nexus_parser 1.0.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 mjy
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2008 [name of plugin creator]
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README

@@ -0,0 +1,13 @@
+NexusParser
+===========
+
+Introduction goes here.
+
+
+Example
+=======
+
+Example goes here.
+
+
+Copyright (c) 2008 Matt Yoder, released under the MIT license

data/README.rdoc

@@ -0,0 +1,17 @@
+= nexus_parser
+
+Description goes here.
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 mjy. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,53 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "nexus_parser"
+    gem.summary = %Q{A Nexus file format (phylogenetic inference) parser in Ruby.}
+    gem.description = %Q{A full featured and extensible Nexus file parser in Ruby. }
+    gem.email = "diapriid@gmail.com"
+    gem.homepage = "http://github.com/mjy/nexus_parser"
+    gem.authors = ["mjy"]
+    # gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "nexus_parser #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+1.0.0

data/init.rb

@@ -0,0 +1 @@
+# Include hook code here

data/install.rb

@@ -0,0 +1 @@
+# Install hook code here

data/lib/lexer.rb

@@ -0,0 +1,66 @@
+
+
+class NexusFile::Lexer
+
+  def initialize(input)
+    @input = input
+    # linefeed check the input here -
+    @input.gsub!(/\x0D/,"") # get rid of possible dos carrige returns
+    @next_token = nil
+  end
+  
+  # checks whether the next token is of the specified class. 
+  def peek(token_class)
+    token = read_next_token(token_class)
+    return token.class == token_class
+  end
+
+  # return (and delete) the next token from the input stream, or raise an exception
+  # if the next token is not of the given class.
+  def pop(token_class)
+    token = read_next_token(token_class)
+    @next_token = nil
+    if token.class != token_class
+        raise(NexusFile::ParseError,"expected #{token_class.to_s} but received #{token.class.to_s} at #{@input[0..10]}...", caller)
+    else
+        return token
+    end
+  end
+  
+  private
+   # read (and store) the next token from the input, if it has not already been read.
+   def read_next_token(token_class)
+      if @next_token
+         return @next_token
+      else
+      # check for a match on the specified class first
+      if match(token_class)
+        return @next_token
+      else
+        # now check all the tokens for a match
+        NexusFile::Tokens.nexus_file_token_list.each {|t|
+          return @next_token if match(t)
+        }
+      end
+         # no match, either end of string or lex-error
+         if @input != ''
+             raise( NexusFile::ParseError, "Lex Error, unknown token at #{@input[0..10]}...", caller)
+         else
+            return nil
+      end
+    end
+  end
+  
+  def match(token_class)
+    if (m = token_class.regexp.match(@input))
+      @next_token = token_class.new(m[1])
+       @input = @input[m.end(0)..-1]
+      return true
+    else
+      return false
+    end
+  end
+end
+
+
+

