DateKeys/testdata/vectors/paths.json

{
  "spec": "0.16",
  "description": "Paths of a format 3 head (spec §29.5) with the Unicode 18.0.0 and best-fit tables of §29.5.1, generated by the reference implementation. paths: one path and the rules of one entry, R2 to R6c and R10; trees: the paths of a head, of 0 bytes each, and the result of decoding it. See testdata/README.md.",
  "unicode_version": "18.0.0",
  "tables_digest": "07cf5d54aea1cd13a3ecef14a06976cc49a3cdad755cf9bc10395178b93aeb07",
  "paths": [
    {
      "name": "a file",
      "path": "nota.txt",
      "result": "ok"
    },
    {
      "name": "a file in two folders",
      "path": "fotos/2025/playa.jpg",
      "result": "ok"
    },
    {
      "name": "non-ASCII letters",
      "path": "música/canción.txt",
      "result": "ok"
    },
    {
      "name": "U+00BF, which bestfit1250 maps to '?'",
      "path": "¿Qué es esto.jpg",
      "result": "ok"
    },
    {
      "name": "U+00A7, which bestfit874 maps to a C0 control",
      "path": "§ 3 contrato.pdf",
      "result": "ok"
    },
    {
      "name": "U+2665, which bestfit874 maps to a C0 control",
      "path": "Para ti ♥.jpg",
      "result": "ok"
    },
    {
      "name": "U+2192, which bestfit1253 maps to '\u003e'",
      "path": "Madrid → Lisboa",
      "result": "ok"
    },
    {
      "name": "U+00A0 at the start of a segment: no table maps it to ASCII",
      "path": " a",
      "result": "ok"
    },
    {
      "name": "U+00A0 at the end of a segment",
      "path": "a ",
      "result": "ok"
    },
    {
      "name": "U+3000 at the start: bestfit1250 and others map it to U+0020",
      "path": "　a",
      "result": "R6c: segment 1: code page 1250 maps the segment to one that breaks R5: the segment starts with U+0020"
    },
    {
      "name": "U+3000 at the end",
      "path": "a　",
      "result": "R6c: segment 1: code page 1250 maps the segment to one that breaks R5: the segment ends with U+0020"
    },
    {
      "name": "CON.txt in full-width forms",
      "path": "ＣＯＮ.txt",
      "result": "R6c: segment 1: code page 874 maps the segment to one that breaks R6: CON is a reserved device name"
    },
    {
      "name": "U+2216 SET MINUS",
      "path": "a∖b",
      "result": "R6c: segment 1: code page 1250 maps the segment to one with U+005C"
    },
    {
      "name": "U+2236 RATIO",
      "path": "a∶b",
      "result": "R6c: segment 1: code page 1250 maps the segment to one with U+003A"
    },
    {
      "name": "U+00A5, which cp932 maps to '\\'",
      "path": "a¥b",
      "result": "R6c: segment 1: code page 932 maps the segment to one with U+005C"
    },
    {
      "name": "U+20A9, which cp949 maps to '\\'",
      "path": "a₩b",
      "result": "R6c: segment 1: code page 949 maps the segment to one with U+005C"
    },
    {
      "name": "U+00B4, which cp1253 maps to '/'",
      "path": "a´b",
      "result": "R6c: segment 1: code page 1253 maps the segment to one with U+002F"
    },
    {
      "name": "full-width solidus",
      "path": "a／b",
      "result": "R6c: segment 1: code page 874 maps the segment to one with U+002F"
    },
    {
      "name": "full-width reverse solidus",
      "path": "a＼b",
      "result": "R6c: segment 1: code page 874 maps the segment to one with U+005C"
    },
    {
      "name": "full-width colon",
      "path": "a：b",
      "result": "R6c: segment 1: code page 874 maps the segment to one with U+003A"
    },
    {
      "name": "two full-width full stops",
      "path": "．．",
      "result": "R6c: segment 1: code page 874 maps the segment to one that breaks R3: the segment is two dots"
    },
    {
      "name": "8.3 alias",
      "path": "ABCDEF~1",
      "result": "R6b: segment 1: the segment has the form of an 8.3 alias"
    },
    {
      "name": "8.3 alias with an extension",
      "path": "ABCDEF~1.TXT",
      "result": "R6b: segment 1: the segment has the form of an 8.3 alias"
    },
    {
      "name": "~1 alone",
      "path": "~1",
      "result": "R6b: segment 1: the segment has the form of an 8.3 alias"
    },
    {
      "name": "8.3 alias with a non-ASCII letter",
      "path": "Ä~1.txt",
      "result": "R6b: segment 1: the segment has the form of an 8.3 alias"
    },
    {
      "name": "nine characters before ~1",
      "path": "ABCDEFGHI~1",
      "result": "ok"
    },
    {
      "name": "~1 inside a name",
      "path": "a~1b",
      "result": "ok"
    },
    {
      "name": "~2023 in a long name",
      "path": "report~2023.txt",
      "result": "ok"
    },
    {
      "name": "unassigned U+0378",
      "path": "a͸b",
      "result": "R4: segment 1: unassigned U+0378"
    },
    {
      "name": "noncharacter U+FFFE",
      "path": "a￾b",
      "result": "R4: segment 1: unassigned U+FFFE"
    },
    {
      "name": "U+206A",
      "path": "ab",
      "result": "R4: segment 1: invisible U+206A"
    },
    {
      "name": "U+206F",
      "path": "ab",
      "result": "R4: segment 1: invisible U+206F"
    },
    {
      "name": "soft hyphen U+00AD",
      "path": "a­b",
      "result": "R4: segment 1: invisible U+00AD"
    },
    {
      "name": "U+034F COMBINING GRAPHEME JOINER",
