From 3d6f07a8a48c93fa1602d0ee4c0725d7a88671ad Mon Sep 17 00:00:00 2001 From: Kees van Kempen Date: Tue, 15 Nov 2022 10:47:50 +0100 Subject: [PATCH] 08: Draft before I reroll it --- Exercise sheet 8/exercise_sheet_08.ipynb | 86 ++++++++++++++++------- Exercise sheet 8/qgdimension.hdf5 | Bin 23344 -> 580144 bytes 2 files changed, 61 insertions(+), 25 deletions(-) diff --git a/Exercise sheet 8/exercise_sheet_08.ipynb b/Exercise sheet 8/exercise_sheet_08.ipynb index 182d0d2..e58c122 100644 --- a/Exercise sheet 8/exercise_sheet_08.ipynb +++ b/Exercise sheet 8/exercise_sheet_08.ipynb @@ -20,7 +20,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 13, "id": "220d541e", "metadata": {}, "outputs": [], @@ -62,7 +62,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 14, "id": "5e4391a6", "metadata": { "deletable": false, @@ -302,7 +302,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 15, "id": "bcc7acba", "metadata": { "deletable": false, @@ -325,7 +325,7 @@ "True" ] }, - "execution_count": 4, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -561,7 +561,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 16, "id": "ee683060", "metadata": { "deletable": false, @@ -587,36 +587,28 @@ "# data gathering and storing in qgdimension.hdf5\n", "import h5py\n", "\n", - "max_distance = 30\n", - "def expected_distance(V, adj, max_distance=30):\n", - " '''\n", - " Calculates the expectation value of the distance profile given the amount\n", - " of vertices V, an array of adjacencies for a triangulation sample,\n", - " and max_distance as upper limit for the summation for the expectation value.\n", - " '''\n", - " return 1/V * vertex_distance_profile(adj,max_distance)@np.arange(max_distance)\n", + "max_distance = 15\n", "\n", "with h5py.File(\"qgdimension.hdf5\", \"a\") as f:\n", " if not \"num-vertices\" in f:\n", " f.create_dataset(\"num-vertices\",data=num_vertices)\n", " \n", " for model in models:\n", - " models_key = f\"expectation-graph-distance-{model}\"\n", + " models_key = f\"distance-profiles-{model}\"\n", " if not models_key in f:\n", " graph_distance_expectations = np.zeros((len(num_vertices), measurements, max_distance))\n", " for idx_N, N in enumerate(num_vertices):\n", - " V = (N + 4)/2\n", " for idx_measurement in range(measurements):\n", " adj = generate_random_triangulation(N, model)\n", - " expectation = expected_distance(V, adj, max_distance)\n", - " graph_distance_expectations[idx_N][idx_measurement] = expectation\n", + " distance_profile = vertex_distance_profile(adj,max_distance)\n", + " graph_distance_expectations[idx_N][idx_measurement] = distance_profile\n", "\n", " f.create_dataset(models_key,data=graph_distance_expectations)" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 31, "id": "351f7a01", "metadata": { "deletable": false, @@ -633,9 +625,40 @@ } }, "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[ 1. 1. 9. ... 0. 0. 0.]\n", + " [ 1. 4. 11. ... 0. 0. 0.]\n", + " [ 1. 1. 10. ... 0. 0. 0.]\n", + " ...\n", + " [ 1. 1. 9. ... 0. 0. 0.]\n", + " [ 1. 3. 8. ... 0. 0. 0.]\n", + " [ 1. 3. 12. ... 0. 0. 0.]]