miga-base 1.2.2.2 → 1.2.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4b1fb93676b3b4c48d2204f48a106575274ee50ab294bbf34a3790e7c9adb94b
-  data.tar.gz: 629d74fd9c861b9afc99c9764b1990e8ea8c9b89e5d10780201828fd68ab3c7c
+  metadata.gz: 5a2b155a7dd169adddb5bc6c1470c252adb2357521e5df1cb37634a80031a123
+  data.tar.gz: dc99e9614989ea17bf173c8d1fc8c1f0dd5692030079d54197099471f8f17041
 SHA512:
-  metadata.gz: 46d9ad97e0033b0c99e06476594148baaf2bc630f59c4775d763a2ab322a2ad449229fa9f342509fdfe6ca9a0949405f50b17c719fc817eb426f32a9dd287f54
-  data.tar.gz: 4e6ae0abee96441ac65eb2e8e886f4c2f3d00cc9716205936563022d7858f0d966d28d110c3b18ecdaa8aa328ef58b3b53410e9c32560aa0368b88e7ea6604b8
+  metadata.gz: e4d1271135ba5c66a712f6ba7f19e14b351b367342d0a6f8e268ede58f7d85cc5bc2c4830040cdfa0e9bb742075ef61de4bf0cd086e075e9318ba4cd62eba4e2
+  data.tar.gz: 95d6881e9c0df6f5d2dbbef6f0ae144ac922a1e1a3b355785f78376cef1ed1e8b783ea08bf24674b6e17ca5543d90cc4555b11f11c261baa574398ddace9bb97

data/lib/miga/cli/action/doctor/base.rb

@@ -31,6 +31,7 @@ module MiGA::Cli::Action::Doctor::Base
         file = File.join(base, dir, file_db)
         blk[file, metric, result, rank] if File.exist? file
       end
+      # Query databases for reference databases refer to taxonomy runs
       base = File.join(base, '05.taxonomy')
       result = :taxonomy
     end
@@ -137,10 +138,11 @@ module MiGA::Cli::Action::Doctor::Base
   def save_bidirectional(a, dist)
     each_database_file(a) do |db_file, metric, result, rank|
       next if rank == :haai # No need for hAAI to be bidirectional
+      next if result == :taxonomy # Taxonomy is never bidirectional
 
       b2a = dist[rank].map { |b_name, v| b_name if v[a.name] }.compact
       a2b = dist[rank][a.name]&.keys || []
-      SQLite3::Database.new(db_file) do |db|
+      MiGA::SQLite.new(db_file).run do |db|
         sql = <<~SQL
           insert into #{metric}(seq1, seq2, #{metric}, sd, n, omega) \
           values(?, ?, ?, ?, ?, ?);

data/lib/miga/cli/action/run.rb

@@ -5,7 +5,7 @@ require 'miga/cli/action'
 
 class MiGA::Cli::Action::Run < MiGA::Cli::Action
   def parse_cli
-    cli.defaults = { try_load: false, thr: 1, env: false }
+    cli.defaults = { try_load: false, thr: 1, env: false, check_first: false }
     cli.parse do |opt|
       cli.opt_object(opt, [:project, :dataset_opt, :result_opt])
       opt.on(
@@ -25,6 +25,10 @@ class MiGA::Cli::Action::Run < MiGA::Cli::Action
         '-e', '--environment',
         'Load PROJECT, DATASET, and CORES from the environment'
       ) { |v| cli[:env] = v }
+      opt.on(
+        '--check-first',
+        'Check if the result exists, and run only if it does not'
+      ) { |v| cli[:check_first] = v }
     end
   end
 
@@ -51,6 +55,15 @@ class MiGA::Cli::Action::Run < MiGA::Cli::Action
     # Load project
     p = cli.load_project
 
