greek-ocr / x1 /codec.json
fffoivos's picture
Greek OCR v0.1: x1, x1.5, x2 release + evaluation
a841ef3 verified
Raw History Blame Contribute Delete
31 kB
{ "version": "v2.1", "blank_id": 0, "policy": { "mark_order": "NFD canonical ordering; equal-ccc keeps source order (D-4a strict)", "normalization": "NFD", "note_decompositions": "U+037E -> ';', U+0387 -> U+00B7, ё/й/ї/ΐ/ΰ etc. -> base+mark", "unknown_codepoint": "reject line at ingest (accounted)", "whitespace": "runs collapse to U+0020", "change_note": "E4 wave 1b frozen codec: original v1 atom IDs unchanged; seven census additions appended. Native v2 imports preserve appended literals. A/B original labels are retained exactly.", "literal_override_atoms": "΄јѣ᾽᾿„•" }, "atoms": [ { "id": 1, "cp": "U+0020", "ch": " ", "kind": "space", "script": "zyyy" }, { "id": 2, "cp": "U+0041", "ch": "A", "kind": "base", "script": "latn" }, { "id": 3, "cp": "U+0042", "ch": "B", "kind": "base", "script": "latn" }, { "id": 4, "cp": "U+0043", "ch": "C", "kind": "base", "script": "latn" }, { "id": 5, "cp": "U+0044", "ch": "D", "kind": "base", "script": "latn" }, { "id": 6, "cp": "U+0045", "ch": "E", "kind": "base", "script": "latn" }, { "id": 7, "cp": "U+0046", "ch": "F", "kind": "base", "script": "latn" }, { "id": 8, "cp": "U+0047", "ch": "G", "kind": "base", "script": "latn" }, { "id": 9, "cp": "U+0048", "ch": "H", "kind": "base", "script": "latn" }, { "id": 10, "cp": "U+0049", "ch": "I", "kind": "base", "script": "latn" }, { "id": 11, "cp": "U+004A", "ch": "J", "kind": "base", "script": "latn" }, { "id": 12, "cp": "U+004B", "ch": "K", "kind": "base", "script": "latn" }, { "id": 13, "cp": "U+004C", "ch": "L", "kind": "base", "script": "latn" }, { "id": 14, "cp": "U+004D", "ch": "M", "kind": "base", "script": "latn" }, { "id": 15, "cp": "U+004E", "ch": "N", "kind": "base", "script": "latn" }, { "id": 16, "cp": "U+004F", "ch": "O", "kind": "base", "script": "latn" }, { "id": 17, "cp": "U+0050", "ch": "P", "kind": "base", "script": "latn" }, { "id": 18, "cp": "U+0051", "ch": "Q", "kind": "base", "script": "latn" }, { "id": 19, "cp": "U+0052", "ch": "R", "kind": "base", "script": "latn" }, { "id": 20, "cp": "U+0053", "ch": "S", "kind": "base", "script": "latn" }, { "id": 21, "cp": "U+0054", "ch": "T", "kind": "base", "script": "latn" }, { "id": 22, "cp": "U+0055", "ch": "U", "kind": "base", "script": "latn" }, { "id": 23, "cp": "U+0056", "ch": "V", "kind": "base", "script": "latn" }, { "id": 24, "cp": "U+0057", "ch": "W", "kind": "base", "script": "latn" }, { "id": 25, "cp": "U+0058", "ch": "X", "kind": "base", "script": "latn" }, { "id": 26, "cp": "U+0059", "ch": "Y", "kind": "base", "script": "latn" }, { "id": 27, "cp": "U+005A", "ch": "Z", "kind": "base", "script": "latn" }, { "id": 