nexus_parser 1.2.0 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 93e9b7ced7b53e19e2cd33c72c433736058c4adcf7555dc6b43635c08f5dcea7
-  data.tar.gz: 4b9bce06037be960e29e1e4f02bbeef286f47a35e977384a5d451e1f0c3e3f91
+  metadata.gz: be7f8d6dc4a222f456df1bb18dc3d63182cfb83b88ee036c227a93883c5ff70a
+  data.tar.gz: 1ab8785c3ca791476efe19d290ef25f20dc790792cf82fdee4ab1a0cd7468347
 SHA512:
-  metadata.gz: 2297128f4ad470e7de1760996aaa712ed8bc691fee0a3cc8a59de54cf1b40bcc9d1cd6478049ae14f93b90ea208a93b6bc4872b76ecf8fc99221ea1b583f954d
-  data.tar.gz: 19615c9fcdc2469bf32e681ac3b81b1a4ca8f468a0154671573b73c0e54f247d78b075ee3a2a1d63a4ba21c0cd657dfe656f8140b8feed07ca54d93fadf1772a
+  metadata.gz: e2c206656a9c8a1760e158641923b47f789ef42156fd9486dd75f70f92db670f31308adf739355eca6192ae3c702f6868b04fcab8ab87e7e44590371b3838bf7
+  data.tar.gz: fb4a0f18b0430dc04aa4feebd9d9ea46fb91b8557bc61efe7d75d4ad4427da1a0fa9f0632a3afe074fe5e47c17b18f9cd6a58786833b6c07a7181f819cece0d8

data/.gitignore

@@ -13,6 +13,9 @@ tmtags
 ## VIM
 *.swp
 
+## BYEBUG
+.byebug_history
+
 ## PROJECT::GENERAL
 coverage
 rdoc

data/lib/nexus_parser/parser.rb

@@ -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

data/lib/nexus_parser/tokens.rb

@@ -1,5 +1,7 @@
 module NexusParser::Tokens
 
+  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
@@ -31,12 +33,12 @@ module NexusParser::Tokens
   end
 
   class EndBlk < Token
-    @regexp = Regexp.new(/\A\s*([\s]*End[\s]*;[\s]*)/i)
+    @regexp = Regexp.new(/\A\s*([\s]*#{ENDBLKSTR}[\s]*;[\s]*)/i)
   end
 
   # label
   class AuthorsBlk < Token
-    @regexp = Regexp.new(/\A\s*(Authors;.*?END;)\s*/im)
+    @regexp = Regexp.new(/\A\s*(Authors;.*?#{ENDBLKSTR};)\s*/im)
   end
 
   # label
@@ -66,6 +68,11 @@ module NexusParser::Tokens
     @regexp = Regexp.new(/\A\s*(format)\s*/i)
   end
 
+  # 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)
@@ -133,35 +140,35 @@ module NexusParser::Tokens
   # 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]*(END;)\s*/i)
+    @regexp = Regexp.new(/\A[\s]*(#{ENDBLKSTR};)\s*/i)
   end
 
   class LBracket < Token
@@ -246,6 +253,7 @@ module NexusParser::Tokens
       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,

data/lib/nexus_parser/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module NexusParser
-  VERSION = "1.2.0"
+  VERSION = "1.2.1"
 end

data/lib/nexus_parser.rb

@@ -75,7 +75,7 @@ class NexusParser
   class Coding
     # unfortunately we need this for notes
     attr_accessor :notes
-    attr_writer :state 
+    attr_writer :state
 
     def initialize(options = {})
       @states = options[:states]
@@ -85,7 +85,7 @@ class NexusParser
     def states
       @states.class == Array ? @states : [@states]
     end
-    
+
   end
 
   class Note
@@ -270,7 +270,7 @@ 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)
+  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
 

data/test/test_nexus_parser.rb

@@ -56,6 +56,12 @@ class Test_Lexer < Test::Unit::TestCase
     assert lexer2.pop(NexusParser::Tokens::LParen)
     assert lexer2.pop(NexusParser::Tokens::RParen)
 
