nexus_parser 1.1.4 → 1.2.1

data/lib/nexus_parser.rb

@@ -8,12 +8,12 @@
 
 module NexusParser
 
-  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 NexusParser 
-  
+  require File.expand_path(File.join(File.dirname(__FILE__), 'nexus_parser', 'tokens'))
+  require File.expand_path(File.join(File.dirname(__FILE__), 'nexus_parser', 'parser'))
+  require File.expand_path(File.join(File.dirname(__FILE__), 'nexus_parser', 'lexer'))
+
+class NexusParser
+
   attr_accessor :taxa, :characters, :sets, :codings, :vars, :notes
 
   def initialize
@@ -26,7 +26,9 @@ class NexusParser
   end
 
   class Character
-    attr_accessor :name, :states, :notes
+    attr_accessor  :states, :notes
+    attr_writer :name
+
     def initialize
       @name = nil
       @states = {}
@@ -39,7 +41,7 @@ class NexusParser
         :name => ''
       }.merge!(options)
       return false if !@opt[:label]
-      
+
       @states.update(@opt[:label] => ChrState.new(@opt[:name]))
     end
 
@@ -49,7 +51,7 @@ class NexusParser
     end
 
     def name
-      ((@name == "") || (@name == nil)) ? "Undefined" : @name
+      ((@name == "") || (@name.nil?)) ? "Undefined" : @name
     end
   end
 
@@ -70,17 +72,20 @@ class NexusParser
     end
   end
 
-  class Coding 
-    # unfortunately we need this for notes  
-    attr_accessor :states, :notes
+  class Coding
+    # unfortunately we need this for notes
+    attr_accessor :notes
+    attr_writer :state
+
     def initialize(options = {})
       @states = options[:states]
-      @notes = [] 
+      @notes = []
     end
 
     def states
-      @states.class == Array ? @states  :  [@states]
+      @states.class == Array ? @states : [@states]
     end
+
   end
 
   class Note
@@ -98,7 +103,7 @@ class NexusParser
       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!
@@ -107,7 +112,7 @@ class NexusParser
         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] == '"' 
+        n = n[1..-2] if n[0..0] == '"'
       end
       n.strip
     end
@@ -120,11 +125,11 @@ end
 class Builder
 
   def initialize
-    @nf = NexusParser.new 
+    @nf = NexusParser.new
   end
 
   def stub_taxon
-    @nf.taxa.push(NexusParser::Taxon.new) 
+    @nf.taxa.push(NexusParser::Taxon.new)
     return @nf.taxa.size
   end
 
@@ -138,11 +143,11 @@ class Builder
     @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] = NexusParser::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 !! 
+
+      # !! 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
@@ -160,12 +165,12 @@ class Builder
     end
     @nf.vars.update(hash)
   end
-  
+
   def update_taxon(options = {})
     @opt = {
       :name => ''
     }.merge!(options)
-    return false if !@opt[:index] 
+    return false if !@opt[:index]
     (@nf.taxa[@opt[:index]].name = @opt[:name]) if @opt[:name]
   end
 
@@ -177,29 +182,29 @@ class Builder
     return false if !@opt[:index]
 
     @index = @opt[:index].to_i
-    
+
     # need to create the characters
-    
+
     raise(NexusParser::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 = {})
@@ -218,11 +223,11 @@ class Builder
     case @opt[:type]
 
     # Why does mesquite differentiate b/w footnotes and annotations?!, apparently same data structure?
-    when 'TEXT' # a footnote 
+    when 'TEXT' # a footnote
       if @opt[:file]
        @nf.notes << NexusParser::Note.new(@opt)
-        
-      elsif  @opt[:taxon] && @opt[:character] # its a cell, parse this case         
+
+      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 << NexusParser::Note.new(@opt)
 
@@ -230,7 +235,7 @@ class Builder
         @nf.taxa[@opt[:taxon].to_i - 1].notes << NexusParser::Note.new(@opt)
 
       elsif @opt[:character] && !@opt[:taxon]
-        
+
         @nf.characters[@opt[:character].to_i - 1].notes << NexusParser::Note.new(@opt)
       end
 
@@ -244,7 +249,7 @@ class Builder
         @nf.characters[@opt[:c].to_i - 1].notes << NexusParser::Note.new(@opt)
       end
     end
-    
+
   end
 
   def nexus_file
@@ -264,15 +269,15 @@ 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)
+  # quickly peek at the input, does this look like a Nexus file?
+  if !(@input =~ /\#Nexus/i) || !(@input =~ /Begin/i) || !(@input =~ /Matrix/i) || !(@input =~ /(end|endblock)\;/i)
     raise(NexusParser::ParseError, "File is missing at least some required headers, check formatting.", caller)
   end
 
   builder = NexusParser::Builder.new
   lexer = NexusParser::Lexer.new(@input)
   NexusParser::Parser.new(lexer, builder).parse_file
-  
-  return builder.nexus_file  
+
+  return builder.nexus_file
 end
 