28, "cp": "U+0061", "ch": "a", "kind": "base", "script": "latn" }, { "id": 29, "cp": "U+0062", "ch": "b", "kind": "base", "script": "latn" }, { "id": 30, "cp": "U+0063", "ch": "c", "kind": "base", "script": "latn" }, { "id": 31, "cp": "U+0064", "ch": "d", "kind": "base", "script": "latn" }, { "id": 32, "cp": "U+0065", "ch": "e", "kind": "base", "script": "latn" }, { "id": 33, "cp": "U+0066", "ch": "f", "kind": "base", "script": "latn" }, { "id": 34, "cp": "U+0067", "ch": "g", "kind": "base", "script": "latn" }, { "id": 35, "cp": "U+0068", "ch": "h", "kind": "base", "script": "latn" }, { "id": 36, "cp": "U+0069", "ch": "i", "kind": "base", "script": "latn" }, { "id": 37, "cp": "U+006A", "ch": "j", "kind": "base", "script": "latn" }, { "id": 38, "cp": "U+006B", "ch": "k", "kind": "base", "script": "latn" }, { "id": 39, "cp": "U+006C", "ch": "l", "kind": "base", "script": "latn" }, { "id": 40, "cp": "U+006D", "ch": "m", "kind": "base", "script": "latn" }, { "id": 41, "cp": "U+006E", "ch": "n", "kind": "base", "script": "latn" }, { "id": 42, "cp": "U+006F", "ch": "o", "kind": "base", "script": "latn" }, { "id": 43, "cp": "U+0070", "ch": "p", "kind": "base", "script": "latn" }, { "id": 44, "cp": "U+0071", "ch": "q", "kind": "base", "script": "latn" }, { "id": 45, "cp": "U+0072", "ch": "r", "kind": "base", "script": "latn" }, { "id": 46, "cp": "U+0073", "ch": "s", "kind": "base", "script": "latn" }, { "id": 47, "cp": "U+0074", "ch": "t", "kind": "base", "script": "latn" }, { "id": 48, "cp": "U+0075", "ch": "u", "kind": "base", "script": "latn" }, { "id": 49, "cp": "U+0076", "ch": "v", "kind": "base", "script": "latn" }, { "id": 50, "cp": "U+0077", "ch": "w", "kind": "base", "script": "latn" }, { "id": 51, "cp": "U+0078", "ch": "x", "kind": "base", "script": "latn" }, { "id": 52, "cp": "U+0079", "ch": "y", "kind": "base", "script": "latn" }, { "id": 53, "cp": "U+007A", "ch": "z", "kind": "base", "script": "latn" }, { "id": 54, "cp": "U+00C6", "ch": "Æ", "kind": "base", "script": "latn" }, { "id": 55, "cp": "U+00DF", "ch": "ß", "kind": "base", "script": "latn" }, { "id": 56, "cp": "U+00E6", "ch": "æ", "kind": "base", "script": "latn" }, { "id": 57, "cp": "U+0152", "ch": "Œ", "kind": "base", "script": "latn" }, { "id": 58, "cp": "U+0153", "ch": "œ", "kind": "base", "script": "latn" }, { "id": 59, "cp": "U+0391", "ch": "Α", "kind": "base", "script": "grek" }, { "id": 60, "cp": "U+0392", "ch": "Β", "kind": "base", "script": "grek" }, { "id": 61, "cp": "U+0393", "ch": "Γ", "kind": "base", "script": "grek" }, { "id": 62, "cp": "U+0394", "ch": "Δ", "kind": "base", "script": "grek" }, { "id": 63, "cp": "U+0395", "ch": "Ε", "kind": "base", "script": "grek" }, { "id": 64, "cp": "U+0396", "ch": "Ζ", "kind": "base", "script": "grek" }, { "id": 