\n", + "()\n" + ] + }, + { + "ename": "ValueError", + "evalue": "matmul: Input operand 0 does not have enough dimensions (has 0, gufunc core with signature (n?,k),(k,m?)->(n?,m?) requires 1)", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "Input \u001b[0;32mIn [31]\u001b[0m, in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 34\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m idx_V, V \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(num_vertices):\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28mprint\u001b[39m(profiles[model][idx_V])\n\u001b[0;32m---> 36\u001b[0m mu[idx_V], err[idx_V] \u001b[38;5;241m=\u001b[39m \u001b[43mbatch_estimate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprofiles\u001b[49m\u001b[43m[\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx_V\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 37\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdistance_profile\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mexpected_distance\u001b[49m\u001b[43m(\u001b[49m\u001b[43mV\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_distance\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdistance_profile\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 38\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m20\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 40\u001b[0m fitfunc \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m V, c, d_H: c\u001b[38;5;241m*\u001b[39mV\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m(\u001b[38;5;241m1\u001b[39m\u001b[38;5;241m/\u001b[39md_H)\n\u001b[1;32m 41\u001b[0m popt, pcov \u001b[38;5;241m=\u001b[39m curve_fit(fitfunc, num_vertices, mu, sigma\u001b[38;5;241m=\u001b[39merr)\n", + "Input \u001b[0;32mIn [14]\u001b[0m, in \u001b[0;36mbatch_estimate\u001b[0;34m(data, observable, k)\u001b[0m\n\u001b[1;32m 170\u001b[0m \u001b[38;5;124;03m'''Devide data into k batches and apply the function observable to each.\u001b[39;00m\n\u001b[1;32m 171\u001b[0m \u001b[38;5;124;03mReturns the mean and standard error.'''\u001b[39;00m\n\u001b[1;32m 172\u001b[0m batches \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mreshape(data,(k,\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m))\n\u001b[0;32m--> 173\u001b[0m values \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply_along_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobservable\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatches\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 174\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39mmean(values), np\u001b[38;5;241m.\u001b[39mstd(values)\u001b[38;5;241m/\u001b[39mnp\u001b[38;5;241m.\u001b[39msqrt(k\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n", + "File \u001b[0;32m<__array_function__ internals>:5\u001b[0m, in \u001b[0;36mapply_along_axis\u001b[0;34m(*args, **kwargs)\u001b[0m\n", + "File \u001b[0;32m/opt/jupyter-conda/lib/python3.9/site-packages/numpy/lib/shape_base.py:379\u001b[0m, in \u001b[0;36mapply_along_axis\u001b[0;34m(func1d, axis, arr, *args, **kwargs)\u001b[0m\n\u001b[1;32m 375\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 