▽

Package utf8internal

Constants

The default lowest and highest continuation byte.

const (
    LoCB = 0x80 // 1000 0000
    HiCB = 0xBF // 1011 1111
)

Constants related to getting information of first bytes of UTF-8 sequences.

const (
    // ASCII identifies a UTF-8 byte as ASCII.
    ASCII = as

    // FirstInvalid indicates a byte is invalid as a first byte of a UTF-8
    // sequence.
    FirstInvalid = xx

    // SizeMask is a mask for the size bits. Use use x&SizeMask to get the size.
    SizeMask = 7

    // AcceptShift is the right-shift count for the first byte info byte to get
    // the index into the AcceptRanges table. See AcceptRanges.
    AcceptShift = 4
)

Variables

AcceptRanges is a slice of AcceptRange values. For a given byte sequence b

AcceptRanges[First[b[0]]>>AcceptShift]

will give the value of AcceptRange for the multi-byte UTF-8 sequence starting at b[0].

var AcceptRanges = [...]AcceptRange{
    0: {LoCB, HiCB},
    1: {0xA0, HiCB},
    2: {LoCB, 0x9F},
    3: {0x90, HiCB},
    4: {LoCB, 0x8F},
}

First is information about the first byte in a UTF-8 sequence.

var First = [256]uint8{

    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,
    as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as,

    xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx,
    xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx,
    xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx,
    xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx,
    xx, xx, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1,
    s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1,
    s2, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s4, s3, s3,
    s5, s6, s6, s6, s7, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx,
}

type AcceptRange ¶

AcceptRange gives the range of valid values for the second byte in a UTF-8 sequence for any value for First that is not ASCII or FirstInvalid.

type AcceptRange struct {
    Lo uint8 // lowest value for second byte.
    Hi uint8 // highest value for second byte.
}