# Copyright 2026 Toyota Research Institute.  All rights reserved.


import os
import numpy as np

from glob import glob

from anydata.utils.read import 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
from anydata.utils.geometry import invert_extrinsics

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

def get_sequences(args):
    seqs = crawl(f'{args.src}/geometry', '*.txt')
    return seqs


def parse_sequence(seq, args):
    return parse_dst_seq(seq, args, remove=[0], remext=True)

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

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']

    ### Get filenames
    filename_rgbs = f'{seq.replace("/geometry/", "/")}'[:-4]
    filename_rgbs = sorted(glob(f'{filename_rgbs}/*.png'))

    ### Get geometry data
    with open(seq, 'r') as f:
        geometry = f.readlines()

    ############ LOOP OVER CAMERAS
    for cam in cameras:
        dense = {label: dict() for label in dense_labels}

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

            ######## RGB
            rgb = np.array(read_image(filename_rgb))
            dense['rgb'][frame] = rgb

            line = [float(v) for v in geometry[i+1].split(' ')]
            K, T = line[1:7], line[7:]
            wh = rgb.shape[:2][::-1]

            intrinsics = np.array([
                [K[0] * wh[0], 0.0, K[2] * wh[0]],
                [0.0, K[1] * wh[1], K[3] * wh[1]],
                [0.0, 0.0, 1.0]
            ])

            extrinsics = np.array(T).reshape(3, 4)
            extrinsics = np.vstack([extrinsics, [0.0, 0.0, 0.0, 1.0]])

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

            ######## INTRINSICS + EXTRINSICS
            filename_lowdim = add_key_to_dict(lowdim, f'{dst}/lowdim/{cam}/{frame}.npz')
            lowdim[filename_lowdim]['extrinsics'] = invert_extrinsics(extrinsics)
            lowdim[filename_lowdim]['intrinsics'] = intrinsics

        ######## 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='RealEstate10K',
            tags=['real','static'],
            raw_id=seq.replace(f'{args.src}/', ''),
        ),
        labels=labels,
        cameras=cameras,
        resolution=resolution,
        num_frames=num_frames,
        framerate=10,
        rgb=dict(extension='jpg'),
        intrinsics=dict(model='pinhole'),
        extrinsics=dict(transform='cam2world',metric=False),
        depth=None,
        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)

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