import numpy as np
import os
from torch.utils.data import Dataset
import torch
from pointnet_util import farthest_point_sample, pc_normalize
import json


class ModelNetDataLoader(Dataset):
    """ModelNet40

    Args:
        12311 pointclouds
        40:
            9843 train
            2468 test
        10:
            3991 train
            908 test
    """
    def __init__(self, root, npoint=1024, split='train', uniform=False, 
            normal_channel=True, cache_size=15000, classes=10):
        self.root    = root
        self.npoints = npoint
        self.uniform = uniform
        self.cache_n = cache_size  # how many data points to cache in memory
        self.cache   = {}  # from index to (point_set, cls) tuple
        self.catfile = os.path.join(self.root, 'modelnet' + str(classes) + '_shape_names.txt')

        self.cat = [line.rstrip() for line in open(self.catfile)]
        self.classes = dict(zip(self.cat, range(len(self.cat))))
        self.normal_channel = normal_channel

        shape_ids = {}
        shape_ids['train'] = [line.rstrip() for line in open(
            os.path.join(self.root, 'modelnet' + str(classes) +'_train.txt'))]
        shape_ids['test'] = [line.rstrip() for line in open(
            os.path.join(self.root, 'modelnet' + str(classes) +'_test.txt'))]

        assert (split == 'train' or split == 'test')
        shape_names = ['_'.join(x.split('_')[0:-1]) for x in shape_ids[split]]
        # list of (shape_name, shape_txt_file_path) tuple
        self.datapath = [(shape_names[i], os.path.join(self.root, shape_names[i], shape_ids[split][i]) + '.txt') for i
                         in range(len(shape_ids[split]))]
        print('The size of %s data is %d'%(split,len(self.datapath)))

    def __len__(self):
        return len(self.datapath)
    
    def fps(self, xyz, npoint):
        """farthest_point_sample
        Input:
            xyz: pointcloud data, [N, 3]
            npoint: number of samples
        Return:
            centroids: sampled pointcloud index, [npoint]
        """
        N, C = xyz.shape
        centroids = torch.zeros(npoint, dtype=torch.long)
        distance = torch.ones(N) * 1e10
        farthest = torch.randint(0, N, (1,), dtype=torch.long)
        for i in range(npoint):
            centroids[i] = farthest
            centroid = xyz[farthest, :3].view(1, 3)
            dist = torch.sum((xyz[:,:3] - centroid) ** 2, -1) # TODO: jia
            distance = torch.min(distance, dist)
            farthest = torch.max(distance, -1)[1]
        return centroids
        
    def __getitem__(self, index):
        if index in self.cache:
            point_set, label = self.cache[index]
        else:
            fn = self.datapath[index]
            label = self.classes[self.datapath[index][0]]
            label = np.array([label]).astype(np.int32)
            point_set = np.loadtxt(fn[1], delimiter=',').astype(np.float32)
            if self.uniform:
                point_set = torch.Tensor(point_set)
                point_idx = self.fps(point_set, self.npoints)
                point_set = point_set[point_idx,:]
                point_set = point_set.data.numpy()
            else:
                point_set = point_set[0:self.npoints, :]
                # choice = np.random.choice(len(label), self.npoints, replace=True)
                # point_set = point_set[choice, :]
                # label = label[choice]
      
            point_set[:, 0:3] = pc_normalize(point_set[:, 0:3])
            if not self.normal_channel:
                point_set = point_set[:, 0:3]
            if len(self.cache) < self.cache_n:
                self.cache[index] = (point_set, label)
        return point_set, label


class PartNormalDataset(Dataset):
    def __init__(self, root='./data/shapenetcore_partanno_segmentation_benchmark_v0_normal', npoints=1024, split='train', class_choice=None, normal_channel=False):
        self.npoints = npoints
        self.root = root
        self.catfile = os.path.join(self.root, 'synsetoffset2category.txt')
        self.cat = {}
        self.normal_channel = normal_channel


        with open(self.catfile, 'r') as f:
            for line in f:
                ls = line.strip().split()
                self.cat[ls[0]] = ls[1]
        self.cat = {k: v for k, v in self.cat.items()}
        self.classes_original = dict(zip(self.cat, range(len(self.cat))))

