ting 0.2.1 → 0.3.0

data/lib/ting.rb

@@ -6,6 +6,7 @@
 
 $: << File.dirname(__FILE__)
 
+require 'ting/version'
 require 'ting/support'
 require 'ting/groundwork'
 require 'ting/exception'
@@ -16,8 +17,6 @@ require 'ting/conversions'
 require 'ting/conversions/hanyu'
 
 module Ting
-  VERSION = "0.2.1"
-
   class Reader
     def initialize(conv, tone)
       @conv = conv.to_s

data/lib/ting/conversions.rb

@@ -12,7 +12,8 @@ module Ting
       klazz=Ting.const_get c
       begin
         CSV.open(DATA_DIR+c.downcase+'.csv', 'r').each do |name, *values|
-          All << name.to_s unless All.index name || name =~ /name|standalone/i
+          next if name == "name"
+          All << name.to_s unless All.include?(name) || name =~ /standalone/i
           klazz.class_eval {attr_accessor name.to_sym}
           values.each_with_index do |v,i|
             klazz::All[i].send(name+'=', v)
@@ -29,11 +30,15 @@ module Ting
     @@rules=YAML::load(IO.read(DATA_DIR+'rules.yaml'))
 
     def self.parse(type, string)
-      if (fin = Final::All.find {|f| f.respond_to?("#{type}_standalone") && f.send("#{type}_standalone") == string})
-        TonelessSyllable.new(Initial::Empty, fin)
+      if (final = Final::All.find {|f| f.respond_to?("#{type}_standalone") && f.send("#{type}_standalone") == string})
+        TonelessSyllable.new(Initial::Empty, final)
       else
-        Initial::All.find do |ini|
-          Final::All.find do |fin|
+        finals = Final::All.dup
+        finals.unshift(finals.delete(Final::Uo)) #hack : move Uo to the front
+                                                 #otherwise wadegiles parses 'lo' as Le+O rather than Le+Uo
+                                                 #probably better to add a hardcoded 'overrule' table for these cases
+        Initial::All.each do |ini|
+          finals.each do |fin|
             next                                  if TonelessSyllable.illegal?(ini,fin)
             return TonelessSyllable.new(ini,fin)  if apply_rules(type, (ini.send(type)||'') + (fin.send(type)||'')) == string
           end

data/lib/ting/conversions/hanyu.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 module Ting
   module Conversions
     class Hanyu
@@ -20,7 +22,7 @@ module Ting
         valid_chars = []
         Ting.valid_combinations do |i,f|
           1.upto(5) do |tone|
-            valid_chars += @tone.add_tone(Conversions.unparse(:hanyu,TonelessSyllable.new(i,f)), tone).chars
+            valid_chars += @tone.add_tone(Conversions.unparse(:hanyu,TonelessSyllable.new(i,f)), tone).uchars
           end
         end
         valid_chars.sort!.uniq!
@@ -30,7 +32,7 @@ module Ting
       def parse(string)
         result = []
         looking_at = []
-        string.chars.each do |ch|
+        string.uchars.each do |ch|
           head, syll = parse_tail(looking_at)
           looking_at << ch
           if syll && !parse_tail(looking_at)

data/lib/ting/data/rules.yaml

@@ -1,24 +1,27 @@
-hanyu: - match: (j|q|x)ü
-         subst: \1u
-wadegiles: - match: pie\Z
-             subst: pieh
-           - match: (ts|ch)`eh
-             subst: \1`e
-           - match: ts`ih
-             subst: tz`u
-           - match: (k|k`|h)e\Z
-             subst: \1o
-           - match: (k|k`)ui\Z
-             subst: \1uei
-           - match: (sh|ch)o\Z
-             subst: \1e
-           - match: (ch|ch`|ts`|t|t`|l|n|j|s)uo
-             subst: \1o
-           - match: tsih
-             subst: tzu
-           - match: sih
-             subst: ssu
-tongyong: - match: feng
-            subst: fong
+hanyu: 
+  - match: (j|q|x)ü
+    subst: \1u
+wadegiles: 
+  - match: pie\Z
+    subst: pieh
+  - match: (ts|ch)`eh
+    subst: \1`e
+  - match: ts`ih
+    subst: tz`u
+  - match: (k|k`|h)e\Z
+    subst: \1o
+  - match: (k|k`)ui\Z
+    subst: \1uei
+  - match: (sh|ch)o\Z
+    subst: \1e
+  - match: (ch|ch`|ts`|t|t`|l|n|j|s)uo
+    subst: \1o
+  - match: tsih
+    subst: tzu
+  - match: sih
+    subst: ssu
+tongyong: 
+  - match: feng
+    subst: fong
 