376\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 377\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCannot apply_along_axis when any iteration dimensions are 0\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m 378\u001b[0m ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28mNone\u001b[39m\n\u001b[0;32m--> 379\u001b[0m res \u001b[38;5;241m=\u001b[39m asanyarray(\u001b[43mfunc1d\u001b[49m\u001b[43m(\u001b[49m\u001b[43minarr_view\u001b[49m\u001b[43m[\u001b[49m\u001b[43mind0\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 381\u001b[0m \u001b[38;5;66;03m# build a buffer for storing evaluations of func1d.\u001b[39;00m\n\u001b[1;32m 382\u001b[0m \u001b[38;5;66;03m# remove the requested axis, and add the new ones on the end.\u001b[39;00m\n\u001b[1;32m 383\u001b[0m \u001b[38;5;66;03m# laid out so that each write is contiguous.\u001b[39;00m\n\u001b[1;32m 384\u001b[0m \u001b[38;5;66;03m# for a tuple index inds, buff[inds] = func1d(inarr_view[inds])\u001b[39;00m\n\u001b[1;32m 385\u001b[0m buff \u001b[38;5;241m=\u001b[39m zeros(inarr_view\u001b[38;5;241m.\u001b[39mshape[:\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m] \u001b[38;5;241m+\u001b[39m res\u001b[38;5;241m.\u001b[39mshape, res\u001b[38;5;241m.\u001b[39mdtype)\n", + "Input \u001b[0;32mIn [31]\u001b[0m, in \u001b[0;36m\u001b[0;34m(distance_profile)\u001b[0m\n\u001b[1;32m 34\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m idx_V, V \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(num_vertices):\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28mprint\u001b[39m(profiles[model][idx_V])\n\u001b[1;32m 36\u001b[0m mu[idx_V], err[idx_V] \u001b[38;5;241m=\u001b[39m batch_estimate(profiles[model][idx_V],\n\u001b[0;32m---> 37\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m distance_profile: [expected_distance(V, data, max_distance) \u001b[38;5;28;01mfor\u001b[39;00m data \u001b[38;5;129;01min\u001b[39;00m distance_profile],\n\u001b[1;32m 38\u001b[0m \u001b[38;5;241m20\u001b[39m)\n\u001b[1;32m 40\u001b[0m fitfunc \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m V, c, d_H: c\u001b[38;5;241m*\u001b[39mV\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m(\u001b[38;5;241m1\u001b[39m\u001b[38;5;241m/\u001b[39md_H)\n\u001b[1;32m 41\u001b[0m popt, pcov \u001b[38;5;241m=\u001b[39m curve_fit(fitfunc, num_vertices, mu, sigma\u001b[38;5;241m=\u001b[39merr)\n", + "Input \u001b[0;32mIn [31]\u001b[0m, in \u001b[0;36m\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 34\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m idx_V, V \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(num_vertices):\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28mprint\u001b[39m(profiles[model][idx_V])\n\u001b[1;32m 36\u001b[0m mu[idx_V], err[idx_V] \u001b[38;5;241m=\u001b[39m batch_estimate(profiles[model][idx_V],\n\u001b[0;32m---> 37\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m distance_profile: [\u001b[43mexpected_distance\u001b[49m\u001b[43m(\u001b[49m\u001b[43mV\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_distance\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m