bio-gff3 0.8.4 → 0.8.5

data/Gemfile

@@ -1,8 +1,8 @@
 source "http://rubygems.org"
-# Add dependencies required to use your gem here.
-# Example:
-#   gem "activesupport", ">= 2.3.5"
+
+# Runtime dependencies
 gem "bio", ">= 1.3.1"
+gem "bio-logger", "> 0.5.0"
 
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
@@ -11,6 +11,5 @@ group :development do
   gem "bundler", "~> 1.0.0"
   gem "jeweler", "~> 1.5.2"
   gem "rcov", ">= 0"
-  gem "bio", ">= 1.3.1"
-	gem "rspec", ">= 2.0.0"
+  gem "rspec", ">= 2.0.0"
 end

data/Gemfile.lock

@@ -2,12 +2,15 @@ GEM
   remote: http://rubygems.org/
   specs:
     bio (1.4.1)
+    bio-logger (0.6.1)
+      log4r (> 1.1.6)
     diff-lcs (1.1.2)
     git (1.2.5)
     jeweler (1.5.2)
       bundler (~> 1.0.0)
       git (>= 1.2.5)
       rake
+    log4r (1.1.9)
     rake (0.8.7)
     rcov (0.9.9)
     rspec (2.3.0)
@@ -25,6 +28,7 @@ PLATFORMS
 
 DEPENDENCIES
   bio (>= 1.3.1)
+  bio-logger
   bundler (~> 1.0.0)
   jeweler (~> 1.5.2)
   rcov

data/Rakefile

@@ -1,12 +1,12 @@
 require 'rubygems'
-require 'bundler'
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
-  exit e.status_code
-end
+# require 'bundler'
+# begin
+#   Bundler.setup(:default, :development)
+# rescue Bundler::BundlerError => e
+#   $stderr.puts e.message
+#   $stderr.puts "Run `bundle install` to install missing gems"
+#   exit e.status_code
+# end
 require 'rake'
 
 require 'jeweler'
@@ -24,8 +24,10 @@ Support for external FASTA files.
   gem.authors = ["Pjotr Prins"]
   # Include your dependencies below. Runtime dependencies are required when using your gem,
   # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
-  #  gem.add_runtime_dependency 'jabber4r', '> 0.1'
-  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+  gem.add_runtime_dependency 'bio', '>= 1.4.1'
+  gem.add_runtime_dependency 'log4r', '> 1.1.6'
+  gem.add_runtime_dependency 'bio-logger', '>= 0.6.1'
+  gem.add_development_dependency 'rspec', '> 2.0'
 end
 Jeweler::RubygemsDotOrgTasks.new
 

data/VERSION

@@ -1 +1 @@
-0.8.4
+0.8.5

data/bin/gff3-fetch

@@ -10,32 +10,35 @@ USAGE = <<EOM
 
   Fetch and assemble GFF3 types (e.g. ORF, mRNA, CDS) + print in FASTA format. 
 
-    gff3-fetch [--low-mem] [--validate] type [filename.fa] filename.gff3
-
-  Where (NYI == Not Yet Implemented):
-
-    --translate     : output as amino acid sequence 
-    --validate      : validate GFF3 file by translating
-    --fix           : check 3-frame translation and fix, if possible 
-    --fix-wormbase  : fix 3-frame translation on ORFs named 'gene1'
-    --no-assemble   : output each record as a sequence -- NYI
-    --add-phase     : output records using phase (useful w. no-assemble CDS to AA) --NYI
+    gff3-fetch [options] type [filename.fa] filename.gff3
+
+    --translate      : output as amino acid sequence 
+    --validate       : validate GFF3 file by translating
+    --fix            : check 3-frame translation and fix, if possible 
+    --fix-wormbase   : fix 3-frame translation on ORFs named 'gene1'
+    --no-assemble    : output each record as a sequence 
+    --phase          : output records using phase (useful w. no-assemble CDS to AA) 
   
   type is any valid type in the GFF3 definition. For example:
 
