zhongwen_tools 0.18.4 → 0.19.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 87292bf853bdd642cf95b4f28d163ba79ca92ffd
+  data.tar.gz: 4ecc9dce49d0eba08b910f0dceea0da7001a3fde
+SHA512:
+  metadata.gz: b39dfe2644f3f10776635d601fccb2d383ba356769556f8338135b7b9b46ada44753bd9d554816b8277b21f0b236fc9d0cc031abc05e16e81787e4764c1280d1
+  data.tar.gz: 56f86364a7b9a882353287a85648af8b110b09205493f7d918fca5d69a950367e33f9c71a0d3a3871724df9395ac4c3b6f1ae8b592d5c845db4d3344389fa87c

data/lib/zhongwen_tools/number.rb

@@ -4,23 +4,19 @@ require 'zhongwen_tools/zhongwen'
 require 'zhongwen_tools/romanization/pinyin'
 require 'zhongwen_tools/number/number_table'
 
-# Number.to_pyn, to_i, to_zhs, etc.
 module ZhongwenTools
+  # Number.to_pyn, to_i, to_zhs, etc.
   module Number
     def self.number?(obj)
-      klass = obj.class
-
-      if klass == String
+      case obj
+      when String
         regex = /([\d]|#{ZhongwenTools::Regex.zh_numbers}){1,}/
-          "#{obj}".gsub(regex, '') == ''
-      elsif klass == Integer
-        true
-      elsif klass == Fixnum
+        "#{obj}".gsub(regex, '') == ''
+      when Integer, Fixnum, Float
         true
       end
     end
 
-    #needs to be a class method
     %w(i zhs zht pyn).each do |action|
       define_singleton_method("to_#{ action }") do |*args|
         obj, from, separator = args
@@ -31,9 +27,8 @@ module ZhongwenTools
     end
 
     def self.to_zh(obj, type = :zhs, from = nil)
-      type = type.to_sym
-
-      if type == :zht
+      case type.to_sym
+      when :zht
         to_zht(obj, from)
       else
         to_zhs(obj, from)
@@ -51,7 +46,7 @@ module ZhongwenTools
       if to == :i
         combine_integers(number)
       elsif to == :pyn
-        regex = /#{ %w(yi4 wan4 qian1 bai2 shi2).map{ |x| 'ling2\-' + x }.join('|')}/
+        regex = /#{ %w(yi4 wan4 qian1 bai2 shi2).map { |x| 'ling2\-' + x }.join('|')}/
         finalize_number(number, '-').gsub(regex, '').gsub(/\-+/, '-').gsub(/\-$/, '')
       else
         finalize_number(number)
@@ -65,15 +60,13 @@ module ZhongwenTools
         :i
       else
         if ZhongwenTools::Zhongwen.zh?(obj)
-          # need to check zhs or zht
           if zht?(obj)
             :zht
           else
             :zhs
           end
-        else #assume it is pyn
-          #if ZhongwenTools.const_defined?(:Romanization) && ZhongwenTools::Romanization.romanization?(obj)
-          # might need to convert to pyn
+        else # assume it is pyn
+          # FIXME: might need to convert to pyn
           :pyn
         end
       end
@@ -105,13 +98,13 @@ module ZhongwenTools
       pyns = ZhongwenTools::Romanization::Pinyin.split_pyn(pyn)
 
       pyns.map do |p|
-        convert_number(p).fetch( to ){ p }
+        convert_number(p).fetch(to) { p }
       end
     end
 
     def self.convert_from_zh(to, number)
       converted_number = number.chars.map do |zh|
-        convert_number(zh).fetch(to){ zh }
+        convert_number(zh).fetch(to) { zh }
       end
 
       converted_number
@@ -127,7 +120,7 @@ module ZhongwenTools
       integers.each_with_index do |curr_num, i|
         next if skipped == i
 
-        if (i+2) <= length
+        if (i + 2) <= length
           number, i = combine_integer(integers, number, curr_num, i)
           skipped = i + 1
         else
@@ -139,18 +132,16 @@ module ZhongwenTools
     end
 
     def self.year?(integers)
-      integers.select{ |i| i < 10 }.size == integers.size
+      integers.select { |i| i < 10 }.size == integers.size
     end
 
     def self.combine_year(integers)
-      integers.map{ |i| i.to_s }.join.to_i
+      integers.map(&:to_s).join.to_i
     end
 
-    def self.combine_integer integers, result, curr_num, i
+    def self.combine_integer(integers, result, curr_num, i)
       next_number = integers[i + 1]
-      if number_multiplier? next_number
-        result += next_number * curr_num
-      end
+      result += next_number * curr_num if number_multiplier?(next_number)
 
       [result, i]
     end
@@ -163,8 +154,7 @@ module ZhongwenTools
       [10, 100, 1_000, 10_000, 100_000_000].include? number
     end
 
-
-    def self.convert_from_integer to, int
+    def self.convert_from_integer(to, int)
       # FIXME: this will fail for numbers over 1 billion.
       result = []
       nums = convert_integer_to_reversed_array_of_integers(int)
@@ -191,11 +181,11 @@ module ZhongwenTools
     end
 
     def self.convert_integer_to_reversed_array_of_integers(int)
-      int.to_s.chars.to_a.reverse.map{ |x| x.to_i }
+      int.to_s.chars.to_a.reverse.map(&:to_i)
     end
 
     def self.wan_ok?(num, wan, i)
-        (num == 1 && (10**(i) / 10_000 ** wan) != 10) || num != 1
+      (num == 1 && (10**(i) / 10_000**wan) != 10) || num != 1
     end
 
     def self.wan_level(wan, i)
@@ -210,18 +200,18 @@ module ZhongwenTools
     end
 
     def self.convert_integer(int, to)
-      NUMBERS_TABLE.find{ |x| x[:i] == int }.fetch(to){ 0 }
+      NUMBERS_TABLE.find { |x| x[:i] == int }.fetch(to) { 0 }
     end
 
     def self.convert_number(number)
-      NUMBERS_TABLE.find{ |x|  x[:zhs] == number || x[:zht] == number  || x[:pyn] == number }
+      NUMBERS_TABLE.find { |x|  x[:zhs] == number || x[:zht] == number || x[:pyn] == number }
     end
 
     def self.finalize_number(number, separator = '')
       # FIXME: is finalize_number the best name you can think of?
       # NOTE: Figuring out usage of "liang" vs. "er" is pretty
       #       difficult, so always use "er" instead.
-      number.join(separator).gsub(/零[#{ Regex.zh_number_multiple }]*/u,'')
+      number.join(separator).gsub(/零[#{ Regex.zh_number_multiple }]*/u, '')
     end
   end
 end

data/lib/zhongwen_tools/regex.rb

@@ -10,6 +10,18 @@ module ZhongwenTools
       @py ||= /(#{pyn_regexes.map { |_k, v| v.to_s[7..-2].gsub(/[aeiouv]/, py_tones) }.join('|')}([\s\-])?)/
     end
 
+    def self.pinyin_caps
+      @pinyin_caps ||= /#{py}|[ĀÁǍÀĒÉĚÈĪÍǏÌŌÓǑÒ]|#{py_syllabic_nasals}/
+    end
+
+    def self.pyn_and_pynt
+      @pyn_and_pynt ||= /(#{ Regex.pyn }|#{ Regex.pinyin_toneless })/
+    end
+
+    def self.capture_pinyin_toneless
+      @capture_pinyin_toneless ||= /(#{ Regex.pinyin_toneless })/
+    end
+
     def self.pinyin_num
       # FIXME: n?g? might need to be replaced with (ng|n)?
       /(([BPMFDTNLGKHZCSRJQXWYbpmfdtnlgkhzcsrjqxwy]?[h]?)(A[io]?|a[io]?|i[aeu]?o?|Ei?|ei?|Ou?|ou?|u[aoe]?i?|ve?)?(n?g?)(r?)([1-5])(\-+)?)/
@@ -24,11 +36,11 @@ module ZhongwenTools
     end
 
     def self.capital_letters
-      /(#{Regexp.union(ZhongwenTools::Caps::CAPS.keys)})/
+      @capital_letters ||=  /(#{Regexp.union(ZhongwenTools::Caps::CAPS.keys)})/
     end
 
     def self.lowercase_letters
-      /(#{Regexp.union(ZhongwenTools::Caps::CAPS.values)})/
+      @lowercase_letters ||= /(#{Regexp.union(ZhongwenTools::Caps::CAPS.values)})/
     end
 
     def self.zh
@@ -41,7 +53,7 @@ module ZhongwenTools
 
     def self.zh_punc
       # TODO: includes non-zh punctuation codes. Should only include punctuation in CJK ranges.
-      /[\u2E00-\u2E2E]|[\u2E30-\u2E3B]|[\u3001-\u3003]|[\u3008-\u3011]|[\u3014-\u301F]|[\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF]|[\uA60D-\uA60F]|[\uA673\uA67E]|[\uA6F2-\uA6F7]|[\uA874-\uA877]|[\uA8CE\uA8CF]|[\uA8F8-\uA8FA]|[\uA92E\uA92F\uA95F]|[\uA9C1-\uA9CD]|[\uA9DE\uA9DF]|[\uAA5C-\uAA5F]|[\uAADE\uAADF\uAAF0\uAAF1\uABEB\uFD3E\uFD3F]|[\uFE10-\uFE19]|[\uFE30-\uFE52]|[\uFE54-\uFE61]|[\uFE63\uFE68\uFE6A\uFE6B]|[\uFF01-\uFF03]|[\uFF05-\uFF0A]|[\uFF0C-\uFF0F]|[\uFF1A\uFF1B\uFF1F\uFF20]|[\uFF3B-\uFF3D]|[\uFF3F\uFF5B\uFF5D]|[\uFF5F-\uFF65]/
+      @zh_punc ||= /[\u2E00-\u2E2E]|[\u2E30-\u2E3B]|[\u3001-\u3003]|[\u3008-\u3011]|[\u3014-\u301F]|[\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF]|[\uA60D-\uA60F]|[\uA673\uA67E]|[\uA6F2-\uA6F7]|[\uA874-\uA877]|[\uA8CE\uA8CF]|[\uA8F8-\uA8FA]|[\uA92E\uA92F\uA95F]|[\uA9C1-\uA9CD]|[\uA9DE\uA9DF]|[\uAA5C-\uAA5F]|[\uAADE\uAADF\uAAF0\uAAF1\uABEB\uFD3E\uFD3F]|[\uFE10-\uFE19]|[\uFE30-\uFE52]|[\uFE54-\uFE61]|[\uFE63\uFE68\uFE6A\uFE6B]|[\uFF01-\uFF03]|[\uFF05-\uFF0A]|[\uFF0C-\uFF0F]|[\uFF1A\uFF1B\uFF1F\uFF20]|[\uFF3B-\uFF3D]|[\uFF3F\uFF5B\uFF5D]|[\uFF5F-\uFF65]/
     end
 
     def self.zh_numbers

data/lib/zhongwen_tools/romanization/pinyin.rb

@@ -38,10 +38,15 @@ module ZhongwenTools
       end
 
       def self.split_pyn(str)
+        # NOTE: This methods is called quite frequently. Unfortunately, it was
+        #       slower than it needed to be. After looking into several
+        #       optimizations, I ended up settling on one that cached the Regexp
+        #       creation.
         # FIXME: ignore punctuation
-        regex = str[/[1-5]/].nil? ? /(#{ Regex.pinyin_toneless })/ : /(#{ Regex.pyn }|#{ Regex.pinyin_toneless })/
-        # NOTE: p[/[^\-]*/].to_s is 25% faster than gsub('-', '')
-        str.scan(regex).map { |arr| arr[0].strip[/[^\-]*/].to_s }.flatten
+        regex = str[simple_tone_numbers].nil? ? Regex.capture_pinyin_toneless : Regex.pyn_and_pynt
+        # NOTE: Fast Ruby: p[/[^\-]*/].to_s is 25% faster than gsub('-', '')
+        strip_regex = not_hyphen_regex
+        str.scan(regex).flat_map { |arr| arr[0].strip[strip_regex].to_s }
       end
 
       def self.split_py(str)
@@ -110,6 +115,14 @@ module ZhongwenTools
 
       private
 
+      def self.simple_tone_numbers
+        @simple_tone_numbers ||= /[1-5]/
+      end
+
+      def self.not_hyphen_regex
+        @not_hyphen_regex ||= /[^\-]*/
+      end
+
       def self.pyn_matches_properly?(pyn_arr, normalized_str)
         pyn_arr.join('') == normalized_str
       end
@@ -190,7 +203,7 @@ module ZhongwenTools
       end
 
       def self.capitalized?(str)
-        first_letter = str[/#{Regex.py}|[ĀÁǍÀĒÉĚÈĪÍǏÌŌÓǑÒ]|#{Regex.py_syllabic_nasals}/][0]
+        first_letter = str[ZhongwenTools::Regex.pinyin_caps][0]
 