data \u001b[38;5;129;01min\u001b[39;00m distance_profile],\n\u001b[1;32m 38\u001b[0m \u001b[38;5;241m20\u001b[39m)\n\u001b[1;32m 40\u001b[0m fitfunc \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m V, c, d_H: c\u001b[38;5;241m*\u001b[39mV\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m(\u001b[38;5;241m1\u001b[39m\u001b[38;5;241m/\u001b[39md_H)\n\u001b[1;32m 41\u001b[0m popt, pcov \u001b[38;5;241m=\u001b[39m curve_fit(fitfunc, num_vertices, mu, sigma\u001b[38;5;241m=\u001b[39merr)\n", + "Input \u001b[0;32mIn [31]\u001b[0m, in \u001b[0;36mexpected_distance\u001b[0;34m(V, distance_profile, max_distance)\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[38;5;124;03m'''\u001b[39;00m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;124;03mCalculates the expectation value of the distance profile given the amount\u001b[39;00m\n\u001b[1;32m 16\u001b[0m \u001b[38;5;124;03mof vertices V, an array distance_profiles of length max_distance,\u001b[39;00m\n\u001b[1;32m 17\u001b[0m \u001b[38;5;124;03mand max_distance as upper limit for the summation for the expectation value.\u001b[39;00m\n\u001b[1;32m 18\u001b[0m \u001b[38;5;124;03m'''\u001b[39;00m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;28mprint\u001b[39m(distance_profile\u001b[38;5;241m.\u001b[39mshape)\n\u001b[0;32m---> 20\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;241;43m/\u001b[39;49m\u001b[43mV\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mdistance_profile\u001b[49m\u001b[38;5;129;43m@np\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marange\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmax_distance\u001b[49m\u001b[43m)\u001b[49m\n", + "\u001b[0;31mValueError\u001b[0m: matmul: Input operand 0 does not have enough dimensions (has 0, gufunc core with signature (n?,k),(k,m?)->(n?,m?) requires 1)" + ] + }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -659,9 +682,18 @@ "\n", "d_H_list = {}\n", "\n", + "def expected_distance(V, distance_profile, max_distance=30):\n", + " '''\n", + " Calculates the expectation value of the distance profile given the amount\n", + " of vertices V, an array distance_profiles of length max_distance,\n", + " and max_distance as upper limit for the summation for the expectation value.\n", + " '''\n", + " print(distance_profile.shape)\n", + " return 1/V*distance_profile@np.arange(max_distance)\n", + "\n", "with h5py.File(\"qgdimension.hdf5\", \"r\") as f:\n", " num_vertices = np.array(f[\"num-vertices\"])\n", - " expectations = {model: np.array(f[f\"expectation-graph-distance-{model}\"]) for model in models}\n", + " profiles = {model: np.array(f[f\"distance-profiles-{model}\"]) for model in models}\n", " \n", " fig, axs = plt.subplots(2, 2, figsize=(12, 8))\n", " axs = axs.ravel()\n", @@ -669,18 +701,22 @@ " \n", " for idx_model, model in enumerate(models):\n", " # Calculate mean and standard deviation of the expectations.\n", - " # TODO: Look at whether I store the right data and do the right calculations.