public void IsVowelRecognizesVowels()
{
foreach (var vowel in CharacterRanges.Vowels)
{
Assert.True(SpecialCharacterChecker.IsVowel(vowel));
}
}
public static string ToKatakana(string input, WanaKanaOptions?options = null)
{
if (input is null)
{
throw new ArgumentNullException(nameof(input));
}
options ??= new WanaKanaOptions();
if (input.Length == 0)
{
return(string.Empty);
}
if (options.PassRomaji)
{
return(KanaConverters.HiraganaToKatakana(input));
}
if (MixedChecker.IsMixed(input) || RomajiChecker.IsRomaji(input) || SpecialCharacterChecker.IsEnglishPunctuation(input[0]))
{
var hiragana = KanaConverters.ToKana(input.ToLowerInvariant(), options);
return(KanaConverters.HiraganaToKatakana(hiragana));
}
return(KanaConverters.HiraganaToKatakana(input));
}
public void IsConsonantRecognizesConsonants()
{
foreach (var consonant in CharacterRanges.Consonants)
{
Assert.True(SpecialCharacterChecker.IsConsonant(consonant));
}
}
public static string HiraganaToKatakana(string input)
{
if (input is null)
{
throw new ArgumentNullException(nameof(input));
}
var builder = new StringBuilder();
foreach (var character in input)
{
// Short circuit to avoid incorrect codeshift for 'ー' and '・'
if (SpecialCharacterChecker.IsLongDash(character) || SpecialCharacterChecker.IsSlashDot(character))
{
builder.Append(character);
}
else if (HiraganaChecker.IsHiragana(character))
{
// Shift charcode.
var katakanaCode = (character - CharacterRanges.HiraganaStart) + CharacterRanges.KatakanaStart;
var katakanaCharacter = (char)katakanaCode;
builder.Append(katakanaCharacter);
}
else
{
// Pass non-hiragana chars through
builder.Append(character);
}
}
return(builder.ToString());
}
public void IsJapanesePunctuationAllJapanesePunctuationsAreRecognized()
{
foreach (var range in CharacterRanges.JapanesePunctuationRanges)
{
for (char character = range.Start; character <= range.End; character++)
{
Assert.True(SpecialCharacterChecker.IsJapanesePunctuation(character));
}
}
}
public void IsEnglishPunctuationAllJapanesePunctuationsAreInvalid()
{
foreach (var range in CharacterRanges.JapanesePunctuationRanges)
{
for (char character = range.Start; character <= range.End; character++)
{
Assert.False(SpecialCharacterChecker.IsEnglishPunctuation(character));
}
}
}
public static string KatakanaToHiragana(string input, bool isDestinationRomaji = false)
{
if (input is null)
{
throw new ArgumentNullException(nameof(input));
}
char?previousKana = null;
var builder = new StringBuilder();
for (int index = 0; index < input.Length; index++)
{
var character = input[index];
// Short circuit to avoid incorrect codeshift for 'ー' and '・'
if (SpecialCharacterChecker.IsSlashDot(character) || IsInitialLongDash(character, index) || IsKanaAsSymbol(character))
{
builder.Append(character);
// Transform long vowels: 'オー' to 'おう'
}
else if (previousKana != null && IsInnerLongDash(character, index))
{
// Transform previousKana back to romaji, and slice off the vowel
var romaji = RomajiConverter.ToRomaji(previousKana.ToString()).Last();
// However, ensure 'オー' => 'おお' => 'oo' if this is a transform on the way to romaji
if (KatakanaChecker.IsKatakana(input[index - 1]) && romaji == 'o' && isDestinationRomaji)
{
builder.Append('お');
}
else
{
builder.Append(_longVowels[romaji]);
}
}
else if (!SpecialCharacterChecker.IsLongDash(character) && KatakanaChecker.IsKatakana(character))
{
// Shift charcode.
var hiraganaCode = (character - CharacterRanges.KatakanaStart) + CharacterRanges.HiraganaStart;
var hiragana = (char)hiraganaCode;
previousKana = hiragana;
builder.Append(hiragana);
}
else
{
// Pass non katakana chars through
previousKana = null;
builder.Append(character);
}
}
return(builder.ToString());
}
public void IsConsonantExcludingY()
{
Assert.False(SpecialCharacterChecker.IsConsonant('y', false));
}
public void IsEnglishPunctuationVarious(char character, bool expectedResult)
{
Assert.Equal(expectedResult, SpecialCharacterChecker.IsEnglishPunctuation(character));
}
public void IsVowelInvalidCases(char character)
{
Assert.False(SpecialCharacterChecker.IsVowel(character));
}
public void IsVowelExcludingY()
{
Assert.False(SpecialCharacterChecker.IsVowel('y', false));
}
public void IsConsonantInvalidCases(char character)
{
Assert.False(SpecialCharacterChecker.IsConsonant(character));
}
public void IsConsonantIncludesYByDefault()
{
Assert.True(SpecialCharacterChecker.IsConsonant('y'));
}
private static bool IsInnerLongDash(char character, int index) => SpecialCharacterChecker.IsLongDash(character) && index > 0;
private static string GetTokenType(char character, bool compact = false)
{
if (compact)
{
if (IsJaNumber(character))
{
return(TokenTypes.Other);
}
if (IsEnNumber(character))
{
return(TokenTypes.Other);
}
if (IsEnSpace(character))
{
return(TokenTypes.English);
}
if (SpecialCharacterChecker.IsEnglishPunctuation(character))
{
return(TokenTypes.Other);
}
if (IsJaSpace(character))
{
return(TokenTypes.Japanese);
}
if (SpecialCharacterChecker.IsJapanesePunctuation(character))
{
return(TokenTypes.Other);
}
if (JapaneseChecker.IsJapanese(character))
{
return(TokenTypes.Japanese);
}
if (RomajiChecker.IsRomaji(character))
{
return(TokenTypes.English);
}
}
else
{
if (IsJaSpace(character))
{
return(TokenTypes.Space);
}
if (IsEnSpace(character))
{
return(TokenTypes.Space);
}
if (IsJaNumber(character))
{
return(TokenTypes.JapaneseNumber);
}
if (IsEnNumber(character))
{
return(TokenTypes.EnglishNumber);
}
if (SpecialCharacterChecker.IsEnglishPunctuation(character))
{
return(TokenTypes.EnglishPunctuation);
}
if (SpecialCharacterChecker.IsJapanesePunctuation(character))
{
return(TokenTypes.JapanesePunctuation);
}
if (KanjiChecker.IsKanji(character))
{
return(TokenTypes.Kanji);
}
if (HiraganaChecker.IsHiragana(character))
{
return(TokenTypes.Hiragana);
}
if (KatakanaChecker.IsKatakana(character))
{
return(TokenTypes.Katakana);
}
if (JapaneseChecker.IsJapanese(character))
{
return(TokenTypes.Japanese);
}
if (RomajiChecker.IsRomaji(character))
{
return(TokenTypes.English);
}
}
return(TokenTypes.Other);
}
