compose/accent_*.json: improvements (more accents) (#770)

compose/accent_*.json: improve/complete implementation
compose/shift.json: uppercase for superscript letters & characters without preapplied uppercase versions

18 files changed, 381 insertions, 26 deletions

diff --git a/srcs/compose/accent_aigu.json b/srcs/compose/accent_aigu.json
index bfc04b8..f34b90c 100644
--- a/srcs/compose/accent_aigu.json
+++ b/srcs/compose/accent_aigu.json
@@ -1,17 +1,52 @@
 {
+  // latin
   "a": "á",
   "c": "ć",
   "e": "é",
+  "g": "ǵ",
   "i": "í",
+  "k": "ḱ",
   "l": "ĺ",
-  "ń": "ń",
+  "m": "ḿ", 
+  "n": "ń",
   "o": "ó",
+  "p": "ṕ",
   "r": "ŕ",
   "s": "ś",
   "u": "ú",
+  "w": "ẃ",
   "y": "ý",
   "z": "ź",
+  // extended latin (multiple diacritics)
+  "â": "ấ",
+  "ă": "ắ",
+  "å": "ǻ",
+  "æ": "ǽ",
+  "ç": "ḉ",
+  "ê": "ế",
+  "ē": "ḗ",
+  "ï": "ḯ",
+  "ô": "ố",
+  "ơ": "ớ",
+  "õ": "ṍ",
+  "ō": "ṓ",
+  "ø": "ǿ",
+  "ṡ": "ṥ",
   "ü": "ǘ",
+  "ư": "ứ",
+  "ũ": "ṹ",
+  // greek
+  "α": "ά",
+  "ε": "έ",
+  "η": "ή",
+  "ι": "ί",
+  "ο": "ό",
+  "υ": "ύ",
+  // cyrillic
+  "к": "ќ",
+  "г": "ѓ",
+  // combining character
+  "ą": "ą\u0301",
   "j": "j\u0301",
   "у": "у\u0301",
   "е": "е\u0301",
diff --git a/srcs/compose/accent_bar.json b/srcs/compose/accent_bar.json
index 14dc9f6..de3b940 100644
--- a/srcs/compose/accent_bar.json
+++ b/srcs/compose/accent_bar.json
@@ -1,8 +1,12 @@
 {
+  // latin
+  "2": "ƻ",
   "b": "ƀ",
   "c": "ꞓ",
   "d": "đ",
+  "f": "ꞙ",
   "g": "ǥ",
+  "h": "ħ",
   "i": "ɨ",
   "j": "ɉ",
   "k": "ꝁ",
@@ -14,5 +18,13 @@
   "t": "ŧ",
   "u": "ʉ",
   "y": "ɏ",
-  "z": "ƶ"
+  "z": "ƶ",
+  // extended latin
+  "ȷ": "ɟ",
+  // cyrillic
+  "о": "ө",
+  "ӧ": "ӫ",
+  "ү": "ұ",
+  "ь": "ҍ",
+  "х": "ӿ"
 }
diff --git a/srcs/compose/accent_caron.json b/srcs/compose/accent_caron.json
index 2e1a953..2684cb3 100644
--- a/srcs/compose/accent_caron.json
+++ b/srcs/compose/accent_caron.json
@@ -1,9 +1,14 @@
 {
+  // latin
   "a": "ǎ",
   "c": "č",
   "d": "ď",
   "e": "ě",
+  "g": "ǧ",
+  "h": "ȟ",
   "i": "ǐ",
+  "j": "ǰ", // no uppercase
+  "k": "ǩ",
   "l": "ľ",
   "n": "ň",
   "o": "ǒ",
@@ -12,5 +17,17 @@
   "t": "ť",
   "u": "ǔ",
   "z": "ž",
-  "ü": "ǚ"
+  // extended latin
+  "ṡ": "ṧ",
+  "ü": "ǚ",
+  "ʒ": "ǯ",
+  // combining character
+  "в": "в\u030C",
+  "г": "г\u030C",
+  "ғ": "ғ\u030C",
+  "д": "д\u030C",
+  "з": "з\u030C",
+  "р": "р\u030C",
+  "т": "т\u030C",
+  "х": "х\u030C"
 }
diff --git a/srcs/compose/accent_cedille.json b/srcs/compose/accent_cedille.json
index 3c05760..f04768b 100644
--- a/srcs/compose/accent_cedille.json
+++ b/srcs/compose/accent_cedille.json
@@ -1,4 +1,5 @@
 {
+  // latin
   "c": "ç",
   "d": "ḑ",
   "e": "ȩ",
@@ -9,5 +10,8 @@
   "n": "ņ",
   "r": "ŗ",
   "s": "ş",
-  "t": "ţ"
+  "t": "ţ",
+  // extended latin
+  "ć": "ḉ",
+  "ĕ": "ḝ"
 }
diff --git a/srcs/compose/accent_circonflexe.json b/srcs/compose/accent_circonflexe.json
index 448cc87..a16d063 100644
--- a/srcs/compose/accent_circonflexe.json
+++ b/srcs/compose/accent_circonflexe.json
@@ -1,4 +1,7 @@
 {
+  "+": "⨣",
+  "≈": "⩯",
+  // latin
   "a": "â",
   "c": "ĉ",
   "e": "ê",
@@ -9,7 +12,27 @@
   "o": "ô",
   "ŝ": "ŝ",
   "u": "û",
+  "w": "ŵ",
+  "x": "x̂",
+  "y": "ŷ",
   "z": "ẑ",
+  // extended latin
+  "á": "ấ",
+  "à": "ầ",
+  "ã": "ẫ",
+  "ạ": "ậ",
+  "ả": "ẩ",
+  "é": "ế",
+  "è": "ề",
+  "ẽ": "ễ",
+  "ẹ": "ệ",
+  "ẻ": "ể",
+  "ó": "ố",
+  "ò": "ồ",
+  "ơ": "ổ",
+  "õ": "ỗ",
+  "ọ": "ộ",
+  // combining characters
   "а": "а\u0302",
   "е": "е\u0302",
   "и": "и\u0302",
diff --git a/srcs/compose/accent_dot_above.json b/srcs/compose/accent_dot_above.json
index 12f2f58..b270a1d 100644
--- a/srcs/compose/accent_dot_above.json
+++ b/srcs/compose/accent_dot_above.json
@@ -17,5 +17,30 @@
   "w": "ẇ",
   "x": "ẋ",
   "y": "ẏ",
-  "z": "ż"
+  "z": "ż",
+  // remove dot since i and j already have one
+  "i": "ı",
+  "j": "ȷ",
+  // extended latin
+  "ā": "ǡ",
+  "ō": "ȱ",
+  "ś": "ṥ",
+  "ṣ": "ṩ",
+  "š": "ṧ",
+  "ſ": "ẛ",
+  // combining character
+  "k": "k\u0307",
+  "l": "l\u0307",
+  "q": "q\u0307",
+  "u": "u\u0307",
+  "v": "v\u0307",
+  // math
+  "∈": "⋵",
+  "⨯": "⨰",
+  "∧": "⩑",
+  "∨": "⩒",
+  "≡": "⩧",
+  "~": "⩪",
+  "⊆": "⫃",
+  "⊇": "⫄"
 }
diff --git a/srcs/compose/accent_dot_below.json b/srcs/compose/accent_dot_below.json
index 35114d0..c0bcfd4 100644
--- a/srcs/compose/accent_dot_below.json
+++ b/srcs/compose/accent_dot_below.json
@@ -1,14 +1,34 @@
 {
+  // latin
   "a": "ạ",
-  "ă": "ặ",
-  "â": "ậ",
+  "b": "ḅ",
+  "d": "ḍ",
   "e": "ẹ",
-  "ê": "ệ",
+  "h": "ḥ",
   "i": "ị",
+  "k": "ḳ",
+  "l": "ḷ",
+  "m": "ṃ",
+  "n": "ṇ",
   "o": "ọ",
+  "r": "ṛ",
+  "s": "ṣ",
+  "t": "ṭ",
+  "u": "ụ",
+  "v": "ṿ",
+  "w": "ẉ",
+  "y": "ỵ",
+  "z": "ẓ",
+  // extended latin
+  "ă": "ặ",
+  "â": "ậ",
+  "ê": "ệ",
   "ô": "ộ",
   "ơ": "ợ",
-  "u": "ụ",
+  "ṡ": "ṩ",
   "ư": "ự",
-  "y": "ỵ"
+  // math
+  "-": "⨪",
+  "+": "⨥",
+  "=": "⩦"
 }
diff --git a/srcs/compose/accent_double_aigu.json b/srcs/compose/accent_double_aigu.json
index 1732b26..ad40497 100644
--- a/srcs/compose/accent_double_aigu.json
+++ b/srcs/compose/accent_double_aigu.json
@@ -1,7 +1,11 @@
 {
+  " ": "˝",
+  // latin
   "o": "ő",
   "u": "ű",
-  " ": "˝",
+  // cyrillic
+  "у": "ӳ",
+  // combining character
   "a": "a\u030b",
   "e": "e\u030b",
   "i": "i\u030b",
diff --git a/srcs/compose/accent_grave.json b/srcs/compose/accent_grave.json
index efd07c2..16320a5 100644
--- a/srcs/compose/accent_grave.json
+++ b/srcs/compose/accent_grave.json
@@ -1,8 +1,38 @@
 {
+  // latin
   "a": "à",
   "e": "è",
   "i": "ì",
+  "n": "ǹ",
   "o": "ò",
   "u": "ù",
-  "ü": "ǜ"
+  "w": "ẁ",
+  "y": "ỳ",
+  // extended latin
+  "â": "ầ",
+  "ă": "ằ",
+  "ê": "ề",
+  "ē": "ḕ",
+  "ơ": "ờ",
+  "ô": "ồ",
+  "ō": "ṑ",
+  "ü": "ǜ",
+  "ư": "ừ",
+  // greek (technically not a grave, but a varia)
+  "α": "ὰ",
+  "ε": "ὲ",
+  "η": "ὴ",
+  "ι": "ὶ",
+  "ο": "ὸ",
+  "υ": "ὺ",
+  "ω": "ὼ",
+  // there is more like ἒ, ᾣ, etc
+  // cyrillic
+  "е": "ѐ",
+  "и": "ѝ",
+  // combining character
+  "ɔ": "ɔ\u0300",
+  "s": "s\u0300",
+  "ʌ": "ʌ\u0300",
+  "z": "z\u0300"
 }
diff --git a/srcs/compose/accent_macron.json b/srcs/compose/accent_macron.json
index b311974..7224517 100644
--- a/srcs/compose/accent_macron.json
+++ b/srcs/compose/accent_macron.json
@@ -1,8 +1,35 @@
 {
+  // latin
   "a": "ā",
   "e": "ē",
+  "g": "ḡ",
   "i": "ī",
   "o": "ō",
   "u": "ū",
-  "ü": "ǖ"
+  "y": "ȳ",
+  // extended latin
+  "æ": "ǣ",
+  "ä": "ǟ",
+  "ȧ": "ǡ",
+  "è": "ḕ",
+  "é": "ḗ",
+  "ḷ": "ḹ",
+  "ṛ": "ṝ",
+  "ö": "ȫ",
+  "ȯ": "ȱ",
+  "ǫ": "ǭ",
+  "õ": "ȭ",
+  "ò": "ṑ",
+  "ó": "ṓ",
+  "ü": "ǖ", // there is also ṻ
+  // cyrillic
+  "и": "ӣ",
+  "у": "ӯ",
+  // greek
+  "α": "ᾱ",
+  "ι": "ῑ",
+  "υ": "ῡ",
+  // combining characters
+  "l": "l\u0304",
+  "r": "r\u0304"
 }
diff --git a/srcs/compose/accent_ogonek.json b/srcs/compose/accent_ogonek.json
index a722cef..4a7f8b6 100644
--- a/srcs/compose/accent_ogonek.json
+++ b/srcs/compose/accent_ogonek.json
@@ -1,10 +1,10 @@
 {
+  // latin
   "a": "ą",
   "e": "ę",
   "i": "į",
-  "k": "ķ",
-  "l": "ļ",
-  "n": "ņ",
   "o": "ǫ",
-  "u": "ų"
+  "u": "ų",
+  // extended latin
+  "ō": "ǭ"
 }
diff --git a/srcs/compose/accent_ring.json b/srcs/compose/accent_ring.json
index 9fad5bc..ac6ed66 100644
--- a/srcs/compose/accent_ring.json
+++ b/srcs/compose/accent_ring.json
@@ -1,4 +1,11 @@
 {
+  // latin
   "a": "å",
-  "u": "ů"
+  "u": "ů",
+  "w": "ẘ", // no uppercase
+  "y": "ẙ", // no uppercase
+  // extended latin
+  "á": "ǻ",
+  // extra
+  "~": "⸛"
 }
diff --git a/srcs/compose/accent_slash.json b/srcs/compose/accent_slash.json
index 1d07925..5743935 100644
--- a/srcs/compose/accent_slash.json
+++ b/srcs/compose/accent_slash.json
@@ -8,7 +8,11 @@
   "l": "ł",
   "n": "ꞥ",
   "o": "ø",
+  "ó": "ǿ",
+  "ɔ": "ꬿ",
   "r": "ꞧ",
   "s": "ꞩ",
-  "t": "ⱦ"
+  "t": "ⱦ",
+  "u": "ꞹ",
+  "v": "ꝟ"
 }
diff --git a/srcs/compose/accent_subscript.json b/srcs/compose/accent_subscript.json
index 79a3c93..2cf2daf 100644
--- a/srcs/compose/accent_subscript.json
+++ b/srcs/compose/accent_subscript.json
@@ -1,4 +1,6 @@
 {
+  // arabic numbers
+  "0": "₀",
   "1": "₁",
   "2": "₂",
   "3": "₃",
@@ -8,12 +10,13 @@
   "7": "₇",
   "8": "₈",
   "9": "₉",
-  "0": "₀",
+  // math operators
   "+": "₊",
   "-": "₋",
   "=": "₌",
   "(": "₍",
   ")": "₎",
+  // latin
   "a": "ₐ",
   "e": "ₑ",
   "h": "ₕ",
@@ -30,5 +33,13 @@
   "t": "ₜ",
   "u": "ᵤ",
   "v": "ᵥ",
-  "x": "ₓ"
+  "x": "ₓ",
+  // extended latin
+  "ə": "ₔ",
+  // greek
+  "β": "ᵦ",
+  "γ": "ᵧ",
+  "ρ": "ᵨ",
+  "φ": "ᵩ",
+  "χ": "ᵪ"
 }
diff --git a/srcs/compose/accent_superscript.json b/srcs/compose/accent_superscript.json
index 68b9751..292815d 100644
--- a/srcs/compose/accent_superscript.json
+++ b/srcs/compose/accent_superscript.json
@@ -1,4 +1,6 @@
 {
+  // numbers
+  "0": "⁰",
   "1": "¹",
   "2": "²",
   "3": "³",
@@ -8,12 +10,18 @@
   "7": "⁷",
   "8": "⁸",
   "9": "⁹",
-  "0": "⁰",
+  // math operators
   "+": "⁺",
   "-": "⁻",
   "=": "⁼",
   "(": "⁽",
   ")": "⁾",
+  // latin
+  "n": "ⁿ",
+  
+  // since there are no more "superscript" characters,
+  // we substitute with "modifier letter small"s which looks the same
+  // latin
   "a": "ᵃ",
   "b": "ᵇ",
   "c": "ᶜ",
@@ -26,10 +34,11 @@
   "j": "ʲ",
   "k": "ᵏ",
   "l": "ˡ",
+  // see above for n
   "m": "ᵐ",
-  "n": "ⁿ",
   "o": "ᵒ",
   "p": "ᵖ",
+  "q": "ꟴ", // there is no proper lowercase superscript q
   "r": "ʳ",
   "s": "ˢ",
   "t": "ᵗ",
@@ -38,5 +47,47 @@
   "w": "ʷ",
   "x": "ˣ",
   "y": "ʸ",
-  "z": "ᶻ"
+  "z": "ᶻ",
+  // extended latin
+  "ɐ": "ᵄ",
+  "ᴂ": "ᵆ",
+  "ɕ": "ᶝ",
+  "ə": "ᵊ",
+  "ɛ": "ᵋ",
+  "ɜ": "ᶟ", // turned open e, ↓ not the same
+  "ᴈ": "ᵌ", // reversed open e
+  "ɥ": "ᶣ",
+  "ɦ": "ʱ",
+  "ᴉ": "ᵎ",
+  "ɨ": "ᶤ",
+  "ɟ": "ᶡ",
+  "ɱ": "ᶬ",
+  "ɯ": "ᵚ",
+  "ɰ": "ᶭ",
+  "ŋ": "ᵑ",
+  "ᴝ": "ᵙ",
+  "ɵ": "ᶱ",
+  "œ": "ꟹ",
+  "ɔ": "ᵓ",
+  "ɹ": "ʴ",
+  "ɻ": "ʵ",
+  "ʁ": "ʶ",
+  "ʂ": "ᶳ",
+  "ʉ": "ᶶ",
+  "ʃ": "ᶴ",
+  "ʒ": "ᶾ",
+  "ʍ": "ꭩ",
+  // greek
+  "ɒ": "ᶛ",
+  "β": "ᵝ",
+  "ɣ": "ˠ",
+  "δ": "ᵟ",
+  "φ": "ᵠ",
+  "χ": "ᵡ",
+  "ι": "ᶥ",
+  "ʊ": "ᶷ",
