bio-executables 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5589dde11154d41e1b5e57ae7a95881543b4c2f8
+  data.tar.gz: ec8e45140eda4d7a9cff61fdee7f25f4d7b59df6
+SHA512:
+  metadata.gz: 548567973ee72e744c572498e3c063c9cdfebcc20325ecbbfb5cb024f1ebee12666fd39c58acd67fe74914c2878350a0da7af17cfb69b940122448591840ae2b
+  data.tar.gz: a01c3a332a2ee4a7d50234300a46307a740afe8bfd20b8ca19ed771e7f53fec323c15ac6ad091cf59a269500fc889aceca6a2479442e7a2adab82c142897a0db

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/rdoc/
+/pkg/
+/spec/reports/
+/tmp/

data/BSDL

@@ -0,0 +1,22 @@
+Copyright (C) 1993-2013 Yukihiro Matsumoto. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+1. Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright
+notice, this list of conditions and the following disclaimer in the
+documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGE.

data/COPYING

@@ -0,0 +1,56 @@
+BioRuby is copyrighted free software by Toshiaki Katayama <k@bioruby.org>.
+You can redistribute it and/or modify it under either the terms of the
+2-clause BSDL (see the file BSDL), or the conditions below:
+
+  1. You may make and give away verbatim copies of the source form of the
+     software without restriction, provided that you duplicate all of the
+     original copyright notices and associated disclaimers.
+
+  2. You may modify your copy of the software in any way, provided that
+     you do at least ONE of the following:
+
+       a) place your modifications in the Public Domain or otherwise
+          make them Freely Available, such as by posting said
+	  modifications to Usenet or an equivalent medium, or by allowing
+	  the author to include your modifications in the software.
+
+       b) use the modified software only within your corporation or
+          organization.
+
+       c) give non-standard binaries non-standard names, with
+          instructions on where to get the original software distribution.
+
+       d) make other distribution arrangements with the author.
+
+  3. You may distribute the software in object code or binary form,
+     provided that you do at least ONE of the following:
+
+       a) distribute the binaries and library files of the software,
+	  together with instructions (in the manual page or equivalent)
+	  on where to get the original distribution.
+
+       b) accompany the distribution with the machine-readable source of
+	  the software.
+
+       c) give non-standard binaries non-standard names, with
+          instructions on where to get the original software distribution.
+
+       d) make other distribution arrangements with the author.
+
+  4. You may modify and include the part of the software into any other
+     software (possibly commercial).  But some files in the distribution
+     are not written by the author, so that they are not under these terms.
+
+     For the list of those files and their copying conditions, see the
+     file LEGAL.
+
+  5. The scripts and library files supplied as input to or produced as 
+     output from the software do not automatically fall under the
+     copyright of the software, but belong to whomever generated them, 
+     and may be sold commercially, and may be aggregated with this
+     software.
+
+  6. THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR
+     IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+     WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+     PURPOSE.

data/COPYING.ja

@@ -0,0 +1,51 @@
+本プログラムはフリーソフトウェアです．2-clause BSDL
+または以下に示す条件で本プログラムを再配布できます
+2-clause BSDLについてはBSDLファイルを参照して下さい．
+
+  1. 複製は制限なく自由です．
+
+  2. 以下の条件のいずれかを満たす時に本プログラムのソースを
+     自由に変更できます．
+
+     (a) ネットニューズにポストしたり，作者に変更を送付する
+         などの方法で，変更を公開する．
+
+     (b) 変更した本プログラムを自分の所属する組織内部だけで
+         使う．
+
+     (c) 変更点を明示したうえ，ソフトウェアの名前を変更する．
+         そのソフトウェアを配布する時には変更前の本プログラ
+         ムも同時に配布する．または変更前の本プログラムのソー
+         スの入手法を明示する．
+
+     (d) その他の変更条件を作者と合意する．
+
+  3. 以下の条件のいずれかを満たす時に本プログラムをコンパイ
+     ルしたオブジェクトコードや実行形式でも配布できます．
+
+     (a) バイナリを受け取った人がソースを入手できるように，
+         ソースの入手法を明示する．
+
+     (b) 機械可読なソースコードを添付する．
+
+     (c) 変更を行ったバイナリは名前を変更したうえ，オリジナ
+         ルのソースコードの入手法を明示する．
+
+     (d) その他の配布条件を作者と合意する．
+
+  4. 他のプログラムへの引用はいかなる目的であれ自由です．た
+     だし，本プログラムに含まれる他の作者によるコードは，そ
+     れぞれの作者の意向による制限が加えられる場合があります．
+
+     それらファイルの一覧とそれぞれの配布条件などに付いては
+     LEGALファイルを参照してください．
+
+  5. 本プログラムへの入力となるスクリプトおよび，本プログラ
+     ムからの出力の権利は本プログラムの作者ではなく，それぞ
+     れの入出力を生成した人に属します．また，本プログラムに
+     組み込まれるための拡張ライブラリについても同様です．
+
+  6. 本プログラムは無保証です．作者は本プログラムをサポート
+     する意志はありますが，プログラム自身のバグあるいは本プ
+     ログラムの実行などから発生するいかなる損害に対しても責
+     任を持ちません．