-    mRNA            : assemble mRNA
-    CDS             : assemble CDS 
-    exon            : list all exons
-    gene|ORF        : list gene ORFs 
-    other           : use any type from GFF3 definition, e.g. 'Terminate' -- NYI
+    mRNA             : assemble mRNA
+    CDS              : assemble CDS 
+    exon             : list all exons
+    gene|ORF         : list gene ORFs 
+    other            : use any type from GFF3 definition, e.g. 'Terminate' -- NYI
 
   and the following performance options:
 
-    --cache full    : load all in RAM (fast)
-    --cache none    : do not load anything in memory (slow)
-    --low-mem       : use LRU cache (limit RAM use, fast) -- NYI
-    --max-cpus num  : use num threads -- NYI
-    --emboss        : use EMBOSS translation (fast) -- NYI
+		--parser bioruby : use BioRuby GFF3 parser (slow)
+    --parser line    : use GFF3 line parser -- in preparation
+    --parser block   : use GFF3 block parser (optimistic) -- NYI
+    --cache full     : load all in RAM (fast, default)
+    --cache none     : do not load anything in memory (slow)
+    --cache lru      : use LRU cache (limit RAM use, fast) -- NYI
+    --max-cpus num   : use num threads -- NYI
+    --emboss         : use EMBOSS translation (fast) -- NYI
+
+  Where (NYI == Not Yet Implemented):
 
   Multiple GFF3 files can be used. With external FASTA files, always the last
   one before the GFF3 filename is matched.
@@ -52,7 +55,7 @@ USAGE = <<EOM
 
     Find CDS records from external FASTA file, adding phase and translate to protein sequence
 
-      gff3-fetch --no-assemble --add-phase --translate CDS test/data/gff/MhA1_Contig1133.fa test/data/gff/MhA1_Contig1133.gff3
+      gff3-fetch --no-assemble --phase --translate CDS test/data/gff/MhA1_Contig1133.fa test/data/gff/MhA1_Contig1133.gff3
 
     Find mRNA from external FASTA file, without loading everything in RAM
 
@@ -67,14 +70,24 @@ USAGE = <<EOM
 
       gff3-fetch terminal chromosome1.fa geneid.gff3
 
+    Fine tuning output - show errors only
+
+      gff3-fetch mRNA test/data/gff/test.gff3 --trace ERROR
+
+    Fine tuning output - write log messages to file.log
+
+      gff3-fetch mRNA test/data/gff/test.gff3 --trace ERROR --logger file.log
+
 == Performance
 
-time gff3-fetch cds m_hapla.WS217.dna.fa m_hapla.WS217.gff3 > test.fa
+time gff3-fetch cds m_hapla.WS217.dna.fa m_hapla.WS217.gff3 2> /dev/null > test.fa 
 
-  Cache      real     user     sys
-  ----------------------------------------------------
-  full       12m41s   12m28s   0m09s (0.8.0 Jan. 2011)
-  none      504m39s  477m49s  26m50s (0.8.0 Jan. 2011)
+  Cache              real     user     sys
+  ------------------------------------------------------------
+  full,bioruby       12m41    12m28    0m09 (0.8.0)
+  full,line          12m13    12m06    0m07 (0.8.5)
+  none,bioruby      504m39   477m49   26m50 (0.8.0)
+  lru,bioruby        ?
   ----------------------------------------------------
 
 where
@@ -97,10 +110,10 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
 EOM
 
-SEP = File::SEPARATOR
-rootpath = File.dirname(File.dirname(__FILE__))+SEP
-$: << rootpath+'lib'
-GFF3_VERSION = File.new(rootpath+'VERSION').read.chomp
+rootpath = File.dirname(File.dirname(__FILE__))
+$: << File.join(rootpath,'lib')
+
+GFF3_VERSION = File.new(File.join(rootpath,'VERSION')).read.chomp
 
 require 'bio-gff3'
 require 'optparse'
@@ -113,7 +126,14 @@ if ARGV.size == 0
   print USAGE
 end
 
