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

import gzip

import numpy
from six.moves import xrange  # pylint: disable=redefined-builtin

from tensorflow.contrib.learn.python.learn.datasets import base
from tensorflow.python.framework import dtypes
from tensorflow.python.framework import random_seed
from tensorflow.python.platform import gfile
from tensorflow.python.util.deprecation import deprecated

import os
import numpy as np
from PIL import Image

DEFAULT_SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/'

#读取数据
def readImages(source_dir,one_hot=False, num_classes=10):
  # 第一次遍历图片目录是为了获取图片总数
  input_count = 0
  for i in range(0, 10):
    # dir = './tensorflow/mnist_digits_images/%s/' % i  # 这里可以改成你自己的图片目录，i为分类标签
    dir = source_dir+'/%s/'% i
    print(dir)
    for rt, dirs, files in os.walk(dir):
      for filename in files:
        input_count += 1

  # 定义对应维数和各维长度的数组,得到一个input_count行, 784列的二位数组, 其值皆为0
  input_images = np.array([[0] * 784 for i in range(input_count)])
  input_labels = np.array([[0] * 10 for i in range(input_count)])

  # 第二次遍历图片目录是为了生成图片数据和标签
  index = 0
  for i in range(0, 10):
    # dir = './tensorflow/mnist_digits_images/%s/' % i  # 这里可以改成你自己的图片目录，i为分类标签
    dir = source_dir + '/%s/' % i
    for rt, dirs, files in os.walk(dir):
      for filename in files:
        filename = dir + filename
        img = Image.open(filename)
        width = img.size[0]
        height = img.size[1]
        for h in range(0, height):
          for w in range(0, width):
            # 通过这样的处理，使数字的线条变细，有利于提高识别准确率
            #if img.getpixel((w, h)) > 230:
              input_images[index][w + h * width] = img.getpixel((w, h))
            #else:
              #input_images[index][w + h * width] = 1
        input_labels[index][i] = 1
        index += 1
  input_images = input_images.reshape(input_count,height, width, 1)
  if one_hot:
    return input_images,dense_to_one_hot(input_labels, num_classes)
  return input_images,input_labels

#数据读取
def _read32(bytestream):
  dt = numpy.dtype(numpy.uint32).newbyteorder('>')
  return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]


@deprecated(None, 'Please use tf.data to implement this functionality.')
def extract_images(f):
  print('Extracting', f.name)
  with gzip.GzipFile(fileobj=f) as bytestream:
    magic = _read32(bytestream)
    if magic != 2051:
      raise ValueError('Invalid magic number %d in MNIST image file: %s' %
                       (magic, f.name))
    num_images = _read32(bytestream)
    rows = _read32(bytestream)
    cols = _read32(bytestream)
    buf = bytestream.read(rows * cols * num_images)
    data = numpy.frombuffer(buf, dtype=numpy.uint8)
    data = data.reshape(num_images, rows, cols, 1)
    return data


@deprecated(None, 'Please use tf.one_hot on tensors.')
def dense_to_one_hot(labels_dense, num_classes):
  """Convert class labels from scalars to one-hot vectors."""
  num_labels = labels_dense.shape[0]
  index_offset = numpy.arange(num_labels) * num_classes
  labels_one_hot = numpy.zeros((num_labels, num_classes))
  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
  return labels_one_hot


@deprecated(None, 'Please use tf.data to implement this functionality.')
def extract_labels(f, one_hot=False, num_classes=10):
  print('Extracting', f.name)
  with gzip.GzipFile(fileobj=f) as bytestream:
    magic = _read32(bytestream)
    if magic != 2049:
      raise ValueError('Invalid magic number %d in MNIST label file: %s' %
                       (magic, f.name))
    num_items = _read32(bytestream)
    buf = bytestream.read(num_items)
    labels = numpy.frombuffer(buf, dtype=numpy.uint8)
    print(np.shape(labels))
    print(type(labels))
    if one_hot:
      return dense_to_one_hot(labels, num_classes)
    return labels


class DataSet(object):
  """Container class for a dataset (deprecated).

  THIS CLASS IS DEPRECATED. See
  [contrib/learn/README.md](https://www.tensorflow.org/code/tensorflow/contrib/learn/README.md)
  for general migration instructions.
  """

  @deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
              ' from tensorflow/models.')
  def __init__(self,
               images,
               labels,
               fake_data=False,
               one_hot=False,
               dtype=dtypes.float32,
               reshape=True,
               seed=None):
    """Construct a DataSet.
    one_hot arg is used only if fake_data is true.  `dtype` can be either
    `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
    `[0, 1]`.  Seed arg provides for convenient deterministic testing.
    """
    seed1, seed2 = random_seed.get_seed(seed)
    # If op level seed is not set, use whatever graph level seed is returned
    numpy.random.seed(seed1 if seed is None else seed2)
    dtype = dtypes.as_dtype(dtype).base_dtype
    if dtype not in (dtypes.uint8, dtypes.float32):
      raise TypeError(
          'Invalid image dtype %r, expected uint8 or float32' % dtype)
    if fake_data:
      self._num_examples = 10000
      self.one_hot = one_hot
    else:
      assert images.shape[0] == labels.shape[0], (
          'images.shape: %s labels.shape: %s' % (images.shape, labels.shape))
      self._num_examples = images.shape[0]