65, "cp": "U+0397", "ch": "Η", "kind": "base", "script": "grek" }, { "id": 66, "cp": "U+0398", "ch": "Θ", "kind": "base", "script": "grek" }, { "id": 67, "cp": "U+0399", "ch": "Ι", "kind": "base", "script": "grek" }, { "id": 68, "cp": "U+039A", "ch": "Κ", "kind": "base", "script": "grek" }, { "id": 69, "cp": "U+039B", "ch": "Λ", "kind": "base", "script": "grek" }, { "id": 70, "cp": "U+039C", "ch": "Μ", "kind": "base", "script": "grek" }, { "id": 71, "cp": "U+039D", "ch": "Ν", "kind": "base", "script": "grek" }, { "id": 72, "cp": "U+039E", "ch": "Ξ", "kind": "base", "script": "grek" }, { "id": 73, "cp": "U+039F", "ch": "Ο", "kind": "base", "script": "grek" }, { "id": 74, "cp": "U+03A0", "ch": "Π", "kind": "base", "script": "grek" }, { "id": 75, "cp": "U+03A1", "ch": "Ρ", "kind": "base", "script": "grek" }, { "id": 76, "cp": "U+03A3", "ch": "Σ", "kind": "base", "script": "grek" }, { "id": 77, "cp": "U+03A4", "ch": "Τ", "kind": "base", "script": "grek" }, { "id": 78, "cp": "U+03A5", "ch": "Υ", "kind": "base", "script": "grek" }, { "id": 79, "cp": "U+03A6", "ch": "Φ", "kind": "base", "script": "grek" }, { "id": 80, "cp": "U+03A7", "ch": "Χ", "kind": "base", "script": "grek" }, { "id": 81, "cp": "U+03A8", "ch": "Ψ", "kind": "base", "script": "grek" }, { "id": 82, "cp": "U+03A9", "ch": "Ω", "kind": "base", "script": "grek" }, { "id": 83, "cp": "U+03B1", "ch": "α", "kind": "base", "script": "grek" }, { "id": 84, "cp": "U+03B2", "ch": "β", "kind": "base", "script": "grek" }, { "id": 85, "cp": "U+03B3", "ch": "γ", "kind": "base", "script": "grek" }, { "id": 86, "cp": "U+03B4", "ch": "δ", "kind": "base", "script": "grek" }, { "id": 87, "cp": "U+03B5", "ch": "ε", "kind": "base", "script": "grek" }, { "id": 88, "cp": "U+03B6", "ch": "ζ", "kind": "base", "script": "grek" }, { "id": 89, "cp": "U+03B7", "ch": "η", "kind": "base", "script": "grek" }, { "id": 90, "cp": "U+03B8", "ch": "θ", "kind": "base", "script": "grek" }, { "id": 91, "cp": "U+03B9", "ch": "ι", "kind": "base", "script": "grek" }, { "id": 92, "cp": "U+03BA", "ch": "κ", "kind": "base", "script": "grek" }, { "id": 93, "cp": "U+03BB", "ch": "λ", "kind": "base", "script": "grek" }, { "id": 94, "cp": "U+03BC", "ch": "μ", "kind": "base", "script": "grek" }, { "id": 95, "cp": "U+03BD", "ch": "ν", "kind": "base", "script": "grek" }, { "id": 96, "cp": "U+03BE", "ch": "ξ", "kind": "base", "script": "grek" }, { "id": 97, "cp": "U+03BF", "ch": "ο", "kind": "base", "script": "grek" }, { "id": 98, "cp": "U+03C0", "ch": "π", "kind": "base", "script": "grek" }, { "id": 99, "cp": "U+03C1", "ch": "ρ", "kind": "base", "script": "grek" }, { "id": 100, "cp": "U+03C2", "ch": "ς", "kind": "base", "script": "grek" }, { "id": 101, "cp": "U+03C3", "ch": "σ", "kind": "base", "script": "grek" }, { "id": 102, "cp": "U+03C4", "ch": "τ", "kind": "base", "script": "grek" }, { "id": 