wzray/tt9
1
0
Fork 0
Code Activity

Gujarati

Browse source
This commit is contained in:
sspanak 2024-12-28 14:07:57 +02:00 • committed by Dimo Karaivanov
parent 240e5c444a
commit e3d0bac90f
13 changed files with 1380245 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

15
app/languages/definitions/Gujarati.yml Normal file
View file

@ -0,0 +1,15 @@
locale: gu-IN
dictionaryFile: gu-utf8.csv
abcString: કખગ
hasUpperCase: no
layout:
- [SPECIAL] # 0
- [્, ઼, ઃ, ઽ, ૐ, PUNCTUATION_IN] # 1 ==> [halant, nuqta, avagraha, visarga, om]
- [અ, આ, બ, ભ, ચ, છ, ા] # 2 ==> [a, aa, b, bh, c, ch, aa (m)]
- [દ, ધ, ડ, ઢ, એ, ઐ, ઍ, ફ, ે, ૈ, ૅ] # 3 ==> [d, dh, ḍ (dd), ḍh (ddh), e, ai, ae, ph, e (m), ai (m), ae (m)]
- [ગ, ઘ, હ, ઇ, ઈ, િ, ી] # 4 ==> [g, gh, h, i, ii, i (m), ii (m) ]
- [જ, ઝ, ક, ખ, લ, ળ, ઌ, ૢ] # 5 ==> [j, jh, k, kh, l, ḷ (ll), l̥, l̥ (m)]
- [મ, ઙ, ઞ, ણ, ન, ઓ, ઑ, ઔ, ો, ૉ, ૌ, ં, ઁ] # 6 ==> [m, ṅ (ng), ñ, ṇ (nn), n, o, ŏ, au, o (m), ŏ (m), au (m), anusvara, m̐ (m-combining with vowel, e.g. "am", "em")]
- [પ, ર, ઋ, સ, શ, ષ, ૃ, ૄ] # 7 ==> [p, r, r̥, s, sh, ss, r̥ (m), rr (m)]
- [ત, થ, ટ, ઠ, ઉ, ઊ, વ, ુ, ૂ] # 8 ==> [t, th, ṭ (tt), ṭh, u, uu, v, u (m), uu (m)]
- [ય] # 9 ==> [y]

1380080
app/languages/dictionaries/gu-utf8.csv Normal file
View file

File diff suppressed because it is too large Load diff

6
app/src/main/java/io/github/sspanak/tt9/ime/modes/predictions/LocaleWordsSorter.java
View file

@ -17,11 +17,7 @@ class LocaleWordsSorter {
LocaleWordsSorter(@Nullable Language language) {
if (LanguageKind.isHindi(language)) {
sortingPattern = Pattern.compile("[\\u0904-\\u0939\\u0958-\\u0961][\\u0900-\\u0904\\u093A-\\u094F\\u0962\\u0963]+");
} else {
sortingPattern = null;
}
sortingPattern = LanguageKind.isIndic(language) ? Pattern.compile("\\p{L}\\p{M}+") : null;
}

10
app/src/main/java/io/github/sspanak/tt9/languages/LanguageKind.java
View file

@ -5,17 +5,19 @@ import java.util.Locale;
public class LanguageKind {
public static final int KOREAN = 601579;
public static boolean isArabic(Language language) { return language != null && language.getId() == 502337; }
public static boolean isCyrillic(Language language) { return language != null && language.getKeyCharacters(2).contains("а"); }
public static boolean isLatinBased(Language language) { return language != null && language.getKeyCharacters(2).contains("a"); }
public static boolean isRTL(Language language) { return isArabic(language) || isHebrew(language); }
public static boolean isArabic(Language language) { return language != null && language.getId() == 502337; }
public static boolean isEnglish(Language language) { return language != null && language.getLocale().equals(Locale.ENGLISH); }
public static boolean isFrench(Language language) { return language != null && language.getId() == 596550; }
public static boolean isGreek(Language language) { return language != null && language.getId() == 597381; }
public static boolean isGujarati(Language language) { return language != null && language.getId() == 468647; }
public static boolean isHebrew(Language language) { return language != null && (language.getId() == 305450 || language.getId() == 403177); }
public static boolean isHindi(Language language) { return language != null && language.getId() == 468264; }
public static boolean isIndic(Language language) { return isHindi(language); }
public static boolean isHinglish(Language language) { return language != null && language.getId() == 468421; }
public static boolean isIndic(Language language) { return isGujarati(language) || isHindi(language); }
public static boolean isKorean(Language language) { return language != null && language.getId() == KOREAN; }
public static boolean isLatinBased(Language language) { return language != null && language.getKeyCharacters(2).contains("a"); }
public static boolean isRTL(Language language) { return isArabic(language) || isHebrew(language); }
public static boolean isUkrainian(Language language) { return language != null && language.getId() == 54645; }
}

5
app/src/main/java/io/github/sspanak/tt9/ui/main/keys/SoftKeyNumber.java
View file

@ -211,9 +211,12 @@ public class SoftKeyNumber extends SoftKey {
// Greek diacritics and ending sigma
|| currentLetter == 'ς'
|| (isGreek && (currentLetter < 'α' || currentLetter > 'ω'))
// Hindi matras
// Hindi combining
|| (currentLetter >= 0x0900 && currentLetter <= 0x0903) || (currentLetter >= 0x093A && currentLetter <= 0x094F)
|| (currentLetter >= 0x0951 && currentLetter <= 0x0957) || currentLetter == 0x0962 || currentLetter == 0x0963
// Gujarati combining
|| (currentLetter >= 0x0A81 && currentLetter <= 0x0A83) || (currentLetter >= 0xABC && currentLetter <= 0x0ACD)
|| currentLetter == 0x0AE2 || currentLetter == 0x0AE3
;
}
}

16
app/src/main/java/io/github/sspanak/tt9/util/chars/Punctuation.java
View file

@ -25,10 +25,13 @@ class Punctuation {
',', '-', '\'', ':', ';', '!', '?', '.'
));
final private static ArrayList<Character> CombiningPunctuationIndic = new ArrayList<>(Arrays.asList(
'्', '़', 'ऽ', 'ः', '।', '॰', '॥'
final private static ArrayList<Character> CombiningPunctuationGujarati = new ArrayList<>(Arrays.asList(
'્', '઼', 'ઽ', 'ઃ', '।', '॰', '॥' // Indic combining chars look the same, but have different Unicode values
));
final private static ArrayList<Character> CombiningPunctuationHindi = new ArrayList<>(Arrays.asList(
'्', '़', 'ऽ', 'ः', '।', '॰', '॥' // Indic combining chars look the same, but have different Unicode values
));
final private static ArrayList<Character> CombiningPunctuationHebrew = new ArrayList<>(Arrays.asList(
',' , '-', '\'', ':', ';', '!', '?', '.', '"'
@ -65,11 +68,16 @@ class Punctuation {
public static boolean isCombiningPunctuation(Language language, char ch) {
return
CombiningPunctuation.contains(ch)
|| (LanguageKind.isIndic(language) && CombiningPunctuationIndic.contains(ch))
|| (LanguageKind.isGujarati(language) && CombiningPunctuationGujarati.contains(ch))
|| (LanguageKind.isHindi(language) && CombiningPunctuationHindi.contains(ch))
|| (LanguageKind.isHebrew(language) && CombiningPunctuationHebrew.contains(ch));
}
public static boolean isCombiningPunctuation(char ch) {
return CombiningPunctuation.contains(ch) || CombiningPunctuationIndic.contains(ch) || CombiningPunctuationHebrew.contains(ch);
return
CombiningPunctuation.contains(ch)
|| CombiningPunctuationGujarati.contains(ch)
|| CombiningPunctuationHindi.contains(ch)
|| CombiningPunctuationHebrew.contains(ch);
}
}