nexus_parser 1.1.4 → 1.2.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: be7f8d6dc4a222f456df1bb18dc3d63182cfb83b88ee036c227a93883c5ff70a
+  data.tar.gz: 1ab8785c3ca791476efe19d290ef25f20dc790792cf82fdee4ab1a0cd7468347
+SHA512:
+  metadata.gz: e2c206656a9c8a1760e158641923b47f789ef42156fd9486dd75f70f92db670f31308adf739355eca6192ae3c702f6868b04fcab8ab87e7e44590371b3838bf7
+  data.tar.gz: fb4a0f18b0430dc04aa4feebd9d9ea46fb91b8557bc61efe7d75d4ad4427da1a0fa9f0632a3afe074fe5e47c17b18f9cd6a58786833b6c07a7181f819cece0d8

data/.gitignore

@@ -13,9 +13,21 @@ tmtags
 ## VIM
 *.swp
 
+## BYEBUG
+.byebug_history
+
 ## PROJECT::GENERAL
 coverage
 rdoc
 pkg
 
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
 ## PROJECT::SPECIFIC

data/LICENSE

@@ -1,20 +1,28 @@
-Copyright (c) 2009 mjy
+Copyright (c) 2008- Matt Yoder. All rights reserved.
 
-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:
+Developed by: Matt Yoder, Species File Group, and Collaborators
+              University of Illinois
+              https://speciesfilegroup.org
 
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal with
+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:
+* Redistributions of source code must retain the above copyright notice,
+  this list of conditions and the following disclaimers.
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimers in the documentation
+  and/or other materials provided with the distribution.
+* Neither the names of <NAME OF DEVELOPMENT GROUP>, <NAME OF INSTITUTION>,
+  nor the names of its contributors may be used to endorse or promote products
+  derived from this Software without specific prior written permission.
 
-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.
+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
+CONTRIBUTORS 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 WITH THE
+SOFTWARE.

data/{README.rdoc → README.md}

@@ -1,8 +1,10 @@
-= nexus_parser
+# nexus_parser
+
+A Ruby lexer/parser for [nexus](https://en.wikipedia.org/wiki/Nexus_file) files, as used in phylogenetic analysis in taxonomy.
 
 See the test files for usage for now, lots of examples there.
 
-== Note on Patches/Pull Requests
+## Note on Patches/Pull Requests
  
 * Fork the project.
 * Make your feature addition or bug fix.
@@ -10,8 +12,8 @@ See the test files for usage for now, lots of examples there.
   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.
+* Make a pull request.
 
-== Copyright
+## License
 
-Copyright (c) 2010 Matt Yoder. See LICENSE for details.
+`nexus_parser` is open source and is now available under the [University of Illinois/NCSA Open Source License](https://en.wikipedia.org/wiki/University_of_Illinois/NCSA_Open_Source_License).

data/Rakefile

@@ -1,23 +1,9 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
 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'
@@ -38,13 +24,11 @@ rescue LoadError
   end
 end
 
-task :test => :check_dependencies
-
 task :default => :test
 
-require 'rake/rdoctask'
+require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+  version = NexusParser::VERSION
 
   rdoc.rdoc_dir = 'rdoc'
   rdoc.title = "nexus_parser #{version}"

