Struct HuffmanEncoder 

pub struct HuffmanEncoder { /* private fields */ }

Huffman encoder for lossless compression

Builds an optimal prefix-free code based on symbol frequencies, assigning shorter codes to more frequent symbols.

Implementations

impl HuffmanEncoder

pub fn from_frequencies( frequencies: &HashMap<u32, u64>, ) -> TokenizerResult<Self>

Build a Huffman encoder from symbol frequencies

Arguments

• frequencies - Map from symbol to frequency count

Returns

A Huffman encoder with optimal prefix-free codes

Example

let mut freqs = HashMap::new();
freqs.insert(0, 10);  // Symbol 0 appears 10 times
freqs.insert(1, 5);   // Symbol 1 appears 5 times
freqs.insert(2, 2);   // Symbol 2 appears 2 times

let encoder = HuffmanEncoder::from_frequencies(&freqs);

pub fn encode(&self, symbols: &[u32]) -> TokenizerResult<Vec<u8>>

Encode a sequence of symbols using Huffman coding

Arguments

• symbols - Sequence of symbols to encode

Returns

Compressed bitstream as a Vec, with length information prepended

pub fn codebook(&self) -> &HashMap<u32, Vec<bool>>

Get the codebook (for decoder)

pub fn tree(&self) -> (&[HuffmanNode], usize)

Get the Huffman tree (for decoder)

pub fn average_code_length(&self, frequencies: &HashMap<u32, u64>) -> f64

Compute average code length

pub fn entropy(frequencies: &HashMap<u32, u64>) -> f64

Compute entropy of the distribution