data/lib/nexus_file.rb

@@ -0,0 +1,282 @@
+# NexusParser
+
+# version 0.3 by Matt Yoder 
+# uses the PhyloTree parser/lexer engine by Krishna Dole which in turn was based on
+# Thomas Mailund's <mailund@birc.dk> 'newick-1.0.5' Python library
+
+# outstanding issues:
+## need to resolve Tokens Labels, ValuePair, IDs
+
+module NexusFile
+
+  require File.expand_path(File.join(File.dirname(__FILE__), 'tokens'))
+  require File.expand_path(File.join(File.dirname(__FILE__), 'parser'))
+  require File.expand_path(File.join(File.dirname(__FILE__), 'lexer'))
+ 
+class NexusFile 
+  
+  attr_accessor :taxa, :characters, :sets, :codings, :vars, :notes
+
+  def initialize
+    @taxa = []
+    @characters = []
+    @sets = []
+    @codings = []
+    @notes = []
+    @vars = {}
+  end
+
+  class Character
+    attr_accessor :name, :states, :notes
+    def initialize
+      @name = nil
+      @states = {}
+      @notes = []
+    end
+
+    # requires :label
+    def add_state(options = {})
+      @opt = {
+        :name => ''
+      }.merge!(options)
+      return false if !@opt[:label]
+      
+      @states.update(@opt[:label] => ChrState.new(@opt[:name]))
+    end
+
+    # test this
+    def state_labels
+      @states.keys.sort
+    end
+
+    def name
+      ((@name == "") || (@name == nil)) ? "Undefined" : @name
+    end
+  end
+
+  class Taxon
+    attr_accessor :name, :mesq_id, :notes
+    def initialize
+      @name = ""
+      @mesq_id = ""
+      @notes = []
+    end
+  end
+
+  class ChrState
+    # state is stored as a key in Characters.states
+    attr_accessor :name, :notes
+    def initialize(name)
+      @name = name
+    end
+  end
+
+  class Coding 
+    # unfortunately we need this for notes  
+    attr_accessor :states, :notes
+    def initialize(options = {})
+      @states = options[:states]
+      @notes = [] 
+    end
+
+    def states
+      @states.class == Array ? @states  :  [@states]
+    end
+  end
+
+  class Note
+    attr_accessor :vars
+    def initialize(options = {})
+      @vars = options
+    end
+
+    def note
+      n = ''
+      if @vars[:tf]
+        n = @vars[:tf]
+      elsif @vars[:text]
+        n = @vars[:text]
+      else
+        n = 'No text recovered, possible parsing error.'
+      end
+      
+      # THIS IS A HACK for handling the TF = (CM <note>) format, I assume there will be other params in the future beyond CM, at that point move processing to the parser
+      if n[0..2] =~ /\A\s*\(\s*CM\s*/i
+        n.strip!
+        n = n[1..-2] if n[0..0] == "(" # get rid of quotation marks
+        n.strip!
+        n = n[2..-1] if n[0..1].downcase == "cm" # strip CM
+        n.strip!
+        n = n[1..-2] if n[0..0] == "'" # get rid of quote marks
+        n = n[1..-2] if n[0..0] == '"' 
+      end
+      n.strip
+    end
+  end
+
+end
+
+
+# constructs the NexusFile
+class Builder
+
+  def initialize
+    @nf = NexusFile.new 
+  end
+
+  def stub_taxon
+    @nf.taxa.push(NexusFile::Taxon.new) 
+    return @nf.taxa.size
+  end
+
+  def stub_chr
+    @nf.characters.push(NexusFile::Character.new)
+    return @nf.characters.size
+  end
+
+  def code_row(taxon_index, rowvector)
+
+    @nf.characters.each_with_index do |c, i|
+      @nf.codings[taxon_index.to_i] = [] if !@nf.codings[taxon_index.to_i]
+      @nf.codings[taxon_index.to_i][i] = NexusFile::Coding.new(:states => rowvector[i])
+    
+      # !! we must update states for a given character if the state isn't found (not all states are referenced in description !! 
+
+      existing_states = @nf.characters[i].state_labels
+      
+      new_states = rowvector[i].class == Array ? rowvector[i].collect{|s| s.to_s} :  [rowvector[i].to_s]
+      new_states.delete("?") # we don't add this to the db
+      new_states = new_states - existing_states
+
+      new_states.each do |s|
+        @nf.characters[i].add_state(:label => s)
+      end
+
+    end
+  end
+
+  def add_var(hash)
