v0.3.6

shenwei356 · Nov 3, 2016 · 4210208 · 4210208
1 parent 3cd6bb1
commit 4210208
Show file tree

Hide file tree

Showing 6 changed files with 99 additions and 36 deletions.
diff --git a/README.md b/README.md
@@ -93,7 +93,7 @@ Categories          |Features               |seqkit  |fasta_utilities|fastx_tool
 
 Go to [Download Page](http://bioinf.shenwei.me/seqkit/download) for more download options and changelogs.
 
-`seqkit` is implemented in [Golang](https://golang.org/) programming language,
+`SeqKit` is implemented in [Go](https://golang.org/) programming language,
  executable binary files **for most popular operating systems** are freely available
   in [release](https://github.com/shenwei356/seqkit/releases) page.
 

diff --git a/doc/docs/download.md b/doc/docs/download.md
@@ -1,49 +1,49 @@
 # Download
 
-SeqKit is implemented in [Golang](https://golang.org/) programming language,
+SeqKit is implemented in [Go](https://golang.org/) programming language,
  executable binary files **for most popular operating systems** are freely available
   in [release](https://github.com/shenwei356/seqkit/releases) page.
 
 ## Latest Version
 
-[SeqKit v0.3.5](https://github.com/shenwei356/seqkit/releases/tag/v0.3.5)
-[![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v0.3.5/total.svg)](https://github.com/shenwei356/seqkit/releases/download/v0.3.4.1)
+[SeqKit v0.3.6](https://github.com/shenwei356/seqkit/releases/tag/v0.3.6)
+[![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v0.3.6/total.svg)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6)
 
-- fig bug of `seqkit grep`: flag `-i` (`--ignore-case`) did not work when not using regular expression
+- add new feature for `seqkit grep`: new flag `-R` (`--region`) for specifing sequence region for searching.
 
 ***64-bit versions are highly recommended.***
 
 ### Links
 
 - **Linux**
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_386.tar.gz)
-    [seqkit_linux_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_386.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_amd64.tar.gz)
-    [seqkit_linux_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_amd64.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_arm.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_arm.tar.gz)
-    [seqkit_linux_arm.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_linux_arm.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_386.tar.gz)
+    [seqkit_linux_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_386.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_amd64.tar.gz)
+    [seqkit_linux_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_amd64.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_linux_arm.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_arm.tar.gz)
+    [seqkit_linux_arm.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_linux_arm.tar.gz)
 - **Mac OS X**
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_darwin_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_darwin_386.tar.gz)
-    [seqkit_darwin_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_darwin_386.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_darwin_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_darwin_amd64.tar.gz)
-    [seqkit_darwin_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_darwin_amd64.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_darwin_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_darwin_386.tar.gz)
+    [seqkit_darwin_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_darwin_386.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_darwin_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_darwin_amd64.tar.gz)
+    [seqkit_darwin_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_darwin_amd64.tar.gz)
 - **Windows**
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_windows_386.exe.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_windows_386.exe.tar.gz)
-    [seqkit_windows_386.exe.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_windows_386.exe.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_windows_amd64.exe.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_windows_amd64.exe.tar.gz)
-    [seqkit_windows_amd64.exe.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_windows_amd64.exe.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_windows_386.exe.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_windows_386.exe.tar.gz)
+    [seqkit_windows_386.exe.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_windows_386.exe.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_windows_amd64.exe.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_windows_amd64.exe.tar.gz)
+    [seqkit_windows_amd64.exe.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_windows_amd64.exe.tar.gz)
 - **FreeBSD**
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_386.tar.gz)
-    [seqkit_freebsd_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_386.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_amd64.tar.gz)
-    [seqkit_freebsd_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_amd64.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_arm.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_arm.tar.gz)
-    [seqkit_freebsd_arm.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_freebsd_arm.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_386.tar.gz)
+    [seqkit_freebsd_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_386.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_amd64.tar.gz)
+    [seqkit_freebsd_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_amd64.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_freebsd_arm.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_arm.tar.gz)
+    [seqkit_freebsd_arm.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_freebsd_arm.tar.gz)
 - **OpenBSD**
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_openbsd_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_openbsd_386.tar.gz)
-    [seqkit_openbsd_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_openbsd_386.tar.gz)
-    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_openbsd_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_openbsd_amd64.tar.gz)
-    [seqkit_openbsd_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.5/seqkit_openbsd_amd64.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_openbsd_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_openbsd_386.tar.gz)
+    [seqkit_openbsd_386.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_openbsd_386.tar.gz)
+    - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/seqkit/latest/seqkit_openbsd_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_openbsd_amd64.tar.gz)
+    [seqkit_openbsd_amd64.tar.gz](https://github.com/shenwei356/seqkit/releases/download/v0.3.6/seqkit_openbsd_amd64.tar.gz)
 
 ### Mirror site for Chinese users
 
@@ -90,6 +90,10 @@ For Go developer, just one command:
     go get -u github.com/shenwei356/seqkit/seqkit
 
 ## Release History
+
+- [SeqKit v0.3.5](https://github.com/shenwei356/seqkit/releases/tag/v0.3.5)
+[![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v0.3.5/total.svg)](https://github.com/shenwei356/seqkit/releases/download/v0.3.5)
+    - fig bug of `seqkit grep`: flag `-i` (`--ignore-case`) did not work when not using regular expression
 - [SeqKit v0.3.4.1](https://github.com/shenwei356/seqkit/releases/tag/v0.3.4.1)
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v0.3.4.1/total.svg)](https://github.com/shenwei356/seqkit/releases/download/v0.3.4.1)
     - improve performance of reading (~10%) and writing (100%) gzip-compressed file

diff --git a/doc/docs/usage.md b/doc/docs/usage.md
@@ -99,7 +99,7 @@ Usage
 ```
 SeqKit -- a cross-platform and ultrafast toolkit for FASTA/Q file manipulation
 
-Version: 0.3.4.1
+Version: 0.3.6
 
 Author: Wei Shen <shenwei356@gmail.com>
 
@@ -635,6 +635,22 @@ Usage
 ```
 search sequences by pattern(s) of name or sequence motifs
 
