Struct CharacterSplitter 

pub struct CharacterSplitter { /* private fields */ }

Single-separator character splitter.

Implementations

impl CharacterSplitter

pub fn new() -> Self

New splitter with default settings.

pub fn with_chunk_size(self, n: usize) -> Self

Set the maximum chunk size measured by length_fn (default: chars).

pub fn with_overlap(self, n: usize) -> Self

Set the overlap between adjacent chunks.

pub fn with_separator(self, s: impl Into<String>) -> Self

Set the separator string used to split text. Default: "\n\n".

pub fn with_keep_separator(self, keep: bool) -> Self

If true, the separator is prepended to subsequent chunks (preserving boundary context). Default: false.

pub fn with_length_fn<F>(self, f: F) -> Self

where F: Fn(&str) -> usize + Send + Sync + 'static,

Replace the length measure (default: chars).

Trait Implementations

impl Debug for CharacterSplitter

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

Formats the value using the given formatter.

impl Default for CharacterSplitter

fn default() -> Self

Returns the “default value” for a type.

impl TextSplitter for CharacterSplitter

fn split(&self, doc: &Document) -> Vec<Document>

Split doc into chunks.

fn split_all(&self, docs: &[Document]) -> Vec<Document>

Convenience: split many documents and concatenate the chunks.