+Bio::Log::CLI.logger('stderr')
+Bio::Log::CLI.trace('info')
+
 options = OpenStruct.new()
+
+# ---- Default options
+options.parser = :bioruby
+
 opts = OptionParser.new() { |opts|
   opts.on_tail("-h", "--help", "Show help and examples") {
     print(opts)
@@ -121,6 +141,17 @@ opts = OptionParser.new() { |opts|
     exit()
   }
 
+  opts.on("--parser [bioruby,line]", String, "Parser (default bioruby)") do |p|
+    case p.downcase
+      when 'bioruby'
+        options.parser = :bioruby
+      when 'line'
+        options.parser = :line
+      else
+        raise 'Unknown --parser option'
+    end
+  end
+
   opts.on("--cache [none,full]", String, "Caching (default full)") do |cache|
     case cache.downcase
       when 'none'
@@ -134,13 +165,20 @@ opts = OptionParser.new() { |opts|
     end
   end
 
+  opts.on("--no-assemble", "output sequences without assembling") do |b|
+    options.no_assemble = true
+  end
+
+  opts.on("--phase", "adjust for phase (useful for CDS --no-assemble --translate)") do |b|
+    options.phase = true
+  end
+
   opts.on("--translate", "output as amino acid sequence") do |b|
     options.translate = b
   end
 
   opts.on("--validate", "validate GFF3 file by translating") do |v|
     options.validate = v
-    $stop_on_error = true  # replace global in near future
   end
 
   opts.on("--fix", "Fix frame errors in the GFF3 definition") do |v|
@@ -151,20 +189,32 @@ opts = OptionParser.new() { |opts|
     options.fix_wormbase = true
   end
 
-  # opts.on("-q", "--quiet", "Run quietly") do |q|
-  #   options.quiet = q
-  # end
+  opts.on("--logger filename",String,"Log to file (default stderr)") do | name |
+    Bio::Log::CLI.logger(name)
+  end
+
+  opts.on("--trace options",String,"Set log level (default INFO, see bio-logger)") do | s |
+    Bio::Log::CLI.trace(s)
+  end
 
-  # opts.on("-v", "--[no-]verbose", "Run verbosely") do |v|
-  #   options.verbose = v
-  # end
+  opts.on("-q", "--quiet", "Run quietly") do |q|
+    Bio::Log::CLI.trace('error')
+  end
 
-  # opts.on("-t", "--[no-]trace", "Debug") do |t|
-  #   options.trace = t
-  # end
-}
+  opts.on("-v", "--verbose", "Run verbosely") do |v|
+    Bio::Log::CLI.trace('info')
+  end
+
+  opts.on("--debug", "Show debug messages") do |v|
+    Bio::Log::CLI.trace('debug')
+    options.debug = true
+  end
+
+ }
 opts.parse!(ARGV)
 
+Bio::Log::CLI.configure('bio-gff3')
+
 gfftype = ARGV.shift
 
 fastafn = nil
@@ -177,15 +227,22 @@ ARGV.each do | fn |
   end
 
   opts = {}
-  opts[:validate] = options.validate
+  opts[:validate]         = options.validate
+  opts[:parser]           = options.parser
   opts[:cache_components] = options.cache
   opts[:cache_records]    = options.cache
-  opts[:fasta_filename] = fastafn if fastafn
-  opts[:fix_wormbase] = options.fix_wormbase
-  opts[:fix] = options.fix
-  gffdb = Bio::GFFbrowser::GFFdb.new(fn,opts)
-  gff = gffdb.assembler
+  opts[:fasta_filename]   = fastafn if fastafn
+  opts[:fix_wormbase]     = options.fix_wormbase
+  opts[:fix]              = options.fix
+  opts[:no_assemble]      = options.no_assemble
+  opts[:phase]            = options.phase
+  opts[:debug]            = options.debug
+
+  gff3 = Bio::GFFbrowser::GFF3.new(fn,opts)
+
+  gff = gff3.assembler
   writer = Bio::GFFbrowser::FastaWriter.new(options.translate, options.validate)
+
   case gfftype.downcase
     when 'gene'
           gff.each_gene_seq do | id, seq |