+You can specify the sequence region for searching with flag -R/--region.
+The definition of region is 1-based and with some custom design.
+
+Examples:
+
+ 1-based index    1 2 3 4 5 6 7 8 9 10
+negative index    0-9-8-7-6-5-4-3-2-1
+           seq    A C G T N a c g t n
+           1:1    A
+           2:4      C G T
+         -4:-2                c g t
+         -4:-1                c g t n
+         -1:-1                      n
+          2:-2      C G T N a c g t
+          1:-1    A C G T N a c g t n
+
 Usage:
   seqkit grep [flags]
 
@@ -645,8 +661,9 @@ Flags:
       --delete-matched        delete matched pattern to speedup
   -i, --ignore-case           ignore case
   -v, --invert-match          invert the sense of matching, to select non-matching records
-  -p, --pattern value         search pattern (multiple values supported) (default [])
+  -p, --pattern stringSlice   search pattern (multiple values supported)
   -f, --pattern-file string   pattern file
+  -R, --region string         specify sequence region for searching. e.g 1:12 for first 12 bases, -12:-1 for last 12 bases
   -r, --use-regexp            patterns are regular expression
 
 ```
@@ -694,6 +711,9 @@ Examples
 
         $ zcat hairpin.fa.gz | seqkit grep -s -r -i -p TT[CG]AA
 
+1. Specify sequence regions for searching. e.g., leading 30 bases.
+
+        $ seqkit grep -s -R 1:30 -i -r -p GCTGG
 
 ## locate
 

diff --git a/doc/site b/doc/site
diff --git a/seqkit/cmd/grep.go b/seqkit/cmd/grep.go
@@ -25,6 +25,7 @@ import (
 	"io"
 	"regexp"
 	"runtime"
+	"strconv"
 	"strings"
 
 	"github.com/shenwei356/bio/seq"
@@ -38,9 +39,14 @@ import (
 var grepCmd = &cobra.Command{
 	Use:   "grep",
 	Short: "search sequences by pattern(s) of name or sequence motifs",
-	Long: `search sequences by pattern(s) of name or sequence motifs
+	Long: fmt.Sprintf(`search sequences by pattern(s) of name or sequence motifs
 
-`,
+You can specify the sequence region for searching with flag -R/--region.
+The definition of region is 1-based and with some custom design.
+
+Examples:
+%s
+`, regionExample),
 	Run: func(cmd *cobra.Command, args []string) {
 		config := getConfigs(cmd)
 		alphabet := config.Alphabet
@@ -60,6 +66,7 @@ var grepCmd = &cobra.Command{
 		byName := getFlagBool(cmd, "by-name")
 		ignoreCase := getFlagBool(cmd, "ignore-case")
 		degenerate := getFlagBool(cmd, "degenerate")
+		region := getFlagString(cmd, "region")
 
 		if len(pattern) == 0 && patternFile == "" {
 			checkError(fmt.Errorf("one of flags -p (--pattern) and -f (--pattern-file) needed"))
@@ -68,6 +75,31 @@ var grepCmd = &cobra.Command{
 			checkError(fmt.Errorf("could not give both flags -d (--degenerat) and -r (--use-regexp)"))
 		}
 
+		var start, end int
+		var err error
+		var limitRegion bool
+		if region != "" {
+			limitRegion = true
+			if !bySeq {
+				log.Infof("when flag -R (--region) given, flag -s (--by-seq) is automatically on")
+				bySeq = true
+			}
+			if !reRegion.MatchString(region) {
+				checkError(fmt.Errorf(`invalid region: %s. type "seqkit grep -h" for more examples`, region))
+			}
+			r := strings.Split(region, ":")
+			start, err = strconv.Atoi(r[0])
+			checkError(err)
+			end, err = strconv.Atoi(r[1])
+			checkError(err)
+			if start == 0 || end == 0 {
+				checkError(fmt.Errorf("both start and end should not be 0"))
+			}
+			if start < 0 && end > 0 {
+				checkError(fmt.Errorf("when start < 0, end should not > 0"))
+			}
+		}
+
 		files := getFileList(args)
 
 		// prepare pattern
@@ -156,7 +188,11 @@ var grepCmd = &cobra.Command{
 				if byName {
 					subject = record.Name
 				} else if bySeq {
-					subject = record.Seq.Seq
+					if limitRegion {
+						subject = record.Seq.SubSeq(start, end).Seq
+					} else {
+						subject = record.Seq.Seq
+					}
 				} else {
 					subject = record.ID
 				}
@@ -210,4 +246,7 @@ func init() {
 	grepCmd.Flags().BoolP("by-seq", "s", false, "match by seq")
 	grepCmd.Flags().BoolP("ignore-case", "i", false, "ignore case")
 	grepCmd.Flags().BoolP("degenerate", "d", false, "pattern/motif contains degenerate base")
+	grepCmd.Flags().StringP("region", "R", "", "specify sequence region for searching. "+
+		"e.g 1:12 for first 12 bases, -12:-1 for last 12 bases")
+
 }
diff --git a/seqkit/cmd/helper.go b/seqkit/cmd/helper.go
@@ -43,7 +43,7 @@ import (
 )
 
 // VERSION of seqkit
-const VERSION = "0.3.5"
+const VERSION = "0.3.6"
 
 func checkError(err error) {
 	if err != nil {