data/nexus_parser.gemspec

@@ -1,60 +1,59 @@
-# Generated by jeweler
-# DO NOT EDIT THIS FILE DIRECTLY
-# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
-# -*- encoding: utf-8 -*-
-
-Gem::Specification.new do |s|
-  s.name = %q{nexus_parser}
-  s.version = "1.1.4"
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["mjy"]
-  s.date = %q{2011-04-12}
-  s.description = %q{A full featured and extensible Nexus file parser in Ruby. }
-  s.email = %q{diapriid@gmail.com}
-  s.extra_rdoc_files = [
+# frozen_string_literal: true
+
+require_relative "lib/nexus_parser/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "nexus_parser"
+  spec.version = NexusParser::VERSION
+  spec.authors = ["mjy", "kleintom"]
+  spec.email = ["diapriid@gmail.com"]
+
+  spec.summary = "A Nexus file format (phylogenetic inference) parser in Ruby."
+  spec.description = "A full featured and extensible Nexus file parser in Ruby."
+  spec.homepage = "http://github.com/mjy/nexus_parser"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+
+  spec.extra_rdoc_files = [
     "LICENSE",
-     "README",
-     "README.rdoc"
+    "README.md"
   ]
-  s.files = [
+  spec.files = [
     ".document",
-     ".gitignore",
-     "LICENSE",
-     "MIT-LICENSE",
-     "README",
-     "README.rdoc",
-     "Rakefile",
-     "VERSION",
-     "init.rb",
-     "install.rb",
-     "lib/lexer.rb",
-     "lib/nexus_parser.rb",
-     "lib/parser.rb",
-     "lib/tokens.rb",
-     "nexus_parser.gemspec",
-     "tasks/nexus_parser_tasks.rake",
-     "test/MX_test_03.nex",
-     "test/test.nex",
-     "test/test_nexus_parser.rb",
-     "uninstall.rb"
+    ".gitignore",
+    "LICENSE",
+    "README.md",
+    "Rakefile",
+    "install.rb",
+    "lib/nexus_parser.rb",
+    "lib/nexus_parser/lexer.rb",
+    "lib/nexus_parser/parser.rb",
+    "lib/nexus_parser/tokens.rb",
+    "lib/nexus_parser/version.rb",
+    "nexus_parser.gemspec",
+    "tasks/nexus_parser_tasks.rake",
+    "test/MX_test_03.nex",
+    "test/test.nex",
+    "test/test_nexus_parser.rb",
+    "uninstall.rb"
   ]
-  s.homepage = %q{http://github.com/mjy/nexus_parser}
-  s.rdoc_options = ["--charset=UTF-8"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.5.3}
-  s.summary = %q{A Nexus file format (phylogenetic inference) parser in Ruby.}
-  s.test_files = [
+
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.rdoc_options = ["--charset=UTF-8"]
+  spec.require_paths = ["lib"]
+
+  spec.test_files = [
     "test/test_nexus_parser.rb"
   ]
 
-  if s.respond_to? :specification_version then
-    s.specification_version = 3
+  spec.required_ruby_version = '>= 3.3.0'
 
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-    else
-    end
-  else
-  end
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'rake', '~> 13.0'
+  spec.add_development_dependency 'rdoc', '~> 6.6.2'
+  spec.add_development_dependency 'byebug', '~> 11.1'
+  spec.add_development_dependency 'test-unit'
 end
 

data/test/MX_test_03.nex

@@ -9,7 +9,7 @@ BEGIN TAXA;
 	TITLE 'Scharff&Coddington_1997_Araneidae';
 	DIMENSIONS NTAX=10;
 	TAXLABELS
-		Dictyna Uloborus Deinopis Nephila&Herennia 'Nephilengys_cruentata' Meta Leucauge_venusta Pachygnatha 'Theridiosoma_01' Tetragnatha 
+		Dictyna Uloborus Deinopis Nephila&Herennia 'Nephilengys_cruentata' Meta Leucauge_venusta Pachygnatha 'Theridiosoma_01' Tetragnatha
 	;
 	IDS JC1191fcddc2b128 JC1191fcddc2b129 JC1191fcddc2b130 JC1191fcddc2b131 JC1191fcddc2b132 JC1191fcddc2b133 JC1191fcddc2b134 JC1191fcddc2b135 JC1191fcddc2b137 JC1191fcddc2b136 ;
 	BLOCKID JC1191fcddc0c4;
@@ -21,8 +21,8 @@ BEGIN CHARACTERS;
 	TITLE  'Scharff&Coddington_1997_Araneidae';
 	DIMENSIONS  NCHAR=10;
 	FORMAT DATATYPE = STANDARD GAP = - MISSING = ? SYMBOLS = "  0 1 2 3 4 5 6 7 8 9 A";
-	CHARSTATELABELS 
-		1 Tibia_II /  norm modified, 2 TII_macrosetae /  '= TI' stronger, 3 Femoral_tuber /  abs pres 'm-setae', 5 Cymbium /  dorsal mesal lateral, 6 Paracymbium /  abs pres, 7 Globular_tegulum /  abs pres, 8  /  entire w_lobe, 9 Conductor_wraps_embolus, 10 Median_apophysis /  pres abs ; 
+	CHARSTATELABELS
+		1 Tibia_II /  norm modified, 2 TII_macrosetae /  '= TI' stronger, 3 Femoral_tuber /  abs pres 'm-setae', 5 Cymbium /  dorsal mesal lateral, 6 Paracymbium /  abs pres, 7 Globular_tegulum /  abs pres, 8  /  entire w_lobe, 9 Conductor_wraps_embolus, 10 Median_apophysis /  pres abs ;
 	MATRIX
 	Dictyna                0?00201001
 	Uloborus               0?11000000