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in bio-executables.gemspec
+gemspec

data/LEGAL

@@ -0,0 +1,8 @@
+LEGAL NOTICE INFORMATION
+------------------------
+
+All the files in this distribution are covered under either the Ruby's
+license (see the file COPYING) or public-domain except some files
+mentioned below.
+
+(no files)

data/README.md

@@ -0,0 +1,63 @@
+# BioRuby Executables
+
+[![Build Status](https://secure.travis-ci.org/bioruby/bio-executables.png)](http://travis-ci.org/bioruby/bio-executables)
+
+bio-executables is a collection of miscellaneous utilities for bioinformatics
+that were formerly part of the [BioRuby](http://bioruby.org/) core ("bio" gem).
+Because of reducing complexity, they were moved to this gem.
+
+This code has historically been part of
+[the BioRuby gem](https://github.com/bioruby/bioruby),
+but has been split into its own gem as part of an effort to
+[modularize](http://bioruby.open-bio.org/wiki/Plugins) BioRuby.
+bio-executables and many more plugins are available at
+[biogems.info](http://www.biogems.info/).
+
+
+## Requirements
+
+bio-executables uses `bio` and `bio-old-biofetch-emulator` gems.
+They will automatically be installed during the installation of
+`bio-executables` in normal cases.
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'bio-executables'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install bio-executables
+
+## Usage
+
+See BioRuby documentation at https://github.com/bioruby/documentation
+
+## Development
+
+To install this gem onto your local machine, run `bundle exec rake install`.
+To release a new version, update the version number in `version.rb`,
+and then run `bundle exec rake release`, which will create a git tag
+for the version, push git commits and tags, and push the `.gem` file
+to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at
+https://github.com/bioruby/bioruby-executables
+
+## Cite
+
+If you use this software, please cite one of
+
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+

data/Rakefile

@@ -0,0 +1,20 @@
+require "bundler/gem_tasks"
+require 'rdoc/task'
+require 'rake/testtask'
+
+task :default => :test
+
+Rake::TestTask.new do |t|
+  t.test_files = FileList["test/**/test_*.rb"]
+end
+
+Rake::RDocTask.new do |r|
+  r.rdoc_dir = "rdoc"
+  r.rdoc_files.include("README.md",
+                       "COPYING", "COPYING.ja", "BSDL", "LEGAL",
+                       "lib/**/*.rb")
+  r.main = "README.md"
+  r.options << '--title' << 'BioRuby Executables API documentation'
+  r.options << '--line-numbers'
+end
+