data/bio-gff3.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{bio-gff3}
-  s.version = "0.8.4"
+  s.version = "0.8.5"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Pjotr Prins"]
-  s.date = %q{2011-01-03}
+  s.date = %q{2011-01-13}
   s.default_executable = %q{gff3-fetch}
   s.description = %q{GFF3 (genome browser) information and digest mRNA and CDS sequences.
 Options for low memory use and caching of records.
@@ -31,20 +31,29 @@ Support for external FASTA files.
     "bin/gff3-fetch",
     "bio-gff3.gemspec",
     "lib/bio-gff3.rb",
-    "lib/bio/db/gff/gffassemble.rb",
-    "lib/bio/db/gff/gffdb.rb",
-    "lib/bio/db/gff/gfffasta.rb",
-    "lib/bio/db/gff/gfffileiterator.rb",
-    "lib/bio/db/gff/gffinmemory.rb",
-    "lib/bio/db/gff/gffnocache.rb",
-    "lib/bio/db/gff/gffparser.rb",
+    "lib/bio/db/gff/digest/gffinmemory.rb",
+    "lib/bio/db/gff/digest/gffnocache.rb",
+    "lib/bio/db/gff/digest/gffparser.rb",
+    "lib/bio/db/gff/file/gfffasta.rb",
+    "lib/bio/db/gff/file/gfffileiterator.rb",
+    "lib/bio/db/gff/gff3.rb",
+    "lib/bio/db/gff/gff3fasta.rb",
+    "lib/bio/db/gff/gff3parsefile.rb",
+    "lib/bio/db/gff/gff3parserec.rb",
+    "lib/bio/db/gff/gffcomponent.rb",
+    "lib/bio/db/gff/gffrecord.rb",
+    "lib/bio/db/gff/gffsection.rb",
+    "lib/bio/db/gff/gffsequence.rb",
+    "lib/bio/db/gff/gffvalidate.rb",
     "lib/bio/output/gfffastawriter.rb",
+    "lib/bio/output/gfflogger.rb",
     "lib/bio/system/lruhash.rb",
     "spec/gff3_assemble2_spec.rb",
     "spec/gff3_assemble3_spec.rb",
     "spec/gff3_assemble_spec.rb",
     "spec/gff3_fileiterator_spec.rb",
     "spec/gffdb_spec.rb",
+    "spec/gffparserec.rb",
     "test/data/gff/MhA1_Contig1133.fa",
     "test/data/gff/MhA1_Contig1133.gff3",
     "test/data/gff/MhA1_Contig125.fa",
@@ -54,7 +63,12 @@ Support for external FASTA files.
     "test/data/gff/test-ext-fasta.fa",
     "test/data/gff/test-ext-fasta.gff3",
     "test/data/gff/test.gff3",
+    "test/data/regression/test_ext_gff3.rtest",
+    "test/data/regression/test_gff3.rtest",
+    "test/data/regression/test_nocache_ext_gff3.rtest",
+    "test/data/regression/test_nocache_gff3.rtest",
     "test/helper.rb",
+    "test/regressiontest.rb",
     "test/test_bio-gff3.rb"
   ]
   s.homepage = %q{http://github.com/pjotrp/bioruby-gff3}
@@ -68,7 +82,9 @@ Support for external FASTA files.
     "spec/gff3_assemble_spec.rb",
     "spec/gff3_fileiterator_spec.rb",
     "spec/gffdb_spec.rb",
+    "spec/gffparserec.rb",
     "test/helper.rb",
+    "test/regressiontest.rb",
     "test/test_bio-gff3.rb"
   ]
 