-          
+          

data/lib/ting/groundwork.rb

@@ -144,8 +144,8 @@ module Ting
      [Initial::Group_1, Final::Group_V],
      [Initial::Group_3, Final::Group_V],
 
-     #2008.05.26 lo is also valid!
-     #[Initial::Group_2, [Final::O]],  #Only bo, po, mo and fo are valid -o combinations
+     # For "咯 / lo5" to parse correctly we need to list "Le + O" as valid,
+     [Initial::Group_2 - [Initial::Le], [Final::O]],  #Only bo, po, mo and fo are valid -o combinations
      [Initial::Group_3, [Final::O]],
      [Initial::Group_4, [Final::O]],
      [Initial::Group_5, [Final::O]],

data/lib/ting/string.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 class String
   PINYIN_CACHE={}
 

data/lib/ting/support.rb

@@ -1,5 +1,5 @@
 class String
-  def chars
+  def uchars
     self.unpack('U*').map{|c| [c].pack('U')}
   end
 

data/lib/ting/tones/accents.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 module Ting
   module Tones
     class Accents < Tone
@@ -22,11 +24,16 @@ module Ting
         syll.gsub!('ü','v')
         tone %= MAX_TONE
         case syll
-        when /a/ : syll.sub(/a/, tone_glyph(:a,tone))
-        when /e/ : syll.sub(/e/, tone_glyph(:e,tone))
-        when /o/ : syll.sub(/o/, tone_glyph(:o,tone))
-        when /(i|u|v)/ : syll.sub($1, tone_glyph($1,tone))
-        else syll
+        when /a/
+          syll.sub(/a/, tone_glyph(:a,tone))
+        when /e/
+          syll.sub(/e/, tone_glyph(:e,tone))
+        when /o/
+          syll.sub(/o/, tone_glyph(:o,tone))
+        when /(i|u|v)/
+          syll.sub($1, tone_glyph($1,tone))
+        else
+          syll
         end  
       end
 
@@ -56,7 +63,7 @@ module Ting
           end
         end
 
-    end
+      end
     end
   end
 end

data/lib/ting/tones/ipa.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 module Ting
   module Tones
     class Ipa < Tone
@@ -10,7 +12,9 @@ module Ting
         end
 
         def peek_tone(syll)
-          return t if t = GLYPHS.index(syll.chars[-1])
+          if t = GLYPHS.index(syll.uchars[-1])
+            return t
+          end
           return NEUTRAL_TONE
         end
 

data/lib/ting/tones/marks.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 module Ting
   module Tones
     class Marks < Tone
@@ -11,10 +13,14 @@ module Ting
 
         def peek_tone(syll)
           case syll
-          when /ˊ/ : 2
-          when /ˇ/ : 3
-          when /ˋ/ : 4
-          when /˙/ : NEUTRAL_TONE
+          when /ˊ/
+            2
+          when /ˇ/
+            3
+          when /ˋ/
+            4
+          when /˙/
+            NEUTRAL_TONE
           else 
             1
           end

data/lib/ting/tones/supernum.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 module Ting
   module Tones
     class Supernum < Tone
@@ -10,7 +12,9 @@ module Ting
         end
 
         def peek_tone(syll)
-          return t if t = GLYPHS.index(syll.chars[-1])
+          if t = GLYPHS.index(syll.uchars[-1])
+            return t
+          end
           return NEUTRAL_TONE
         end
 

data/lib/ting/version.rb

@@ -0,0 +1,3 @@
+module Ting
+  VERSION = '0.3.0'
+end

data/test/test_comparison.rb

@@ -29,7 +29,7 @@ class TestCompare < Test::Unit::TestCase
     ito   = CHART[0].index to.to_s
 
     CHART[1..-1].each do |vals|
-      assert_equal(vals[ito].strip, writer << (reader << vals[ifrom].strip), "Converting from #{from} to #{to} value #{vals[ito]}")
+      assert_equal(vals[ito].strip, writer << (reader << vals[ifrom].strip), "Converting `#{vals[ifrom]}' from #{from} to #{to} value #{vals[ito]}")
     end
   end
 end

data/test/test_hanyu_coverage.rb

@@ -2,7 +2,9 @@ require 'test/unit'
 require 'ting'
 require 'yaml'
 
