CLDR-17177 Merge remote-tracking branch 'origin/main' into srl295/kbd/c…

…ldr-17177/mdfeedback
unicode-org · Feb 27, 2024 · 79763f9 · 79763f9
2 parents 4041bfd + a5825d3
commit 79763f9
Show file tree

Hide file tree

Showing 49 changed files with 659 additions and 178 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -50,13 +50,15 @@ begin with the accepted Jira ticket number.
 
 ## Contributor License Agreement
 
-In order to contribute to this project, the Unicode Consortium must have on file a Contributor License Agreement (CLA) covering your contributions, either an individual or a corporate CLA. Pull Requests will not be merged until the correct CLA is signed. Which version needs to be signed depends on who owns the contribution being made: you as the individual making the contribution or your employer. _It is your responsibility to determine whether your contribution is owned by your employer._ Please review [The Unicode Consortium Intellectual Property, Licensing, and Technical Contribution Policies][policies] for further guidance on which CLA to sign, as well as other information and guidelines regarding the Consortium’s licensing and technical contribution policies and procedures.
+In order to contribute to this project, the Unicode Consortium must have on file a Contributor License Agreement (CLA) covering your contributions, either an individual or a corporate CLA. Pull Requests, issues, and other contributions will not be merged/accepted until the correct CLA is signed. Which version needs to be signed depends on who owns the contribution being made: you as the individual making the contribution or your employer. **It is your responsibility to determine whether your contribution is owned by your employer.** Please review the [Unicode Intellectual Property, Licensing, & Technical Contribution Policy][policies] for further guidance on which CLA to sign, as well as other information and guidelines regarding the Consortium’s licensing and technical contribution policies and procedures.
 
-- **Individual CLA**: If you have determined that the Individual CLA is appropriate, then when you open your first Pull Request, an automated comment will appear that contains a link you can follow to accept the Individual CLA.
+To sign the CLA in Github, open a Pull Request (a comment will be automatically added with a link to the CLA Form), or go directly to [the CLA Form][sign-cla]. You may need to sign in to Github to see the entire CLA Form.
 
-- **Corporate CLA**: If you have determined that a Corporate CLA is appropriate, please check the [public list of Corporate CLAs][unicode-corporate-clas] that the Consortium has on file. If your employer has already signed a CLA, then when you open your first Pull Request, an automated comment will appear that contains a link you can follow to declare your affiliation with this employer. If your employer has not already signed a CLA, you will need to arrange for your employer to sign the Corporate CLA, as described in [How to Sign a Unicode CLA][signing].
+- **Individual CLA**: If you have determined that the Individual CLA is appropriate, then when you access the CLA Form, click the Individual CLA and complete the Form.
 
-Unless otherwise noted in the [LICENSE](./LICENSE) file, this project is released under the free and open-source [Unicode License][unicode-license], also known as Unicode, Inc. License Agreement - Data Files and Software.
+- **Corporate CLA**: If you have determined that a Corporate CLA is appropriate, please first check the [public list of Corporate CLAs][unicode-corporate-clas] that the Consortium has on file. If your employer is listed, then when you access the CLA Form, you can click the box indicating that you are covered by your employer’s corporate CLA. If your employer is not on the list, then it has not already signed a CLA and you will need to arrange for your employer to do so before you contribute, as described in [How to Sign a Unicode CLA][signing].
+
+Unless otherwise noted in the [`LICENSE`](./LICENSE) file, this project is released under the [OSI-approved][osi-Unicode-License-3.0] free and open-source [Unicode License v3][unicode-license].
 
 ## Building
 
@@ -108,4 +110,6 @@ All rights reserved. [Terms of use][]
 [policies]: https://www.unicode.org/policies/licensing_policy.html
 [unicode-corporate-clas]: https://www.unicode.org/policies/corporate-cla-list/
 [signing]: https://www.unicode.org/policies/licensing_policy.html#signing
-[unicode-license]: ./LICENSE
+[sign-cla]: https://cla-assistant.io/unicode-org/.github
+[osi-Unicode-License-3.0]: https://opensource.org/license/unicode-license-v3/
+[unicode-license]: https://www.unicode.org/license.txt
diff --git a/LICENSE b/LICENSE
@@ -37,3 +37,5 @@ Except as contained in this notice, the name of a copyright holder shall
 not be used in advertising or otherwise to promote the sale, use or other
 dealings in these Data Files or Software without prior written
 authorization of the copyright holder.
+
+SPDX-License-Identifier: Unicode-3.0
diff --git a/common/dtd/ldmlSupplemental.dtd b/common/dtd/ldmlSupplemental.dtd
@@ -944,8 +944,11 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ELEMENT parentLocale EMPTY >
 <!ATTLIST parentLocale parent NMTOKEN #REQUIRED >
     <!--@MATCH:validity/locale-->
+<!ATTLIST parentLocale localeRules NMTOKENS #IMPLIED >
+    <!--@MATCH:set/literal/nonlikelyScript-->
+    <!--@VALUE-->
 <!ATTLIST parentLocale locales NMTOKENS #REQUIRED >
-    <!--@MATCH:or/set/validity/locale||literal/nonlikelyScript-->
+    <!--@MATCH:set/validity/locale-->
     <!--@VALUE-->
 
