# Adapted from
# https://github.com/datitran/raccoon_dataset/blob/master/generate_tfrecord.py
# and
# https://github.com/datitran/raccoon_dataset/blob/master/xml_to_csv.py

'''
MIT License

Copyright (c) 2017 Dat Tran

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
'''

from __future__ import division
from __future__ import print_function
from __future__ import absolute_import

import os
import io
import pandas as pd
import tensorflow as tf
import glob
import xml.etree.ElementTree as ET

from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict


# Add more class labels as needed, make sure to start at 1
def class_text_to_int(row_label):
    if row_label == 'waldo':
        return 1
    if row_label == 'woof':
        return 2
    if row_label == 'wenda':
        return 3
    if row_label == 'wizard':
        return 4
    if row_label == 'odlaw':
        return 5
    if row_label == 'key':
        return 6
    if row_label == 'bone':
        return 7
    if row_label == 'camera':
        return 8
    if row_label == 'scroll':
        return 9
    if row_label == 'binoculars':
        return 10
    else:
        None

def split(df, group):
    data = namedtuple('data', ['filename', 'object'])
    gb = df.groupby(group)
    return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]

def create_tf_example(group, path):
    with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
        encoded_jpg = fid.read()
    encoded_jpg_io = io.BytesIO(encoded_jpg)
    image = Image.open(encoded_jpg_io)
    width, height = image.size

    filename = group.filename.encode('utf8')
    image_format = b'jpg'
    xmins = []
    xmaxs = []
    ymins = []
    ymaxs = []
    classes_text = []
    classes = []

    for index, row in group.object.iterrows():
        xmins.append(row['xmin'] / width)
        xmaxs.append(row['xmax'] / width)
        ymins.append(row['ymin'] / height)
        ymaxs.append(row['ymax'] / height)
        classes_text.append(row['class'].encode('utf8'))
        classes.append(class_text_to_int(row['class']))

    tf_example = tf.train.Example(features=tf.train.Features(feature={
        'image/height': dataset_util.int64_feature(height),
        'image/width': dataset_util.int64_feature(width),
        'image/filename': dataset_util.bytes_feature(filename),
        'image/source_id': dataset_util.bytes_feature(filename),
        'image/encoded': dataset_util.bytes_feature(encoded_jpg),
        'image/format': dataset_util.bytes_feature(image_format),
        'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
        'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
        'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
        'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
        'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
        'image/object/class/label': dataset_util.int64_list_feature(classes),
    }))
    return tf_example

def xml_to_csv(path):
    xml_list = []
    for xml_file in glob.glob(path + '/*.xml'):
        tree = ET.parse(xml_file)
        root = tree.getroot()
        for member in root.findall('object'):
            value = (root.find('filename').text,
                     int(root.find('size')[0].text),
                     int(root.find('size')[1].text),
                     member[0].text,
                     int(member[4][0].text),
                     int(member[4][1].text),
                     int(member[4][2].text),
                     int(member[4][3].text)
                     )
            xml_list.append(value)
    column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
    xml_df = pd.DataFrame(xml_list, columns=column_name)
    return xml_df

def main(_):
    end_of_file_name = '_waldo.csv'

    for folderName in ['val', 'train']:
        #Create csv file from the xml files
        image_path = os.path.join(os.getcwd(), folderName)
        xml_df = xml_to_csv(image_path)
        xml_df.to_csv(folderName + end_of_file_name, index=None)
        #print('Successfully converted xml to ' + folderName + '.csv.')

        #Create TFRecord
        writer = tf.python_io.TFRecordWriter(folderName + '.record')
        examples = pd.read_csv(folderName + end_of_file_name)
        grouped = split(examples, 'filename')
        for group in grouped:
            tf_example = create_tf_example(group, image_path)
            writer.write(tf_example.SerializeToString())
        writer.close()
        print('Successfully created the ' + folderName + ' TFRecords')
        os.remove(folderName + end_of_file_name)


if __name__ == '__main__':
    tf.app.run()