miga-base 0.3.13.1 → 0.4.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f3dfdd455be947124886bb35a9e6ebc800e63e9eae62d8d61f7e3f647732ebfd
-  data.tar.gz: 536a76534d93cfdd50ea58e7036df5cfc01d6bb28314d42d8f43490b318ad3ee
+  metadata.gz: 37bf8085cc9b33f88367c8134cd2b01115cfcd9e9116fab7ba3f93abc33c6d6f
+  data.tar.gz: bdefeaa9f965ea991071a70b48239ad7129763bcb05f0cc2ebcd6d66511bd3e6
 SHA512:
-  metadata.gz: 1294bcb2f772e520bfe5f289df53f8b03dc9b8cfb97d1a514753d776295a5052f2cd19d831b7e015b124d4eede94a58b518b0c4a52ed7ae2b9ba68c1e9c1ba93
-  data.tar.gz: dfc521fe2478f0cbf8c5a4d1ac25c5a20705885a1bdd94a2445d317dfccab7018fe80e4664b929a45e2b3c773427d2bd34fed7597eb890f28ad2e99bf4632dc5
+  metadata.gz: 9e1463de777f3d77bcb8f804bdfedeb3781ccf0b36330faf21d501b1a87cf9b55f0d03f2668a1889ae165cbaaf2030ab955ad8c0f42a5aaad341a6eb7154b356
+  data.tar.gz: 6738493c3a716f553fea6486841f612616bad38cc4091103ec490417336df327ae03046a04907b9dcaed9c5d81e17ab918d64d841a67a50b23565dc46308736b

data/actions/add.rb

@@ -3,10 +3,32 @@
 # @package MiGA
 # @license Artistic-2.0
 
-o = {q: true, ref: true, update: false}
+input_types = {
+  raw_reads_single: 
+    ['Single raw reads in a single FastQ file',
+      :raw_reads, %w[.1.fastq]],
+  raw_reads_paired: 
+    ['Paired raw reads in two FastQ files',
+      :raw_reads, %w[.1.fastq .2.fastq]],
+  trimmed_reads_single: 
+    ['Single trimmed reads in a single FastA file',
+      :trimmed_fasta, %w[.SingleReads.fa]],
+  trimmed_reads_paired: 
+    ['Paired trimmed reads in two FastA files',
+      :trimmed_fasta, %w[.1.fasta .2.fasta]],
+  trimmed_reads_interleaved: 
+    ['Paired trimmed reads in a single FastA file',
+      :trimmed_fasta, %w[.CoupledReads.fa]],
+  assembly: 
+    ['Assembled contigs or scaffolds in FastA format',
+      :assembly, %w[.LargeContigs.fna]]
+}
+
+o = {q: true, ref: true, ignore_dups: false,
+  regexp: /^(?:.*\/)?(.+?)(?:\..*(?:[12]|Reads|Contigs))?(?i:\.f[nastq]+)?$/}
 OptionParser.new do |opt|
-  opt_banner(opt)
-  opt_object(opt, o, [:project, :dataset, :dataset_type_req])
+  opt_banner(opt, true)
+  opt_object(opt, o, [:project, :dataset_opt, :dataset_type_req])
   opt.on('-q', '--query',
     'If set, the dataset is registered as a query, not a reference dataset.'
     ){ |v| o[:ref] = !v }
@@ -18,73 +40,90 @@ OptionParser.new do |opt|
     'Metadata as key-value pairs separated by = and delimited by comma.',
     'Values are saved as strings except for booleans (true / false) or nil.'
     ){ |v| o[:metadata] = v }
-  opt.on('--update', 'Updates the dataset if it already exists.',
-    'Same as "miga edit".'){ o[:update] = true }
+  opt.on('-r', '--name-regexp REGEXP', Regexp,
+    'Regular expression indicating how to extract the name from the file path.',
+    "By default: '#{o[:regexp]}'"){ |v| o[:regexp] = v }
+  opt.on('-i', '--input-type STRING',
+    'Type of input data, one of the following:',
+    *input_types.map{ |k,v| "~ #{k}: #{v[0]}." }
+    ){ |v| o[:input_type] = v.downcase.to_sym }
+  opt.on('--ignore-dups', 'Continue with a warning if a dataset already exists.'
+    ){ |v| o[:ignore_dups] = v }
   opt_common(opt, o)
+
+  opt.separator 'You can create multiple datasets with a single command, ' \
+    'simply pass all the files at the end (FILES...).'
+  opt.separator 'If -D is passed, only one dataset will be added. ' \
+    'Otherwise, dataset names will be determined by the file paths (-r).'
   opt.separator ''
-  opt.separator 'External input data'
-  opt.on('--raw-reads FILE1,FILE2', Array,
-    'Comma-delimited paths to the raw reads in FastQ format.',
-    'One file is assumed to be single reads, two are assumed to be paired.'
-    ){ |v| o[:raw_reads] = v }
-  opt.on('--trimmed-fasta-single FILE', Array,
-    'Path to the single trimmed reads in FastA format.'
-    ){ |v| o[:trimmed_fasta_s] = v }
-  opt.on('--trimmed-fasta-coupled FILE1,FILE2', Array,
-    'Comma-delimited paths to the coupled trimmed reads in FastA format.',
-    'One file is assumed to be interposed, two are assumed to contain sisters.'
-    ){ |v| o[:trimmed_fasta_c] = v }
-  opt.on('--assembly FILE', Array,
-    'Path to the contigs (or scaffolds) of the assembly in FastA format.'
-    ){ |v| o[:assembly] = v }
 end.parse!
 