data/bin/br_biofetch.rb

@@ -0,0 +1,71 @@
+#!/usr/bin/env ruby
+#
+# = biofetch - BioFetch client
+#
+# Copyright::   Copyright (C) 2002
+#               Toshiaki Katayama <k@bioruby.org>
+# License::     The Ruby License
+#
+#
+
+begin
+  require 'rubygems'
+rescue LoadError
+end
+
+require 'bio/io/fetch'
+
+def require_bio_old_biofetch_emulator(mandatory = true)
+  begin
+    require 'bio-old-biofetch-emulator'
+  rescue LoadError
+    if mandatory then
+      $stderr.puts "Error: please install bio-old-biofetch-emulator gem."
+      exit 1
+    end
+  end
+end
+
+def default_url
+  'http://bioruby.org/cgi-bin/biofetch.rb'
+end
+
+def another_url
+  'http://www.ebi.ac.uk/cgi-bin/dbfetch'
+end
+
+def usage
+  puts "#{$0} [-s[erver] #{another_url}] db id [style] [format]"
+  puts "  server : URL of the BioFetch CGI (default is #{default_url})"
+  puts "      db : database name (embl, genbank, etc.)"
+  puts "      id : entry id"
+  puts "   style : 'raw' or 'html' (default is 'raw')"
+  puts "  format : change the output format ('default', 'fasta', etc.)"
+end
+
+if ARGV.empty? or ARGV[0] =~ /^--?h/
+  usage
+  exit 1
+end
+
+case ARGV[0]
+when /^--?s/				# User specified server
+  require_bio_old_biofetch_emulator(false)
+  ARGV.shift
+  serv = Bio::Fetch.new(ARGV.shift)
+  puts serv.fetch(*ARGV)
+when /^--?e/				# EBI server
+  ARGV.shift
+  serv = Bio::Fetch.new(another_url)
+  puts serv.fetch(*ARGV)
+when /^--?r/				# BioRuby server
+  require_bio_old_biofetch_emulator
+  ARGV.shift
+  serv = Bio::Fetch.new(default_url)
+  puts serv.fetch(*ARGV)
+else					# Default server
+  require_bio_old_biofetch_emulator
+  puts Bio::Fetch.query(*ARGV)
+end
+
+

