gzipped encoded kmer in fixed-length byte array

unikmer/cmd/count.go

@@ -224,5 +224,5 @@ func init() {
 	countCmd.Flags().IntP("kmer-len", "k", 0, "Kmer length")
 	countCmd.Flags().BoolP("circular", "", false, "circular genome")
 	countCmd.Flags().BoolP("canonical", "K", false, "only keep the canonical Kmers")
-	countCmd.Flags().BoolP("sort", "s", false, "sort Kmers, this reduces file size, you can even disable gzip compression by flag -C/--no-compress")
+	countCmd.Flags().BoolP("sort", "s", false, helpSort)
 }

unikmer/cmd/diff.go

@@ -499,5 +499,5 @@ func init() {
 	RootCmd.AddCommand(diffCmd)
 
 	diffCmd.Flags().StringP("out-prefix", "o", "-", `out file prefix ("-" for stdout)`)
-	diffCmd.Flags().BoolP("sort", "s", false, "sort Kmers, this reduces file size, you can even disable gzip compression by flag -C/--no-compress")
+	diffCmd.Flags().BoolP("sort", "s", false, helpSort)
 }

unikmer/cmd/inter.go

@@ -327,5 +327,5 @@ func init() {
 	RootCmd.AddCommand(interCmd)
 
 	interCmd.Flags().StringP("out-prefix", "o", "-", `out file prefix ("-" for stdout)`)
-	interCmd.Flags().BoolP("sort", "s", false, "sort Kmers, this reduces file size, you can even disable gzip compression by flag -C/--no-compress")
+	interCmd.Flags().BoolP("sort", "s", false, helpSort)
 }

unikmer/cmd/root.go

@@ -73,3 +73,5 @@ func init() {
 	RootCmd.PersistentFlags().BoolP("compact", "c", false, "write more compact binary file with little loss of speed")
 	RootCmd.PersistentFlags().StringP("infile-list", "i", "", "file of input files list (one file per line), if given, files from cli arguments are ignored")
 }
+
+const helpSort = "sort Kmers, this significantly reduce file size. You can even disable gzip compression by flag -C/--no-compress. This flag overwrites global option -c/--compact"

unikmer/cmd/union.go

@@ -201,5 +201,5 @@ func init() {
 	RootCmd.AddCommand(unionCmd)
 
 	unionCmd.Flags().StringP("out-prefix", "o", "-", `out file prefix ("-" for stdout)`)
-	unionCmd.Flags().BoolP("sort", "s", false, "sort Kmers, this reduces file size, you can even disable gzip compression by flag -C/--no-compress")
+	unionCmd.Flags().BoolP("sort", "s", false, helpSort)
 }

unikmer/cmd/version.go

@@ -29,7 +29,7 @@ import (
 )
 
 // VERSION is the version
-var VERSION = "0.4.0"
+var VERSION = "0.4.1"
 
 // versionCmd represents the version command
 var versionCmd = &cobra.Command{