103, "cp": "U+03C5", "ch": "υ", "kind": "base", "script": "grek" }, { "id": 104, "cp": "U+03C6", "ch": "φ", "kind": "base", "script": "grek" }, { "id": 105, "cp": "U+03C7", "ch": "χ", "kind": "base", "script": "grek" }, { "id": 106, "cp": "U+03C8", "ch": "ψ", "kind": "base", "script": "grek" }, { "id": 107, "cp": "U+03C9", "ch": "ω", "kind": "base", "script": "grek" }, { "id": 108, "cp": "U+03D8", "ch": "Ϙ", "kind": "base", "script": "grek" }, { "id": 109, "cp": "U+03D9", "ch": "ϙ", "kind": "base", "script": "grek" }, { "id": 110, "cp": "U+03DA", "ch": "Ϛ", "kind": "base", "script": "grek" }, { "id": 111, "cp": "U+03DB", "ch": "ϛ", "kind": "base", "script": "grek" }, { "id": 112, "cp": "U+03DC", "ch": "Ϝ", "kind": "base", "script": "grek" }, { "id": 113, "cp": "U+03DD", "ch": "ϝ", "kind": "base", "script": "grek" }, { "id": 114, "cp": "U+03E0", "ch": "Ϡ", "kind": "base", "script": "grek" }, { "id": 115, "cp": "U+03E1", "ch": "ϡ", "kind": "base", "script": "grek" }, { "id": 116, "cp": "U+0404", "ch": "Є", "kind": "base", "script": "cyrl" }, { "id": 117, "cp": "U+0406", "ch": "І", "kind": "base", "script": "cyrl" }, { "id": 118, "cp": "U+0407", "ch": "Ї", "kind": "base", "script": "cyrl" }, { "id": 119, "cp": "U+0410", "ch": "А", "kind": "base", "script": "cyrl" }, { "id": 120, "cp": "U+0411", "ch": "Б", "kind": "base", "script": "cyrl" }, { "id": 121, "cp": "U+0412", "ch": "В", "kind": "base", "script": "cyrl" }, { "id": 122, "cp": "U+0413", "ch": "Г", "kind": "base", "script": "cyrl" }, { "id": 123, "cp": "U+0414", "ch": "Д", "kind": "base", "script": "cyrl" }, { "id": 124, "cp": "U+0415", "ch": "Е", "kind": "base", "script": "cyrl" }, { "id": 125, "cp": "U+0416", "ch": "Ж", "kind": "base", "script": "cyrl" }, { "id": 126, "cp": "U+0417", "ch": "З", "kind": "base", "script": "cyrl" }, { "id": 127, "cp": "U+0418", "ch": "И", "kind": "base", "script": "cyrl" }, { "id": 128, "cp": "U+041A", "ch": "К", "kind": "base", "script": "cyrl" }, { "id": 129, "cp": "U+041B", "ch": "Л", "kind": "base", "script": "cyrl" }, { "id": 130, "cp": "U+041C", "ch": "М", "kind": "base", "script": "cyrl" }, { "id": 131, "cp": "U+041D", "ch": "Н", "kind": "base", "script": "cyrl" }, { "id": 132, "cp": "U+041E", "ch": "О", "kind": "base", "script": "cyrl" }, { "id": 133, "cp": "U+041F", "ch": "П", "kind": "base", "script": "cyrl" }, { "id": 134, "cp": "U+0420", "ch": "Р", "kind": "base", "script": "cyrl" }, { "id": 135, "cp": "U+0421", "ch": "С", "kind": "base", "script": "cyrl" }, { "id": 136, "cp": "U+0422", "ch": "Т", "kind": "base", "script": "cyrl" }, { "id": 137, "cp": "U+0423", "ch": "У", "kind": "base", "script": "cyrl" }, { "id": 138, "cp": "U+0424", "ch": "Ф", "kind": "base", "script": "cyrl" }, { "id": 