Struct Utf8Encoding 

pub struct Utf8Encoding;

The UTF-8 encoding type behind ONIG_ENCODING_UTF8.

Trait Implementations

impl Encoding for Utf8Encoding

fn mbc_enc_len(&self, p: &[u8]) -> usize

Returns the byte length of the multibyte character at position p.

fn name(&self) -> &str

Encoding name (e.g. “US-ASCII”, “UTF-8”)

fn max_enc_len(&self) -> usize

Maximum encoded character length in bytes

fn min_enc_len(&self) -> usize

Minimum encoded character length in bytes

fn is_mbc_newline(&self, p: &[u8], end: usize) -> bool

Is the byte at p a newline character?

fn mbc_to_code(&self, p: &[u8], end: usize) -> OnigCodePoint

Decode a multibyte character to a code point

fn code_to_mbclen(&self, code: OnigCodePoint) -> i32

Returns the byte length needed to encode a code point

fn code_to_mbc(&self, code: OnigCodePoint, buf: &mut [u8]) -> i32

Encode a code point into buf, returns number of bytes written

fn mbc_case_fold( &self, flag: OnigCaseFoldType, pp: &mut usize, end: usize, source: &[u8], fold_buf: &mut [u8], ) -> i32

Case fold the character at pp, advance pp, write folded to fold_buf. Returns the number of bytes written to fold_buf.

fn apply_all_case_fold( &self, flag: OnigCaseFoldType, f: &mut dyn FnMut(OnigCodePoint, &[OnigCodePoint]) -> i32, ) -> i32

Apply function f to all case fold pairs.

fn get_case_fold_codes_by_str( &self, flag: OnigCaseFoldType, p: &[u8], end: usize, items: &mut [OnigCaseFoldCodeItem], ) -> i32

Get case fold code alternatives for the character at p.

fn property_name_to_ctype(&self, p: &[u8]) -> i32

Convert property name to ctype value.

fn is_code_ctype(&self, code: OnigCodePoint, ctype: u32) -> bool

Is the code point of the given ctype?

fn get_ctype_code_range( &self, ctype: u32, sb_out: &mut OnigCodePoint, ) -> Option<&'static [OnigCodePoint]>

Get the code range for a ctype.

fn left_adjust_char_head(&self, start: usize, s: usize, data: &[u8]) -> usize

Left adjust char head: find the start of the character containing s within [start..].

fn is_allowed_reverse_match(&self, _p: &[u8]) -> bool

Is reverse matching allowed at this position?

fn is_valid_mbc_string(&self, s: &[u8]) -> bool

Validate that the byte string is valid for this encoding

fn flag(&self) -> u32

Encoding flags

fn sb_range(&self) -> OnigCodePoint

Single-byte range boundary

fn index(&self) -> i32

Encoding index

fn init(&self) -> i32

Initialize encoding (for callout registration etc.)

fn is_initialized(&self) -> bool

Is this encoding initialized?