      # Convert shape from [num examples, rows, columns, depth]
      # to [num examples, rows*columns] (assuming depth == 1)
      if reshape:
        assert images.shape[3] == 1
        images = images.reshape(images.shape[0],
                                images.shape[1] * images.shape[2])
      if dtype == dtypes.float32:
        # Convert from [0, 255] -> [0.0, 1.0].
        images = images.astype(numpy.float32)
        images = numpy.multiply(images, 1.0 / 255.0)
    self._images = images
    self._labels = labels
    self._epochs_completed = 0
    self._index_in_epoch = 0

  @property
  def images(self):
    return self._images

  @property
  def labels(self):
    return self._labels

  @property
  def num_examples(self):
    return self._num_examples

  @property
  def epochs_completed(self):
    return self._epochs_completed

  def next_batch(self, batch_size, fake_data=False, shuffle=True):
    """Return the next `batch_size` examples from this data set."""
    if fake_data:
      fake_image = [1] * 784
      if self.one_hot:
        fake_label = [1] + [0] * 9
      else:
        fake_label = 0
      return [fake_image for _ in xrange(batch_size)], [
          fake_label for _ in xrange(batch_size)
      ]
    start = self._index_in_epoch
    # Shuffle for the first epoch
    if self._epochs_completed == 0 and start == 0 and shuffle:
      perm0 = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm0)
      self._images = self.images[perm0]
      self._labels = self.labels[perm0]
    # Go to the next epoch
    if start + batch_size > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Get the rest examples in this epoch
      rest_num_examples = self._num_examples - start
      images_rest_part = self._images[start:self._num_examples]
      labels_rest_part = self._labels[start:self._num_examples]
      # Shuffle the data
      if shuffle:
        perm = numpy.arange(self._num_examples)
        numpy.random.shuffle(perm)
        self._images = self.images[perm]
        self._labels = self.labels[perm]
      # Start next epoch
      start = 0
      self._index_in_epoch = batch_size - rest_num_examples
      end = self._index_in_epoch
      images_new_part = self._images[start:end]
      labels_new_part = self._labels[start:end]
      return numpy.concatenate(
          (images_rest_part, images_new_part), axis=0), numpy.concatenate(
              (labels_rest_part, labels_new_part), axis=0)
    else:
      self._index_in_epoch += batch_size
      end = self._index_in_epoch
      return self._images[start:end], self._labels[start:end]


@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
            ' from tensorflow/models.')
def read_data_sets(train_dir,
                   test_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=dtypes.float32,
                   reshape=True,
                   validation_size=1000,
                   seed=None,
                   source_url=DEFAULT_SOURCE_URL):
  if fake_data:

    def fake():
      return DataSet(
          [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)

    train = fake()
    validation = fake()
    test = fake()
    return base.Datasets(train=train, validation=validation, test=test)

  # if not source_url:  # empty string check
  #   source_url = DEFAULT_SOURCE_URL
  #
  # TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
  # TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
  # TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
  # TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
  #
  # local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
  #                                  source_url + TRAIN_IMAGES)
  # with gfile.Open(local_file, 'rb') as f:
  #   train_images = extract_images(f)
  #
  # local_file = base.maybe_download(TRAIN_LABELS, train_dir,
  #                                  source_url + TRAIN_LABELS)
  # with gfile.Open(local_file, 'rb') as f:
  #   train_labels = extract_labels(f, one_hot=one_hot)
  #
  # local_file = base.maybe_download(TEST_IMAGES, train_dir,
  #                                  source_url + TEST_IMAGES)
  # with gfile.Open(local_file, 'rb') as f:
  #   test_images = extract_images(f)
  #
  # local_file = base.maybe_download(TEST_LABELS, train_dir,
  #                                  source_url + TEST_LABELS)
  # with gfile.Open(local_file, 'rb') as f:
  #   test_labels = extract_labels(f, one_hot=one_hot)

  train_images, train_labels = readImages(train_dir,one_hot=one_hot)
  test_images, test_labels = readImages(test_dir,one_hot=one_hot);
  print(type(train_images))
  print(np.shape(train_images))

  if not 0 <= validation_size <= len(train_images):
    raise ValueError('Validation size should be between 0 and {}. Received: {}.'
                     .format(len(train_images), validation_size))

  validation_images = train_images[:validation_size]
  validation_labels = train_labels[:validation_size]
  train_images = train_images[validation_size:]
  train_labels = train_labels[validation_size:]

  options = dict(dtype=dtype, reshape=reshape, seed=seed)

  train = DataSet(train_images, train_labels, **options)
  validation = DataSet(validation_images, validation_labels, **options)
  test = DataSet(test_images, test_labels, **options)

  return base.Datasets(train=train, validation=validation, test=test)

#
# mnist = read_data_sets("./tensorflow/mnist_digits_images","./tensorflow/mnist_test_images",one_hot=False) #MNIST数据输入
# # mnist = read_data_sets("./tensorflow/MNIST_data","", one_hot=True) #MNIST数据输入
# print(np.shape(mnist.train.images))
# print(np.shape(mnist.train.labels))
# print(np.shape(mnist.test.images))
# print(np.shape(mnist.test.labels))