+    # Check if result already exists
+    if cli[:check_first]
+      obj = cli[:dataset] ? p.dataset(cli[:dataset]) : p
+      if obj.result(cli[:result])
+        cli.say 'Result already exists'
+        return
+      end
+    end
+
     # Prepare command
     miga = MiGA.root_path
     opts = {}

data/lib/miga/cli/action/wf.rb

@@ -69,15 +69,20 @@ module MiGA::Cli::Action::Wf
       'By default: ~/.miga_daemon.json'
     ) { |v| cli[:daemon_json] = v }
     opt.on(
-      '-j', '--jobs INT',
+      '-j', '--jobs INT', Integer,
       'Number of parallel jobs to execute',
       'By default controlled by the daemon configuration (maxjobs)'
-    ) { |v| cli[:jobs] = v.to_i }
+    ) { |v| cli[:jobs] = v }
     opt.on(
-      '-t', '--threads INT',
+      '-t', '--threads INT', Integer,
       'Number of CPUs to use per job',
       'By default controlled by the daemon configuration (ppn)'
-    ) { |v| cli[:threads] = v.to_i }
+    ) { |v| cli[:threads] = v }
+    opt.on(
+      '--threads-project INT', Integer,
+      'Number of CPUs to use per project-wide job',
+      'By default controlled by the daemon configuration (ppn_project or ppn)'
+    ) { |v| cli[:threads_project] = v }
   end
 
   def opts_for_wf_distances(opt)
@@ -184,9 +189,10 @@ module MiGA::Cli::Action::Wf
 
   def run_daemon
     cmd  = ['daemon', 'run', '-P', cli[:outdir], '--shutdown-when-done']
-    cmd += ['--json', cli[:daemon_json]] unless cli[:daemon_json].nil?
-    cmd += ['--max-jobs', cli[:jobs]] unless cli[:jobs].nil?
-    cmd += ['--ppn', cli[:threads]] unless cli[:threads].nil?
+    cmd += ['--json', cli[:daemon_json]] if cli[:daemon_json]
+    cmd += ['--max-jobs', cli[:jobs]] if cli[:jobs]
+    cmd += ['--ppn', cli[:threads]] if cli[:threads]
+    cmd += ['--ppn-project', cli[:threads_project]] if cli[:threads_project]
     cmd += ['--debug', MiGA::MiGA.debug_trace? ? '2' : '1'] if MiGA::MiGA.debug?
     cwd = Dir.pwd
     call_cli(cmd)

data/lib/miga/common/with_daemon_class.rb

@@ -29,7 +29,7 @@ module MiGA::Common::WithDaemonClass
     return nil if c.nil? || c.empty?
 
     Time.parse(c)
-  rescue Errno::ENOENT
+  rescue Errno::ENOENT, ArgumentError
     return nil
   end
 end

data/lib/miga/common/with_result.rb

@@ -26,9 +26,7 @@ module MiGA::Common::WithResult
     task = task.to_sym
     return nil if result_dirs[task].nil?
 
-    base = File.join(
-      project.path, "data/#{result_dirs[task]}/#{result_base}"
-    )
+    base = File.join(project.path, 'data', result_dirs[task], result_base)
     json = "#{base}.json"
     return MiGA::Result.load(json) unless save
 

data/lib/miga/sqlite.rb

@@ -31,16 +31,30 @@ class MiGA::SQLite < MiGA::MiGA
   def initialize(path, opts = {})
     @opts = MiGA::SQLite.default_opts(opts)
     @path = File.absolute_path(path)
+    MiGA::MiGA.DEBUG("Accessing database: #{path}")
   end
 
   ##
-  # Executes +cmd+ and returns the result
+  # Executes +cmd+ and returns the result. Alternatively, if a block is
+  # passed, the commands are ignored and the block is executed with a
+  # single parameter of the database connection
   def run(*cmd)
+    if block_given?
+      run_block { |conn| yield(conn) }
+    else
+      y = nil
+      run_block { |conn| y = conn.execute(*cmd) }
+      y
+    end
+  end
+
+  ##
+  # Executes +blk+ that accepts a single parameter for the database
+  # connection
+  def run_block(&blk)
     busy_attempts ||= 0
     io_attempts ||= 0
-    y = nil
-    SQLite3::Database.new(path) { |conn| y = conn.execute(*cmd) }
-    y
+    SQLite3::Database.new(path) { |conn| blk[conn] }
   rescue SQLite3::BusyException => e
     busy_attempts += 1
     raise "Database busy #{path}: #{e.message}" if busy_attempts >= 3

data/lib/miga/version.rb

@@ -12,7 +12,7 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.2, 2, 2].freeze
+  VERSION = [1.2, 4, 0].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2022, 2, 2)
+  VERSION_DATE = Date.new(2022, 2, 25)
 
   ##
   # References of MiGA

data/utils/core-pan-plot.R

@@ -1,29 +1,48 @@
 #!/usr/bin/env Rscript
 
-argv <- commandArgs(trailingOnly=T)
+argv <- commandArgs(trailingOnly = TRUE)
 
