Struct Chunk 

pub struct Chunk<'a> { /* private fields */ }

A chunk of text with positional metadata.

Chunks are produced by Chunker and contain borrowed text along with metadata useful for tracking position within the original document.

Example

use pdfvec::{Chunker, ChunkStrategy};

let text = "First paragraph.\n\nSecond paragraph.";
let chunker = Chunker::new(ChunkStrategy::Paragraph);

for chunk in chunker.chunks(text) {
    println!("Chunk {}: {} chars at offset {}",
        chunk.index(),
        chunk.char_count(),
        chunk.byte_offset());
}

Implementations

impl<'a> Chunk<'a>

pub fn new(text: &'a str, index: usize, byte_offset: usize) -> Self

Creates a new chunk with the given metadata.

pub fn text(&self) -> &'a str

Returns the text content of this chunk.

Example

use pdfvec::{Chunker, ChunkStrategy};

let text = "Hello world";
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Fixed)
    .chunk_size(5)
    .chunks(text)
    .collect();

assert_eq!(chunks[0].text(), "Hello");

pub fn index(&self) -> usize

Returns the zero-based index of this chunk.

Example

use pdfvec::{Chunker, ChunkStrategy};

let text = "abcdefghij";
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Fixed)
    .chunk_size(5)
    .chunks(text)
    .collect();

assert_eq!(chunks[0].index(), 0);
assert_eq!(chunks[1].index(), 1);

pub fn byte_offset(&self) -> usize

Returns the byte offset of this chunk within the original text.

Example

use pdfvec::{Chunker, ChunkStrategy};

let text = "abcdefghij";
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Fixed)
    .chunk_size(5)
    .chunks(text)
    .collect();

assert_eq!(chunks[0].byte_offset(), 0);
assert_eq!(chunks[1].byte_offset(), 5);

pub fn char_count(&self) -> usize

Returns the number of characters in this chunk.

Example

use pdfvec::{Chunker, ChunkStrategy};

let text = "Hello";
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Fixed)
    .chunk_size(100)
    .chunks(text)
    .collect();

assert_eq!(chunks[0].char_count(), 5);

pub fn byte_len(&self) -> usize

Returns the byte length of this chunk.

Trait Implementations

impl<'a> Clone for Chunk<'a>

fn clone(&self) -> Chunk<'a>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<'a> Debug for Chunk<'a>

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

Formats the value using the given formatter.

impl<'a> PartialEq for Chunk<'a>

fn eq(&self, other: &Chunk<'a>) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<'a> Eq for Chunk<'a>

impl<'a> StructuralPartialEq for Chunk<'a>