hanzi-converter 0.1.1 → 0.2.0

data/README.rdoc

@@ -6,6 +6,10 @@ Example usage:
 
   HanziConverter.load_data
   HanziConverter.to_pinyin('走红') # zou3hong2
+  HanziConverter.to_pinyin('簡單') # jian3dan1
+  HanziConverter.to_pinyin('为什么') # wei4shen2me5
+  HanziConverter.to_pinyin('no! 为什么！') # no! wei4shen2me5！
+  HanziConverter.to_pinyin('你好， 我是康昱辰。') # ni3hao3， wo3shi4kang1yu4chen2。
 
 To run tests:
 

data/VERSION

@@ -1 +1 @@
-0.1.1
+0.2.0

data/hanzi-converter.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "hanzi-converter"
-  s.version = "0.1.1"
+  s.version = "0.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Steve Jackson"]

data/lib/hanzi-converter.rb

@@ -22,7 +22,7 @@ class HanziConverter
         line_data[:simplified] = line[0, line.index(' ')]
 
         line = line[line.index('['), line.length]
-        line_data[:pinyin] = line[1, line.index(']') - 1]
+        line_data[:pinyin] = line[1, line.index(']') - 1].downcase
 
         line = line[line.index('/'), line.rindex('/')]
         line_data[:english] = line[1, line.rindex('/') - 1]
@@ -34,10 +34,49 @@ class HanziConverter
 
     def to_pinyin(text, options={})
       load_data if @data.nil?
+
+      result = ''
+      pos = 0
+
+      loop do
+        char = text[pos]
+        break if !char
+
+        if char.ord < 0x4E00 || char.ord > 0x9FFF
+          # it's not a chinese character.
+          result << char
+          pos += 1
+        else
+          # it's a chinese character. start by trying to find a long word match,
+          # and if it fails, all the way down to a single hanzi.
+          match = nil
+          match_length = 0
+          4.downto(1) do |length|
+            match = find_match(text[pos, length])
+            match_length = length
+            break if match
+          end
+
+          if match
+            result << match[:pinyin].gsub("\s", '')
+            pos += match_length
+            next
+          else
+            # if we're still here, we didn't find a match at all.
+            result << char
+            pos += 1
+          end
+        end
+      end
+
+      result
+    end
+
+    private
+    def find_match(text)
       entry = @data.find do |word|
         word[:simplified] == text || word[:traditional] == text
       end
-      entry[:pinyin].gsub("\s", '') if entry
     end
   end
 end

data/test/test_hanzi-converter.rb

@@ -24,4 +24,14 @@ class TestHanziConverter < Test::Unit::TestCase
     assert_equal 'jian3dan1', result
   end
 
+  def test_can_convert_with_surrounding_english
+    result = HanziConverter.to_pinyin('no! 为什么！')
+    assert_equal 'no! wei4shen2me5！', result
+  end
+
+  def test_can_convert_sentence_of_hanzi
+    result = HanziConverter.to_pinyin('你好， 我是康昱辰。')
+    assert_equal 'ni3hao3， wo3shi4kang1yu4chen2。', result
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: hanzi-converter
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -78,7 +78,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3181578378699029479
+      hash: 4343939069972924356
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: