emoji-regex 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: edfcf4b0f99966f3383647592cc6476ba81987ab
-  data.tar.gz: 350ae4ba0a7739ecbada3be6f676b2f84b4a9ea4
+  metadata.gz: aff4ba19125ff68b4dbc92ba6a9ecb43051200c5
+  data.tar.gz: e6c10bdca195eb5f7bf40f6738b5d8f7e23bbb2e
 SHA512:
-  metadata.gz: cd8ebeb0a23c6b13fed77edb3e2baf519ad18ee92b84dcb43ea92caff50663ced62079c2dadc4ab626530609ae5440bf79651496ca9ec8949fea53d8b7207525
-  data.tar.gz: 53648372e78593c6464acc0d37e743433c32433ee8b76c15fdda1f2f53a2f798c3cc3aa24f9b36cddec7ada188782fa9c02d2a0c36f888c0b1d61b7f48231fba
+  metadata.gz: 85e0d80a9e3f5616dca5a9b988356b7907dc23eb8869733b55184717b10fbdd09388477ef27cd1b59f1f931975f51d9735b6c2864bd24211b2c00c285db21184
+  data.tar.gz: f760cc56558bf8c6105705f527fee4ce0a6fa7ebb8e9b9e46c299f912ad1540afa5112537715e14a32f2a274d0365922e711d476c23190527e079cde5c156c8a

data/emoji-regex.gemspec

@@ -16,7 +16,6 @@ Gem::Specification.new do |spec|
   spec.files = `git ls-files -z`.split("\x0").reject do |f|
     f.match(%r{^(test|spec|features)/})
   end
-
   spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']

data/lib/emoji-regex/fetcher.rb

@@ -2,20 +2,37 @@ require 'open-uri'
 
 module EmojiRegex
   class Fetcher
-    SOURCE = 'http://www.unicode.org/Public/emoji/1.0/emoji-data.txt'.freeze
+    SOURCE = 'https://www.unicode.org/Public/emoji/6.0/emoji-data.txt'.freeze
 
     def initialize
-      @emoji_code = open(SOURCE, &:read).split("\n").map { |x| x.split(" ;\t")[0] }
       @emoji_file_path = File.join(Dir.tmpdir, 'sorted_emoji.txt')
     end
 
     def save
-      @emoji_file.tap do
-        lines = @emoji_code.map { |line| line if line[0] != '#' }.compact.join("\n")
+      emoji_file = open(SOURCE, &:read)
+      emoji_code_lines = emoji_file.split("\n").map { |x| x.split(' ;')[0] }.compact.map(&:rstrip)
 
-        File.write(@emoji_file_path, lines)
+      emoji_codes = emoji_code_lines.each_with_object([]) do |line, result|
+        case line
+        when /^#/
+          nil
+        when /^(0023|002A|0030)/
+          nil
+        when /^.{4,5}\.\./
+          start_code_hex, end_code_hex = line.split('..')
+          base_10_code_range = (start_code_hex.to_i(16)..end_code_hex.to_i(16))
+          hex_codes = base_10_code_range.to_a.map { |base_10_code| base_10_code.to_s(16).rjust(4, '0').upcase }
+          hex_codes.each { |code| result << code }
+        else
+          result << line
+        end
+      end
+
+      File.open(@emoji_file_path, 'w') do |f|
+        f << emoji_codes.uniq.join("\n")
       end
     end
+
     alias update save
 
     def saved_path

data/lib/emoji-regex/maker.rb

@@ -2,47 +2,47 @@ module EmojiRegex
   class Maker
     def initialize
       @input_file_path = Fetcher.new.saved_path
-      @prev = -1
-      @prev_hex = ''
-      @left = ''
-      @ranges = []
+    end
+
+    def regex
+      regex = ranges.map do |e|
+        l = e[0]
+        r = e[1]
+        next if l == '' || r == '' || !l[/\s/].nil? || !r[/\s/].nil?
+        if l == r
+          "\\u{#{l}}"
+        else
+          "\\u{#{l}}-\\u{#{r}}"
+        end
+      end
+      regex.unshift '['
+      regex.push ']'
+
+      Regexp.new(regex.join)
     end
 
     def ranges
-      ranges =
-        File.open(@input_file_path).map do |line|
-          hex = line.to_i(16)
+      prev = -1
+      prev_hex = ''
+      left = ''
 
-          if [@prev, @prev + 1].include?(hex)
-            @prev, @prev_hex = [hex, line.chomp] && next
-          else
-            [@left, @prev_hex].tap do
-              @left = line.chomp
-              @prev = hex
-              @prev_hex = @left
-            end
-          end
+      ranges = File.open(@input_file_path).map do |line|
+        hex = line.to_i(16)
+        if hex == prev || hex == prev + 1
+          prev = hex
+          prev_hex = line.chomp
+          next
         end
+        range = [left, prev_hex]
+        left = line.chomp
+        prev = hex
+        prev_hex = left
+        range
+      end
 
       ranges
         .compact
-        .reject { |ary| ary[0].empty? || ary[1].empty? }
-    end
-
-    def regex
-      regex = '[' +
-              ranges.map do |range|
-                left = range[0]
-                right = range[1]
-                next if left == '' || right == '' || !left[/\s/].nil? || !right[/\s/].nil?
-
-                if left == right
-                  "\\u{#{left}}"
-                else
-                  "\\u{#{left}}-\\u{#{right}}"
-                end
-              end.join + ']'
-      Regexp.new(regex)
+        .reject { |a, b| a.empty? || b.empty? }
     end
   end
 end

data/lib/emoji-regex/version.rb

@@ -1,3 +1,3 @@
 module EmojiRegex
-  VERSION = '0.1.0'.freeze
+  VERSION = '0.1.1'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: emoji-regex
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Satoshi Ohmori
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-11 00:00:00.000000000 Z
+date: 2017-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -121,7 +121,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.2
+rubygems_version: 2.5.2.1
 signing_key: 
 specification_version: 4
 summary: Make regex for latest unicode emoji.