data/bin/br_bioflat.rb

@@ -0,0 +1,293 @@
+#!/usr/bin/env ruby
+# 
+# = bioflat - OBDA flat file indexer (executable)
+# 
+# Copyright::   Copyright (C) 2002
+#               Naohisa Goto <ng@bioruby.org>
+# License::     The Ruby License
+#
+# $Id: br_bioflat.rb,v 1.17 2007/04/05 23:35:39 trevor Exp $ 
+# 
+
+require 'bio'
+
+def usage
+  print <<EOM
+Search:
+  #{$0} [--search] [options...] [DIR/]DBNAME KEYWORDS
+or
+  #{$0} [--search] --location DIR --dbname DBNAME [options...] KEYWORDS
+
+Search options:
+  --namespace NAME       set serch namespace to NAME
+  (or --name NAME)         You can set this option many times to specify
+                           more than one namespace.
+
+Create index:
+  #{$0} --create --location DIR --dbname DBNAME [--format <genbank|embl|fasta>] [options...] [--files] FILES
+Update index:
+  #{$0} --update --location DIR --dbname DBNAME [options...] [--files] FILES
+
+Create index options:
+  --primary=UNIQUE       set primary namespece to UNIQUE
+                           Default primary/secondary namespaces depend on
+                           each format of flatfiles.
+  --secondary=KEY        set secondary namespaces.
+                           You may use this option many times to specify
+                           more than one namespace.
+  --add-secondary=KEY    add secondary namespaces to default specification.
+                           You can use this option many times.
+
+Options only valid for --create (or --update) --type flat:
+  --sort=/path/to/sort   use external sort program (e.g. /usr/bin/sort)
+  --sort=BUILTIN         use builtin sort routine
+                         (default: /usr/bin/sort or BUILTIN)
+  --env=/path/to/env     use env program to run sort (default: /usr/bin/env)
+  --env-arg=XXXXXX       argument given to the env program (default: LC_ALL=C)
+                         (multiple --env-arg=XXXXXX can be specified)
+
+Options only valid for --update:
+  --renew                re-read all flatfiles and update whole index
+
+Backward compatibility:
+  --makeindex DIR/DBNAME
+      same as --create --type flat --location DIR --dbname DBNAME
+  --makeindexBDB DIR/DBNAME
+      same as --create --type bdb  --location DIR --dbname DBNAME
+  --format=CLASS
+      instead of genbank|embl|fasta, specifing a class name is allowed
+
+Show namespaces:
+  #{$0} --show-namespaces [--location DIR --dbname DBNAME] [DIR/DBNAME]
+or
+  #{$0} --show-namespaces [--format=CLASS]
+or
+  #{$0} --show-namespaces --files file
+
+EOM
+
+end
+
+
+def do_index(mode = :create)
+  case ARGV[0]
+  when /^\-\-?make/
+    dbpath = ARGV[1]
+    args = ARGV[2..-1]
+    is_bdb = nil
+  when /^\-\-?make.*bdb/i
+    dbname = ARGV[1]
+    args = ARGV[2..-1]
+    is_bdb = Bio::FlatFileIndex::MAGIC_BDB
+  when /^\-\-create/, /^\-\-update/
+    args = ARGV[1..-1]
+  else
+    usage
+  end
+
+  options = {}
+
+  while args.first =~ /^\-/
+    case x = args.shift
+
+    # OBDA stuff
+
+    when /^\-\-?format$/
+      args.shift
+      format = nil		# throw this f*ckin' mess for auto detect :)
+    when /^\-\-?location/
+      location = args.shift.chomp('/')
+    when /^\-\-?dbname/
+      dbname = args.shift
+    when /^\-\-?(index)?type/
+      indextype = args.shift
+      case indextype
+      when /bdb/
+	is_bdb = Bio::FlatFileIndex::MAGIC_BDB
+      when /flat/
+	is_bdb = nil
+      else
+	usage
+      end
+
+    # BioRuby extension
+
+    when /^\-\-?files/i
+      break
+
+    when /^\-\-?format\=(.*)/i
+      format = $1
+
+    when /^\-\-?sort\=(.*)/i
+      options['sort_program'] = $1
+      options['onmemory'] = nil
+    when /^\-\-?no\-?te?mp/i
+      options['onmemory'] = true
+
+    when /^\-\-?env\=(.*)/i
+      options['env_program'] = $1
+
+    when /^\-\-?env-arg(?:ument)?\=(.*)/i
+      options['env_program_arguments'] ||= []