+    hash.keys.each do |k|
+      raise "var #{k} has already been set" if @nf.vars[:k]
+    end
+    @nf.vars.update(hash)
+  end
+  
+  def update_taxon(options = {})
+    
+    @opt = {
+      :name => ''
+    }.merge!(options)
+    return false if !@opt[:index] 
+    
+    (@nf.taxa[@opt[:index]].name = @opt[:name]) if @opt[:name]
+  end
+
+  # legal hash keys are :index, :name, and integers that point to state labels
+  def update_chr(options = {} )
+    @opt = {
+      :name => ''
+    }.merge!(options)
+    return false if !@opt[:index]
+
+    @index = @opt[:index].to_i
+    
+    # need to create the characters
+    
+    raise(NexusFile::ParseError, "Can't update character of index #{@index}, it doesn't exist! This is a problem parsing the character state labels. Check the indices. It may be for this character \"#{@opt[:name]}\".") if !@nf.characters[@index]
+
+    (@nf.characters[@index].name = @opt[:name]) if @opt[:name]
+  
+    @opt.delete(:index)
+    @opt.delete(:name)
+   
+    # the rest have states
+    @opt.keys.each do |k|
+      
+      if (@nf.characters[@index].states != {}) && @nf.characters[@index].states[k] # state exists
+        
+        ## !! ONLY HANDLES NAME, UPDATE TO HANDLE notes etc. when we get them ##
+        update_state(@index, :index => k, :name => @opt[k])
+        
+      else # doesn't, create it
+        @nf.characters[@index].add_state(:label => k.to_s, :name => @opt[k])
+      end
+    end
+    
+  end
+
+  def update_state(chr_index, options = {})
+    # only handling name now
+    #options.keys.each do |k|
+      @nf.characters[chr_index].states[options[:index]].name = options[:name]
+        # add notes here
+    # end
+  end
+
+  def add_note(options = {})
+    @opt = {
+      :text => ''
+    }.merge!(options)
+
+    case @opt[:type]
+
+    # Why does mesquite differentiate b/w footnotes and annotations?!, apparently same data structure?
+    when 'TEXT' # a footnote 
+      if @opt[:file]
+       @nf.notes << NexusFile::Note.new(@opt)
+        
+      elsif  @opt[:taxon] && @opt[:character] # its a cell, parse this case         
+        @nf.codings[@opt[:taxon].to_i - 1][@opt[:character].to_i - 1].notes = [] if !@nf.codings[@opt[:taxon].to_i - 1][@opt[:character].to_i - 1].notes
+        @nf.codings[@opt[:taxon].to_i - 1][@opt[:character].to_i - 1].notes << NexusFile::Note.new(@opt)
+
+      elsif @opt[:taxon] && !@opt[:character]
+        @nf.taxa[@opt[:taxon].to_i - 1].notes << NexusFile::Note.new(@opt)
+
+      elsif @opt[:character] && !@opt[:taxon]
+        
+        @nf.characters[@opt[:character].to_i - 1].notes << NexusFile::Note.new(@opt)
+      end
+
+    when 'AN' # an annotation, rather than a footnote, same dif
+      if @opt[:t] && @opt[:c]
+        @nf.codings[@opt[:t].to_i - 1][@opt[:c].to_i - 1].notes = [] if !@nf.codings[@opt[:t].to_i - 1][@opt[:c].to_i - 1].notes
+        @nf.codings[@opt[:t].to_i - 1][@opt[:c].to_i - 1].notes << NexusFile::Note.new(@opt)
+      elsif @opt[:t]
+        @nf.taxa[@opt[:t].to_i - 1].notes << NexusFile::Note.new(@opt)
+      elsif @opt[:c]
+        @nf.characters[@opt[:c].to_i - 1].notes << NexusFile::Note.new(@opt)
+      end
+    end
+    
+  end
+
+  def nexus_file
+    @nf
+  end
+
+end # end file
+
+  # NexusFile::ParseError
+  class ParseError < StandardError
+  end
+
+
+end # end module
+
+
+def parse_nexus_file(input)
+  @input = input
+  @input.gsub!(/\[[^\]]*\]/,'')  # strip out all comments BEFORE we parse the file
+    
+  # quickly peek at the input, does this look like a Nexus file? 
+  if !(@input =~ /\#Nexus/i) || !(@input =~ /Begin/i) || !(@input =~ /Matrix/i) || !(@input =~ /end\;/i)
+    raise(NexusFile::ParseError, "File is missing at least some required headers, check formatting.", caller)
+  end
+
+  builder = NexusFile::Builder.new
+  lexer = NexusFile::Lexer.new(@input)
+  NexusFile::Parser.new(lexer, builder).parse_file
+  
+  return builder.nexus_file  
+end
+