swissparser 0.11.1 → 1.0.0

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: swissparser
 version: !ruby/object:Gem::Version 
-  version: 0.11.1
+  prerelease: false
+  segments: 
+  - 1
+  - 0
+  - 0
+  version: 1.0.0
 platform: ruby
 authors: 
 - paradigmatic
@@ -9,30 +14,46 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-11-16 00:00:00 +01:00
+date: 2010-12-18 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: cucumber
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 4
         version: "0.4"
-    version: 
+  type: :development
+  version_requirements: *id001
 - !ruby/object:Gem::Dependency 
   name: bones
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 3.0.1
-    version: 
-description: Simple DSL to define parser for flat files formats common in biofinformatics.
+        segments: 
+        - 3
+        - 5
+        - 4
+        version: 3.5.4
+  type: :development
+  version_requirements: *id002
+description: |-
+  Simple DSL to define parser for flat files formats common in
+  biofinformatics, such as Swissprot, Uniprot, KEGG, TREMBL, etc.
+  
+  SwissParser API was changed in its version 1.0.0 to simplify parser
+  definition. The code was tested on entire Uniprot and KEGG releases
+  and functional testing guarantees that existing features will not
+  break after an update.
 email: paradigmatic@streum.org
 executables: []
 
@@ -41,33 +62,31 @@ extensions: []
 extra_rdoc_files: 
 - CHANGELOG.rdoc
 - README.rdoc
-- benchmarks/whole_uniprot.txt
+- lib/swissparser.rbc
+- lib/swissparser/entries.rbc
+- lib/swissparser/rules.rbc
 files: 
+- .gitignore
 - CHANGELOG.rdoc
 - LICENSE
 - README.rdoc
 - Rakefile
-- benchmarks/whole_uniprot.txt
+- Rakefile.compiled.rbc
 - examples/data/EColPositives_noTAT.bas
 - examples/data/kegg_enzyme_short.txt
 - examples/data/uniprot.txt
 - examples/kegg_demo.rb
-- examples/parse_from_uri.rb
-- examples/signal_demo.rb
-- examples/tutorial_1.rb
-- examples/tutorial_2.rb
-- examples/uniprot_param_demo.rb
+- examples/uniprot.rb
 - features/basic_parsing.feature
-- features/parser_extension.feature
-- features/parsing_context.feature
-- features/polite.feature
-- features/step_definitions/core.rb
-- features/step_definitions/definitions.rb
-- features/step_definitions/extra.rb
-- lib/swiss_parser.rb
+- features/extra.feature
+- features/step_definitions/basic_steps.rb
+- features/step_definitions/sugar_steps.rb
 - lib/swissparser.rb
-- lib/swissparser/parsing_context.rb
-- lib/swissparser/parsing_rules.rb
+- lib/swissparser.rbc
+- lib/swissparser/entries.rb
+- lib/swissparser/entries.rbc
+- lib/swissparser/rules.rb
+- lib/swissparser/rules.rbc
 has_rdoc: true
 homepage: http://github.com/paradigmatic/SwissParser
 licenses: []
@@ -79,23 +98,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: swissparser
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
-summary: Simple DSL to define parser for flat files formats common in biofinformatics
+summary: Simple DSL to define parser for flat files formats common in biofinformatics, such as Swissprot, Uniprot, KEGG, TREMBL, etc.
 test_files: []
 

data/benchmarks/whole_uniprot.txt

@@ -1,7 +0,0 @@
-$ time ruby tutorial_1.rb uniprot_sprot.dat 
-Parsed: 512205
-real 3313.672   user 3239.700   sys 66.360      pcpu 99.77
-
-$ time ruby bioruby.rb uniprot_sprot.dat 
-512205
-real 1054.322   user 998.170    sys 55.580      pcpu 99.94

data/examples/parse_from_uri.rb

@@ -1,88 +0,0 @@
-=begin
-Copyright (C) 2009 Paradigmatic
-
-This file is part of SwissParser.
-
-SwissParser is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-SwissParser is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with SwissParser.  If not, see <http://www.gnu.org/licenses/>.
-=end
-
-#!/usr/bin/ruby -w
-
-require 'yaml'
-require 'swissparser.rb'
-
-class Protein
-
-  attr_accessor :id, :size, :species, :taxonomy, :sequence
-
-  def initialize
-    @taxonomy = []
-    @sequence = ""
-  end
-
-end
-
-module Uniprot
-
-  Parser = Swiss::Parser.define do
-
-    # Each entry must be stored in a Protein instance
-    new_entry do
-      Protein.new
-    end
-    
-    rules do 
-      
-      # Parse the uniprot id
-      with("ID") do |content,protein|
-        content =~ /([A-Z]\w+)\D+(\d+)/
-        protein.id = $1
-        protein.size = $2.to_i
-      end
-      
-      # Parse the organism
-      with("OS") do |content,protein|
-        content =~ /(\w+ \w+)/
-        protein.species = $1
-      end
-      
-      # Parse the complete taxonomy
-      with("OC") do |content,protein|
-        ary = content.gsub(".","").split("; ")
-        protein.taxonomy += ary
-      end
-      
-      # Parse the Sequence
-      with_text_after("SQ") do |content,protein|
-        seq = content.strip.gsub(" ","")
-        protein.sequence += seq
-      end
-      
-    end
-    
-  end
-  
-end
-  
-if $0 == __FILE__
-    
-  uri = ARGV.shift
-
-  entries = Uniprot::Parser.parse_URI( uri )
-
-  entries.each do |e|
-    puts e.to_yaml
-  end
-
-end