data/lib/{lexer.rb → nexus_parser/lexer.rb}

@@ -8,8 +8,8 @@ class NexusParser::Lexer
     @input.gsub!(/\x0D/,"") # get rid of possible dos carrige returns
     @next_token = nil
   end
-  
-  # checks whether the next token is of the specified class. 
+
+  # 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
@@ -21,18 +21,18 @@ class NexusParser::Lexer
     token = read_next_token(token_class)
     @next_token = nil
     if token.class != token_class
-        raise(NexusParser::ParseError,"expected #{token_class.to_s} but received #{token.class.to_s} at #{@input[0..40]}...", caller)
+      raise(NexusParser::ParseError,"expected #{token_class.to_s} but received #{token.class.to_s} at #{@input[0..40]}...", caller)
     else
-        return token
+      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
+  # 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
@@ -42,19 +42,19 @@ class NexusParser::Lexer
           return @next_token if match(t)
         }
       end
-         # no match, either end of string or lex-error
-         if @input != ''
-             raise( NexusParser::ParseError, "Lex Error, unknown token at #{@input[0..10]}...", caller)
-         else
-            return nil
+      # no match, either end of string or lex-error
+      if @input != ''
+        raise( NexusParser::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]
+      @input = @input[m.end(0)..-1]
       return true
     else
       return false

data/lib/{parser.rb → nexus_parser/parser.rb}

@@ -8,7 +8,7 @@ class NexusParser::Parser
 
   def parse_file
     # nf = @builder.new_nexus_file # create new local NexusParser instance, nf
-    blks = []
+    # blks = []
     @lexer.pop(NexusParser::Tokens::NexusStart)
      
     while @lexer.peek(NexusParser::Tokens::BeginBlk)
@@ -151,8 +151,10 @@ class NexusParser::Parser
   # prolly pop header then fuse with parse_dimensions
   def parse_format
     @lexer.pop(NexusParser::Tokens::Format) 
-    while @lexer.peek(NexusParser::Tokens::ValuePair)
-      @builder.add_var(@lexer.pop(NexusParser::Tokens::ValuePair).value)
+
+    while @lexer.peek(NexusParser::Tokens::ValuePair) || @lexer.peek(NexusParser::Tokens::RespectCase)
+      @lexer.pop(NexusParser::Tokens::RespectCase) if @lexer.peek(NexusParser::Tokens::RespectCase) # !! TODO: nothing is set, respect case is ignored
+      @builder.add_var(@lexer.pop(NexusParser::Tokens::ValuePair).value) if @lexer.peek(NexusParser::Tokens::ValuePair)
     end
 
     check_initialization_of_ntax_nchar
@@ -215,7 +217,7 @@ class NexusParser::Parser
         
         opts.update({:index => (index - 1), :name => name})
        
-        raise(NexusParser::ParseError, "Error parsing character state labels for (or around) character #{index -1}.") if !opts[:name]
+        raise(NexusParser::ParseError, "Error parsing character state labels for (or around) character #{index - 1}.") if !opts[:name]
         @builder.update_chr(opts)
       end     
 

data/lib/{tokens.rb → nexus_parser/tokens.rb}

@@ -1,9 +1,11 @@
 module NexusParser::Tokens
 
-  class Token 
+  ENDBLKSTR = '(end|endblock)'.freeze
+
+  class Token
     # this allows access the the class attribute regexp, without using a class variable
     class << self; attr_reader :regexp; end
-    attr_reader :value    
+    attr_reader :value
     def initialize(str)
       @value = str
     end
@@ -11,7 +13,7 @@ module NexusParser::Tokens
 
   # in ruby, \A is needed if you want to only match at the beginning of the string, we need this everywhere, as we're
   # moving along popping off
- 
+
   class NexusStart < Token
     @regexp = Regexp.new(/\A.*(\#nexus)\s*/i)
   end
@@ -21,7 +23,7 @@ module NexusParser::Tokens
   #   @regexp = Regexp.new(/\A\s*(\[[^\]]*\])\s*/i)
   #   def initialize(str)
   #     str = str[1..-2] # strip the []
-  #     str.strip!   
+  #     str.strip!
   #    @value = str
   #  end
   # end
@@ -31,20 +33,20 @@ module NexusParser::Tokens
   end
 
   class EndBlk < Token
-    @regexp = Regexp.new(/\A\s*([\s\n]*End[\s\n]*;[\s\n]*)/i)
+    @regexp = Regexp.new(/\A\s*([\s]*#{ENDBLKSTR}[\s]*;[\s]*)/i)
   end
 
