diff --git a/README.md b/README.md index 64c9a30..d3e8f34 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,11 @@ -# TaxonKit - NCBI Taxonomy Toolkit +# TaxonKit - Crossplatform and Efficient NCBI Taxonomy Toolkit +**Documents:** [http://bioinf.shenwei.me/taxonkit](http://bioinf.shenwei.me/taxonkit) +([**Usage**](http://bioinf.shenwei.me/taxonkit/usage/)) + +**Source code:** [https://github.com/shenwei356/taxonkit](https://github.com/shenwei356/taxonkit) +[![GitHub stars](https://img.shields.io/github/stars/shenwei356/taxonkit.svg?style=social&label=Star&?maxAge=2592000)](https://github.com/shenwei356/taxonkit) +[![license](https://img.shields.io/github/license/shenwei356/taxonkit.svg?maxAge=2592000)](https://github.com/shenwei356/taxonkit/blob/master/LICENSE) **Latest version:** [![Latest Version](https://img.shields.io/github/release/shenwei356/taxonkit.svg?style=flat?maxAge=86400)](https://github.com/shenwei356/taxonkit/releases) [![Github Releases](https://img.shields.io/github/downloads/shenwei356/taxonkit/latest/total.svg?maxAge=3600)](http://bioinf.shenwei.me/taxonkit/download/) diff --git a/doc/docs/download.md b/doc/docs/download.md index 430773c..b867b6e 100644 --- a/doc/docs/download.md +++ b/doc/docs/download.md @@ -18,10 +18,6 @@ Links: [taxonkit_linux_386.tar.gz](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_386.tar.gz) - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/taxonkit/latest/taxonkit_linux_amd64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_amd64.tar.gz) [taxonkit_linux_amd64.tar.gz](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_amd64.tar.gz) - - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/taxonkit/latest/taxonkit_linux_arm.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_arm.tar.gz) - [taxonkit_linux_arm.tar.gz](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_arm.tar.gz) - - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/taxonkit/latest/taxonkit_linux_arm64.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_arm64.tar.gz) - [taxonkit_linux_arm64.tar.gz](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_linux_arm64.tar.gz) - **Mac OS X** - [![Github Releases (by Asset)](https://img.shields.io/github/downloads/shenwei356/taxonkit/latest/taxonkit_darwin_386.tar.gz.svg?maxAge=3600)](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_darwin_386.tar.gz) [taxonkit_darwin_386.tar.gz](https://github.com/shenwei356/taxonkit/releases/download/v0.1/taxonkit_darwin_386.tar.gz) @@ -65,28 +61,26 @@ For Go developer, just one command: ## Previous Versions -- +
- + diff --git a/doc/docs/usage.md b/doc/docs/usage.md index a37b796..5e52635 100644 --- a/doc/docs/usage.md +++ b/doc/docs/usage.md @@ -61,7 +61,7 @@ Flags: Examples -1. default usage +1. Default usage $ taxonkit list --nodes nodes.dmp --ids 9605 9605 @@ -70,7 +70,7 @@ Examples 741158 1425170 -1. change ident, the list could be used to extract sequences from BLAST database with `blastdbcmd` +1. Removing indent. The list could be used to extract sequences from BLAST database with `blastdbcmd` $ taxonkit list --nodes nodes.dmp --ids 9605 --indent "" 9605 @@ -79,7 +79,16 @@ Examples 741158 1425170 -1. adding names + **Performance:** Time and memory usage for whole taxon tree: + + $ # emptying the buffers cache + $ su -c "free && sync && echo 3 > /proc/sys/vm/drop_caches && free" + + $ memusg -t taxonkit list --nodes nodes.dmp --ids 1 --indent "" > t0.txt + elapsed time: 2.987s + peak rss: 82.79 MB + +1. Adding names $ taxonkit list --nodes nodes.dmp --names names.dmp --ids 9605 9605 [genus] Homo @@ -88,27 +97,35 @@ Examples 741158 [subspecies] Homo sapiens ssp. Denisova 1425170 [species] Homo heidelbergensis + **Performance:** Time and memory usage for whole taxon tree: + + $ # emptying the buffers cache + $ su -c "free && sync && echo 3 > /proc/sys/vm/drop_caches && free" + + $ memusg -t taxonkit list --nodes nodes.dmp --names names.dmp --ids 1 > t1.txt + elapsed time: 9.825s + peak rss: 648.65 MB + +
- + diff --git a/doc/site b/doc/site index 9158b05..30163e2 160000 --- a/doc/site +++ b/doc/site @@ -1 +1 @@ -Subproject commit 9158b051d23796fcdce5bdf2f78cb8ee0971e0e2 +Subproject commit 30163e243813a487663e63caabc2337c8ef51c7a diff --git a/taxonkit/cmd/root.go b/taxonkit/cmd/root.go index 00e988a..7f2817c 100644 --- a/taxonkit/cmd/root.go +++ b/taxonkit/cmd/root.go @@ -39,6 +39,7 @@ Version: %s Author: Wei Shen Source code: https://github.com/shenwei356/taxonkit +Documents : http://bioinf.shenwei.me/taxonkit Dataset: diff --git a/taxonkit/main.go b/taxonkit/main.go index 49311a2..04ea2af 100644 --- a/taxonkit/main.go +++ b/taxonkit/main.go @@ -22,6 +22,7 @@ package main import ( "os" + // "runtime/pprof" "github.com/op/go-logging" "github.com/shenwei356/taxonkit/taxonkit/cmd" @@ -39,8 +40,15 @@ func init() { } func main() { + // go tool pprof ./taxonkit pprof // f, _ := os.Create("pprof") // pprof.StartCPUProfile(f) // defer pprof.StopCPUProfile() + cmd.Execute() + + // go tool pprof --alloc_space ./taxonkit mprof + // f2, _ := os.Create("mprof") + // pprof.WriteHeapProfile(f2) + // defer f2.Close() }