 ##=> Main <=
-opt_require(o)
-opt_require_type(o, MiGA::Dataset) unless o[:update]
+opt_require(o, project: '-P')
+files = ARGV
+file_type = nil
+if files.empty?
+  opt_require_type(o, MiGA::Dataset)
+  files = [nil]
+else
+  raise 'Please specify input type (-i).' if o[:input_type].nil?
+  file_type = input_types[o[:input_type]]
+  raise "Unrecognized input type: #{o[:input_type]}." if file_type.nil?
+  raise 'Some files are duplicated, files must be unique.' if
+    files.size != files.uniq.size
+  if o[:input_type].to_s =~ /_paired$/
+    raise 'Odd number of files incompatible with input type.' if files.size.odd?
+    files = Hash[*files].to_a
+  else
+    files = files.map{ |i| [i] }
+  end
+  raise 'The dataset name (-D) can only be specified with one input file.' if
+    files.size > 1 and not o[:dataset].nil?
+end
 
 $stderr.puts 'Loading project.' unless o[:q]
 p = MiGA::Project.load(o[:project])
 raise "Impossible to load project: #{o[:project]}" if p.nil?
 
-raise 'Dataset already exists, aborting.' unless
-  o[:update] or not MiGA::Dataset.exist?(p, o[:dataset])
-$stderr.puts 'Loading dataset.' unless o[:q]
-d = o[:update] ? p.dataset(o[:dataset]) :
-  MiGA::Dataset.new(p, o[:dataset], o[:ref])
-raise 'Dataset does not exist.' if d.nil?
+$stderr.puts 'Creating datasets:' unless o[:q]
+files.each do |file|
+  name = o[:dataset]
+  if name.nil?
+    ref_file = file.is_a?(Array) ? file.first : file
+    m = o[:regexp].match(ref_file)
+    raise "Cannot extract name from file: #{ref_file}" if m.nil? or m[1].nil?
+    name = m[1].miga_name
+  end
 
-in_files = [:raw_reads, :trimmed_fasta_s, :trimmed_fasta_c, :assembly]
-def cp_result(o, d, p, sym, res_sym, ext)
-  return if o[sym].nil? or o[sym].empty?
-  r_dir  = MiGA::Dataset.RESULT_DIRS[res_sym]
-  r_path = File.expand_path("data/#{r_dir}/#{d.name}", p.path)
-  ext.each_index do |i|
-    next if o[sym][i].nil?
-    gz = o[sym][i] =~ /\.gz/ ? '.gz' : ''
-    FileUtils.cp(o[sym][i], "#{r_path}#{ext[i]}#{gz}")
+  if MiGA::Dataset.exist?(p, name)
+    if o[:ignore_dups]
+      warn "Dataset already exists: #{name}."
+      next
+    else
+      raise "Dataset already exists: #{name}."
+    end
   end
-  File.open("#{r_path}.done", 'w') { |f| f.print Time.now.to_s }
-end
-if in_files.any? { |i| not o[i].nil? }
-  $stderr.puts 'Copying files.' unless o[:q]
-  # :raw_reads
-  cp_result(o, d, p, :raw_reads, :raw_reads, %w[.1.fastq .2.fastq])
-  # :trimmed_fasta
-  cp_result(o, d, p, :trimmed_fasta_s, :trimmed_fasta, %w[.SingleReads.fa])
-  if (o[:trimmed_fasta_c] || []).size > 1
-    cp_result(o, d, p, :trimmed_fasta_c, :trimmed_fasta, %w[.1.fasta .2.fasta])
-  else
-    cp_result(o, d, p, :trimmed_fasta_c, :trimmed_fasta, %w[.CoupledReads.fa])
+
+  $stderr.puts "o #{name}" unless o[:q]
+  d = MiGA::Dataset.new(p, name, o[:ref])
+  raise "Unexpected: Couldn't create dataset: #{name}." if d.nil?
+
+  unless file.nil?
+    r_dir = MiGA::Dataset.RESULT_DIRS[ file_type[1] ]
+    r_path = File.expand_path("data/#{r_dir}/#{d.name}", p.path)
+    file_type[2].each_with_index do |ext, i|
+      gz = file[i] =~ /\.gz/ ? '.gz' : ''
+      FileUtils.cp(file[i], "#{r_path}#{ext}#{gz}")
+      $stderr.puts "  file: #{file[i]}" unless o[:q]
+    end
+    File.open("#{r_path}.done", 'w') { |f| f.print Time.now.to_s }
   end
-  # :assembly
-  cp_result(o, d, p, :assembly, :assembly, %w[.LargeContigs.fna])
+  
+  d = add_metadata(o, d)
+  d.save
+  p.add_dataset(name)
+  res = d.first_preprocessing(true)
+  $stderr.puts "  result: #{res}" unless o[:q]
 end
 
