Struct HtmlSplitter 

pub struct HtmlSplitter { /* private fields */ }

HTML-aware splitter. Splits at heading boundaries; metadata records the active heading at each level.

Extension path: implement crate::splitters::TextSplitter directly when the heading-based scheme doesn’t fit. The HtmlSplitter::with_levels / HtmlSplitter::with_strip_tags / HtmlSplitter::with_min_chunk_size knobs cover the common configuration axes for the built-in heuristic.

Implementations

impl HtmlSplitter

pub fn new() -> Self

New splitter with default settings (split on every heading level).

pub fn with_levels<I: IntoIterator<Item = u8>>(self, levels: I) -> Self

Restrict to specific heading levels (e.g. [1, 2] for top-two).

pub fn with_strip_tags(self, strip: bool) -> Self

Whether to strip remaining HTML tags from chunk text. Default true.

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

Coalesce trailing chunks smaller than n chars into the previous one.

Trait Implementations

impl Clone for HtmlSplitter

fn clone(&self) -> HtmlSplitter

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HtmlSplitter

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

Formats the value using the given formatter.

impl Default for HtmlSplitter

fn default() -> Self

Returns the “default value” for a type.

impl TextSplitter for HtmlSplitter

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.