Skip to content

chore: Improve locale affinity logic with LanguageUtils #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ericfjosne merged 1 commit into from
Jun 11, 2025
Merged

chore: Improve locale affinity logic with LanguageUtils #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
33 changes: 30 additions & 3 deletions .../src/main/java/com/spotify/i18n/locales/common/impl/LocaleAffinityCalculatorBaseImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
package com.spotify.i18n.locales.common.impl;

import static com.spotify.i18n.locales.utils.hierarchy.LocalesHierarchyUtils.isRootLocale;
import static com.spotify.i18n.locales.utils.hierarchy.LocalesHierarchyUtils.isSameLocale;

import com.google.auto.value.AutoValue;
import com.google.common.base.Preconditions;
Expand All @@ -33,8 +34,10 @@
import com.spotify.i18n.locales.common.LocaleAffinityCalculator;
import com.spotify.i18n.locales.common.model.LocaleAffinity;
import com.spotify.i18n.locales.common.model.LocaleAffinityResult;
import com.spotify.i18n.locales.utils.language.LanguageUtils;
import com.spotify.i18n.locales.utils.languagetag.LanguageTagUtils;
import edu.umd.cs.findbugs.annotations.Nullable;
import java.util.Optional;
import java.util.Set;

/**
Expand Down Expand Up @@ -97,12 +100,36 @@ private LocaleAffinity getAffinity(@Nullable final String languageTag) {
if (againstLocales().isEmpty()) {
return LocaleAffinity.NONE;
} else {
int bestDistance = getBestDistance(languageTag);
int correspondingScore = convertDistanceToAffinityScore(bestDistance);
return convertScoreToLocaleAffinity(correspondingScore);
// We attempt to match based on corresponding spoken language first, and make use of the
// score-based affinity calculation as fallback.
if (hasSameSpokenLanguageAffinity(languageTag)) {
return LocaleAffinity.SAME_OR_INTERCHANGEABLE;
} else {
return calculateScoreBasedAffinity(languageTag);
}
}
}

private boolean hasSameSpokenLanguageAffinity(final String languageTag) {
return LanguageUtils.getSpokenLanguageLocale(languageTag)
.map(
spokenLanguageLocale ->
againstLocales().stream()
.map(ULocale::toLanguageTag)
.map(LanguageUtils::getSpokenLanguageLocale)
.flatMap(Optional::stream)
.anyMatch(
againstSpokenLocale ->
isSameLocale(spokenLanguageLocale, againstSpokenLocale)))
.orElse(false);
}

private LocaleAffinity calculateScoreBasedAffinity(String languageTag) {
int bestDistance = getBestDistance(languageTag);
int correspondingScore = convertDistanceToAffinityScore(bestDistance);
return convertScoreToLocaleAffinity(correspondingScore);
}

private int getBestDistance(@Nullable final String languageTag) {
return LanguageTagUtils.parse(languageTag)
.map(LocaleAffinityCalculatorBaseImpl::getMaximizedLanguageScriptRegion)
Expand Down
17 changes: 14 additions & 3 deletions ...est/java/com/spotify/i18n/locales/common/impl/ReferenceLocalesCalculatorBaseImplTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
import com.spotify.i18n.locales.common.model.LocaleAffinity;
import com.spotify.i18n.locales.common.model.RelatedReferenceLocale;
import com.spotify.i18n.locales.utils.available.AvailableLocalesUtils;
import com.spotify.i18n.locales.utils.language.LanguageUtils;
import java.util.List;
import java.util.Optional;
import java.util.stream.Stream;
Expand Down Expand Up @@ -69,7 +70,8 @@ public void validateLocaleAffinityScoreRanges(final ULocale input) {

ULocale referenceLanguageScriptOnly = getLocaleWithLanguageAndScriptOnly(referenceLocale);

if (isSameLocale(inputLanguageScriptOnly, referenceLanguageScriptOnly)) {
if (isSameLocale(inputLanguageScriptOnly, referenceLanguageScriptOnly)
|| isSameSpokenLanguage(inputLanguageScriptOnly, referenceLanguageScriptOnly)) {
assertEquals(
SAME_OR_INTERCHANGEABLE,
affinity,
Expand Down Expand Up @@ -101,6 +103,12 @@ public void validateLocaleAffinityScoreRanges(final ULocale input) {
}
}

private boolean isSameSpokenLanguage(
ULocale inputLanguageScriptOnly, ULocale referenceLanguageScriptOnly) {
return LanguageUtils.getSpokenLanguageLocale(inputLanguageScriptOnly.toLanguageTag())
.equals(LanguageUtils.getSpokenLanguageLocale(referenceLanguageScriptOnly.toLanguageTag()));
}

private static ULocale getLocaleWithLanguageAndScriptOnly(ULocale input) {
return new Builder()
.setLocale(ULocale.addLikelySubtags(input))
Expand All @@ -116,10 +124,13 @@ private boolean areKnownInterchangeableLocales(ULocale inputLS, ULocale referenc
switch (input) {
// Bosnian and Croatian
case "bs-Latn":
return reference.equals("hr-Latn");
// Bosnian and Croatian
case "bs-Cyrl":
return reference.equals("hr-Latn");
// Croatian and Bosnian
case "hr-Latn":
return reference.equals("bs-Latn");
return reference.equals("bs-Latn") || reference.equals("bs-Cyrl");
// German and Luxembourgish or Swiss German
case "de-Latn":
return reference.equals("lb-Latn") || reference.equals("gsw-Latn");
Expand Down Expand Up @@ -469,7 +480,7 @@ private static List<RelatedReferenceLocale> norwegian() {
// Norwegian
rrl("no", SAME_OR_INTERCHANGEABLE),
// Nynorsk
rrl("nn", LOW));
rrl("nn", SAME_OR_INTERCHANGEABLE));
}

private static List<RelatedReferenceLocale> serbian() {
Expand Down