@@ -78,29 +94,41 @@ Support for external FASTA files.
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_runtime_dependency(%q<bio>, [">= 1.3.1"])
+      s.add_runtime_dependency(%q<bio-logger>, ["> 0.5.0"])
       s.add_development_dependency(%q<shoulda>, [">= 0"])
       s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_development_dependency(%q<rcov>, [">= 0"])
-      s.add_development_dependency(%q<bio>, [">= 1.3.1"])
       s.add_development_dependency(%q<rspec>, [">= 2.0.0"])
+      s.add_runtime_dependency(%q<bio>, [">= 1.4.1"])
+      s.add_runtime_dependency(%q<log4r>, ["> 1.1.6"])
+      s.add_runtime_dependency(%q<bio-logger>, [">= 0.6.1"])
+      s.add_development_dependency(%q<rspec>, ["> 2.0"])
     else
       s.add_dependency(%q<bio>, [">= 1.3.1"])
+      s.add_dependency(%q<bio-logger>, ["> 0.5.0"])
       s.add_dependency(%q<shoulda>, [">= 0"])
       s.add_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_dependency(%q<rcov>, [">= 0"])
-      s.add_dependency(%q<bio>, [">= 1.3.1"])
       s.add_dependency(%q<rspec>, [">= 2.0.0"])
+      s.add_dependency(%q<bio>, [">= 1.4.1"])
+      s.add_dependency(%q<log4r>, ["> 1.1.6"])
+      s.add_dependency(%q<bio-logger>, [">= 0.6.1"])
+      s.add_dependency(%q<rspec>, ["> 2.0"])
     end
   else
     s.add_dependency(%q<bio>, [">= 1.3.1"])
+    s.add_dependency(%q<bio-logger>, ["> 0.5.0"])
     s.add_dependency(%q<shoulda>, [">= 0"])
     s.add_dependency(%q<bundler>, ["~> 1.0.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
     s.add_dependency(%q<rcov>, [">= 0"])
-    s.add_dependency(%q<bio>, [">= 1.3.1"])
     s.add_dependency(%q<rspec>, [">= 2.0.0"])
+    s.add_dependency(%q<bio>, [">= 1.4.1"])
+    s.add_dependency(%q<log4r>, ["> 1.1.6"])
+    s.add_dependency(%q<bio-logger>, [">= 0.6.1"])
+    s.add_dependency(%q<rspec>, ["> 2.0"])
   end
 end
 

data/lib/bio-gff3.rb

@@ -1 +1,29 @@
-require 'bio/db/gff/gffdb'
+# find local plugin installation, and use it when there
+rootpath = File.dirname(File.dirname(__FILE__))
+bio_logger_path = File.join(rootpath,'..','bioruby-logger','lib')
+if File.directory? bio_logger_path
+  $: << bio_logger_path
+	$stderr.print "bio-logger loaded directly\n"
+else
+  require "rubygems"
+  gem "bio-logger"
+end
+require 'bio-logger'
+
+Bio::Log::LoggerPlus.new('bio-gff3')
+
+require 'bio'
+require 'bio/output/gfflogger'
+require 'bio/db/gff/gffvalidate'
+require 'bio/db/gff/gffsection'
+require 'bio/db/gff/gffcomponent'
+require 'bio/db/gff/gffsequence'
+require 'bio/db/gff/gffrecord'
+require 'bio/db/gff/gff3parserec'
+require 'bio/db/gff/gff3parsefile'
+require 'bio/db/gff/gff3fasta'
+require 'bio/db/gff/file/gfffileiterator'
+require 'bio/db/gff/file/gfffasta'
+require 'bio/db/gff/digest/gffparser'
+require 'bio/db/gff/gff3'
+