\n", - " mu = np.mean(expectations[model], 1)\n", - " sigma = np.std(expectations[model], 1)\n", + " mu = np.zeros(len(num_vertices))\n", + " err = np.zeros(len(num_vertices))\n", + " for idx_V, V in enumerate(num_vertices):\n", + " print(profiles[model][idx_V])\n", + " mu[idx_V], err[idx_V] = batch_estimate(profiles[model][idx_V],\n", + " lambda distance_profile: [expected_distance(V, data, max_distance) for data in distance_profile],\n", + " 20)\n", "\n", " fitfunc = lambda V, c, d_H: c*V**(1/d_H)\n", - " popt, pcov = curve_fit(fitfunc, num_vertices, mu, sigma=sigma)\n", + " popt, pcov = curve_fit(fitfunc, num_vertices, mu, sigma=err)\n", " d_H_list[model] = popt[1]\n", " num_vertices_fit = np.linspace(np.min(num_vertices)/2, np.max(num_vertices)*2, 1000)\n", "\n", " ax = axs[idx_model]\n", " ax.set_title(f\"{model_names[model]} ({model})\")\n", - " ax.errorbar(num_vertices, mu, sigma, label=\"Monte Carlo\",\n", + " ax.errorbar(num_vertices, mu, err, label=\"Monte Carlo\",\n", " fmt='.', markersize=10, capsize=4)\n", " ax.plot(num_vertices_fit, fitfunc(num_vertices_fit, *popt),\n", " label=r\"fit: $c = {:.2f}$, $d_H = {:.2f}$\".format(*popt))\n", diff --git a/Exercise sheet 8/qgdimension.hdf5 b/Exercise sheet 8/qgdimension.hdf5 index 6371f4cd43910f925f26068b53f390f29cf7ffc8..18f5272a901668b813e546ce9f9271cc2e3530db 100644 GIT binary patch literal 580144 zcmeF)-L7QGdEWUTDGeGn2A}~Q5Cg&3NDxFpkcCaEB$ecrxjNNqmuZ?Vkxi>5QPO6K zlquPgHU1d*Fb_Rva|v}ebLdOROPJ$1s!Q-4c-R%s?`>67C3jVI)y{~NvVk4FzGA)q zct0c7%B=tM;fEjnum9kG`v>jQ&wKB+pKD)!_P_r8&wQ@`zxST)vhDay{^tv6|6AJs z=ZpP+zR*7XueGma|36Cq<9Q!{_jiA{{q#)zYjat<{<;2tT?%{uzWuv00uO)pgGZmT z{`Ua?*R`78mElxc05B=hD-t0WL z$%jLWPad`{PZ@{R^lBV%YUx*t*ZHfrIO%QFWASdQlXm&>;=B%*czhX@pHbiyuf85$ zdH1t3FXR94jxFAM;b-rw#wpsuiDT4rak^mf7B7G0zx3+(;+Q2q9&uRQy7YX6d$;wW z5Vz=^z1Ki3`ad{vnIG)74y1lw6z>JG@oLqP{8vlA?EZz07TJMQD<0D`{TAo82-pcR zacbE$ebTr1C10KBZu;Fg=}(;@PSY>`>49z$5HFrn-1J`O-_q}_hsi(sEj=5DS>=CS zx$v^vU)y>QqduMYy8X{~esP4;`jq%Ia?d9J>&k;y%YWJTy^KS}};iSL#Xi)#{wa z2d{Yat6M)}+i~Zw-r`}e@(_Dw->Y+yAFq~P*|lxsvASL3)Z*j6^t?LfDgDYrT6t)< z^(%~v>sM>ZPp=~%?$x+X$%_{k`xUpuE9af+XO;apIxy2^InyZ&FiTHKze(0d(U z92tjr#DD3x>d3`8i9hnv=k=B|v@Te@#jB-X-0~4SciyVlZIRTGWzSXj0acdE*lVai&m++}4?LXPUVh8YQ+4a4x zgIrpi#;Fyj#VzxsOVKk$?JUkvM{xOj2$S1r9d?_@`d9Kb=3>Ph;x|5D;KUiB1C z?a1r=Mb!C%nB-@-o*RkJ#rwjQYwp0yUhi$4LtN(9j;~4inbdf-yR9F)PRp(@jh8*s zFJAlmD6IdNUbXC)|FUPtwX2eo-~3*@!YN)kZ&glm<6yV=M*d4#-@&U@SMlFV;T-k5 z+xi~!d-m+SOKIs<%Z|lq?WN`;yyCNXZ9G=jGY)>rZ|T+X)j7$JXKcl3_0>3^aK3(4 zY00e>r_2l4_bNQM$%&I5cU!*#_oezTJ>u2!YvUqL*LEMCW&V;|OP}gW+{*ynA}CIJ zRA13IyH;=B(%tlj@v_sA8^8V21KlFv$V;E>S{^nYw{$oCVZ7qAdIRsJa8d+bE&ZA| zu;WYf-`&3H82;_((BmL>o{*vXReAra2B*96u<0Wog1(C zj8lEZt~>qufAMPZj`4YQz0wp;_R4?hm)`L@-}S4tjb#9j<3cy%8OTvOWq0p z;e(8WyzKn3zuC9Rt!2Lt!uOkLcWIs17X6T4UGdxDl84L-owq1viH(CD@4_oSt2fxU z@GRCF48V7{o=)EJd97jYMsA$`KLIA)9=}_cjvFpJ96Osjp*Ar ztjfs(anhf<%6x&I*|GCozgk=JM~~w1Z)ID&HXe2UYM_yq{JZectNKbjcHW|xC3bOy z_g-3cmO5H}rCrsJM_ze{9gA1SVO35F#;e84j@dPSdCU3wS*0bnmi}wMR*){v%QpG=B_952zQC^4 z*X-MMv+&#|2VSkXC0@zDyY04~);Nxnp2RD>{Fgr0pgJujUUsZ*yx#gXqy0Khd%EX2 zkKh$=`0F>rYkoxkb^e?BXH*|+iXPj)OW^IyEq*Urv2%13Uz;xc=-&7Pe<_Or@1`L*=8+d2XL z%E$IQzn`_vUvjIH@ruWI`L#NeJ*-38CB;jAJotB8KM%J$di8jPn;y-N#4q|bE`1c% z`-@XNqR026S9!