# Copyright 2026 Toyota Research Institute.  All rights reserved.

import os
import json
import numpy as np

from glob import glob

from anydata.utils.read import read_numpy, read_yaml, read_image
from anydata.utils.write import write_json, write_lowdim, write_labels
from anydata.converters.utils import run, add_key_to_dict, fill_metadata, parse_dst_seq, frame_name, crawl, prepare_lowdim

#######################################################

def get_rgb(filename):
    return np.array(read_image(filename))


def get_depth(filename):
    return np.load(filename).squeeze()


def get_mask_depth(filename):
    mask = np.load(filename)
    return np.clip(mask, 0.0, 1.0).astype(bool)

#######################################################

def get_sequences(args):
    seqs = crawl(args.src, 'scan_*')
    return seqs


def parse_sequence(seq, args):
    return parse_dst_seq(seq, args)

#######################################################

def process_sequence(i, seq, dst, args):

    ### Initialize lists and dicts
    cameras = ['0']
    num_frames = {cam: dict() for cam in cameras}
    resolution = {cam: dict() for cam in cameras}
    labels, lowdim = [], {}
    dense_labels = ['rgb','depth','mask_depth']

    intrinsics = np.array([
        [886.81 , 0.    , 512],
        [0.    , 927.06 , 384],
        [0.    , 0.     , 1. ],
    ])

    ############ LOOP OVER CAMERAS
    for c, cam in enumerate(cameras):
        dense = {key: dict() for key in dense_labels}

        ### Get filenames
        filename_rgbs = sorted(glob(f'{seq}/*.png'))
        filename_depths = sorted(glob(f'{seq}/*depth.npy'))
        filename_masks = sorted(glob(f'{seq}/*depth_mask.npy'))

        ######## RGB FILENAMES
        for i, filename_rgb in enumerate(filename_rgbs):
            frame = frame_name(i)

            ######## RGB
            rgb = get_rgb(filename_rgb)
            dense['rgb'][frame] = rgb

            ######## LOWDIM RGB
            prepare_lowdim(lowdim, dst, cam, frame)

            filename_lowdim = add_key_to_dict(lowdim, f'{dst}/lowdim/{cam}/{frame}.npz')
            lowdim[filename_lowdim]['intrinsics'] = intrinsics

        ######## DEPTH FILENAMES
        for i, filename_depth in enumerate(filename_depths):
            frame = frame_name(i)

            ### DEPTH
            depth = get_depth(filename_depth)
            dense['depth'][frame] = depth

        ######## MASK DEPTH FILENAMES
        for i, filename_mask in enumerate(filename_masks):
            frame = frame_name(i)

            ######## MASK DEPTH
            mask_depth = get_mask_depth(filename_mask)
            dense['mask_depth'][frame] = mask_depth

        ######## WRITE LABELS
        write_labels(dst, cam, args.storage, dense, labels, resolution, num_frames)

    ######## WRITE LOWDIM
    write_lowdim(args, dst, labels, num_frames, lowdim)

############ METADATA 
    filename = f'{dst}/metadata.json'
    seq_metadata = fill_metadata(
        args=args,
        info=dict(
            name='DIODE',
            tags=['real','static','image'],
            raw_id=seq.replace(f'{args.src}/', ''),
        ),
        labels=labels,
        cameras=cameras,
        resolution=resolution,
        num_frames=num_frames,
        framerate=0,
        rgb=dict(extension='jpg'),
        intrinsics=dict(model='pinhole'),
        extrinsics=None,
        depth=dict(extension='npz',metric=True,sparse=True),
        semantic=None, 
        action=None,
        language=None,
        specific=None,
    )
    write_json(filename, seq_metadata)

    return dst

#######################################################

if __name__ == '__main__':
    converter = os.path.basename(__file__)
    run(converter, get_sequences, parse_sequence, process_sequence)

#######################################################