Advanced_Lane_Detection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#import libraries\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.image as mpimg\n",
    "import numpy as np\n",
    "import cv2\n",
    "import glob\n",
    "import os\n",
    "from moviepy.editor import VideoFileClip\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 1: Camera Calibration ###\n",
    "\n",
    "def distortion_factors():\n",
    "    # Prepare object points\n",
    "    # From the provided calibration images, 9*6 corners are identified \n",
    "    nx = 9\n",
    "    ny = 6\n",
    "    objpoints = []\n",
    "    imgpoints = []\n",
    "    # Object points are real world points, here a 3D coordinates matrix is generated\n",
    "    # z coordinates are 0 and x, y are equidistant as it is known that the chessboard is made of identical squares\n",
    "    objp = np.zeros((6*9,3), np.float32)\n",
    "    objp[:,:2] = np.mgrid[0:9,0:6].T.reshape(-1,2)\n",
    "  \n",
    "    # Make a list of calibration images\n",
    "    os.listdir(\"C:/Users/Hripsime/Videos/Lane-Detection/camera_cal/\")\n",
    "    cal_img_list = os.listdir(\"C:/Users/Hripsime/Videos/Lane-Detection/camera_cal/\")  \n",
    "    \n",
    "    # Imagepoints are the coresspondant object points with their coordinates in the distorted image\n",
    "    # They are found in the image using the Open CV 'findChessboardCorners' function\n",
    "    for image_name in cal_img_list:\n",
    "        import_from = \"C:/Users/Hripsime/Videos/Lane-Detection/camera_cal/\" + image_name\n",
    "        img = cv2.imread(import_from)\n",
    "        # Convert to grayscale\n",
    "        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
    "        # Find the chessboard corners\n",
    "        ret, corners = cv2.findChessboardCorners(gray, (nx, ny), None)\n",
    "        # If found, draw corners\n",
    "        if ret == True:\n",
    "            # Draw and display the corners\n",
    "            #cv2.drawChessboardCorners(img, (nx, ny), corners, ret)\n",
    "            imgpoints.append(corners)\n",
    "            objpoints.append(objp)\n",
    "    ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape[::-1], None, None)\n",
    "            \n",
    "    return mtx, dist         \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 2: Perspective Transform from Car Camera to Bird's Eye View ###\n",
    "mtx, dist = distortion_factors()\n",
    "\n",
    "def warp(img):\n",
    "    undist = cv2.undistort(img, mtx, dist, None, mtx)\n",
    "    img_size = (img.shape[1], img.shape[0])\n",
    "    offset = 300\n",
    "    \n",
    "    # Source points taken from images with straight lane lines, these are to become parallel after the warp transform\n",
    "    src = np.float32([\n",
    "        (190, 720), # bottom-left corner\n",
    "        (596, 447), # top-left corner\n",
    "        (685, 447), # top-right corner\n",
    "        (1125, 720) # bottom-right corner\n",
    "    ])\n",
    "    # Destination points are to be parallel, taken into account the image size\n",
    "    dst = np.float32([\n",
    "        [offset, img_size[1]],             # bottom-left corner\n",
    "        [offset, 0],                       # top-left corner\n",
    "        [img_size[0]-offset, 0],           # top-right corner\n",
    "        [img_size[0]-offset, img_size[1]]  # bottom-right corner\n",
    "    ])\n",
    "    # Calculate the transformation matrix and it's inverse transformation\n",
    "    M = cv2.getPerspectiveTransform(src, dst)\n",
    "    M_inv = cv2.getPerspectiveTransform(dst, src)\n",
    "    warped = cv2.warpPerspective(undist, M, img_size)\n",
    "   \n",
    "    return warped, M_inv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 3: Process Binary Thresholded Images ###\n",
    "\n",
    "\n",
    "img = cv2.imread('C:/Users/Hripsime/Videos/Lane-Detection/test_images/test4.jpg')\n",
    "\n",
    "\n",
    "def binary_thresholded(img):\n",
    "    # Transform image to gray scale\n",
    "    gray_img =cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
    "    # Apply sobel (derivative) in x direction, this is usefull to detect lines that tend to be vertical\n",
    "    sobelx = cv2.Sobel(gray_img, cv2.CV_64F, 1, 0)\n",
    "    abs_sobelx = np.absolute(sobelx)\n",
    "    # Scale result to 0-255\n",
    "    scaled_sobel = np.uint8(255*abs_sobelx/np.max(abs_sobelx))\n",
    "    sx_binary = np.zeros_like(scaled_sobel)\n",
    "    # Keep only derivative values that are in the margin of interest\n",
    "    sx_binary[(scaled_sobel >= 30) & (scaled_sobel <= 255)] = 1\n",
    "\n",
    "    # Detect pixels that are white in the grayscale image\n",
    "    white_binary = np.zeros_like(gray_img)\n",
    "    white_binary[(gray_img > 200) & (gray_img <= 255)] = 1\n",
    "\n",
    "    # Convert image to HLS\n",
    "    hls = cv2.cvtColor(img, cv2.COLOR_BGR2HLS)\n",
    "    H = hls[:,:,0]\n",
    "    S = hls[:,:,2]\n",
    "    sat_binary = np.zeros_like(S)\n",
    "    # Detect pixels that have a high saturation value\n",
    "    sat_binary[(S > 90) & (S <= 255)] = 1\n",
    "\n",
    "    hue_binary =  np.zeros_like(H)\n",
    "    # Detect pixels that are yellow using the hue component\n",
    "    hue_binary[(H > 10) & (H <= 25)] = 1\n",
    "\n",
    "    # Combine all pixels detected above\n",
    "    binary_1 = cv2.bitwise_or(sx_binary, white_binary)\n",
    "    binary_2 = cv2.bitwise_or(hue_binary, sat_binary)\n",
    "    binary = cv2.bitwise_or(binary_1, binary_2)\n",
    "    \n",
    "    return binary\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x26b110c7dc0>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAADfCAYAAAAN+JPJAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOy9d3hU5dq+fU5mkslk0vuk94Q0Aqn0HjqC9CKoINaNFdDt1q342rCAiiLYUECq9N4hBAKEFNJJSO+9J1PX9wdmfbKt21d/m+2b8zg8MCuTWWXW3Ot57ue+r0siCAK99NJLL738tTD6Tx9AL7300ksvfzy9wb2XXnrp5S9Ib3DvpZdeevkL0hvce+mll17+gvQG91566aWXvyC9wb2XXnrp5S/InxbcJRLJOIlEkieRSAokEsnzf9Z+eumll156+TGSP6POXSKRSIGbwBigHLgGzBUEIfsP31kvvfTSSy8/4s8auccABYIgFAqCoAG2A/f8SfvqpZdeeunlX5D9Se/rCpT94OdyIPbnXmxlZSVIJBIUCsWfdDh/Hmq1Gr1ej5mZGY2NjWi1WqytrVEoFHR2dtLW1oYgCBgMBgBMTEyQy+W0tbUhkUiwtbWlqakJAF9fXzo6OmhpaUEul9Pd3Y1UKsXY2BhbW1vKyspQq9XY2dnR1taGXq9HKpUik8mQSCQIgoCxsTFKpZK6ujoMBgOWlpbodDo6OjowMjJCIpFgYWFBU1MTgiCgUqnQaDQYGRmh1WoxMjKiubkZGxsbtFotOp0OQRDo7u5GEARkMhkymQy1Wo1cLkcqlYrXwtjYGGNj4zu2/VHIZDLxXHrppReQy+VkZGTUC4Lg8FO//7OCu+Qntt2R/5FIJEuBpQBKpZKmpiYxSP03odPpOHToEJ9//jl2dnZ4e3tz7do17O3taWtr4/r16xgMBsrLy/Hy8iI+Ph4LCwsuXbrEjRs3eOedd2hububy5ctMnTqVgwcPkp6ezrBhwzA2Nqarq4vt27cTHh6Oqakpnp6e+Pn58emnn2Jra4ufnx9SqRSpVEpLSwujR49m9uzZfPHFF3z11VdMmjQJW1tbdu7cyZAhQ8jJySEmJoajR4/S2dmJk5MTERER9OvXD3NzcyorK0lMTMTBwQErKyuuXLlCTU0NVlZWhISEoNPpqK6u5vLly1hZWREUFERgYCCrV6/G3NxcfID00ksvfz4SiaTk5373Z6VlygH3H/zsBlT+8AWCIGwUBCFKEIQoCwuL/8rADiCVSpkwYQI7duwgNjaWyMhIoqOjOXHiBG1tbWi1WhoaGjA2NsbZ2Zny8nKMjIyorq4mLCwMlUpFcHAwly9fprCwEL1ez7hx4ygrK8POzo7ExETmz5/PunXreO+994iKiqK5uZn4+Hisra3JyMjg4sWLnD9/nsLCQhITE3n33XexsrLC0dGRzs5Ojh49irm5OVVVVbi6umJubs6gQYPEEfqVK1coLi5Gq9Wyfft21Go1SqWSEydOoNVqkUqleHt7c+LECa5cucKtW7fQ6/XU1NRw/vx5vvvuO9ra2pBKpf+Vn2EvvfwV+bNG7tcAf4lE4g1UAHOAeb/0B/+tQUEikWBiYoKJiQkxMTG88cYb/M///A8dHR14e3szYcIE5HI527dvx9jYmNbWVuRyORqNhszMTD788EPCw8Pp6uqiuLiYMWPGYDAYqKyspKmpCVdXVwCsra2Ry+UMGDCAr776iqqqKlQqFVqtVkzJGAwGXF1dSUtLIywsDLj98CkrK8Pe3p6xY8dy5MgR6uvrkcluf/Q1NTUEBwfT2NjIyZMnUSqVxMTEUFBQgJWVFeHh4ZiYmLB7926am5vR6/WYmpqiUCgYN24cI0aMAMDU1PQ/8wH00ksvP8mfMnIXBEEHPAEcB3KAnYIgZP0Z+7qbiIyM5Nlnn+WVV14hLi4OvV5PYGAgO3fuJCcnB0dHR4yMjBgyZAg+Pj7o9Xp8fHxoa2tDp9OJwf7111+nsrISV1dXFi5ciJubG3K5HEEQSE9Pp66uDh8fH2bMmIGTkxN+fn64uroSEBDAkSNH6O7uZt26dbi4uKBSqViwYAEKhYIhQ4ZgY2ODj48PTU1NGBsb097eLqZgQkNDcXR0JD09HSsrK5qbmykvL0cul7N8+XKUSiXW1tao1WoCAwNZuHAhTzzxBE888QR2dnb/6cvfSy+9/IA/a+SOIAhHgCO/5bVyufzPOoz/p0gkEmJiYrCyssLW1paMjAyuXr2KVCpl7NixREdHs2bNGl577TVxsXPHjh34+vrS2dlJXl4eYWFhLFmyBIPBgLu7O0VFRcTHxyORSAgMDGTt2rV4eHgQFhaGVColICAAZ2dn9u7dS2trK6ampsyaNYu9e/cil8spKyujsbERvV7Pt99+i7m5OcbGxvj7+5OQkEBLSwuZmZnI5XK8vb1JSUnBzs6OsWPHEh4eTlpaGvX19XR0dNDe3o5UKiU+Ph5XV1c8PDzE8+6ll17uLv604P7v8FcJ7jqdjpycHMaMGcOJEyeYOnUqhw8fpqamhmeeeUZcbK2oqECj0aBQKMQRvpeXF2q1GoPBQHZ2Ni4uLmzfvh0/Pz927NhBeHg4Dg4OTJw4kenTp1NTU8Pu3bvx8PBgxIgRbN++HZ1Oh6mpKX369GHfvn2Ul5fj6upKXFwcYWFh5Ofnk52dTW1tLWPHjkUQBIYNG8acOXPYsGEDbm5uvP7669jb2/PVV1/Rp08fysrKSEtLo6urC1tbW0aNGoWzszPbt29Ho9Hw5ptvYmFh8bPXRBAEqqurqaiowM/PD2tr6/93H0gvvfwf5q6QH9Dr9f/pQ/hDqKio4MaNG+zfv59PP/2U1atXEx8fz/vvv8+tW7cwMjLi5s2blJeXY2xsjIeHBxKJhOnTpxMZGcnkyZMJDg6mvLycGzdukJCQgLGxMeHh4WRlZXHq1Ck+++wzamtrOXDgAB4eHsjlcv7xj3+IJYJqtZr8/HwEQaCzsxMbGxtqa2s5ePAgfn5+rFmzBrlczq5du7CwsKBPnz40NDQwePBgsVJn48aN5OXl0d7ejkQiQa1W09nZSXNzMwcPHqSgoAC1Ws369evZtm3bz14PQRDIzc3l0UcfZdCgQaxYsYLKysqffX0vvfTyx3FXjNy7urr+04fwh+Ds7Ex+fj779++ns7OTY8eOMXHiRIKDg9m7dy+XL1/GwsKCtrY25s2bx5dffkliYiIPP/wwVVVVJCYm0tXVxfHjx5k5cyazZ8+mb9++1NTUsHPnTq5fv05eXh56vZ4pU6aQkZFBZWUl3d3dDB48mMTERARBYMuWLcyaNYvi4mKee+45AAYPHoyFhQVarZahQ4eKQVapVHLp0iWGDRuGnZ0d+fn52NraYm1tzeeff85rr71GWFgYa9aswcnJCXNzc1QqFf7+/iQnJ2NlZSWOzru7u1GpVAAkJyeTlZXFJ598Qn19PRqNhu+++w6VSsV9992HkZERLi4uvQuxvfTyJ3FXBHcLCwsMBgNGRn/MREIQBMrKyti4cSMdHR2MHj2a8ePHo9frOXfuHKdOnWLYsGGMHj0aExMTBEHg2LFjFBcXM2PGDOzt7X9XHtnExITp06dz6dIliouLiY2Npbq6GkdHR0JDQ9m3bx8qlYqqqio6OzuZMmUKL7/8MgUFBXR3d1NWVoaJiQnPPPMMPj4+HD9+nKqqKlxcXJDL5aSnpzNz5kxyc3Oxs7NDo9GQk5ODq6sro0ePpqOjg9TUVFxcXEhMTMTDw4N//OMfzJ07l8zMTGQyGXFxcRw8eJCHH36YkpISNBoNFy5coKCggOnTp9PR0UFxcTE+Pj7Y2NgQHx9PTk4Oa9eupbKyEjMzM7Zu3YqTkxOxsbFkZGSgUCh46623GDduHCUlJTQ3N5OUlERLSwsdHR3i9QkICGDdunV8/PHHmJubM2TIENasWYO9vf1PXk+9Xk9dXR0SiQR7e3vxHvkzmqR66eWvxl0R3Nva2v7w4H7s2DG2bNmCWq2muLiY8vJy2tvbWbt2LeXl5Xz11VcsX76c+Ph4srKyeOuttygsLOT06dNiQ45MJsPGxuY3B3qJRIKpqSklJSU89NBDGBsbk5iYSGRkJE1NTfj6+uLp6YmHhwcBAQEEBgbyxRdfIAgCRUVFaLVaXn31VZYvX05jYyOVlZUkJCTg5OSEnZ0d4eHhCIKAIAgEBgaSkpJCR0cHAwcOxMnJCS8vLzQaDcHBwWRnZ1NSUoKfnx9r164lJSUFd3d3Ojo6qKio4Nq1a5iZmdHR0YGrqyv9+/fn0UcfxcTEhD179nDkyBFiY2P55JNPaGlpQSKRIJfLUalUVFdXU19fj6WlJV9++SWrV6/G1NQUOzs7jhw5gre3N+3t7fj6+tLY2IhOp8NgMFBTU4NOp0OpVGIwGNi9ezePP/74j4K7TqfjypUrfPfdd2zbtg2JRML48eOxtLRk2LBhxMfHY2Zm9ofcK7308lflrgjuBoPhD624aGlp4ciRI2LDjp2dHU8++SRSqZR3332X/fv3Y2NjQ3FxMaNGjcLGxgYXFxecnZ2prKzk/vvvFxcnH3jgAebPn/+bHzzOzs5ERkZSVlbGvffeS0ZGBvn5+fj5+VFWVsb58+eZO3cunZ2dKJVKnJycMDIywtnZmfr6empra1EqleTn5xMXF8fJkyfp7u5mzJgxHDhwgJCQEMrLy4mNjcXMzAwbGxva29tJSUmhT58+VFZWolareeyxx/jggw/YuXMn1tbW9OvXj9TUVAwGA6NGjeLEiRPMnz+fpKQk3nnnHaKjo2lra+P48eO4uLggk8k4cOAA5eXl1NTUYDAYkMlkPPfcc3z11Vc0NTURFxeHIAgcPXqU5uZmCgsLMTc359atW9jb2xMdHc2NGzcoLy+nqamJuro6PDw8mDZtGr6+vrz88su0t7f/6F7YuHEjy5cvp7OzU9z+zTffYGFhwZkzZ/D19RXr+HvppZef5q5YUJVIJH/oVLulpYWUlBRcXV3x9vbGwcGBSZMmIZfLcXNzIzw8nI6ODoKCgjAzMyMoKIja2lpmzJhBTk4O6enpeHp6EhAQQFVVFVeuXKGiooLm5mZ+TUXTwsKClStXkpKSgoODAxERETQ2NuLj44NMJkOlUnH48GH0ej0tLS387W9/Q6VS4ezszPXr1ykuLiY6OpqWlhbi4uLw9fVFLpej1+uxtbVlx44dVFdXk5iYSF5eHrdu3cLc3BwvLy/OnDmDUqkEoLOzk6lTp/L000/z9NNPc9999zF69GiqqqpoaWmhsrKSmpoagoKCkMlkKBQK5HI57777LiUlJRgMBjw9PbGyskKhUIgaN4cPH2bcuHFYWlpia2tLSkoKkZGRyGQybt68iUwmw8XFhbCwMIYOHUpcXBxNTU2MHDmSQYMGUVtbi0Qiobq6mgULFuDu7n7H9dNqtWzevPmOwA4QFBTE5MmTmTBhAn5+fn/YvdJLL39V7orgbmJiIgpr/REYGRkxcOBABg0aRFlZGfHx8fj4+PDYY4/xzTffEB4eTnt7O46OjmIgWrhwIQ0NDdx7770cP36c3NxcioqKOHz4MGPGjGHEiBGMHj2axx9/nNzc3J/dt0QiITQ0lOnTp3Pq1CmmT5+Ou7s7XV1dhIWFUVlZiVarJTMzk6ysLOLi4jA3N6dv374sWbKEffv20djYSGxsLHV1dZSWljJo0CDi4uKIjo4mIiKCzMxMampq+Oyzzxg9ejQymYxDhw5hY2NDXl4e/v7+ODo6Eh0dzYMPPsjzzz+PXC5HLpcTERGBsbExFhYWODk58fbbbzNw4EDg9uLqwoULGTx4MPHx8RQUFDBixAhcXFxwcnISH0i1tbXcunWLzz77jPT0dA4ePEhLSwuOjo7Y2toSGRnJgAEDePnll6mtrWXixIncvHmTsLAwUYvn5MmTpKamkpGRQXd3N3q9nuzsbF588UWampruaIpycXGhoaGBvXv3cuXKFUxMTP6we6WXXv6q3BVpGY1G84fm3NVqNeHh4aSkpNDZ2YlKpaKsrAxzc3NMTExwcXFh1KhRnD9/nhEjRuDl5UXfvn3R6XQEBATg7e1Nnz59MDU1pa6uDrlcTkFBAWZmZkilUlpbW39x/zKZjEmTJvGPf/yD4OBgLC0tARg9ejSnTp1ixIgRNDc3k5qaiq+vLwqFAnt7e7RaLYMGDeLy5cu4uLjQ3t5Oc3Mz6enpCIIg5tgtLCzYv38/EokENzc3vvvuO+rr63nwwQcpLCxEJpMxYsQIsaa8p9xy+PDhnD17lhs3buDs7ExUVNQddedSqZRHH30UnU6HQqEgJyeHL7/8kri4OIqLi6msrKShoYHc3FxxHUEmk5GamopOp8PR0ZHc3FwxoI8fP56SkhJRUfLo0aM4OzszdOhQ9u/fT1RUFK+99hq2trbY2dkxatQo1Go1AwYMwMnJiaamJqqqqli2bBn29vbodDqOHj36h9wjvfTyV+euCO46ne4PC+xwe+SemZmJVqvFzMyMZcuWkZSURGBgIO+99x4eHh7U1NSwY8cO3Nzc6OrqwszMDC8vL3Q6HTdv3mTBggWUlJRQUVGBqakpGRkZooiWubn5rx5DQEAAzzzzDC+99BL9+vWjo6ODxYsXM3XqVPz8/Fi1ahUdHR10dXUxdepUUlJS2LRpE/Pnz0en04nCXK6urtTV1XHs2DE0Gg3Dhg0jPT0dNzc3amtr2bp1K3q9HrlczsWLFwkJCeHDDz9k9uzZ2NjYiMdjYmKCs7Oz2AA1ZcoURo0adcdah0QiEbVyzM3N0Wq1ODs7c+XKFbEXIT8/HwsLC/R6PTExMaSnp+Pg4ICRkREmJia4urpiZmbGrVu3sLa2ZsqUKVy5cgUzMzOqq6uxsrKivLyciRMncvr0aYYOHcoHH3yAtbU1ISEhXL9+HWtra9LT0+ns7GTlypW4u7vT1taGRqP5Ubqml156+WnuiuD+R6sJKhQKsZrD3t4eFxcXMUh+9dVXREZGcuXKFby9vQkJCaGkpASZTEZWVhbl5eVkZWVhZGTE9OnTSUhIoLKyknnz5mFtbc2aNWuoqKjAxcUFS0vLX3wo9evXD09PTy5cuEBYWBjHjx9n8eLFHDhwAIC8vDyKi4tFeQG5XI6JiQlqtZrs7Gz8/PyIjIwUtdWDgoJIS0sjKSmJ559/Hjc3N6qqqqiurkaj0dDU1ER9fT1Dhw69owSxh559LFq0CKlU+rM15oIgkJCQwK5du5g7d644w9m2bRu1tbWoVCquX7/OuXPniI+PZ8OGDezduxelUkl6ejqrVq3Cw8MDrVaLXC7H2dmZq1evolQqiY6OJjk5WdS88fb25ptvviE9PR0/Pz/8/f1JTEwUJRO2bNmCr68vdXV1NDc3o1AoSEpKwtzcnLCwsD90UNBLL38l7opvhlQq/UNz7iqVin379vH888+TmZmJWq2mvr6e5uZmLl68SGhoKMOGDROla8vLyyksLMTDw4Pa2lrMzMyYM2cOc+fO5ZlnniE+Pp5Dhw5hYmJCnz59UCgUWFpa/uoDSS6X8/777+Pu7k5ycrLYJGRubs7IkSN59NFHMTIy4uLFi1hbW+Pg4EBlZSUuLi6MGDEChUKBi4sLt27dwtTUFGNjYxISEnB1dSU9PR0vLy8sLCywsrLCy8sLf39/sSrHxcXlZ4/L1tYWKyurXzz2zZs3U1xcTGpqKjY2Njg7O+Ps7Ex7ezvHjh0jLCyMUaNG8fLLLxMaGsoTTzyBqakpH3/8MZ6enhgZGYmyEhERETzwwAOkpqZSWFjItm3biI+Px9TUlPXr19Pe3o4gCMTFxbF06VKWLl2Kl5cXWq2W8vJybt26RWpqKjNmzKC4uJh7772XpUuX/uQDrJdeernNXTFyNzU1/UNHYBKJBDMzM/r374+rqyufffYZPj4+3HfffQwbNozg4GCCg4Npa2ujs7OT8vJyysvLOXPmDC+//DLOzs64ubmhUChQqVS0tbWRk5NDamoqxcXFPPvss3z++ee/qRzPwsKCxx57jBUrVvDll1/S0dHBBx98wMGDB5k+fToWFhZYW1vj6enJ2LFjqa+vp6KiAoVCQVtbG3K5HLVajampKYIgEBISgo2NDcuWLcPJyYmysjJqa2upqalh/vz57N69mzlz5vyvNVxcXV0xMjLCxsaGa9eukZGRITo92draEhYWhkQiwdraWvzXysqK5ORkhg4dikQioaWlhfLyckJCQvD09MTV1ZXi4mIxzdWjVDl69GiuXr1Kbm4uN27cICQkhJs3b+Lt7S129JqamrJ161YaGhrEtFF6ejqDBw/+X51nL738VbkrgntXV9efoiwokUjw9/fn5MmTNDY2UlZWxrVr1wgMDGTdunVYWFhQW1uLra0t165dw9HRkT59+uDg8P+7VkmlUkJDQwkLC8Pc3Jx77rmHkpISWlpafvMxDB8+nLlz57JhwwaGDx9OW1sbcXFxfP755wQEBFBaWoqvry9KpRKZTEZVVRXBwcEsXbqUiooKxo0bJwbahx9+mNDQUCwtLdHr9QwZMoSGhgbMzMwYOHAgQUFBeHt7/68qStrb26moqEClUtGnTx/q6+u5cOECrq6u2Nvb06dPHxISEggNDRWt/gBSU1NJT0+nsbGR9PR0seTx7bffJjMzkzVr1nD27FmWLVvGY489hkqlwtHREWNjY2QyGX5+frz77rtUVlbi7OxMXV0dDQ0NYjmplZUV3d3dGAwGIiIiaGtr+93n2Esvf3XuiuDeU03yZxAWFsaIESNQq9Xs2rVL3Pbkk09SUlLCrVu32Lp1K4sXL2bMmDEYGRlRVFSEt7e3+B4NDQ2UlZUxYMAAqquriY2N/UUlxJ9i2LBhfPTRRwwdOpTU1FTkcjm+vr4YGRmRnJzM8ePH8ff3Z9y4cRgbG2NkZISfnx/t7e0cPXqU1atXk5WVRVRUlBi4pVIpMTEx9O/f/w/pFRAEgaamJjZs2EBzczMDBw7kyJEjpKWlMXz4cGxtbbl06RLXrl3jvvvuw8XFhebmZuzs7NBqtVhZWXH06FGCgoKQSqW8/vrrGBsbY29vT2FhIcuWLSMqKoqEhAR2797NqlWrxHOxtLRky5YteHl50d7ezsSJE5k2bRpyuZxBgwZRV1fH9OnTEQQBR0dHDh48SHR09P/qfHvp5a/MXRHc/8xFsT179jBnzhxCQ0Opr6/HysqKfv36YWJiglQqpaSkBFNTU/Lz87ly5Qr9+vUjNjZWDO5arZZTp05RW1vL5cuXMTMz48SJE8TG/qzf908SHBzMwoUL6e7uJikpicGDBzN//nzS09O5dOkSjo6ODB8+nOzsbARBYNu2bfTp04dBgwYxYcIESkpKsLS0JC0tjZiYGPF9JRKJaIBtZWWFsbHx775WJSUlvP/++5SVlRESEsKhQ4dwd3dHq9WKefSexWc7OzvKy8tZu3YtTz/9NPb29kRGRnLx4kXy8vJEH9Zp06YRExODSqUiOzubixcvolKpePbZZ0U3KEEQRCvC48ePI5VKaWtr4+233xYrfpydnYmJiaGyshJBEFAoFAwaNOh3n2svvfzVuSsWVNVq9Z/23vb29mRnZ/PRRx/h7e1NQECAmAIyMzPj0qVL6PV6GhsbEQRBbPfvYdu2bTQ0NBAaGkp3dzczZ87kvvvuQ6vV/uZjMBgMrF27lpaWFpydnZk8eTK5ubls2rQJnU6HTCajubmZ9vZ2IiMjmTdvHt7e3piZmYmiWXV1dRQUFNDY2PijOvtr167x/PPPk5KS8r+6Vi0tLfj4+NDQ0EB+fj6VlZUYGRkRFBQE3F4YtbOzQxAE8vLyyMzMpL29HQsLCyQSCTk5Obi4uNDW1kZUVBQBAQGkpaWxf/9+1q5dy/Lly0lPT8fc3JysrCxRprin9NPOzg5ra2siIyN/NDuqqKhgwIAB1NfXk5aWJub0f61jGBD1eHrp5f8Svzpyl0gkXwKTgFpBEEK/32YL7AC8gGJgliAITd//7gVgMaAHlgmCcPzX9vGvtcs99eS/NqIXBAGNRkN2djbp6ek4OjoSERGBjY0N1dXVODg4oFAoOHToEG+//bYoZtUT3Lu7u8nJycHa2pquri7i4uIoKCgQZQYkEgkuLi4YGxszbNgwzp07x+HDhzEYDHh7e4uv+TXy8vKora0FbgfQe++9FxcXFy5cuIBGo8He3p5Vq1ZRVVVFeXk5V65coW/fvuzatQsbGxv27dvH9OnTAThy5Ah1dXXMmjVLrEYZNGgQPj4+v6n+/ufQ6XSUlpZy8eJFtFotFhYWWFhYkJycjFwuJz8/H19fX0xNTTEzMyMwMJDU1FRu3bqFTqdDp9OJTlRyuZxz585RVlaGq6srR44cYdKkSYwcOZLu7m46Ojo4dOiQOAPpkSw4dOgQcLuaB27fFz1rC59++iltbW3cvHmT2tpaSkpKsLOzY9WqVb9Y+SMIAgcPHqS7uxsfHx+USiV+fn7/qxlOL738N/Bb0jKbgHXANz/Y9jxwWhCEtyQSyfPf/7xSIpEEc9sMOwRwAU5JJJIAQRB+0Y1DoVCg1+sxGAwYDAaefPJJjI2NeeWVV7C1tf3ZAJqbm8snn3xCc3Mzu3fvRqlUEhISgr+/P+fPn8fe3p6UlBRxFCyTycQHhiAI5OTkUFxcLHZWNjU1oVKpyMrKoqmpiVOnTlFaWsru3bupqanBxsaGgwcPEhYWxtmzZxk0aBCCIIgm1j30CKH1GFf3nIOxsTFnzpyho6ODvLw8Dh06xLhx41i0aBG2trbY2tpSVlaGTqfDxsaGmpoaBEHAxMREXODU6/WcOXMGIyMj5s2bh0QiEbXR/zfpLZ1Ox5YtW8RqFDs7O+RyOQqFgsWLF6NWq8nIyEAmkzFt2jS+/vprOjo6GDduHPn5+VRUVGBiYkJHRwfJycnExsZy/fp1xo0bx+TJkyktLeW7774THwQvvPCCeLwSiQQnJydGjhzJ/v37SU5OxsHBQZzR1dbW0rdvXx555BEAxo0bx4kTJ9ixYwfPPffczwZ3QRA4d+4cTz31FKWlpchkMuRyOceOHWPAgAG/+1r10st/A78a3AVBuCCRSLz+ZfM9wPDv//9r4Byw8vvt2wVBUANFEomkAIgBLv/SPlpbW3n77be5fPkygiCQnJxMY2Mj1dXVLFu2jAEDBoiLhT2BXq1Ws3HjRrRaLTdv3iQgIIA33niDN998k/b2dtra2lCpVISFhYk6KC+99JK4T4PBQHV1NY8++iienp5kZ2eTmZnJsWPHqKqqYtOmTYwaNYqysjJRGnfs2LGYm5uTlpZGfn4+b775Jm+99daPzic1NZW8vDxmzpzJ6dOn6du3LwsWLGD//v1kZGTg4ODApUuXmD9/PtbW1hQUFODm5kZnZyfnzp2jtrZWLCdsa2sTdd6/++47amtrGTVqFPX19eL+ejRwnnjiid9ddZSamopMJsPf35+kpCQ6OzsxMTGhrq5O7FaNiooiODiY1tZWrKysUCqVeHt7U1dXxz//+U86OztRq9U0NTWxZ88ehg0bRlRUFEFBQezdu5fc3FzCw8NRKpX8/e9/5+WXX2b06NEIgkBzczMlJSUMGDCAxYsXExkZKZZz1tXVkZCQwPDhw7l+/ToWFhbY2dmxePFinJycfvac9Ho9X375JYGBgRQVFaHX68XS0156+avze4d6ToIgVAF8/6/j99tdgbIfvK78+22/SFNTE4WFhbS2tlJVVSVqnHh4eLBq1SquXr1KdnY2arVadP1599132bhxI56entjZ2eHl5cXZs2cpKiri3LlzKBQKEhMTycnJQaFQsH//fqqrq8X8qyAI2NnZcfr0aRobG3FxceH06dOiy1FnZyfffPMNMTExLFmyhEceeYSbN2+iUqkYOHAgVVVV7N69m507d97xnoIgiMFs27ZtrFy5koKCAnx9fZk6dSoODg6Eh4czZMgQqqur8fLywtnZmaysLD744AMEQUCr1VJaWopSqaS7uxsjIyPy8/NFq7phw4YxYsQIMZB3dXWxd+/eO9YK/l1sbGywtrZm6NChLFq0CK1WS2RkJI6Ojmg0GqRSKR9++CGHDx9GLpfz6KOP4uvry8GDB0lKSqKyspJly5YRHR1NXFwcarWaoqIi/Pz8cHd3p7CwkOzsbJydnUXZBUEQyMjIEGUUTExMuHLlCqdOncLe3l5MnYSEhODo6EhlZSUBAQEAPPfcczzxxBM/W/IpCAJZWVkcOnRIVAi1s7OjT58+/9Z6SS+9/LfyR1fL/NSw8SdXsiQSyVJgKdxuYgoKCsLJyYnMzExKS0vx8PDg9OnTLFq0iE2bNmFiYkJUVBRDhgzh7bffFmV0P/30U2JjY3F1daWoqAhXV1fa2tpE71BPT0+eeeYZ3n33Xb799lvCw8MxMjKio6ODU6dOYWRkxCeffMLkyZOJiIggKiqKxx57jNWrV7NhwwY6OjooKirCycmJY8eOMWXKFOzt7XFzcyM3N5fdu3fTv39/Ll26RFZWFh0dHdTU1CCXyyksLMTNzY05c+bw9ddfM3z4cFavXk1DQwMODg6UlZVRWVnJoEGD+OKLL/Dz88PFxQUvLy8OHjzIY489hlQqJSQkBK1WS1lZGf369WP27Nl3jNDz8/OZOnXq7zYa12g05OXlYW9vT0ZGhvggjIyMpLOzEwsLC7799lvGjBlDVlYWDg4OpKenk5eXR1RUFOnp6cTFxZGUlERNTQ0eHh5oNBp8fX3FnoEpU6bwzTffiJIHI0eOZM+ePWLX7YQJE/jb3/5Gc3Mz/v7+d5R19tT419XVMXjwYGbMmEFcXNzPzlIMBgMHDhzgpZdeorm5mUmTJuHg4EBBQQF9+vShoKCA8PDw33Wteunlv4XfG9xrJBKJShCEKolEogJqv99eDvxQoNsN+ElHZEEQNgIbAdzc3ISWlhbq6+vJzs7G19cXR0dHsrOz2bx5M+Hh4eTn53P69GmSk5Opq6vDYDAwcuRI/P39iYmJITg4mEcffRQbGxuqqqqwt7fn+eefF3XY58+fz86dO1mzZg1NTU20traSmZmJvb09Q4YMoaWlhfHjxzN58mTOnTvH0aNHeeCBB3j11Vd58cUXaWhoIDY2luPHjzNjxgyKioqYPXs23d3djBo1Cnt7e5ydndFqtVy6dAkbGxuUSqVY2fLiiy+yc+dOKisrWb9+Pa+++ioKhYLi4mKKiorECpV169bx3nvvERISImrJLF68mJUrV5KRkcGDDz6IRqPBxMREDG6mpqb07dv3d+fcu7q6WLlyJdbW1mK9ur29PUqlUtS0/9vf/kZNTQ1paWl0dHRw/Phx4uPj8fb2Zvjw4bz++usEBASg1Wrx9fXF3NycBx54ADMzM9rb28nJycHPzw+VSkVLSwtvvPEGy5YtIygoiNOnT6NSqRgxYsRP1up3dnZy+vRpYmNj6erqwtXVlZaWljuE0X5IaWkpK1euJD8/H1dXVxoaGmhra8PS0pLhw4f3pmV6+T/B7w3uB4BFwFvf/7v/B9u/lUgk73N7QdUfuPprb9bTPCOTyZDJZBQVFXHw4EEiIyPFEbqfnx8KhYL09HTuv/9+jI2N+fbbb3F0dCQoKAilUsnYsWPZuHEjAwcOxMbGBkdHRxoaGjhw4ABxcXEUFRXR1dWFUqlk5MiRLFiwgLfffpsdO3bw1FNPMX78eG7cuIGxsTFqtZr7779fzAd3d3dTVVVFe3s7pqam2NjYiA+irq4u6urqmDZtGteuXcPY2Ji5c+dib2+PRqNh4MCBpKWlceHCBWxtbWlubhZt74KDg1m9ejW7d+9m8eLFfPPNN8yaNYvY2FgEQRAbmdzc3PDw8GD79u1i6WCfPn3w8fGhX79+GAwGPvzwQx5++GFMTExoamoSq05+iSNHjrB+/XrCwsJobm6moqKCxx57jJs3b4pdoQaDAa1Wy5YtWygpKWHIkCH4+/sTHx/Pxx9/jKOjIz4+PhgbG9PW1kZFRQVGRkZIJBI+++wzdu3aRf/+/YmOjub111/H19eXp59+mq6uLj777DOkUqkod/CvtLW1sXLlSnx9ffnmm29wd3fnxRdfZOLEiZiYmJCcnIyzszMymQwfHx+ys7NJS0sjPDyc5uZmgoKC8PPzY9++fRgZGSEIAuvWrfvNN3ovvfy38ltKIbdxe/HUXiKRlAP/5HZQ3ymRSBYDpcBMAEEQsiQSyU4gG9ABj/9apcz3f0dTUxNKpVI0dBgwYADXr1/H3NycoqIiiouLCQkJISQkhBMnTtC/f3/Gjx9PSkoKa9asYeHChUycOJHU1FTUajUhISHI5XLMzMzw8fGhuLgYlUrF2bNniY6OJjc3FxMTEx599FEOHTpEV1cX27dvx8PDg8mTJ/Phhx/i4ODAq6++yujRo3F2dubYsWMYDAYaGxt5+eWXaWho4OOPPyY+Pp6IiAh27dqFUqkUOyo1Gg3u7u4olUp0Oh3h4eEkJSUxefJksXQwNTVVtJo7cOAAa9euZfLkyaKBiUQioaurC0tLS1Fet7Ozk4KCAry8vMTF5NLSUoqLi7l06RKDBg36zRr5CoWCgIAA/Pz8KC0tpbKykvPnz1NWVoabmxspKSnY2Nhw48YNrKysREnkmJgYMjIymDt3LgCDBw9Gq9UycuRI4HZ5plarZfXq1QQGBpKdnY1CocDJyUlUpKytraWtrQ2FQkHfvn1/lGbR6XRkZmayd+9exo8fT2dnJ2lpadTW1rJv3z66urowNzfH1NQUtVqNSqWisLAQFxcXsR8gISGBwsJCLCwsMDY2Jioq6hcXYXvp5a/Cb6mWmfszvxr1M69/HXj93zkItVrN5MmTsbe3p6qqigMHDtDS0sLp06d5/vnnKSkpoW/fvqxcuRKpVIpGoyE1NZWkpCSxseb9999nzpw5SKVSpFIplpaWNDc3I5VKxUoJW1tbKioq2LRpE8OGDePee+9Fo9Hg6urKvn37ANi4cSNKpRIvLy9KSko4dOgQ58+f55577kEikTBp0iScnZ0xMTERFxdra2upra1lxIgRnD9/npaWFpRKJebm5pw6dYpXX32V8vJyTExMcHNzw8nJidWrV/OPf/yDpqYmTExMRCeooKAgTExMEASBXbt24ePjQ1BQEGPGjBE1bo4dO0ZJSQkqlQpzc3Nqa2uxsbGhs7OTdevW0dHRQUlJCY899tivXvshQ4Zw5swZYmJiaG9vZ+rUqZw4cQJPT0/kcjk+Pj6EhYWJjUlPP/0048ePR6PRiCbiwE/mv/fu3Uu/fv2oqqrCzs5OlCIoLS2lvr4evV7PvHnzROPwf6Wrq4szZ85gZmYmukdNmTIFnU5HUVERubm5KBQK2tvb8fLyIj8/n+nTp7N79260Wi1KpZKOjg6sra2JiIhAKpXy+OOPo1Ao/p3bs5de/iu5K+QHBEHg4sWLeHp6Ultby0MPPcSRI0ewtLSkqqoKLy8vbty4QU1NDS4uLsjlciIjI9m/fz9nzpwRv7DffPMNer2eyspKUdXx2rVrhIeHo9frqa+vp7u7m5EjR+Lu7k5KSgrGxsaUl5fj4+PDoEGDuHHjhuhRamFhwZtvvsm1a9f4+uuviY2NxcPDAy8vLwoLCxkzZgwWFhZcv36drVu3MmnSJCQSCa+//jqXLl1i3759uLm5kZycTEJCAg4ODgwZMoSzZ8+Sm5vLkSNHiI6OZuLEiZiZmZGdnS3m6Nvb28nKysLGxoarV69SU1ODXq8XjbUrKytZvnw5UVFR9O/fX+xmnTBhAufPn8fLy+tXyyIFQaCxsZHLly8TEBBAZGQkGo2G/fv389133zFixAgcHR2RSCQ8+OCD9O/fX/Ro7fn3l947Ly+PYcOGcebMGQIDA0lKSmL8+PGcOHECR0dHzM3N8ff3FxuVevLtOp2Oa9eu4ezsLK6dKJVKamtrGTlypCjhPGzYMLKzs8UGsR49fGNjY8zNzcVKo8DAQJycnHj44YdxcHD4U0TqeunlbuOuCe5JSUmYmZmJ+V0jIyPGjBnD+vXrmTlzJm5ubuzYsYNZs2bh5uaGVqtFq9XS1tZGZmYm3t7efPfdd6hUKoyMjLC1taWjowOJRMKNGzf45z//SVpaGkqlEhMTE44fP46FhYWYBurbty9yuZyoqCjOnDmDp6cn5eXlREdHExMTw+nTpzEzM+PMmTNijthgMPDJJ58QHBzM448/jlKpxNnZmSlTplBXV8e4cePE/LeJiQkff/wxcXFxyGQyPDw8qK6uxtnZmZSUFBobG6mpqcHS0pLW1lYKCgqwsLDAYDAglUqxsrKirKyMkydPEhwczOLFi6muriY4OBgLCws8PDy4efMmn376KQaDgZkzZ/7qda+urmbTpk0olUrxYRMYGMjUqVPFOveGhgauXbtGZGTkrwb0pqYmzM3NxRJGpVLJjRs3ROMUU1NT0fjbyMiIUaNG8dJLL7Fo0SIxnaNWq9m/fz/d3d3Y2dlRVna7srauro4TJ06QlJSETqejvr4eExMTpkyZQmtrK3K5HK1Wy9GjR3F1daWkpASFQoGzszPV1dUsXLgQLy+v/92N2ksv/0XcNcHd0dGRmzdvMnz4cPz9/REEgd27d2NhYUFpaSm2trbY29tTUlIiNvzk5+ej0WgoKiqiT58+1NbWMnXqVA4fPkx3dzeJiYk88sgjnDx5ElNTUxITE0lOTkahUIjiYHq9nnHjxlFUVMT169fx9fUlODiYnJwctFotGRkZHDt2jIiICE6ePElTUxPFxcVYWFgwf/583N3dSUhI4PHHHxdrwtva2jAzM2Pw4MGi2JezszM3btzgq6++wtnZmUceeYTy8nJycnJYt24dzz//PAMHDqS5uZmsrCwuXryIn58f4eHh2NjY3JFKaG1tJS0tDVtbW9rb2ykpKaG5uZmmpiZCQkLo37//HeJiP4ejoyP33HMPgwYN4u2336a4uJhhw4bx8MMPM3DgQFauXIlcLqerq4vc3Fzc3Nw4c+YMvr6+9O/f/0f5fK1Wi0ajERekq6qqxKYsX19fDAYDJ06cYPz48Xh5eWFubk5TU5PoX2tiYoJOpyM7O5uAgAC++OIL0tLSuHz5sqhpHxcXR319PUVFRVRWVlJdXU1ISAju7u44OzuTmJjIQw89xHvvvUddXR12dnY888wzjB8//g+/b3vp5W7mrgjuPWV9mZmZREZG0traio2NDbGxsVhaWvLVV1+JC4c9I1I7Ozu++uorWlpauHbtGgEBAZiZmaHRaJg+fTotLS1UV1cD8MYbb/DSSy8REBBAXl4evr6+3Lx5U9Rt8fHxwcHBgbq6Or777jtmzJiBj48PEomEc+fOMXLkSJydnfH19WXv3r3MmTOHxMRE3n//fcLCwhg0aBD5+fmo1Wp0Oh1Lly5l9uzZordpQUGB6IzUo3kjk8mwtrampaWFAQMGEBoayoABA1i2bBmWlpa4u7vj6elJZWUlpaWlxMXFidfLwsJCXFMoKyvD0tKS6upqjh49yvz5839RsbLHvUipVFJeXs7FixdZu3YtTz31FJcuXcLe3h6A+Ph4PD09xQfc119/TXNzM+fPn8fS0pIPPvjgR7lrW1tbOjs7uXXrFlevXkWr1XLr1i2USiXZ2dmMHj2aL774gtbWVmxtbSkvL8fJyYmuri7Ky8vx9vYmMTGRvLw8MQevUqnQ6XRoNBpxpvb000/T3NzMG2+8QWNjIw0NDeTk5Ij6QdevX6exsZE5c+bwxhtv4OHh8Qfdqb308t/DXRHc29ra8PPzE6fhFy5cICMjg/vuuw83NzcOHz6Mubk548ePF2ubJRIJtra22NjYYGtri8Fg4O9//zt79uzBysqKiooK4uPjCQ4ORqlU8vLLL9PU1CRK5Hp6epKRkcGQIUMYMmQINTU1DBw4kJycHBITEwkNDcXExISgoCDKy8tRqVRcvHgRFxcXEhISUKvVtLa2kpeXh4+PDykpKURFRaFUKjl8+DBJSUnk5OQwZMgQ7OzsUKlUwO20g1KppKWlBTc3N9auXcuyZcvEKpQpU6agUqkoLi6mq6sLBweHH1V3SCQSOjs72bp1K76+vjQ0NNDU1IRGo8HDwwOFQiGqIHZ1dSGXy8VRdlZWFo6OjiiVSjZt2sT27dtxdHTE1NSUgQMHMmXKFA4ePEhLS4to3WdsbMyePXvYsmULer2ee++9F71e/yPhtPPnz7N69WpcXV25ceMGsbGxqFQqKisrqayspL29nTFjxojNSg0NDQwfPpzExESGDh2KWq3mo48+IiYmhpSUFLq6unBxceHRRx/lyJEj5ObmcuHCBdzc3MjOzmb48OGcO3dOfKC7u7uzePFi1q5dy/jx4xk1ahQeHh69OfZe/k9yVwR3g8FATk4Orq6uSKVS1Go1ZWVl7N27l+rqasLCwpg1axZz58790RdVIpGQnZ3NsWPHePzxxzly5Ai3bt0iMzOToKAg3NzckEql2NnZYWtry/z58+nq6uK1114jLCyMOXPmcODAAerr6xkyZAiBgYFcv36dESNG0NLSgqOjIxs2bMDa2hovLy98fX3p6OggJSWF0NBQli1bxrZt20hJSeGrr75i0aJFfPbZZ1y9ehULCwtqamoIDw8X6+ONjIzw8PCgpKQEV1dXlixZQkhICOXl5aLLEdxuuV+zZg1Tp07FysqKmpoaOjo6cHV1Ra/X09bWxoABA2hvb2ft2rU8/vjjREdHU15ezsGDB5k6dSpGRka8//77DBw4kHnz5mFsbExQUBBmZmYABAYG4urqyqpVq+jfv784g9JoNJiamlJQUMCmTZsIDw8nODiY7u5uVCoVHh4e5OXlERoaCkBhYSE2NjakpaXR0NCAqakpY8aMISwsjOLiYqqrq2lqaiIgIIC2tjY8PDzw8/Ojf//+1NbWinLGV65cwcLCgrS0NJycnBg7diwJCQlkZ2cTFBQkykT0PFjOnj1LR0cHMTExTJw4kdGjR7Nnzx4AYmNjuffee4Hbg4eioiJKS0sJDAzEz8+vN+D38pfnrgjuPZKvNjY2eHl5kZKSQkxMDOfPnycwMBBnZ2cKCgqor6+/wwKvh8jISCIjI5FKpQwZMoTKykpMTEw4d+4cY8aMYdiwYcDtB0FwcDCCIODu7o65uTnnz5/H19eXhIQEmpqaCA0NZeTIkdTU1DB69Gg++OADEhMTMTExYcmSJdTU1JCUlMTo0aPJycnh1KlTJCUlERgYyKBBg8jLy2Ps2LFMnjyZPXv2oNFoSElJwdPTEzc3N4YMGQKAk5MTTk5OFBQUcODAAUaMGCGmRHpclZ5++mmkUimCIHDs2DG2bdvGhx9+SGtrK1euXKGmpob77ruPfv36kZqaSmtrK+3t7URHR2NpaUlDQwMajYbr168zefJkDAYDNjY2YlXKrFmzmDFjBlKp9I5gd++999LR0UFqairDhg0T5YkHDRqEp6cnAQEBGBkZYWRkxM2bN1mzZg2RkZFYWlqiVCqpq6tj//79qNVq/Pz8MBgMqNVqGhoaOHv2LDNnzsTX15fr16/z1FNP0bdvX65evUpoaCg5OTlERETQ3t7OunXrRN/Vfv36MWvWLEpKSvD392fevHnMnj2be+65h46ODgoLC6murqahoYGjR4+KVTE9qbaeHPzTTz/NkiVLcHNz+7Nv6156+Y9yV5h1aDQaAgICKC4uJj8/H39/f77++mu6urrEL7NKpaK7u1vMvf4QQRDEYDN48GBMTU3RaDRERESIXYk9SCQSampqALCysuLixYscPXqUPn368OSTT2JtbY23t7eogTJq1ChWrVpFUVERTU1NNDQ0YG9vT3FxMTExMXh6eiKRSCgsLKS9vR1bW1tSU1N5++232bVrFzKZDFdXVxobG5k0aRLjx49n8eLFREVFYWdnR3NzM21tbXfIBPccp0wmE3+OjY0VdXH69+/PQw89RHl5OcXFxZiYmODi4kJERATGxsZcvnyZgoICysrKkMlk4gOlsrKStWvXcvHiRbFM8If76MHIyAhzc3OCg4NxcHAgMzOTRYsWsXHjRgIDAzE2NhYfCH5+fnh5eXH8+HFSU1O5//77eeaZZ8QH8vnz55FIJKhUKuzs7Kiurkar1ZKbm8srr7xCdXU1x44dIycnh5iYGEaPHk1wcDA3b97E1tZWfCgdOHBAlEXWaDRkZmbi5uZGv379OHLkCA0NDeTl5bFw4UKcnJzENNShQ4fEmYVer+f06dO0tbWJRiG99PJX5a4I7iYmJrS2ttLQ0MCNGzdISUnBw8ODe++9l6KiIk6ePElGRgbfffcdr776Kp9//jmCIFBbW0tjYyPl5eXU1tYikUjEbkU/Pz8OHDjA6dOnxYVVuF1SZ2NjQ79+/bCxsWH06NE8+OCDzJgxg6amJgYNGkRycjImJibI5XICAwOpqakRa69lMhlxcXHI5XJsbGxob29n5cqVjBgxgrS0NAwGAxqNhubmZpKTkwHw9PSkurqaqqoqAG7dusWJEycAePzxx5k0aRJubm4/myqQSCS4u7vz0ksv4e7ujpGREc7Ozrz55psoFApu3rzJrVu3UCgUxMXF8cQTTyCXyzl//jzDhg1j2LBhol6Mg4MDx48fp6io6Fc/l5SUFN59912MjY2xs7P7kWAZ3H4QzJ49GwsLCwYMGMD06dOZPn06jz32GJaWljg4ONC3b1/mzZtHUlISQ4cOxdHREXd3d0JDQykvL6etrQ1jY2M6Ozu5fPkybm5uTJo0CY1Gw82bN2ltbcXFxYWAgADR3LygoIC//e1v3Lp1C7Vazfnz57GysrpjkVev11NWVoZer8fDw4Pg4GAcHR0xGAz/3g3aSy//hdwVwd3IyIjPPvtMTCEUFBTg7u5OeXk5AOXl5VRXV/M///M/FBcXi5USzz33HJs3bwZuGywLgkBqairvvfceu3btwszMDEdHR3FBUq/Xc/nyZS5evMi5c+dob2/H29ubrKwsMjMz+eKLLwAYP348NTU1NDQ0IJFIGDBgADY2NuIIPSMjg9jYWBoaGsTKjLNnzzJmzBhKS0tJT0/Hzs6OwMBAysrKkMvllJeX4+npiUajISsri08++YSXX36Zzs5OsrKyftVqsLm5GYlEIio/9qSYxo0bx8mTJ1mwYAHp6enA7RH6xYsXMTMzExeqZTIZXV1dXL16FSMjI4qLi39xfwaDgatXr+Lr64uFhYXY0PTD8ke9Xk9dXR0WFhZ89NFHzJw5E0tLSyQSCffeey8rV65k9OjRREdHs2PHDhoaGli3bh22traYm5vz6KOPsnz5cjZs2MDs2bP59ttvaWtro7q6Gn9/f0xMTHBycsLBwYGwsDCqq6tFbaHq6mpSU1OJj4/HysqKqVOnitVKPaSmprJhwwb0ej1NTU2UlJTQ3d1NcnLyn2rt2EsvdwN3RXDX6/Vi+V5oaCh1dXWUlJSQnZ2NnZ0dnp6eTJ48mSeeeEIUpurbty9JSUkkJyczadIkli9fzvnz59m5cyfd3d00Njbi7e1NTEyMGJA6Ojo4cuQIjz32GIMGDUIikWBmZsaECROwtrZmwoQJbN26VUyxFBcX4+XlRVJSEq+88gpBQUEYDAYiIyOJiYmhtLSU+fPn09DQwIwZMyguLuaRRx4hJSUFqVRKZmamKBa2dOlSFi1aRGxsLEVFRSiVSpycnFAqlYwaNUpc5Pw5XF1df9JGTy6X4+bmxuzZs1mxYgVTp05l8ODB5OXlUV9fT319vTjatrW1xc/PDxMTE44dO/aLuuY916azs5OHHnqI0NBQhgwZcsfIvauriz179nD06FHkcrmYyoLbD+zQ0FAefPBBhg8fjlQqZfHixRgbG4vv0SMCNmDAAKZMmYKLiwtFRUW4ubmJ2v4HDhygu7ub0NBQQkJC6OzsZOTIkeTn54tdyPHx8RgbG/Phhx/S1tYmHkOPfPLNmzfR6XTY29vj6OjId999x5YtW3p9VXv5S3NXLKhKpVIUCgWBgYHs2rWLvn37YmxsTEtLC6GhocTGxlJTU4OVlRWxsbEMHz6c8PBw+vXrx/nz51EqlZw6dYrr16+LDkXz5s3jk08+ERtjpFIpSqUSuVxOXV0dx48fx9XVlfr6eqKiovj6669xcnKisbGRU6dO8fe//x1bW1uqqqoYNGgQBw8exMvLi9jYWD766COee+457rnnHjw9PdmwYQOPPPIImzZtQqVS8fLLL5Oamsqrr77KvHnzsLOzu8NS7oUXXmDJkiV0dXVhZGT0q4H9t9CjqCkIAgUFBTg5OREdHX2HTaHBYCAuLo6zZ8+SmppKXV2dWH//r0gkEurr62lqaiI8PJypU6diMBgoKChALpcjk8lwdHQUre9+7j0cHBy45557GDNmjJjGEgQBS0tLjIyMMDU1JSEhQRyxW1paYmtry/Xr13F0dOTBBx+kpaWF2bNn09HRgVQqZe/evSgUCtGFS6VSkZ+fzxNPPCHK+QqCQHFxMQ0NDWi1Wurr65kwYQIREREcPXoUJyen3+yB20sv/43cFcHd1NSUyspKDhw4QJ8+fQgMDKSgoIDAwECamprQ6/UsWbIEMzMzsZNx+/bttLa20rdvX9555x0eeughrl27JgaMa9eucfLkSXQ6HefOnWPFihWoVCqee+450YD6s88+o1+/flhaWhIQEEB7eztNTU2MHTuWQ4cO8dprr9Ha2sqAAQP46KOPaGlp4b777mPkyJEYDAbReenZZ5/FzMyM+fPnI5PJRB9XtVqNpaXlj85XKpXi7Oz8p1zL2tpaTpw4wT/+8Q90Op0ovQu3UzuJiYmkpqaiUCh+Mbh3dXVx4cIF0c+2rKyM8+fPc/r0aWxsbIiPj0etVosLyr+EUqlEqVSi1+vFzmFHR0dRmuHWrVu4ublhZWWFlZUVp06dwtzcnMjISIqKili4cCGff/45JSUlovhafX09O3bsYMyYMWJ6qE+fPuKxtLa28u2334oPhClTplBTU8OQIUOYOnUq9vb2vYG9l780d0VaBqCqqko0yR42bBh1dXVirvWTTz7h7NmzSKVS5HI5UqmUuLg4Fi5cyEMPPURSUhLl5eUYDAa6urpoamqiu7sbe3t7vLy87ngwWFtbExwcjEqlYtGiRVRUVODq6kppaSn9+/dn7ty59O3bF71ezzfffCPKEfdou3/00UcYGxuj0WjEEsGwsDAkEgk2NjYUFRWJM4WfSqP8VgwGAzqd7o7UQc/D5JfoWSw2MTHBwsJC1IMpKyujuLiY4OBg1Go1Pj4+pKen/+ziokKh4L333mPy5MnExcVRU1NDe3u7mL8+fPgwr732GuXl5b85vaHX6zl8+DBr1qxhzpw5TJgwgQceeECsdDl37hwXLlygsvK2v0tdXR2bNm3i2Wef5YUXXmDz5s1i56uLiwvW1tYkJiaKchE9OfceDX61Wo2FhQU3b95k48aNoj9vYmIizc3NvQurvfyluSuCu0wmY/z48SxZsgQnJyfWr19PSUkJu3btIicnh/vvv5933nmHp59+mn379pGbm8vjjz/OsWPHSEtLQ6VS0b9/f6ytrfHw8MDIyIjS0lIkEgkRERFit+nx48cxGAzMmDFDrC65//77UavVVFZWkpCQgMFg4Ny5czg5OXH69GmOHTvGE088gcFg4OmnnyY0NBSpVEpTUxMHDhxAJpPR3NyMm5sbMpmM+vp6Pv74Y/bt2ycGqd9Damoq69evp729ncuXL9PR0cGVK1e4ceMGGo2GiooKOjo6frQw2JNzrqurQ6+/LaWvVquprq5mz549NDQ0kJWVRWJiIvX19bS0tPzk/iUSCTExMcjlcjo7O0X/0lOnTnH58mXCw8NZsmQJO3fuFPXofw5BELh58yb5+fn079+fpUuXotVqaW1tFWWZz507hyAIzJ07l+joaAoLC9mxY4eoH/Too48SGBhInz59MDU1xdvbm6CgIBYtWsS2bduorq5m8+bNPProo+zfv5+XXnqJTZs2ce+992JkZIRaraampoaDBw/y7bffMmTIEA4dOkRJSQkajeZ3f0699HK3clcE97a2NoyMjHByckIikaBQKBg2bBgNDQ2cP38eMzMzSktLSUtL47PPPuP69esMGjSIixcvsmPHDvbv34+VlRUDBgxgxYoVuLu7M2nSJLy9vcV9mJqaigYeOp2OS5cuMXjwYFGfZfDgwRQXF+Ph4UF0dDSjR4/m5ZdfRqvVMnfuXMLCwnB0dOSll15i4cKFaDQaqqqqOHbsGC0tLVhaWhIXFyd2eebk5ODo6PgLZ/3L9OvXj4ULF7J7927Wrl3LwYMHaW9vR6vV8u2333Lt2jUuXLgg1uz3YGlpiUKhICcnR0w7CIJAW1sbzs7OHDx4kMbGRmpra6murv5FpceeuvuMjAw+/fRTurq6GDVqFG+//TajRo0iLi6O2bNn/6x3a89Mau/evaxbt46ioiLc3d25evUqarUaW1tb7OzscHBwYNiwYSxcuJCgoCDgts58ZGQkMpkMMzMzbty4QXd3N8bGxuJCcHNzM9nZ2VRVVfHss88yZ84cKisr2bt3L/v37yc8PByZTMa8efN46623iIyMJC8vT1zkXrZsGUOGDBHLUnvp5a/EXZFzVygUVFRU0NjYyNChQ7l69SqBgYFUV1czduxYiouLxe5EDw8PdDod3377Lfb29ixfvpxPPvmEFStWkJCQgFKpZPLkybz00kvY2tqKqYyEhAQGDhyIIAhs3LiRzs5OPv30UzIyMnj++edxd3fnzJkzfPfdd8TFxeHg4EBMTAwjR468I2/dc7yzZ89mx44dSKVSdu7ciVKpxMjICB8fH8rKyti2bRuxsbEMHjz4VxdMKyoqsLa2viPQGhkZYWlpyYwZM4iIiMDExISysjIyMjJwdXUlOzubJUuW/Cg463Q61Go1NjY21NTUiHo9WVlZ7N27F2dnZ5555hmUSiXh4eGiPO8v4e3tTUBAAAqFgk8//VRsfBIEAVdX1x+9Xq/Xc+bMGdF4u8cndvXq1axYsYJr166h0WgYP348gwYNwsLCgpKSEszMzER54+PHj6NQKAgODqapqQlPT09MTU05duwYycnJvPPOO7S0tJCZmcnrr7/OsGHD+Pbbb/Hy8uLatWsEBwcTFhbGwIED8ff3Z8qUKSiVSoqKisjPz2f37t10dnaKXb0NDQ3Y2dn96rXo5f9HEASys7NJT0+npqYGZ2dnZs6c+aOO517+M9wVwd3W1pbIyEiuXbuGm5sbbW1tnD17liFDhpCTk8Ply5f5xz/+gbu7O1u3bhVHbn5+fly9epWioiJeeOEFWltbsbOzY+nSpSxfvpzQ0FAWLVqEpaUlly5don///hgMBp544gnc3NzIy8sjJiaGe+65h88//xwPDw+amppE4TCJRPKTNnU94mPXr1+nqqqKmpoaURUyLi6OZ599FhsbGxISEqitrWXevHm/aHd38uRJFAoFs2bNuuNLIZFIsLCwwM/PT0yfNDc3Y21tjbOzM3V1daJJRw9tbW2kpqbi5uaGqakper2e69evI5PJsLW1Zdq0aURFReHq6oqdnd1v+hKGh4ezfv36O5yX4PbI/P3332f69On4+PiI2/V6PWfPnqWuro6nnnqKBQsWYGpqSnh4OBqNRjxunU5HVVUVtbW1HD9+nKFDh9LV1cXNmzfx9PQkPT2dBx98kHXr1nHlyhUWL15Mc3MzgwcPJiIigpSUFPz8/Bg/fjz79u3j66+/ZtGiRSQlJYkSww0NDcyePVt8iPn4+ODo6MjBgwextrbG3d2drq6u3vz776DHhObChQscOHCAN954g/Xr19O3b18GDBjwmwYOvfx5/BYPVXfgG8AZMAAbBUH4QCKR2AI7AC+gGJglCELT93/zArAY0APLBEE4/kv7kEqlREVF4efnx/Xr1zl69Cg2NjZcvnyZpKQkbGxsePXVV7GzsyMzM5PBgwczbdo0/P398fT0pKamhm3btmFlZYVarebSpUuUlpaKzk4ymYz58+dTV1eHm5sbY8aMISsri/DwcOLi4rCysmLy5Mns27cPtVpNU1MTKpWKtrY2lEqlqMXyQ3oeMD3qk+PHjxfb/s+dO0ddXR2TJ0/GwcFBrPD5OeLi4mhqavrZ3/cYcwcGBpKeno5eryc6OvonFQ9bW1sJDAwkICAAgBs3bojH/+WXX+Lq6npHgP6t9JQY/hC9Xo+/v784ezAYDOTm5tLV1YW/vz8rVqygsLAQW1tbgoODKS8vJy0tjbCwMAYMGMDhw4dF8w6ZTEZZWRk+Pj7o9Xq0Wi2TJk0iJyeHN998k40bNxIUFER+fj6nTp1CpVLh5uZGTEwMq1ev5vPPPycmJobPP/+ckJAQXFxcKCgoYPjw4eL59nQ1r127lr59+xIUFISNjQ3W1ta/yUy8l9vXUKPRcOjQIbZv3859993HO++8g5mZGbm5uVhZWXHlyhVKS0txd3dn4MCBvUH+P8Rv+ZbrgGcFQUiRSCQWwHWJRHISuB84LQjCWxKJ5HngeWClRCIJBuYAIYALcEoikQT8mlG2kZER8fHx9O3bl8cffxw7OzsEQSA9PZ2NGzdSVVXFV199xdGjRzl48CCVlZWcPn2akSNHMnLkSAICAsjNzaW0tBSdTodMJsPe3h43NzdWrVrFiy++KE67e/xJx48fL5paeHp6snXrVtFUWqVSkZ6ejo+Pz09+8aVSKcXFxfj5+dHZ2UlhYSEjR47kscceQ6lUsmbNGtLT05kzZw7GxsaidoxOpyMxMRGDwYC3t7e4MPhL9ARqgD59+iAIAra2tj/50OnJwTs7O5ORkUFUVJQoAWxhYfGHTZcFQaC1tZX+/fuLaws9UsQrVqxg0aJFWFlZ4eTkhLe3N0eOHKG+vp6goCAGDRpEdHQ0+/fvp7S0lOvXr3PfffdRVFSEnZ0dgwcPRiKRsHbtWuB2BZCzszONjY088MADZGdn4+PjwzvvvMOBAwe4evUqQUFBhISEoFKpuHHjBufOnaN///6sXbuWhQsXEhISgsFg4KuvvqK8vJzIyEhRKnrUqFG/aiT+f53W1lYSExO5evUqp0+fZty4cdTU1JCZmcmYMWPYvn07paWlonLnzp07WbBgAevXr+eRRx75xcFNL38Ov8Uguwqo+v7/2yQSSQ7gCtwDDP/+ZV8D54CV32/fLgiCGiiSSCQFQAxw+ef2oVarGTFihKhh8oN9iw0qq1evxt3dnaVLl7Jw4UJqamq4cOECOTk5WFhYsGTJElGlsbOzE2dnZzEAtbS0/CinWldXx7Jly9izZw8eHh7I5fI7TB0aGxtJT08XA+m/otPpUCqVWFpaEh8fj0Kh4I033iA9PZ1Ro0aJM4Yet6SUlBRcXV05fPgwp0+fFmWIN2zY8JNBuocePfauri7MzMzo16/fz742OzsbQRBQKBSig1GPYXRERASenp4/OhdBEOjo6KCsrAy1Wi2Kk/0SgiCg1WrZtWsXly5dYtWqVXh4eCCVSgkJCeHee+9l6NChSCQSHB0deeaZZ3BwcKC1tZXOzk7KysowMjJi0qRJTJo0SVxgvXTpEoWFhRgZGbFkyRKCg4N56623WLBgAZ6enhw8eBB7e3tRNK2oqIjy8nImTJjAyJEj2blzJ9OmTWPMmDF89NFHVFZWcv36dbq7uxk9erSYArp+/Tpz587F3NycqKio3sD+K7S2tvLaa6+xY8cOamtrGTBgAJcvXyYrK4uamhpOnjzJyJEj2bJliyinvXTpUjo6OigoKGDz5s2MGzdOlKz+11RiL38O/9b8XCKReAH9gCuA0/eBH0EQqiQSSU9piCuQ9IM/K/9+27++11JgKdxWZ+z5gvWMur9/DT4+PuzevRtXV1fxhlAoFHh5eeHl5UVtbS16vZ7a2loxH93a2kp1dTXnz5/H1NSU9PR0tm3bhru7O42NjcBtyd01a9b8rPSrUqnk2LFjKJVKoqOjxbrznimmRqOhb9++JCcn09DQgFQqJSwsjKtXr3LkyBH69etHaGgoX375pfg3paWltLa2MmfOHE6dOsWYMWPuCCyCIIiNRz3bDxw4gK+vL8eOHePZZ58VhbEMBgNZWVl4e3uL9fT29vbiKHbDhg0sXbqU5ORk2tvbSUtLQ6/X/+SDKjMzkxUrVlBbW8vp06dxcXH5xS+fIAio1WpUKhW+vr4kJiZib2+PhYUFCoWCJ554Qnxdc3Mzvr6+REdHc+PGDTo6OqiqquLMmTO88MILeHp6EhISQktLizjbyMzMpKuri8LCQjw9PdmzZw+TJk1izZo1+Pn5ceXKFTo7O3nhhRfYtWsXxcXFHD9+nP79+7NkyRLkcjmXL18mNzcXU1NTkpKS2L17NwsWLBAN1SdMmNAbYH4DBoOBDRs24O/vj0ajQa1Wk5GRQXd3N46OjrS3t/Pggw9iYWHBQw89xIoVK5gwYQLt7e188cUXvP322zzzzDO88MILaLVafH19efTRR7n//vt/cVDTy/+e3xzcJRKJOfAd8JQgCK2/8MX4qV/8qMtFEISNwEYAFxcXAW7ncKurq+8IuFKpFHd39589LkdHR9G8YdOmTWi1WrF6xcrKisLCQmpqati/fz/u7u60t7dTW1vLggULkEqltLS0oFarRZXHHoqKimhpaRFb+hsaGnjrrbcYPHgw48eP58iRIwwbNowdO3Zw+fJl5s2bx9atW3F0dCQsLIyysjJSUlIwMzNDpVJx+vRpxo4dS1NTE5aWlkybNu2OACMIArdu3SI9PR1XV1fCw8PvkGSoqamhpKRETOFotVrUarUoadzT6j9r1iza2toIDQ1l/fr1BAQEEBYWRt++fX+2GzUxMZHS0lImTpxIfX39z76uh+7ubs6ePSu2+EdGRv5o2q3T6SgpKSElJQWDwUB7ezv9+/cnNTWVwMBAzp07h4eHBxYWFsDtnP60adOYPHkyGRkZdHR0iNLNN27cYODAgSxYsICMjAxRi/+9996jrKyMpqYm1Go1//znP7G2tkYQBGJiYujTpw/5+fmUlJQwZswYjh07xpNPPsnChQt7A/tvRKvVYm5ujk6nQyKRsGDBAszMzETLw3vuuYeEhASsra3x9PRk6NChbN26FUEQMDU15c033xSb6tLT09FqtWzZsoXg4GDi4uJ6P4c/kd80H5VIJMbcDuxbBUHY8/3mGolEovr+9yqg9vvt5cAPo7Eb8IvdPD2ldTKZ7HeZKEgkEszNzbGzs+PQoUPU1NSI6o3r1q0jKCiIFStWMHjwYDw9PXnkkUc4evQoq1atorOzEysrqzu6SfV6PSUlJfTp0we5XE5HRwd2dnZMnTqViIgIZDIZN2/eZNmyZbi7u+Pn54dUKqW7u5tt27bR0dFBVFQUEomE/Px8FAoFEyZMICsri6KiIvLy8ggMDLxj5NLc3Mw///lPVq5cybfffkteXh4SiYTw8HD69OmDmZkZ2dnZ6HQ6DAYDxsbGollGbm6ueB3MzMywsLDAYDAwcuRIXF1dmTBhAm5ubnfMEgoKCsSRdF1dHX379sXDw4Ovv/6aq1evUlFR8aPO054UTkZGBkVFRaJsQ8+56PV68T+dTkdjYyOBgYF0d3dz/PhxZDIZmzZt4sqVKwwePPhn74V+/frR2trKmTNnUCqVdHZ20tTUhKurKzY2NjQ2NorCYQ8++CBOTk7Ex8ffoZg5cuRIDh8+jFwup62tDalUynvvvccDDzzwuxaU/y8hCALl5eW0t7dTXV3NzZs3kcvlGBsbs3z5cl555RX69+9PdXU18fHxbNiwgccee4x58+axf/9+bG1tsba25uzZs5w4cYKKigra29vp6uri1q1bGBsb8/777/P111+LjXa9/PH8lmoZCfAFkCMIwvs/+NUBYBHw1vf/7v/B9m8lEsn73F5Q9Qeu/tI+FArFj3RQ/h2Sk5NZuXIlOTk5tLS0YGFhQXt7O9OmTaOqqoqkpCQqKyvp27cvhYWFDBkyhLCwMDw8PMjIyGDs2LF37LegoID9+/cjl8uprKzk888/Z+jQoURHR4tB9YUXXqCxsZGysjJOnTpFe3s7kyZN4uTJk3zwwQf4+fmxatUqBg4cKOrQlJaW4u/vT2hoqOip2lOGp1AocHR0xMfHR7Tx67GWs7GxobKykqqqKq5cuYJWqxWVMbOysn6Uh1coFDz55JMAP1niZzAY2LJlC/Pnz+fAgQPY2NgQHR2Ng4MDeXl5LF++HE9PT7766qs7AmFnZycvvvgiWq2WNWvWcPnyZSZOnIifnx/vv/8+NjY2NDc34+rqiqmpKVlZWSxfvpx3330XV1dXPv74Y6qqqggKCsLExIT8/HwGDRr0o+MTBIH9+/ezefNmWltb2bJlC9XV1eTl5dHd3c2tW7fYuXMnsbGxHDp0CE9PT5544gn8/f3F8zt79iyTJk3ixo0bzJw5k3Hjxv1quqmX29d+3759LF++nNjYWNEGsX///uIi982bN8nOzhYb6h577DGOHz9OV1eX2K08atQoIiIiaGho4NChQ+L3IzIykq1bt6JSqfjoo4/w8/P72Qd9L/87fssQZhBwH5AhkUjSvt/2d24H9Z0SiWQxUArMBBAEIUsikewEsrldafP4r1XKSKVSLl++zKBBg8TR5W/NxwmCIEoEW1tbo1KpkEql+Pn5MW3aNMaPH09xcTFNTU3s3LmTmpoatm7dir29PZmZmahUKrG9XqPRcPLkSdzc3NBqtezZs4dx48ZRV1fHBx98wMsvv4y9vT1DhgzBysqKd955hxs3bnDixAkSEhKYMWMGf//73/nss89obm6mpaUFc3NzKisrcXBwYO7cuVy5coX29naOHTtGREQEubm5WFhY4O/vz/PPP8/OnTv59ttvSU5OpqqqCjs7O8zMzFi6dCk3btzg2rVr9O3bF09PTxobG5FIJHdU08D/31kK/ORiYWNjI1KplK+//prc3FxeeuklUWo5Pj6ehIQEtFotRkZGdHV10dDQgKurK2VlZUilUry8vEhPT8fCwgIHBwc6Ozs5evQoISEhXLp0iYiICIYOHUpRURE1NTXcuHGDxYsXU1VVhVarZciQIcjlcsaOHfuTn6nBYKC5uRkrKytcXFx4++23yc/PJy0tjddee42Ghgb69u0r9kJMnToVPz8/8X44fvw4J0+eJCoqCr1ezwMPPPC7Bw7/16ivrycpKQk/Pz+srKzw9fXF2dmZZcuWIZfLSUtLIzU1lejoaKRSKW+99RYDBw5Er9cjl8uZNm0aDg4OFBYWsm/fPlauXEliYiJWVla8++67eHh4MGHCBFavXs3ChQtJS0sjMjLyDpOVXv4Yfku1zEV+Oo8OMOpn/uZ14PV/50B6NFF6xMN+a3DX6XSigqSZmRn19fVigO+pUw8PDxc13vft20daWhoDBgygoKCA1atXU19fz/Dhw3nttddQKBRip2l3dzc7d+5k+vTp2NvbU1lZSXx8vLjab2FhwaBBgzhy5IhY5tjW1sbw4cMZMGAAarWaCxcuoFAoUKlUDBkyBH9/f65cuSJqmjg7O1NTUyNqlet0OgICAsjKyqKyspJr165hYWFBcHAwZ86coV+/fsycORONRiMaW/8SPamVnsDW0tLCxYsXxYXW6upqCgsLkUqlrFy5kn79+vHkk09iZmaGwWBg3759XLx4kYULF/LFF1+IdeNKpRJPT0+USqVYjXT9+nXi4+NJSUnh/PnzODg4IJfLWb58OQ0NDYSGhmJubs6lS5d4+umnf/LB02O4cvr0aby8vHjwwQdFEbiIiAjuv/9+jh8/jr+/PwUFBRgbG/Pdd9/dYeBdW1uLm5sbq1ev5vHHH+8N7L8Rg8HAl19+SUtLC66uriQnJxMZGYmfn5/4Wfv5+SEIAh9//DHp6ek899xzpKamkpCQgLe3N7GxsbS0tDBlyhQeeeQRNmzYwPDhw/Hy8qKqqgoPDw/69u3Lww8/zMGDBzE1NeXIkSPce++9vZ/RH8xdkXzU6/VMnDjxjhHnb6VnlDZ58mSKioooKyvj6tWr+Pj48N133zFr1iwUCgVlZWWsXLkSY2Nj5s2bx9q1azE3NycsLIyEhAT27t3LlStX8Pb2xsXFhZCQEMLCwkhMTOTw4cM8/fTTXLlyhaioKIYPHy4uYhoMBgYPHoy1tTWXLl3i6tWrzJs3j23btiGXy2lqasLJyYl58+aJpYG3bt3i5s2bnDhxAhMTE6ZPn87NmzfJyMigtbWVoUOH4uvrS3h4OFlZWXR2dmJkZMTDDz/MmDFjsLS0RKvV8uabb/6kYfgPaWtrQ6PRiObbcrmc1NRU5s2bx7Vr1zA3NyctLY0RI0agUCj45JNP8PHxYe7cuSQmJtKvXz8EQWDLli0oFAquXbvG448/jo+Pj/hZmZmZ8eyzz5KamoqPjw85OTliM5VGoyE/P58LFy7w3HPPYW9vz5dffskDDzzAk08+yYwZM0hNTRW7ZfV6PefOncPS0pJJkyaJXaYLFy6ks7OTkpISjIyMqKurE0eJSUlJODg40NLSQmVlJW+88Qaenp78/e9/58CBAzz00EN3LJb38tMYDAYSEhLQ6XSiumZPWiUuLo4dO3YwdepUHnvsMdLS0vjyyy/p6urizTffRK1Wc//995Oamsr06dNFdc+KigpmzZolqn92dnaSl5eHj48PbW1txMfHs3nzZmJjY3tNy/9g7org/q/m0P8OMTExNDY2kp2dTWxsLGPHjhXTIklJSaxYsQIzMzP27dsn+mkKgsDYsWPJyclBoVBw8eJFOjo6sLW1xcrKCqVSSVNTE0FBQeh0OhoaGvD29mbgwIFs3ryZb775hmnTpnHPPfdgMBjYu3cv1tbWREZGsnDhQrKzs+nXrx+TJ0/m9OnTd7go9SgQNjY2Eh4eLkrztrS0IAgCe/bswcXFheXLlxMVFYWpqSlNTU1cvHiRmJgY0eRCLpf/Jk34a9euoVKpaG1txd3dHblczj//+U/RE7ampoZHH30UKysr1q9fT1FRERqNBr1ez9GjR4mLi2Ps2LEcOHCAESNGUFdXJ5qPCIIgLu4uWLCAmJgYPvzwQ1xcXDh48CAXL15EpVJxzz33UFBQwAsvvMDAgQPx8PDAxcVFbP6qr6/n+eefJyYmhjFjxrB06VKeeeYZsrKyUCgUdHd3U1NTg7W1Nf7+/kRFRZGdnQ3cLi8dOXIkXl5e6PV6Vq9eTWdnJ08++aSohfNTmvq9/BiZTMbMmTN54403xMo1jUaDm5sb+fn5rFq1igEDBhAaGsquXbtITk5GIpGIiqE3b97kwIEDuLu7s2PHDrFqyWAwcOrUKaZNm8Y333zD559/zpYtW/Dz8+PBBx/kySef5P333+edd97pLY/8jfSIAf4Sd0Vw7+7u/lEqRhAE9Hq9OKX+ucDv6OiIq6sra9asIS4uDr1ez/3338/BgwdxcnLizJkzwG0TC29vb8rKyuju7sbCwoLAwEBkMhljxowhOjqa8ePHs3v3bsaPH4+Liwuff/45I0eOFKV/g4ODsbW1ZezYsaKWirGxMbNmzeKhhx5i1KhRxMTE0NLSQlNTE7t37+b+++9ny5Yt5OTkEBsbi0KhICIigg0bNiAIAv369SMsLIzTp0/T2tpKdHQ0paWlJCcnExAQQEdHB5WVlaJ88L/bcNPTIFRfX8/TTz+Nr68vEomEhoYG2traiIuLw8vLSyyldHBwQBAEurq6SElJERufPv/8c+C2umbPIuu1a9coKytj+vTpop69ra0tgYGB2NrakpqailQqJSgoiAkTJogyxeHh4eJaw7vvvktQUBAzZsxAIpFgbW2Nk5MTRkZGxMbGilVUAQEB2NvbExwczPXr17l16xbW1taiWFxmZibl5eW0trbyxRdfsHXrVm7dusVTTz3FjBkz/r0b8v8gBoMBvV5PVFSUOOPq6OhgwoQJfPDBByxcuFA0Qj979ixnz56lT58+mJiY4ODggIuLCwqFgvnz5+Pk5ER5eTlyuZyHHnoIBwcHsTzSzMyM/Px84uPjaWxsRKfT4eLiQmZmJt3d3b0NTt/TE/969K1+eE00Gg3vvvsue/fu/cX3uCuCe89ouoeekVpPt2lUVBTOzs6Ym5uLZh0/VEPUarVYW1uTlJREY2Mjjo6OlJeX09DQIKoBGgwGXFxc2L59O2fOnMHa2horKysEQaCzsxODwYCrqyvLly9HJpNRWlpKUFAQW7duFQ0fTExMSEtLEzVpeh4Sw4cPJzAwkEuXLuHi4kJZWRmTJ09my5YtlJWV0b9/f3x9fdFqtRgbGxMYGCha11laWlJZWUlubi6WlpaYmppia2srpkwsLS2pqKggLi6O0NDQn72G/5pb7+zsFNUhe2YIPxT3cnR05Mknn8TPz+9H2h8SiUSsTx8+fLhYavqv+9u2bRsA9957L1lZWfj4+GBtbY2ZmRmbNm0iPDwcd3d3du3axYULF8SpuK+vLx0dHSxZsoRdu3axefNmVq5cyYQJE/D09LzDkhBup5Lee+89PvjgAzIzM0lOTqawsJDm5maCg4NxdnbGzMyM4uJiXnrpJUxMTHjnnXd48803e3VNfoWeRrPNmzezfft2Ojs7ycjIICwsDDs7OzZv3kx3d7c467t48SKXL1/m3Xff5cyZM7z77rssWbKE8PBw7O3tOX36NBqNBhsbG+RyOadPn2bKlCnk5OSIA62mpiY8PDyIjY1FpVJRVlbGuXPnuOeee1izZg1hYWH/4avyn6enImzq1Kmi5EhjYyMWFhYcPnyY1atXM2DAgF98j7siuP8QvV7PCy+8QEVFhVha+OabbxIUFMTMmTPFE37ooYfEFXaFQkFmZqZoH9evXz/Gjx8vaq1nZGRQV1fH3/72NwIDA7lw4QKxsbH069cPlUqFSqVi37597N27l7q6OgYMGEB9fT1vvPEGNjY2jBw5Ent7e06ePImPjw8lJSXiAwNuB6Ge1MeYMWP44IMP2LBhA6+++irt7e0YGRlhZWWFRqNBJpPh6urKF198QXV1tViK6OPjQ1JSElFRUchkMnx9fREEAUdHR5YvX862bdtEYw61Wo1er79DSri+vp7q6mrxAXD48GFef/11vvjiC4KDg39U2y2VSgkODr5j2w9nS97e3qxcuRK5XE5paekd0gw9r+3u7iY/Px+DwYC/vz95eXnY2tqSnJyMhYUF586dY9asWVy4cIFx48YxZswYCgoKkEqlTJ48Gblcjq2tLTExMVRXVxMQEPCT03IjIyN0Oh3Nzc0cOnSIhoYG5HK5KDiWlpZGREQECxcupKKiAqlUypUrVyguLv7Zipxebpfh7t+/X5TtSE9PB257Anz88cfMnj2bxsZGVCoVBw4cID8/n4KCAnx8fMjOzhYb/8aNG8f58+cpLCzkwIEDmJub4+TkRGxsLNu3b6exsZHCwkL8/PyYOHEin3zyCa6urvj5+VFTU8OwYcOQyWRcvHiRvLy8/xPBXRAEMjMz7zDL8fHxERsIXV1deeKJJ8SUoiAI5ObmEhMTQ2dnJxKJhIkTJ3Ls2LGf3cddE9z1ej1qtRq1Wo23tzcdHR189dVX2Nvb889//pOWlhZ2795Nv379SExM5NatW1hYWPD8888TGxvLF198wXPPPUdhYSFVVVV0d3cTFRWFVqulublZNOXYs2cPUqmUmpoanJycqKmpoW/fvpSVlfH3v/+dqVOncv78efR6PYWFheh0Ol577TVcXFwYOnQoRkZGDB48GKlUKjYutba2ipoutbW1WFhYkJCQQFVVFQD5+fkYGRmhVCpJTk7G29sba2trfH19CQsLY9OmTbz22mvY29tz9uxZsc69oKCAfv368eWXXzJjxgwxQNfV1ZGbm8vo0aPF69djdlJRUYGLiws2NjY89dRTog77byEtLY2PPvqI0aNHM2/ePJydnfnkk0+IiIj4UXA3MjJi8eLFfPbZZ9y6dQutVsuSJUsYN24cKSkpjBgxQixN/fjjjzExMcHIyIjIyEgAUQ/+k08+QaVSIZFI7gjsWq2W5ORk+vfvj1wux9/fny+++IK33nqLdevWodPpOH36NI8//ji+vr6cP3+exx9/nKqqKt555x0CAwMZMWLEzxqJ9AKXLl3ijTfeYPr06chkMsLCwkhLS0Or1bJixQqxSem5557jvvvuIyAggBEjRnD69GkOHjyImZkZra2trF+/HgcHB0pKSnB1dSUtLQ2DwUBLSwt6vZ7jx49jZWWFXC4Xv6tlZWWEhISQnZ1NTU0Ntra22NjYEBERISpK/qfTM/+aTegp9/yhPEoPOp2O7u5u1Go1bW1ttLe34+Pjg0Kh+MnzMBgMPPPMM5w9exa4vd6xdu1a0XBeoVDc8b2VSCS4urpy+fJlvv32W4YOHUp+fv4vHv9dE9x1Oh21tbebXKurq4mKisLb25vc3FxOnDiBl5cX5ubm1NbWEhAQwJdffomPjw++vr54e3uTlZUl5gp7LtJ9992Hra0tERERvPTSSzQ2NuLp6UlDQwNdXV1cunSJqKgoOjs7MTU1pbW1ldzcXGpqavDz88PHx4fKykqys7MZN24cVVVVpKamkpWVxZkzZxgyZAjFxcWsXbsWDw8PnnnmGTIyMsjJyaGpqQkTExOqqqrEUadSqaSuro7i4mKGDBmCk5MTY8eOZdSoUchkMrGMb8OGDdjZ2eHk5ERISAj29vZ3BD65XE5OTg6jRo26o2KlqalJ7PYdOXIk8O/l6JubmzEzMxNvXqlUymOPPfajm9NgMFBfX8/evXs5e/YsMpmMGTNmEB4ejpmZGR0dHbS0tODg4EBQUBCmpqbi3/6rXv3PSUs0Nzfz1Vdf4evrK6pOSqVSpk+fzvHjx0lMTMTDwwNTU1P8/f1FsbaUlBSWL1/OyJEjMTY2/o8HiLsZMzMz4uPjuXHjBh4eHjQ3NzN79my2bt1Kbm4uvr6+okRyXV0dgwcPZvfu3Vy5cgWDwUC/fv1wcHAQR6ADBgzg6NGjuLq6snjxYg4fPkxdXZ2Y+lSr1axatYrq6mq8vLw4fPgw7e3tFBcXY25uzoQJEzhx4gSbNm3ivffeE9VB/5Ncv36dlpYW6uvr6erqEn16o6OjRUVZQNQs0mq1dHR00NXVxfDhw3n55ZeJjo7+0Xm0tLSwbNkyFi1aBNzWhYqLi7vjNR0dHZiYmCCTycjOzuaVV17h2LFj6HQ6Pv74Y4qKin7x2O+a4C6Xy/H29qa7u5vy8nIAVCoVxsbG4ij88OHDFBYWMmXKFLG0UBAE1q5dy9WrV8Xc/ZIlSzAYDLz55ptYWVnx3HPPMX/+fC5cuICjoyNBQUHExMTg5OREZ2cnr7zyCk899ZSYx21sbKSpqYlFixbR3t5OVlYWZmZmXL9+nYiICJqamtBqtSQkJNDV1YWtrS329vZiK7xEIhFz8jdu3ECr1YrOTOvWrWPy5Ml0dXXdMTIwGAx0dHSwbt06rKysMDY2Zv369URGRv4oVWFvb8+sWbPu2PZTT/ofUl9fj1qtxsXFBa1Wi0wm+1HgHzp0KAMGDLhj+7/uu7GxkYaGBu6//37Mzc3F2czevXsRBAETExPq6+uZPHkyEyZMwMrK6nfcDbfvh6VLl+Lg4CD2PvR01vZ8hlZWVty6dYv6+npxvWLEiBFMmjTpF3PtPaqW+fn5+Pn5cerUKVFYzdPTk+nTp4trDAaDgdbWVvR6PTY2Nn8ZBUm1Ws2+ffvEZrjc3Fz+9re/8dZbbzFy5Eg+/PBD9u7dy0svvURaWproOJaYmIiLiwuVlZViTfsTTzzBpk2b6OzsxNvbGx8fH8LCwjA3N+fmzZvU1dWh0WhIS0sT95+UlIS7uzv19fXY2NhgZmbGwYMHWbVqFY6OjiQkJPzHOlc1Gg3vvPMO1dXV4rbTp09TUlIi/jxr1ixsbW0pKSkhKipKVMD8IT3raD+kp8RUEASGDx+Oubm5+F3t8THoWUA9fPgwBw4cYPz48axbt47r168Dtx/Ka9eu/VUZjbsiuPfYq8HtC1tbW0tlZSVNTU1MnjyZK1euIJfLGTJkCHl5eWRlZbFw4UI++ugjioqKiImJobS0VFxsTUlJYdKkSZw7d46KigpKS0tFedce3Ze8vDxCQ0MxGAzcc889JCcnEx8fT2dnJ6NGjRKNoSUSCZMmTaK1tZXhw4eTn5+PmZkZ48eP5+DBg4SFheHj40NzczMGg4ExY8ZQWVkpjrzHjRvH22+/zcyZM/Hy8mLAgAFkZ2dTWlrKCy+8gEwm44MPPsDV1ZV7772XZ555Bj8/P2xsbAgJCfnJICWRSHBycvq3rrFer+fpp59m7dq12NjY/OSN0ZNq+il6bsj6+nqkUin33HMP58+fZ8GCBaLmTFdXFx988AHt7e14eXkRHBz8u4Ohubm5KKvw1ltvceLECbq6usjNzUWtVvPCCy/Q3t5OYWEhzs7OhIaGMmjQINGo/OfoWUCsqqpCqVSyePFiTE1NqaioELt/fX196du3L2ZmZpw6dYrr169TVFSEs7MzCxcuxMHBASsrq//4qPJ/Q3NzM9u3b+e1115Dr9fj6urK2rVrcXBwYPv27aJ/wsqVK2lra+PSpUucOXMGqVRKfHw8hw4d4urVq0ybNo1z587R0NDAhg0b0Ov19O/fn+vXr5OXl4der0cqlWJtbY2Pj4+4UD969Gjs7e1pamqisrKSv/3tb2zfvp2DBw8ya9YsZDLZHSqs/y/ouTdMTEyYMGGCaMgjCAIZGRloNBp0Oh1lZWVieqanYig0NJR33nmHiooKdu7ciUajwdLS8g7tHIPBwD//+U/S09PZvHkzFy5cYNSoUeLMtri4WNThOXToEIMHD2bZsmUAfPDBB+h0OvLy8li1ahVGRka/agt5VwR3tVotlkI2NDTQ3NzMI488wkMPPcStW7fQ6/Vs3LgRLy8vTExMsLa2pqCggO7ubiorKwkMDMTHx4fExERkMhkajYbjx4+LdaCbN29mxIgRODg4YGNjw5UrVzAyMuLs2bPo9Xrc3NxEo4958+YBt1NDSUlJ+Pj4iFOj1NRUrKysSExMJDo6mpEjR3Lz5k1effVVxo0bh1Qqxc3NjZaWFmbMmEF9fT1KpZIZM2ag0WhobW1l2rRp4pdFp9OxZ88evL29SUhIYO7cuTzyyCN/yujQ0dGRp556Cmtr69/V6i0IAu+88w59+vRBqVTy7LPPIggCN27coKmpicGDB7Nv3z4uXbrEpEmTRJvC30vPNejq6uLgwYNiYxTcLscMDAwkKSmJ/Px8ioqKsLa2ZtKkSWJa6ufoqYHvaWry9PSkra2NzMxMcYEvKyuLlStXir61Y8eOxczMDCsrKxYuXIhOp2PZsmVMmjQJGxubH1Uq/Tdgb29PTEwMBQUFWFpa8s033+Dg4MDMmTOxsbHhzJkzLF68mPj4eCorK9m/fz9hYWHcunWLL7/8EoDz58+TnZ1NW1sbKpUKU1NTUUrA3d1drIOPioriH//4B6WlpQQEBIj17++++y4jR46ksrKSnTt34ufnx+bNm/Hx8cHZ2fn/qcBbT7f21KlTsbKy4sUXXxTXmXpmpKNGjcLY2JjKykpGjBiBl5eX+Pd+fn48++yzaDQalixZQkFBAXPmzGHChAnMmTOHcePGoVKp2LRpE7W1tRw7dozZs2ej1+tpbW3FwsJCrAhcsWIFhw4dwsnJiYaGBtGlrampierqampqahg5ciSXL/+sRQZwlwT3H5ZCCoKAlZWV2HJvYmJCSUkJpqam5OTkMG7cOOLj4/nwww+ZN28e7e3tmJmZUVdXR2BgIF5eXqLKoYmJCRcvXuTGjRvs2rWLKVOmUFNTQ1lZGa+//jpVVVUUFhZSXl7OokWLOH36NKWlpTg6OlJUVERrayuZmZlERESg1WpxdHQkPz+f4uJibt26hZubG6dOnaKjo4PvvvuO4cOH09raSt++fTE3NxenmX369KGtrU3snHV1dSU0NBRra2suXLiApaUlkydPRqPRiAuPvxedTifWGPfUi8PtwDNw4MDf/b4SiYQZM2aIC5nDhw/n2WefJTExkYMHD/L1118TEhKChYUFHR0deHp6/iHBrrW1FSMjIzGw99j62dvbi2WVTU1NKJVK1q1bh6WlJffccw8qleoOGWKtVkteXh579+7l6tWrdHV1sWjRIhQKBQcOHGDYsGE4OzuLUgpqtRpLS0scHR3RarUcPXqUjRs34ujoyLPPPktCQgJWVlaMGjWK8vJyUlJSiI+PF/Xy7/ZA35MGdHJy4vjx47i5ubFixQrmzJlDbW0tLS0tTJw4EalUSkREBEZGRhQWFtLd3U1ERAQtLS2UlJSg1WpxdXVl7NixHDp0iNmzZyOTybCxsUGv19Pe3s5bb73FO++8w8aNG5k/fz5Xr15l+PDhmJqakpmZiU6nIycnB1dXV7q6uvjwww/54osvfnYhsrOzE0EQMDIywmAw3DHz/yV6YkzP9+xfa8evXLmCRqMhOTmZ0tLSO2JSW1sbx48fFz/f5ubmO9KqBQUFvPrqqzQ2NpKRkYFarcbY2JimpiaSkpLo6uri6tWrYr/KihUruHDhAu7u7uK60quvvkpeXh61tbXI5XJ27txJY2PjHemhHrZs2fKrceKuCO4/9Cm1s7OjpqaG9evXs2DBAnHRU6/XM3z4cBISEli/fr1o0DFq1Ciqq6uZOHEiGzZsICQkhICAAE6cOMG8efOora1FrVaLo4kxY8Zw/vx5tm/fTlBQEBKJhPvuu4/U1FTy8/OJiIjAxMSEyZMnk5qaSl1dHdeuXcPIyAgXFxemTZvGgQMH6Nu3L05OTuTk5IjOTz03Xn19vWgY0t3dzbJly6itrUWlUlFVVYVcLhdLFj09PcVGntraWqZMmYJMJhM1bv5d8vLyWLx4MW5ubmzcuPEP8waVSCSiOcrgwYPFvOCgQYMwMTHhwIED1NfXM3DgQKKion4kF/x7qampEUv0FAoFL774otjs8uabb/Loo4+Sm5vL6tWr8ff3Z+vWrSxevJgnnniCqVOnAre/nG+++SYffvghr7zyCi4uLpSUlJCZmUlCQgJNTU2EhYVhMBiYPHkyGzZsIDQ0lL59+3L+/HkUCgVz5szh4MGDDB06lO7uboYNG8ann37Kxo0b6dOnDzY2NixatIhBgwbx7LPP3vW2cteuXcPDwwNnZ2cqKiowMTHB2NhYLBb4+uuveffdd/Hy8hLXnzIzM0lJSSE6OppLl/4/9t46zMqqbf//7JjuZDqYHhhi6G7pflBKMFERECzgUcQmLAQFFaRbVESkpXOAIWaYLqa7e8f6/THu9WVgKOvl/R3veRxzwOy5953rXnFd53WeZ1EoFHh4ePDxxx/z0ksvUV5eTlVVFRcuXGDRokXS50CtVuPk5ERoaCjHjh2jrKwMPz8/Jk6cyMmTJ2nZsiXHjh0jKysLJycnAgICmlQLhYbBftOmTXLFGBUVxQ8//ECrVq3ue82HDx9m/fr12NjY8PXXXzfq3M3MzGjVqhVjx47l9OnTvP322zIsA0jdJ0Pc/auvvuL48ePy7zk5OURERMh27+DgwKJFi+jRowfm5uZ3uKhlZmby448/Sg/o3NxcGY+HhhWroQq7KdTX1zeq9WkKj0TnrlQqqaysxMLCAktLS7p168bOnTv58MMPpUTvzZs32bx5M48//jiFhYWcPXuW1atXEx4ejr29PQcOHMDHx0cq0vXu3VsuwY8ePSqlc0+ePIlWq6Vdu3acPXuW4OBgUlJSiIyMRKVSUVlZSW1tLeHh4Vy9ehV3d3fKy8slO6SkpISJEydy4cIFSktLsbS0pFevXpiamvL111+zdOlS5s+fj5GREefPNxhSvfXWWwwYMAA7OztatmxJUFAQxsbG0jDaxcWF3377jU6dOmFsbExFRUUjhsnDwCCT0Lp1a6AhAZqamoqJiclfioFDQ/Y+LS0NR0dH+WIY9Ne3b99Ojx49sLa2lqGsvwKDWcqhQ4fQ6/W0a9eOgQMHUltbS2xsLJWVlRw8eJDIyEhGjhxJUFAQtra2zJgxgylTpqDT6WQVbFRUFEePHsXPzw+1Wk3v3r3x9vYmJSVFWhNmZ2czb948NBoNY8eO5ebNm5w+fRoLCwsyMzMJCwuTWistWrRgxYoVtG/fnlWrVnHmzBmqq6uxtbXF19f3bxvY/ilUVFRInZgXX3yRqqoqvLy8+OKLL+Q7BLBmzRrGjRtHhw4dUKvVNG/enKeffprz58/L+3bt2jW+/fZb3N3dSU9P54033mDgwIHs2LGD9PR0Nm/ejE6nIzY2lg4dOsjZ6549ezAyMuL06dMAuLm58dhjj5GYmEhOTg5RUVFYWFhQUVGBs7MzarWaoqIicnNziYuLo6KigmvXrnHz5k1Z/3E/tGvXjqKiIrKzs3nhhRfkc7KwsJDMs7q6Onx8fFCpVFIqBBomTQYXN2hwL4uOjpa/G1h5BtTU1DBnzhwGDx4sq+Fvl98uKCigoKDg4R4eDbmxzp07k5ycTFVV1V23eyQ6d4PeeV1dHcbGxvj6+lJZWck333xD8+bNqaysJCkpiSlTpmBkZMSQIUOIi4ujqqqKvXv3cu3aNezt7TE2Nmbfvn1ShsDZ2Zm6ujqys7NJS0vj8ccfp7i4mOLiYtnZpaamsmrVKmpra1m5ciW//PILAQEBmJmZ0alTJ3bv3s2UKVP44osv6NChA+Hh4SxatIiKigqMjIzo0aMHa9euxdHRkc8//xwnJyfMzc1xcnLilVdekdWTo0aNwsLColGCyMzMDBcXF/bv309ISAhmZmaYmJj8JfnTxMREhBAMHToUOzs70tPTWb9+PW3btuX69euMHDnyviP+3WBtbX1HVZxerycjI4OcnBx+/vlnOnbsSLdu3dBqtX+pg7e2tubVV1/lwoULDBw4kPr6esLCwqipqSEnJ4dVq1ZJH1tDnBQaVhg2NjZoNBqefvppbGxs2LFjBy4uLqxZs4YLFy7IRHZycjLOzs5s376diooKvL29sbGxoWXLluzatYvz589LSmVqaiqDBw+WPq1Xr14lMTERIyMjqqqqCAoKkhLJK1eupH///mi1Wlq1avWX9FKEELL47e/SXdFqtZw4cUKytkxNTenatStPPfWUXBUJIUhISGDAgAFkZWURGRlJREQEN2/e5NKlS3JflpaWZGRk4OzsLA1brl69Sl1dHTNnzuTLL7/kwoUL1NXVERkZiaurK127dmXlypVotVoZV/b09GTdunX0799f5r6cnZ0pLi7G09OTgIAArl+/Tnp6ugzLQMPk4sKFC2zbtk1+9sQTT0gzEYOY360DbkZGBj/++KP83djYmJMnT0rzG4Mm/b1gYOoZUFxc3GQMfOfOnUBDjsMQWnyQfRuKMW/cuIGVlRWZmZnyeCqViilTpvDRR/cW3n0kOnedTkdhYSE2NjYcO3aM48ePU1dXx88//8zu3bvZv38/V69excLCgjNnzuDr64uTkxP29vacP3+eV155RToEGRsbc/z4cYqLi2WH361bN5m1jo2N5cqVKwwaNIgJEyaQkJBAQkKCVI40jLDHjx8nPz+fw4cPM27cOIyNjUlJSSElJYXc3FxcXV0RQsgcQFBQEOnp6YSHh0v6k4ODA9OnT7/rdZuZmTF06FBqa2tJS0sjNjb2L3eKgYGBvPnmmzg4OFBaWio12ouKiqRUbocOHe76/YdJDgohOHnyJCtXrqS8vJwRI0Zw7tw5rl+/ztKlSxtV0D7IvgzHFUJga2vLW2+9xbBhwzh9+jRPPfUUQUFBLF26lPz8fNzc3CgoKECj0fDOO+9w6tQphgwZQkBAAKamplRWVpKamiot3tq0aUPHjh3p06cPKpVKcuyfeOIJnJ2dadWqlXxuxcXFfP3114SGhjJo0CCcnZ2pqqrCxsaG9evXk5aWRlxcHDExMYwcOZIjR44AEBISQlJSEtu2bWPhwoU0a9aM06dPPzSz6VYY+NCff/65VPb8qzh//jxVVVW4ubkxZcoUmRzXaDTMnz+fli1bMmnSJEaPHg00JONbtmxJZmYmZ8+eRaVS4evri6+vL++//z4KhYKff/5ZFjLV1dXRvn17AgMDSUlJoa6uDrVajV6vx9vbmwsXLqDT6VCr1VJNct++fTg5OTFy5EgmTJhARUWFTCQWFBQQGRkJcIcMhlarZe7cudTU1MjP9u/fj729PQkJCVRUVEinNANu77xvp2neDwY9naysrAf+TmFh4QNt17VrV9zd3WVIMDg4mPDwcDZt2iQJIpaWlmg0GmbOnMkbb7xx1309Ep27Xq8nPj4eHx8fKbJleMEPHz4sDZP37NlDdnY2V65cYdKkSbRo0YKjR4+yfv16nnnmGd5++20KCwuZPXs2U6ZMoX379iQkJGBpaYlarebUqVNkZWUxduxYnn76aTZu3Ii/vz9jx45FqVSyd+9ehgwZQo8ePXjzzTepqamhU6dO5OTk0K9fP7Zt20azZs1o3bo1dnZ2dOzYUS7FDS5KDwOD/V7r1q1JT08nNDSUgwcP0rNnzzv44QZpgPsxCG7lu9va2hIeHk51dTWXLl2ic+fO9y3tLigooKioiJCQkAe6BrVaTadOnUhISECv13P58mVmzZr1ULH+qqoq9u3bR9++fTlw4ABxcXFkZGRQU1NDv379cHJyIjExkUmTJhEbG4uFhQXW1tbU19ej0Wi4fPky169fZ926dTIRb8h9vPjii7Ro0YIpU6ZgbW3daNAyJP7GjRsHNNzjEydO4OXlha2tLd26deP69evodDrGjh1LTU0NSqVS6hYZGxvj4eFBfX09GRkZvPXWW7z88ssy6Ttnzpz7SjIbYDBQuf25V1ZWcvHixTuW9OXl5cTHx8tB0TDhuR8MtQKtWrUiNTWVDh06oNVqWbhwIYcOHaKyshJLS8tG+7Kzs+Ptt99m8ODBzJs3j6SkJB577DE++eQTLC0tSU9Px8zMjNLSUmbMmEFqaioKhYKYmBhJr33jjTf4/vvvOX/+PEZGRnh4eBAcHMzIkSM5d+6cTNgXFRUxfvx4kpKSpBbNrXBycqK2thatVgs0TAZCQ0OlFy80TODi4+OBhnfAy8tLDg5Ao3DLn0F9ff1DdewPimbNmjF9+nS++eYbVqxYwfPPP49Wq2XSpEmMGTOGzMxMjh8/jk6n44MPPpA5pbvhkejcDb6bBmU4pVKJubk5OTk5LFmyBL1ez2OPPUZtba2crR06dIgxY8YQHR2Ns7MzgwYNIjU1le3bt5Ofn09eXh4qlQqlUsmPP/6Iubm5NHMwmCn369ePs2fPcuXKFby8vIiOjmbcuHHs2bMHlUpF//79cXJy4pdffqFZs2b069cPpVLJuXPn8PHx4bvvviM5OZm3336b8ePHPzR1y9DReHh44OHhgU6nIzQ0lLKyMvLz82nevDkqlYqamhqio6PRaDSEhYU1asj32399fT0KhQJfX1927NhBaWnpXaWCk5KSyM3NfeCZpoGBY21tTadOnbhw4QKPPfZYkxV598KVK1dYtmwZmzdv5syZM4wePRqFQsGNGzfw9fXFx8eH2NhYWW5dVVVFVVUVLi4uKJVKsrOz0Wg05OXlkZeXJ4tJjI2NKS8v59lnn8XBwaGRyig0dOa5ubk4ODjIATEvL4+qqiqUSiUbNmzg9ddfl9K3J0+epH379rLN2djYcPz4canbv3TpUqkIOmHCBAYPHiyrM01NTWW+48yZM43itba2tlL+2MvLS7JPTp48SVxcHEqlko0bN+Lm5sbgwYM5fPgw1dXVbNu2jQ4dOlBXV4eDg0MjzXqlUilXgM2bN8fU1BQTExNJRJg7dy779++nqKhI5hd0Oh329vYsW7aMyspKjh8/ztChQ7G0tJQSE3PmzOHgwYOMGDECIYQ0fA8LC2Pt2rV4e3uTlpZGly5d2L59u0xAbt68mZdffpnz589z5coV0tPTad++PR07duTjjz8mODiYNm3a8MUXX0ilVmdnZw4ePEhZWRkuLi7k5OTcUZUphGgUJrodpaWl99RfeRSgVCpxdHSke/fuXL16lVGjRuHs7Cz9IgwaMoYVT1lZGWVlZXz77bf33O+DeKiaAicBkz+23yWEWKhQKOyBHYAPkAY8LoQo+eM784FnAR0wSwhx8F7HKCkpYdOmTdjb21NQUIBarcbS0lJySg3FJEZGRtJrtbCwkFOnTmFnZ0dAQACWlpZS80WhUGBiYkJOTg59+/bFwcEBT09PysvLWbNmDZ6enri7u5OUlER2djaZmZmYm5vj4uLC6tWrqaiooKioCD8/PyIiIigtLWXq1KlUVVVx48YNoCEBZGlpyWOPPUZaWhorVqxg9OjRjbivD4rS0lI5q2zevDlarZZNmzaRk5NDixYtOH/+PGlpadjb2+Pt7f3AnTs0VHqamJhIpcR7hUrq6+sJDw9/qHCKQqGgRYsWqFSqP1VRWFtby9q1a2nTpg3m5uYEBgYSHBzMgQMHmDBhAr/++qs0a74dubm5dwwi5ubmVFdX4+7uTmBgIMeOHZPJ5WvXruHn5ydnx0qlEnt7+0bG2gMGDODs2bO4u7tz6NAhlEol7u7uGBkZkZSUhI+PDykpKfj4+ODs7My5c+coKSnB09MTY2NjbGxspAxEcXEx169fZ8GCBYSFhTFu3DjCw8PZtm0bX3/9tTznJ598ks8//5xjx46hUCgIDg6mqKiI77//nszMTOld+/rrr2NlZcX06dOxtbXlq6++kqytZ555hg0bNsh9tm/fnvnz57Nt2zbefvttqbn+9ddfc/HiRezs7Dh79iwZGRl4eHiwevVqPDw80Ov1ODo6UlBQIJVMAU6fPs23337LyJEjuXbtGq+99pos5Dp37hzLli1DqVQyZswYoqKi6NixY6NkX0ZGBikpKXTp0oWsrCwKCgq4du0ax44do6CggHbt2rF3715yc3MpKyuTFcf19fW0a9cOhUJBSUkJJiYmlJaWPnQ7e1RhZGTEmDFjaN68OStXrqRdu3Zs3bq1kU3miy++2Eg40MjISFZt3wsPMtWsA/oKISoVCoURcFqhUOwHxgC/CyEWKxSKecA8YK5CoQgFxgMtaDDIPqJQKALv5aNaV1fH2bNn8fT0lCwJgxmFkZERxsbGJCUl0b59e2xsbMjIyKCsrIzDhw+Tl5eHubk5n3zyCc7OzgwbNgwHBwf27duHm5sbOp2OX3/9lYSEBJ577jmaNWuGVqtl3bp1kiWg1Wq5evUqzZs3JzExkby8PAC2bNmCs7Mzer2e69ev88svv+Dq6oqTkxP79u3Dw8MDJycnfHx8GD9+/J8WqSorK8PMzIzr16/Log8D5U4IQU5ODr6+vsTHx5OVlYW7u/tDH8PIyKhRMtfA3TV0/sAdKpEGGBpRU0yb2wW/HhRCCMrKyti9ezdt27alqqqKq1evYmxsTGRkJE888QS5ubmYmpqycePGe+7nVgwZMkSWhBukn5VKJXV1dXh7eze6B4YV4q2wsbFBp9NRX1+Pv78/qamptGjRQlovZmZmEhgYiLOzM4cPH8bf358rV65QVVWFnZ0dw4YN47fffmPTpk0cPHgQIQT5+flcuXKF06dPy1DS7ffQxsaGHj16cOPGDQ4cOMDatWvRaDS89tpruLm5MWbMGD755BN5LUVFRcyZM4e1a9c2uRLz9fWVukk+Pj7Y2trK5b6RkRFnzpyRq8WAgACMjIwahRVbtGjBsWPHJGtr1KhR5OTkcPPmTSorKyksLMTLywudTse2bdsIDAzE29ubM2fO4OnpSVJSEomJiYSEhJCcnIxWqyU6Opq6ujqio6NltfPGjRuxtrZmz5498tj/+c9/sLKy4sknn+T111/H1dWV7777jqtXr/L888+zZs0aGY//347BgwcTHh7OO++8gxCCvn373hFeq6+v56mnniIsLIwPPviAl19+Ga1Wy4oVKyTbqCk8iIeqAAzTJqM/fgQwEuj9x+cbgOPA3D8+3y6EqANSFQpFEtARuGs5lYmJCZmZmVJTBhqoRLeP0OfPn5fMmtu/r1KpyMrKIioqSmb/y8rKePfdd7l58yZJSUm88847mJiY4OTkhLOzM5GRkWg0GlQqFdOmTWPWrFkytpuVlYVarcbFxYWMjAx27dqFVqslKioKX19fWch05coVRo8ezX/+8x/y8vIeOu4ODVx3IQSBgYHEx8fLTs3Ly0s6NRUXFxMeHv63yaEaZk7h4eEolcp7lnmfOnWKX3/9lalTpz7Q8aOiojA3N29kxXc7SkpKWL9+PWZmZuzdu5fMzEwSEhLw8fGhV69eeHt7c+XKFVq1asXJkycfmF54/vx5OnbsSIsWLTh06JAMNUBDJ1pbW3tPDR6FQkG/fv1Yv349hYWFUhArNzeXdevWkZiYiL29Pf7+/uTm5uLv7y85zM2bNycwMBBbW1t2795Neno6gCwVb9++Pf379+fQoUPs2rVLHvPAgQP07t2b1NRUCgoKZDwZYO7cufj7+zfpuhMXF8fjjz/OL7/8csf92bNnD5cuXaJNmzbExsbi4eHB7t27MTExYcSIERgZGREVFYWnpycffPABq1atumP/BmouNMS658+fz5kzZzAxMeG3337j559/pkePHpw8eZJnn32WS5cu4erqyqFDh+jRoweJiYkMGTKEa9euMWXKFKnD/+KLLxIQEICJiQkffPABgYGBUllVp9NRVFREjx49OH78OBqNBk9PT5ydnVEqlbRv357169c/UFt4VGGYVFRVVeHq6ipXlMnJyVy6dIkDBw5gZmYmQ4kpKSnU19eTk5PDV199ha2tLWq1mj59+khRvabwQEFihUKhAi4D/sDXQogLCoWimRAiB0AIkaNQKAxHcQfO3/L1zD8+u32f04BpwAOLS92q03Ar3NzcaNmypZzlnzlzhoqKCnbu3CkrwpycnGTl4cSJE7GysiI1NVUmxvz8/HB0dKSurk5avF29ehWlUklRURHW1tbSy/T69euYmJjQrl077O3tiY6O5uTJkyQnJ/PUU09ha2v7QNdz2/3AxsaGjh07SurbrSX4cXFxJCYmYmZm1kiN7q+gsrIStVrNgQMHGDx4sAxpGXRiDANsdHQ0ycnJd+XkarVaYmJicHBwQKVSSVGqV155pUmLu8LCQtLS0rC2tubkyZNy1mtnZ0dSUhIWFhbSALukpOS+HbutrS2VlZVotVoKCgro2rUrsbGxFBYWEhgYSE1NDRYWFlhYWBATE0NZWRmnTp0iKCgIBwcHXF1dJT3U4Hwzd+5cmYSuqamhqKiIs2fPynM9efIkqampGBsb8/TTT6NQKCgsLGTDhg2MHj26kdb/U089xeDBg2nWrBlqtVqyawwoKyvj7NmzTV5bbm5ukxWKBmRmZjJixIg7WCR1dXWkpqaSmprKzz//jEKhoEOHDgQHB5OYmIi7uzvx8fGkpKQQFBQkWUqG/I5hkLoVRkZGODs7S1/csrIycnNz6datGxUVFQwaNIi0tDSuXLnC0aNHJQ313XffZfz48fTt2xe9Xo+dnR1FRUUsWbIElUqFkZERM2bMwMfHh5s3b2JmZkZ8fDzR0dGYm5tz48YNQkND0Wg0nD9/XnodPCgD5VGDi4sL06ZNY926dZw8eZI+ffoQFhZGaGgoP/74I6dPn8bZ2ZkXX3wRR0dHbt68yW+//UZOTg6//PILJSUlrFq1Skql3A0P1Ln/EVJpo1AobIGfFQrF3S2BoKmp2h1vpxDiO+A7gODgYGHoWNRqNYWFhZiYmGBqakptba0U7DFAqVRia2tLSUkJHh4e9OzZk2+++QaVSsWuXbuIj4/n4sWLTJ06lfz8fC5evCjNINLT0zlx4gTFxcV4eXnJ2PyxY8dITExkx44d9O/fH2tra65fv45Wq0WlUjF06FAsLCwIDw/n3Xffxd7enj59+hAUFMQ333zDhAkTeOqpp1i5ciVz58596FDFrcm+26mQU6ZMITc3ly1btnDz5s07OneDl+ntdlz3guFenzx5UhZmTZw4EWtrazw9PTEzM2PRokVcvnwZBwcHWrduTXV1dZP7qqmpkQ72cXFxbN++nRkzZjSZGzCEFG7evClnIDdv3sTKykoutaOjo3nnnXfuy2pQKBRYW1tTWlqKlZUVFRUV1NXVkZubS2lpKU899RQjRoyQpea5ubkMGzaMdu3aUVZWhqWlJY8//jgjR45stF9TU1M6duxIp06dJDdZp9PRoUMHPD09iY+Px9XVleTkZHktubm59OvXj/DwcBYvXizvlRCCDRs28OuvvzJw4ECGDBnCY489xm+//Yarqys9evTA1NSUPXv2SAaGmZkZw4YNw9HRkbNnz5Keni6rFwMCAmjZsiW///47AQEBkgFmbGzcKMSk1Wob3T8TExMUCgUffvgh69evl+X9ixcvZsyYMZw6dYqCggLmzp3Ltm3b2Lt3byO/AGiQcPDw8CAgIIDAwEA++OADrly5wgsvvCClrA2DmsHpbMuWLYSHhyOEYPXq1YwbNw4PDw9SUlKkmF2rVq3YtGmTVFzt0KEDTk5OREVFkZeXR2xsLElJSQQGBpKVlUV9fT2LFy9m7ty5FBUV3bONPIqwsrLi2rVrtG7dml69emFhYYGbmxuzZ8/G1NQUlUpFTEwMc+bMAZBhU71eT1paGv7+/tI/4V54KHqHEKJUoVAcBwYBeQqFwvWPWbsrkP/HZpnArSLdHkD2vfZrYWHBd999R2VlJR4eHsTGxtKyZUtiY2O5du0a0dHR7N69W25vMIgOCAjgo48+YuDAgRgbGyOEoE2bNgQGBnL9+nUOHz6Mm5sb7u7uvP7663Tu3JmCggI2btyIkZERJ06coLS0VMa7DeYChoHGy8uLoKAgKioqsLOzQ6PRMHDgQA4fPszly5fJz88nNTVVLvX79etHbW3tw9xSAFng0bZt2yYrUw3SBzNmzLgjXqvRaNixYwe5ubm88sor8tzv1cnX19fzyy+/MG/ePLy8vOjduzeFhYVcuHCB9PR0Vq9ejampKf7+/jKnkJubK+2+DPs2UFgPHz7MsGHDsLKywsTERCbSbj8HjUbDp59+iru7O9u2bWP48OHs3LkTDw8PTE1N5crMwJ5yd3dHp9NRXFzcZEdviNvb29vTrl07Ll26hJ2dHQMHDqRnz57yXiiVSurr69m9ezc6nY4bN25I28Xu3bvfsXK89bwNK4/y8nIyMjJwdXWVs09nZ2eGDh3KunXrJOXv3Llzku9t2NeUKVOYNWuW1LY3VNfm5ORgY2ND586dOX36tDR36dWrF5s2bcLY2FiybwztKioqis2bNxMWFsaaNWt46aWXOH/+PO+//77U8IeGsMyGDRsYMWIEBw4coKqqCn9/fzIzM0lMTMTExIQhQ4bg4uLCggULSEhIwM3NTeYJzMzMyMnJkQlnrVZLbm4uTk5OTJ48GQcHB+rr6/nss8+kimlsbKwsFHR3d8fGxqaRhsugQYMwNjamvr6e06dPExoayuOPP87bb78tlRBLS0ulp3JRURGHDh0iIyOD1q1b4+PjQ01NjZQc8PPz+1/ZuRuolBqNRuYknJyccHd3JyUlBSMjI+nh0KlTJ6ytrWUtwLp16+jUqRP//e9/ZbHk3fAgbBknQPNHx24G9AeWAHuAqcDiP/795Y+v7AG2KhSKz2lIqAYAEfc6RmZmJk5OTpw5c4aWLVvi5eVFaGgo2dnZnD17FltbWzmLh4ZZSU5ODn5+fuzcuVN6jDo4OJCSkkJSUhJqtZpnnnmGX375RRYatWjRAmhIYhhmGevWrZPl02+++aY0gIiIiGDEiBFkZmayfft2zpw5w/jx42XF5OzZs+ncuTMRERF88MEHdOjQgevXrzN79uyHLvE3aFrfT3Lgds12aOj4hw0bRlJSkpytGXRC7nas8+fPU1BQwIQJEyguLqZZs2asX78eIyMj6X155swZzM3Nyc/PR6PRUFhYyMqVK3n77bdlCMBQmBIbG8vUqVOxtrbG0dFRhqxuhYGyZgi9KJVKzpw5I92rDGERS0tL6Wmbn5+PQqGQrIl73Zdnn32WF154gZ49e+Lg4HDHM6ipqSE0NFRS9YqLi3nppZcaFb8YoNVqKSwsJCMjg5YtW5Kdnc3x48dRKBRUVFQwcOBArKyssLS05Ny5c5ibmzNgwABWrlyJs7OzNDk3sG88PDyorKykpKQEV1dXLC0tWbx4MTqdjuzsbGpra3nppZewtrZGpVLRs2dP2Sna2tpia2tLXV0dZWVlODo68vHHH2NjY4O7uzsbNmzg8OHDjBkzptEzf+mll+Qs+rXXXuPTTz/FycmJpKQkHn/8cUpKSpg1axYLFizgp59+wtramhkzZlBcXIxOp6O2tpZLly7h4eGBsbEx27ZtIysriwEDBqDRaOjfvz8eHh588MEHdOvWjezsbMLCwvD09MTb27vJ5xQeHi7pyZ07d0alUqHRaEhPT+fo0aNMmDCBsLAwwsLCyMzMJCIigszMTFq1aoUQArVaTceOHamtreXgwXsS8B5pPPPMM0RERBAXF8fJkydZvXo1ffr0oVu3biQkJJCfn4+9vT39+vWjU6dOrFy5kpqaGg4cOICLiwtBQUEUFRU14u43hQeZubsCG/6IuyuBnUKIvQqF4hywU6FQPAukA+MAhBA3FArFTiAG0AIv34spAw2iPFZWVgwePBgbGxvpztOmTRtmzZrF1q1b6d27dyO+qpOTE+np6fTu3ZsJEyZw/Phxampq+PbbbwkMDCQzMxOVSsWrr74qhffffPNNgoKCZBGFmZkZr732Gjdv3iQ1NRWNRsPVq1c5duwYGzZsoFWrVpSWljJ8+HBcXV0JDg6murqap556Si6VPDw8aNu2Le3atZNhji5dusgS4gehFT4M+8VgtGGYDRm0sm+1r7sXDJ6uhhnPr7/+Sn5+Pl26dKG4uJh+/fqh1Wq5dOkSv/32Gx4eHmRlZXHixAnq6+uZM2cOVVVVJCcn06tXL0JDQ1m+fLk8JyMjI3r37n3HccvLy5k3bx7jx4/n999/JyQkhOzsbLy8vMjPz5f0QXd3d7RarUxGajQavLy86NKlC5cuXaKsrAytVotCoSAwMBBXV1cmTpzImDFj7in3a2VlRX19PT4+PmRlZdG/f39efPHFO3ICQggiIiJYu3YtFy9eZMKECRw6dIi+ffvSokULJk2ahF6vx8LCgk8++YS8vDy++uorduzYASDjxUIIjIyMWLhwoTRcufXcmjdvTm1tLU5OThgbG9/X69VABOjTp0+j/djY2NC7d+87BnMLCwvefPNN0tPTuXnzppTWtbOzo3379nz99dcsXLiQLVu2yDyTIb6t0+mkwqe5ubmsBSgsLKRTp06YmZlhb29Ps2bN5HX5+/tL/4O7wRBuFELg5eUlpW4tLS3R6/VERUVx5coVPDw8cHR0pLa2li+//JKAgACWL1+Or68vSqWS2bNnk5ycTFZW1gPryjwq6N27N0IIGSr+9NNPUalUWFtb8/TTT/Pss8/y7LPPEhgYyJNPPsm2bduwtLQkKSkJX19fjhw5IpOot1tf3o4HYctcB9o28XkR0O8u3/kIuLfwwS1wc3Nj586dzJw5s9ELmp6ezooVK3BycmrUsSuVSt544w3Gjx8v6ZJt27bl119/ZcKECTz++OPs379f2s3Z29vj5OSEl5eXDGsYQgAGDes1a9Zw9epVWV1oKJk+fvw4FhYWFBUV8eOPP9K8eXO5TDWEj0aPHs0vv/yCra2tLL0fP348Dg4OjBs37m/TBIGGmbejo+MdL/ODxto9PT0lhfPdd9+VlYTDhg2Ty2y9Xk99fT1btmzB1NQUIyMjrl+/LhuajY2NbGCGDv1+2LVrF+fOnZOiXzk5OaSnp+Pi4oJGo6GmpkZWOQoh5OCp0WhISkqSHP/s7GycnZ0RQtCsWTNWrFiBj4/Pfc9BqVTSrVs36ab18ssv37VewMbGhqNHj+Lm5iaT8KmpqbRs2ZKamhpKSkqoqqpi7NixODs7s3btWvR6Pd27d0er1cp7Y9h/WVlZk6sJU1PThxKIa+oZKxSKJq/DsK2bmxtCCJ566in27NmDvb09a9eu5fr161y4cEGaxIwbN47g4GB2796NjY0N1tbWZGRk4O/vj6urK9XV1WzevBknJydpnH77+SQkJBAWFvZAxXzXrl1jy5YtdO3alRYtWki6spubGxkZGWzdupVOnTrh5ORERkYGERERGBkZSTtJGxsbSZZ41GFmZiZF08rKymQfAg2rxE6dOlFRUcGXX37Ja6+9RnBwsNTa8fb2Zty4cbRq1YrIyEicnJzkff9fYdahUqkIDw+/4wXVarWSkmjQbg4ODpbx0/Hjx0vhpp07d0p97V27dlFaWkrvP5yTtFotgYGBGBkZMX/+fDw9PbGysmLy5MlUVFSwa9cuiouLsbW1ZdCgQTIOqlAosLe3l+a07du3l8pvGo0GjUaDQqGgY8eOtG7dml9//ZVdu3YxdepUVq9ejb29Pe7u7vTo0eNvu1eurq4yufZnNMNVKhVCCG7evCkZK0VFRQwZMoTIyEhqa2t57rnn5ItkQNu2bQkLC5OGvw+rf1NcXMyIESMoLy/n999/p6ioSHL4DTBUnjaFixcvStZMeXk59fX1MicTHBz8QOdga2vL22+/fc+chGEW6unpSU1NDfn5+QwZMoSKigqsra2l9EVVVRWDBw/mxo0bTJw4kU2bNlFeXo6npycajUZWVdfV1fHss8/y0UcfSZlngzHN34GmuPq3wsjICG9vbyIjI2VidsyYMVKqeuHChbRp04aAgACMjY0ZM2YMFRUVJCUlERISgkqlQqvVSm/QEydOEBsby1tvvdVIwlahUODn50dsbKz83r3ucd++fenZsyc6nY6qqiq6d++Ora0tWq0WV1dXabozb948xo0bR+/evfnxxx+JjY3lyJEjVFZW/mua+SYmJo3CgkIILCwssLe3JyMjo8nrMzMzY/DgwRQWFqJUKmV1u5eXlww1Dh8+XOa6pk2bRnR0NCtWrOCJJ57gww8/ZMCAAUycOFHajT722GMPFfJ9JDp3g3dlRUWFLCvX6XRyFqFUKvn+++/573//S25uLq1atcLZ2ZnCwkIcHByIjIzk4MGDODo6sn79erRaLe+99x5WVlb4+fnh7e0tZ+r+/v4cOHCAt956S2qLzJkzh6SkJCZMmIBCoaBLly7o9fo7Zie3ml2YmZkRHh4ONDzMrKwsjh07homJiRRcunDhwgMpzD0sbty48UD61XeDTqfjyJEjMrRy8uRJ3NzcpJZHU9RUY2PjPyVoJoQgKyuL8+fPy/uk1+sJCgoiMzNTFow9yH4MqK6uRq1WM27cOAYPHvxQ56NUKiUD6m6dg7GxMRMnTmTJkiV06NCB1q1bs2fPHkmJ9Pf3l9/19fVFq9UyZMgQ6cm6ceNGBgwYQPPmzbG2tiYnJ4c1a9bwxBNPyMKif9Omz9Dxvv3221KqeOvWrezZs4dWrVo1kkYwqGWuWrWKcePG0adPH2praxk6dCibN2+mbdu2JCcnk5KSQps2bRol16uqqrh+/brM4xgolnc7J0NhnampKYMGDZJ/MxSQ7dmzh1GjRtG8eXNatmwpQ0x1dXWNzDT+KpRKpYz/336OnTt35vHHH+fLL7/ExsaG4OBgysrKpDHL66+/LttEZWUlXl5e5ObmolKpyMzMJDY2ltGjR0uHqezsbFltP3HiRE6fPo1SqWTWrFlYW1vzzTffcPToUZYuXYq3t3ejhOnDTggUj4L2tLW1tfDz85OVdiEhIbRq1Yq33nqLsrIymWQ9ceIE+fn5KJVKyfOsra1l8+bN7N69m8mTJ/Pzzz9TW1vLnDlzSExMlKEeA4QQ1NbWYmJiglKpRKfTkZGRgbW1tSx2ub0i08CpdXJyQq/XS5aDTqejtLQUlUqFq6srBw4coFevXpibm5OXl0d8fLyMURr2ez8mi+F4hrhyU52QYaAqLS1tJNB1/Phx7OzsaN269T2PIYQgNTWV5ORkzpw5w9KlS3nzzTc5ceIEQ4YM4dVXX23UkGpqamSS0cvL66EaWVZWFsOHDyc2NhZTU1NZmNajRw9sbGzYu3fvA+/LAKVSybRp0/jss88eSioBGlZcZ8+eJSQk5J4FIIWFhXz88cfMnj1bMnvc3NwwMzO7w8XnVhi44tOmTaO2tpZhw4Zx5MgRjI2NefLJJ/nxxx/p3r07Xbt2xcXF5V8z9TAwkDZt2kTr1q1p2bIlR48eZdWqVQwfPpwpU6bIxPXBgwfJz89n7NixWFtbywExLi4OBwcHLl26hJ+fHyEhIWi1WtRqtTQRF0Kwdu1azMzMePnll//0AGZYtTs4OGBqasr27dtJT08nPj6ePXv2SIqq4Z26Vz92v7/36dOHwMBAfvnlF1lT0K1bN/R6PR06dKB///7Exsby4osvyhzEjh07iIiIoH///ly6dIm6ujq2bdsmjdxtbW3RaDSYmpoyffp0XFxc+OSTT0hLS8PPz49Ro0axfv16TE1NpUhf9+7dee6551CpVPdsm7dd22UhRPum/vZIzNwNiUxoeHFv3LjB+vXrJe9Zq9Xyww8/NJolHD58mClTppCRkcGXX37JyJEj6du3L8OGDSMlJQVoSCoZ4p0GGJZMBhhclG4dAJpa+hiollevXmX79u2MHz+eoKAgGYOurq4mJyeHrKwsfv75Zx5//HHMzMz49ddfcXNzo1u3bkRHR+Pj49NkYc+t0Ov1bNmyBYCpU6fe8XfDUtnA9MjJyUEIgb29/QPpzhg0bHx9fTEyMiI3N5fRo0fj5OREfn4+sbGxklmkUChkGEir1T50SMHOzo5vv/2Wzz77TCYdbW1tiYuLY+zYsQ+8n1sxdepU5s+f/9AdOzRw6G1tbbl27RoDBgy463YWFhbo9Xpu3LjBpEmTcHNze6AlsUHX6MUXXyQhIUGaXKSlpbFx40ZMTU358MMPcXFxkWYOhv0apK//ikTw3WBQyczNzcXd3Z0dO3awd+9eLl26xNChQykvL8fU1FTmDgxFdYZ3Tq1Wy7DS8OHDgQbvgJdffpnPP/+cZs2aMX/+fJYvX8748eOxtLT8SysTQ3W4YfDr168fhYWF2Nra0rJlSyoqKti3bx8JCQl4eHgADWqQSqUSKysrysrKgIa25uHhISuem4rTGyrO33jjDd544w169+7N/Pnz+fTTT4mJieGDDz5oVORnCLUaGxuzatUq1Go10dHRWFtbY2trS3JyMpaWlsyePZvy8nLOnDnDZ599xm+//UZ2djY5OTkMGTIEnU7Hjh07uHbtGrNnz2by5MnY2Nj8qXbd5D38W/byF2FkZCRpjkqlkry8vEYxruTkZBwcHAgODubMmTPyoev1er788kvs7e157rnn8Pb2RqlUEhMTw/bt25kyZcp9kw4P2hna2NgghKCqqgpTU1MSExMJDQ2V+7ewsKCmpob169czatQovLy8aNasGXV1dQQEBAAQFBT0QB2jgbaXlpZ2R7m8AWq1Gg8PDzQaDdbW1qSnpxMQEPDQol/du3eXBhzBwcFyhhcVFSVNrg336H6DEvy/mathyW1ubk779u1xcnLC29ubmzdvotfrG83iHxYBAQGSUfWwaNOmjSz6uhfMzMx49dVX/9TsWqVS0bVrV1xdXYmJiSE9PZ02bdpw/fp1du3aJX1mt2zZwsCBA9Hr9cTExJCUlCRF6tLT0/Hw8HigZPWDwNLSEjMzM6ytrVm5ciUdO3YkNzcXFxcXWrVqJZf/pqamUnFy0KBB95TTsLKyoqCggFmzZvHmm2+yYMECaWf5V6HX69m1axfjx4+noKCACxcuYGJiQuvWrWXea+TIkcTExGBubs727duBhuS1IRTq7u5Ofn4+Wq2WsWPHYmtry44dO/Dw8CAtLU1eQ8eOHVm+fDk+Pj5YWFgwdOhQjIyMyMjIYPLkyVhZWTUaqBQKhdSoSktL49133yUmJoaamhp27dqFEIL09HRyc3OllPN///tfsrOzGTBgAOfPn+fQoUOoVCreeecd/P398fPzw93d/W8N1T0SnfutuLUS1YDS0lJZ1WYouunVqxcxMTHs2bOHdu3aSTNoQ4IzKiqqke3V3wGFokHiNjExkb59+94hFKZUKrGzs2PdunVkZWXh5+dHz5495d8fRljMoBGfmppKYGCgHBRuf/i//fYb/v7+MiH2sFCr1XewG27cuIGjo+OfsuTLyclhwYIFvPDCC3To0IH6+np27tzJrl275JK3vLycwYMH07VrV3755ZcmueZNYdq0aZLd9GdfAkNY7EGu7X5Us7tBp9ORmprKpUuXUCgUZGRkyJoAU1NTsrKyKC0tZfDgwZSXl2NmZsbatWvZtWsXnp6eeHl5kZqayuOPP/7A0hx3Q0VFBXq9npSUFPz8/AgKCuLzzz/Hy8uLrKwsZsyYcccs29bWlkmTJt134pOQkICzszOTJk2Sua2/E/7+/iiVSs6ePStpqydPnsTc3ByFQkG7du0IDw8nKSmJzMxMfHx8OHr0KJGRkXKb999/n/fff59NmzYRFhZGmzZtaNasmfRW9vHxoaysDC8vLzw8PJg+fTojRozgxRdfpKioCCcnpyYNtb29vZk1axbnzp3j5MmThIeH8+WXX0qJEjMzM3bs2MGbb76JmZkZ69at48CBAxw/fpxhw4bRunVrYmJisLW1pWPHjnfIR/wdeOQ696bg4+ODqakpo0aN4sKFC0RHR/Pss8/i5+fHsmXL0Gg0fPvttzz//PM0a9YMS0tLXnnllX/kXJRKJaNGjcLOzu6O0byqqooWLVpw7tw5srOzH9jw4nZYWlpiaWkptW5SUlI4dOgQXbp0abI4KD8/H0tLSzw8PCguLpbFSH8Ghob+MLLCt+Knn35i/fr19O/fn+LiYlasWMGRI0fuKEJq1qwZffr0YcSIETJccz8YGxvzxhtvPNAK4n8SSqUSFxcXWrRoQXR0tJywtG3blh49epCUlERMTAwlJSV88cUXODs7c+jQIdzc3AgICODLL7/E1NSUSZMmyfzQnx3MlEoly5cvJy4ujk8++YTi4mJ69epFaWkplZWVLFy4kIKCAkJDQ1Gr1aSmpkqa6e0DYGRkJGq1mrCwMBnHnjBhAiNHjvzLg1BT592pUyegoWLX2dmZdu3aNfLvhYb2b2pqyrVr1zh9+rQMu5qamuLt7U1AQAB+fn7SgaxHjx4yPBUcHEy3bt2orq7m5MmTfPvttzg6OjJz5kzOnDlDbW0tM2bMYNeuXbJQ8dbjHjx4kG7duvHTTz/x/vvv4+PjQ3V1NW3atCEoKIiTJ0/y6quvYmxsTFhYGD4+PsyfPx+FokGn3XB9/xQe+c5doVDw9NNPY2Jiwv79+8nIyECn07Fnzx4CAgKYMmUKOTk5HD58+F8xJjbQI29HVFQUHh4eZGdn8/LLL+Pv74+1tfWfpiwCxMTEYGxszLVr16QlmQGGJWFZWVkjipVOp0Or1f7pzj0rKwsjI6MmO/f7WfBpNBp+++03Zs6cybJly4iMjGxyJQbIwW/KlCns3LnzgZ7d5cuXMTIy+tdYJn8WCoUCS0tLKQbVp08fHB0dUavVVFZWkpKSQkREhKSl/vbbb8THx9OnTx80Gg2+vr6YmpqSkpLC+vXrWbBggTTbuBUGazy1Wi0TkHZ2dlLwyyAZbWJiIlcB5eXlXLp0ifXr18v6AAPts7q6mv3797N582bmzJkjxdg6deoktX9uZW+4urqiVCr/8cG2srKSgoICzp07R1JS0h3S1Eqlkueffx43NzfCw8OZOXMmSqWSmTNn8uGHH5KQkCDrVjQaDVeuXAEaVplnzpwhLy8PrVbL2rVrgQa2WPPmzUlISKBLly6cO3eODRs2cP78ecaMGYO7uzt79uxhwYIFaLVaysvL8fb2Jj4+HhMTE7y8vAgPD