Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,9 @@ dasher.log
# Training files written by the engine to CWD when contexts are destroyed.
# This is a real bug (Tier 1 item: library should not write to CWD) — for
# now we ignore the leaked files so they don't pollute git status.
training_*.txt
# Root-anchored: Data/training/ holds the SHIPPED corpora and must stay
# trackable (training_emoji.txt was silently ignored by the bare pattern).
/training_*.txt

build-san/
build-tidy/
Expand Down
354 changes: 354 additions & 0 deletions Data/alphabets/alphabet.emoji.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,354 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE alphabet SYSTEM "../alphabet.dtd">
<!-- Emoji alphabet (issue Dasher-Android #61, option 2).

Language-neutral: any user can switch here from the toolbar to pick
emoji, then switch back — the engine's alphabet switch API makes this
a pure data asset. Nodes carry multi-codepoint labels (ZWJ sequences,
variation selectors); AlphIO stores the full label string as the
node's Text, so a selection commits the entire sequence atomically
(see ReadCharAttributes: Text = "text" attr, default Display/label).

Groups are kept to 9 topical clusters plus separators: Dasher's
zooming interface needs a shallow tree — two zoom levels to any
emoji. A flat 200-node root would be unusable.

Frequencies: training_emoji.txt provides mild ordering priors
(common juxtapositions); without training the engine falls back to
symbol-order defaults (NodeCreationManager "Dasher will still work").
NOTE: the trainer matches ONE code point per symbol lookup, so only
single-codepoint emoji are learnable from the corpus. The 31
multi-codepoint nodes (ZWJ sequences, VS16 variants like ✈️) always
take default frequencies — a longest-match trainer would be needed
to train those (engine follow-up, not blocking).
-->
<alphabet name="Emoji" orientation="LR" trainingFilename="training_emoji.txt" colorsName="Default">
<group name="Smileys and faces" label="😀">
<node label="😀"><textCharAction /></node>
<node label="😃"><textCharAction /></node>
<node label="😄"><textCharAction /></node>
<node label="😁"><textCharAction /></node>
<node label="😆"><textCharAction /></node>
<node label="😅"><textCharAction /></node>
<node label="🤣"><textCharAction /></node>
<node label="😂"><textCharAction /></node>
<node label="🙂"><textCharAction /></node>
<node label="😉"><textCharAction /></node>
<node label="😊"><textCharAction /></node>
<node label="😇"><textCharAction /></node>
<node label="🥰"><textCharAction /></node>
<node label="😍"><textCharAction /></node>
<node label="😘"><textCharAction /></node>
<node label="😋"><textCharAction /></node>
<node label="😜"><textCharAction /></node>
<node label="🤪"><textCharAction /></node>
<node label="🤨"><textCharAction /></node>
<node label="🧐"><textCharAction /></node>
<node label="🤓"><textCharAction /></node>
<node label="😎"><textCharAction /></node>
<node label="🥳"><textCharAction /></node>
<node label="😏"><textCharAction /></node>
<node label="😒"><textCharAction /></node>
<node label="😔"><textCharAction /></node>
<node label="🙁"><textCharAction /></node>
<node label="☹️"><textCharAction /></node>
<node label="🥺"><textCharAction /></node>
<node label="😢"><textCharAction /></node>
<node label="😭"><textCharAction /></node>
<node label="😤"><textCharAction /></node>
<node label="😠"><textCharAction /></node>
<node label="😡"><textCharAction /></node>
<node label="🤯"><textCharAction /></node>
<node label="😳"><textCharAction /></node>
<node label="🥵"><textCharAction /></node>
<node label="🥶"><textCharAction /></node>
<node label="😱"><textCharAction /></node>
<node label="😨"><textCharAction /></node>
<node label="😥"><textCharAction /></node>
<node label="🤗"><textCharAction /></node>
<node label="🤔"><textCharAction /></node>
<node label="🤭"><textCharAction /></node>
<node label="🙄"><textCharAction /></node>
<node label="😮"><textCharAction /></node>
<node label="🥱"><textCharAction /></node>
<node label="😴"><textCharAction /></node>
<node label="🤤"><textCharAction /></node>
<node label="😪"><textCharAction /></node>
<node label="🥴"><textCharAction /></node>
<node label="🤢"><textCharAction /></node>
<node label="🤮"><textCharAction /></node>
<node label="🤧"><textCharAction /></node>
<node label="😷"><textCharAction /></node>
<node label="🤒"><textCharAction /></node>
<node label="🤕"><textCharAction /></node>
<node label="🥲"><textCharAction /></node>
</group>
<group name="Gestures and hands" label="👍">
<node label="👍"><textCharAction /></node>
<node label="👎"><textCharAction /></node>
<node label="👍🏽"><textCharAction /></node>
<node label="👌"><textCharAction /></node>
<node label="🤌"><textCharAction /></node>
<node label="✌️"><textCharAction /></node>
<node label="🤞"><textCharAction /></node>
<node label="🤟"><textCharAction /></node>
<node label="🤘"><textCharAction /></node>
<node label="🤙"><textCharAction /></node>
<node label="👈"><textCharAction /></node>
<node label="👉"><textCharAction /></node>
<node label="👆"><textCharAction /></node>
<node label="👇"><textCharAction /></node>
<node label="☝️"><textCharAction /></node>
<node label="👋"><textCharAction /></node>
<node label="🤚"><textCharAction /></node>
<node label="🖐️"><textCharAction /></node>
<node label="✋"><textCharAction /></node>
<node label="🖖"><textCharAction /></node>
<node label="👏"><textCharAction /></node>
<node label="🙌"><textCharAction /></node>
<node label="🤲"><textCharAction /></node>
<node label="🤝"><textCharAction /></node>
<node label="🙏"><textCharAction /></node>
<node label="💪"><textCharAction /></node>
<node label="✍️"><textCharAction /></node>
</group>
<group name="Hearts and celebration" label="❤️">
<node label="❤️"><textCharAction /></node>
<node label="🧡"><textCharAction /></node>
<node label="💛"><textCharAction /></node>
<node label="💚"><textCharAction /></node>
<node label="💙"><textCharAction /></node>
<node label="💜"><textCharAction /></node>
<node label="🖤"><textCharAction /></node>
<node label="🤍"><textCharAction /></node>
<node label="🤎"><textCharAction /></node>
<node label="💔"><textCharAction /></node>
<node label="❣️"><textCharAction /></node>
<node label="💕"><textCharAction /></node>
<node label="💞"><textCharAction /></node>
<node label="💓"><textCharAction /></node>
<node label="💗"><textCharAction /></node>
<node label="💖"><textCharAction /></node>
<node label="💘"><textCharAction /></node>
<node label="💝"><textCharAction /></node>
<node label="✨"><textCharAction /></node>
<node label="⭐"><textCharAction /></node>
<node label="🌟"><textCharAction /></node>
<node label="💫"><textCharAction /></node>
<node label="🔥"><textCharAction /></node>
<node label="🎉"><textCharAction /></node>
<node label="🎊"><textCharAction /></node>
<node label="🎈"><textCharAction /></node>
<node label="🎁"><textCharAction /></node>
<node label="✅"><textCharAction /></node>
<node label="❌"><textCharAction /></node>
<node label="❗"><textCharAction /></node>
<node label="❓"><textCharAction /></node>
<node label="💯"><textCharAction /></node>
</group>
<group name="People and family" label="👪">
<node label="👶"><textCharAction /></node>
<node label="👧"><textCharAction /></node>
<node label="👦"><textCharAction /></node>
<node label="👩"><textCharAction /></node>
<node label="👨"><textCharAction /></node>
<node label="👵"><textCharAction /></node>
<node label="👴"><textCharAction /></node>
<node label="👮"><textCharAction /></node>
<node label="💁"><textCharAction /></node>
<node label="🙋"><textCharAction /></node>
<node label="🤦"><textCharAction /></node>
<node label="🤷"><textCharAction /></node>
<node label="💃"><textCharAction /></node>
<node label="🕺"><textCharAction /></node>
<node label="👫"><textCharAction /></node>
<node label="👪"><textCharAction /></node>
<node label="👨‍👩‍👧"><textCharAction /></node>
<node label="🤰"><textCharAction /></node>
<node label="👰"><textCharAction /></node>
</group>
<group name="Animals and nature" label="🐶">
<node label="🐶"><textCharAction /></node>
<node label="🐱"><textCharAction /></node>
<node label="🐭"><textCharAction /></node>
<node label="🐹"><textCharAction /></node>
<node label="🐰"><textCharAction /></node>
<node label="🦊"><textCharAction /></node>
<node label="🐻"><textCharAction /></node>
<node label="🐼"><textCharAction /></node>
<node label="🐨"><textCharAction /></node>
<node label="🐯"><textCharAction /></node>
<node label="🦁"><textCharAction /></node>
<node label="🐮"><textCharAction /></node>
<node label="🐷"><textCharAction /></node>
<node label="🐸"><textCharAction /></node>
<node label="🐵"><textCharAction /></node>
<node label="🐔"><textCharAction /></node>
<node label="🐧"><textCharAction /></node>
<node label="🐦"><textCharAction /></node>
<node label="🦆"><textCharAction /></node>
<node label="🦉"><textCharAction /></node>
<node label="🦋"><textCharAction /></node>
<node label="🐝"><textCharAction /></node>
<node label="🐞"><textCharAction /></node>
<node label="🐢"><textCharAction /></node>
<node label="🐙"><textCharAction /></node>
<node label="🐬"><textCharAction /></node>
<node label="🐳"><textCharAction /></node>
<node label="🌻"><textCharAction /></node>
<node label="🌹"><textCharAction /></node>
<node label="🌷"><textCharAction /></node>
<node label="🌸"><textCharAction /></node>
<node label="💐"><textCharAction /></node>
<node label="🌈"><textCharAction /></node>
<node label="☀️"><textCharAction /></node>
<node label="🌞"><textCharAction /></node>
<node label="🌙"><textCharAction /></node>
<node label="☁️"><textCharAction /></node>
<node label="❄️"><textCharAction /></node>
<node label="⚡"><textCharAction /></node>
</group>
<group name="Food and drink" label="🍕">
<node label="🍏"><textCharAction /></node>
<node label="🍎"><textCharAction /></node>
<node label="🍐"><textCharAction /></node>
<node label="🍊"><textCharAction /></node>
<node label="🍋"><textCharAction /></node>
<node label="🍌"><textCharAction /></node>
<node label="🍉"><textCharAction /></node>
<node label="🍇"><textCharAction /></node>
<node label="🍓"><textCharAction /></node>
<node label="🫐"><textCharAction /></node>
<node label="🍒"><textCharAction /></node>
<node label="🍑"><textCharAction /></node>
<node label="🥭"><textCharAction /></node>
<node label="🍍"><textCharAction /></node>
<node label="🥥"><textCharAction /></node>
<node label="🥝"><textCharAction /></node>
<node label="🍅"><textCharAction /></node>
<node label="🥑"><textCharAction /></node>
<node label="🌽"><textCharAction /></node>
<node label="🥕"><textCharAction /></node>
<node label="🍞"><textCharAction /></node>
<node label="🧀"><textCharAction /></node>
<node label="🥚"><textCharAction /></node>
<node label="🍳"><textCharAction /></node>
<node label="🥓"><textCharAction /></node>
<node label="🍔"><textCharAction /></node>
<node label="🍟"><textCharAction /></node>
<node label="🍕"><textCharAction /></node>
<node label="🌭"><textCharAction /></node>
<node label="🌮"><textCharAction /></node>
<node label="🌯"><textCharAction /></node>
<node label="🥗"><textCharAction /></node>
<node label="🍜"><textCharAction /></node>
<node label="🍣"><textCharAction /></node>
<node label="🍚"><textCharAction /></node>
<node label="🍛"><textCharAction /></node>
<node label="🍦"><textCharAction /></node>
<node label="🍰"><textCharAction /></node>
<node label="🎂"><textCharAction /></node>
<node label="🍫"><textCharAction /></node>
<node label="🍬"><textCharAction /></node>
<node label="☕"><textCharAction /></node>
<node label="🍵"><textCharAction /></node>
<node label="🧃"><textCharAction /></node>
<node label="🥤"><textCharAction /></node>
<node label="🍺"><textCharAction /></node>
<node label="🍷"><textCharAction /></node>
