Struct ChunkMetadata 

pub struct ChunkMetadata {
    pub source: Option<String>,
    pub content_type: Option<String>,
    pub chunk_size: usize,
    pub overlap: usize,
    pub preserve_lines: bool,
    pub preserve_sentences: bool,
    pub max_chunks: usize,
}

Metadata provided to chunkers for context-aware processing.

This allows callers to customize chunking behavior without modifying the chunker itself.

Fields

source: Option<String>

Source file path (for content-type detection).

content_type: Option<String>

File MIME type or extension (e.g., “md”, “json”, “py”).

chunk_size: usize

Target chunk size in characters.

overlap: usize

Overlap between consecutive chunks.

preserve_lines: bool

Whether to preserve line boundaries.

preserve_sentences: bool

Whether to preserve sentence boundaries.

max_chunks: usize

Maximum chunks to produce (0 = unlimited).

Implementations

impl ChunkMetadata

pub fn new() -> Self

Creates new metadata with default chunk size.

pub fn with_size(chunk_size: usize) -> Self

Creates metadata with custom chunk size and no overlap.

pub fn with_size_and_overlap(chunk_size: usize, overlap: usize) -> Self

Creates metadata with custom size and overlap.

pub fn source(self, source: &str) -> Self

Sets the source path.

pub fn content_type(self, content_type: &str) -> Self

Sets the content type.

pub const fn preserve_lines(self, preserve: bool) -> Self

Sets whether to preserve line boundaries.

pub const fn preserve_sentences(self, preserve: bool) -> Self

Sets whether to preserve sentence boundaries.

pub const fn max_chunks(self, max: usize) -> Self

Sets maximum chunks.

Trait Implementations

impl Clone for ChunkMetadata

fn clone(&self) -> ChunkMetadata

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChunkMetadata

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

Formats the value using the given formatter.

impl Default for ChunkMetadata

fn default() -> ChunkMetadata

Returns the “default value” for a type.