+      options['env_program_arguments'].push $1
+
+    when /^\-\-?primary.*\=(.*)/i
+      options['primary_namespace'] = $1
+
+    when /^\-\-?add-secondary.*\=(.*)/i
+      unless options['additional_secondary_namespaces'] then
+	options['additional_secondary_namespaces'] = []
+      end
+      options['additional_secondary_namespaces'] << $1 if $1.length > 0
+
+    when /^\-\-?secondary.*\=(.*)/i
+      unless options['secondary_namespaces'] then
+	options['secondary_namespaces'] = []
+      end
+      options['secondary_namespaces'] << $1 if $1.length > 0
+
+    when /^\-\-?renew/
+      options['renew'] = true
+
+    else
+      $stderr.print "Warning: ignoring invalid option #{x.inspect}\n"
+    end
+  end
+
+  dbpath = File.join(location, dbname) unless dbpath
+  if mode == :update then
+    Bio::FlatFileIndex::update_index(dbpath, format, options, *args)
+  else
+    Bio::FlatFileIndex::makeindex(is_bdb, dbpath, format, options, *args)
+  end
+end
+
+
+def do_search
+  dbname = nil
+  location = nil
+  names = []
+  while x = ARGV.shift
+    case x
+    when /\A\-\-?search/i
+      #do nothing
+    when /\A\-\-?location/i
+      location = ARGV.shift.to_s.chomp('/')
+    when /\A\-\-?dbname/i
+      dbname = ARGV.shift
+    when /\A\-\-?name(?:space)?(?:\=(.+))?/i
+      if $1 then
+	names << $1
+      elsif x = ARGV.shift
+	names << x
+      end
+    else
+      ARGV.unshift x
+      break
+    end
+  end
+  dbname = ARGV.shift unless dbname
+  dbname = File.join(location, dbname) unless location.to_s.empty?
+  db = Bio::FlatFileIndex.open(dbname)
+  ARGV.each do |key|
+    $stderr.print "Searching for \'#{key}\'...\n"
+    #r = db.search(key)
+    #$stderr.print "OK, #{r.size} entry found\n"
+    #if r.size > 0 then
+    #  print r
+    #end
+    begin
+      if names.empty? then
+	r = db.include?(key)
+      else
+	r = db.include_in_namespaces?(key, *names)
+      end
+    rescue RuntimeError
+      $stderr.print "ERROR: #{$!}\n"
+      next
+    end
+    r = [] unless r
+    $stderr.print "OK, #{r.size} entry found\n"
+    r.each do |i|
+      print db.search_primary(i)
+    end
+  end
+  db.close
+end
+
+
+def do_show_namespaces
+  dbname = nil
+  location = nil
+  files = nil
+  format = nil
+  names = []
+  while x = ARGV.shift
+    case x
+    when /\A\-\-?(show\-)?name(space)?s/i
+      #do nothing
+    when /\A\-\-?location/i
+      location = ARGV.shift.to_s.chomp('/')
+    when /\A\-\-?dbname/i
+      dbname = ARGV.shift
+    when /\A\-\-?format(?:\=(.+))?/i
+      if $1 then
+	format = $1
+      elsif x = ARGV.shift
+	format = x
+      end
+    when /\A\-\-?files/i
+      files = ARGV
+      break
+    else
+      ARGV.unshift x
+      break
+    end
+  end
+  if files then
+    k = nil
+    files.each do |x|
+      k = Bio::FlatFile.autodetect_file(x)
+      break if k
+    end
+    if k then
+      $stderr.print "Format: #{k.to_s}\n"
+      format = k
+    else
+      $stderr.print "ERROR: couldn't determine file format\n"
+      return
+    end
+  end
+  $stderr.print "Namespaces: (first line: primary namespace)\n"
+  if format then
+    parser = Bio::FlatFileIndex::Indexer::Parser.new(format)
+    print parser.primary.name, "\n"
+    puts parser.secondary.keys
+  else
+    dbname = ARGV.shift unless dbname
+    dbname = File.join(location, dbname) unless location.to_s.empty?
+    db = Bio::FlatFileIndex.open(dbname)
+    puts db.namespaces
+    db.close
+  end
+end
+
+if ARGV.size > 1
+  case ARGV[0]
+  when /--make/, /--create/
+    Bio::FlatFileIndex::DEBUG.out = true
+    do_index
+  when /--update/
+    Bio::FlatFileIndex::DEBUG.out = true
+    do_index(:update)
+  when /\A\-\-?(show\-)?name(space)?s/i
+    do_show_namespaces
+  when /--search/
+    do_search
+  else #default is search
+    do_search
+  end
+else
+  usage
+end
+