-  # label 
+  # label
   class AuthorsBlk < Token
-    @regexp = Regexp.new(/\A\s*(Authors;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(Authors;.*?#{ENDBLKSTR};)\s*/im)
   end
 
-  # label 
+  # label
   class TaxaBlk < Token
     @regexp = Regexp.new(/\A\s*(\s*Taxa\s*;)\s*/i)
   end
 
-  # label 
+  # label
   class NotesBlk < Token
     @regexp = Regexp.new(/\A\s*(\s*Notes\s*;)\s*/i)
   end
@@ -66,9 +68,14 @@ module NexusParser::Tokens
     @regexp = Regexp.new(/\A\s*(format)\s*/i)
   end
 
-  # label 
+  # TODO: Handled, but ignored
+  class RespectCase < Token
+    @regexp = Regexp.new(/\A\s*(respectcase)\s*/i)
+  end
+
+  # label
   class Taxlabels < Token
-     @regexp = Regexp.new(/\A\s*(\s*taxlabels\s*)\s*/i)
+    @regexp = Regexp.new(/\A\s*(\s*taxlabels\s*)\s*/i)
   end
 
   # same as ID
@@ -77,8 +84,8 @@ module NexusParser::Tokens
     def initialize(str)
       str.strip!
       str = str[1..-2] if str[0..0] == "'" # get rid of quote marks
-      str = str[1..-2] if str[0..0] == '"' 
-      str.strip! 
+      str = str[1..-2] if str[0..0] == '"'
+      str.strip!
       @value = str
     end
   end
@@ -91,15 +98,15 @@ module NexusParser::Tokens
     @regexp = Regexp.new(/\A\s*(link.*\s*;)\s*\n*/i)
   end
 
-  # note we grab EOL and ; here 
+  # note we grab EOL and ; here
   class ValuePair < Token
-    @regexp = Regexp.new(/\A\s*([\w\d\_\&]+\s*=\s*((\'[^\']+\')|(\(.*\))|(\"[^\"]+\")|([^\s\n\t;]+)))[\s\n\t;]+/i) #  returns key => value hash for tokens like 'foo=bar' or foo = 'b a ar'
+    @regexp = Regexp.new(/\A\s*([\w]+\s*=\s*((\'[^\']+\')|(\(.*\))|(\"[^\"]+\")|([^\s;]+)))[\s;]+/i) #  returns key => value hash for tokens like 'foo=bar' or foo = 'b a ar'
     def initialize(str)
       str.strip!
       str = str.split(/=/)
       str[1].strip!
-      str[1] = str[1][1..-2] if str[1][0..0] == "'" 
-      str[1] = str[1][1..-2] if str[1][0..0] ==  "\"" 
+      str[1] = str[1][1..-2] if str[1][0..0] == "'"
+      str[1] = str[1][1..-2] if str[1][0..0] ==  "\""
       @value = {str[0].strip.downcase.to_sym => str[1].strip}
     end
   end
@@ -110,10 +117,10 @@ module NexusParser::Tokens
 
   class RowVec < Token
     @regexp = Regexp.new(/\A\s*(.+)\s*\n/i)
-     def initialize(str)
-       # meh! Ruby is simpler to read than Perl?
-       # handles both () and {} style multistates
-       s = str.split(/\(|\)|\}|\{/).collect{|s| s=~ /[\,|\s]/ ? s.split(/[\,|\s]/) : s}.inject([]){|sum, x| x.class == Array ? sum << x.delete_if {|y| y == "" } : sum + x.strip.split(//)}
+    def initialize(str)
+      # meh! Ruby is simpler to read than Perl?
+      # handles both () and {} style multistates
+      s = str.split(/\(|\)|\}|\{/).collect{|s| s=~ /[\,|\s]/ ? s.split(/[\,|\s]/) : s}.inject([]){|sum, x| x.class == Array ? sum << x.delete_if {|y| y == "" } : sum + x.strip.split(//)}
       @value = s
     end
   end
@@ -131,37 +138,37 @@ module NexusParser::Tokens
   end
 