      "path": "a͏b",
      "result": "R4: segment 1: invisible U+034F"
    },
    {
      "name": "U+200B ZERO WIDTH SPACE",
      "path": "a​b",
      "result": "R4: segment 1: invisible U+200B"
    },
    {
      "name": "U+2060 WORD JOINER",
      "path": "a⁠b",
      "result": "R4: segment 1: invisible U+2060"
    },
    {
      "name": "U+3164 HANGUL FILLER",
      "path": "aㅤb",
      "result": "R4: segment 1: invisible U+3164"
    },
    {
      "name": "U+FEFF",
      "path": "ab",
      "result": "R4: segment 1: invisible U+FEFF"
    },
    {
      "name": "U+202E RIGHT-TO-LEFT OVERRIDE",
      "path": "a‮b",
      "result": "R4: segment 1: invisible U+202E"
    },
    {
      "name": "tag U+E0041",
      "path": "a󠁁",
      "result": "R4: segment 1: invisible U+E0041"
    },
    {
      "name": "variation selector VS17",
      "path": "😀󠄀",
      "result": "R4: segment 1: invisible U+E0100"
    },
    {
      "name": "the flag of Scotland, with tags",
      "path": "🏴󠁧󠁢󠁳󠁣󠁴󠁿",
      "result": "R4: segment 1: invisible U+E0067"
    },
    {
      "name": "U+F03A of the private use area",
      "path": "informeanexo",
      "result": "R4: segment 1: private use U+F03A"
    },
    {
      "name": "TAB",
      "path": "a\tb",
      "result": "R4: segment 1: control U+0009"
    },
    {
      "name": "U+2028 LINE SEPARATOR",
      "path": "a\u2028b",
      "result": "R4: segment 1: separator U+2028"
    },
    {
      "name": "':'",
      "path": "a:b",
      "result": "R4: segment 1: character U+003A"
    },
    {
      "name": "'\\'",
      "path": "a\\b",
      "result": "R4: segment 1: character U+005C"
    },
    {
      "name": "'?'",
      "path": "a?b",
      "result": "R4: segment 1: character U+003F"
    },
    {
      "name": "'\"'",
      "path": "a\"b",
      "result": "R4: segment 1: character U+0022"
    },
    {
      "name": "'*', '\u003c', '\u003e' and '|'",
      "path": "a*b\u003cc\u003ed|e",
      "result": "R4: segment 1: character U+002A"
    },
    {
      "name": "a dot and ZWJ",
      "path": ".‍",
      "result": "R3: segment 1: the segment is a dot without ZWNJ, ZWJ, VS15 and VS16"
    },
    {
      "name": "a segment of ZWJ alone",
      "path": "‍",
      "result": "R3: segment 1: the segment is empty without ZWNJ, ZWJ, VS15 and VS16"
    },
    {
      "name": "two dots",
      "path": "..",
      "result": "R3: segment 1: the segment is two dots"
    },
    {
      "name": "one dot inside",
      "path": "a/./b",
      "result": "R3: segment 2: the segment is a dot"
    },
    {
      "name": "a segment of 256 bytes",
      "path": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
      "result": "R3: segment 1: 256 bytes, more than 255"
    },
    {
      "name": "a segment of 255 bytes",
      "path": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
      "result": "ok"
    },
    {
      "name": "127 times U+0390: 381 UTF-16 units after NFD",
      "path": "ΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐ",
      "result": "R3: segment 1: its NFD is 381 UTF-16 code units, more than 255"
    },
    {
      "name": "85 times U+0390: 255 UTF-16 units after NFD",
      "path": "ΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐΐ",
      "result": "ok"
    },
    {
      "name": "VS16 after U+2764, which admits it",
      "path": "❤️.txt",
      "result": "ok"
    },
    {
      "name": "VS16 after a",
      "path": "a️",
      "result": "R4b: segment 1: U+FE0F is not part of an emoji variation sequence"
    },
    {
      "name": "ZWJ at the start",
      "path": "‍a",
      "result": "R4b: segment 1: U+200D at the start"
    },
    {
      "name": "ZWJ at the end",
      "path": "a‍",
      "result": "R4b: segment 1: U+200D at the end"
    },
    {
      "name": "two ZWJ in a row",
      "path": "a‍‍b",
      "result": "R4b: segment 1: U+200D right after U+200D"
    },
    {
      "name": "ZWNJ and ZWJ in a row",
      "path": "a‌‍b",
      "result": "R4b: segment 1: U+200D right after U+200C"
    },
    {
      "name": "ZWNJ inside a name",
      "path": "ab‌c",
      "result": "ok"
    },
    {
      "name": "the rainbow flag",
      "path": "🏳️‍🌈",
      "result": "ok"
    },
    {
      "name": "a family, joined with ZWJ",
      "path": "👨‍👩‍👧",
      "result": "ok"
    },
    {
      "name": "a leading slash",
      "path": "/a",
      "result": "R2: segment 1 is empty"
    },
    {
      "name": "two slashes",
      "path": "a//b",
      "result": "R2: segment 2 is empty"
    },
    {
      "name": "a trailing slash",
      "path": "a/",
      "result": "R2: segment 2 is empty"
    },
    {
      "name": "33 segments",
      "path": "a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a",
      "result": "R2: 33 segments, more than 32"
    },
    {
      "name": "a leading space",
      "path": " a",
      "result": "R5: segment 1: the segment starts with U+0020"
    },
    {
      "name": "a trailing space",
      "path": "a ",
      "result": "R5: segment 1: the segment ends with U+0020"
    },
    {
      "name": "a trailing dot",
      "path": "a.",
      "result": "R5: segment 1: the segment ends with '.'"
