package core:unicode/utf8

⌘K
Ctrl+K
or
/

    Types

    Accept_Range ¶

    Accept_Range :: struct {
    	lo: u8,
    	hi: u8,
    }

    Constants

    HICB ¶

    HICB :: 0b1011_1111

    LOCB ¶

    LOCB :: 0b1000_0000
     

    The default lowest and highest continuation byte.

    MASK2 ¶

    MASK2 :: 0b0001_1111

    MASK3 ¶

    MASK3 :: 0b0000_1111

    MASK4 ¶

    MASK4 :: 0b0000_0111

    MASKX ¶

    MASKX :: 0b0011_1111

    MAX_RUNE ¶

    MAX_RUNE :: '\U0010ffff'

    RUNE1_MAX ¶

    RUNE1_MAX :: 1 << 7 - 1

    RUNE2_MAX ¶

    RUNE2_MAX :: 1 << 11 - 1

    RUNE3_MAX ¶

    RUNE3_MAX :: 1 << 16 - 1

    RUNE_BOM ¶

    RUNE_BOM :: 0xfeff

    RUNE_EOF ¶

    RUNE_EOF: rune : ~rune(0)

    RUNE_ERROR ¶

    RUNE_ERROR :: '\ufffd'

    RUNE_SELF ¶

    RUNE_SELF :: 0x80

    SURROGATE_HIGH_MAX ¶

    SURROGATE_HIGH_MAX :: 0xdbff
     

    A high/leading surrogate is in range SURROGATE_MIN..SURROGATE_HIGH_MAX, A low/trailing surrogate is in range SURROGATE_LOW_MIN..SURROGATE_MAX.

    SURROGATE_LOW_MIN ¶

    SURROGATE_LOW_MIN :: 0xdc00

    SURROGATE_MAX ¶

    SURROGATE_MAX :: 0xdfff

    SURROGATE_MIN ¶

    SURROGATE_MIN :: 0xd800

    T1 ¶

    T1 :: 0b0000_0000

    T2 ¶

    T2 :: 0b1100_0000

    T3 ¶

    T3 :: 0b1110_0000

    T4 ¶

    T4 :: 0b1111_0000

    T5 ¶

    T5 :: 0b1111_1000

    TX ¶

    TX :: 0b1000_0000

    UTF_MAX ¶

    UTF_MAX :: 4

    Variables

    accept_ranges ¶

    accept_ranges: [5]Accept_Range = …

    accept_sizes ¶

    accept_sizes: [256]u8 = …

    Procedures

    decode_last_rune_in_bytes ¶

    decode_last_rune_in_bytes :: proc "contextless" (s: []u8) -> (rune, int) {…}

    decode_last_rune_in_string ¶

    decode_last_rune_in_string :: proc "contextless" (s: string) -> (rune, int) {…}

    decode_rune_in_bytes ¶

    decode_rune_in_bytes :: proc "contextless" (s: []u8) -> (rune, int) {…}

    decode_rune_in_string ¶

    decode_rune_in_string :: proc "contextless" (s: string) -> (rune, int) {…}

    encode_rune ¶

    encode_rune :: proc "contextless" (c: rune) -> ([4]u8, int) {…}

    full_rune_in_bytes ¶

    full_rune_in_bytes :: proc "contextless" (b: []u8) -> bool {…}
     

    full_rune_in_bytes reports if the bytes in b begin with a full utf-8 encoding of a rune or not An invalid encoding is considered a full rune since it will convert as an error rune of width 1 (RUNE_ERROR)

    full_rune_in_string ¶

    full_rune_in_string :: proc "contextless" (s: string) -> bool {…}
     

    full_rune_in_string reports if the bytes in s begin with a full utf-8 encoding of a rune or not An invalid encoding is considered a full rune since it will convert as an error rune of width 1 (RUNE_ERROR)

    rune_at ¶

    rune_at :: proc "contextless" (s: string, byte_index: int) -> rune {…}

    rune_at_pos ¶

    rune_at_pos :: proc "contextless" (s: string, pos: int) -> rune {…}

    rune_count_in_bytes ¶

    rune_count_in_bytes :: proc "contextless" (s: []u8) -> int {…}

    rune_count_in_string ¶

    rune_count_in_string :: proc(s: string) -> int {…}

    rune_offset ¶

    rune_offset :: proc "contextless" (s: string, pos: int, start: int = 0) -> int {…}
     

    Returns the byte position of rune at position pos in s with an optional start byte position. Returns -1 if it runs out of the string.

    rune_size ¶

    rune_size :: proc "contextless" (r: rune) -> int {…}

    rune_start ¶

    rune_start :: proc "contextless" (b: u8) -> bool {…}

    rune_string_at_pos ¶

    rune_string_at_pos :: proc "contextless" (s: string, pos: int) -> string {…}

    runes_to_string ¶

    runes_to_string :: proc(runes: []rune, allocator := context.allocator) -> string {…}

    string_to_runes ¶

    string_to_runes :: proc(s: string, allocator := context.allocator) -> (runes: []rune) {…}

    valid_rune ¶

    valid_rune :: proc "contextless" (r: rune) -> bool {…}

    valid_string ¶

    valid_string :: proc "contextless" (s: string) -> bool {…}

    Procedure Groups

    full_rune ¶

    full_rune :: proc{
    	full_rune_in_bytes,
    	full_rune_in_string,
    }
    
     

    full_rune reports if the bytes in b begin with a full utf-8 encoding of a rune or not An invalid encoding is considered a full rune since it will convert as an error rune of width 1 (RUNE_ERROR)

    Source Files

    Generation Information

    Generated with odin version dev-2024-04 (vendor "odin") Windows_amd64 @ 2024-04-25 21:10:22.409535600 +0000 UTC