lederhosen 1.2.0 → 1.2.1

data/lederhosen.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "1.2.0"
+  s.version = "1.2.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]

data/lib/lederhosen/tasks/get_reps.rb

@@ -9,21 +9,31 @@ module Lederhosen
     method_option :output,   :type => :string, :required => true
 
     def get_reps
-      input    = options[:input]
+      inputs   = Dir[options[:input]]
       database = options[:database]
       output   = options[:output]
 
       taxa = Set.new
 
-      ohai "getting representative database sequences from #{database} using #{input} clusters and saving to #{output}"
+      ohai "getting representative database sequences from #{database} using #{inputs} clusters and saving to #{output}"
 
       # parse uc file, get list of taxa we need to get
       # full sequences for from the database
-      File.open(input).each do |line|
-        header = parse_usearch_line(line.strip)
-        taxa << header[:original] rescue nil
+      total_bytes = inputs.map { |x| File.size(x) }.inject(:+)
+      pbar = ProgressBar.new 'reading uc(s)', total_bytes
+
+      inputs.each do |input|
+        File.open(input) do |handle|
+          handle.each do |line|
+            pbar.inc line.unpack('*C').size
+            header = parse_usearch_line(line.strip)
+            taxa << header[:original] rescue nil
+          end
+        end
       end
 
+      pbar.finish
+
       ohai "found #{taxa.size} representative sequences"
 
       # print representative sequences from database

data/lib/lederhosen/version.rb

@@ -3,7 +3,7 @@ module Lederhosen
     MAJOR = 1
     MINOR = 2
     CODENAME = 'Regenmantel' # changes for minor versions
-    PATCH = 0
+    PATCH = 1
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/readme.md

@@ -79,3 +79,14 @@ lederhosen otu_table \
 This will create the files:
 
     otu_table.domain.csv, ..., otu_table.species.csv
+
+### Get representative sequences
+
+You can get the representative sequences for each cluster using the `get_reps` tasks. This will extract the representative sequence from
+the __database__ you ran usearch with. Make sure you use the same database that you used when running usearch.
+
+    lederhosen get_reps --input=clusters.uc --database=taxcollector.fa --output=representatives.fasta
+
+You can get the representatives from more than one cluster file using a glob:
+
+    lederhosen get_reps --input=*.uc --database=taxcollector.fa --output=representatives.fasta

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lederhosen
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.1
   prerelease: 
 platform: ruby
 authors:
@@ -159,7 +159,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2175708922821992201
+      hash: -2571588270597711944
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: