Skip to content

Commit

Permalink
CLDR-12026 kbd: add proper azerty-optimisé (#3220)
Browse files Browse the repository at this point in the history 
(cherry picked from commit 2907ef5)
  • Loading branch information
@srl295 @pedberg-icu
srl295 authored and pedberg-icu committed Apr 22, 2024
1 parent 542cc53 commit d3aad09
Show file tree
Hide file tree
Showing 4 changed files with 263 additions and 4 deletions.
2 changes: 1 addition & 1 deletion keyboards/3.0/fr-t-k0-azerty.xml → keyboards/3.0/fr-t-k0-test.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
<!--
See CLDR-12026 for the real new azerty keyboard
-->
<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="fr-t-k0-azerty" conformsTo="45">
<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="fr-t-k0-test" conformsTo="45">
<locales>
<locale id="br" /> <!-- example of including Breton -->
</locales>
Expand Down
259 changes: 259 additions & 0 deletions keyboards/3.0/fr.xml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,259 @@
<?xml version="1.0" encoding="UTF-8"?>
<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" conformsTo="45"
locale="fr">
<version number="1.0.0" />

<info author="Team Keyboard" name="Français normalisé (AZERTY)" layout="AZERTY" indicator="FR" />

<displays>
<!-- display for diacritics -->
<display output="\u0300" display="${grave}" />
<display output="\m{acute}" display="´" />
<display output="\m{grave}" display="`" />
<display output="\m{umlaut}" display="¨" />
<display output="\m{caret}" display="^" />
<display output="\m{tilde}" display="~" />
<display output="\m{invbreve}" display="\u{20}\u{0311}" />

<!-- display for 'mode' keys -->
<display keyId="mark-currency" display="\u{00A4}" />
<display keyId="mark-greek" display="\u{B5}" />
<display keyId="mark-euro" display="Eu" />
</displays>

<keys>
<import base="cldr" path="45/keys-Zyyy-punctuation.xml" />
<import base="cldr" path="45/keys-Zyyy-currency.xml" />

<!-- deadkeys -->
<key id="mark-acute" output="\m{acute}" />
<key id="mark-breve" output="\m{breve}" />
<key id="mark-caret" output="\m{caret}" />
<key id="mark-caron" output="\m{caron}" />
<key id="mark-cedilla" output="\m{cedilla}" />
<key id="mark-invbreve" output="\m{invbreve}" />
<key id="mark-comma" output="\m{comma}" />
<key id="mark-currency" output="\m{currency}" />
<key id="mark-dotabove" output="\m{dotabove}" />
<key id="mark-dotbelow" output="\m{dotbelow}" />
<key id="mark-doubleacute" output="\m{doubleacute}" />
<key id="mark-doublegrave" output="\m{doublegrave}" />
<key id="mark-euro" output="\m{euro}" />
<key id="mark-grave" output="\m{grave}" />
<key id="mark-macron" output="\m{macron}" />
<key id="mark-ogonek" output="\m{ogonek}" />
<key id="mark-ring" output="\m{ring}" />
<key id="mark-greek" output="\m{greek}" />
<key id="mark-solidus" output="\m{solidus}" />
<key id="mark-stroke" output="\m{stroke}" />
<key id="mark-submacron" output="\m{submacron}" />
<key id="mark-tilde" output="\m{tilde}" />
<key id="mark-umlaut" output="\m{umlaut}" />

<!-- spaces -->
<key id="nbsp" output="\u{A0}" />
<key id="nnbsp" output="\u{202F}" />

<!-- extra keys -->
<key id="e-grave" output="è" />
<key id="e-acute" output="é" />
<key id="c-cedilla" output="ç" />
<key id="a-acute" output="á" />
<key id="a-grave" output="à" />
<key id="e-caret" output="ê" />

<!-- extra symbols -->
<key id="bullet" output="•" />
<key id="umlaut" output="¨" />
<key id="sub-2" output="₂" />
<key id="super-2" output="²" longPressKeyIds="sub-2" />
<key id="en-dash" output="–" />
<key id="plus-minus" output="±" />
<key id="vulgar-half" output="½" />
<key id="vulgar-quarter" output="¼" />
<key id="ellipsis" output="…" />
<key id="open-apos" output="‘" />
<key id="close-apos" output="’" />
<key id="open-g" output="«" />
<key id="close-g" output="»" />

<key id="theta" output="θ" /> <!-- "for Romani" -->
<key id="Theta" output="ϴ" /> <!-- "for Romani" -->
<key id="tm" output="™" />
<key id="open-double" output="“" />
<key id="close-double" output="”" />
<key id="oe" output="œ" />
<key id="Oe" output="Œ" />
<key id="registered" output="®" />
<key id="minus-sign" output="−" />
<key id="ss" output="ß" />
<key id="infinity" output="∞" />
<key id="division" output="÷" />
<key id="less-equal" output="⩽" />
<key id="greater-equal" output="⩾" />
<key id="copy" output="©" />
<key id="inverse-question" output="¿" />
<key id="inverse-bang" output="¡" />
<key id="middle-dot" output="•" />
<key id="A-grave" output="À" />
<key id="E-acute" output="É" />
<key id="E-caret" output="Ê" />
<key id="em-dash" output="—" />
<key id="open-single" output="’" />
<key id="close-single" output="’" />
<key id="u-grave" output="Ù" />
<key id="radix" output="√" />
<key id="C-cedilla" output="Ç" />
<key id="not-equal" output="≠" />
<key id="open-angle-quote" output="‹" />
<key id="close-angle-quote" output="›" />

<key id="E-grave" output="È" />
<key id="U-grave" output="Ù" />
<key id="nb-hyphen" output="‑" />
<key id="multiplication" output="×" />
<key id="ezh" output="ʒ" />
<key id="Ezh" output="Ʒ" />
<key id="ae" output="æ" />
<key id="Ae" output="Æ" />
<key id="permille" output="‰" />
<key id="dbl-dagger" output="‡" />
<key id="dagger" output="†" />
<key id="asym-equal" output="≃" />
<key id="Ss" output="ẞ" />
</keys>

<layers formId="iso">
<layer modifiers="none">
<row
keys="at a-grave e-acute e-grave e-caret open-paren close-paren open-apos close-apos open-g close-g apos mark-caret" />
<row keys="a z e r t y u i o p hyphen plus" />
<row keys="q s d f g h j k l m slash asterisk" />
<row keys="open-angle w x c v b n period comma colon semi-colon" />
<row keys="space" />
</layer>

<layer modifiers="shift">
<row keys="hash 1 2 3 4 5 6 7 8 9 0 double-quote mark-umlaut" />
<row keys="A Z E R T Y U I O P en-dash plus-minus" />
<row keys="Q S D F G H J K L M backslash vulgar-half" />
<row keys="close-angle W X C V B N question bang ellipsis equal" />
<row keys="space" />
</layer>
<!-- layer is for AltGr - for now we use ctrl alt -->
<layer modifiers="ctrl alt">
<row
keys="mark-breve section mark-acute mark-grave amp open-square close-square mark-macron underscore open-double close-double degree mark-caron" />
<row
keys="ae pound euro registered open-curly close-curly u-grave mark-dotabove oe percent minus-sign dagger" />
<row
keys="theta ss dollar mark-currency mark-greek mark-euro gap mark-solidus pipe infinity division multiplication" />
<row
keys="less-equal ezh copy c-cedilla mark-cedilla mark-stroke mark-tilde inverse-question inverse-bang middle-dot asym-equal" />
<row keys="nbsp" />
</layer>

<layer modifiers="ctrl alt shift">
<row
keys="mark-invbreve A-grave E-acute E-grave E-caret mark-doubleacute mark-doublegrave gap em-dash open-angle-quote close-angle-quote mark-ring gap" />
<row keys="Ae gap gap gap tm gap U-grave mark-dotbelow Oe permille nb-hyphen dbl-dagger" />
<row keys="Theta Ss gap gap gap mark-submacron gap gap gap gap radix vulgar-quarter" />
<row
keys="greater-equal Ezh gap C-cedilla mark-ogonek gap gap gap mark-comma gap not-equal" />
<row keys="nnbsp" />
</layer>
</layers>

<variables>
<!-- spacing accents as string variables -->
<string id="grave" value="`" />
<string id="caret" value="^" />
<string id="umlaut" value="¨" />
<string id="tilde" value="~" />

<!-- sets representing vowels and accented vowels. -->
<!-- There's an extra space between the lower and upper case for visual separation -->
<!-- but, there are only 10 vowels in the following four sets -->
<!-- plus space at end for the visible version -->
<set id="vowel" value="a e i o u A E I O U" />

<!-- everything that should take an accented combining char -->
<set id="upaccentable" value="A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Ʒ Æ Œ" />
<set id="lwaccentable" value="a b c d e f g h i j k l m n o p q r s t u v w x y z ʒ æ œ" />
<set id="accentable" value="$[upaccentable] $[lwaccentable]" />

<!-- currency key from/to -->
<set id="currfrom" value="e r t y p s d f g h k l m w c b n A R T P S D F L M C B" />
<set id="currto" value="₠ ₽ ₸ ¥ ₱ ₪ ₫ ƒ ₲ ₴ ₭ ₺ ₥ ₩ ¢ ₿ ₦ ₳ ₹ ₮ ₧ ₷ ₯ ₣ ₤ ℳ ₡ ﺀ" />

<!-- greek from/to: deviating from spec, uppercase final sigma (X) is encoded as another Σ -->
<set id="greekfrom"
value="a z e r u i o p s d g h j k l m x b n A Z E R U I O P S D G H J K L M X B N" />
<set id="greekto"
value="α ζ ε ρ θ ι ο π σ δ γ η ξ κ λ μ ς β ν Α Ζ Ε Ρ Θ Ι Ο Π Σ Δ Γ Η Ξ Κ Λ Μ Σ Β Ν" />

<!-- euro key from/to -->
<set id="eurofrom" value="a e t i o s d g j ‘ ’ « » ' E T I D G J 7 8 9 0" />
<set id="euroto" value="ª ə þ ı º ſ ð ŋ ij ‚ ‘ „ ‟ ’ Ə Þ İ Đ Ŋ IJ › ‹ » «" />

<!-- numbers -->
<set id="digits" value="0 1 2 3 4 5 6 7 8 9" />
<set id="superdigits" value="⁰ ¹ ² ³ ⁴ ⁵ ⁶ ⁷ ⁸ ⁹" />
<set id="subdigits" value="₀ ₁ ₂ ₃ ₄ ₅ ₆ ₇ ₈ ₉" />
</variables>

<transforms type="simple">
<transformGroup>
<!-- super/sub digits -->
<transform from="\m{breve}($[digits])" to="$[1:superdigits]" />
<transform from="\m{invbreve}($[digits])" to="$[1:subdigits]" />

<!-- special cases - any more of these? -->
<transform from="\m{dotabove}i" to="ı" />

<!-- match accentables with combining marks -->
<transform from="\m{breve}($[accentable])" to="$1\u{0306}" />
<transform from="\m{umlaut}($[accentable])" to="$1\u{0308}" />
<transform from="\m{invbreve}($[accentable])" to="$1\u{0311}" />
<transform from="\m{acute}($[accentable])" to="$1\u{0301}" />
<transform from="\m{caret}($[accentable])" to="$1\u{0302}" />
<transform from="\m{caron}($[accentable])" to="$1\u{030c}" />
<transform from="\m{cedilla}($[accentable])" to="$1\u{0327}" />
<transform from="\m{comma}($[accentable])" to="$1\u{0326}" />
<transform from="\m{dotabove}($[accentable])" to="$1\u{0307}" />
<transform from="\m{dotbelow}($[accentable])" to="$1\u{0323}" />
<transform from="\m{doubleacute}($[accentable])" to="$1\u{030b}" />
<transform from="\m{doublegrave}($[accentable])" to="$1\u{030f}" />
<transform from="\m{grave}($[accentable])" to="$1\u{0300}" />
<transform from="\m{macron}($[accentable])" to="$1\u{0304}" />
<transform from="\m{ogonek}($[accentable])" to="$1\u{0328}" />
<transform from="\m{ring}($[accentable])" to="$1\u{030a}" />
<transform from="\m{solidus}($[accentable])" to="$1\u{338}" />
<transform from="\m{stroke}($[accentable])" to="$1\u{0335}" />
<transform from="\m{submacron}($[accentable])" to="$1\u{0331}" />
<transform from="\m{tilde}($[accentable])" to="$1\u{0303}" />

<!-- curr/greek/euro layer for hardware -->
<transform from="\m{currency}($[currfrom])" to="$[1:currto]" />
<transform from="\m{greek}\m{greek}" to="\u{B5}" />
<transform from="\m{greek}($[greekfrom])" to="$[1:greekto]" />
<transform from="\m{euro}($[eurofrom])" to="$[1:euroto]" />

<!-- these are harder to see because they are from AltGr and AltGr+Shift layers -->
<transform from="\m{currency}®" to="₨" /> <!-- AltGr-R -->
<transform from="\m{currency}%" to="₰" /> <!-- AltGr-P -->
<transform from="\m{currency}\|" to="₾" /> <!-- AltGr-L - note pipe is escaped -->
<transform from="\m{currency}∞" to="₼" /> <!-- AltGr-M -->
<transform from="\m{currency}ç" to="₢" /> <!-- AltGr-C -->
<transform from="\m{currency}\m{currency}" to="¤" /> <!-- AltGr-Shift-E -->
<transform from="\m{currency}Ç" to="₵" /> <!-- AltGr-Shift-C (Cedi sign) -->
</transformGroup>
<!-- now, cleanup -->
<transformGroup>
<!-- catch-all: drop any marker that didn't otherwise match before a char -->
<transform from="\m{.}(.)" to="$1" />
<!-- not defined, so drop double euro -->
<transform from="\m{euro}\m{euro}" />
</transformGroup>
</transforms>
</keyboard3>
2 changes: 1 addition & 1 deletion keyboards/test/fr-t-k0-azerty-test.xml → keyboards/test/fr-t-k0-test-test.xml
View file
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE keyboardTest3 SYSTEM "../dtd/ldmlKeyboardTest3.dtd">
<keyboardTest3 conformsTo="techpreview">
<info keyboard="fr-t-k0-azerty.xml" author="Team Keyboard" name="fr-test" />
<info keyboard="fr-t-k0-test.xml" author="Team Keyboard" name="fr-test" />
<repertoire name="simple-repertoire" chars="[a b c d e \u{22}]" type="simple" /> <!-- verify that these outputs are all available from simple keys on any layer, for all form factors -->
<repertoire name="chars-repertoire" chars="[á é ó]" type="gesture" /> <!-- verify that these outputs are all available from simple or gesture keys on any layer, for touch -->
<tests name="key-tests">
Expand Down
4 changes: 2 additions & 2 deletions tools/cldr-code/src/main/java/org/unicode/cldr/util/ElementAttributeInfo.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -103,11 +103,11 @@ private static Map<DtdType, ElementAttributeInfo> makeElementAttributeInfoMap(
addElementAttributeInfo(
result,
DtdType.keyboard3,
canonicalCommonDirectory + "/../keyboards/3.0/fr-t-k0-azerty.xml");
canonicalCommonDirectory + "/../keyboards/3.0/fr-t-k0-test.xml");
addElementAttributeInfo(
result,
DtdType.keyboardTest3,
canonicalCommonDirectory + "/../keyboards/test/fr-t-k0-azerty-test.xml");
canonicalCommonDirectory + "/../keyboards/test/fr-t-k0-test-test.xml");
return result;
}

Expand Down

0 comments on commit d3aad09

Please sign in to comment.