data/bin/br_biogetseq.rb

@@ -0,0 +1,45 @@
+#!/usr/bin/env ruby
+# 
+# = biogetseq - OBDA sequence data retrieval (executable)
+# 
+# Copyright::   Copyright (C) 2003
+#               Toshiaki Katayama <k@bioruby.org>
+# License::     The Ruby License
+#
+# $Id: br_biogetseq.rb,v 1.4 2007/04/05 23:35:39 trevor Exp $
+# 
+
+require 'bio'
+
+def usage
+  print <<END
+  #{$0} --dbname <dbname> [--namespace <namespace>] entry_id [entry_id]
+END
+  exit 1
+end
+
+if ARGV.size < 3
+  usage
+end
+
+while ARGV.first =~ /^-/
+  case ARGV.shift
+  when /^\-\-format/
+    ARGV.shift
+    raise NotImplementedError
+  when /^\-\-dbname/
+    dbname = ARGV.shift
+  when /^\-\-namespace/
+    namespace = ARGV.shift
+  end
+end
+
+reg = Bio::Registry.new
+db = reg.get_database(dbname)
+if namespace
+  db['namespace'] = namespace
+end
+ARGV.each do |entry|
+  puts db.get_by_id(entry)
+end
+

data/bin/br_pmfetch.rb

@@ -0,0 +1,422 @@
+#!/usr/bin/env ruby
+#
+# = pmfetch - PubMed client
+#
+# Copyright::   Copyright (C) 2004, 2005
+#               Toshiaki Katayama <k@bioruby.org>
+# License::     The Ruby License
+#
+# $Id:$
+#
+
+require 'bio'
+
+PROG_VER  = "Powered by BioRuby #{Bio::BIORUBY_VERSION_ID}"
+PROG_NAME = File.basename($0)
+
+
+require 'getoptlong'
+
+
+### formatting
+
+class String
+  def fill(fill_column = 80, prefix = '', separater = ' ')
+    prefix = ' ' * prefix if prefix.is_a?(Integer)
+    maxlen = fill_column - prefix.length
+    raise "prefix is longer than fill_column" if maxlen <= 0
+
+    cursor = pos = 0
+    lines = []
+    while cursor < self.length
+      line = self[cursor, maxlen]
+      pos = line.rindex(separater)
+      pos = nil if line.length < maxlen
+      if pos
+        len = pos + separater.length
+        lines << self[cursor, len]
+        cursor += len
+      else
+        lines << self[cursor, maxlen]
+        cursor += maxlen
+      end
+    end
+    return lines.join("\n#{prefix}")
+  end
+end
+
+
+module Bio
+  class Reference
+    def report
+      if (num = @authors.size) > 10
+        authors = "#{@authors[0]} et al. (#{num} authors)"
+      elsif num > 4
+        sep = ',' * (num - 1)
+        authors = "#{@authors[0]}#{sep} #{@authors[-1]}"
+      else
+        authors = authors_join(' & ')
+      end
+      journal = "#{@journal} #{@year} #{@volume}(#{@issue}):#{@pages}"
+
+      indent = 8
+      prefix = ' ' * indent
+      [
+        "#{@pages[/\d+/]}".ljust(indent) + "#{@title}".fill(78, indent),
+        authors,
+        "#{journal} [PMID:#{@pubmed}]",
+      ].join("\n#{prefix}")
+    end
+  end
+end
+
+
+class PMFetch
+
+  class Examples < StandardError; end
+  class Version < StandardError; end
+  class Usage < StandardError; end
+
+  ### default options
+
+  def initialize
+    @format = 'rd'
+    @search_opts = {
+      'retmax' => 20,
+    }
+    @query = nil
+    @query_opts = []
+    @pmid_list_only = false
+
+    pmfetch
+  end
+
+
+  ### main
+
+  def pmfetch
+    begin
+      set_options
+      parse_options
+      check_query
+    rescue PMFetch::Examples
+      puts examples
+      exit
+    rescue PMFetch::Version
+      puts version
+      exit
+    rescue PMFetch::Usage
+      puts usage
+      exit
+    rescue GetoptLong::MissingArgument, GetoptLong::InvalidOption
+      puts usage
+      exit
+    end
+
+    list = pm_esearch
+
+    if list.empty?
+      ;
+    elsif @pmid_list_only
+      puts list
+    else
+      pm_efetch(list)
+    end
+  end
+
+
+  ### help
+
+  def usage
+%Q[
+Usage: #{PROG_NAME} [options...] "query string"
+    or #{PROG_NAME} --query "query string" [other options...] 
+
+Options:
+ -q  --query "genome AND virus"  Query string for PubMed search
+ -t  --title "mobile elements"   Title of the article to search
+ -j  --journal "genome res"      Journal title to search
+ -v  --volume #                  Journal volume to search
+ -i  --issue #                   Journal issue to search
+ -p  --page #                    First page number of the article to search
+ -a  --author "Altschul SF"      Author name to search
+ -m  --mesh "SARS virus"         MeSH term to search
+ -f  --format bibtex             Summary output format
+     --pmidlist                  Output only a list of PubMed IDs
+ -n  --retmax #                  Number of articles to retrieve at the maximum
+ -N  --retstart #                Starting number of the articles to retrieve
+ -s  --sort pub+date             Sort method for the summary output
+     --reldate #                 Search articles published within recent # days
+     --mindate YYYY/MM/DD        Search articles published after the date
+     --maxdate YYYY/MM/DD        Search articles published before the date
+     --help                      Output this help, then exit
+     --examples                  Output examples, then exit
+     --version                   Output version number, then exit
+
+Formats:
+ endnote, medline, bibitem, bibtex, report, rd,
+ nature, science, genome_res, genome_biol, nar, current, trends, cell
+
+Sort:
+ author, journal, pub+date, page
+
+See the following pages for the PubMed search options:
+ http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html
+ http://www.ncbi.nlm.nih.gov/entrez/query/static/esearch_help.html
+
+#{version}
+
+]
+  end
+
+  def version
+    PROG_VER
+  end
+
+  def examples
+    DATA.read.gsub('PMFetch', PROG_NAME)
+  end
+
+
+  private
+
+
+  ### options
+
+  def set_options
+    @parser = GetoptLong.new
+
+    @parser.set_options(