 <!ELEMENT personNamesDefaults ( alias | ( nameOrderLocalesDefault* ) ) >

diff --git a/common/properties/coverageLevels.txt b/common/properties/coverageLevels.txt
@@ -144,7 +144,6 @@ th ;	modern ;	Thai
 ti ;	basic ;	Tigrinya
 tk ;	modern ;	Turkmen
 to ;	basic ;	Tongan
-tok ;	basic ;	Toki Pona
 tr ;	modern ;	Turkish
 tt ;	basic ;	Tatar
 ug ;	basic ;	Uyghur

diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml
@@ -5423,7 +5423,7 @@ XXX Code for transations where no currency is involved
     </codeMappings>
 
 	<parentLocales>
-		<parentLocale parent="root" locales="nonlikelyScript"/>
+		<parentLocale parent="root" localeRules="nonlikelyScript" locales="az_Arab az_Cyrl bal_Latn blt_Latn bm_Nkoo bs_Cyrl byn_Latn cu_Glag dje_Arab dyo_Arab en_Dsrt en_Shaw ff_Adlm ff_Arab ha_Arab iu_Latn kk_Arab ks_Deva ku_Arab kxv_Deva kxv_Orya kxv_Telu ky_Arab ky_Latn ml_Arab mn_Mong mni_Mtei ms_Arab pa_Arab sat_Deva sd_Deva sd_Khoj sd_Sind shi_Latn so_Arab sr_Latn sw_Arab tg_Arab ug_Cyrl uz_Arab uz_Cyrl vai_Latn wo_Arab yo_Arab yue_Hans zh_Hant"/>
 		<parentLocale parent="en_001" locales="en_150 en_AG en_AI en_AU en_BB en_BM en_BS en_BW en_BZ en_CC en_CK en_CM en_CX en_CY en_DG en_DM en_ER en_FJ en_FK en_FM en_GB en_GD en_GG en_GH en_GI en_GM en_GY en_HK en_ID en_IE en_IL en_IM en_IN en_IO en_JE en_JM en_KE en_KI en_KN en_KY en_LC en_LR en_LS en_MG en_MO en_MS en_MT en_MU en_MV en_MW en_MY en_NA en_NF en_NG en_NR en_NU en_NZ en_PG en_PK en_PN en_PW en_RW en_SB en_SC en_SD en_SG en_SH en_SL en_SS en_SX en_SZ en_TC en_TK en_TO en_TT en_TV en_TZ en_UG en_VC en_VG en_VU en_WS en_ZA en_ZM en_ZW"/>
 		<parentLocale parent="en_150" locales="en_AT en_BE en_CH en_DE en_DK en_FI en_NL en_SE en_SI"/>
 		<parentLocale parent="en_IN" locales="hi_Latn"/>

diff --git a/common/testData/localeIdentifiers/likelySubtags.txt b/common/testData/localeIdentifiers/likelySubtags.txt
@@ -1,5 +1,5 @@
 # Test data for Likely Subtags
-#  Copyright © 1991-2023 Unicode, Inc.
+#  Copyright © 1991-2024 Unicode, Inc.
 #  For terms of use, see http://www.unicode.org/copyright.html
 #  SPDX-License-Identifier: Unicode-DFS-2016
 #  CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)

diff --git a/common/testData/localeIdentifiers/localeCanonicalization.txt b/common/testData/localeIdentifiers/localeCanonicalization.txt
@@ -1,5 +1,5 @@
 # Test data for locale identifier canonicalization
-#  Copyright © 1991-2023 Unicode, Inc.
+#  Copyright © 1991-2024 Unicode, Inc.
 #  For terms of use, see http://www.unicode.org/copyright.html
 #  SPDX-License-Identifier: Unicode-DFS-2016
 #  CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)

diff --git a/common/testData/localeIdentifiers/localeDisplayName.txt b/common/testData/localeIdentifiers/localeDisplayName.txt
@@ -1,5 +1,5 @@
 # Test data for locale display name generation
-#  Copyright © 1991-2023 Unicode, Inc.
+#  Copyright © 1991-2024 Unicode, Inc.
 #  For terms of use, see http://www.unicode.org/copyright.html
 #  SPDX-License-Identifier: Unicode-DFS-2016
 #  CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)

diff --git a/common/testData/units/unitPreferencesTest.txt b/common/testData/units/unitPreferencesTest.txt
@@ -1,6 +1,6 @@
 
 # Test data for unit preferences
-#  Copyright © 1991-2023 Unicode, Inc.
+#  Copyright © 1991-2024 Unicode, Inc.
 #  For terms of use, see http://www.unicode.org/copyright.html
 #  SPDX-License-Identifier: Unicode-DFS-2016
 #  CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)

diff --git a/common/testData/units/unitsTest.txt b/common/testData/units/unitsTest.txt
@@ -1,5 +1,5 @@
 # Test data for unit conversions
-#  Copyright © 1991-2023 Unicode, Inc.
+#  Copyright © 1991-2024 Unicode, Inc.
 #  For terms of use, see http://www.unicode.org/copyright.html
 #  SPDX-License-Identifier: Unicode-DFS-2016
 #  CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
@@ -189,9 +189,9 @@ speed	;	meter-per-second	;	meter-per-second	;	1 * x	;	1,000.00
 substance-amount	;	item	;	item	;	1 * x	;	1,000.00
 substance-amount	;	mole	;	item	;	602,214,076,000,000,000,000,000 * x	;	6.022141E26
 temperature	;	rankine	;	kelvin	;	5/9 * x	;	555.5556
-temperature	;	fahrenheit	;	kelvin	;	5/9 * x - 2,298.35/9	;	810.9278
+temperature	;	fahrenheit	;	kelvin	;	5/9 * x + 2,298.35/9	;	810.9278
 temperature	;	kelvin	;	kelvin	;	1 * x	;	1,000.00
-temperature	;	celsius	;	kelvin	;	1 * x - 273.15	;	1273.15
+temperature	;	celsius	;	kelvin	;	1 * x + 273.15	;	1273.15
 typewidth	;	em	;	em	;	1 * x	;	1,000.00
 voltage	;	volt	;	kilogram-square-meter-per-cubic-second-ampere	;	1 * x	;	1000.0
 volume	;	drop	;	cubic-meter	;	0.0000001540287998046875/3 * x	;	5.134293E-5

diff --git a/docs/charts/keyboard/package-lock.json b/docs/charts/keyboard/package-lock.json
diff --git a/docs/charts/keyboard/package.json b/docs/charts/keyboard/package.json
@@ -12,7 +12,7 @@
   },
   "keywords": [],
   "author": "Steven R. Loomis <[email protected]>",
-  "license": "Unicode-DFS-2016",
+  "license": "Unicode-3.0",
   "bugs": {
     "url": "https://github.com/unicode-org/cldr/issues"
   },

diff --git a/docs/ldml/tr35.md b/docs/ldml/tr35.md
@@ -1790,18 +1790,21 @@ then a mixture of child and parent textual data is a mishmash of different scrip
 Thus there are two cases where the truncation inheritance needs to be overridden:
 
 1.  When the parent locale would have a different script, and text would be mixed.
-2.  In certain exceptional circumstances where the parent.
+2.  In certain exceptional circumstances where the 'truncation' parent needs to be adjusted.
 
 The `parentLocale` element is used to override the normal inheritance when accessing CLDR data.
 
-For case 1, there is a special value for the locales, `nonlikelyScript`,
-which includes all locales of the form <lang>_<script>, where the <script> is not the likely script for <lang>.
+For case 1, there is a special attribute and value, `localeRules="nonlikelyScript"`,
+which specifies **all locales** of the form <lang>_<script>, wherever the <script> is **not** the likely script for <lang>.
+For migration, the previous short list of locales (a subset of the nonlikelyScript locales) is retained,
+but those locales are slated for removal in the future. 
+For example, `ru_Latn` is not included in the short list but is included (programmatically) in the rule.
 
 ```xml
-<parentLocale parent="root" locales="nonlikelyScript"/>
+<parentLocale parent="root" localeRules="nonlikelyScript" locales="az_Arab az_Cyrl bal_Latn … yue_Hans zh_Hant"/>/>
 ```
 
-This is used for the main component.
+The `localeRules` is used for the main component, for example.
 It is not used to components where text is not mixed, 
 such as the collations component or the plurals component.
 
@@ -1811,7 +1814,11 @@ For case 2, the children and parent share the same primary language, but the reg
 <parentLocale parent="es_419" locales="es_AR es_BO … es_UY es_VE"/>
 ```
 
-There are certain components that require addenda to the common parent fallback rules. For a locale like `zh_Hant` in the example above, the `parentLocale` element would dictate the parent as `root` when referring to main locale data, but for collation data, the parent locale should still be `zh`, even though the `parentLocale` element is present for that locale. To address this, components can have their own fallback rules that inherit from the common rules and add additional parents that supplement or override the common rules:
+There are certain components that require addenda to the common parent fallback rules. 
+For a locale like `zh_Hant` in the example above, the `parentLocale` element would dictate the parent as `root` when referring to main locale data,
+but for collation data, the parent locale should still be `zh`,
+even though the `parentLocale` element is present for that locale.
+To address this, components can have their own fallback rules that inherit from the common rules and add additional parents that supplement or override the common rules:
 
 ```xml
 <parentLocales component="segmentations">
@@ -1827,7 +1834,8 @@ the parentLocale information is contained in CLDR’s [supplemental data.](tr35-
 
 When a `parentLocale` element is used to override normal inheritance, the following guidelines apply in most cases:
 
-1.  If X is the parentLocale of Y, then either X is the root locale, or X has the same base language code as Y. For example, the parent of `en` cannot be `fr`, and the parent of `en_YY` cannot be `fr` or `fr_XX`.
+1.  If X is the parentLocale of Y, then either X is the root locale, or X has the same base language code as Y.
+For example, the parent of `en` cannot be `fr`, and the parent of `en_YY` cannot be `fr` or `fr_XX`.
 2.  If X is the parentLocale of Y, Y must not be a base language locale. For example, the parent of `en` cannot be `en_XX`.
 
 There may be specific exceptions to these for certain closely-related languages or language-script combinations, for example:

diff --git a/keyboards/3.0/bn.xml b/keyboards/3.0/bn.xml
@@ -1,6 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="bn" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="bn" conformsTo="techpreview">
     <!--
         History:
           Based on

diff --git a/keyboards/3.0/fr-t-k0-azerty.xml b/keyboards/3.0/fr-t-k0-azerty.xml
@@ -7,8 +7,7 @@
 
 	Also NOTE: this is really a test keyboard.  CLDR-12026 will be for the real new azerty keyboard
 -->
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="fr-t-k0-azerty" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="fr-t-k0-azerty" conformsTo="techpreview">
 	<locales>
 		<locale id="br" /> <!-- example of including Breton -->
 	</locales>

diff --git a/keyboards/3.0/ja-Latn.xml b/keyboards/3.0/ja-Latn.xml
@@ -1,6 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="ja-Latn" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="ja-Latn" conformsTo="techpreview">
 	<locales>
 		<locale id="en" />
 	</locales>

diff --git a/keyboards/3.0/mt-t-k0-47key.xml b/keyboards/3.0/mt-t-k0-47key.xml
@@ -1,6 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="mt-t-k0-47key" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="mt-t-k0-47key" conformsTo="techpreview">
     <locales>
         <!-- English is also an official language in Malta.-->
         <locale id="en" />

diff --git a/keyboards/3.0/mt.xml b/keyboards/3.0/mt.xml
@@ -5,8 +5,7 @@
     This file is subject to change.
     Please see https://cldr.unicode.org/index/keyboard-workgroup for the latest information.
 -->
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="mt" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="mt" conformsTo="techpreview">
     <locales>
         <!-- English is also an official language in Malta.-->
         <locale id="en" />

diff --git a/keyboards/3.0/pcm.xml b/keyboards/3.0/pcm.xml
@@ -1,6 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="pcm" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="pcm" conformsTo="techpreview">
   <version number="1.0.0" />
   <info name="Naijíriá Píjin" />
   <keys>

diff --git a/keyboards/3.0/pt-t-k0-abnt2.xml b/keyboards/3.0/pt-t-k0-abnt2.xml
@@ -1,6 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE keyboard3 SYSTEM "../dtd/ldmlKeyboard3.dtd"> <!-- TODO: to make tests pass, see CLDR-17191 -->
-<keyboard3 locale="pt-t-k0-abnt2" conformsTo="techpreview">
+<keyboard3 xmlns="https://schemas.unicode.org/cldr/45/keyboard3" locale="pt-t-k0-abnt2" conformsTo="techpreview">
 	<locales>
 		<locale id="pt" />
 	</locales>

diff --git a/keyboards/dtd/ldmlKeyboard3.dtd b/keyboards/dtd/ldmlKeyboard3.dtd
@@ -17,6 +17,9 @@ Please view the subcommittee page for the most recent information.
 <!ATTLIST keyboard3 conformsTo (techpreview) #REQUIRED >
     <!--@MATCH:any-->
     <!--@METADATA-->
+<!ATTLIST keyboard3 xmlns CDATA #IMPLIED >
+    <!--@MATCH:any-->
+    <!--@METADATA-->
 
 <!ELEMENT import EMPTY >
     <!--@TECHPREVIEW-->