Native regexes: Use native Emoji props for Emoji text presentation

janlelis · Oct 20, 2024 · 9852eba · 9852eba
1 parent 7aa5987
commit 9852eba
Show file tree

Hide file tree

Showing 10 changed files with 14 additions and 11 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ### 3.8.0 (unreleased)
 
+- Native regexes: Use native Emoji props for Emoji text presentation
 - Improve documentation and add detailed table about which regex has which features
 - Add specs running through `emoji-text.txt` and classify qualification statuses per regex
 

diff --git a/data/generate_constants.rb b/data/generate_constants.rb
@@ -68,10 +68,10 @@ def pack_and_join(ords)
   end
 end
 
-def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_component:, emoji_presentation:, picto:, picto_no_emoji:)
+def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_component:, emoji_presentation:, text_presentation:, picto:, picto_no_emoji:)
   emoji_presentation_sequence = \
     join(
-      pack_and_join(TEXT_PRESENTATION) + pack(EMOJI_VARIATION_SELECTOR),
+      text_presentation + pack(EMOJI_VARIATION_SELECTOR),
       emoji_presentation + "(?!" + pack(TEXT_VARIATION_SELECTOR) + ")" + pack(EMOJI_VARIATION_SELECTOR) + "?",
     )
 
@@ -83,7 +83,7 @@ def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_compo
 
   text_presentation_sequence = \
     join(
-      pack_and_join(TEXT_PRESENTATION)+ "(?!" + join(emoji_modifier, pack(EMOJI_VARIATION_SELECTOR)) + ")" + pack(TEXT_VARIATION_SELECTOR) + "?",
+      text_presentation + "(?!" + join(emoji_modifier, pack(EMOJI_VARIATION_SELECTOR)) + ")" + pack(TEXT_VARIATION_SELECTOR) + "?",
       emoji_presentation + pack(TEXT_VARIATION_SELECTOR),
     )
 
@@ -246,6 +246,7 @@ def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_compo
   emoji_modifier_base:  pack_and_join(EMOJI_MODIFIER_BASES),
   emoji_component:      pack_and_join(EMOJI_COMPONENT),
   emoji_presentation:   pack_and_join(EMOJI_PRESENTATION),
+  text_presentation:    pack_and_join(TEXT_PRESENTATION),
   picto:                pack_and_join(EXTENDED_PICTOGRAPHIC),
   picto_no_emoji:       pack_and_join(EXTENDED_PICTOGRAPHIC_NO_EMOJI)
 )
@@ -257,6 +258,7 @@ def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_compo
   emoji_modifier_base:  "\\p{EBase}",
   emoji_component:      "\\p{EComp}",
   emoji_presentation:   "\\p{EPres}",
+  text_presentation:    "\\p{Emoji}(?<!\\p{EPres})",
   picto:                "\\p{ExtPict}",
   picto_no_emoji:       "\\p{ExtPict}(?<!\\p{Emoji})"
 )

diff --git a/lib/unicode/emoji/generated_native/regex.rb b/lib/unicode/emoji/generated_native/regex.rb
diff --git a/lib/unicode/emoji/generated_native/regex_basic.rb b/lib/unicode/emoji/generated_native/regex_basic.rb
@@ -3,6 +3,6 @@
 
 module Unicode
   module Emoji
-    REGEX_BASIC = /(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)/
+    REGEX_BASIC = /(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)/
   end
 end
diff --git a/lib/unicode/emoji/generated_native/regex_include_text.rb b/lib/unicode/emoji/generated_native/regex_include_text.rb
diff --git a/lib/unicode/emoji/generated_native/regex_text.rb b/lib/unicode/emoji/generated_native/regex_text.rb
@@ -3,6 +3,6 @@
 