+  "ʌ": "ᶺ",
+  "θ": "ᶿ",
+  // cyrillic
+  "ө": "ᶱ"
 }
diff --git a/srcs/compose/accent_tilde.json b/srcs/compose/accent_tilde.json
index a79d1a3..7939068 100644
--- a/srcs/compose/accent_tilde.json
+++ b/srcs/compose/accent_tilde.json
@@ -1,13 +1,21 @@
 {
+  // latin
   "a": "ã",
   "e": "ẽ",
   "i": "ĩ",
   "n": "ñ",
   "o": "õ",
   "u": "ũ",
+  "v": "ṽ",
+  "y": "ỹ",
+  // extended latin
   "ă": "ẵ",
   "â": "ẫ",
   "ê": "ễ",
   "ơ": "ỡ",
-  "ư": "ữ"
+  "ō": "ȭ",
+  "ó": "ṍ",
+  "ö": "ṏ",
+  "ư": "ữ",
+  "ú": "ṹ"
 }
diff --git a/srcs/compose/accent_trema.json b/srcs/compose/accent_trema.json
index 64cba56..dc9c5f8 100644
--- a/srcs/compose/accent_trema.json
+++ b/srcs/compose/accent_trema.json
@@ -1,8 +1,54 @@
 {
+  // fun
+  "~": "⍨",
+  "*": "⍣",
+  "∇": "⍢",
+  "°": "⍤",
+  // latin
   "a": "ä",
   "e": "ë",
+  "h": "ḧ",
   "i": "ï",
   "o": "ö",
+  "t": "ẗ",
   "u": "ü",
-  "y": "ÿ"
+  "w": "ẅ",
+  "x": "ẍ",
+  "y": "ÿ",
+  // extended latin
+  "ā": "ǟ",
+  "ō": "ȫ",
+  "õ": "ṏ",
+  "í": "ḯ",
+  "ū": "ǖ", // there is also ṻ
+  "ú": "ǘ",
+  "ù": "ǜ",
+  "ǔ": "ǚ",
+  // greek
+  "ι": "ϊ",
+  "υ": "ϋ",
+  "ὺ": "ῢ",
+  "ύ": "ΰ",
+  "ῦ": "ῧ",
+  "ϒ": "ϔ",
+  // cyrillic
+  "а": "ӓ",
+  "ә": "ӛ",
+  "ж": "ӝ",
+  "з": "ӟ",
+  "и": "ӥ",
+  "о": "ӧ",
+  "ө": "ӫ",
+  "э": "ӭ",
+  "у": "ӱ",
+  "ч": "ӵ",
+  "ы": "ӹ",
+  // combining character
+  "c": "c\u0308",
+  "j": "j\u0308",
+  "k": "k\u0308",
+  "l": "l\u0308",
+  "m": "m\u0308",
+  "n": "n\u0308",
+  "s": "s\u0308"
 }
diff --git a/srcs/compose/shift.json b/srcs/compose/shift.json
index 3c52024..57e3490 100644
--- a/srcs/compose/shift.json
+++ b/srcs/compose/shift.json
@@ -18,7 +18,38 @@
   "┐": "╗",
   "─": "═",
   "│": "║",
+  // superscript
+  "ᵃ": "ᴬ",
+  "ᵇ": "ᴮ",
+  "ᶜ": "ꟲ",
+  "ᵈ": "ᴰ",
+  "ᵉ": "ᴱ",
+  "ᶠ": "ꟳ",
+  "ᵍ": "ᴳ",
+  "ʰ": "ᴴ",
+  "ⁱ": "ᴵ",
+  "ʲ": "ᴶ",
+  "ᵏ": "ᴷ",
+  "ˡ": "ᴸ",
+  "ᵐ": "ᴹ",
+  "ⁿ": "ᴺ",
+  "ᵒ": "ᴼ",
+  "ᵖ": "ᴾ",
+  "ʳ": "ᴿ",
+  "ᵗ": "ᵀ",
+  "ᵘ": "ᵁ",
+  "ᵛ": "ⱽ",
+  "ʷ": "ᵂ",
+  "ᶾ": "ᴣ",
+  "ᵠ": "ᶲ",
+  // german eszett has an uppercase, but because it is uncommon, java doesn't know about it
   "ß": "ẞ",
+  // these characters don't have a preapplied uppercase version, so we use combining characters
+  "ẗ": "T\u0308",
+  "ẘ": "W\u030A",
+  "ẙ": "Y\u030A",
+  "ǰ": "J\u030C",
+  "ȷ": "J\u0307",
   // In Turkish, upper case of 'iı' is 'İI' but Java's toUpperCase will
   // return 'II'. To make 'İ' accessible, make it the shift of 'ı'. This
   // has the inconvenient of swapping i and ı on the keyboard.