| Denys Vlasenko | d8528b8 | 2010-01-31 05:15:38 +0100 | [diff] [blame] | 1 | # DO NOT EDIT THIS FILE! MOST TEXT EDITORS WILL DAMAGE IT! |
| 2 | >'0001_1__Some_correct_UTF-8_text___________________________________________|' |
| 3 | >'0002_2__Boundary_condition_test_cases_____________________________________|' |
| 4 | >'0003_2.1__First_possible_sequence_of_a_certain_length_____________________|' |
| 5 | >'0004_2.1.2__2_bytes__U-00000080_:________"Â"______________________________|' |
| 6 | >'0005_2.1.3__3_bytes__U-00000800_:________"à "______________________________|' |
| 7 | >'0006_2.1.4__4_bytes__U-00010000_:________"ð"______________________________|' |
| 8 | >'0007_2.1.5__5_bytes__U-00200000_:________"ø"______________________________|' |
| 9 | >'0008_2.1.6__6_bytes__U-04000000_:________"ü"______________________________|' |
| 10 | >'0009_2.2__Last_possible_sequence_of_a_certain_length______________________|' |
| 11 | >'0010_2.2.1__1_byte___U-0000007F_:________""______________________________|' |
| 12 | >'0011_2.2.2__2_bytes__U-000007FF_:________"ß¿"______________________________|' |
| 13 | >'0012_2.2.3__3_bytes__U-0000FFFF_:________"ï¿¿"______________________________|' |
| 14 | >'0013_2.2.4__4_bytes__U-001FFFFF_:________"÷¿¿¿"______________________________|' |
| 15 | >'0014_2.2.5__5_bytes__U-03FFFFFF_:________"û¿¿¿¿"______________________________|' |
| 16 | >'0015_2.2.6__6_bytes__U-7FFFFFFF_:________"ý¿¿¿¿¿"______________________________|' |
| 17 | >'0016_2.3__Other_boundary_conditions_______________________________________|' |
| 18 | >'0017_2.3.1__U-0000D7FF_=_ed_9f_bf_=_"í¿"___________________________________|' |
| 19 | >'0018_2.3.2__U-0000E000_=_ee_80_80_=_"î"___________________________________|' |
| 20 | >'0019_2.3.3__U-0000FFFD_=_ef_bf_bd_=_"�"___________________________________|' |
| 21 | >'0020_2.3.4__U-0010FFFF_=_f4_8f_bf_bf_=_"ô¿¿"________________________________|' |
| 22 | >'0021_2.3.5__U-00110000_=_f4_90_80_80_=_"ô"________________________________|' |
| 23 | >'0022_3__Malformed_sequences_______________________________________________|' |
| 24 | >'0023_3.1__Unexpected_continuation_bytes___________________________________|' |
| 25 | >'0024_3.1.1__First_continuation_byte_0x80:_""_____________________________|' |
| 26 | >'0025_3.1.2__Last__continuation_byte_0xbf:_"¿"_____________________________|' |
| 27 | >'0026_3.1.3__2_continuation_bytes:_"¿"____________________________________|' |
| 28 | >'0027_3.1.4__3_continuation_bytes:_"¿"___________________________________|' |
| 29 | >'0028_3.1.5__4_continuation_bytes:_"¿¿"__________________________________|' |
| 30 | >'0029_3.1.6__5_continuation_bytes:_"¿¿"_________________________________|' |
| 31 | >'0030_3.1.7__6_continuation_bytes:_"¿¿¿"________________________________|' |
| 32 | >'0031_3.1.8__7_continuation_bytes:_"¿¿¿"_______________________________|' |
| 33 | >'0032_3.1.9__Sequence_of_all_64_possible_continuation_bytes__0x80-0xbf_:___|' |
| 34 | >'0033____"
_________________________________________________|' |
| 35 | >'0034______________________________________________________|' |
| 36 | >'0035_____ ¡¢£¤¥¦§¨©ª«¬®¯_________________________________________________|' |
| 37 | >'0036_____°±²³´µ¶·¸¹º»¼½¾¿"________________________________________________|' |