139, "cp": "U+0425", "ch": "Х", "kind": "base", "script": "cyrl" }, { "id": 140, "cp": "U+0426", "ch": "Ц", "kind": "base", "script": "cyrl" }, { "id": 141, "cp": "U+0427", "ch": "Ч", "kind": "base", "script": "cyrl" }, { "id": 142, "cp": "U+0428", "ch": "Ш", "kind": "base", "script": "cyrl" }, { "id": 143, "cp": "U+0429", "ch": "Щ", "kind": "base", "script": "cyrl" }, { "id": 144, "cp": "U+042A", "ch": "Ъ", "kind": "base", "script": "cyrl" }, { "id": 145, "cp": "U+042B", "ch": "Ы", "kind": "base", "script": "cyrl" }, { "id": 146, "cp": "U+042C", "ch": "Ь", "kind": "base", "script": "cyrl" }, { "id": 147, "cp": "U+042D", "ch": "Э", "kind": "base", "script": "cyrl" }, { "id": 148, "cp": "U+042E", "ch": "Ю", "kind": "base", "script": "cyrl" }, { "id": 149, "cp": "U+042F", "ch": "Я", "kind": "base", "script": "cyrl" }, { "id": 150, "cp": "U+0430", "ch": "а", "kind": "base", "script": "cyrl" }, { "id": 151, "cp": "U+0431", "ch": "б", "kind": "base", "script": "cyrl" }, { "id": 152, "cp": "U+0432", "ch": "в", "kind": "base", "script": "cyrl" }, { "id": 153, "cp": "U+0433", "ch": "г", "kind": "base", "script": "cyrl" }, { "id": 154, "cp": "U+0434", "ch": "д", "kind": "base", "script": "cyrl" }, { "id": 155, "cp": "U+0435", "ch": "е", "kind": "base", "script": "cyrl" }, { "id": 156, "cp": "U+0436", "ch": "ж", "kind": "base", "script": "cyrl" }, { "id": 157, "cp": "U+0437", "ch": "з", "kind": "base", "script": "cyrl" }, { "id": 158, "cp": "U+0438", "ch": "и", "kind": "base", "script": "cyrl" }, { "id": 159, "cp": "U+043A", "ch": "к", "kind": "base", "script": "cyrl" }, { "id": 160, "cp": "U+043B", "ch": "л", "kind": "base", "script": "cyrl" }, { "id": 161, "cp": "U+043C", "ch": "м", "kind": "base", "script": "cyrl" }, { "id": 162, "cp": "U+043D", "ch": "н", "kind": "base", "script": "cyrl" }, { "id": 163, "cp": "U+043E", "ch": "о", "kind": "base", "script": "cyrl" }, { "id": 164, "cp": "U+043F", "ch": "п", "kind": "base", "script": "cyrl" }, { "id": 165, "cp": "U+0440", "ch": "р", "kind": "base", "script": "cyrl" }, { "id": 166, "cp": "U+0441", "ch": "с", "kind": "base", "script": "cyrl" }, { "id": 167, "cp": "U+0442", "ch": "т", "kind": "base", "script": "cyrl" }, { "id": 168, "cp": "U+0443", "ch": "у", "kind": "base", "script": "cyrl" }, { "id": 169, "cp": "U+0444", "ch": "ф", "kind": "base", "script": "cyrl" }, { "id": 170, "cp": "U+0445", "ch": "х", "kind": "base", "script": "cyrl" }, { "id": 171, "cp": "U+0446", "ch": "ц", "kind": "base", "script": "cyrl" }, { "id": 172, "cp": "U+0447", "ch": "ч", "kind": "base", "script": "cyrl" }, { "id": 173, "cp": "U+0448", "ch": "ш", "kind": "base", "script": "cyrl" }, { "id": 174, "cp": "U+0449", "ch": "щ", "kind": "base", "script": "cyrl" }, { "id": 175, "cp": "U+044A", "ch": "ъ", "kind": "base", "script": "cyrl" }, { "id": 176, "cp": "U+044B", "ch": "ы", "kind": "base", "script": "cyrl" }, { "id": 177, "cp": "U+044C", "ch": "ь", "kind": "base", "script": "cyrl" }, { "id": 178, "cp": "U+044D", "ch": "э", "kind": "base", "script": "cyrl" }, { "id": 179, "cp": "U+044E", "ch": "ю", "kind": "base", "script": "cyrl" }, { "id": 180, "cp": "U+044F", "ch": "я", "kind": "base", "script": "cyrl" }, { "id": 181, "cp": "U+0454", "ch": "є", "kind": "base", "script": "cyrl" }, { "id": 182, "cp": "U+0456", "ch": "і", "kind": "base", "script": "cyrl" }, { "id": 183, "cp": "U+0490", "ch": "Ґ", "kind": "base", "script": "cyrl" }, { "id": 184, "cp": "U+0491", "ch": "ґ", "kind": "base", "script": "cyrl" }, { "id": 185, "cp": "U+0300", "ch": "̀", "kind": "mark", "script": "zinh" }, { "id": 186, "cp": "U+0301", "ch": "́", "kind": "mark", "script": "zinh" }, { "id": 187, "cp": "U+0302", "ch": "̂", "kind": "mark", "script": "zinh" }, { "id": 188, "cp": "U+0303", "ch": "̃", "kind": "mark", "script": "zinh" }, { "id": 189, "cp": "U+0304", "ch": "̄", "kind": "mark", "script": "zinh" }, { "id": 190, "cp": "U+0306", "ch": "̆", "kind": "mark", "script": "zinh" }, { "id": 191, "cp": "U+0308", "ch": "̈", "kind": "mark", "script": "zinh" }, { "id": 192, "cp": "U+030A", "ch": "̊", "kind": "mark", "script": "zinh" }, { "id": 193, "cp": "U+030C", "ch": "̌", "kind": "mark", "script": "zinh" }, { "id": 194, "cp": "U+0313", "ch": "̓", "kind": "mark", "script": "zinh" }, { "id": 195, "cp": "U+0314", "ch": "̔", "kind": "mark", "script": "zinh" }, { "id": 196, "cp": "U+0327", "ch": "̧", "kind": "mark", "script": "zinh" }, { "id": 197, "cp": "U+0342", "ch": "͂", "kind": "mark", "script": "zinh" }, { "id": 198, "cp": "U+0345", "ch": "ͅ", "kind": "mark", "script": "zinh" }, { "id": 199, "cp": "U+0030", "ch": "0", "kind": "digit", "script": "zyyy" }, { "id": 200, "cp": "U+0031", "ch": "1", "kind": "digit", "script": "zyyy" }, { "id": 201, "cp": "U+0032", "ch": "2", "kind": "digit", "script": "zyyy" }, { "id": 202, "cp": "U+0033", "ch": "3", "kind": "digit", "script": "zyyy" }, { "id": 203, "cp": "U+0034", "ch": "4", "kind": "digit", "script": "zyyy" }, { "id": 204, "cp": "U+0035", "ch": "5", "kind": "digit", "script": "zyyy" }, { "id": 205, "cp": "U+0036", "ch": "6", "kind": "digit", "script": "zyyy" }, { "id": 206, "cp": "U+0037", "ch": "7", "kind": "digit", "script": "zyyy" }, { "id": 207, "cp": "U+0038", "ch": "8", "kind": "digit", "script": "zyyy" }, { "id": 208, "cp": "U+0039", "ch": "9", "kind": "digit", "script": "zyyy" }, { "id": 209, "cp": "U+0021", "ch": "!", "kind": "punct", "script": "zyyy" }, { "id": 210, "cp": "U+0022", "ch": "\"", "kind": "punct", "script": "zyyy" }, { "id": 211, "cp": "U+0027", "ch": "'", "kind": "punct", "script": "zyyy" }, { "id": 212, "cp": "U+0028", "ch": "(", "kind": "punct", "script": "zyyy" }, { "id": 