generate_constants.rb in unicode-emoji-3.7.0

- old
+ new

@@ -95,14 +95,11 @@
 
   emoji_valid_flag_sequence = \
     pack_and_join(VALID_REGION_FLAGS)
 
   emoji_well_formed_flag_sequence = \
-    "(?:" +
-      pack_and_join(REGIONAL_INDICATORS) +
-      pack_and_join(REGIONAL_INDICATORS) +
-    ")"
+    '\p{RI}{2}'
 
   emoji_valid_core_sequence = \
     join(
       # emoji_character,
       emoji_keycap_sequence,
@@ -126,22 +123,22 @@
 
   emoji_valid_tag_sequence = \
     "(?:" +
       pack(EMOJI_TAG_BASE_FLAG) +
       "(?:" + VALID_SUBDIVISIONS.sort_by(&:length).reverse.map{ |sd|
-        Regexp.escape(sd.tr("\u{20}-\u{7E}", "\u{E0020}-\u{E007E}"))
+        sd.tr("\u{30}-\u{39}\u{61}-\u{7A}", "\u{E0030}-\u{E0039}\u{E0061}-\u{E007A}")
       }.join("|") + ")" +
       pack(CANCEL_TAG) +
     ")"
 
   emoji_well_formed_tag_sequence = \
     "(?:" +
       join(
         non_component_emoji_presentation_sequence,
         emoji_modifier_sequence,
       ) +
-      pack_and_join(TAGS) + "+" +
+      pack_and_join(SPEC_TAGS) + "{1,30}" +
       pack(CANCEL_TAG) +
     ")"
 
   # Sort to make sure complex sequences match first
   emoji_rgi_zwj_sequence = \
@@ -178,19 +175,39 @@
       emoji_valid_zwj_sequence,
       emoji_well_formed_tag_sequence,
       emoji_well_formed_core_sequence,
     )
 
+  emoji_possible_modification = \
+    join(
+      emoji_modifier,
+      pack([EMOJI_VARIATION_SELECTOR, EMOJI_KEYCAP_SUFFIX]) + "?",
+      "[󠀠-󠁾]+󠁿" # raw tags
+    )
+
+  emoji_possible_zwj_element = \
+    join(
+      emoji_well_formed_flag_sequence,
+      emoji_character + emoji_possible_modification + "?"
+    )
+
+  emoji_possible = \
+    emoji_possible_zwj_element + "(?:" + pack(ZWJ) + emoji_possible_zwj_element + ")*"
+
   regexes = {}
 
   # Matches basic singleton emoji and all kind of sequences, but restrict zwj and tag sequences to known sequences (rgi)
   regexes[:REGEX] = Regexp.compile(emoji_rgi_sequence)
 
   # Matches basic singleton emoji and all kind of valid sequences
   regexes[:REGEX_VALID] = Regexp.compile(emoji_valid_sequence)
 
   # Matches basic singleton emoji and all kind of sequences
   regexes[:REGEX_WELL_FORMED] = Regexp.compile(emoji_well_formed_sequence)
+
+  # Quick test which might lead to false positves
+  # See https://www.unicode.org/reports/tr51/#EBNF_and_Regex
+  regexes[:REGEX_POSSIBLE] = Regexp.compile(emoji_possible)
 
   # Matches only basic single, non-textual emoji
   # Ignores "components" like modifiers or simple digits
   regexes[:REGEX_BASIC] = Regexp.compile(
     "(?!" + emoji_component + ")" + emoji_presentation_sequence