113 lines
3.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ------------------------------------------------------------
# AAC Coder/Decoder - Huffman wrappers (Level 3)
#
# Multimedia course at Aristotle University of
# Thessaloniki (AUTh)
#
# Author:
# Christos Choutouridis (ΑΕΜ 8997)
# cchoutou@ece.auth.gr
#
# Description:
# Thin wrappers around the provided Huffman utilities (material/huff_utils.py)
# so that the API matches the assignment text.
#
# Exposed API (assignment):
# huff_sec, huff_codebook = aac_encode_huff(coeff_sec, huff_LUT_list, force_codebook)
# dec_coeffs = aac_decode_huff(huff_sec, huff_codebook, huff_LUT_list)
#
# Notes:
# - Huffman coding operates on tuples. Therefore, decode(encode(x)) may return
# extra trailing symbols due to tuple padding. The AAC decoder knows the
# true section length from side information (band limits) and truncates.
# ------------------------------------------------------------
from __future__ import annotations
from typing import Any
import numpy as np
from material.huff_utils import encode_huff, decode_huff
def aac_encode_huff(
coeff_sec: np.ndarray,
huff_LUT_list: list[dict[str, Any]],
force_codebook: int | None = None,
) -> tuple[str, int]:
"""
Huffman-encode a section of coefficients (MDCT symbols or scalefactors).
Parameters
----------
coeff_sec : np.ndarray
Coefficient section to be encoded. Any shape is accepted; the input
is flattened and treated as a 1-D sequence of int64 symbols.
huff_LUT_list : list[dict[str, Any]]
List of Huffman Look-Up Tables (LUTs) as returned by material.load_LUT().
Index corresponds to codebook id (typically 1..11, with 0 reserved).
force_codebook : int | None
If provided, forces the use of this Huffman codebook. In the assignment,
scalefactors are encoded with codebook 11. For MDCT coefficients, this
argument is usually omitted (auto-selection).
Returns
-------
tuple[str, int]
(huff_sec, huff_codebook)
- huff_sec: bitstream as a string of '0'/'1'
- huff_codebook: codebook id used by the encoder
"""
coeff_sec_arr = np.asarray(coeff_sec, dtype=np.int64).reshape(-1)
if force_codebook is None:
# Provided utility returns (bitstream, codebook) in the auto-selection case.
huff_sec, huff_codebook = encode_huff(coeff_sec_arr, huff_LUT_list)
return str(huff_sec), int(huff_codebook)
# Provided utility returns ONLY the bitstream when force_codebook is set.
cb = int(force_codebook)
huff_sec = encode_huff(coeff_sec_arr, huff_LUT_list, force_codebook=cb)
return str(huff_sec), cb
def aac_decode_huff(
huff_sec: str | np.ndarray,
huff_codebook: int,
huff_LUT: list[dict[str, Any]],
) -> np.ndarray:
"""
Huffman-decode a bitstream using the specified codebook.
Parameters
----------
huff_sec : str | np.ndarray
Huffman bitstream. Typically a string of '0'/'1'. If an array is provided,
it is passed through to the provided decoder.
huff_codebook : int
Codebook id that was returned by aac_encode_huff.
Codebook 0 represents an all-zero section.
huff_LUT : list[dict[str, Any]]
Huffman LUT list as returned by material.load_LUT().
Returns
-------
np.ndarray
Decoded coefficients as a 1-D np.int64 array.
Note: Due to tuple coding, the decoded array may contain extra trailing
padding symbols. The caller must truncate to the known section length.
"""
cb = int(huff_codebook)
if cb == 0:
# Codebook 0 represents an all-zero section. The decoded length is not
# recoverable from the bitstream alone; the caller must expand/truncate.
return np.zeros((0,), dtype=np.int64)
if cb < 0 or cb >= len(huff_LUT):
raise ValueError(f"Invalid Huffman codebook index: {cb}")
lut = huff_LUT[cb]
dec = decode_huff(huff_sec, lut)
return np.asarray(dec, dtype=np.int64).reshape(-1)