   # unparsed blocks
-  
+
   class TreesBlk < Token
-    @regexp = Regexp.new(/\A\s*(trees;.*?END;)\s*/im) # note the multi-line /m
+    @regexp = Regexp.new(/\A\s*(trees;.*?#{ENDBLKSTR};)\s*/im) # note the multi-line /m
   end
 
   class SetsBlk < Token
-    @regexp = Regexp.new(/\A\s*(sets;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(sets;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class MqCharModelsBlk < Token
-    @regexp = Regexp.new(/\A\s*(MESQUITECHARMODELS;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(MESQUITECHARMODELS;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class LabelsBlk < Token
-    @regexp = Regexp.new(/\A\s*(LABELS;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(LABELS;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class AssumptionsBlk < Token
-    @regexp = Regexp.new(/\A\s*(ASSUMPTIONS;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(ASSUMPTIONS;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class CodonsBlk < Token
-    @regexp = Regexp.new(/\A\s*(CODONS;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(CODONS;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class MesquiteBlk < Token
-    @regexp = Regexp.new(/\A\s*(Mesquite;.*?END;)\s*/im) 
+    @regexp = Regexp.new(/\A\s*(Mesquite;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   class BlkEnd < Token
-    @regexp = Regexp.new(/\A[\s\n]*(END;)\s*/i)
+    @regexp = Regexp.new(/\A[\s]*(#{ENDBLKSTR};)\s*/i)
   end
 
   class LBracket < Token
@@ -173,13 +180,13 @@ module NexusParser::Tokens
   end
 
   class LParen < Token
-      @regexp = Regexp.new('\A\s*(\()\s*')
+    @regexp = Regexp.new('\A\s*(\()\s*')
   end
 
   class RParen < Token
     @regexp = Regexp.new('\A\s*(\))\s*')
   end
- 
+
   class Equals < Token
     @regexp = Regexp.new('\A\s*(=)\s*')
   end
@@ -192,7 +199,7 @@ module NexusParser::Tokens
   class ID < Token
     @regexp = Regexp.new('\A\s*((\'[^\']+\')|(\w[^,:(); \t\n]*|_)+)\s*')
     def initialize(str)
-      str.strip! 
+      str.strip!
       str = str[1..-2] if str[0..0] == "'" # get rid of quote marks
       @value = str
     end
@@ -241,11 +248,12 @@ module NexusParser::Tokens
       NexusParser::Tokens::LabelsBlk,
       NexusParser::Tokens::TaxaBlk,
       NexusParser::Tokens::NotesBlk,
-      NexusParser::Tokens::Title, 
+      NexusParser::Tokens::Title,
       NexusParser::Tokens::Taxlabels,
       NexusParser::Tokens::Dimensions,
       NexusParser::Tokens::FileLbl,
       NexusParser::Tokens::Format,
+      NexusParser::Tokens::RespectCase,
       NexusParser::Tokens::Equals,
       NexusParser::Tokens::ValuePair,  # this has bad overlap with Label and likely IDs (need to kill the latter, its a lesser Label)
       NexusParser::Tokens::CharStateLabels,
@@ -263,12 +271,12 @@ module NexusParser::Tokens
       NexusParser::Tokens::RParen,
       NexusParser::Tokens::LBracket,
       NexusParser::Tokens::RBracket,
-      NexusParser::Tokens::Label, # must be before RowVec 
+      NexusParser::Tokens::Label, # must be before RowVec
       NexusParser::Tokens::RowVec,
       NexusParser::Tokens::LinkLine,
       NexusParser::Tokens::ID # need to trash this
-    ]   
+    ]
   end
-  
+
 end
 

data/lib/nexus_parser/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module NexusParser
+  VERSION = "1.2.1"
+end