+    lexer2a = NexusParser::Lexer.new("begin authors; BLORF endblock; []")
+    assert lexer2a.pop(NexusParser::Tokens::BeginBlk)
+    assert lexer2a.pop(NexusParser::Tokens::AuthorsBlk)
+    assert lexer2a.pop(NexusParser::Tokens::LBracket)
+    assert lexer2a.pop(NexusParser::Tokens::RBracket)
+
     lexer3 = NexusParser::Lexer.new("[ foo ] Begin Characters; BLORF end; [] ()  some crud here")
     assert lexer3.pop(NexusParser::Tokens::LBracket)
     assert id = lexer3.pop(NexusParser::Tokens::ID)
@@ -149,7 +155,7 @@ class Test_Lexer < Test::Unit::TestCase
   def test_EndBlk
     lexer = NexusParser::Lexer.new("   \n\n End   ;")
     assert foo = lexer.pop(NexusParser::Tokens::EndBlk)
-    lexer = NexusParser::Lexer.new("\n\nEnd;")
+    lexer = NexusParser::Lexer.new("\n\nEndblock;")
     assert foo = lexer.pop(NexusParser::Tokens::EndBlk)
 
     lexer = NexusParser::Lexer.new("123123  \n\nEnd;")
@@ -401,13 +407,13 @@ class Test_Lexer < Test::Unit::TestCase
         CHARGROUPLABEL Behavior COLOR = (RGB 1.0 0.46666667 1.0) ;
 
 
-      END;
+      ENDBLOCK;
 
     BEGIN some other block;")
 
     assert foo = lexer.pop(NexusParser::Tokens::LabelsBlk)
     assert_equal 'LABELS', foo.value.slice(0,6)
-    assert_equal 'END;', foo.value.slice(-4,4)
+    assert_equal 'ENDBLOCK;', foo.value.slice(-9,9)
   end
 
   def test_SetsBlk
@@ -513,8 +519,6 @@ class Test_Parser < Test::Unit::TestCase
     assert_equal "Tetragnatha", foo.taxa[9].name
   end
 
-
-
   def test_parse_characters_blk
     input=  "
       TITLE  'Scharff&Coddington_1997_Araneidae';
@@ -589,7 +593,7 @@ class Test_Parser < Test::Unit::TestCase
       Tetragnatha            0?01011011
 
     ;
-    END;"
+    ENDBLOCK;"
 
     builder = NexusParser::Builder.new
     @lexer = NexusParser::Lexer.new(input)
@@ -655,6 +659,20 @@ class Test_Parser < Test::Unit::TestCase
     # add test that nothing is left in lexer
   end
 
+  def test_parse_format_respect_case
+    input = "FORMAT DATATYPE = STANDARD RESPECTCASE GAP = - MISSING = ? SYMBOLS = \"  0 1 2 3 4 5 6 7 8 9 A\";"
+    builder = NexusParser::Builder.new
+    lexer = NexusParser::Lexer.new(input)
+
+    NexusParser::Parser.new(lexer,builder).parse_format
+    foo = builder.nexus_file
+
+    assert_equal "STANDARD", foo.vars[:datatype]
+    assert_equal "-", foo.vars[:gap]
+    assert_equal "?", foo.vars[:missing]
+    assert_equal '0 1 2 3 4 5 6 7 8 9 A', foo.vars[:symbols]
+  end
+
   def test_parse_chr_state_labels
     input =" 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 ;

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nexus_parser
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.1
 platform: ruby
 authors:
 - mjy
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-04-03 00:00:00.000000000 Z
+date: 2024-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -128,7 +128,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
+rubygems_version: 3.5.9
 signing_key:
 specification_version: 4
 summary: A Nexus file format (phylogenetic inference) parser in Ruby.