    },
    {
      "name": "CON.txt",
      "path": "CON.txt",
      "result": "R6: segment 1: CON is a reserved device name"
    },
    {
      "name": "con",
      "path": "con",
      "result": "R6: segment 1: CON is a reserved device name"
    },
    {
      "name": "Aux with a space before the dot",
      "path": "Aux .log",
      "result": "R6: segment 1: AUX is a reserved device name"
    },
    {
      "name": "COM with a superscript one",
      "path": "COM¹",
      "result": "R6: segment 1: COM¹ is a reserved device name"
    },
    {
      "name": "lpt9.doc",
      "path": "lpt9.doc",
      "result": "R6: segment 1: LPT9 is a reserved device name"
    },
    {
      "name": "CONIN$",
      "path": "CONIN$",
      "result": "R6: segment 1: CONIN$ is a reserved device name"
    },
    {
      "name": ".datekeys-x at the first level",
      "path": ".datekeys-x",
      "result": "R10: the first segment starts with \".datekeys-\""
    },
    {
      "name": ".DateKeys-X at the first level, compared by its key",
      "path": ".DateKeys-X/b",
      "result": "R10: the first segment starts with \".datekeys-\""
    },
    {
      "name": ".datekeys-x at another level",
      "path": "a/.datekeys-x",
      "result": "ok"
    }
  ],
  "trees": [
    {
      "name": "three files in two folders",
      "paths": [
        "a/b",
        "a/c",
        "d"
      ],
      "result": "ok"
    },
    {
      "name": "U+FF5E before U+1F600: UTF-8 byte order",
      "paths": [
        "～",
        "😀"
      ],
      "result": "ok"
    },
    {
      "name": "U+1F600 before U+FF5E: UTF-16 order, not UTF-8 byte order",
      "paths": [
        "😀",
        "～"
      ],
      "result": "ERR_NON_CANONICAL_CBOR"
    },
    {
      "name": "b and a, in that order",
      "paths": [
        "b",
        "a"
      ],
      "result": "ERR_NON_CANONICAL_CBOR"
    },
    {
      "name": "b/.. and a: R8 comes first, in layer 3",
      "paths": [
        "b/..",
        "a"
      ],
      "result": "ERR_NON_CANONICAL_CBOR"
    },
    {
      "name": "the same path twice",
      "paths": [
        "a",
        "a"
      ],
      "result": "ERR_NON_CANONICAL_CBOR"
    },
    {
      "name": "a path of 1025 bytes",
      "paths": [
        "a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a/a"
      ],
      "result": "ERR_NON_CANONICAL_CBOR"
    },
    {
      "name": ".. and a: R3, in layer 4",
      "paths": [
        "..",
        "a"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "file 1: R3: segment 1: the segment is two dots"
    },
    {
      "name": "A.txt and a.txt",
      "paths": [
        "A.txt",
        "a.txt"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "A and a/b",
      "paths": [
        "A",
        "a/b"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "a/b and a/b/c",
      "paths": [
        "a/b",
        "a/b/c"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 makes a file of path 1 a folder, or the reverse, in segment 2"
    },
    {
      "name": "Fotos/b and fotos/a",
      "paths": [
        "Fotos/b",
        "fotos/a"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "STRASSE and Straße",
      "paths": [
        "STRASSE",
        "Straße"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "k and the Kelvin sign",
      "paths": [
        "k",
        "K"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "ab with and without ZWNJ",
      "paths": [
        "ab",
        "a‌b"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    },
    {
      "name": "the NFD and the NFC of a name",
      "paths": [
        "é",
        "é"
      ],
      "result": "ERR_HEAD_INVALID",
      "detail": "R7: path 2 collides with path 1 in segment 1"
    }
  ]
}