+f48ePSyvCll17CyclJDph/Z+3L3fBId+5mZma4u7uzdu1aKioqpPu4SqXixx9/ZP78+UBDI5syZcr/2Hlev36dnJwcBg0axJo1axg6dCguLi4PxIy5FwIDA8nPz+fq1au0adOG4OBgGdNeuXIlKSkphIaGUlxcTHp6Ot7e3ri6uv6la7mbprsQgsjISKytrYmNjZU6IbdCp9NRUlJCcnKy5FTfDbfS7x4EarX6DoGv/w1QqVSN9NYtLS1p1apVIyqrhYUFhw4d4tixY9Jk2tjYmGbNmjFw4EDOnj2Li4sL7u7ujeSLMzIyOHjwIAqFgpCQEGbMmMG4ceN44403qK2tJS8vDz8/P2bPni0nB/369WPr1q18+OGHsjhPq9Vy5MgRfvjhByIiInjyySdRq9XExcXh7OxMUVERAwYMYMyYMXz22WeyTTdv3hw/P79//B6Wl5dTUVGBhYVFk6FQR0dHampqqKioYN26dTg6OuLq6kpBQQHXr1+XYSlDPD4+Pp7WrVtTWVnJli1bpN6NAQanI0dHR7755hsWL17M/v372bBhA507d8bW1paTJ0+Sm5uLn58fbm5unDp1ipCQEF577TUUigYDk4qKCiZOnMgLL7zwjyTJ74dHunOvra0lNTX1Dqlfg5hUcXHxfROm/wZqa2vZtGkTffr0Ydq0aZI+9ldhZGSEm5sbwcHBxMTE4O/vz9WrV8nOzpbFEwaVSIP2joHi+U/g6tWrUuDsboNWTU3NA9EbDSJtt3OLb0dwcDA5OTnU1NTQt2/fJpPL/9th4HIvXbqUX375Bb1ej4+PDx06dMDe3p6IiAi2bt3KjRs3cHJywsLCgm7duvHEE0/w3HPPyaKpo0ePSl308vJymjVrJum00JDzad68OT/88APHjx9n1KhRrFy5kjfeeANLS0vatWvH4MGDcXd3Z8uWLbRr145jx47x6aefkp+fz4YNG6iurmbFihVYW1s/tK3kn4WjoyN9+vQhMzOT3NzcO3wCDC5ZQ4YMIT09nccff5z8/Hxpuh0WFoaJiQldu3Zl7dq1uLm5MWHCBJycnJg0aVKjjt3Ozo6+ffuye/duiouLmTNnDgMGDKCiooKffvqJqVOnYmpqSnp6Ora2tmzZsoXKyko6d+5M9+7dGTNmDMbGxnTo0IG2bdvSp0+fu9pa/uMQQvyP/1hZWQkaZIEf+MfExERs2rRJaLVa8T8BjUYjysvLhRBCaLVaER0dLerq6kRtba3IzMwUFy5cEDk5OX/LsUpKSsSrr74q0tPTxaJFi0RCQoLYtm2bGDhwoNi1a5c4evSo2Ldvn9ixY4e4evWq0Ov1d92XXq+/59/vBo1GIzIyMkRZWdkd36+trRURERGisrJStGrV6oGeX3BwsCgqKhJfffXVPbebPn26ePbZZ4WFhYWIiIi477lrNJo/dX2PAqqrq8WaNWtEUFCQ8PPzE0VFRfJ5lZWViWvXrol9+/aJlJQUUVtbe9frfJhnnJycLDw9PQUghg4dKvr06SNcXFyEs7OzcHZ2Fmq1WgDCwsJCmJiYCLVaLQ4dOvR3XvZ9odfrRUREhFi0aJH46aefRGVl5R3b1NfXC61WK6/bcM9ycnLE2bNnRffu3cXkyZOFSqUSgLCxsREhISFCqVQ2am9z5swRUVFR4qWXXhKzZs0S4eHhYsWKFWLw4MFyG1tbW/HKK6+IJ554QuTk5IjNmzcLGxsb8eWXX4r6+nqh0WhEfX39v3JvgEviLv3qIz1zvxfq6uqYMWMGnp6e9OrV618/vkqlkkqGKpWKFi1aIITg6NGjaLVa9u3bx+jRo/+WUdvGxobRo0djZ2eHu7s7er2e//znP/To0QNLS0vi4+PZu3cvjz32GImJiTLh1RRyc3OxtraW534/GJxxqqqqOHbsGFOnTr0joXXo0CEpMmYQJDNImRpmRQb5CGiwcJs1axa2trb4+PjQp08fLl68iFqtvoMeWV1dTWxsrCxWs7W1xdfXV84aS0tLJR9br9dz7tw5Onfu/LdRCP9NmJmZ8cwzz9ClSxd++umnRhQ8a2vrO8I5BmRlZWFlZSVj3w8SCqyoqOCHH36gvr5e8rOjo6MpLCy8QwLCzMyM5557joyMDC5evChVGrOzs3Fzc/tHcyD5+fn88ssvVFdXEx8fT1xcHHl5ebi5udGlSxccHR1lIZVer6e4uBhjY2MsLCxQKBS4uLhw7Ngxzp4928iSzhB6MVyfUqlECMHGjRulw1Z+fj4vvfQS06dPl5TjPn36kJ+fj5GRkYy5f/HFF1RVVUlW1COTE7pbr/9v/lhYWDz0zN3w88UXX/wzQ+JfRH5+/j8yeqenp4uVK1cKvV4vCgoKxM6dO0VJSYkoKSn5248lhBA6nU5UVVXd9e81NTVi4sSJYu/evcLExEQ+FwcHB/l/hUIhDKszY2NjMX/+/Eb7LC8vF7///rtYs2ZNo+/d/uPg4CAOHDggNBqNqKurE5WVlY1ma9XV1aK6uvofuQ+PMmpqakRdXd1DfScjI0O4uLjImau/v7+cwd/+Y2JiIl5//XURFhYm3nzzTVFcXCx0Op3YtWuXSE5O/oeuqgH5+fni7bffFmZmZsLe3l60bNlSuLi4iDZt2ojhw4eL+fPnizFjxoipU6eK//znP8LHx0csXrxYLFmyREycOFEUFRWJ33//XXh5eTW6JqVSKfz9/YVSqRT29vbCyspKeHl5CVNTU2Fvby+6dOkiBg4cKFavXi0mTZokHBwchKmpqejZs6fw8fERL7/8svjxxx/Fpk2bRFBQkJg8ebLIy8v711eN/G+Zubds2ZKMjAwZN7wfDN6U/ya0Wi2lpaXodDqcnZ2bHKVTU1Ol4t7fKRoWFxfHxYsXOXDgAOPHj0ehUDBy5EiMjY1l6ff9Zg0PIoFgaBxKpfK+wlRlZWU0a9aMb775plHs8lYThVvPa8SIETz11FONYudWVlb06dOHTp06ER0dzbJly+44jkql4qOPPqJPnz4yOXh7texficc/qDTEo4iHUZY0wCCXsW3bNtLS0njsscdYtGgR0HCvmzVrRkBAAPb29gwfPpzHHnsMPz8/PDw8SEpKAhpWlGvXruW99977x9gfjo6O+Pr6YmJiwttvv83zzz9PUVERNjY2lJaWsn79ei5duoSxsTFJSUlSZtkgKFhQUCBXqrfKEKhUKhwcHEhNTZVEDSMjIzp37kxpaalkIS1atIj//ve/siL822+/lfTL+vp64uLi+P3337G3t8fU1PTRaj936/X/zR9fX1+xYMECkZWVJY4fPy6WL18uOnbsKGd93bp1E/b29nLUfeGFF0S/fv3Eq6+++o/NWO+GX375RUyYMEG89957Ijc3t9HfDLFOrVYrCgoKxMGDB++7v4eJj5aUlIiYmBgxb948sXPnTjFmzBixb98+odFoxIULF0R5ebncn16vF7W1tSIjI0OUlpYKnU4nTpw4IWbOnClSU1NFdXW12Lx5s0hLS2vyGvfs2fNA575r1y4xaNAgYWRkdNcZt42NjXB2dhaAGDt2rKivr7/rNS9btkwolUphbGwsBg0aJBQKhQCEkZGRiIiIeKD79LCIjY0Vhw4dEqdOnRJJSUn/yDH+Tuh0OhEdHS3zC0VFReLq1atCp9Pd9TtNtTO9Xi/q6+tFeXm50Gq14vTp02LRokXim2++EXl5eaKurk5+r6KiQuTm5ora2lqxc+dOcfnyZVFXVydOnDgh8vLy/rFrLSsrE99++63Yu3ev2Lhxo1izZo1YvHixOHXqlHj55ZfFrl27xJEjR8QTTzwhFAqF8PT0FBYWFjK2zi2rj7u1T8OPkZGRMDIyEkqlUrzzzjsiPj5eTJ8+XTg5OYlXX31VJCYmirKyMqHRaO56T/9t8KjP3O3t7XnvvfdQKBS4urrSs2dPmjdvzujRo+nSpQtGRkbSZ7CoqAh3d3e+/PJLjIyM/jFmSFPQ6/XExcXx/PPP4+7ujlKppLq6WtL6MjIySE5Opnfv3tjb2zcqemgK1dXVZGRk4OTk1CR3/lYI0cBpNniaWltb07ZtW6Kioujbty+tWrWisLCQ5ORkWrVqRUVFBZs2baJz587U1tZy5swZfvrpJ8LCwqQ5cWFhIWPHjkUIQUlJiTwHa2tr8vLyyMvLu+vqxAB/f3/KysoIDg4mPj6+ScckGxsbGZs9cuQIS5YsoU+fPnJmmJmZiYODA0IIHBwcsLOzk1IF4gFWcH8VRUVF2NnZERwc/Jdi9UI0CLK5u7s/VDXyw8JgFRgSEoJOp2PVqlWcOHGCGTNm0K9fvybzKQa7yokTJ8p3RqFQkJ+fT21tLc2bN6dbt25069btju9qtVq2bt1KWVkZTz31FBqNRspLdOvW7R97RuKPGXKPHj2kr+s333xDfHw8kydPJicnh06dOpGTkyPrBl555RUSExP57rvvGDNmDCdPnqSwsPC+ph52dnaMHj2aHTt20LNnT7777jsA+vbty7Fjx6TxjkFBEh7cQ+F/Co9E5w7/70YZ/m3dujVjx47lySefpLKyEk9PT0JDQ4mKiqKkpOQffXnuBT8/P2xsbPD396eiokI6yTs6OkqtjerqaiwsLJosJBKiQWHSwsICMzMzqTvzILC0tKR9+/YoFAqSkpIYOnQoJiYmXLx4kU6dOknVQoWiwTj6hRdeoLq6mvT0dMLDw+WSOjk5md9//50BAwZIBySDXyZAp06deOGFF9i+fTtbtmxpMiwjRAPfPjIykps3b/L+++8za9asOzp3d3d3hg8fzocffsi8efP49ttveeeddzA3N2flypWMGjWK69evs2/fPrKzszlw4ABWVlb07NmTpKQkevfuTUpKCsXFxY30YPLy8qRT0F+FQVvn75goaLXaO6i7fzfUajVjx46VNMc33niDcePG8dxzz9G1a9cmO3dzc3MCAwPRaDSNSum3bduGi4tLkxoyQghiY2M5efIka9euxdbWFp1Ox4IFC/jss89o2bLlP1qMo9FoWLFiBdHR0dJNKjc3lyFDhmBsbExOTo607evfvz+1tbWsXr1a1pjs379fPgsjIyNJu1Wr1Y28fgGcnZ35+eefqaqq4sKFCxQXF/P1118TFhbGiy++yIsvvoher5ceDv8rcLcp/e0/gAq4Auz943d74DCQ+Me/drdsOx9IAuKBgffbd1hYmKitrb1jyaHRaCTV0ZBANIQe/iyqqqpEfn7+PZewt0Kv18tlmOH3qqoqUVFRIb7//nuxdetWsXTpUlFYWCiEaFgy3+v8SkpKRP/+/cUbb7zR5DU/CHJzc8WVK1fEtm3bxKRJk5qkJxqOtWnTJvHee++J8+fPi379+okpU6aI2bNni7lz54r4+HiRlZUlcnJyGlHJ9u3bJ8LDw0VAQID46quvRFxcXKP919bWig0bNohu3brJcIyrq+sdtDL+CMmcO3dO1NbWin379skwi1KpFOvXrxfV1dVCp9OJY8eOSdodINzd3UV6errQ6/WipqZGlJeXNwqDabXaB36G/9PQ6/UiLS1NJCYm3pW6q9PpRGxsrIiOjhbFxcX3pbMa9lddXS3Ky8tFXFycSElJuWtitbS0VEyePFlMnz5dpKSkiLKyMnHu3DmxZMkSsXXr1iaPYUhEWlhYCB8fH2FsbCzs7OyEubm52LVr10Pfh/Ly8nsm55s6h7q6OnHy5EmRmZkpysrK7njmWq1W1NbWiurqanHq1Cnx1VdfiYSEBDF8+PBG7bBbt26N2pehHQJCpVI1+t3U1FQoFArh5OQkvv/++/8xuvWDgHuEZR6mc38V2HpL574UmPfH/+cBS/74fyhwDTABfIFkQHWvffv4+Iivv/76nheh0+nE5s2bxbhx48SWLVv+9M2Ij48XixYtEtevX3+g7evr6+/YVqfTibVr14pjx46JDRs2iHfeeUfk5+c/0P5+++03ERAQID788EORlZX10Od/KyoqKsR7770nkpKSZAedmJgoO8Hk5GTRvHlz4enpKVq3bi3Mzc2Ft7e3GDRokIiIiBAajUYkJSWJU6dOicmTJ4vZs2eLwsJCsXjxYvHTTz+J1NRUERcXJ3744YdGzJ/Y2Fjh7u4u2rRpI/r27StsbW1lhw2IkJAQyXdXKBRi3rx5ory8XEycOLHRC/fhhx+KK1euiE8++US0aNFCGBkZCTMzM6FSqYSRkZGYO3fu/1gHbsid/B0x1fr6ejFp0iTh4+MjPvroo0aTBQNqa2vF2bNnxd69e0V8fHyTx01PTxcLFiwQM2bMEF5eXsLKykp07txZvPPOO+L5559v1AY1Go1ITk4WycnJ4uuvvxabN28WSqVSuLq6ivT0dJGamipatGghkpOTmzwfvV4vxowZIwDh7e0trl27Jpo1ayaUSqWYM2eOKC4ufuj7sGzZMnHixImH+o7hOTzotob79tprr4kWLVqIF198Ufj7+zfqvA3t1NraWjRr1kwMGzZMdOjQQVhYWIiwsDDx3//+V0yePFksX778oQaj/wncq3N/oLCMQqHwAIbS4Iv66h8fjwR6//H/DcBxYO4fn28XQtQBqQqFIgnoCJy72/5NTEwoKCiQPpq3orq6WnJXR48eTVVV1QML2TeFgIAAZs+e/cDLSYOOdVVVleTD1tXV0a1bN8rKyujfvz+jR4+W2XMjIyPKy8sxNzentrYWS0tLdDqdXEJ36NCBoUOHsmHDBiZOnPinr8PwAAMCAigvLycnJ4fMzEy2bdtG69atmTJlCh4eHrRq1Yrz58+TmJiIkZERc+bMITY2luXLlzNs2DCOHz9OmzZtMDExoaioiKVLl7Jo0SIUCgVlZWW88cYbnDhxgpYtW0o7O5VKxQsvvMCQIUPw8vLihRdeIDIykueff55ffvmF7t274+HhwYIFC7C1tWXw4MHk5eWRnJzc6BqSkpL47LPP2LJlCzY2NqhUKqysrJg5cyYFBQW89NJL/+gSWIgG4xa1Wn1HrL20tJSvvvpKeosatr9VAkOv10slUmtra8m1r6mpaRQaUavVjBgxgmPHjuHm5nZH26utrUWhUODm5saZM2dISEhg4sSJMt9hMI+Oiopi5cqVuLm5SQPxa9eusWDBAjZu3EhCQoJ8f/bs2cOsWbNwc3OT56zX66mrqyM6OprmzZtjbGxMXV0dOp2uyWrTW8Nger0eKysrKioq8PT0/FPMpNGjRz+0IN2tFbbQkG+oq6uT4TjxRy7qdtXG119/nSeeeEKamhvCpjk5OYwdO5bY2FheffVVnJyciIqKIiAgAI1Gg42NjTSsf6Q4638CDxpzXwa8Cdz6ZJoJIXIAhBA5CoXC0OO6A+dv2S7zj88aQaFQTAOmQYPE6IoVK7CwsGDw4MEEBQWhVCopLCzkk08+ISAggIyMDNq2bUv37t0b+W4+LAz+hQ+zPdCo8eTl5UmqmGEbIRq03iMiInjjjTcICwtj6tSpdO3aleTkZJRKpbTNWrJkCWq1+i/Hiw3mCoZkbteuXZk/f76UIkhISMDR0ZG8vDyMjY2prq7mnXfeITg4mL59+9K9e3dGjRqFsbExTz/9NEqlUupf5+XlYW9vL31pDdLCer2e5s2b88orr3DhwgWOHj3KwoULiYuLw9bWlq5du/Ltt9/y/fffo1Qqee6556ivr0epVDJy5EguXLggz7+kpISePXvi5uaGWq3m4sWLZGRkkJWVxaJFizAyMuLq1au0atVKxsPv1hk/LGpqaoiNjWX//v0888wzd2jyHDlyhIEDB0ptciEairUMsdfnnnuOoqIiIiIicHBw4LXXXqNdu3YolUq++eYbunbtSufOnYEGgxAnJyfUajU///wzzZo1o2XLlpiammJjY8PNmzfZtm0bK1eupLCwEJVKRXJyMkuWLAEgIiKCV155hbFjx9KtWzfS0tIwNzeX8rI//fQTqamprFixgnfeeYe4uDhOnTqFra0tH3/8MWFhYVy9epWjR48ycOBAWrRogbm5OX379uWNN95g3rx5sp0YOlIhhKSzNmvWjOXLl3Pz5k06d+7MxIkTMTExkYnUmJgYiouLqa+vp3fv3nedOJ0+fZr+/fv/qeclhKC6uprLly/TvHlz+e5otVquXbtGSEiItIIUQmBlZUV+fj4///wzffv2lXH5Zs2aodfrJT3XwsICX19f4NFPkD4s7muzp1AohgFDhBDTFQpFb+B1IcQwhUJRKoSwvWW7EiGEnUKh+Bo4J4TY/Mfn3wP7hBA/3u0Y7u7uoqqqSjaYF154gfDwcA4fPsymTZvYtGkT27Zto6amhoyMDEaNGsXChQv/+tX/SRju2e2NQaPRsGnTJqKjo7l8+TLt2rVj1KhR+Pn5ER8fj5OTE2ZmZjRv3pyamhqpOf1XcOnSJc6dOydnvcbGxowbN46YmBheeeUV5s6dy9mzZ2nTpg0LFy6kV69ejB8/nvbt298h/CWEQKfTyRUIwObNm5k/fz5LlizB0dGRtLQ0XnzxRb788kvq6+txcXHB3t6eAQMGcPToUZ5++mkKCgpQKpX4+flx8+ZNVCoVM2fOlEbm/fr146effsLR0ZF3330XT09P3njjDXQ6HdOnT+fMmTO0aNGCp556iqlTp+Lt7U3fvn05e/YsycnJdO/enZEjR/5pH9n6+npWr17Nd999x7Zt2wgJCbnjOdzKexeiQTTtySefJDY2lqCgIH755RemTZvGyZMngYYJSmhoKDNmzGDr1q1MnjyZDh06EBkZyWeffcb169fRaDQIIXB0dGTAgAFcunSJbt26ERsby8WLF1GpVJK/b2xsTNeuXTE2Nkaj0ciZ/Nq1azl16hQVFRXY2NiwevVqhgwZwscff4yJiQkvv/wyKSkpVFZWolKpOHPmDIcOHSIjI4MOHTpw9uxZ+vXrxwsvvIClpSV79uwhNTWVw4cPk56eLmsHDHo1QghatmxJQUGB9Czu1KmTlOR97bXXWLZsGUeOHOHpp5/miSeeuGtiOj8/n7Nnz9K/f3/JO39QaLVaZsyYwYkTJ5g6dSqDBw+mdevWCCGk3jr8P+ewBQsWsHfvXqZNm0a3bt2k3/GtEH+QAv4u56P/CfxVm71uwAiFQjEEMAWsFQrFZiBPoVC4/jFrdwXy/9g+E7jVisUDuNPb6hZUVlaiVqtxcnIiLy+P1atXs2DBAs6cOcOQIUM4duwYAwcOJD09nYSEhEaZfb1eT3JyciPT4n8adzuOWq3G0tKSqqoq2rVrx40bN3j55Zepra2Vy3aFQsH3339PYGDgQ8km1NXVoVAo7uiQi4uLCQ8PR61Ws2rVKj755BMqKiqorKwkOzub0NBQ+vfvT2FhIcuXL6ddu3ayQOl26HQ65s6di0KhYPbs2Zw7d46MjAwCAwMxMjIiMDCQ4OBgVCoVffv25Z133uGpp54iIyNDmgk7ODhQUFAgJRlu3rzJsGHDpJjTjz/+yK5du7C1tWX69Ok8+eSTfP/999y4cQMhBF999RX5+fn89NNPHDp0iJiYGI4ePcqGDRuAhud96NAhEhMT+eyzz3BwcHgolosQgtWrV/P222/z3HPP3dWo+vZ9xsfH4+bmRlZWFh9//DGbNm3i8uXLKBQKHBwcmDJlCr/99huffPIJH3/8MWvWrGH69OlSIE2tVrNixQqsrKw4d+4ce/bsISMjg7i4OMzMzGQ4av/+/Vy4cAE7OzvCwsJYt24dJiYm0tHLMLmxsrJi1KhR9OjRA41Gg729PRcuXGDIkCFcvnwZCwsL1Gp1IwPyuLg4oMHZbOfOnSxevBgzMzNOnjzJ4MGDqauro7y8HCsrK2mAkZaWhqurK4GBgej1eurr67lw4QLl5eVkZGRga2tLQUEBX331Fb6+vpSUlFBVVYWnp2ej+6rRaLCzs2PlypVs3LiRL7744qHMPYQQJCUlkZiYyIYNGwgNDZVewbcz51QqFfPmzWPGjBn3lEe4m2mLVqu9q6CdkZHRvyaY9ldx37MUQsyngf3CLTP3yQqF4hNgKrD4j39/+eMre4CtCoXic8ANCAAi7nMM9Ho9zzzzDKdOnWLfvn3MmzdP6ji7uLjw3//+l5dffpmKigoZE/vjnP52OtbdZub3Q2VlpXyRu3fvjre3N82bNyc9PZ3AwECsra3JyMggKCjooV2iTp48SUJCAi+//DI6nU7GesPCwkhJSSE7O5tPPvlEhmlcXFxYsmQJNjY2FBcXS1Pj1157DV9fX6ZMmYKzs3MjA24hBObm5nTq1ImKigqioqKwtramc+fOWFhY8Mknn2Bqasqnn35Kq1at2Lhxo6w7MDY2Rq1W4+fnR1xcHCNHjmTChAly1jh+/HhycnKoq6tDq9XSo0cPZs+ezapVq6isrMTIyAh7e3u++OILvvrqK3Jzc7lw4YJcRTz++OO4uLjw2WefoVKpMDIyYseOHQwaNAh/f/+7Psf6+nq5Iqyvr0etVrN792569eolqYGGJfrdoFAo8PDwkIbR/fr1Y9euXSiVSubMmcP06dPx9vamc+fObNmyhfDwcLp06SLleJs3b45KpWL37t34+/tTVFSEvb09jo6OODs7Sx63YXIDDbPclStXSn3+ixcvEh0dTZs2bRg9ejQ3b97kgw8+wMXFhejoaNLT0yktLcXY2BgzMzNatWpFQkICgORme3l54eTkREREBKWlpbzzzjs4OzsTHx8v7Q8NMs06nQ53d3e+++47Fi9eTGpqqqQdGp5hZGQkM2bMwMzMjJ9++omgoCASEhJQKBQcPXpUhrQyMzOZOXMmvr6+dO3alUmTJj20FZ9arWb8+PFcuXKFhQsXMnDgQPmeGp6x4ZnX1tZSW1vL2rVrycrKknLR/fr1u6MzNzY2ZseOHcTGxpKfn49er28yP2SAn5+ftCYMCwujQ4cO/2O07PvibpnWpn5oSKAa2DIOwO80UCF/B+xv2e4tGlgy8cDg++3XyspK9OnTR/j6+orly5eL5557Tma21Wq1GDlypHjnnXeEg4ODeOmll0RqaqrMFhvU3+7FatBoNOLcuXMPzLwoKSkR2dnZD8yUqK2tlZSsffv2ibNnz4rp06eLZcuWyXM0/MybN0+MGzdOKv49KLKzs0VKSooQQohr1641Yjjk5eWJp59+WlRXV8vj3LhxQ/z222/ihx9+EEOGDBEuLi5ix44dok+fPuKnn34SOTk5YseOHUKr1Up6aVJSkoiMjBRff/21cHJyEmPGjBGVlZUiOztbzJ07V1y7dk1cvnxZbN68WbJnbmUoGFhExsbG4qeffhL19fViy5YtomfPngIQbm5uYvXq1cLX11d8/vnnQqPRiHHjxglXV1fh6ekp/Pz8xOLFi0VqaqpISEgQO3fulAyf1atXixEjRggrKyvx/fffi9OnT4vTp0/fk81QWVkpLly4IHQ6ndTI0Wq14sMPPxQHDx4UlZWVYsaMGSImJua+97+oqEjExMSI6Ohoce3aNREfHy+OHDkiMjMzhV6vF7m5uaK6ulrMmTNHXL16VRw4cEBcunRJ7Nu3T7Ru3Vp06NBBODs7i5kzZ8rqSSsrK/HSSy+JcePGiZdeekmEhobeUVl5+4+tra3Yvn27+O6774SDg4NwdXVtxAQZPny46Nevn2jfvr347LPPhEqlEiqVShgbGwsTExPRoUMHYW1tLczMzMSzzz4rFixYILZv3y5++eUXceHChUY/ly9fFjU1NeL69evys/Pnz4t169aJ9957T3Tv3l3Y2NiIsWPHiuHDhwuFQiEUCoUYPXq0KCsrk/euuLhYfv9+7+q9kJGRISIiIkRaWpr4/vvvRWVlpaQmC9HwHl67dk3Mnz9f+Pr6NrqXtra24uLFi00+188//1x89dVXomXLlgIQ5ubmwtra+p7PQaVSCVNTU/HCCy+IioqKP3U9fwf4O6iQ/+SPtbW16N69u/Dy8hJr1qwRo0ePFr6+vsLS0lI4OjqKFi1aiCeeeEL4+vqKrKysJiU/74Xq6mqxfPlyUVFRIXQ6naioqLgnvUqn04mMjIwmy7VvLznWaDTipZdeEh9++KG4cOGC6Ny5s+jatasIDAwUy5cvF0I0DBY6nU5oNBqxc+dOsW3bNjFr1qyHahR6vV7Sz24/B71eLw4fPtzovpSWlordu3eL1atXi48++kgsXrxYHDlyRLz//vvixIkToqKiQhw8eFAUFBSIoUOHigULFojPP/9c7NixQyxatEgMGzZMrFmzRgjRwCU2vJRN3QMDzpw5I1xcXISHh4e4fv26SEhIEFqtVkyfPl0olUoxZMgQceHCBbFlyxYxfPhwUVdXJ4qLi0VcXJz473//K0xNTcXChQtFUVGRyMvLE9XV1aJnz57C1tZWODo6CmiQnm3durWYNWuW2LRpkygrK7trB5+WliZef/31JusUKisrRX19vVi7dq0oKip6oGdQXFwsIiIi5MCWmJgoCgoKxI0bN8TPP/8snn/+eTF58mSxdOlScfz4cXH06FHx5JNPys7XwsJC3C6SZ25uLlQq1QOVxwPC2dlZHD9+XCxbtkz85z//EUFBQbJTAoSdnZ2kpt4upW2g/T333HOiS5cuclCPjY0Vly9fbnSP9Hr9PWs2DPUHc+fOFaGhoeK3334TI0aMEOPHjxcpKSmSwpiWlva301mbaoN6vV7cvHlTDBs2TBgZGYkOHTo04rUD4pNPPmnync7IyBA9e/YU5ubmAhCtW7cWoaGhAhBOTk7Cy8uryRoO/pAs2LZt2/+YDMG9Ovf7JlT/Ddja2oqysjK8vb1RKBS0b9+eyspKLl++zKpVq/Dz82PBggX06NGD8PBwrl27xogRI/D29n4g2zWdTkdZWRn19fVUVVXxwgsv0LNnT3r27Env3r0f+Dy1Wi3bt2+na9eu+Pr6UlpayvXr13nyySdZvHgxlpaWxMXFsW3bNrKystiyZYu8lpiYGLy8vPD395d2a+bm5g8cUiopKcHGxuau8eXLly9TUlIi2Qg3b94kNzeXzZs38+mnn7Jv3z7Mzc1xcnJi0aJFdO7cmdGjR3P06FFWrVpFfn6+lHVo06YNlZWV2NjYPFR88fjx4wwZMkSyanQ6HdOmTePjjz/GyMiIyMhI7O3teeaZZzA2NmbVqlVs27aNDz/8EK1WS0VFBT169OCZZ55h6NChKJVK4uLi2L17NyEhIURHR9O7d2/27t1LZGQky5YtQ6fT4e/v3yQ1LzMzk6NHjzJp0qS/JXRXW1uLTqejoqKCtLQ0jh8/zuHDh4mMjJSWdNDgrGRhYUFtbS0VFRX81XfM1NSUuro6mSuxsrKipqZGmju7uLhw7do16eLUFPz9/cnOzmbatGnU19cTExPDzp07cXJyoqamhmPHjtGtWzdsbGzIzc1l6dKlJCYmEhoaSmBgIJMnT24y/FBeXs4nn3xCUlISgwcPZsyYMTJZqtfrKSsrw9bW9i/nw4QQMhxkkAG49W8FBQU89dRTHDhwgH79+jFs2DBee+21Rvdj8uTJbNy48Y5zqa6u5sSJE1y8eJFr167xn//8h+TkZDZv3owQAjc3N1xdXUlKSqJLly5kZmZiamqKnZ2dpE+OHj2a4ODgP21v+WfxVxOq/zgMfFqtVoubmxuTJ09m+/bthIaG4uTkRFpaGklJSSxZsoSQkBAqKyvp1asX7du3Z9myZXeUThtGLkOM1UCdUygUFBcXY2lpSVRUFE8++eRDnadKpWLUqFHExsaSmJjI8ePHpQ751q1bGTFiBIsXL+bxxx9Ho9EQFRXF7t27pRejiYkJ+fn5NG/e/I6Yo/gj76BSqaiqqiI7OxsvLy+uXr2Kh4eHTAzV1NQ0qT5nbW1NREQE/fr1Q6FQSBppWVkZly9fxtzcnMTERCorKzlx4gQKhQJfX182b97MW2+9RUhICEuXLsXGxgZjY+M/pbZZWFiIpaUlQ4YMwcfHh0uXLvHWW29RU1PD5MmTuXnzJjNmzCAtLY333nuPiIgIoqKimD17NgcPHiQxMZGJEycSGBgo20OzZs2YP38+GRkZDBw4UPLLNRoN48aNo2PHjixatKjJzt3Dw+NvtV80OPOcPn2agoICmSSsqalBq9ViamqKqakpCxcuJCkpiTNnzhAVFXVPOQILCwtqamoaccpvR2hoKF27diUuLo7ExER8fX05fvw4CQkJUqlRp9MxfPhwli1bRk1NjfyupaUlpqamPPvss6xdu5bAwEC2b9+Om5ubTM6bmppKPZzKykrS0tLYsGED3bt35/PPP8fU1BRjY2M8PDzo3LmzvNcGJ63s7GzJyDLkgqAh1v93dHY6nY7Vq1ezceNG6urq2L17d6P3p66ujpkzZ3Ly5EmcnJyYMGECn332WaP77uHhwZgxY5rcv7m5OYMHD2bQoEEyZ6XX65k5cya1tbXExsZibW2Nh4cHjo6OCCFISEjAzs5OGnZrNJp/VefqQfBIdO4KhQJzc3Nat27NqlWr8PDwYNCgQeTk5ODk5ERRURHjx4/Hz89PJhGVSiWHDh0iPj5eNky9Xk95eTmVlZWUl5djY2NDdXU1ly5dIiEhgfDwcCorK+nSpQvh4eH4+Pg89HlaWloCcPDgQSwtLVmyZAmZmZncvHmT7du3Y2lpyZkzZ2jWrBmWlpbMmjWLs2fP4u3tjY2NDYsXL2bp0qV37Lu4uBi1Wo2NjQ0FBQVcvXpVekampqbi5ubW5DkZClNcXFwIDQ2lqKgIBwcHVCoVYWFh7N27lytXrjB16lRatGjBDz/8wOTJk3n22WcJCAggLCyMjIwMrK2tcXd3x8bG5g4p3QfF8OHDWbduHdeuXQPg2WefpX///lRWVlJUVMS5c+ckt72+vh4fHx+mT5+OUqkkICCAwMBAbG1tsba2pra2loKCAry8vAAavcw9evSgvr6e4OBgvLy8/rWXKiUlhcuXL8vZaNu2bXn//fdJT0+npqaG1q1bo9Pp8Pb2pqqqiuXLl2NlZcX169cpLy+XBs0ODg5SG8Xe3p7CwsJGHbKJiQlubm74+/szZMgQ2rZtS2BgIHl5eXz55ZckJydjaWlJZWUlycnJpKSk4OzsTFlZGa+++irNmjXjo48+kmYTFRUV7N+/n759+2Jvby9N1RMTE2nfvr2sXbh8+bI0Ni8rK+Ps2bPodDoqKyt59tlnMTY2pnv37nIyVVJSQnl5OaamphQWFrJp0yZmzpz5t9/3qqoqgoODeeaZZ1AoFI00YYQQnD59mtOnT+Pt7U2zZs04d+4cZWVlGBsb4+joiLW1NcuWLaN///73TZwb2r1KpcLGxgYbG5sm/U9DQkIa/f5vGF4/LB6JsIyTk5Ows7PD19eX1atX4+HhcceyKzs7GxcXF+kYn5CQwMKFC1Gr1UybNg29Xs/JkyclFev8+fMsX76c3bt34+7uTpcuXejYsaPUYjc3N8fGxob09HSuXLlCREQEw4cPl4UnVVVVVFZWcvHiRTp27ChHaGjQMDcyMuLNN9+UA40QgkWLFlFWVibdhKZNm0anTp2YOnUq0FDssXfvXgYOHEjbtm2pqqpqpDN9e8PT6XTExMTQsmXLuzZKvV5PfHw8gDQF9vf3R6vVkpCQQFZWFh06dEClUnHo0CG2bNnCihUrcHd3lwPh4sWLOX/+POXl5ZJPPGPGDIyMjGTFZWlpKQqFQupWG56LTqeTgk3t27cnMDAQY2NjMjIyCA4OlvQ6wyzK3t4etVpNYmIiaWlpQIP+fWpqqrymoqIiYmJiUCgUhIaGEhoaiqWlJZaWljz++OOYmZn9KeGwyspKTExMiImJISAgoFGVo4HTbZh5NnW/hRDk5+eTn5+PtbU1zZo1w8TE5K7PRqPRkJqayqpVq3B2dqZPnz5cu3aNVq1aYWdnx4EDBxBCkJOTQ2xsrPxe8+bNeffdd7GwsGgUdhSiwRs1KyuLjz76iOPHj6NSqQgJCaFly5bExsayceNG7O3tGTt2LOfPn2f37t3U1NQwadIkPv30U1auXMn58+cxMjJi27ZtdOzYkfr6elJTU4mIiCAzMxNbW1tSUlIIDw+X4RWlUilXkAatdCsrK+rr60lOTiYtLY29e/fy9ddf0759k1GCfwRCCM6cOcOaNWto27YtKpWK4OBgnJyc0Gg0eHh4yDDZ7ZMAwwrf8LmMVd8mYnhr+7gVqampeHt7y4Ivw76cnZ1RKpXEx8dTVFSEv78/ycnJshK8vr4eU1NTioqKZH0KIPuRW8+nqYmLEA0Fk+Xl5bi7u981LPNIdO42Njbi9ddfp6qqioEDB9KjR49GFD1oWKIbyo4Nn58/fx5zc3NiYmJYunQpX331FR06dKC6uppTp04REBDA888/T1RUFN988w2jRo2StLgTJ05QVFREZmYmixYtorq6msmTJ+Ph4YGvry/+/v689tprkldsY2PD/PnzpSmAr68v6enpbNmyhd9//51PPvmEGzduYG5uTmpqKnV1dTg5OdG+fXvc3NxwdHTE2NhYhhQMph/u7u537RyEENJCzPC7Tqe7ozrT8HlTUqRarZaUlBRiYmJYs2YNCQkJbN68GScnJ1577TUuXLhAcHAwRUVFcsZtCK0EBQWRl5dHREQEOTk52NjY8Pzzz9O2bVsSExOJjY0lPj4etVrN1atXCQoKol27dqSnpxMQEEB2djYRERFkZzeUOZiZmREeHk5xcTGJiYnodDrc3NyIioq649otLCyYMmUKp06dIiUlhT59+vD222/TsWPHe76Mhs9ulbIoKiri5MmT/Pbbb1JhcurUqcyYMYPvvvuOgoICObvu168f06dP/9tip7e+X/d6zk1td6/tNRoNFRUVUvpApVJRWVmJhYUFdXV1vP3227Itf/HFF0RERODl5UVycjI6nQ4TExNCQkJQq9VMnDgRT09P3N3dCQ0NlZWehoGuqqqKiooKNm7ciLGxMWPHjuXw4cNyoL169SpCCLy9vdHr9ZiamsoVyr9Re3Kve2z4W1PnkZqaytq1a3n11Ve5cOECly5dwtbWliFDhpCWliZDUJWVlTzzzDPk5+fLfalUKkpKSrCysqKuro7k5GT0ej2tW7fmhx9+wMrKitdff53a2lrS09MpKytj+vTpnD9/HmNjYz766COWLl1KTk6OtOK0sbFh3759PPHEE1RWVpKZmcncuXNxdnZGq9Vy/PhxTp8+jU6n4+jRoyQkJFBYWPhox9xNTU3Zu3cvly9fJiYmhuPHjzNz5kypGWFoJD/88AP9+vXDw8MDhUJBu3btUKlUBAUF0b9/f7mdkZER1dXVHDx4kJEjR/Lss8/KFyglJYXS0lK++OILWrZsiZ2dHc8//zy1tbUI0VA92L59e8zNzWnVqhWdO3dGrVazd+9e7O3tefzxx9m/fz9RUVFMmDCBKVOmoFQqUavVhIWFERYW1qjQSKPRoNPppHyBSqWSnbAhxHMrDLmC1NRUCgsLCQoKwsnJCZ1OxzfffENJSQmPPfYY7u7u0g/Vw8MDMzMzucIpKysjKyuL69evk5CQIPVtTp48KXVOhBDSccZQdGRAZWUlJ0+e5Pfff8fd3Z26ujo6d+5MYGAgycnJHDx4kObNm8tKSYP+zocffkhISAhpaWlMnTqVyMjIRi+en58fQ4YMYcmSJbz++uusW7eOuXPn8uSTT94xKzIzM2PAgAEoFApu3LhBSkoKu3fvxtvbm4yMDC5cuMDVq1fJycnBwcGByZMnAw3hMgNn+bHHHsPIyIi0tDQOHz5McXEx//nPf1i4cCGXL1/m5MmTrF+/nrq6OqZOnUpFRQUdO3bE1tb2b2vbD9K53W2lcK/tm8qLGGaApqamDBgwgIKCAmbPnk1BQQFt27blhx9+YMKECZw6dQoPDw8++eQT2rRpIyWf6+rqOH78OPb29lIGWQjBtWvXiI2NxcrKChsbG3Jychg8eLBs04bq1QsXLjBt2jQiIyP58ssvefHFF2nTpo30dhWiQUJAp9NhZmYmJym3PnuNRkNtba0kGzzo/TPIUtxOAMjOzsbR0bHJZLC5uTk+Pj6kpKRw6dIlTE1N6devH5cvX8bU1JSEhARat26NiYkJ1dXVXL16lcDAQGbOnIlWq6W2thZHR0dOnTolB8BPP/1UzvRffvllFAoFeXl5hISEYGZmRv/+/bGyssLMzIwFCxY0Op/MzExMTExo164dZWVlcvCF/zerLygo4NixY8THx98zTwOPyMzdw8NDhISEUFdXR1JSEjqdji5dumBnZ8fHH3+MnZ0dQghWrVpFSEiIrOysrKyURR86nY6cnBzUajXt27cnOjqazz77jE6dOtGnTx9ycnIwNjaWM7Ta2lq8vb0ZN24czZo1o76+npqaGvnCFBUVUVpayr59+0hJSaG6uho7OztmzJjB0aNH6dq1K7GxsQQGBhIUFCQf6K0JpdthYFPcjYGi1Wq5fPkyn376KYcOHUKj0XDixAksLS05fvw4ubm57N69m9jYWOzt7SktLcXKyoqJEycSGhqKEIKMjAyio6M5ceKENABWq9X4+PjQtWtXioqK2LdvX5MMDkMiSalUYmtrS11dHe+//z6hoaGEhYVJ/RWtVsvZs2dZs2YNmZmZeHt706pVK/r374+/vz/p6emMGTNGVkTeCoOF28yZM3n33Xf54IMPeOedd6itrW20nZWVFd7e3gwYMIBvvvkGtVpNVVUVbdq0ISYm5o7tVSoVxsbGjWLXKpUKa2trpk+fjoeHB3FxccycORMfHx/S09NJTEwEGuwdXVxcHjh2b2BuZGVlERUVJfXF77atQdStqKiIxx577K7x2fr6eikI5ufnBzSYX1dUVHDu3DlatWpFmzZt5Ert1pc7MTERe3t7PD090ev1REZGcvToUZRKJT///DMxMTGsW7eOOXPmkJaWxrx58xg3bhxt27ZtFH4wTEYMeucXL16kurqab775hqysLKnNtHXrVpmzurWaU61WEx0dTXFxMW+//TaDBw+W75Rer2fHjh2Ym5szY8YMsrKy0Ov1MpTq6OhIQkIC+/fvl6GmkJAQrKys8PDwoEWLFo3CmIbch+EcbjXSMOBWGYkHea63vhdCCBkGzs/Pp7q6GgAvL69GxxFCUFFRQVVVFS4uLtTV1d0RrissLMTExOShhdOaOkeDvWBeXh5Llix5tMMyISEh4vTp03z//fesXbuW/Px8KioqCA4OZuDAgTg4OBAYGEhmZqY0yDA0upKSEqChYwoLCyMgIIClS5eSnZ3NnDlz8PHx4fPPP8fa2pri4mJyc3Ob1BKpqamhpqZGGlYYXp76+vomzQ9uhyGxGRUVhZubG+7u7kRERMgOBKCgoAAhBH379sXCwoKysjLWrVsnO6Ta2lr27t1LRUWFvKahQ4dSV1fHoUOH/tI9njp1Kt999x1ffPEFS5YsoaysTHYOhsHG2toatVqNp6cnaWlpFBUV8dprr8nchiHMIYRg69atrFy5kpKSEr744gu++eYbhg4dKk1Ipk6dSnl5eZPn4uXlRXh4OLt378bLy4u8vLwmnXIMHrmGeObDtFWFQkG3bt2YOXMmjz32mJw96vX6hy4fN4R5ysrKuHnzJt9++y2xsbHk5uZSUFDA8OHD6d+/P0OHDsXKyopDhw5RWVnJpUuXqKioIC8vj8jISGprayULxUCju3z5MnV1dVy5ckUmv83NzeWqJScnh8rKSiIiIvD29pZidfn5+Y0SixqNhubNm9O6dWu8vLzo3r07oaGhlJaW8sQTT3Dx4kVmzZrFp59+ilKpZP369XJFaJhJCiFIT0/Hzs6OVq1akZGRwXfffcfChQtJT0/n008/xc3NjX79+tGrVy8ZAtq8ebM0WLGxscHIyIhjx46xd+9eli9f3uSzMTIyatK163YYGxvj6+vL119/LRO6hs79QRP/t8fWb4VBcbNFixaoVCquX7+OiYkJwcHBFBQUUFVVdQfxIiEhAVtbW0xMTCgpKWmSmFFVVUVUVBTt27dHrVZTXl6OkZGRfIdqa2ul//DdYKAT19TUkJKSgrW1tUxmV1RUcPz4cUaMGPFod+6BgYEiPj6e/fv3Y2Njw9KlS0lISCAgIID27dtz9epVevfuzfTp01GpVOTm5vLrr79iZWVFUFAQ0NAR+Pv7Y2RkJJXhtFqtLJluKhZnSPIZ6HWGe2FYDhoahU6no7S0FHt7ezmS63Q6CgsLyc/PR6VScePGDY4cOcKePXsIDw8nICCAnTt3kpube8f1GqSDDcnKfwMuLi5cunQJc3NzKVYFDS/PokWLCAkJ4dy5c5w9exZfX1+cnZ35+OOP6dKlC7/++iv19fXShLugoIDp06eTmZlJVlYWJiYmaLVaXFxcqK6uxsvLS8bv/y0YJJbNzc1p0aIFISEhjBgxglGjRjWamRpyE/ebyRk6dEPnPGPGDJKTkzE2NpaJ4FuhUCjw9PTE1taW2NjYu2qTmJiYMGjQIBwdHXFwcCAyMpKoqKhGGjB/BQ4ODqxevZro6GiZ91i5ciWpqaly1dOrVy9WrVqFlZUV58+fZ926dcTGxlJZWcnEiRN56623sLS0JCcnh6VLl9K6dWuWLFlCcnIy9vb22Nvb8/nnnzNo0CCioqJ4+umnqaqqolu3bixdupStW7eiVqtJT0/n66+/RqFQ/CW+f6tWrfjuu++Ij4+nffv2hIaGPtT3y8rKiI2NpVOnTneNycP/y9k09f9bYaiXMSTkmwr53L7f2tpalEqlXOFpNBrKy8vvSTk2DAgFBQXo9XqcnJzkRLO6uprU1FRatmz5aHfuPj4+IjU1VS6tDB2eoVghMjISCwsLgoKC7puUMsx6Dcsfg/5zTU0NNjY2CNEgQBQXF8d3332HTqeTIl+lpaVYW1szbdo0amtrOXXqlGSdJCcn069fP0lJjI6OpqqqipycHIqKiigqKpJhl0cRCoWCpUuX0qpVK6ZPny61Mwwyy7169eLgwYPs3bsXT09PSUVUqVS0atWK6upqySAyUE4fFdzqPG/QnSkqKsLW1pbFixfj4+ODiYkJxcXF0h5OrVbL4hzDgK3RaKiqqiI/P5/Dhw+zc+dOUlJSKC8vl+3q74BarUar1UoqZ3p6Ojdv3pR5n78CJycnfv75Z5YtW8auXbvk54bkoFKpZPPmzTRr1kx2YElJSURHR5ORkcF//vMfHB0dZTy8rq6OyMhI2V7atWuHmZkZzs7OWFhYUF9fT1RUFFVVVaSlpeHu7s7x48fJycnBzs6OEydOAHDlypU//X6MGjWKt956i8LCQuzt7WnTpg2///67rC2IjIxEpVJJivOtdSBCCA4cOMAHH3zAjh07HlrT5lHHvYqYHonO3d/fX5w/f56ioiJcXFywsLCQ8WPDjCYpKUkW9jS1DCouLmb16tUy0WDYpq6ujpKSEvLz8wkICECn0xEVFUVlZeVdX6RbG8b/n2BgGhkqLf+3wt3dHScnJ2JjY6mrq0OtVmNra0thYWGj7QwrNm9vb/z8/CgsLCQuLk6aaYwYMUKqLur1el5//XX27Nkj8y3/Fjp37szChQuJj49vVCfwZ6BSqVixYgUVFRXMnTtXfrZ3717JzurRo4fcXghBfHw8Pj4+HDx4UIqpVVVV4eHh0ShGXFhYSE5ODkZGRgQFBUnlUUdHRzkRM1SlPvPMMxQXF0ua7v2gVCoZM2YM3t7e5Ofns2nTJqytrVEqlbRv356vvvqKwsJCDh8+zMCBA/nwww8pLS3F19eXw4cPk5+fj7GxMe3ateOxxx5j6NChkpKZkJDAzJkzmTBhAk899dS/qttuoG27u7s3IlAIIbh+/TqWlpYyv/Jn8MhXqBobGzNr1iyOHDmCubk5wcHB6HQ6IiMj5QzREBJQKpV35X7e2mEZFPFuRVMhkqbw/7dO3QBDQuhRhmH2fa9ZXlZWFtnZ2fI5abXaOzp2aAhFGaig+fn51NTUoFQq6du3Ly+88AKjRo2SzKq0tDQuXLhwVzXAfxJXrlzh6tWrzJ49mzFjxjBu3DgiIiL+VDsUQsgJkqGzNXQkr732GtHR0Vy5cgUbGxt8fX25ceMGRUVFeHl5ERAQIOPkubm52NnZNTK2qayslOwoJycnGTd2cnIiMDBQFsFNnTqV5cuX8+abbz5w524YZPLz82nWrBk2NjYMHTqUgoICTE1Nsba2xtTUlJycHMzNzdm4cSPW1tZER0fj4uJCfHw8GRkZVFdX8+uvv8raEoVCgZ+fH0uXLuXw4cNUVlb+5aTmg6C2tlaGcisrK6msrESpVFJWVkZeXh4KhYJmzZpRVlbG9evX8fPzu6+/g8FroakK9abwSHTuWVlZjYo4bt68eddt9Xr9fSlA/4f/vTA2Nsba2pqCgoJ7bvcgHV9+fj4uLi6Sqx0eHs4rr7zC8OHDsbW1laGY5557jv379/+rs/VbUVdXx8KFC0lNTeW9995j3bp19OnT50/F4fV6vTTmMOSS9Ho9JiYmKJVKtm3bxu+//87GjRsBcHR0xM3NDSEE8+bNIyEhAVdXV55++mmqq6sbPQdfX198fX2Jjo7m3LlzaLVaAgMDiY2NJSsri5SUFHJycpgyZYrMn/n5+T3QgCmEuKPeYevWrQA888wzKJVKDhw4QPPmzQkMDJSJybZt29K2bVtpcqJQKKirq5P+CQA5OTk4Ozuzf/9+hg8fLm0T/w7o9XpycnKkBo1h4pmWlsa0adP45ptvOHnyJDExMcTHx5OcnNzI4crA3OvWrRu9e/eWYaOgoCAZHjMzM5MaQCkpKfcsarwVj0Tn/v/XmfL/4f/BUAtwL4aEnZ0dXbp0oby8HHt7exITE//SQO7p6UnPnj3x8vLCy8uLoUOHyoKRpKQkae24Z8+eRsyT/wnU19fz/fffs2/fPlxdXZtciTwIDBz42+9bVlYW0MBUMiScoSHnEhERgZubG8uWLaNZs2Yolcq7WlEa4vT19fXSMcrw/7i4OPr27UtlZSU//PCD9Bn+q6uhuro6ysrK6NGjh8ynVFVVsXv3burq6iSrxcvLi+nTp8tKZAMdsaysjOLiYp555pkHYugYYKi+NkQMTE1NycjI4PLly3Ibw2AqhKBLly60b98eIRp8EdatW0fz5s2lVElsbGyj52qgvQL8/vvv/P777/J3gwRFQEAAFhYWdO3aFUdHRy5fvkxQUNBd5UhuxSPRuf8fHh0YGxtja2uLTqejvLxcFqpUVlbe97sqlQoTExPMzMyoqKiQcdji4mJsbGxo0aIFp0+fbvK7ISEhrF27lsLCQhISEujWrRtffPEFP/30012ZJwZRrNLSUhnGMcxorKyseP755wkKCmLkyJEyRFFQUEBxcTGTJk0iMjLyT96lfwY6nY7MzEwyMzPlZ4ZORaFQyCrte8HAq2/fvr1kjlVXV8tQRPPmzSkoKJBUX4O1n5WVFTExMeTl5ZGUlESfPn04cOAASUlJct8tWrTA1dUVOzs7PDw8OH/+PD/88AOzZs2iY8eOWFlZ4ezsjK2tLZs2bUKv1zN69Oi/fF+OHTuGsbExEyZMoGPHjlRWVpKVlUVpaSm7du0iJSVFXsuGDRvQarV07tyZb7/9Fnt7e4yMjFizZg1jxoy5a67JUNJvyPcZ2D03btxg2bJl6PV6QkJC+PHHH5us3wBwc3OTyra9evWiU6dOHDp0iNraWn744YeHGrDr6uoayXL8/PPPD33f/q9z/z80whNPPMGnn35KVVUV586dIz09HVdXV2bPnk1tbS2urq7069ePgoICLl68SEVFBS1atCApKUkWmIWEhHD9+nXGjBlDZmYmb775JtXV1ZSWltKiRQsASktL5WwSkHK169ev59SpU5ibm0tnq7vB1tYWOzs7qqurZec+ePBgWT05fvx4WekohCAiIoIJEyY00v951GFvb8/s2bMpKyvjxIkTRETc09QMaDDUfv7559m9ezeVlZWsWLFCDnq//fYbMTExnD17lqysLAIDA9mwYQPjxo3js88+49q1a9TV1WFnZ0dFRUWjmW7v3r25fPkyWq0WT09PHB0diY2NJSQkhI4dO+Lm5sahQ4eIjo6W6q1NQa1Wy5XFg6zMsrOzOXr0KN27d6dt27ZotVrefvttbG1tKS4ulvvQ6XSSplpSUkJNTQ3p6elotVpefPFFKfx3a6RAp9Nx5MgRLly4gJOTEzY2Nhw8eJCrV6/Kld+pU6fQ6/UcP34cc3NzPD09paBdU1CpVDg4OLB3714OHjzIuHHj8PHxadTe/w08EmwZa2tr8XdSzf4PDwZDRZ9BBMvW1pZvv/2WFi1ayM5Ar9dTWlpKdHQ0Wq2WFi1aSFGm3bt388wzz6DVajExMcHc3JyXXnqJ+fPno9Fo5NI+JyeHI0eONOL0X79+ndTUVAYPHoyXlxdWVlaEhITIF7W6uprVq1fz+++/c+PGjbvO3g0ICwtj0qRJ/P7773z33XdyBmVo30IIvvzyS+bNm/dQS/NHAQY9d3iwEGarVq1Yvnw55ubmaLVazpw5Q48ePejYsSPff/89WVlZTJ06laqqKk6dOoWfn5+UXN6zZ8999+/k5MTu3bsJCwuT9GEDzbiiooJDhw5RVFTEgAED6Nixo4wxQ0MY6LPPPqOyspIDBw5w5MiRB7oH7u7ujBo1Cnt7e5KSkujZsyempqZMnz4djUYjk5MGSnRdXR0hISF8//33hIWFYWpqilarZe/evbi5uZGbm0t8fDzXr18nOjoac3NzevXqhbu7u2Sv5OXl0bJly0aFRiYmJuh0OoqKirCzs8PBwUH6M5iamkoph8zMTNzd3Vm3bh2RkZFyBv8P4K+xZRQKRRpQAegArRCivUKhsAd2AD5AGvC4EKLkj+3nA8/+sf0sIcTBv3gB/4e/EYMHDyY3N5e2bduSnJzM8OHDef7559Hr9XcYRiuVSuzt7enZs2ejfRjqDwwZ/Pr6eioqKvj888+prKyU/qvGxsbU1tZy7ty5RjM5jUZDTU0N0dHRPPnkk/Tq1Yvy8nISExPZv38/AO+99x7z5s3j3XfflRWKtzKlDKXyBrz44ovMmTMHtVotO/ZTp05hamoqC60eNc3tB8HDdgo3btxgyJAhaLVaXF1def3112nRogXR0dFS0TE3N5f//ve/TJo0ifT0dH7++ef7hnwMMDMzw9XVFUtLy0bME4VCgVqt5siRI3Tq1Inc3FwpgWFATU0N77//PuXl5Q9FSSwoKODMmTMUFxfTsWNHTp06RW5urvRlHT16NG5ubvI5X7x4kc8//5wjR47Qvn17ycKqqanh0KFDlJWVMWDAAIYNG4apqSmOjo5YWlre0T7q6+tZt24dKSkpuLq6YmJiwoEDBzh+/DhWVla0b9+elStXUldXx7FjxwBk8WRwcDBHjhy5aygSwNnZmS5dunD27Nn7kggeFg80c/+jc28vhCi85bOlQLEQYrFCoZgH2Akh5ioUilBgG9CRBoPsI0CgEOKu6+v/m7n/ezAwITZv3kxwcDBt2rRh4sSJtG7d+oH3YeDujhs3rklFx9vRvHlzXn/9dTp16iSrQ3/99VfeffdduT+lUomJiQk1NTWyijQwMFDOhMrLy6XrvYEB8sEHH5CdnU3btm157rnnCA8Pb6QYqdFoGD9+PLa2ttTX17Nly5Y/dc8eddy6QmkKdnZ2hIeH88YbbxAZGcmiRYvo1auXrEqtqqriueeeY9euXfekC7dr107q+gQGBjJ27Fj69etHt27dqKysJDU1lS+//JLg4GDpTrZixQr5fTMzs3+kIlupVMpwiYeHBy1btqRTp06o1WqKioqYOHEi0DDoHTp0iOnTp2Nvb8/69evZunUrffv2Zc6cOXKFZMgzlZaWSup1eno6Go2GK1eucOrUKeLi4sjKyqKuro758+fj6enJ2LFj5XMIDQ1l27Zt9OnTh+Li4ibPOygoSJrNf/jhh6SkpODt7Y2DgwPHjh3jypUrD1KP8teKmO7SuccD/1975x0W1bW18XdPYZgZOgygNCkW0KiAEMTeYoyIRmNJMBJjS3ITo4mxJDfexGiMJhov0c8SE3tJYoua2EtsURFsYKWJ9F4Hpq7vD5gTRhjECnrP73n2A3POPufsPWWdfdZe+109iSiTMdYMwHEial09agcRza+udwDAF0T0t6nz88b96eHp6YnNmzdDIpFAoVDA0tLSKGysPtRqNe7evYvTp09j/vz53MSSra1tLf94TV+qm5sbJ8y1cOFCdO/eHbm5udxkUWxsLObNm8dN0tWEMYbw8HAwxrBhwwakpqbi3LlzyM/P5yRXp02bVktSQKfT4Z133sFvv/3GuYhM/cieVRhj8PHxgUKhgFKpxO3bt01G/VhbW+Oll17iRu89evQAEcHLywu3b99Gt27duMlEUzg5OaGgoIBzkUmlUmg0Gvj6+nJSDTdv3oRUKoVcLsecOXNw/fp1Tpq4devWJicjnwRyuRyOjo4YPHgwoqOjYWdnh0WLFsHJyQlXr17lBgdt27bFlClTUFhYCIlEAisrKxQWFiIjIwMikQj29vZo3bo1ZDIZJ0GiUqmgUqm4yfyUlBR88cUXcHR0BBGhY8eOiI2Nxe+//26yfc2bN4dCoYCNjQ2Cg4Ph5OSEV155BW3atEFOTg527dqFX3/9FSkpKVAqlSAiKBQKiEQiFBUVoaysrF7J34Ya92QAhahKCruSiFYxxoqIyKZGnUIismWMLQVwlog2Vm//CcA+Itp2zzknApgIABKJJLChj4Q8j4ZEIsHhw4fRpUuXBj8Wq9Vq3L59G1u3bsWyZctQVFQEIoK9vT3eeecdREZGIjs7m/vRG1Z7Xrp0qda5hg4dirVr18LCwoK7fnR0NLp3716n+8GQM/SDDz7A5MmTcevWLXz22WdYtWoVRCIRnJycjBZ/GKIeMjIy0Lt376c+ifU0MTc3x9KlSznBsuPHj2P69Om4ffv2fecoDNTUjjfowj8KBt2VBxV6e5wYVs8aPnuJRMLlOjVkwZJKpVCr1XB2doa/vz+IiNO0N0gy1LRJhgVx3t7etcJEiQh///03MjMzwRiDi4sLysvLcf78eezfv/+B2j5w4EBs3LiRE7rLycnBX3/9hVatWsHc3BwJCQkQiUTIy8tDVlYWpk+fbtK4cx9CfQVA8+q/jgAuA+gOoOieOoXVf5cBGF1j+08AhtV3/nuztPPlyRSxWEzu7u4UFRXVoGzthgzzR44coeDgYLKysuLOxRgjPz8/GjBgAI0ePZpyc3O5+lqtlnr16lVnGwQCAb333nuk0Wi46+Tl5ZGLi4vJdr/wwgs0c+ZMWrt2LR04cIByc3NJqVTWamtWVhZt3bqVOnbsSE5OTsQYa/T3/EkXiURCr7/+OiUkJJBer6fCwkL68ccfqVWrVo3etsYocrmchg4dSkuXLqW1a9fS22+/Tfb29g06ViAQkFAofKjyuNovEAioQ4cOFBYWxpWOHTuSg4MDNW/enORyOQmFQhKLxYbP+IJJu90Q436PEf8CwDQANwE0q97WDMDN6v9nAZhVo/4BAJ154/70isEIM8ZIKpVSu3btqEePHrR06VI6evQoFRUVkV6vp+LiYsrNzaUjR47Q7du3SaPRUElJCcXFxVF0dDQtWbKEXn/9dfL09OTO7ebmRt7e3sQYI8YYDRkyhPbt20fvvPMOjRo1ikaNGkUjR44kR0dHk+3btGmT0c1Fo9FQnz596qzbrFkzznBptdo6b0p6vZ7WrFlDoaGhj/WH9iwVd3d3Wrp0Kfcepaam0kcffVTv5/A8FltbW5o/fz7duXOHiIh0Oh2dP3+eJkyYQAEBAaRQKEgsFhNQZUifVDsUCgWNGTPmaXwfTRr3+7plGGNyAAIiKq3+/xCAOQD6AMinfyZU7YhoOmOsLYDN+GdC9QiAlsRPqD4VDL7Nd+OrOwAAPhJJREFUZs2a4dq1a2jVqhVefvllDBkyBK1bt+Yeu6l6gYZIJMKMGTNw9epVvPDCC9BoNLhw4QLKy8sRFBSE0aNHIzY2FsuXLwcA/PDDD3jttdewb98+CIVCDBo0CAKBAO3btzdacWcKoVCI8ePHY+TIkXB3d8eGDRuQlpaGW7duoU2bNti6dStmzZqFkpISrF+/HhEREZg0aRIYY5yWdU0qKyuxYsUKfPvtt1w6v/9VLC0tERkZiXnz5sHKygp6vR6JiYn49ttvsWbNmiatWvq46dq1KycHLhKJ4OPjA51Oh5deegmFhYW4e/cuzM3NUVZWhsLCQsybN6/etQ8SiaTB0URAlUifjY3N0/hOPrxbBoAXqlwxlwHEA/isers9qgz37eq/djWO+QxAIqpG9wPudw1+5N7wIhAIyN7enpycnAgAWVpakpWVFTHGyNPTk1q1akUbNmygTz75hL7++mvasmULqVQqbsSrUqlo/vz59OGHH1KvXr0oMDCQbGxs6rzWpEmTiIhox44d3LYffvih1si5qKiI3N3dG9wHkUhEHh4eFBkZSebm5gSA2rdvT9OmTaNBgwbR2bNnaeTIkfT777/Tzp07SafTkU6nM7qmWq2m3377jQYOHMiNxPhS5Xr74osvaOfOnRQbG0tarZaUSiX98ssv1KVLF5JKpY3exsYqIpGIvLy8aPjw4RQfH09lZWWk1+tJo9HQkSNHaM6cOTRlyhQKCwujfv36UfPmzbmRt0wma/T2mygPP3J/GvAj94Zjbm4OW1tb9OjRA6WlpRCLxbh9+zYsLCwwbNgwuLi4YOTIkVxIoEajQX5+PpdLNC4uDp988kmDlkJPmjQJK1aswI0bN/Drr78C+EedsyYqlQorV66sFdP8ILRu3RobN26Eubk5SkpK4OrqioqKCrRq1arWxK9er8fly5fxySefGOlx8FTBGINEIoFcLseHH36IWbNmcTHee/bswfTp0xv0lPU8Y2lpiZYtWyIsLAwvvPACkpOT0b17d9jZ2XFy4QUFBfjjjz9w5MgRuLq64s8//8SNGzea2hNQ09Zzt7S0pIZol/yvwRjjEiy0bduW0wjJycmBVqtFcXExRo0ahcjISC6/pGFxUHp6OsrKypCfn4+5c+ciOTkZpaWlEAgEXMKN+2Ew7gaICJMnT8bSpUufSH/d3NwQGhqKHj16YOLEiVxiccO1iQh37tzh0q3duXOHF527DzKZDG+99RZ69uyJkpISFBcXIyUlxSj+/H8dQ/JpiUQCOzs7+Pr6wtzcHJ06dcJrr70GPz8/MMZQUFCAy5cvIy4uDklJSTh16hSuXbvG5Ux9WlnV7qFpG3ehUEi8jO8/mJubQ6FQoFOnTpg5cybMzc3xxx9/YMeOHXB1dYWjoyMYYwgLC8NLL71kZAA3bdqE2bNnIy8vD5WVlbCwsMCQIUNgZmaGzp07IygoCOHh4fUq9QUGBiIwMBDdu3dHUFAQt/KOiLB9+3Zuybrh6UCn0yEhIeG+4Xfm5uYYPny4US7W/Px8WFpa4urVq+jZsydee+01BAcH1wrJUyqVWLduHRYsWMAtQZdKpVySBkdHRyPBLR5jDAaMqheM8b+3hhEQEIAJEyYYPT26uLigbdu2cHR0RHx8PLKyslBZWYnvvvsOKSkpEIvFEAqFSEtLexqDj0cLhXzSxczMrLH9Vo1ahEIh2djYUK9evah58+bUuXNnioyMpHXr1lF5eTkXEZKdnW0UQlgXhw8fNooC8PDwoKKiIm5/eXk5tWnTxuj6zs7O5OPjw5WoqCgiqoo0mDp1Kjk6OlLr1q1JLpcTAGrTpg0VFBSQUqkkpVJJWVlZ5Obmdt9+KhQKysrKIiIipVJJCQkJ9Nprr3HRDdeuXaP8/PxaETFarZZWrVrV4JA2vvDlSRahUEiBgYE0fvx4+vHHH+nMmTOUlpZGFRUVdP78eUpPT6fMzEwaN24c+fn5PdGoHNTjc28SqpDP+yjCIIVryIQkEAhga2sLhUIBoqos7qWlpbhx4wbatWsHZ2dnTJw4EcHBwTh9+jRKS0vRrl07NGvWDMA/2hWMsVrJS+zs7BAeHs6NGBQKBZcP04BIJOJGxowxfP/99wgLC+P2V1RUICUlBX///Td27tyJsLAw/Pe//8Wvv/6KSZMmcZmPDIs5SktLH/gzPHDgADIyMmBmZoYRI0bAzc2tzkTEJ06cgJ+fH9avX28kQMXD01jodDrExMQgJiYGq1evhkQiwYABA7Bo0SLk5OQgPT2dS+Lh5eWFhISERhGraxJumed9QpUxBrlcDhsbG3Ts2BEikQg5OTnIy8tDfn4+J7olk8kwadIkZGZmws/PD5WVlVi7di2ys7Ph4OCATp06obKyEowxTJgwAXZ2djh79qzRKrjAwEAsXry4lgCSwXDqdDpcunTJyD8YGxtrlPUnOjoa0dHRqKiowJo1azBo0CDI5XLk5+ejQ4cOyMrK4lbQAQARNcjAKxQKXL16lVv+ferUKajVarz//vtGbhgiglKphEajQdeuXTn3zcNkJuLheRqIxWLIZLKHGug8Ik07h+rzioODA8zNzREaGoqAgACcPn2aW8I8cOBAlJaW4sKFCwgJCcHRo0eRmZmJ5cuXQ61Ww8LCAuXl5Zg8eTJeeuklyOVy+Pj4YMqUKfj1119x9OhR+Pr6clnnDUgkEgCoV1pAKBRyxtTS0hJpaWk4efIktz8tLQ1FRUWwsLBAYGAgl9jXkIA4NTUVGRkZnDSqTqfD5cuXjUYnvr6+sLKyQk5ODqchY4ihd3Jygo+PD8aOHQuxWFzrRpSeno5p06YhLy8PPXr0wB9//AGtVgsLC4sGJQ3h4XnaaDSaR4oWeyI0tr+dnqM4d4lEQu7u7hQSEkIBAQHUr18/+u9//0uZmZmUm5tLN27coOjoaIqJiaFr165RUlISqVQq0mq1pNFoKCUlxcivLBaL6fz580b+58jISAJAZmZm9Ndff9G6deuoQ4cOXJkwYUKtmHADer2eCgoKyM/Pj0QiEYnFYpo3bx6p1Wqjsnv3bpo8eTLt3LmTKisrjY7XaDR0+fJlevnll6m8vJzUajXl5eUZxbkzxuiNN96g8PBw6tixI3l4eJC7uzvJ5XIKCwujLVu2UFlZWa126vV6unbtGi1atIi8vLwIqIrrN6yGbezPly98aYKlafvcn2UcHR1hZWUFGxsbuLm5ISMjAzdu3EBJSQm+/vprvPvuu5zP+9atW1i7di0YY+jfvz8qKiowcuRIbhRtYWGBli1bcmGO9eHl5YUOHTogNDQUI0aM4LYLBII6R+1EhCNHjmD27NlISEiAVqtFly5djNpHVJUb05DNSKvVcqnpHBwcOL1ukUiExMRE3LhxA56enhCJRLWutWXLlqqFFIyhV69e+Ne//gVPT0/4+flxTxc166ekpMDR0RHfffcdysrKuP4/7/MxPDxPCt64PyAWFhZo37497ty5g+zsbLRv3x5ubm5o2bIllxR4wYIFeOuttxAVFYXCwkJ8+eWXKC8vR15eHlauXGl0vpqG2M7ODocPH8b58+cxZMiQeuNm+/btCysrK5SWlhotm5ZIJHB0dKxV/+7duxg3bhy3eEUul+Obb76BjY0N/v77b8TExODSpUu4ePEiXFxcIBAIkJKSAiKCv78/1qxZY3S+9PR09OzZEzt27EC3bt0wZ84cI5dJdnY25s6dC3t7ewwePBiDBw+uU3GQiFBZWYkLFy7gyJEjOHXqFF588UVYWlryE6g8PI9AkzDuTWzFF4chk7ynpyd0Oh3S09MhkUiQnZ2N0tJSLlmBtbU1/P39uWwwBl3ovLw8WFpawszMjPO15+TkcOcXi8WwtbU1kl2Vy+UIDg6Gr68v0tLSoFKpuBEwAFhZWcHR0ZFbublz5058/fXX3DkDAgKMJlSFQiHs7Oxw9+5dZGZmAgDs7e3Rs2dPvPjiiwCAlStXYv/+/aisrERxcTGXONre3h6BgYF48cUXkZOTw7UXqDLK5ubmaNOmDcRiMd544w1otVoQEXQ6Hd59912IRCJMmTIFH3zwgcmniVu3buHDDz+Eo6Mjdu/ejZKSEty6dQs9evRATk4OF2HEw8PzgDS2v72p+dwZY2Rvb0+hoaE0cuRIWrBgAS1dupT69OlDkZGRZGNjQ7a2tjRt2jTKycmh3Nxcys/P5/zHer2e3n77bQJAc+fOpbKyMs6nvHnzZlIoFFwJCAig7OzsWr7xyspKio+Pp/T0dNq7d69R3HdxcTFlZ2dz8e/l5eWUnZ3Nld27d5OTkxN3DX9/fyouLialUknff/89vfLKKxQTE8MpQ+r1eioqKqLs7Gy6fPkyhYeHk0KhIKBqDsHBwYE718CBA0mj0VB8fDxJpVLy8/Oj4uJi0mq1VFJSQitWrKDY2FhKTk6mzz//nAYMGECXLl0y6f9PSEggPz8/AqqkWmtqxDRhLQ++8KUplccn+fs8GnczMzOysLCgXr16Uffu3WnChAn0888/U0pKCul0OsrPz6eFCxdSUlISXb9+nVJSUqi8vJzKyspIrVYbGV+9Xk/Lly8nOzs7Wrx4MZWWlnJl+fLlRtcVi8U0ffp0unz5Mmm1WlKr1ZSfn08HDhygdu3aUVJSUoN012tiahGTwZCr1WrSarV1HqvT6SguLo7GjRtX6z1ycHCg//znP6TVaik+Pp48PT3pxIkTnBTv1atXae/evXTw4EFSq9W0adOmOttvaMfhw4drLabiC1/48sDlf2tCVSgUmsw9aHBX2Nvbw8XFBSqVClKpFJmZmZDJZAgLC8OAAQPg5ubG1bW1tcWbb76JTz/9FLdu3cKmTZug0+kwduxYSCQSrFixgksUzBjD+PHj8fLLL2Pp0qXw9/fnru3k5ISxY8dyr/Pz8/HDDz9g9erVGDZsGIKDgxEVFQU3NzdMmDABBw4cwOjRo7lQxIehrKwMGzduRHZ2NpKSkkBE+Oqrr+qUzxUIBDAzM6u14KJTp05Yv349LC0tsXXrVhQVFeG1116DXq+HVquFUqnE+++/Dy8vLzg6OqJHjx5c3sp7SUxMxKZNm5CamsqlXBOJRAgMDER0dDQ/gcrD87ho7FH74xy5G1wFvr6+RiL5jDGSyWTUpUsXWr58OW3evJliYmJo5cqV5ObmRiKRiEaPHk23bt2iiooKUqvVlJqaShcuXCCdTkdqtZquX79Otra2ZG1tTV26dKHbt29TfHw8+fv7U0xMjFEoocFFM3nyZKP2jRkzxqheUVERRUdH05w5c0ihUJBAICCRSESMMWrbti1Nnz691rnvV/bv31/ncmfD+yGVSuny5ctcfZVKRcuWLaNFixaRUqkktVpN//73v42OHTZsGGk0Gho+fDgJhUJq06YNlZSUkFqtJo1GQ/n5+TR//nxuFH8vKpWKW5L9/fffk5ubWy0pgf91CQq+8OUhS9MeuT+u/KkVFRUoKSnhoiwsLS3h4uICZ2dnpKamIjQ0FJMmTQIAzJgxA5aWltizZw9UKhV2796NiIgI7lwdOnTArFmzsGLFCqxbtw4VFRUoLy/HqlWroFKpuBDGtLQ0REZGcmJYjDHMnTsX/fr1q9W+P//8E126dKm1XSAQwMrKCq6urvjmm28QFRWF/Px8jB8/Hp9//jmSkpIa/B6UlJTUGv3a29tj1qxZmDlzJlQqFUaPHm2UBzIxMREqlQq//PILBAKBkQCXWCzG2LFjERMTgw4dOoAxhsOHD+Orr77CyZMnERERgR49emDkyJFgjNWKiCGqUnIcO3YsUlJS4OTkBH9/fzg7O2PVqlVcvcZYns3z+GCMwdLSEhUVFdxTM2MM9vb2KC0tbSzFxP9pmoRxl0gk9f64W7VqBWdnZ3h5ecHNzY0LnTOoFRqQSqXQarXo0KEDBAIBioqKUF5ejhMnTsDNzQ0jR47k6hpCAzt06AC9Xo8dO3YgOjqa219SUoKMjAwcO3aM+2KKxWK0bdsWJSUluHTpEmdEc3Nzjdpx5swZ9OrVq1Y/8vLyjHTUmzdvjrFjx8LPzw+BgYFwdnaGlZUVOnXqBKVSCUdHRyQmJuLChQvcMeHh4ejQoQP3+ty5czh48GC9769YLMbQoUORlJSE7du3Iz4+3ugGMGfOHHTt2pV7vXbtWqxfvx5A1Q/UsJJWIpGgbdu2yMvLw+bNm/H5559j6NChUCgUta5JRMjLy8OWLVu4BMTp6elIT0/nonF4nh8kEgm++uorZGdnw9vbG7a2trCzs0PLli1x7NgxjB07tsFJu3keD03CuNdEJBLB0tISWq0WZWVlaNWqFWbPno1u3brh2rVrMDc3x44dO3Dx4kXI5XIAgLW1NZycnDBw4ECEhIRALpejoKAAZ8+ehVQqRWBgICQSCVxdXXHx4kUkJyfD09OTuxkQEUpKSozacfPmTdy8efOB2m7IqP7dd9/h1KlTRrK61tbWeOGFF3Dq1Clum4uLC2bPns1J9hqws7ODnZ1dnTe8AQMGGD1hLFu2rF7jbghftLKyQlRUFD755BP069cPCQkJXJ127doZ3YyOHz9udI7U1FRER0dj9+7dYIxhxowZ3GIjBweHOq+r1Woxffp07lrnz5832UaeZ5/KykrMmTMH7u7uWLJkCfz8/FBeXo7bt2/j7Nmz/FxKI9Ag484YswGwGkA7VPl53kZVCr1fALQAkAJgBBEVVtefBWAcAB2AyUR0oL7zGx7lBQIB+vXrB29vb2zZsgVCoRBmZmb44IMPIJFIUFBQALFYDFdXV3Tq1An29vZwd3eHVqvFgAEDEBQUBCsrK067OiwsDBqNBnK5HEqlEhMmTMD27du5EURUVBQ++ugjTJ8+vc7RZ008PT2RlZVlcr9AIMCqVasgFArx8ccf4/Dhw0b7P/jgA3h6ehoZ99zcXPz555/o1q0b7OzsuFhwIkJZWVmtlZ8AMHv2bHz77bfc69DQUGzevNlku2QyGfz9/WFjYwOhUAhHR8c6z1sf3bp14xZKGbL8TJ06FWKxuM749fLycpw8eRJ//PEHLl68iNdffx0+Pj7cBCrP80l+fj7y8/MxcuRIiMViVFZWorCwsMmuY3neaZAqJGNsHYCTRLSaMWYGQAbgUwAF9E+CbFsimsEY8wOwBf8kyD4MoBU9ZIJsiUQCKysr2NraQqfTITc3FwKBAOXl5ejXrx927NiBmJgYfPDBB3Bzc4Orqys8PT3h5uaGM2fO4Pr163BzcwMRIS4urtYIUiAQIDw8HHfu3MHFixdr9tnICLZv3x5Xr17FgAEDoNFo8Oeff3L1Jk2ahICAANy4cQPFxcW4cOECLl++jJEjR6Jv374AqlaUHjt2DG+//bbR9YVCITp06GAUVQMA165dg5ubG44ePVpvSry2bdsiJCTE5H57e3vMnj0bhw4dwqBBg6BSqRAYGAhzc3O8++67+O9//4vmzZvDw8ODO6agoAAJCQmQyWR49dVXIZVKER0djS+++IITCzOFIWH1kiVLUFFRgeLi4sc2p8LDw1OLh1eFZIxZAegO4C0AICI1ADVjbDCAntXV1gE4DmAGgMEAthKRCkAyYywBVYb+74a0lDGG1q1bQy6XIzExEWq1Gt7e3ggODkbPnj3h5uaGrVu34vvvv4dKpcLMmTNx9+5dxMbGIjMzE1qtFnK5HBMnTkSvXr2wY8cOFBUVYfHixUarQw3o9Xrs2rUL/fv3x+LFi7nt9vb28PPz417n5uZi1apV0Gq1EAgE6N+/P06cOIGKigpER0cjNDQUhw4dwtWrV7ljOnfujPHjx9fbX51Oh9jY2Dr90H//ff+3LD4+HvHx8Sb3u7u7Y8iQIZg1axYnHVxeXo7WrVtj3Lhx2LZtGw4dOgSgyiWmUChgbm6O9PR0uLu7Y9iwYcjKykKvXr3g6upq8jpEhD179kCpVCIsLAxbt27FuXPn7tt+Hh6eJ0NDns+9AOQCWMMY6wAgBsCHAJyIKBMAiCiTMWYQNHEBcLbG8WnV20wiFAoRGhqK1NRUtGrVCr6+vtizZw9GjRqFFi1a4K+//kLXrl3RrVs3AMDbb78NZ2dnXL9+HUuWLOHOk5mZiZMnT0Kj0eCbb76BUCiElZUVXnjhBaPoEG9vbxARJ0UrEAgQEhKCMWPGcHUSExOxZ88eGJ5sFAoFtm7dyo3mS0pK0LFjR6SmpiImJsbo2KZEdnY2Ro4cibt37+Kdd96BUCjktOVrIhKJ8Mknn2Dq1KkoKipCeno6SkpKIJfLuQgfUxICQNVN8urVq5g7dy6na/2wyOVylJeXP/TxPDw8DTPuIgABAD4gonOMsf8CmFlP/bqExGv5fhhjEwFMBKp+zC4uLpg1axZCQkIgk8kQEREBf39/iMVilJaWYuXKldi4cSOAqoiRadOmYf369di8eTMqKyu583p6emLixImYPHkyysrK4OrqCisrKzg7O0Mmk+HmzZvIysrCrFmzOFeIwY9fMyN8VlaWkYHJz8/HiRMnuPkBIsLnn3+OGzduQKVSISYmBnFxcY9k1AzaMobFUwaXka2tLc6fP4+bN2+itLTUKOrAzMzM6MbVvHlzdOvWDb///jtycnKgUqlw9+5dbr9Op0NJSYmR2BgA+Pj4YObMmbCyssLx48chEAjw66+/onXr1lwGqJoYjPr+/fuRlZWFM2fOoFWrVtDr9fD390diYqKRzvyDwIdF8vA8Og0x7mkA0ojI8Iy9DVXGPZsx1qx61N4MQE6N+m41jncFkHHvSYloFYBVAODk5ERDhw7FwIEDudFh586dubo9e/aEk5MT91qlUmHlypVQq9UYOnQozpw5wxmSy5cv41//+hciIiIgFothb28PV1dXDBkyBKWlpejVqxeuXbuGtLQ0o0gPW1tbdOr0j+vK398f4eHhDXh7qgydSqXCgAEDcPz4cfTp0wfe3t5o165dg443IJVKMXbsWLi7u+PVV1+FUChEs2bNuFWj2dnZ+Oijj7B9+3bumIiICHz++edG53B0dERkZCQ2btyIkpIS/Pbbb9wNQSgUon379khJSUFMTAwCAwOh1+u5CWWlUony8nKEh4cjPDzc5OQrEWH//v3Ys2cPNm/eDFdXV86lc+zYMTRkLscUfMgcz8Mgk8mg1Wr5wYGBhqwgBXASQOvq/78A8G11mVm9bSaAhdX/twVwGYAEgCeAJADC+s4fGBhYa1VjTQwJKh60uLq6UkBAAG3cuJF0Oh1pNBoKDQ2ts+4XX3xRbxvuh06no3nz5lFERAQtXLiQNmzYQNevXzeq8/PPPzeo3c7OzpSYmEgajYa+/PJLGjt2LFd8fHyM6n744Yf1tis5OZmsrKy4+lKplD777DMCQL6+vvT111/T+PHjKSAggF5++WXaunUrJSQk1Ktpo9PpSKVS0dq1a5908l++8IUv9ZdHXqH6AYBN1ZEySQDGAhAA+JUxNg5AKoDhAEBE8YyxXwFcA6AF8C+qJ1LGFESEs2fPIjs728hd8qDnWLFiBTp16sQlk35SCAQCzJo1CwDw+uuv45dffsGSJUvQpk2bBz5XVlYWJk2ahHnz5uH333+vd9FPUlISdu3aZXJ/bm6uyZHw9evXMW/ePG7VqYODA6RSKZo1a1bLv05UlcjbsLDr559/RkBAAHx8fHDr1q0H7iMPD8+TpUHGnYguAagr3KaPifrzAMx7kIZQ9WM8EeHChQucOyEpKemh4qMlEglmz56NgICAevOJPixarRZnz5418vcbUCgU6NOnDyoqKozi3a9du9bg8x8+fBjR0dGQy+VGMfglJSVGoYV79uzBnj17GnROxhheeuklODo6wtbWFiNGjEBoaChSUlKwd+9evP/++0bur5oolUq88847+Ouvv5CXl4eKigpotVp07twZd+/ehUql4heq8PA0JUwN6Z9m6dixI6WkpFBubi5lZWVRcHAwCYVCWrRoEZ06dYoGDBjQoEcUgUBAHTt2pJCQEBo4cCAVFhYSEZFWq6WLFy/S3bt3aeLEiRQSEkK2trYEVImKtWvXjlavXl2ve4OIqKKigs6dO0dnzpyhQ4cOUbNmzUggEHClbdu2ZG9vT19++SWdOnWKRowYYbT/QfOACoVC+vbbb2nnzp20c+dOio+PpxEjRjToWJlMRsHBwRQSEkI+Pj4kEolo8ODBlJqaSrt27aKoqChKT0+nq1evUkVFBel0OpOumJSUFDp48CCNGzeOFixYQO+99x7Z2tqSSCQiuVxO//nPfzgNeL7whS9PtTRtPXc3NzfOuKhUKurUqRMBVcbNoJLYkI66urpSamoqp1ZoMFbl5eXUrl07ioqKIo1GQ2q1msLDwwmo0lQ/c+ZMLTXDugxdYmIiZ9REIpHRtQUCAR04cIAGDhxopO74qB+e4T0QiUS0bdu2Bs8/tG/fnkpLS0mtVtPXX39NNjY2FBcXRxs2bKAWLVrQpEmTKCcnh+Li4kwadcP2HTt2cP2RyWQkFAqN+lZTgZMvfOHLUy1NWxVSJBJx4X8ikQhffPEF8vLykJqaip9//rlWSJ2NjQ0cHR1BREhNTeXcFOPHj+fyf96LVquFTqczkjowIBQKjUIck5OTcebMGQQFBXF1JBIJ9Ho9NBqNyeXUQqGQ8+0/LhdFTV16eoAIFMMK26KiIvzyyy/47LPPUFRUhH//+9/IyMjAqFGjoFAoTMouEBGKi4tx8eJFLFu2jOtzXWnvTGnnPwjW1tYoLy+HmZkZKioqHinahoeHp4kIh9WUiRUIBBg4cCCAKgMjkUgwY8YMo/pvvPEGFi5ciIqKCvTq1QtxcXEAgI0bNyIsLMykn33z5s0YOXIknJ2d62wHEeHSpUt47bXXcOfOHUgkEm5fmzZtOKXExmTYsGGIjY01WglbH+Xl5UhNTYW7uzsOHjyI0aNHw97evpbcQU2ICJs2bcIPP/yA1NRUiMXix9V8k3Tu3BlXrlyBr68vTp06xUsW8PA8IrWHuI2AqWgOxhhatmwJmUxmtF0sFnPKj3fu3IFYLIajoyNKSkowe/ZsVFRUICcnB9nZ2cjOzkZOTg50Oh2io6Oxbt06ZGdncxOhRASNRoOysjLk5ORg8eLFSEpKgk6ng1KphJmZGSwsLCCTySAUCuHg4GBygrawsNCkUTKoXZrC0tKy3nMbRuLdu3fH0qVLYWdnV2c9sVgMBwcH2NnZobKyEnl5efD09MS2bdugUqnw5ZdfYsqUKbC2tq7zeCLiVv5WVlbC0dERQqGQe48NCbIfNwcPHkRmZiaOHDnCG3YensdBY/vbiQj+/v6k0WiouLiYdDodFRcXU0FBARUUFFB6ejoNGTLEyM9kiO3+7bffiDFGXbt2pczMTMrOzqb8/Hy6c+cOeXl5cYmdHRwcOL+wXC4nhULBZf5hjNGaNWtowYIFpFAoSCKRcNdhjNG2bdu482o0Grpy5QrZ2NjU6f+ytrY2mVGobdu29O2335r0nX399dcUHx9PDg4Ode63tLSk27dv0/vvv08ODg61fP6GYmFhQV27dqWDBw/Sjz/+SOHh4TR37lwuj6sp1Go1RUdH065duyggIIBEIhHZ29tzfbW0tKQ333yTQkJCHstcAl/4wpfHUpq2z50xhunTp2Pv3r146623cOjQISO98YKCgjqP02g0ICKYmZlBoVBw7p2SkhLk5eXV0mgHqtwUNWUFpFIp/P39sWPHjlpJNxhjsLa2hqOjI7etpjTvvRQXF5vso7u7ey09l5rk5eWhRYsWWL9+PTdy1el0mDlzJhISEqDRaFBQUIDS0tJ6VSIrKiqgUCjg7e2N0NBQREZGQigU1jkPUZOjR49i1qxZ0Ol0uHLlCgBwGa0AoLS0FBs2bKj3HDw8PE2HJmHc9Xo99u7di9u3b+Pbb7+FSqV6oLRcer0elZWVnAFryGO9RCKBu7s7xo8fjzZt2jyRGO3u3bvj/PnzqKysRNeuXWuloKvJqlWrkJmZiY8//phzQ2m1Wk43prKyElFRUfUadqBKp+fFF1/Er7/+iqtXr+Knn34y6TMnIuh0OmRlZcHMzAz+/v7IysrijDsPD8+zS5Mw7kKhEOPHj8eCBQvw448/Yu7cuUba6nVhiH4BgOjoaHTu3JnTQVGr1SgrKwMAbtu9ES4LFy5EZGQkGGP4+uuv8dtvv9XZLsYYZwQNr8ViMUQikcmoGUMu0bCwMKhUKly4cAEtW7asNbIXCoVcH8rKyrBlyxbs2rXLKGlHzRvVpk2bjETFDP8bziEUCqFUKnHr1i307dsXQ4YMMZoUrolSqcRvv/2GHTt2QKlUonfv3oiLi4OjoyNat279wFmoeHh4mhZNwrgDwL/+9S+Ym5vj999/56R4DTDGjFwhAoEAK1eu5OR+y8vLkZKSwiVwVqlUEIlEkMlk2LhxI6ysrPDxxx9z6oiGiVpra2uoVCoMGjQIGRkZRgbthRdewOLFi9GxY0ecPn0aP/30E5YvXw4HBwf8+eefKC4uRkRERJ3ZmYYPH46PP/4Ybm5uGDhwIJYtW4ZPP/3UKGRQJBIhODi4Vgqy+z2xGOr6+/uja9euyM7OxpkzZyCRSLBixQowxtCuXbv7ZpbKyMjARx99BLVajWbNmmHnzp2oqKhAVlbWIylb8vDwNA2ajHGXy+X44IMPUFhYiCtXruDSpUvcvunTp6N///7ca1dXV9jb2+PmzZtYv349iouLUVpayqWwc3Jywvbt22FtbY3g4GCYmZnhwIEDRsbVELkikUjQqVMn7N2716g9Wq0Wubm5uHjxIv744w9cu3YNer0e5ubmCAwMRHFxca3cpwDg4OCAyZMnIzg4GADQrFkzuLm5ISEhAU5OTujQoQNu3ryJyspKnDlz5qHfr5iYGMTGxkIqlaJ9+/ac9G9oaGi9x2k0Gvz0009QqVRYsmQJBAIBoqKi+BynPE0KqVQKLy8vZGVlGc398DwAjR0pQ2SsCllzhaqhrFmzps4Ij6tXr9K8efNo7NixJJfLufoeHh5UVFRkMjKkLs6ePUthYWGcymFQUBCnjqjVaunq1atGq1iLiorI19eXLCwsyMLCgiwtLSksLIzOnDlTa8Xn/PnzCQCNGTOGysrK6LfffiNzc/NHnik3NzensLAwOnToEFVUVJBara63jxqNhm7dukULFiygW7du0bZt28jNzY2PfuFLkysCgYDs7e2Nftd8qbM07WiZkpISlJaWwtLSEmq1usFxzr6+vsjNzUV+fj5WrVqFqKioh07t9uKLL2LNmjXo2rUrbt68ifj4eERERGDTpk11arNbWlpi3759Rn53Z2dnyOVyk9cQCASQy+UYMGAA2rRpY/R00lCaN2+OjIwMyOVyrFmzBlZWVgCqnkDqE0gjIhQUFCA7OxtdunTBjRs3sGHDBrRp0wYCgQB37tx54Lbw8DxOJBIJ99vX6/VNcsQul8tRUVHxTIjkNQnjnp2djYiICHTs2BHZ2dm11BPXrFnDuVzqIiMjA8uXL+cMbXl5ObZv3w5HR0f4+vpCr9cjPj6e82dbWFjg+vXrnFQtYww2Nja4c+cOZ+Ts7Ozg6emJffv2wdfXF3K5HEFBQVzES0VFBZydnbkJSyLiXCUXLlyAXq+Hg4MDLCwscPDgQYjFYpw7dw7r1q3Dm2++iXHjxiEqKgofffQRN+lbWVmJffv2GS2wunDhAkpLS2FlZYWxY8ciICAAX375Jb766iv07Nnzvr51A1euXMHJkyfRqVMnHDhwAAkJCejYsSNCQkJQUFBgJCtw8uRJo/e7vLwc2dnZRuerb0L5ceLi4oK8vDyTN3xDmKdWq+UlC3ieOE5OTkhNTX0mjDtrCj8IS0tLMkS3PE6EQiGkUimAqugQwwdiMND1aaJ4e3tj0KBB3Gu5XI7g4GD4+vrCzs6OWyFqGC3rdDoMHDgQhw8fhl6vBxHhm2++wcSJE5GSkgKdToc9e/bA3Nwc06ZN43Karlq1igtVzMvLQ58+fWqNWOzs7DBy5Eh8+umnuHr1KqZNm4bt27ejdevW9Y7W9Xo94uLijBJ9i0Qi6HS6eg3h3r17jeYgioqKcPnyZeTm5sLf3x8ikQhyuRyHDx82metUIBAY/QAYY1x0T7t27SCTyZCUlIT8/HwQEZc1y9fXF5WVlUhKSjI6nyFxes3VyjKZDKNGjYKrqyuWLl2K9evXw8XFBcOHD8eaNWvqXXfQUJydnaFUKutcM1EXZmZmiIyM5J6ogKrPz8zMDETEfV4FBQU4ceIEzp8/D0dHR3Ts2BFqtRpisRh3795Ffn4+iouLn0guWUOAwrNgoHiqVp23aNECt2/frmt3DBHVJcfeNIy7XC6nugSpmhqMMVhZWaFHjx4IDAxEUFCQUf5SrVYLMzMzZGRk4PLly7C3t0enTp2QmpqKxMREpKam4saNG5BIJMjKykJycjIsLCy4H7xer0dxcTFneAUCAWbMmIHIyEj4+PhAKBQiMzMTxcXF8Pb2Nhm/bkhW7eDggLS0NBw7dgx2dnYoKSmBv78/Tp06haNHj5rsZ0pKilGCFLFYDIlEwoWXSqVSyOVyFBUVcaN3Q8iovb09OnTogNdffx15eXlcyjMfHx+4uFTlSffw8ICzszOKioqQkJAAnU4HqVQKb29vWFtbQ6fT4d6bPWMMlpaWRjdmnU4HiUSCK1euYMqUKTh+/Djc3Nzg4uKChISE+64JaAjm5ubQarUNfkoxLHyruWisRYsWsLCwMKpHRMjJycGtW7fg7OyMIUOG4M8//0ROTg5cXFzQr18/JCUl4dChQ4/dCDdr1gzDhw/Hjz/+yD3NMsbg4+PDfZ+pWpSvoTe1pk7NQdC9Ns/w3TV1XKtWrVBQUAC1Wm305P4ga3EeBcYYzMzMTD29Nm3jLpVKqa6kF02de1d9+vr6IiQkhDO+27ZtQ3JyMjfBYW5uzmniNOR9F4lEWLVqFWdYSkpKEBQUhG7dupkcsWu1WpSXl2Po0KGIi4uDVqtFcXExWrVqheTkZKjVaq49ppBIJEbx8UQEpVIJnU4HKysrDB48GNbW1khOTkabNm0gEokQGBiI+Ph49O/fH/7+/ibnAIiIS/Qhl8vrXdhVHxUVFaisrISZmRn69u2Ls2fPPtR5/lcxMzPjVngbsLOzM8qZW1RUZJSPtK5jHpXBgwcjPT0dFy5cqHO/ubk5RCJRrZu9AcYY5zY1hZubG1q2bMm9LiwsRFxcHAICAmBrawsPDw9Mnjy5TsVTmUyGn3/+GRs3bkRiYiL3u8jKyqozDBqoep/EYvETeeqqg4c37oyx1gB+qbHJC8BsAOurt7cAkAJgBBEVVh8zC8A4ADoAk4noQH3XEAgE1BRuMo+C4UN/GNEriUTCGd17kclkEIlEePXVV2Fubo7IyEij5OE1USqVOHr0KPz8/KDVatG/f3/07dsXL7/8Mrp06YKVK1ciPT2dy5wUGxuL4uJiTJs2DaWlpdxjX3h4OPr3749t27ahrKwMlZWVWLduHYqKivDKK69g9OjRGDZsGAQCAbew636Ul5dj7969yM3NxaZNm5CTk4NXX32V+9EpFAoMHjzYSHq5srISQqGwzpBTA0SEffv2Yfz48cjMzES7du0QEhKC3bt3Iycnx+RxPKYRiUQIDw9HbGyskdx2SEgIrK2tkZKS8tgWubVp06beTGvNmzdHcHAwjhw5Uuf6C6FQiKlTp8LDwwO9e/eGi4sLTp8+jcTExHqvaxDiY4whPz8fX331VZ1Z1QBwrt2GjtT79esHDw8PrF279onOS4nFYmg0msczcmeMCQGkA3gRwL8AFBDRN4yxmQBsiWgGY8wPwBYAwQCaAzgMoBXVk0e1OhTvqWFpaQlzc3MjLRlra2tOR9zgj6zvgxGLxRg4cCDkcjkEAgHGjBkDKysrxMfHg4iQlZWFlStXGt3dO3fujDFjxiA/Px8nT57E9evXMW7cOPTr1w9Hjx7Fv//9b6ORklQqxU8//QQXFxeEhoYajaoM3LhxAxcvXkR0dDQSEhLg6OiIVatWQaPRICUlBUKhEJ6enpzRVKlU+Pzzz5GRkcGdY8qUKViyZAk2bdoEAPjPf/6Drl27YsqUKVCpVLC1tUWrVq24+gqFAhMnTuTaIxAI4O7uXq808O7duzFnzhzExMTUuf+FF17AL7/8gtTUVJw+fRrJycmca8vT05Or5+npCR8fH7Rv3x5paWnIzc3F9evXsWzZMgQHB2PZsmXw9PTE7NmzMX/+fPj7+0Or1TZYIrkh1PcY31SRSqUNNk7+/v44ceIE3nzzzXrz8z4NXFxcYG5ujtTUVJPqsQZcXV1hYWGBjIyMZ9KdFBgYCCcnJxw8ePC+N4VmzZrhxx9/RFhYmEnj/qDRMn0AJBLRHcbYYAA9q7evA3AcwAwAgwFsJSIVgGTGWAKqDP3fpk76tCIvDIwePRrp6enYvXs3t+2dd95B7969YWlpCYlEgrS0NJw6dYr7Eefn52PDhg1cO6VSKZYsWQJ3d3fuHHq9HgEBARAIBGCMISIiwmhy1N7eHh4eHiAiDB06FAsXLkRpaSny8/Mhk8kgl8s54+7l5YU33ngD3t7euHbtGhISEhAUFAQvLy/IZDJuMlitVsPJyQmvvvoq7O3t4e7uDsYYJBIJWrduDaVSif3790Oj0UAul6Nly5ZcflegylC5uLjA3t7e6D3q0qUL5+ownM/AzZs30b17d1RUVMDMzAxOTk44cOAA3N3dUVhYiN27d4OIjITS9u/fX2uStCbx8fEICgqCSqWq9V04fvx4rfoymQxqtdqo7u3btzF//nxIJBIcPHgQAB6rUTdgaWn5TBkPgUAADw+PBuciLikpwR9//IHMzMwn3LL7k56e3uC6aWlpT7AlT54333wT48ePx0svvVTvAkeBQID3338fr7zySr3ne1DjPgpVo3IAcCKiTAAgokzGmEE60QVATQdoWvU2k0ilUqhUKqjVaohEIuj1enh5eaG8vPyBvmCvv/46bG1tsWvXLmRmZpocXZ0+fbrWKJiI0Lt3b87NkJGRgdWrV3PnMDWSrzkZOnXqVMTGxqJv377o168fmjdvDldXV66uYbKKMYZffvkFq1evhkwmw3fffceNSuzs7FBWVoasrCwsXboUS5YsARHBw8MDPj4+CAoKglQqxdmzZ1FRUYF+/fpxrgmlUonAwEAsXrwYRISkpCTs2LEDUVFRUCqVKCsrg1wuR2lpKXdzYIxhx44dtfpmMOaxsbFYvHix0QSrQeIAqHqCsbW1hUQigVarxYcffohNmzahY8eORprzRFTnk4cBvV7/QD5KpVIJPz8/ODo64tq1a8jJyUFJSQnOnTuH4uJizijU7JdIJIJQKHxkvfhnybADVe/tgySZT0xMxKhRo55gi5o+FhYWJv38T4q9e/fi4MGDtULB78XBwQGjR4++rzu0wcadMWYGIBzArPtVrWNbLSvLGJsIYCJQ1djvvvsOa9eu5Xx6ffr0wblz5xps3Fu2bImIiAi0bt0aEyZMQPfu3U1qpBhUDxUKBby8vBAXF4fVq1dDo9FgypQpcHd3h0ajgUAgQPPmzREfH3/fiAUiQlxcHE6fPg2ZTIbevXtj6dKl+P333+Hn5weBQIDevXtj8uTJAIARI0Zwj2E5OTm4efMmkpOT0bFjR2zfvh3nzp1DTk4OAgICMHfuXC570t69e5GXl4eIiAjcvHkTS5cuhU6n4wydu7s7zp49i5s3b+LTTz+FWCzGsWPHIBAIcPLkScycORNFRUUAgLZt28LS0hI5OTlGPsrjx48jIyMDd+7cQVlZGfLy8rg1AQZqpkUMDQ0FESEjIwP79u0DACxYsAC9evXi6qekpOCnn35CVFQUWrRogcrKyvv6ReujZcuWWLRoEZKSkrhMXQUFBSbloQFwIao8j4aVldVTv8HZ2dnB1tb2kb4zD0JjJIw5fPhwg+p5enoiNTX1vk81DzJyHwAglogMq1myGWPNqkftzQAYZq/SALjVOM4VQAbugYhWAVgFAJ06dSKxWAxXV1e4uLggNzcX//d//2fyhygSidCvXz8AwJEjRxAQEMDNTo8YMQLvvfdeg8LHXnnlFfzf//0fevTogZiYGBw5cgRWVlbo378/srKysHjxYvTv3x+hoaG1XAp6vR7Xrl1DUVERvL29uUkXADhz5gwUCgW0Wi2ysrIwfPhwNG/eHAEBAUarUj09PdGyZUswxhAYGIhFixahU6dOeOONN7B//37MmTMHc+fOxZYtW3Dy5Ens378fly5dMopBr6ysREZGBlJTU8EY41xNhjyuHh4ecHR0hLW1NeLj4zk3kUAgwNSpU9GhQwfMmDEDx44d487p5eWFpKQkHDlyBD4+PvD3969l3Gu+v127doVMJoOZmRmsrKyQn5+P5ORkODg4cHUWLVqELVu2QCaT4b333sPdu3fxzTff3PczqguDC+vjjz/GjRs3oNfrDZNL9R73MCGFz6J//Unj5OT01I17WVlZndEsT4r7fZcak/PnzxsNnExiSpfg3gJgK4CxNV5/C2Bm9f8zASys/r8tgMsAJAA8ASQBENZ37rZt21JUVBS5urpSUFAQeXt716un4OzsTLt27aLDhw+Th4cHRUREkEAgICsrK2KMcVmX7lfGjh1LKpWKgoKCjLabmZnRoEGDSKPRkF6vp4kTJ9Z5vJmZGZmbm9Obb75JaWlp1KtXLwJAUqmU4uPjae/eveTn52dUXyKRcCU0NJRUKhUVFBRQ3759ycnJibKzs4mISKfTUVlZGb322mvc8a+//jqVlJRQRUUFV+rL7gRUZZ5atGgR5eXlUUREhNE+sVhMEomE09MxlPreP8YYOTg4GOnRSKVSWrhwIU2YMIFsbW2Nzm0oNc/p7OxMLVu2fGg9jaCgICotLaXRo0dz29q1a/dENHIUCgXJZLLHft5nsVhZWTV6G/hSq5jUlmmoYZcByAdgXWObPYAjAG5X/7Wrse8zAIkAbgIYcL/zt2rVit577z0CqoxHQ36kgwYNok8//ZQEAgHJZDLq378/ffHFFxQYGEgTJ05skDCXKePOGKNhw4ZxAmAxMTG1vtiMMWrevDm5ubmRh4cH9ezZk9zd3Qn4x7jr9XrKzMykvn371nn9oKAgysnJoSlTppBAICCFQkGZmZlkQKVSUf/+/bn6Xbt2pYKCAqrJ999/f99+CoVC8vb2NpkC8EHKsGHD6OjRo3W+vxYWFg02APfeUB6kBAcHk1qtpsjIyMb+YTVKsbW1NZlm8UkWw2fGGHvg75KzszO5ubkZpbF8mkUikTzWm3/Nc7m5udGLL77YWN+HRzPuT7q0bNmSBg8e/ECdWr58ORUWFpKvry91796dKisrSalUUlFRESUnJzfIyNRl3N3d3emHH36g69evc8ZdpVJRjx49jI61tLSkK1euUGFhIRUWFlJ+fj5169aNgH+M+9mzZ6mgoIAOHTpEERERNH/+fKOyYsUKGjhwIPejEYlENHXqVNLpdNzofd++feTh4UGjR4+m5OTkWoqTDTHuhmIYVT9sEYvFdPDgQYqPjyepVFprv1AofCpG53/ZuAuFQurevbvJPL5Po4hEInJyciKg6snwfp+5mZkZnTx5kvLz82nKlCmP9NT2sOXdd999LEqshjJmzBh66623iDFGo0ePpu3btz/1PlV7OEwa9yaxQpUxVoqqUf7zhAOAR1//3nTg+9P0ed76xPfn/ngQUZ3qgU1CFRLATTIRiP+swhi78Dz1ie9P0+d56xPfn0dDcP8qPDw8PDzPGrxx5+Hh4XkOaSrGfVVjN+AJ8Lz1ie9P0+d56xPfn0egSUyo8vDw8PA8XprKyJ2Hh4eH5zHS6MadMfYyY+wmYyyhWjq4ycMYc2OMHWOMXWeMxTPGPqzebscYO8QYu13917bGMbOq+3iTMda/8VpvGsaYkDF2kTG2t/r1s94fG8bYNsbYjerPqvOz3CfG2NTq71scY2wLY8z8WeoPY+xnxlgOYyyuxrYHbj9jLJAxdrV6XxRrSEKBJ4SJPn1b/Z27whjbyRizqbHv6fWpMRcvARCiaiWrFwAzVMkW+DX2oqoGtLsZgIDq/y0B3ALgB2AhjCUZFlT/7wdjSYZE3EeSoZH69RGAzQD2Vr9+1vuzDsD46v/NANg8q31ClbJqMgBp9etfAbz1LPUHQHcAAQDiamx74PYDOA+gM6pECvehAavgn3KfXgIgqv5/QWP1qbFH7sEAEogoiYjUqNKvGdzIbbovRJRJRLHV/5cCuI6qH99gVBkUVP8dUv3/YFRr3BNRMgCDxn2TgTHmCmAggNU1Nj/L/bFC1Q/vJwAgIjURFeEZ7hOq1qVIGWMiVEmCZOAZ6g8RnQBwr2znA7W/WqTQioj+piqruL7GMU+duvpERAeJyKA1fRZV4onAU+5TYxt3FwB3a7y+r/Z7U4Mx1gKAP4BzuEfjHkBNjfum3s8lAKYDqCmd+Cz3xwtALoA11a6m1YwxOZ7RPhFROoDvAKQCyARQTEQH8Yz2pwYP2n6X6v/v3d5UeRtVI3HgKfepsY17g7TfmyqMMQsA2wFMIaL6NFCbdD8ZY2EAcoio7hx4dRxSx7Ym059qRKh6XF5ORP4AylH12G+KJt2nal/0YFQ9zjcHIGeMja7vkDq2NZn+NABT7X9m+sUY+wyAFsAmw6Y6qj2xPjW2cW+Q9ntThDEmRpVh30REO6o3Z1c/YoE9hMZ9I9IFQDhjLAVVrrHejLGNeHb7A1S1MY2IzlW/3oYqY/+s9qkvgGQiyiUiDYAdAELx7PbHwIO2Pw3/uDlqbm9SMMYiAYQBiKh2tQBPuU+NbdyjAbRkjHmyqkxPowDsvs8xjU71TPZPAK4T0eIau3YDiKz+PxLA7zW2j2KMSRhjngBaomoCpUlARLOIyJWIWqDqMzhKRKPxjPYHAIgoC8Bdxljr6k19AFzDs9unVAAhjDFZ9fevD6rmep7V/hh4oPZXu25KGWMh1e/DmBrHNAkYYy+jKp90OBHVzDDydPvUWLPMNWaWX0FVtEkigM8auz0NbHNXVD02XQFwqbq8gseocd+IfeuJf6Jlnun+AOgI4EL157QLgO2z3CcAXwK4ASAOwAZURV08M/1BVf7lTAAaVI1Wxz1M+wF0qn4PEgEsRfVizCbUpwRU+dYNtmFFY/SJX6HKw8PD8xzS2G4ZHh4eHp4nAG/ceXh4eJ5DeOPOw8PD8xzCG3ceHh6e5xDeuPPw8PA8h/DGnYeHh+c5hDfuPDw8PM8hvHHn4eHheQ75fy+gRs+IbwWRAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "img = cv2.imread('C:/Users/Hripsime/Videos/Lane-Detection/test_images/test6.jpg')\n",