| 38 | >'0037_3.2__Lonely_start_characters_________________________________________|' |
| 39 | >'0038_3.2.1__All_32_first_bytes_of_2-byte_sequences__0xc0-0xdf_,___________|' |
| 40 | >'0039________each_followed_by_a_space_character:___________________________|' |
| 41 | >'0040____"À_Á_Â_Ã_Ä_Å_Æ_Ç_È_É_Ê_Ë_Ì_Í_Î_Ï__________________________________|' |
| 42 | >'0041_____Ð_Ñ_Ò_Ó_Ô_Õ_Ö_×_Ø_Ù_Ú_Û_Ü_Ý_Þ_ß_"________________________________|' |
| 43 | >'0042_3.2.2__All_16_first_bytes_of_3-byte_sequences__0xe0-0xef_,___________|' |
| 44 | >'0043________each_followed_by_a_space_character:___________________________|' |
| 45 | >'0044____"à_á_â_ã_ä_å_æ_ç_è_é_ê_ë_ì_í_î_ï_"________________________________|' |
| 46 | >'0045_3.2.3__All_8_first_bytes_of_4-byte_sequences__0xf0-0xf7_,____________|' |
| 47 | >'0046________each_followed_by_a_space_character:___________________________|' |
| 48 | >'0047____"ð_ñ_ò_ó_ô_õ_ö_÷_"________________________________________________|' |
| 49 | >'0048_3.2.4__All_4_first_bytes_of_5-byte_sequences__0xf8-0xfb_,____________|' |
| 50 | >'0049________each_followed_by_a_space_character:___________________________|' |
| 51 | >'0050____"ø_ù_ú_û_"________________________________________________________|' |
| 52 | >'0051_3.2.5__All_2_first_bytes_of_6-byte_sequences__0xfc-0xfd_,____________|' |
| 53 | >'0052________each_followed_by_a_space_character:___________________________|' |
| 54 | >'0053____"ü_ý_"____________________________________________________________|' |
| 55 | >'0054_3.3__Sequences_with_last_continuation_byte_missing___________________|' |
| 56 | >'0055_3.3.1__2-byte_sequence_with_last_byte_missing__U+0000_:_____"À"______|' |
| 57 | >'0056_3.3.2__3-byte_sequence_with_last_byte_missing__U+0000_:_____"à"______|' |
| 58 | >'0057_3.3.3__4-byte_sequence_with_last_byte_missing__U+0000_:_____"ð"______|' |
| 59 | >'0058_3.3.4__5-byte_sequence_with_last_byte_missing__U+0000_:_____"ø"______|' |
| 60 | >'0059_3.3.5__6-byte_sequence_with_last_byte_missing__U+0000_:_____"ü"______|' |
| 61 | >'0060_3.3.6__2-byte_sequence_with_last_byte_missing__U-000007FF_:_"ß"______|' |
| 62 | >'0061_3.3.7__3-byte_sequence_with_last_byte_missing__U-0000FFFF_:_"ï¿"______|' |
| 63 | >'0062_3.3.8__4-byte_sequence_with_last_byte_missing__U-001FFFFF_:_"÷¿¿"______|' |
| 64 | >'0063_3.3.9__5-byte_sequence_with_last_byte_missing__U-03FFFFFF_:_"û¿¿¿"______|' |
| 65 | >'0064_3.3.10_6-byte_sequence_with_last_byte_missing__U-7FFFFFFF_:_"ý¿¿¿¿"______|' |
| 66 | >'0065_3.4__Concatenation_of_incomplete_sequences___________________________|' |
| 67 | >'0066____"Ààðøüßï¿÷¿¿û¿¿¿ý¿¿¿¿"______________________________________________________|' |
| 68 | >'0067_3.5__Impossible_bytes________________________________________________|' |
| 69 | >'0068_3.5.1__fe_=_"þ"______________________________________________________|' |
| 70 | >'0069_3.5.2__ff_=_"ÿ"______________________________________________________|' |
| 71 | >'0070_3.5.3__fe_fe_ff_ff_=_"þþÿÿ"__________________________________________|' |
| 72 | >'0071_4__Overlong_sequences________________________________________________|' |
| 73 | >'0072_4.1__Examples_of_an_overlong_ASCII_character_________________________|' |
| 74 | >'0073_4.1.1_U+002F_=_c0_af_____________=_"À¯"_______________________________|' |
| 75 | >'0074_4.1.2_U+002F_=_e0_80_af__________=_"à¯"_______________________________|' |
| 76 | >'0075_4.1.3_U+002F_=_f0_80_80_af_______=_"ð¯"_______________________________|' |
| 77 | >'0076_4.1.4_U+002F_=_f8_80_80_80_af____=_"ø¯"_______________________________|' |
| 78 | >'0077_4.1.5_U+002F_=_fc_80_80_80_80_af_=_"ü¯"_______________________________|' |
| 79 | >'0078_4.2__Maximum_overlong_sequences______________________________________|' |
| 80 | >'0079_4.2.1__U-0000007F_=_c1_bf_____________=_"Á¿"__________________________|' |
| 81 | >'0080_4.2.2__U-000007FF_=_e0_9f_bf__________=_"à¿"__________________________|' |
| 82 | >'0081_4.2.3__U-0000FFFF_=_f0_8f_bf_bf_______=_"ð¿¿"__________________________|' |
| 83 | >'0082_4.2.4__U-001FFFFF_=_f8_87_bf_bf_bf____=_"ø¿¿¿"__________________________|' |
| 84 | >'0083_4.2.5__U-03FFFFFF_=_fc_83_bf_bf_bf_bf_=_"ü¿¿¿¿"__________________________|' |
| 85 | >'0084_4.3__Overlong_representation_of_the_NUL_character____________________|' |
| 86 | >'0085_4.3.1__U+0000_=_c0_80_____________=_"À"______________________________|' |
| 87 | >'0086_4.3.2__U+0000_=_e0_80_80__________=_"à"______________________________|' |
| 88 | >'0087_4.3.3__U+0000_=_f0_80_80_80_______=_"ð"______________________________|' |
| 89 | >'0088_4.3.4__U+0000_=_f8_80_80_80_80____=_"ø"______________________________|' |
| 90 | >'0089_4.3.5__U+0000_=_fc_80_80_80_80_80_=_"ü"______________________________|' |
| 91 | >'0090_5__Illegal_code_positions____________________________________________|' |
| 92 | >'0091_5.1_Single_UTF-16_surrogates_________________________________________|' |
| 93 | >'0092_5.1.1__U+D800_=_ed_a0_80_=_"í "_______________________________________|' |
| 94 | >'0093_5.1.2__U+DB7F_=_ed_ad_bf_=_"í¿"_______________________________________|' |
| 95 | >'0094_5.1.3__U+DB80_=_ed_ae_80_=_"í®"_______________________________________|' |
| 96 | >'0095_5.1.4__U+DBFF_=_ed_af_bf_=_"í¯¿"_______________________________________|' |
| 97 | >'0096_5.1.5__U+DC00_=_ed_b0_80_=_"í°"_______________________________________|' |
| 98 | >'0097_5.1.6__U+DF80_=_ed_be_80_=_"í¾"_______________________________________|' |
| 99 | >'0098_5.1.7__U+DFFF_=_ed_bf_bf_=_"í¿¿"_______________________________________|' |
| 100 | >'0099_5.2_Paired_UTF-16_surrogates_________________________________________|' |
| 101 | >'0100_5.2.1__U+D800_U+DC00_=_ed_a0_80_ed_b0_80_=_"í í°"______________________|' |
| 102 | >'0101_5.2.2__U+D800_U+DFFF_=_ed_a0_80_ed_bf_bf_=_"í í¿¿"______________________|' |
| 103 | >'0102_5.2.3__U+DB7F_U+DC00_=_ed_ad_bf_ed_b0_80_=_"í¿í°"______________________|' |
| 104 | >'0103_5.2.4__U+DB7F_U+DFFF_=_ed_ad_bf_ed_bf_bf_=_"í¿í¿¿"______________________|' |
| 105 | >'0104_5.2.5__U+DB80_U+DC00_=_ed_ae_80_ed_b0_80_=_"í®í°"______________________|' |
| 106 | >'0105_5.2.6__U+DB80_U+DFFF_=_ed_ae_80_ed_bf_bf_=_"í®í¿¿"______________________|' |
| 107 | >'0106_5.2.7__U+DBFF_U+DC00_=_ed_af_bf_ed_b0_80_=_"í¯¿í°"______________________|' |
| 108 | >'0107_5.2.8__U+DBFF_U+DFFF_=_ed_af_bf_ed_bf_bf_=_"􏿿"______________________|' |
| 109 | >'0108_5.3_Other_illegal_code_positions_____________________________________|' |
| 110 | >'0109_5.3.1__U+FFFE_=_ef_bf_be_=_"￾"_______________________________________|' |
| 111 | >'0110_5.3.2__U+FFFF_=_ef_bf_bf_=_"ï¿¿"_______________________________________|' |