<node label="🥂"><textCharAction /></node>
</group>
<group name="Travel and places" label="🚗">
<node label="🚗"><textCharAction /></node>
<node label="🚕"><textCharAction /></node>
<node label="🚌"><textCharAction /></node>
<node label="🚑"><textCharAction /></node>
<node label="🚒"><textCharAction /></node>
<node label="🚚"><textCharAction /></node>
<node label="🚜"><textCharAction /></node>
<node label="🛵"><textCharAction /></node>
<node label="🚲"><textCharAction /></node>
<node label="🚨"><textCharAction /></node>
<node label="✈️"><textCharAction /></node>
<node label="🚀"><textCharAction /></node>
<node label="🚁"><textCharAction /></node>
<node label="⛵"><textCharAction /></node>
<node label="🚤"><textCharAction /></node>
<node label="🗺️"><textCharAction /></node>
<node label="🗽"><textCharAction /></node>
<node label="🗼"><textCharAction /></node>
<node label="🏰"><textCharAction /></node>
<node label="🏝️"><textCharAction /></node>
<node label="🏔️"><textCharAction /></node>
<node label="🏕️"><textCharAction /></node>
<node label="🏖️"><textCharAction /></node>
<node label="🏜️"><textCharAction /></node>
<node label="⛰️"><textCharAction /></node>
<node label="🌋"><textCharAction /></node>
</group>
<group name="Objects and activities" label="📱">
<node label="⌚"><textCharAction /></node>
<node label="📱"><textCharAction /></node>
<node label="💻"><textCharAction /></node>
<node label="⌨️"><textCharAction /></node>
<node label="🖥️"><textCharAction /></node>
<node label="🖨️"><textCharAction /></node>
<node label="🖱️"><textCharAction /></node>
<node label="📷"><textCharAction /></node>
<node label="📸"><textCharAction /></node>
<node label="🎥"><textCharAction /></node>
<node label="📞"><textCharAction /></node>
<node label="🔋"><textCharAction /></node>
<node label="🔌"><textCharAction /></node>
<node label="💡"><textCharAction /></node>
<node label="🔦"><textCharAction /></node>
<node label="🕯️"><textCharAction /></node>
<node label="💵"><textCharAction /></node>
<node label="💰"><textCharAction /></node>
<node label="💳"><textCharAction /></node>
<node label="💎"><textCharAction /></node>
<node label="🔑"><textCharAction /></node>
<node label="🔒"><textCharAction /></node>
<node label="🔓"><textCharAction /></node>
<node label="📌"><textCharAction /></node>
<node label="📍"><textCharAction /></node>
<node label="✂️"><textCharAction /></node>
<node label="📏"><textCharAction /></node>
<node label="🔧"><textCharAction /></node>
<node label="🔨"><textCharAction /></node>
<node label="⚙️"><textCharAction /></node>
<node label="🎯"><textCharAction /></node>
<node label="🎨"><textCharAction /></node>
<node label="🎬"><textCharAction /></node>
<node label="🎤"><textCharAction /></node>
<node label="🎧"><textCharAction /></node>
<node label="🎸"><textCharAction /></node>
<node label="🎹"><textCharAction /></node>
<node label="🥁"><textCharAction /></node>
<node label="🎮"><textCharAction /></node>
<node label="🎲"><textCharAction /></node>
</group>
<group name="Communication and symbols" label="💬">
<node label="✉️"><textCharAction /></node>
<node label="📧"><textCharAction /></node>
<node label="📨"><textCharAction /></node>
<node label="📤"><textCharAction /></node>
<node label="📥"><textCharAction /></node>
<node label="📦"><textCharAction /></node>
<node label="📰"><textCharAction /></node>
<node label="💬"><textCharAction /></node>
<node label="💭"><textCharAction /></node>
<node label="🗣️"><textCharAction /></node>
<node label="♻️"><textCharAction /></node>
<node label="🔱"><textCharAction /></node>
<node label="⭕"><textCharAction /></node>
<node label="⚠️"><textCharAction /></node>
<node label="🚫"><textCharAction /></node>
<node label="🔞"><textCharAction /></node>
<node label="📵"><textCharAction /></node>
</group>
<group name="Separators" label="␣">
<node label="␣" text=" "><textCharAction /></node>
<node label="¶" text="&#10;"><textCharAction /></node>
</group>
</alphabet>
Loading
Loading