213, "cp": "U+0029", "ch": ")", "kind": "punct", "script": "zyyy" }, { "id": 214, "cp": "U+002C", "ch": ",", "kind": "punct", "script": "zyyy" }, { "id": 215, "cp": "U+002D", "ch": "-", "kind": "punct", "script": "zyyy" }, { "id": 216, "cp": "U+002E", "ch": ".", "kind": "punct", "script": "zyyy" }, { "id": 217, "cp": "U+003A", "ch": ":", "kind": "punct", "script": "zyyy" }, { "id": 218, "cp": "U+003B", "ch": ";", "kind": "punct", "script": "zyyy" }, { "id": 219, "cp": "U+003F", "ch": "?", "kind": "punct", "script": "zyyy" }, { "id": 220, "cp": "U+005B", "ch": "[", "kind": "punct", "script": "zyyy" }, { "id": 221, "cp": "U+005D", "ch": "]", "kind": "punct", "script": "zyyy" }, { "id": 222, "cp": "U+00A1", "ch": "¡", "kind": "punct", "script": "zyyy" }, { "id": 223, "cp": "U+00AB", "ch": "«", "kind": "punct", "script": "zyyy" }, { "id": 224, "cp": "U+00B7", "ch": "·", "kind": "punct", "script": "zyyy" }, { "id": 225, "cp": "U+00BB", "ch": "»", "kind": "punct", "script": "zyyy" }, { "id": 226, "cp": "U+00BF", "ch": "¿", "kind": "punct", "script": "zyyy" }, { "id": 227, "cp": "U+02B9", "ch": "ʹ", "kind": "punct", "script": "zyyy" }, { "id": 228, "cp": "U+0375", "ch": "͵", "kind": "punct", "script": "zyyy" }, { "id": 229, "cp": "U+2013", "ch": "–", "kind": "punct", "script": "zyyy" }, { "id": 230, "cp": "U+2014", "ch": "—", "kind": "punct", "script": "zyyy" }, { "id": 231, "cp": "U+2018", "ch": "‘", "kind": "punct", "script": "zyyy" }, { "id": 232, "cp": "U+2019", "ch": "’", "kind": "punct", "script": "zyyy" }, { "id": 233, "cp": "U+201C", "ch": "“", "kind": "punct", "script": "zyyy" }, { "id": 234, "cp": "U+201D", "ch": "”", "kind": "punct", "script": "zyyy" }, { "id": 235, "cp": "U+2026", "ch": "…", "kind": "punct", "script": "zyyy" }, { "id": 236, "cp": "U+0025", "ch": "%", "kind": "sym", "script": "zyyy" }, { "id": 237, "cp": "U+0026", "ch": "&", "kind": "sym", "script": "zyyy" }, { "id": 238, "cp": "U+002A", "ch": "*", "kind": "sym", "script": "zyyy" }, { "id": 239, "cp": "U+002B", "ch": "+", "kind": "sym", "script": "zyyy" }, { "id": 240, "cp": "U+002F", "ch": "/", "kind": "sym", "script": "zyyy" }, { "id": 241, "cp": "U+003D", "ch": "=", "kind": "sym", "script": "zyyy" }, { "id": 242, "cp": "U+00A3", "ch": "£", "kind": "sym", "script": "zyyy" }, { "id": 243, "cp": "U+00A7", "ch": "§", "kind": "sym", "script": "zyyy" }, { "id": 244, "cp": "U+00B0", "ch": "°", "kind": "sym", "script": "zyyy" }, { "id": 245, "cp": "U+2020", "ch": "†", "kind": "sym", "script": "zyyy" }, { "id": 246, "cp": "U+2021", "ch": "‡", "kind": "sym", "script": "zyyy" }, { "id": 247, "cp": "U+20AC", "ch": "€", "kind": "sym", "script": "zyyy" }, { "id": 248, "cp": "U+0384", "ch": "΄", "kind": "sym", "script": "grek" }, { "id": 