generate_constants.rb in unicode-emoji-3.1.1

- old
+ new

@@ -13,11 +13,13 @@
 def write_regex(const_name, regex, dirpath)
   filename = const_name.to_s.downcase
   filepath = File.join(dirpath, "#{filename}.rb")
 
   File.write(filepath, <<~CONTENT)
-    # This file was generated. Please, do not edit this file by hand.
+    # This file was generated by a script, please do not edit it by hand.
+    # See `$ rake generate_constants` and data/generate_constants.rb for more info.
+
     module Unicode
       module Emoji
         #{const_name} = #{regex.inspect}
       end
     end
@@ -113,17 +115,20 @@
       emoji_modifier_sequence,
       non_component_emoji_presentation_sequence,
       emoji_well_formed_flag_sequence,
     )
 
+  # Sort to make sure complex sequences match first
   emoji_rgi_tag_sequence = \
-    pack_and_join(RECOMMENDED_SUBDIVISION_FLAGS)
+    pack_and_join(RECOMMENDED_SUBDIVISION_FLAGS.sort_by(&:length).reverse)
 
   emoji_valid_tag_sequence = \
     "(?:" +
       pack(EMOJI_TAG_BASE_FLAG) +
-      "(?:" + VALID_SUBDIVISIONS.map{ |sd| Regexp.escape(sd.tr("\u{20}-\u{7E}", "\u{E0020}-\u{E007E}"))}.join("|") + ")" +
+      "(?:" + VALID_SUBDIVISIONS.sort_by(&:length).reverse.map{ |sd|
+        Regexp.escape(sd.tr("\u{20}-\u{7E}", "\u{E0020}-\u{E007E}"))
+      }.join("|") + ")" +
       pack(CANCEL_TAG) +
     ")"
 
   emoji_well_formed_tag_sequence = \
     "(?:" +
@@ -133,11 +138,12 @@
       ) +
       pack_and_join(TAGS) + "+" +
       pack(CANCEL_TAG) +
     ")"
 
+  # Sort to make sure complex sequences match first
   emoji_rgi_zwj_sequence = \
-    pack_and_join(RECOMMENDED_ZWJ_SEQUENCES)
+    pack_and_join(RECOMMENDED_ZWJ_SEQUENCES.sort_by(&:length).reverse)
 
   emoji_valid_zwj_element = \
     join(
       emoji_modifier_sequence,
       emoji_presentation_sequence,