-$KCODE='u'
+if RUBY_VERSION =~ /^1.8/
+  $KCODE='u'
+end
 
 module HanyuCoverage 
   grid=YAML.load(IO.read(File.dirname(__FILE__)+'/../lib/ting/data/valid_pinyin.yaml'))
@@ -22,7 +24,7 @@ module HanyuCoverage
           end
 
           def test_unparse_#{hanyu}
-            ts=*@reader.parse('#{hanyu}')
+            ts=@reader.parse('#{hanyu}').first
             assert_not_nil(ts, 'Reader<:hanyu, :no_tone>#parse("#{hanyu}") returned nil')
             assert_equal(Initial::#{iname}, ts.initial, 'Wrong initial for `#{hanyu}`, expected Initial::#{iname}')
             assert_equal(Final::#{fname}, ts.final, 'Wrong final for `#{hanyu}`, expected Final::#{fname}')

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: ting
 version: !ruby/object:Gem::Version 
-  prerelease: false
+  hash: 19
+  prerelease: 
   segments: 
   - 0
-  - 2
-  - 1
-  version: 0.2.1
+  - 3
+  - 0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Arne Brasseur
@@ -14,13 +15,12 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-04-04 00:00:00 +02:00
-default_executable: 
+date: 2012-05-06 00:00:00 Z
 dependencies: []
 
-description: Ting can convert between various systems for phonetically writing Mandarin Chinese. It can also handle various representation of tones, so it can be used to convert pinyin with numbers to pinyin with tones.
+description: Ting can convert between various phonetic representations of Mandarin Chinese. It can also handle various representation of tones, so it can be used to convert pinyin with numbers to pinyin with tones.
 email: 
-- arne@arnebrasseur.net
+- arne.brasseur@gmail.com
 executables: []
 
 extensions: []
@@ -28,38 +28,39 @@ extensions: []
 extra_rdoc_files: 
 - README.rdoc
 - History.txt
+- TODO
 files: 
 - History.txt
 - README.rdoc
 - Rakefile
 - TODO
-- examples/cgiform/cgiform.rb
-- examples/cgiform/template.rhtml
-- examples/hello.rb
-- lib/ting.rb
-- lib/ting/conversion.rb
+- lib/ting/tones.rb
 - lib/ting/conversions.rb
+- lib/ting/tones/supernum.rb
+- lib/ting/tones/accents.rb
+- lib/ting/tones/numbers.rb
+- lib/ting/tones/ipa.rb
+- lib/ting/tones/no_tones.rb
+- lib/ting/tones/marks.rb
+- lib/ting/version.rb
 - lib/ting/conversions/hanyu.rb
+- lib/ting/groundwork.rb
+- lib/ting/exception.rb
+- lib/ting/conversion.rb
+- lib/ting/string.rb
+- lib/ting/support.rb
+- lib/ting.rb
 - lib/ting/data/comparison.csv
 - lib/ting/data/final.csv
 - lib/ting/data/initial.csv
 - lib/ting/data/paladiy.txt
-- lib/ting/data/rules.yaml
 - lib/ting/data/valid_pinyin.yaml
-- lib/ting/exception.rb
-- lib/ting/groundwork.rb
-- lib/ting/string.rb
-- lib/ting/support.rb
-- lib/ting/tones.rb
-- lib/ting/tones/accents.rb
-- lib/ting/tones/supernum.rb
-- lib/ting/tones/ipa.rb
-- lib/ting/tones/marks.rb
-- lib/ting/tones/no_tones.rb
-- lib/ting/tones/numbers.rb
-- test/test_comparison.rb
+- lib/ting/data/rules.yaml
+- examples/hello.rb
+- examples/cgiform/cgiform.rb
+- examples/cgiform/template.rhtml
 - test/test_hanyu_coverage.rb
-has_rdoc: true
+- test/test_comparison.rb
 homepage: http://github.com/arnebrasseur/ting
 licenses: []
 
@@ -70,23 +71,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.6
+rubygems_version: 1.8.10
 signing_key: 
 specification_version: 2
 summary: A conversion library for Chinese transcription methods like Hanyu Pinyin, Bopomofo and Wade-Giles.