+	[ '--query',	'-q',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--title',	'-t',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--journal',	'-j',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--volume',	'-v',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--issue',	'-i',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--page',	'-p',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--author',	'-a',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--mesh',	'-m',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--format',	'-f',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--pmidlist',		GetoptLong::NO_ARGUMENT ],
+	[ '--retmax',	'-n',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--retstart', '-N',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--sort',	'-s',	GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--reldate',		GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--mindate',		GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--maxdate',		GetoptLong::REQUIRED_ARGUMENT ],
+	[ '--examples',		GetoptLong::NO_ARGUMENT ],
+	[ '--help',		GetoptLong::NO_ARGUMENT ],
+	[ '--version',		GetoptLong::NO_ARGUMENT ]
+    )
+  end
+
+  def parse_options
+    @parser.each_option do |optname, optarg|
+      case optname
+      when /--query/
+        @query = optarg
+      when /--title/
+        @query_opts << "#{optarg}[ti]"
+      when /--journal/
+        @query_opts << "#{optarg}[ta]"
+      when /--volume/
+        @query_opts << "#{optarg}[vi]"
+      when /--issue/
+        @query_opts << "#{optarg}[ip]"
+      when /--page/
+        @query_opts << "#{optarg}[pg]"
+      when /--author/
+        @query_opts << "#{optarg}[au]"
+      when /--mesh/
+        @query_opts << "#{optarg}[mh]"
+      when /--format/
+        @format = optarg
+      when /--pmidlist/
+        @pmid_list_only = true
+      when /--examples/
+        raise PMFetch::Examples
+      when /--help/
+        raise PMFetch::Usage
+      when /--version/
+        raise PMFetch::Version
+      when /--sort/
+        @sort = optarg
+        @search_opts["sort"] = @sort unless @sort == "page"
+      else
+        optname.delete!('-')
+        @search_opts[optname] = optarg
+      end
+    end
+  end
+
+
+  ### check query
+
+  def check_query
+    p @query if $DEBUG
+    @query ||= ARGV.join(" ") unless ARGV.empty?
+
+    p @query if $DEBUG
+    @query_str = [ @query, @query_opts ].flatten.compact.join(" AND ")
+
+    p @query_str if $DEBUG
+    if @query_str.empty?
+      raise PMFetch::Usage
+    end
+  end
+
+
+  ### search
+
+  def pm_esearch
+    return Bio::PubMed.esearch(@query_str, @search_opts)
+  end
+
+  def pm_efetch(list)
+    entries = Bio::PubMed.efetch(list)
+
+    if @format == 'medline'
+      medline_format(entries)
+    else
+      entries = parse_entries(entries)
+      if @sort == 'page'
+        entries = sort_entries(entries)
+      end
+      if @format == 'report'
+        report_format(entries)
+      else
+        other_format(entries)
+      end
+    end
+  end
+
+
+  ### output
+
+  def medline_format(entries)
+    entries.each do |entry|
+      puts entry
+      puts '//'
+    end
+  end
+
+  def parse_entries(entries)
+    entries.map { |entry| Bio::MEDLINE.new(entry) }
+  end
+
+  def sort_entries(entries)
+    if RUBY_VERSION > "1.8.0"
+       entries.sort_by { |x|
+         [ x.journal, x.volume.to_i, x.issue.to_i, x.pages.to_i ]
+       }
+    else
+      entries.map { |x|
+        [ x.journal, x.volume.to_i, x.issue.to_i, x.pages.to_i, x ]
+      }.sort { |a, b|
+        a[0..3] <=> b[0..3]
+      }.map { |y|
+        y.pop
+      }
+    end
+  end
+
+  def report_format(entries)
+    entries.each do |entry|
+      puts entry.reference.report
+      puts
+    end
+  end
+
+  def other_format(entries)
+    entries.each do |entry|
+      puts entry.reference.format(@format)
+      puts
+    end
+  end
+
+end
+
+
+PMFetch.new
+
+
+__END__
+
+= Examples : PubMed search
+
+These four lines will do the same job.
+
+  % PMFetch transcription factor
+  % PMFetch "transcription factor"
+  % PMFetch --query "transcription factor"
+  % PMFetch -q "transcription factor"
+
+
+Retrieve max 100 artiecles (20 is a NCBI's default) at a time, use --retmax as
+
+  % PMFetch -q "transcription factor" --retmax 100
+
+and, to retrieve next 100 articles, use --retstart as
+
+  % PMFetch -q "transcription factor" --retmax 100 --retstart 100
+
+
+You can narrow the search target for an issue of the journal.
+
+  % PMFetch --journal development --volume 131 --issue 3  transcription factor
+
+
+Short options are also available.
+
+  % PMFetch -j development -v 131 -i 3  transcription factor
+
+
+Search articles indexed in PubMed within these 90 days.
+
+  % PMFetch -q "transcription factor" --reldate 90
+
+
+Search articles indexed in PubMed during the period of 2001/04/01 to 2001/08/31
+
+  % PMFetch -q "transcription factor" --mindate 2001/04/01 --maxdate 2001/08/31
+
+
+Output format can be changed by --format option.
+
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f report
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f rd
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f endnote
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f medline
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f bibitem
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f bibtex
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f nature
+  % PMFetch -q "transcription factor" -j development -v 131 -i 3 -f science
+
+
+Generate title listings for the journal report meeting (don't forget
+to inclease the number of --retmax for fetching all titles).
+
+  % PMFetch -f report -j development -v 131 -i 3 -n 100
+
+
+Search by author name.
+
+  % PMFetch -a "Karlin S"
+  % PMFetch -a "Koonin EV"
+
+
+Search by MeSH term.
+
+  % PMFetch -m "computational biology"
+  % PMFetch -m "SARS virus"
+
+
+Search by PubMed ID (PMID).
+
+  % PMFetch 12345
+
+
+Output PMID only.
+
+  % PMFetch --pmidlist tardigrada
+
+

