Struct MarkdownStructureSplitter 

pub struct MarkdownStructureSplitter { /* private fields */ }

Heading-aware markdown splitter.

Construct via Self::new for the default [1, 2, 3] configuration, or Self::with_heading_levels to widen / narrow the split granularity.

Implementations

impl MarkdownStructureSplitter

pub fn new() -> Self

Build with the default [1, 2, 3] heading-levels configuration.

pub fn with_heading_levels<I>(self, levels: I) -> Self

where I: IntoIterator<Item = u8>,

Override which ATX heading levels open a new chunk. Levels outside 1..=6 are silently ignored at split time. Order is irrelevant — duplicates are tolerated.

pub fn heading_levels(&self) -> &[u8]

Borrow the configured heading levels.

Trait Implementations

impl Clone for MarkdownStructureSplitter

fn clone(&self) -> MarkdownStructureSplitter

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MarkdownStructureSplitter

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

Formats the value using the given formatter.

impl Default for MarkdownStructureSplitter

fn default() -> Self

Returns the “default value” for a type.

impl TextSplitter for MarkdownStructureSplitter

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).