    "\n",
    "binary_thresh = binary_thresholded(img)\n",
    "out_img = np.dstack((binary_thresh, binary_thresh, binary_thresh))*255\n",
    "binary_warped, M_inv = warp(binary_thresh)\n",
    "plt.imshow(out_img, cmap='gray')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 4: Detection of Lane Lines Using Histogram ###\n",
    "\n",
    "def find_lane_pixels_using_histogram(binary_warped):\n",
    "    # Take a histogram of the bottom half of the image\n",
    "    histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)\n",
    "    \n",
    "    # Find the peak of the left and right halves of the histogram\n",
    "    # These will be the starting point for the left and right lines\n",
    "    midpoint = np.int(histogram.shape[0]//2)\n",
    "    leftx_base = np.argmax(histogram[:midpoint])\n",
    "    rightx_base = np.argmax(histogram[midpoint:]) + midpoint\n",
    "\n",
    "    # Choose the number of sliding windows\n",
    "    nwindows = 9\n",
    "    # Set the width of the windows +/- margin\n",
    "    margin = 100\n",
    "    # Set minimum number of pixels found to recenter window\n",
    "    minpix = 50\n",
    "\n",
    "    # Set height of windows - based on nwindows above and image shape\n",
    "    window_height = np.int(binary_warped.shape[0]//nwindows)\n",
    "    # Identify the x and y positions of all nonzero pixels in the image\n",
    "    nonzero = binary_warped.nonzero()\n",
    "    nonzeroy = np.array(nonzero[0])\n",
    "    nonzerox = np.array(nonzero[1])\n",
    "    # Current positions to be updated later for each window in nwindows\n",
    "    leftx_current = leftx_base\n",
    "    rightx_current = rightx_base\n",
    "\n",
    "    # Create empty lists to receive left and right lane pixel indices\n",
    "    left_lane_inds = []\n",
    "    right_lane_inds = []\n",
    "\n",
    "    # Step through the windows one by one\n",
    "    for window in range(nwindows):\n",
    "        # Identify window boundaries in x and y (and right and left)\n",
    "        win_y_low = binary_warped.shape[0] - (window+1)*window_height\n",
    "        win_y_high = binary_warped.shape[0] - window*window_height\n",
    "        win_xleft_low = leftx_current - margin\n",
    "        win_xleft_high = leftx_current + margin\n",
    "        win_xright_low = rightx_current - margin\n",
    "        win_xright_high = rightx_current + margin\n",
    "        \n",
    "        # Identify the nonzero pixels in x and y within the window #\n",
    "        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & \n",
    "        (nonzerox >= win_xleft_low) &  (nonzerox < win_xleft_high)).nonzero()[0]\n",
    "        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & \n",
    "        (nonzerox >= win_xright_low) &  (nonzerox < win_xright_high)).nonzero()[0]\n",
    "        \n",
    "        # Append these indices to the lists\n",
    "        left_lane_inds.append(good_left_inds)\n",
    "        right_lane_inds.append(good_right_inds)\n",
    "        \n",
    "        # If you found > minpix pixels, recenter next window on their mean position\n",
    "        if len(good_left_inds) > minpix:\n",
    "            leftx_current = np.int(np.mean(nonzerox[good_left_inds]))\n",
    "        if len(good_right_inds) > minpix:        \n",
    "            rightx_current = np.int(np.mean(nonzerox[good_right_inds]))\n",
    "\n",
    "    # Concatenate the arrays of indices (previously was a list of lists of pixels)\n",
    "    try:\n",
    "        left_lane_inds = np.concatenate(left_lane_inds)\n",
    "        right_lane_inds = np.concatenate(right_lane_inds)\n",
    "    except ValueError:\n",
    "        # Avoids an error if the above is not implemented fully\n",
    "        pass\n",
    "\n",
    "    # Extract left and right line pixel positions\n",
    "    leftx = nonzerox[left_lane_inds]\n",
    "    lefty = nonzeroy[left_lane_inds] \n",
    "    rightx = nonzerox[right_lane_inds]\n",
    "    righty = nonzeroy[right_lane_inds]\n",
    "\n",
    "    return leftx, lefty, rightx, righty\n",
    "\n",
    "\n",
    "def fit_poly(binary_warped,leftx, lefty, rightx, righty):\n",
    "    ### Fit a second order polynomial to each with np.polyfit() ###\n",
    "    left_fit = np.polyfit(lefty, leftx, 2)\n",
    "    right_fit = np.polyfit(righty, rightx, 2)   \n",
    "    \n",
    "    # Generate x and y values for plotting\n",
    "    ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )\n",
    "    try:\n",
    "        left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]\n",
    "        right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]\n",
    "    except TypeError:\n",
    "        # Avoids an error if `left` and `right_fit` are still none or incorrect\n",
    "        print('The function failed to fit a line!')\n",
    "        left_fitx = 1*ploty**2 + 1*ploty\n",
    "        right_fitx = 1*ploty**2 + 1*ploty\n",
    "    \n",
    "    return left_fit, right_fit, left_fitx, right_fitx, ploty\n",
    "\n",
    "def draw_poly_lines(binary_warped, left_fitx, right_fitx, ploty):     \n",
    "    # Create an image to draw on and an image to show the selection window\n",
    "    out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255\n",
    "    window_img = np.zeros_like(out_img)\n",
    "        \n",
    "    margin = 100\n",
    "    # Generate a polygon to illustrate the search window area\n",
    "    # And recast the x and y points into usable format for cv2.fillPoly()\n",
    "    left_line_window1 = np.array([np.transpose(np.vstack([left_fitx-margin, ploty]))])\n",
    "    left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([left_fitx+margin, \n",
    "                              ploty])))])\n",
    "    left_line_pts = np.hstack((left_line_window1, left_line_window2))\n",
    "    right_line_window1 = np.array([np.transpose(np.vstack([right_fitx-margin, ploty]))])\n",
    "    right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([right_fitx+margin, \n",
    "                              ploty])))])\n",
    "    right_line_pts = np.hstack((right_line_window1, right_line_window2))\n",
    "\n",
    "    # Draw the lane onto the warped blank image\n",
    "    cv2.fillPoly(window_img, np.int_([left_line_pts]), (100, 100, 0))\n",
    "    cv2.fillPoly(window_img, np.int_([right_line_pts]), (100, 100, 0))\n",
    "    result = cv2.addWeighted(out_img, 1, window_img, 0.3, 0)\n",
    "    \n",
    "    # Plot the polynomial lines onto the image\n",
    "    plt.plot(left_fitx, ploty, color='green')\n",
    "    plt.plot(right_fitx, ploty, color='blue')\n",
    "    ## End visualization steps ##\n",
    "    return result\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 5: Detection of Lane Lines Based on Previous Step ###\n",
    "\n",
    "def find_lane_pixels_using_prev_poly(binary_warped):\n",
    "    global prev_left_fit\n",
    "    global prev_right_fit\n",
    "    # width of the margin around the previous polynomial to search\n",
    "    margin = 100\n",
    "    # Grab activated pixels\n",
    "    nonzero = binary_warped.nonzero()\n",
    "    nonzeroy = np.array(nonzero[0])\n",
    "    nonzerox = np.array(nonzero[1])    \n",
    "    ### Set the area of search based on activated x-values ###\n",
    "    ### within the +/- margin of our polynomial function ###\n",
    "    left_lane_inds = ((nonzerox > (prev_left_fit[0]*(nonzeroy**2) + prev_left_fit[1]*nonzeroy + \n",
    "                    prev_left_fit[2] - margin)) & (nonzerox < (prev_left_fit[0]*(nonzeroy**2) + \n",
    "                    prev_left_fit[1]*nonzeroy + prev_left_fit[2] + margin))).nonzero()[0]\n",
    "    right_lane_inds = ((nonzerox > (prev_right_fit[0]*(nonzeroy**2) + prev_right_fit[1]*nonzeroy + \n",
    "                    prev_right_fit[2] - margin)) & (nonzerox < (prev_right_fit[0]*(nonzeroy**2) + \n",
    "                    prev_right_fit[1]*nonzeroy + prev_right_fit[2] + margin))).nonzero()[0]\n",
    "    # Again, extract left and right line pixel positions\n",
    "    leftx = nonzerox[left_lane_inds]\n",
    "    lefty = nonzeroy[left_lane_inds] \n",
    "    rightx = nonzerox[right_lane_inds]\n",
    "    righty = nonzeroy[right_lane_inds]\n",
    "\n",
    "    return leftx, lefty, rightx, righty\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 6: Calculate Vehicle Position and Curve Radius ###\n",
    "\n",
    "def measure_curvature_meters(binary_warped, left_fitx, right_fitx, ploty):\n",
    "    # Define conversions in x and y from pixels space to meters\n",
    "    ym_per_pix = 30/720 # meters per pixel in y dimension\n",
    "    xm_per_pix = 3.7/700 # meters per pixel in x dimension\n",
    "    \n",
    "    left_fit_cr = np.polyfit(ploty*ym_per_pix, left_fitx*xm_per_pix, 2)\n",
    "    right_fit_cr = np.polyfit(ploty*ym_per_pix, right_fitx*xm_per_pix, 2)\n",
    "    # Define y-value where we want radius of curvature\n",
    "    # We'll choose the maximum y-value, corresponding to the bottom of the image\n",
    "    y_eval = np.max(ploty)\n",
    "    \n",
    "    # Calculation of R_curve (radius of curvature)\n",
    "    left_curverad = ((1 + (2*left_fit_cr[0]*y_eval*ym_per_pix + left_fit_cr[1])**2)**1.5) / np.absolute(2*left_fit_cr[0])\n",
    "    right_curverad = ((1 + (2*right_fit_cr[0]*y_eval*ym_per_pix + right_fit_cr[1])**2)**1.5) / np.absolute(2*right_fit_cr[0])\n",
    "    \n",
    "    return left_curverad, right_curverad\n",
    "\n",
    "def measure_position_meters(binary_warped, left_fit, right_fit):\n",
    "    # Define conversion in x from pixels space to meters\n",
    "    xm_per_pix = 3.7/700 # meters per pixel in x dimension\n",
    "    # Choose the y value corresponding to the bottom of the image\n",
    "    y_max = binary_warped.shape[0]\n",
    "    # Calculate left and right line positions at the bottom of the image\n",
    "    left_x_pos = left_fit[0]*y_max**2 + left_fit[1]*y_max + left_fit[2]\n",
    "    right_x_pos = right_fit[0]*y_max**2 + right_fit[1]*y_max + right_fit[2] \n",
    "    # Calculate the x position of the center of the lane \n",
    "    center_lanes_x_pos = (left_x_pos + right_x_pos)//2\n",
    "    # Calculate the deviation between the center of the lane and the center of the picture\n",
    "    # The car is assumed to be placed in the center of the picture\n",
    "    # If the deviation is negative, the car is on the felt hand side of the center of the lane\n",
    "    veh_pos = ((binary_warped.shape[1]//2) - center_lanes_x_pos) * xm_per_pix \n",
    "    return veh_pos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "### STEP 7: Project Lane Delimitations Back on Image Plane and Add Text for Lane Info ###\n",
    "\n",
    "def project_lane_info(img, binary_warped, ploty, left_fitx, right_fitx, M_inv, left_curverad, right_curverad, veh_pos):\n",
    "    # Create an image to draw the lines on\n",
    "    warp_zero = np.zeros_like(binary_warped).astype(np.uint8)\n",
    "    color_warp = np.dstack((warp_zero, warp_zero, warp_zero))\n",
    "    \n",
    "    # Recast the x and y points into usable format for cv2.fillPoly()\n",
    "    pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])\n",
    "    pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])\n",
    "    pts = np.hstack((pts_left, pts_right))\n",
    "    \n",
    "    # Draw the lane onto the warped blank image\n",
    "    cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))\n",
    "    \n",
    "    # Warp the blank back to original image space using inverse perspective matrix (Minv)\n",
    "    newwarp = cv2.warpPerspective(color_warp, M_inv, (img.shape[1], img.shape[0]))\n",
    "    \n",
    "    # Combine the result with the original image\n",
    "    out_img = cv2.addWeighted(img, 1, newwarp, 0.3, 0)\n",
    "    \n",
    "    cv2.putText(out_img,'Curve Radius [m]: '+str((left_curverad+right_curverad)/2)[:7],(40,70), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1.6, (255,255,255),2,cv2.LINE_AA)\n",
    "    cv2.putText(out_img,'Center Offset [m]: '+str(veh_pos)[:7],(40,150), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1.6,(255,255,255),2,cv2.LINE_AA)\n",
    "    \n",
    "    return out_img\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "global left_fit_hist \n",
    "left_fit_hist = np.array([])\n",
    "#print(len(left_fit_hist))\n",
    "\n",
    "global right_fit_hist \n",
    "right_fit_hist = np.array([])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moviepy - Building video C:/Users/Hripsime/Videos/video_output/output.mp4.\n",
      "Moviepy - Writing video C:/Users/Hripsime/Videos/video_output/output.mp4\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                                                       \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moviepy - Done !\n",
      "Moviepy - video ready C:/Users/Hripsime/Videos/video_output/output.mp4\n",
      "CPU times: total: 3min 23s\n",
      "Wall time: 23.7 s\n"
     ]
    }
   ],
   "source": [
    "### STEP 8: Lane Finding Pipeline on Video ###\n",
    "\n",
    "def lane_finding_pipeline(img):\n",
    "    global left_fit_hist \n",
    "    global right_fit_hist\n",
    "    global prev_left_fit\n",
    "    global prev_right_fit\n",
    "    binary_thresh = binary_thresholded(img)\n",
    "    binary_warped, M_inv = warp(binary_thresh)\n",
    "    #out_img = np.dstack((binary_thresh, binary_thresh, binary_thresh))*255\n",
    "    if (len(left_fit_hist) == 0):\n",
    "        leftx, lefty, rightx, righty = find_lane_pixels_using_histogram(binary_warped)\n",
    "        left_fit, right_fit, left_fitx, right_fitx, ploty = fit_poly(binary_warped,leftx, lefty, rightx, righty)\n",
    "        # Store fit in history\n",
    "        left_fit_hist = np.array(left_fit)\n",
    "        new_left_fit = np.array(left_fit)\n",
    "        left_fit_hist = np.vstack([left_fit_hist, new_left_fit])\n",
    "        right_fit_hist = np.array(right_fit)\n",
    "        new_right_fit = np.array(right_fit)\n",
    "        right_fit_hist = np.vstack([right_fit_hist, new_right_fit])\n",
    "    else:\n",
    "        prev_left_fit = [np.mean(left_fit_hist[:,0]), np.mean(left_fit_hist[:,1]), np.mean(left_fit_hist[:,2])]\n",
    "        prev_right_fit = [np.mean(right_fit_hist[:,0]), np.mean(right_fit_hist[:,1]), np.mean(right_fit_hist[:,2])]\n",
    "        leftx, lefty, rightx, righty = find_lane_pixels_using_prev_poly(binary_warped)\n",
    "        if (len(lefty) == 0 or len(righty) == 0):\n",
    "            leftx, lefty, rightx, righty = find_lane_pixels_using_histogram(binary_warped)\n",
    "        left_fit, right_fit, left_fitx, right_fitx, ploty = fit_poly(binary_warped,leftx, lefty, rightx, righty)\n",
    "        \n",
    "        # Add new values to history\n",
    "        new_left_fit = np.array(left_fit)\n",
    "        left_fit_hist = np.vstack([left_fit_hist, new_left_fit])\n",
    "        new_right_fit = np.array(right_fit)\n",
    "        right_fit_hist = np.vstack([right_fit_hist, new_right_fit])\n",
    "        \n",
    "        # Remove old values from history\n",
    "        if (len(left_fit_hist) > 10):\n",
    "            left_fit_hist = np.delete(left_fit_hist, 0,0)\n",
    "            right_fit_hist = np.delete(right_fit_hist, 0,0)\n",
    "                                       \n",
    "    left_curverad, right_curverad =  measure_curvature_meters(binary_warped, left_fitx, right_fitx, ploty)\n",
    "                                     #measure_curvature_meters(binary_warped, left_fitx, right_fitx, ploty)\n",
    "    veh_pos = measure_position_meters(binary_warped, left_fit, right_fit) \n",
    "    out_img = project_lane_info(img, binary_warped, ploty, left_fitx, right_fitx, M_inv, left_curverad, right_curverad, veh_pos)\n",
    "    return out_img\n",
    "\n",
    "video_output = \"C:/Users/Hripsime/Videos/video_output/output.mp4\"\n",
    "clip1 = VideoFileClip(\"C:/Users/Hripsime/Videos/video_output/challenge_video.mp4\")\n",
    "output_clip = clip1.fl_image(lane_finding_pipeline)\n",
    "%time output_clip.write_videofile(video_output, audio=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}