        if not class_choice is  None:
            self.cat = {k:v for k,v in self.cat.items() if k in class_choice}
        # print(self.cat)

        self.meta = {}
        with open(os.path.join(self.root, 'train_test_split', 'shuffled_train_file_list.json'), 'r') as f:
            train_ids = set([str(d.split('/')[2]) for d in json.load(f)])
        with open(os.path.join(self.root, 'train_test_split', 'shuffled_val_file_list.json'), 'r') as f:
            val_ids = set([str(d.split('/')[2]) for d in json.load(f)])
        with open(os.path.join(self.root, 'train_test_split', 'shuffled_test_file_list.json'), 'r') as f:
            test_ids = set([str(d.split('/')[2]) for d in json.load(f)])
        for item in self.cat:
            # print('category', item)
            self.meta[item] = []
            dir_point = os.path.join(self.root, self.cat[item])
            fns = sorted(os.listdir(dir_point))
            # print(fns[0][0:-4])
            if split == 'trainval':
                fns = [fn for fn in fns if ((fn[0:-4] in train_ids) or (fn[0:-4] in val_ids))]
            elif split == 'train':
                fns = [fn for fn in fns if fn[0:-4] in train_ids]
            elif split == 'val':
                fns = [fn for fn in fns if fn[0:-4] in val_ids]
            elif split == 'test':
                fns = [fn for fn in fns if fn[0:-4] in test_ids]
            else:
                print('Unknown split: %s. Exiting..' % (split))
                exit(-1)

            # print(os.path.basename(fns))
            for fn in fns:
                token = (os.path.splitext(os.path.basename(fn))[0])
                self.meta[item].append(os.path.join(dir_point, token + '.txt'))

        self.datapath = []
        for item in self.cat:
            for fn in self.meta[item]:
                self.datapath.append((item, fn))

        self.classes = {}
        for i in self.cat.keys():
            self.classes[i] = self.classes_original[i]

        # Mapping from category ('Chair') to a list of int [10,11,12,13] as segmentation labels
        self.seg_classes = {'Earphone': [16, 17, 18], 'Motorbike': [30, 31, 32, 33, 34, 35], 'Rocket': [41, 42, 43],
                            'Car': [8, 9, 10, 11], 'Laptop': [28, 29], 'Cap': [6, 7], 'Skateboard': [44, 45, 46],
                            'Mug': [36, 37], 'Guitar': [19, 20, 21], 'Bag': [4, 5], 'Lamp': [24, 25, 26, 27],
                            'Table': [47, 48, 49], 'Airplane': [0, 1, 2, 3], 'Pistol': [38, 39, 40],
                            'Chair': [12, 13, 14, 15], 'Knife': [22, 23]}

        # for cat in sorted(self.seg_classes.keys()):
        #     print(cat, self.seg_classes[cat])

        self.cache = {}  # from index to (point_set, cls, seg) tuple
        self.cache_size = 20000


    def __getitem__(self, index):
        if index in self.cache:
            point_set, cls, seg = self.cache[index]
        else:
            fn = self.datapath[index]
            cat = self.datapath[index][0]
            cls = self.classes[cat]
            cls = np.array([cls]).astype(np.int32)
            data = np.loadtxt(fn[1]).astype(np.float32)
            if not self.normal_channel:
                point_set = data[:, 0:3]
            else:
                point_set = data[:, 0:6]
            seg = data[:, -1].astype(np.int32)
            if len(self.cache) < self.cache_size:
                self.cache[index] = (point_set, cls, seg)
        point_set[:, 0:3] = pc_normalize(point_set[:, 0:3]) # TODO:

        choice = np.random.choice(len(seg), self.npoints, replace=True)
        # resample
        point_set = point_set[choice, :]
        seg = seg[choice]

        return point_set, cls, seg

    def __len__(self):
        return len(self.datapath)


if __name__ == '__main__':
    data = ModelNetDataLoader('modelnet40_normal_resampled/', split='train', uniform=False, normal_channel=True)
    DataLoader = torch.utils.data.DataLoader(data, batch_size=12, shuffle=True)
    for point,label in DataLoader:
        print(point.shape)
        print(label.shape)