data/bio-executables.gemspec

@@ -0,0 +1,30 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "bio-executables/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "bio-executables"
+  spec.version       = Bio::Executables::VERSION
+  spec.authors       = ["BioRuby project"]
+  spec.email         = ["staff@bioruby.org"]
+
+  spec.summary       = %q{BioRuby executables: utilities bundled with BioRuby}
+  spec.description   = %q{BioRuby executables is a collection of miscellaneous utilities for bioinformatics that were formerly part of the BioRuby core ("bio" gem). Because of reducing complexity, they were moved to this gem.}
+  spec.homepage      = "https://github.com/bioruby/bioruby-executables"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "bin"
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "bio", ">= 1.5.1"
+  spec.add_runtime_dependency "bio-old-biofetch-emulator", ">= 0.0.1"
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rdoc", "~> 5"
+  spec.add_development_dependency "test-unit", "~> 3"
+end

data/lib/bio-executables/version.rb

@@ -0,0 +1,5 @@
+module Bio
+  module Executables
+    VERSION = "0.0.0".freeze
+  end
+end

metadata

@@ -0,0 +1,147 @@
+--- !ruby/object:Gem::Specification
+name: bio-executables
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- BioRuby project
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-09-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bio
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.1
+- !ruby/object:Gem::Dependency
+  name: bio-old-biofetch-emulator
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.1
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+description: BioRuby executables is a collection of miscellaneous utilities for bioinformatics
+  that were formerly part of the BioRuby core ("bio" gem). Because of reducing complexity,
+  they were moved to this gem.
+email:
+- staff@bioruby.org
+executables:
+- br_biofetch.rb
+- br_bioflat.rb
+- br_biogetseq.rb
+- br_pmfetch.rb
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- BSDL
+- COPYING
+- COPYING.ja
+- Gemfile
+- LEGAL
+- README.md
+- Rakefile
+- bin/br_biofetch.rb
+- bin/br_bioflat.rb
+- bin/br_biogetseq.rb
+- bin/br_pmfetch.rb
+- bio-executables.gemspec
+- lib/bio-executables/version.rb
+homepage: https://github.com/bioruby/bioruby-executables
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.11
+signing_key: 
+specification_version: 4
+summary: 'BioRuby executables: utilities bundled with BioRuby'
+test_files: []