-plot_core_pan <- function(core_pan, pdf){
-  a <- read.table(core_pan, sep="\t", header=TRUE)
+plot_core_pan <- function (core_pan, pdf) {
+  a <- read.table(core_pan, sep = "\t", header = TRUE)
+  col <- c(
+    rgb(96, 11, 64, max = 255),
+    rgb(0, 121, 166, max = 255),
+    rgb(0.5, 0.5, 0.5, 1/3),
+    rep(rgb(0.5, 0.5, 0.5), 2)
+  )
   pdf(pdf, 7, 5)
-  plot(1, type="n", xlim=c(0, max(a$genomes)*1.05), xaxs="i", yaxs="i",
-    ylim=c(0, max(a$pan_q3)*1.05), xlab="Genomes", ylab="Orthologous Groups")
+  plot(
+    1, type = "n", xlim = c(0, max(a$genomes) * 1.05), xaxs = "i", yaxs = "i",
+    ylim = c(0, max(a$pan_q3) * 1.05)/1e3, xlab = "Genomes",
+    ylab = "Orthologous Groups (thousands)"
+  )
+
   # Core
-  polygon(c(a$genomes, rev(a$genomes)), c(a$core_q1, rev(a$core_q3)),
-    border=NA, col=rgb(0, 121, 166, 128/2, max=255))
-  lines(a$genomes, a$core_avg, col=rgb(0,121,166,max=255), lty=2)
-  lines(a$genomes, a$core_q2, col=rgb(0,121,166,max=255), lty=1)
+  polygon(
+    c(a$genomes, rev(a$genomes)), c(a$core_q1, rev(a$core_q3))/1e3,
+    border = NA, col = rgb(0, 121, 166, 256/4, max = 255)
+  )
+  lines(a$genomes, a$core_avg/1e3, col = col[2], lty = 2)
+  lines(a$genomes, a$core_q2/1e3, col = col[2], lty = 1)
+
   # Pan
-  polygon(c(a$genomes, rev(a$genomes)), c(a$pan_q1, rev(a$pan_q3)),
-    border=NA, col=rgb(96, 11, 64, 128/2, max=255))
-  lines(a$genomes, a$pan_avg, col=rgb(96,11,64,max=255), lty=2)
-  lines(a$genomes, a$pan_q2, col=rgb(96,11,64,max=255), lty=1)
+  polygon(
+    c(a$genomes, rev(a$genomes)), c(a$pan_q1, rev(a$pan_q3))/1e3,
+    border = NA, col = rgb(96, 11, 64, 256/4, max = 255)
+  )
+  lines(a$genomes, a$pan_avg/1e3, col = col[1], lty = 2)
+  lines(a$genomes, a$pan_q2/1e3, col = col[1], lty = 1)
+
   # Legend
-  legend("topleft",
-    legend=c("pangenome","core genome","Inter-Quartile","Median","Average"),
-    pch=c(16,16,15,NA,NA),lty=c(NA,NA,NA,1,2), pt.cex=c(1,1,2,NA,NA),
-    col=c(rgb(96,11,64,max=255), rgb(0,121,166,max=255),
-      rgb(0.5,0.5,0.5,166/255), rep(rgb(0.5,0.5,0.5),2)), bty="n")
+  legend <- c("pangenome", "core genome", "Inter-Quartile", "Median", "Average")
+  legend(
+    "topleft", legend = legend, col = col, bty = "n",
+    pch = c(16, 16, 15, NA, NA),
+    lty = c(NA, NA, NA, 1, 2),
+    pt.cex = c(1, 1, 2, NA, NA),
+  )
   dev.off()
 }
 
 plot_core_pan(argv[1], argv[2])
+

data/utils/index_metadata.rb

@@ -19,6 +19,7 @@ end
 p.each_dataset do |d|
   next unless d.ref? && d.active?
 
+  db.execute('BEGIN TRANSACTION')
   searchable(db, d, :name, d.name)
   d.metadata.each do |k, v|
     next if [:created, :updated].include? k
@@ -26,4 +27,5 @@ p.each_dataset do |d|
     v = v.sorted_ranks.map { |r| r[1] }.join(' ') if k == :tax
     searchable(db, d, k, v)
   end
+  db.execute('COMMIT')
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.2.2.2
+  version: 1.2.4.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-02-02 00:00:00.000000000 Z
+date: 2022-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons