bio-gff3 0.8.6 → 0.8.7

data/Gemfile.lock

@@ -2,8 +2,8 @@ GEM
   remote: http://rubygems.org/
   specs:
     bio (1.4.1)
-    bio-logger (0.6.1)
-      log4r (> 1.1.6)
+    bio-logger (1.0.0)
+      log4r (>= 1.1.9)
     diff-lcs (1.1.2)
     git (1.2.5)
     jeweler (1.5.2)
@@ -11,16 +11,16 @@ GEM
       git (>= 1.2.5)
       rake
     log4r (1.1.9)
-    rake (0.8.7)
+    rake (0.9.2)
     rcov (0.9.9)
-    rspec (2.3.0)
-      rspec-core (~> 2.3.0)
-      rspec-expectations (~> 2.3.0)
-      rspec-mocks (~> 2.3.0)
-    rspec-core (2.3.1)
-    rspec-expectations (2.3.0)
+    rspec (2.6.0)
+      rspec-core (~> 2.6.0)
+      rspec-expectations (~> 2.6.0)
+      rspec-mocks (~> 2.6.0)
+    rspec-core (2.6.4)
+    rspec-expectations (2.6.0)
       diff-lcs (~> 1.1.2)
-    rspec-mocks (2.3.0)
+    rspec-mocks (2.6.0)
     shoulda (2.11.3)
 
 PLATFORMS
@@ -28,9 +28,10 @@ PLATFORMS
 
 DEPENDENCIES
   bio (>= 1.3.1)
-  bio-logger
+  bio-logger (> 0.8.0)
   bundler (~> 1.0.0)
   jeweler (~> 1.5.2)
+  log4r (> 1.1.6)
   rcov
-  rspec (>= 2.0.0)
+  rspec (>= 2.3.0)
   shoulda

data/README.rdoc

@@ -5,15 +5,17 @@ including assembled mRNA, protein and CDS sequences.
 
 Features:
 
-# Take GFF3 (genome browser) information of any type, and assemble sequences, e.g. mRNA and CDS
-# Options for low memory use and caching of records
-# Support for external FASTA input files
-# Use of multi-cores (NYI)
+* Take GFF3 (genome browser) information of any type, and assemble sequences, e.g. mRNA and CDS
+* Options for low memory use and caching of records
+* Support for external FASTA input files
+* Use of multi-cores (NYI)
 
 Currently the output is a FASTA file.
 
-You can use this plugin in two ways. First as a standalone program, next as a
-plugin library to BioRuby.
+You can use this plugin in two ways. First as a standalone program,
+second as a plugin library to BioRuby.
+
+Note: a really fast GFF3 parser is in the works at https://github.com/pjotrp/biolib_hpc/tree/master/modules/gff3
 
 == Install and run gff3-fetch
 
@@ -61,32 +63,35 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
   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):
+    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 -- NYI
-    --add-phase     : output records using phase (useful w. no-assemble CDS to AA) --NYI
+    --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'
 
   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 (faster, default)
+    --block          : parse GFF3 by block (optimistic) -- NYI
+    --cache full     : load all in RAM (fast, default)
+    --cache none     : do not load anything in memory (slow)
+    --cache lru      : use least recently used 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.
@@ -103,7 +108,7 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
     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
 
@@ -118,15 +123,50 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
       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 outpt - show messages matching regex 
+
+      gff3-fetch mRNA test/data/gff/test.gff3 --trace '=msg =~ /component/'
+
+    Fine tuning output - write log messages to file.log
+
+      gff3-fetch mRNA test/data/gff/test.gff3 --trace ERROR --logger file.log
+
+For more information on output, see the bioruby-logger plugin.
+
 == 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 
+
+  Digesting parser:
+
+  Cache              real     user     sys  version     RAM
+  ------------------------------------------------------------
+  full,bioruby       12m41    12m28    0m09 (0.8.0)
+  full,line          12m13    12m06    0m07 (0.8.5)
+  full,line,lazy     11m51    11m43    0m07 (0.8.6)     6,600M
+
+  none,bioruby      504m     477m     26m50 (0.8.0)
+  none,line         297m     267m     28m36 (0.8.5)       
+  none,line,lazy    132m     106m     26m01 (0.8.6)       650M
+
+  lru,bioruby       533m     510m     22m47 (0.8.5)
+  lru,line          353m     326m     26m44 (0.8.5)  1K
+  lru,line          305m     281m     22m30 (0.8.5) 10K
+  lru,line,lazy     182m     161m     21m10 (0.8.6) 10K
+  lru,line,lazy      75m      75m      0m17 (0.8.6) 50K   730M
+  ------------------------------------------------------------
+
+  Block parser:
 
-  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  gff3 version
+  ------------------------------------------------------------
+  in preparation see also biolib/HPC:
+    https://github.com/pjotrp/biolib_hpc/tree/master/modules/gff3
+  ------------------------------------------------------------
 
 where
 

data/Rakefile

@@ -13,9 +13,9 @@ require 'jeweler'
 Jeweler::Tasks.new do |gem|
   # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
   gem.name = "bio-gff3"
-  gem.homepage = "http://github.com/pjotrp/bioruby-gff3"
+  gem.homepage = "https://github.com/pjotrp/bioruby-gff3-plugin"
   gem.license = "MIT"
-  gem.summary = %Q{BioRuby GFF3 plugin for big data}
+  gem.summary = %Q{GFF3 parser for big data}
   gem.description = %Q{GFF3 (genome browser) information and digest mRNA and CDS sequences.
 Options for low memory use and caching of records.
 Support for external FASTA files.

data/VERSION

@@ -1 +1 @@
-0.8.6
+0.8.7

data/bio-gff3.gemspec

@@ -5,18 +5,17 @@
 
 Gem::Specification.new do |s|
   s.name = %q{bio-gff3}
-  s.version = "0.8.6"
+  s.version = "0.8.7"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Pjotr Prins"]
-  s.date = %q{2011-01-17}
-  s.default_executable = %q{gff3-fetch}
+  s.authors = [%q{Pjotr Prins}]
+  s.date = %q{2011-07-31}
   s.description = %q{GFF3 (genome browser) information and digest mRNA and CDS sequences.
 Options for low memory use and caching of records.
 Support for external FASTA files.
 }
   s.email = %q{pjotr.prins@thebird.nl}
-  s.executables = ["gff3-fetch"]
+  s.executables = [%q{gff3-fetch}]
   s.extra_rdoc_files = [
     "LICENSE.txt",
     "README.rdoc"
@@ -75,11 +74,11 @@ Support for external FASTA files.
     "test/regressiontest.rb",
     "test/test_bio-gff3.rb"
   ]
-  s.homepage = %q{http://github.com/pjotrp/bioruby-gff3}
-  s.licenses = ["MIT"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.7}
-  s.summary = %q{BioRuby GFF3 plugin for big data}
+  s.homepage = %q{https://github.com/pjotrp/bioruby-gff3-plugin}
+  s.licenses = [%q{MIT}]
+  s.require_paths = [%q{lib}]
+  s.rubygems_version = %q{1.8.6}
+  s.summary = %q{GFF3 parser for big data}
   s.test_files = [
     "spec/gff3_assemble2_spec.rb",
     "spec/gff3_assemble3_spec.rb",
@@ -93,7 +92,6 @@ Support for external FASTA files.
   ]
 
   if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then

data/lib/bio/db/gff/gff3parsefile.rb

@@ -18,7 +18,7 @@ module Bio
           if s == '##FASTA'
             break
           end
-          next if s.length == 0 or s[0] == '#'
+          next if s.length == 0 or s =~ /^#/
           @records.push FastLineRecord.new(parse_line_fast(s))
         end
         fasta = Bio::GFF::FastaReader.new(fh)

metadata

@@ -1,152 +1,119 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: bio-gff3
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 8
-  - 6
-  version: 0.8.6
+version: !ruby/object:Gem::Version
+  version: 0.8.7
+  prerelease: 
 platform: ruby
-authors: 
+authors:
 - Pjotr Prins
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-01-17 00:00:00 +01:00
-default_executable: gff3-fetch
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2011-07-31 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: bio
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: &76668620 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 3
-        - 1
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 1.3.1
   type: :runtime
   prerelease: false
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76668620
+- !ruby/object:Gem::Dependency
   name: log4r
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  requirement: &76668160 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">"
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 1
-        - 6
+    requirements:
+    - - ! '>'
+      - !ruby/object:Gem::Version
         version: 1.1.6
   type: :runtime
   prerelease: false
-  version_requirements: *id002
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76668160
+- !ruby/object:Gem::Dependency
   name: bio-logger
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  requirement: &76667770 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">"
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 8
-        - 0
+    requirements:
+    - - ! '>'
+      - !ruby/object:Gem::Version
         version: 0.8.0
   type: :runtime
   prerelease: false
-  version_requirements: *id003
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76667770
+- !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  requirement: &76667270 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
   prerelease: false
-  version_requirements: *id004
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76667270
+- !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  requirement: &76666730 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 0
-        - 0
+      - !ruby/object:Gem::Version
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *id005
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76666730
+- !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &id006 !ruby/object:Gem::Requirement 
+  requirement: &76662470 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 5
-        - 2
+      - !ruby/object:Gem::Version
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *id006
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76662470
+- !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &id007 !ruby/object:Gem::Requirement 
+  requirement: &76662040 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
   prerelease: false
-  version_requirements: *id007
-- !ruby/object:Gem::Dependency 
+  version_requirements: *76662040
+- !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &id008 !ruby/object:Gem::Requirement 
+  requirement: &76661550 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 2
-        - 3
-        - 0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 2.3.0
   type: :development
   prerelease: false
-  version_requirements: *id008
-description: |
-  GFF3 (genome browser) information and digest mRNA and CDS sequences.
+  version_requirements: *76661550
+description: ! 'GFF3 (genome browser) information and digest mRNA and CDS sequences.
+
   Options for low memory use and caching of records.
+
   Support for external FASTA files.
 
+'
 email: pjotr.prins@thebird.nl
-executables: 
+executables:
 - gff3-fetch
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - LICENSE.txt
 - README.rdoc
-files: 
+files:
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -199,39 +166,32 @@ files:
 - test/helper.rb
 - test/regressiontest.rb
 - test/test_bio-gff3.rb
-has_rdoc: true
-homepage: http://github.com/pjotrp/bioruby-gff3
-licenses: 
+homepage: https://github.com/pjotrp/bioruby-gff3-plugin
+licenses:
 - MIT
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.8.6
 signing_key: 
 specification_version: 3
-summary: BioRuby GFF3 plugin for big data
-test_files: 
+summary: GFF3 parser for big data
+test_files:
 - spec/gff3_assemble2_spec.rb
 - spec/gff3_assemble3_spec.rb
 - spec/gff3_assemble_spec.rb