         first_letter != Caps.downcase(first_letter)
       end

data/lib/zhongwen_tools/version.rb

@@ -1,3 +1,3 @@
 module ZhongwenTools
-  VERSION = '0.18.4'
+  VERSION = '0.19.0'
 end

data/test/test_number.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
-$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+$LOAD_PATH.unshift File.join(File.dirname(__FILE__), '..', 'lib')
 
 require './test/test_helper'
 require 'zhongwen_tools/number'
@@ -9,21 +9,22 @@ class TestNumber < Minitest::Test
       { zhs: '一万二千七', zht: '一萬二千七', i: 12_007, pyn: 'yi1-wan4-er4-qian1-qi1' },
       { zhs: '三千六十三', zht: '三千六十三', i: 3_063, pyn: 'san1-qian1-liu4-shi2-san1' },
       { zhs: '一百五十',   zht: '一百五十', i: 150, pyn: 'yi1-bai2-wu3-shi2' },
-      #{ zhs: '三千亿', i: 300_000_000_000, pyn: '' },
+      # { zhs: '三千亿', i: 300_000_000_000, pyn: '' },
     ]
 
     @liang_number = { zhs: '一万两千七', i: 12_007, pyn: '' }
     @date_numbers = [
       { zhs: '一九六六', i: 1966, pyn: '' },
-      { zhs: '二零零八', i: 2008, pyn: '' },
+      { zhs: '二零零八', i: 2008, pyn: '' }
     ]
   end
 
   def test_number?
     assert ZhongwenTools::Number.number? '一'
     assert ZhongwenTools::Number.number? 1
+    assert ZhongwenTools::Number.number? 1.0
 
-    @numbers.map{ |n| n[:zhs]}.each do |zh|
+    @numbers.map { |n| n[:zhs] }.each do |zh|
       assert ZhongwenTools::Number.number?(zh), "#{zh}"
     end
   end
@@ -35,7 +36,6 @@ class TestNumber < Minitest::Test
         assert_equal n[:pyn], ZhongwenTools::Number.to_pyn(n[type])
       end
     end
-
   end
 
   def test_to_zhs
@@ -73,13 +73,13 @@ class TestNumber < Minitest::Test
     end
 
     @date_numbers.each do |n|
-        assert_equal n[:i], ZhongwenTools::Number.to_i(n[:zhs])
+      assert_equal n[:i], ZhongwenTools::Number.to_i(n[:zhs])
     end
   end
 
   def test_large_numbers
     assert_equal '五十万',  ZhongwenTools::Number.to_zhs(500_000)
     assert_equal '五十亿',  ZhongwenTools::Number.to_zhs(5_000_000_000)
-    #assert_equal '五万亿',  ZhongwenTools::Number.to_zhs(5_000_000_000_000)
+    # assert_equal '五万亿',  ZhongwenTools::Number.to_zhs(5_000_000_000_000)
   end
 end

metadata

@@ -1,164 +1,163 @@
 --- !ruby/object:Gem::Specification
 name: zhongwen_tools
 version: !ruby/object:Gem::Version
-  version: 0.18.4
-  prerelease: 
+  version: 0.19.0
 platform: ruby
 authors:
 - Steven Daniels
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-10 00:00:00.000000000 Z
+date: 2015-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.1'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.9.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.9.1
 - !ruby/object:Gem::Dependency
   name: simplecov-gem-adapter
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.1
 - !ruby/object:Gem::Dependency
   name: coveralls
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.7'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.7.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.7'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.7.0
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '5.5'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 5.5.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '5.5'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 5.5.1
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.10'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.10.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0.10'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 0.10.1
 - !ruby/object:Gem::Dependency
   name: minitest-reporters
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.10
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.10
+- !ruby/object:Gem::Dependency
+  name: memory_profiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.0.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.0.4
 description: Chinese tools for romanization conversions and other helpful string functions
   for Chinese.
 email:
@@ -167,7 +166,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .travis.yml
+- ".travis.yml"
 - Gemfile
 - README.md
 - Rakefile
@@ -217,27 +216,26 @@ files:
 homepage: https://github.com/stevendaniels/zhongwen_tools
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: zhongwen_tools
-rubygems_version: 1.8.23.2
+rubygems_version: 2.4.5
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Zhongwen Tools provide romanization conversions and helper methods for Chinese.
 test_files:
 - test/test_caps.rb
@@ -255,3 +253,4 @@ test_files:
 - test/test_unicode.rb
 - test/test_uri.rb
 - test/test_zhongwen.rb
+has_rdoc: