Skip to content

Commit

Permalink
Treat character 'â' as possible indicator for French (#115)
Browse files Browse the repository at this point in the history
  • Loading branch information
pemistahl committed Nov 14, 2021
1 parent b8c3a25 commit 05f0994
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 5 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -85,24 +85,25 @@ internal object Constant {
"Đđ" to setOf(BOSNIAN, CROATIAN, VIETNAMESE),
"Іі" to setOf(BELARUSIAN, KAZAKH, UKRAINIAN),
"Ìì" to setOf(ITALIAN, VIETNAMESE, YORUBA),
"Øø" to setOf(BOKMAL, DANISH, NYNORSK),

"Ūū" to setOf(LATVIAN, LITHUANIAN, MAORI, YORUBA),
"Ëë" to setOf(AFRIKAANS, ALBANIAN, DUTCH, FRENCH),
"ÈèÙù" to setOf(FRENCH, ITALIAN, VIETNAMESE, YORUBA),
"Êê" to setOf(AFRIKAANS, FRENCH, PORTUGUESE, VIETNAMESE),
"Õõ" to setOf(ESTONIAN, HUNGARIAN, PORTUGUESE, VIETNAMESE),
"Ôô" to setOf(FRENCH, PORTUGUESE, SLOVAK, VIETNAMESE),
"Øø" to setOf(BOKMAL, DANISH, NYNORSK),

"ЁёЫыЭэ" to setOf(BELARUSIAN, KAZAKH, MONGOLIAN, RUSSIAN),
"ЩщЪъ" to setOf(BULGARIAN, KAZAKH, MONGOLIAN, RUSSIAN),
"Òò" to setOf(CATALAN, ITALIAN, VIETNAMESE, YORUBA),
"Ââ" to setOf(PORTUGUESE, ROMANIAN, TURKISH, VIETNAMESE),
"Ææ" to setOf(BOKMAL, DANISH, ICELANDIC, NYNORSK),
"Åå" to setOf(BOKMAL, DANISH, NYNORSK, SWEDISH),

"Ýý" to setOf(CZECH, ICELANDIC, SLOVAK, TURKISH, VIETNAMESE),
"Ää" to setOf(ESTONIAN, FINNISH, GERMAN, SLOVAK, SWEDISH),
"Àà" to setOf(CATALAN, FRENCH, ITALIAN, PORTUGUESE, VIETNAMESE),
"Ææ" to setOf(BOKMAL, DANISH, ICELANDIC, NYNORSK),
"Åå" to setOf(BOKMAL, DANISH, NYNORSK, SWEDISH),
"Ââ" to setOf(FRENCH, PORTUGUESE, ROMANIAN, TURKISH, VIETNAMESE),

"Üü" to setOf(AZERBAIJANI, CATALAN, ESTONIAN, GERMAN, HUNGARIAN, SPANISH, TURKISH),
"Č芚Žž" to setOf(BOSNIAN, CZECH, CROATIAN, LATVIAN, LITHUANIAN, SLOVAK, SLOVENE),
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -663,7 +663,7 @@ class LanguageDetectorTest {
),
arguments(
"labâk",
listOf(PORTUGUESE, ROMANIAN, TURKISH, VIETNAMESE)
listOf(FRENCH, PORTUGUESE, ROMANIAN, TURKISH, VIETNAMESE)
),
arguments(
"pràctiques",
Expand Down

0 comments on commit 05f0994

Please sign in to comment.