^Cb=Z2OU1GdiJn9bbo81flrRaAT9{wpGsW0fa#-$I}a(~G${)o@& z4SE*8=zlrT2#i-;-fjH=zva)i>3dafyzCX9b&c!r^IPZlQCaUV`SH-7JcQf+^$4Gr z7%%^&UvbO)mtQ}B^?F-)we)=SA6VQUA1a_dY-n`?|b9fZT$?q z@-TZB*T#NU*`{Cl1|MF0;@K)(r{u(oi=M~0#oo26^5fNt!=9Ik)4MGrrp@MR4NiK+ ztDeM5-~4zrPV$btqaWkGw0wj|obtSzzmEQGyjE-JS1S(Tzur0#dzO!l13y@W8z;Xt zzaQs;&Rd1+l$PXIC7y-Zp;i__L!6{=tjmLHN{_*6kKVd#T8H`60iRfAJfS zI{&4;&A+qc-@2^3wDkJ^u)oglr!V)nczCs*r|iOQ9adeb&T#(8jwd}(a)(bGR!>^jQIFL5 zlk(gqR>>b;eu|U-vgh0SoBcRm`oqVr<=^t#jLYm?r{u#cUg2ifJA7$z^K0WGUhD7F z{m#9geE7s8^`tnp3$OFfE%%$=pZxrj-oz{0^eR6YpEtelxvs;jWzXW4d7=5QdgNU4 ze%|}y)QVT?NcPOXo%ea~d#>wC{;f-Zmwv5Bv*$YhTmpa2`;wpk;$*+#?&!Dly_$XF z)#AqcAbRJ=pL2N6emPDpebJxzbscWwu*e8>PhFF>SvYx zIOx^7B)zh0dR^U*@oME2_Kg#__-#B!f1X{>IOW^@)+IJS!aY03tICI$UfH$$D?Zcn z>il?d;59G0ioV6?d)ao~tB&g|=aE|+!l|wjzZ}=jBLC~kfmbX4;N5M#M|Mr$uX~?a z&c`WUv0L?|ILyCik^4>Mz{^f|TklEUp=bGMwfr-V3to1*g;zc@4&!yJZsXOmTlvR2 z7XM}Um%?kk>iy_h{HpO-6*O|=h&|W)Ddr8AYR~Eo`SwBdJH{#Jt*U1F)$&_*Ek3jB zRXNFxQ!8GnEAdC~hY!2n55Lpf=6GGN<4Id`vQzpr-~SikvMv8Qe^RWIV&SD%{>q-! z)9Nhw2|w=Y=j5H{I6zJ~Q(+;R2h$TT2$%ZR#(%ranjH1BS21ZhhL6y ziCyz!cI^7uImt&}^8kM7-%G(MPOTCS7@{Mxg zWuM#j?2PSEZyPT9bN<-RD%<2|&-D1P^VYuu#Gb{cRrp3Z@oMqVxBBYC@TYCNzTKS1 zAF7}6Mw4ulFLCOy?;HnpGkd0g=T9R3Yl}gCaaQ~hpZ{g&Z|W<0WCyN)?Hixz0`h9< z@j*EGF*{agIR8vyzwvEL?(oqceMhhCy!jo!vCgV~-dK{mxv=C6Fa7Sa&5pNh@6(E7 z;uZUDlYj8CQ+(d{&U~S!f&iueN@Qc>+H5mO9gZ`W4^wbMi)$94I-%YnvaJ zo#wdx?3f+!Yx5~}sBu)Eof~`P6Nes#k3E|=75}*ff5ZFZ)zX9d!+d`qe*VqhSL4S? zZanzR^VM1G*!gcb%xAj{uXeX}QP}U6ZGOt$#jlFjIj>(m?_ZqsM!(jt@QO!QxU}=4 zy;L&1TKPx){LjO6KP~@uzHur&zw|Ei>?Ai1c5MAhE8ogD@~(Pp9-^Nu30`gVWgWJe zC-7hP?EIhI`+P^qEx)LrtY^?Gd$#Sk`a?hS5k4;wIn_gX?pO1DT)VAb=lth;S!b){ z50Chqb>>=+q+fnZuUd944phIB4F$Qh;*aOM>Phcojl7fL+$zqJi+l@{&9HtoJkUdrpRzevQ`) z13Bpq@{&LK^}v7CmF5S=Wm245#lnk29n4{ms6OSKNs`*K_Xu)(OOAdUoCHe4~8iz6zJT zVqH%C!GF!4oIh*c898m^)w0v;@XJr^y!dk5wm4@!z<9V`oRi1gha7j+;?$Byi(?-? zdN&^Q%^&Vc?l-*;PV#!Lki1)U^!wqZ&o{l_xv#^EL;aL`s^XUUlJi`5F1viwaU11k z$Ly9~#b@KeAH}!o=S>ByOQO8nv%Ke!`tKlg2LvP-<`N%6|IIz-&9 z>p!<7chdoRwYYJrC+U}6v-`V|^6lLPC;K%2k!R%7-PZ4^m5;1%**|;zg_j*?{YG3q znD??@@wwBl_ZKg{uw(fLFS~Z$dZb-qyjuF>pY$qDS;z5x9LHCQ(>S%{X5aFXZTShW zJngu6H>>_naaxbWORsqGsW))yZ+70RtxFibdOqkmlK4Gx&CWNDJ9+VFci|VeJU8RV ztNAVNk(b@lEC1ArWAv<_Ra(67MW6A{!^3Q=Cp=f-ug+hElbm?9IMi9{$Zv&T-6e0i zPJgqvRKx*g-j%RbHf_^-H(*LAD5c*R@w z1^ZP;sWYr=@NfBR751fblt!7%OA}P#3%D4aq3d+8MnNIOTEF5#cy^m zj_>GSJE;la#3wG{l#k2{`LFZL`&Z>noNnY-Uv1GFebTe@jn|}VEwSiV-W8YF?--}; z$Lad&aPt2lul$1JYU_ftYx5-by~}au>8D>c?_YBANBXlacRyVG_d46`VHG>30legv zmy(C-`H?)#4(d7`Ez**k9eYkh&)yH-qF3`^*DZosVv?IZt22C$PM(#A%8sjtwf+Y$ z{i?6RS?gH*S$ta6uJMwe{&ri}n>w03vvb^QX}8ty*Wpf`>~|)c_hiNC)%Zqvacb#V z9j(6FZ~aR12XVY*e?L0^U!2I-^xTpi~5g7LB5vx+^l)96opK8$tcuIsz4 zrdRr=U-n6#@^0+8)@d(=m%iAm_a@n?ZTU&dp39Eu-+)fm(l2`!r_>qp4}aAb-()_brhoSF?5c_X;H9tY&Lv*8?`He=dfT?N?125_)nA+R zQ}Ttw^T2S`{P$swyh>}_X2r(K-^_=sOS0eSx#G2Y z6X&daqg;4*TR&o*d8n_;vpHuhZfm>kR$O%1JJAYUw%iqVh}e zE8MjnFMk;)*Xw__7N=I6QZL3&x9@IUa`}j#&c<__JUHbe`6Y3d9@QBKb}c^1ySLqE zmg9KE)8rp~?fcs^NsCjRX?$kkcvU&@YR5brzkGrJTYVgwbsc_N{k*CGcYGfC=u4YA z>#*-!2YlboHa`}x%s1{>{MWu6-m#URaEG_%h5XpOpMGCkfIGeb=k?ZaJm%d&ul1g+ zIKFDU+J)CVaNoD9ezZ;(eTv&{tUKD|ANox`RVO#|UeEW<6RgkDD}Vo`K0a-iR=>01 zlS@95f1}Us<1YWwzMzrs2WKKYiP zx14vX|JnBA-9_%`^RVyR=KbuqWj&zD*X*|~^1-W~vVGNgE5Gn(`b|A)o>=3;kJ-y? z!+?)n?!w7l$NGX@Tlb-F^Csh@-*Ftz%}*|IC-qXzht$dPk$S^=#%w&djVE3$J5(TB!O#;y9lZQ$?dIC*gLzundaz&)(r z9p&NV<*GMae@EiK_HFRehkD9L0=7Yw8UA*><&vXG^a>s9LU0of?UaiOOw=VFO zmfah-essRScoS!=+Z_I=b5xyW-Nv}gNAhYC;niMu&X#qJ?GO5PJs*^h`1`BfWuCKe zYNN-)qi}yOyy0)`TmE(3JVZZR67upp_0kW*oA_J)e3kvK``NwEca+>(>x}oqmH4!M z^89xFJIAZ}Gfw&yZ$IvQM|o%;UjD1@T9p^KR$WZr_}&k9#>4!m84vN!^=+~bKCL{e ze)PP=x^(hz{eHi^oa1fwxQ#RUx89G;bCY^rCO*r<&R^A@$=u)S+7v`6}0Yk42nwo|d2UpS#A!t0hnTwwW&_ z4mW;lTRz@}7l;1tn&-Crk!z?I`D@Mh`K|dNPI{X)K8^f%$xFYnOY3swx47jk*Ny$o zx{a3~(zA8DtS@ioN#EK!2|eT1k32p*FM0XjE?io52X5~-@bd>bU)|}tHrWTKmY&rQ zv0v*~^?X~MAr9j+UgEv&S+H?x$){en4oz?Jjr#JVt&`0DT)}wb6nFUFbvVp>hxaZVd69XbIOVx7fAzdO`fl=<>-BfH6t8|a@@dVFzP&x`V|&!w zwofZB%R}_a{`K?h>IwgpeBoigV?AO0jvw#)`JOk`x|j2=(jR+nlYH=a-);R2`P6#d_p{$R4!?E1wqHH(Uvg^sp;o=6&Jf3}JA1!D-J$Mu zopIE*jN7?J1gDlf;WPg*litk)tC+>?=E53~D8;Mi=+WJ=gUIYEh zyZSqE+q3N^7tZKa9?~{-1upuxUd?{>b2gw`Zj4vU4(ZABBL14ZT=OOKhDH=5)y z&cxe#e(-VRS2re3S+#g^;???o+3$7UL-H?u*7vK}f$L87Kihut(wFr}`9=O^ z$NN4G%{mV5*|<*0GxG9VJos^XUovgwA@zs6Z5;G}>i&1VpFH#{?j{Z$aEi~VGi%=K ze0f`ccg^vt_amQH-pzcW<^$rE`JuSHDlh%s+xkeUtE_LB|0a$#b@ct5Z=8(VtB&_w zpGQ7z>OsGY^psRv`v>JHD54w(IGhLir>F2dERwDIJNxH^Mlk^ zTk4K_zF^&ERbKX-Jaqhc>m$vM>03N@{=3%4+wPxUcU$i{aYsBlB>x;A<+!{nzV)lt z`HPpn!dvtDkypG{H?Bk4CB>`VZGFFbgFYYj{q-D0{>5*+`qlIP#o0QK@8je0{%gf4 z>(b)*YI?>i&YB<5o4P}Nm3gANy5>jfEd9)?VZ7=hb}J7hP965qf98j6HN6^tyy7iA zv0L*%^8@g$#1{ic|1p{c_9B~A9!cA1DxWF`R_NP zujuz^zQB*wBd%+UeDKnTb;;=Sn0nIpn(O&5I~M2kGdngp<9{{J&%CJWD}HM{TJ%3V z-zXnm@~6JC-df)e{e#YTxalpuw|(Dk_tLh>KX|qBujeSAgyZ*nyG8H5msIPN;yS;W z6&oi%6ko-y4?CwkY+hWPo;SqLn^wJjKjZZvt@zKL?s{DCxvs~&5`$d)FLl)xe?3I6 zwe5L|*1Q65bv)_+;MKBcEq$p!)EgO(_D9<@F#cV?!yz8XU;Nkj=+FF8omPJEj>Ze8 zHu<@+f8qure)8EecxaIeh$CTUz_Yhu3h9-CnhdimwobQ{rHynRqK`Xvzk3e zFSSnf$KgvnJ|-Vmy~VEC={R3#lYZ!TY}s|}xU{c_%ec*^SMr?V z_1>rWWxXovcU$TW@yzcR)O=BXalLK&H$L)}JVc(cCGY2L^}E}8Py99W`zMe4{wML* zmi_HFaz1;VU9X+)#eWaiII9QLTYuX5-u6Ryg;X7;EmbUV4o)?bSRi0wsuPD|#I}Im$*8bwwZ^@6@wKn|6a3B9oKmU-r zjGb3p)9*V2dBu)L-usa|>(1(@W8$-UVZHw?-&hBtNBy?mU;Pg8D~k2bP9v9AeCEfG zBJYoTdwiUhJ$tWZ7X7tbJ~+kC4?2(UuUpqpXO(`fTYbHsKmG3_83w%3>tP?>)Quaz z{5bnFU$WlQ__sVGKF?;yBQI`pUUxq07JjduKX2CWzLoP5zv}&W_ToOXv^cf&v~><~ z$-MV?ll}5={Cm2*b838Xssr;}@PH$Fy!lZ$W8YPOtrDm3;}w_9f7MH#58_uZX1&9> zG;!K>R~aAUnE6H3Ble%Gp2TZ@miSx0!zfO%zf{JP<#*Ova;WFNd*b!6UBU(XTz?pM9P!r$2iJC=X-KMOv2=tX^$IO};oJ&Lc!P}x6N}T^WI(d>!(fnA>UQxH9z`h-&QYHUB!N_$A{N@N{4;=$@NuN z^YeD*4_)}=n^@~W4u-&I{@o${k_ z`F#%Sv+|p^o%w^a#y@iN-}~9N9v%H1qtEtnKVJ1#?7i%oe^mdI@X~Aaqkdw~wGOME zl#de6mYW}mSL*z5_#UiybxfUE|K2nEjolYF`=wWQbY}H__M9Vj%kTK3_xWw}>uewM zzM1)AJqP6n;__^~^cg?(K1J zZ*F>9?=xf^8b8oaoBTsgt++MVZHwQks}8BJ%$r*3(E2?gak*ujW*G*YTJ}s{@hf$d z^_(qr<;H(gf7JJM#3}vF%4^;#&wkSNBR;D$>iHqRwJyRwX49+j9`&lu5Rdczk$K>g z=(X(l{XQPGE~P*H&(@Mp%l`Op^jGmYajbbxs?PGh-9G&6WVSeslU(sveCGL2#plfX zn|Xru*s|l<6gtR*SA4nG_2a!jb@9=2!q~HQYV)P`AbOoWKjCG^*OA+N?z??keQ_f$ z$FJ4dRY&TlP5QyBrDt(So=NLHGxbNsE%k?%p0%@#1I`w`lJ9=D_i4>@Jr|69S3T*x ztQWLhuG4Ru{<*SNY8P`{p^KG4nSDZ>*wvKbm`pwl%mych2PpS0F z{@<2d@2VfXT6)H9o$d#n_n3L$;p4tt`FG#9YktHpcG+M3xAT5Vj>siGS=SN2tjqjX zKd;uY;@7_aEPh$9uJ=05OZnN|@oLo@cpr8?