toPinyin 0.0.3 → 0.0.4

data/lib/performance.rb

@@ -0,0 +1,24 @@
+require 'benchmark'
+require 'toPinyin'
+
+
+Benchmark.bm(15) do |x|
+
+pinyins=[]
+words = "
+人人
+没有
+理想
+跟跟
+咸鱼
+有有
+什么
+区别".split("\n")
+
+#take 4 seconds
+x.report("convert80") { pinyins = (words * 10).map {|w| w.pinyin} }
+x.report("convert800") { pinyins = (words * 100).map {|w| w.pinyin} }
+x.report("sort:") { pinyins.sort {|a , b| a <=> b}}
+end
+
+

data/lib/toPinyin.rb

@@ -16,6 +16,7 @@ class String
                |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
                )*\z/mnx
 
+	@@mm = uniToPyMap
 
 def utf8?	
 	self =~ UTF8REGEX
@@ -41,17 +42,19 @@ def validate_utf8
       Iconv.iconv('UTF-8//IGNORE', 'UTF-8', (self + ' ') ).first[0..-2]
 end
 
-def pinyin 
+def pinyin
+
 	scan(/./mu).map do |c| 
 	    #conver to unicode
 		#u = Iconv.iconv("UNICODEBIG","utf-8",c)[0].each_byte.map {|b| b.to_s(16)}.join
 		u=sprintf("%04X", c.unpack("U*").first) 
 		#handle a-z, A-Z
-		if u =~ /^00/ 
+		if  u =~ /^00/ 
 			#return c as it is
 			c
 		else
-			uniToPyMap[u.upcase].chop unless uniToPyMap[u.upcase].nil?
+			m = @@mm[u]
+			m.chop unless m.nil?
 		end
  	end
 end

data/lib/toPinyin/version.rb

@@ -1,3 +1,3 @@
 module Topinyin
-  VERSION = "0.0.3"
+  VERSION = "0.0.4"
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: toPinyin
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 23
   prerelease: false
   segments: 
   - 0
   - 0
-  - 3
-  version: 0.0.3
+  - 4
+  version: 0.0.4
 platform: ruby
 authors: 
 - pierr.chen
@@ -34,6 +34,7 @@ files:
 - README
 - Rakefile
 - lib/Uni2Pinyin
+- lib/performance.rb
 - lib/test.rb
 - lib/toPinyin.rb
 - lib/toPinyin/uniToPyMap.rb