Struct TextSpan 

pub struct TextSpan {
    pub byte_start: usize,
    pub byte_end: usize,
    pub char_start: usize,
    pub char_end: usize,
}

A text span with both byte and character offsets.

This is the canonical representation for entity positions. Store both to avoid repeated conversion.

Fields

byte_start: usize

Byte offset (start, inclusive)

byte_end: usize

Byte offset (end, exclusive)

char_start: usize

Character offset (start, inclusive)

char_end: usize

Character offset (end, exclusive)

Implementations

impl TextSpan

pub fn from_bytes(text: &str, byte_start: usize, byte_end: usize) -> Self

Create a span from byte offsets, computing char offsets from text.

Arguments

• text - The full text (needed to compute char offsets)
• byte_start - Byte offset start (inclusive)
• byte_end - Byte offset end (exclusive)

Example

use anno::offset::TextSpan;

let text = "Price €50";
// "Price " = 6 bytes, € = 3 bytes, "50" = 2 bytes = 11 total
let span = TextSpan::from_bytes(text, 6, 11); // "€50"
assert_eq!(span.char_start, 6);
assert_eq!(span.char_end, 9); // € is 1 char but 3 bytes

pub fn from_chars(text: &str, char_start: usize, char_end: usize) -> Self

Create a span from character offsets, computing byte offsets from text.

Arguments

• text - The full text (needed to compute byte offsets)
• char_start - Character offset start (inclusive)
• char_end - Character offset end (exclusive)

pub const fn ascii(start: usize, end: usize) -> Self

Create a span for ASCII text where byte == char offsets.

This is a fast path for ASCII-only text.

pub const fn byte_range(&self) -> Range<usize>

Get byte range.

pub const fn char_range(&self) -> Range<usize>

Get character range.

pub const fn byte_len(&self) -> usize

Byte length.

pub const fn char_len(&self) -> usize

Character length.

pub const fn is_empty(&self) -> bool

Check if this span is empty.

pub const fn is_ascii(&self) -> bool

Check if this is ASCII (byte == char offsets).

pub fn extract<'a>(&self, text: &'a str) -> &'a str

Extract the text for this span.

Trait Implementations

impl Clone for TextSpan

fn clone(&self) -> TextSpan

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TextSpan

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TextSpan

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<Range<usize>> for TextSpan

fn from(range: Range<usize>) -> Self

Create from byte range (assumes ASCII).

impl Hash for TextSpan

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for TextSpan

fn eq(&self, other: &TextSpan) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for TextSpan

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for TextSpan

impl Eq for TextSpan

impl StructuralPartialEq for TextSpan