test_input.wsv

a 	U+0061    61            0061        "Latin Small Letter A"
~ 	U+007E    7E            007E        Tilde
¥ 	U+00A5    C2_A5         00A5        "Yen Sign"
» 	U+00BB    C2_BB         00BB        "Right-Pointing Double Angle Quotation Mark"
½ 	U+00BD    C2_BD         00BD        "Vulgar Fraction One Half"
¿ 	U+00BF    C2_BF         00BF        "Inverted Question Mark"
ß 	U+00DF    C3_9F         00DF        "Latin Small Letter Sharp S"
ä 	U+00E4    C3_A4         00E4        "Latin Small Letter A with Diaeresis"
ï 	U+00EF    C3_AF         00EF        "Latin Small Letter I with Diaeresis"
œ 	U+0153    C5_93         0153        "Latin Small Ligature Oe"
€ 	U+20AC    E2_82_AC      20AC        "Euro Sign"
東 	U+6771    E6_9D_B1      6771        "CJK Unified Ideograph-6771"
𝄞 	U+1D11E   F0_9D_84_9E   D834_DD1E   "Musical Symbol G Clef"
𠀇 	U+20007   F0_A0_80_87   D840_DC07   "CJK Unified Ideograph-20007"