249, "cp": "U+0458", "ch": "ј", "kind": "base", "script": "cyrl" }, { "id": 250, "cp": "U+0463", "ch": "ѣ", "kind": "base", "script": "cyrl" }, { "id": 251, "cp": "U+1FBD", "ch": "᾽", "kind": "sym", "script": "grek" }, { "id": 252, "cp": "U+1FBF", "ch": "᾿", "kind": "sym", "script": "grek" }, { "id": 253, "cp": "U+201E", "ch": "„", "kind": "punct", "script": "zyyy" }, { "id": 254, "cp": "U+2022", "ch": "•", "kind": "punct", "script": "zyyy" }, { "id": 255, "cp": "U+045B", "ch": "ћ", "kind": "base", "script": "cyrl" }, { "id": 256, "cp": "U+045A", "ch": "њ", "kind": "base", "script": "cyrl" }, { "id": 257, "cp": "U+0459", "ch": "љ", "kind": "base", "script": "cyrl" }, { "id": 258, "cp": "U+0452", "ch": "ђ", "kind": "base", "script": "cyrl" }, { "id": 259, "cp": "U+045F", "ch": "џ", "kind": "base", "script": "cyrl" }, { "id": 260, "cp": "U+0408", "ch": "Ј", "kind": "base", "script": "cyrl" }, { "id": 261, "cp": "U+040B", "ch": "Ћ", "kind": "base", "script": "cyrl" }, { "id": 262, "cp": "U+040A", "ch": "Њ", "kind": "base", "script": "cyrl" }, { "id": 263, "cp": "U+0409", "ch": "Љ", "kind": "base", "script": "cyrl" }, { "id": 264, "cp": "U+0402", "ch": "Ђ", "kind": "base", "script": "cyrl" }, { "id": 265, "cp": "U+040F", "ch": "Џ", "kind": "base", "script": "cyrl" } ] }
{
"version": "v2.1",
"blank_id": 0,
"policy": {
"mark_order": "NFD canonical ordering; equal-ccc keeps source order (D-4a strict)",
"normalization": "NFD",
"note_decompositions": "U+037E -> ';', U+0387 -> U+00B7, ё/й/ї/ΐ/ΰ etc. -> base+mark",
"unknown_codepoint": "reject line at ingest (accounted)",
"whitespace": "runs collapse to U+0020",
"change_note": "E4 wave 1b frozen codec: original v1 atom IDs unchanged; seven census additions appended. Native v2 imports preserve appended literals. A/B original labels are retained exactly.",
"literal_override_atoms": "΄јѣ᾽᾿„•"
},
"atoms": [
{
"id": 1,
"cp": "U+0020",
"ch": " ",
"kind": "space",
"script": "zyyy"
},
{
"id": 2,
"cp": "U+0041",
"ch": "A",
"kind": "base",
"script": "latn"
},
{
"id": 3,
"cp": "U+0042",
"ch": "B",
"kind": "base",
"script": "latn"
},
{
"id": 4,
"cp": "U+0043",
"ch": "C",
"kind": "base",
"script": "latn"
},
{
"id": 5,
"cp": "U+0044",
"ch": "D",
"kind": "base",
"script": "latn"
},
{
"id": 6,
"cp": "U+0045",
"ch": "E",
"kind": "base",
"script": "latn"
},
{
"id": 7,
"cp": "U+0046",
"ch": "F",
"kind": "base",
"script": "latn"
},
{
"id": 8,
"cp": "U+0047",
"ch": "G",
"kind": "base",
"script": "latn"
},
{
"id": 9,
"cp": "U+0048",
"ch": "H",
"kind": "base",
"script": "latn"
},
{
"id": 10,
"cp": "U+0049",
"ch": "I",
"kind": "base",
"script": "latn"
},
{
"id": 11,
"cp": "U+004A",
"ch": "J",
"kind": "base",
"script": "latn"
},
{
"id": 12,
"cp": "U+004B",
"ch": "K",
"kind": "base",
"script": "latn"
},
{
"id": 13,
"cp": "U+004C",