-d = add_metadata(o, d)
-d.save
-p.add_dataset(o[:dataset]) unless o[:update]
-res = d.first_preprocessing(true)
-$stderr.puts "- #{res}" unless o[:q]
-
 $stderr.puts 'Done.' unless o[:q]

data/bin/miga

@@ -84,11 +84,11 @@ end
 ##=> Functions <=
 
 # OptParse banner
-def opt_banner(opt)
+def opt_banner(opt, files = false)
   opt.banner = <<BAN
 #{$task_desc[$task]}
 
-Usage: #{$0} #{$task} [options]
+Usage: #{$0} #{$task} [options]#{ ' FILES...' if files}
 BAN
   opt.separator ""
 end

data/lib/miga/version.rb

@@ -10,22 +10,22 @@ module MiGA
   # - Float representing the major.minor version.
   # - Integer representing gem releases of the current version.
   # - Integer representing minor changes that require new version number.
-  VERSION = [0.3, 13, 1]
+  VERSION = [0.4, 0, 0]
   
   ##
   # Nickname for the current major.minor version.
-  VERSION_NAME = 'tinge'
+  VERSION_NAME = 'aquatint'
   
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2019, 8, 8)
+  VERSION_DATE = Date.new(2019, 8, 15)
   
   ##
   # Reference of MiGA.
-  CITATION = "Rodriguez-R et al (2018). " +
-    "The Microbial Genomes Atlas (MiGA) webserver: taxonomic and gene " +
-    "diversity analysis of Archaea and Bacteria at the whole genome level. " +
-    "Nucleic Acids Research 46(W1):W282-W288. doi:10.1093/nar/gky467."
+  CITATION = 'Rodriguez-R et al (2018). ' \
+    'The Microbial Genomes Atlas (MiGA) webserver: taxonomic and gene ' \
+    'diversity analysis of Archaea and Bacteria at the whole genome level. ' \
+    'Nucleic Acids Research 46(W1):W282-W288. doi:10.1093/nar/gky467.'
 
 end
 
@@ -39,12 +39,12 @@ class MiGA::MiGA
 
   ##
   # Complete version as string.
-  def self.FULL_VERSION ; VERSION.join(".") ; end
+  def self.FULL_VERSION ; VERSION.join('.') ; end
 
   ##
   # Complete version with nickname and date as string.
   def self.LONG_VERSION
-    "MiGA #{VERSION.join(".")} - #{VERSION_NAME} - #{VERSION_DATE}"
+    "MiGA #{VERSION.join('.')} - #{VERSION_NAME} - #{VERSION_DATE}"
   end
 
   ##

data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl

@@ -1 +1 @@
-utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.N50.pl
+../../Scripts/FastA.N50.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl

@@ -1 +1 @@
-utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.filterN.pl
+../../Scripts/FastA.filterN.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl

@@ -1 +1 @@
-utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.length.pl
+../../Scripts/FastA.length.pl

data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl

@@ -1 +1 @@
-utils/enveomics/Pipelines/blast.pbs/../../Scripts/FastA.split.pl
+../../Scripts/FastA.split.pl

data/utils/enveomics/Scripts/lib/enveomics.R

@@ -1 +1 @@
-utils/enveomics/Scripts/lib/../../enveomics.R
+../../enveomics.R

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.3.13.1
+  version: 0.4.0.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-08-08 00:00:00.000000000 Z
+date: 2019-08-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -509,8 +509,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: MiGA