Struct RecursiveCharacterSplitter 

pub struct RecursiveCharacterSplitter { /* private fields */ }

Recursive character-budget splitter.

Construct via Self::new for the default 1000-char / 100-char shape, or Self::with_chunk_size / Self::with_chunk_overlap / Self::with_separators for tuning. Cloning is cheap — the separator list is held by Arc so multiple pipelines can share one configured splitter.

Implementations

impl RecursiveCharacterSplitter

pub fn new() -> Self

Build with the default chunk size + overlap + separator priority. The 99% case for English / Latin-script corpora.

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

Override the target chunk size in characters. Chunks larger than this are recursed; chunks smaller are accumulated greedily.

pub const fn with_chunk_overlap(self, chunk_overlap: usize) -> Self

Override the overlap (in characters) between consecutive chunks. Must be strictly less than Self::chunk_size — equal-or-greater overlap would loop indefinitely. Values at or above the chunk size silently clamp to chunk_size - 1 at split time.

pub fn with_separators<I, S>(self, separators: I) -> Self

where I: IntoIterator<Item = S>, S: Into<String>,

Override the separator priority list. Pipelines splitting LaTeX, Python source, or other domain-specific corpora ship alternative priority lists that bias toward language-meaningful boundaries.

pub const fn chunk_size(&self) -> usize

Effective chunk size in characters.

pub const fn chunk_overlap(&self) -> usize

Effective chunk overlap in characters.

Trait Implementations

impl Clone for RecursiveCharacterSplitter

fn clone(&self) -> RecursiveCharacterSplitter

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RecursiveCharacterSplitter

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

Formats the value using the given formatter.

impl Default for RecursiveCharacterSplitter

fn default() -> Self

Returns the “default value” for a type.

impl TextSplitter for RecursiveCharacterSplitter

fn name(&self) -> &'static str

Stable splitter identifier — surfaces on every produced chunk’s Lineage::splitter field. "recursive-character", "markdown-structure", "token-count", etc.

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

Slice document and return the resulting chunks. Returning a single-element vec equal to the input is a valid no-op (e.g. when the document already fits the target size); an empty vec is also valid (e.g. content is whitespace-only).