data/examples/signal_demo.rb

@@ -1,100 +0,0 @@
-=begin
-Copyright (C) 2009 Paradigmatic
-
-This file is part of SwissParser.
-
-SwissParser is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-SwissParser is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with SwissParser.  If not, see <http://www.gnu.org/licenses/>.
-=end
-
-require 'swissparser.rb'
-require 'yaml'
-
-class Protein
-  attr_accessor :name, :sequence, :size
-end
-
-parser = Swiss::Parser.define do
-
-  new_entry do
-    Protein.new
-  end
-  
-  rules do
-
-    set_separator '/'
-
-    with('N') do |content,entry|
-      entry.name = content
-    end
-    
-    with('C') do |content,entry|
-      entry.size = content.to_i
-    end
-    
-    with('S') do |content,entry|
-      entry.sequence = content
-    end
-    
-  end
-    
-end
-
-
-stat_parser = parser.extend do
-
-  before do
-    { :min => 1_000, :max => 0, :sum => 0, :n => 0 }
-  end 
-
-  finish_entry do |entry,h|
-    if entry.size < h[:min]
-      h[:min] = entry.size
-    end
-    if entry.size > h[:max]
-      h[:max] = entry.size
-    end
-    h[:sum] += entry.size
-    h[:n] += 1
-  end
-
-  after do |h|
-    h[:average] = h[:sum].to_f / h[:n]
-    h
-  end
-    
-end
-
-
-if $0 == __FILE__
-
-  filename = ARGV.shift
-
-  entries = parser.parse_file( filename )
-  
-  entries.each do |e|
-    puts e.to_yaml
-  end
-  
-  puts
-  
-  results = stat_parser.parse_file( filename )
-
-  puts "Min: #{results[:min]}"
-  puts "Max: #{results[:max]}"
-  puts "Average: #{results[:average]}"
-  puts "Size: #{results[:n]}"
-
-end
-
-

data/examples/tutorial_1.rb

@@ -1,88 +0,0 @@
-=begin
-Copyright (C) 2009 Paradigmatic
-
-This file is part of SwissParser.
-
-SwissParser is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-SwissParser is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with SwissParser.  If not, see <http://www.gnu.org/licenses/>.
-=end
-
-#!/usr/bin/ruby -w
-
-require 'yaml'
-require 'swissparser'
-
-class Protein
-
-  attr_accessor :id, :size, :species, :taxonomy, :sequence
-
-  def initialize
-    @taxonomy = []
-    @sequence = ""
-  end
-
-end
-
-module Uniprot
-
-  Parser = Swiss::Parser.define do
-
-    # Each entry must be stored in a Protein instance
-    new_entry do
-      Protein.new
-    end
-    
-    rules do 
-      
-      # Parse the uniprot id
-      with("ID") do |content,protein|
-        content =~ /([A-Z]\w+)\D+(\d+)/
-        protein.id = $1
-        protein.size = $2.to_i
-      end
-      
-      # Parse the organism
-      with("OS") do |content,protein|
-        content =~ /(\w+ \w+)/
-        protein.species = $1
-      end
-      
-      # Parse the complete taxonomy
-      with("OC") do |content,protein|
-        ary = content.gsub(".","").split("; ")
-        protein.taxonomy += ary
-      end
-      
-      # Parse the Sequence
-      with_text_after("SQ") do |content,protein|
-        seq = content.strip.gsub(" ","")
-        protein.sequence += seq
-      end
-      
-    end
-    
-  end
-  
-end
-  
-if $0 == __FILE__
-    
-  filename = ARGV.shift
-
-  entries = Uniprot::Parser.parse_file( filename )
-
-  entries.each do |e|
-    puts e.to_yaml
-  end
-
-end

data/examples/tutorial_2.rb

@@ -1,65 +0,0 @@
-=begin
-Copyright (C) 2009 Paradigmatic
-
-This file is part of SwissParser.
-
-SwissParser is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-SwissParser is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with SwissParser.  If not, see <http://www.gnu.org/licenses/>.
-=end
-
-#!/usr/bin/ruby -w
-
-require 'swissparser'
-require 'examples/tutorial_1'
-
-class Protein
-
-  attr_accessor :id, :size, :species, :taxonomy, :sequence
-
-  def initialize
-    @taxonomy = []
-    @sequence = ""
-  end
-
-end
-
-module Uniprot
-
-  SpeciesParser = Uniprot::Parser.extend do
-
-    before do 
-      {}
-    end
-
-    finish_entry do |protein, container|
-      if container[protein.species].nil?
-        container[protein.species] = []
-      end
-      container[protein.species] << protein
-    end
-
-  end
-  
-end
-  
-if $0 == __FILE__
-    
-  filename = ARGV.shift
-
-  result = Uniprot::SpeciesParser.parse_file( filename )
-
-  result.each do |species, ary|
-    puts "#{species} => #{ary.map{ |p| p.id }.join(', ')}"
-  end
-
-end