 module Unicode
   module Emoji
-    REGEX_TEXT = /(?:(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳](?!(?:\p{EMod}|️))︎?|\p{EPres}︎)|(?:\#⃣|\*⃣|0⃣|1⃣|2⃣|3⃣|4⃣|5⃣|6⃣|7⃣|8⃣|9⃣))/
+    REGEX_TEXT = /(?:(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})(?!(?:\p{EMod}|️))︎?|\p{EPres}︎)|(?:\#⃣|\*⃣|0⃣|1⃣|2⃣|3⃣|4⃣|5⃣|6⃣|7⃣|8⃣|9⃣))/
   end
 end
diff --git a/lib/unicode/emoji/generated_native/regex_valid.rb b/lib/unicode/emoji/generated_native/regex_valid.rb
diff --git a/lib/unicode/emoji/generated_native/regex_valid_include_text.rb b/lib/unicode/emoji/generated_native/regex_valid_include_text.rb
diff --git a/lib/unicode/emoji/generated_native/regex_well_formed.rb b/lib/unicode/emoji/generated_native/regex_well_formed.rb
@@ -3,6 +3,6 @@
 
 module Unicode
   module Emoji
-    REGEX_WELL_FORMED = /(?:(?:(?:(?:\p{EBase}\p{EMod}|(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{Emoji})‍)+(?:\p{EBase}\p{EMod}|(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{Emoji}))|(?:(?:(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{EBase}\p{EMod})[󠀰-󠀹󠁡-󠁺]{1,30}󠁿)|(?:[\#\*0-9]️⃣|\p{EBase}\p{EMod}|(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{RI}{2}))/
+    REGEX_WELL_FORMED = /(?:(?:(?:(?:\p{EBase}\p{EMod}|(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{Emoji})‍)+(?:\p{EBase}\p{EMod}|(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{Emoji}))|(?:(?:(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{EBase}\p{EMod})[󠀰-󠀹󠁡-󠁺]{1,30}󠁿)|(?:[\#\*0-9]️⃣|\p{EBase}\p{EMod}|(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{RI}{2}))/
   end
 end
diff --git a/lib/unicode/emoji/generated_native/regex_well_formed_include_text.rb b/lib/unicode/emoji/generated_native/regex_well_formed_include_text.rb
@@ -3,6 +3,6 @@
 
 module Unicode
   module Emoji
-    REGEX_WELL_FORMED_INCLUDE_TEXT = /(?-mix:(?:(?:(?:\p{EBase}\p{EMod}|(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{Emoji})‍)+(?:\p{EBase}\p{EMod}|(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{Emoji}))|(?:(?:(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{EBase}\p{EMod})[󠀰-󠀹󠁡-󠁺]{1,30}󠁿)|(?:[\#\*0-9]️⃣|\p{EBase}\p{EMod}|(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]️|\p{EPres}(?!︎)️?)|\p{RI}{2}))|(?-mix:(?!\p{EComp})(?:[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳](?!(?:\p{EMod}|️))︎?|\p{EPres}︎)|(?:\#⃣|\*⃣|0⃣|1⃣|2⃣|3⃣|4⃣|5⃣|6⃣|7⃣|8⃣|9⃣))/
+    REGEX_WELL_FORMED_INCLUDE_TEXT = /(?-mix:(?:(?:(?:\p{EBase}\p{EMod}|(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{Emoji})‍)+(?:\p{EBase}\p{EMod}|(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{Emoji}))|(?:(?:(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{EBase}\p{EMod})[󠀰-󠀹󠁡-󠁺]{1,30}󠁿)|(?:[\#\*0-9]️⃣|\p{EBase}\p{EMod}|(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})️|\p{EPres}(?!︎)️?)|\p{RI}{2}))|(?-mix:(?!\p{EComp})(?:\p{Emoji}(?<!\p{EPres})(?!(?:\p{EMod}|️))︎?|\p{EPres}︎)|(?:\#⃣|\*⃣|0⃣|1⃣|2⃣|3⃣|4⃣|5⃣|6⃣|7⃣|8⃣|9⃣))/
   end
 end