archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-28 15:24:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8308108: Support Unicode extension for collation settings

Browse source 
Reviewed-by: iris, rriggs, jlu, alanb
This commit is contained in:
Naoto Sato 2023-05-25 17:20:02 +00:00
parent 89b3c375ac
commit 27ba8bd4ed
2 changed files with 143 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

59
src/java.base/share/classes/java/text/Collator.java
View file

@ -226,7 +226,43 @@ public abstract class Collator
}
/**
* Gets the Collator for the desired locale.
* Gets the Collator for the desired locale. If the desired locale
* has the "{@code ks}" and/or the "{@code kk}"
* <a href="https://www.unicode.org/reports/tr35/tr35-collation.html#Setting_Options">
* Unicode collation settings</a>, this method will call {@linkplain #setStrength(int)}
* and/or {@linkplain #setDecomposition(int)} on the created instance, if the specified
* Unicode collation settings are recognized based on the following mappings:
* <table class="striped">
* <caption style="display:none">Strength/Decomposition mappings</caption>
* <thead>
* <tr><th scope="col">BCP 47 values for strength (ks)</th>
* <th scope="col">Collator constants for strength</th></tr>
* </thead>
* <tbody>
* <tr><th scope="row" style="text-align:left">level1</th>
* <td>PRIMARY</td></tr>
* <tr><th scope="row" style="text-align:left">level2</th>
* <td>SECONDARY</td></tr>
* <tr><th scope="row" style="text-align:left">level3</th>
* <td>TERTIARY</td></tr>
* <tr><th scope="row" style="text-align:left">identic</th>
* <td>IDENTICAL</td></tr>
* </tbody>
* <thead>
* <tr><th scope="col">BCP 47 values for normalization (kk)</th>
* <th scope="col">Collator constants for decomposition</th></tr>
* </thead>
* <tbody>
* <tr><th scope="row" style="text-align:left">true</th>
* <td>CANONICAL_DECOMPOSITION</td></tr>
* <tr><th scope="row" style="text-align:left">false</th>
* <td>NO_DECOMPOSITION</td></tr>
* </tbody>
* </table>
* If the specified setting value is not recognized, the strength and/or
* decomposition will not be overridden, as if there were no BCP 47 collation
* options in the desired locale.
*
* @apiNote Implementations of {@code Collator} class may produce
* different instances based on the "{@code co}"
* <a href="https://www.unicode.org/reports/tr35/#UnicodeCollationIdentifier">
@ -258,6 +294,27 @@ public abstract class Collator
result = LocaleProviderAdapter.forJRE()
.getCollatorProvider().getInstance(desiredLocale);
}
// Override strength and decomposition with `desiredLocale`, if any
var strength = desiredLocale.getUnicodeLocaleType("ks");
if (strength != null) {
strength = strength.toLowerCase(Locale.ROOT);
switch (strength) {
case "level1" -> result.setStrength(PRIMARY);
case "level2" -> result.setStrength(SECONDARY);
case "level3" -> result.setStrength(TERTIARY);
case "identic" -> result.setStrength(IDENTICAL);
}
}
var norm = desiredLocale.getUnicodeLocaleType("kk");
if (norm != null) {
norm = norm.toLowerCase(Locale.ROOT);
switch (norm) {
case "true" -> result.setDecomposition(CANONICAL_DECOMPOSITION);
case "false" -> result.setDecomposition(NO_DECOMPOSITION);
}
}
while (true) {
if (ref != null) {
// Remove the empty SoftReference if any