{;8fe@5SBr{k-B62iS}LKfCjJ{*N5d zpSZMT{!{Z__A3slw>&>mXBe;Z(A<94@Zz-2s9scW)O(}*t@p{k+57CAMuL8|$rt!N zKe^(k$;StJw%#Lu=|}&wwd5mj@}&IQKG~j0ds58!{D7a%#y83{@@D<`n7YAw zv-QZvkF%ap-^Z|?F~+I!e&^mEdHE&1B|bOnSwm~yZ#`C>;(I#k?HU($s(v>(tODLh&@*v`bIy0x%VdrJ2u~|=eg=eaV+s$-fF+!xof_#&p6yqyGvX4 zo$YqVANtjb&z=WmK4jgh-UIeLAXB(epC;S3eEII?X0tam4d4^I3Ie@|5qZ(EF3e+cOm7P<4m;O8>I}lZU_JRcG;E z?-!=tsCv@#hDV*do}00kS^U;`^bq&^M;mn%9i(X)FJg=j`cbAjMIH)Y4OtM z_&vItJ`U71f zcYn}1)RR?D?Zan$aOtm2`YHJ$zj$SxBk{;OR`t5!hw>iI7Cn#i!Nb1u)^nr>eY<}D%eLp^?EGEv+}1DN7CFTo{`jrz|D?AY|Fz!n zao=C-bmj^AYm0%^0)YepWn1Q{@@(j#4UA`IDC_Mb@ijpbIAN(9NVl5h{y3?{di7T+v1&e*ZX~E zqkyyJKK$)Lwv%6v;e7h<`u-=e?XPe}M*SzjKUH+SYoAy8S_VCxe zEk0cIBHkIdHt7ei{AoQWcImzL_GjT1htsMvJzuDQ=lWd!dD}4KrJvM|CBOPH@vGu- z?7Jmi)4O%qW9Aj=%eM9L;=gD6UK(C`$htGJj`nUpb)U$=&iGm6@;xK#8@^xX{X;E#Xt4|RXuT&a@9F<4_pR}M zx488^3*3p*n1~dav^8ahLaLT6IawbyZKA56c7Y_m1&i=-z#`U+(goAJy{$ zdj25C%@0$59TMMK>JZ~`NSyONkJfmw^Lmb)d|2z6^iIAP0A6!P^%D+$d#`W%-SXof zWm`+nkF!7a%Z^*tyUI>>{k*cLcBT(rEnf1`U-E6u2i2SEt;`$D_uGE!K);$+|9$WI z{+1k(i+qpzHorB$KV+V-?s)R}`ST9Bu73B6f3!(Hc(wHVJK?Z?^SE#0t9gCmlKj+e za$WLP@yAZ;eSd!0?)Za~9-?2*kG9Ay&Uin#>^60xbxU=m`EvWc&aZx{xMu$7eWtCS z*S?z8c#!XH4U7J?-n+8?WcfP*9Y~p{6lW@MDnwnw<@3`6{oIlI>#}7 z`{ajx+c+F@{GiUjORux~FFW3Mo~rx8L%+CNxLf9h;`#O{*Z*2tal!buGkx4&tDe8# z<@B6i-C@1;7(1?Yz0_M(H-8jPytC>z_N?x;p7S(%e2OdW7H;|2x|e*cpZfg<<9a6b zR=yyImOiedr_=?<_~-Vx@2Br4;eV1ic9Zcj|7qev#pg2tRC$F5k5^f8*@F?}{6**8E6)ul_Y}Fz-#Bc@r-7?Riqo6RbzZUh2K~QJ?Pr&J>%D z>popSwVsi6rphnj^L{KpJ*1xAaDOlTSf}Uz^!ToMZtEZKE^>ao*zxoysCWssB@X$iPOjE+4$6W#4qak1N#=Q$?=-v zzxL^MpDw?Dx5+#KkNo@OaX*j!;@RTY^lV)8Q*p{VCI1ztUR&@tya2Cp7GDytDu4d- z&RKOu*0Veh_8v!j+|RSlSL=-WcfU6j_j6z7{>E8+{$}KU*xN1hpQ%JNx%!@oKaFdyJgcj}NJznmY1vDFNx$y*uDMS2 z@BX`RB~RWY?mmhAnjhRe?&o>V;CD9KKGz#J@j(CDcIFQ`wEQ^ssGby`8hg$-*l*pZ z{13*U%a1VK9}{niesLi{Un_6`xoNZZ1a7b>`>lN zf24k@=VqQWg!d};e(=77Izyb6kHv>!*zas})GK+!o77cX{L}kIo-cSWSRMU@ou>}1 z_a%+voq?UW5nh~$SDtIiuQjhvol*5h^lV+rys+lYU*GzTi#OXR#Chkt@v>*U)=yJU zipS!$^&9KT>gx7Mcrp(zZuTNBymPP$U79?={qVU*h|djK@Kpn(^9_@9X)x@!@an zbAHIDp4p4C-eHJ(WAQ2{J1>|$3Crf4Xt=kdYyz9H#@tI{99V}$9MX6 z&3FGe+i9;J_ig!D{oy@_sxR4-`g+%|Ywq9P(Ff<)UiJH1N3V69|Cs$*k5xCbi|OL= zIBYoOU3Qmwk@>;ZP3KfMxA?Ps?E6RJ^x+2?m#l}?d$GH|zup^Zcl^Q2j>yBFtyg?I za>`GM)7C4Ws+Z)gMcZ^xL8+pIlx#~Tl=!c%4JkIg(K8fBNzN`xzlE3Qt z=kn?6Y}J zl=X|7)EWG>e)sF#c6vK$KLf8;9hmi-$|v4eiGGjb)t~fnvM$hK&ov&NFXnl2y}#~$ zuPW!;I?sKz$wN)Ouyr2qjat_^W*uP5e8_XMoA|SB&%-zCeEc};fc4&;`@b!&Q~kJ) z`EKT`_1rf4+SFNjPWI*hy^q7Dj;2=}#!dgH?tj<&$uqY2<>QQlx`O`rv)1zm@lHHD z?ECoCbKzaK#WnYD@A%_B+7>yojy1-wL*mxctV>v@+~i$;s$SHu_8sHg+C4e6^l2U& zzq^rd!-;oG9QQoYdq|a+^n0rycXR@I%-<4EykDbkHZRhOOXcUuXT@p$EKiMg>%Mn{ zS+{XtEkDhCXiJ@>UV0Ke*E){8lzO@Hkvt@Ri3jd8wk6Oz{vY?{x9@MyZfL!2Z0miF z)YI&EyXn`-%Qug+{c&&Gw|ZM~i=WH)=7sGYfAGd0tzWg&8&^N+avuMxw@=hp(Wm&^ zvK~@-`|JJuwo7X~+nGOj$-~cVYZI?49;M!R8hbWBI{szndnzxB+v4A@A8+EK{_koS z@RGy)kG)0C<4u>-?=&3$I&!PCt;3G~Dqh_+*QxQttEJ!Ydw$a5ub%rKQ%APMudA%T zACs>(aqMBng?)=#=iD7L` z^olojY2NcRdTc-G;~@`w{(Hce_}+H?ytA#_;2YbK_bPJcc|3bQM8CB@l{nroo#}&jY-4xcA3Hqia`I#E1N*)=J2>XN zw(sXpx85^yUPsR8#eBEwuGsmOd~3ewy&ZLBOI~U>y+3iUZRtPb+3xx?^2Y9b&x+k1 zDBk!1p`CWME?SK4D=XshqhP&P$-Sy+s#3|!2@|ri$ zQ|9}=Uu50Q`}_6pPG)|={#&l+&+NILmx|}&o%x2i7dhT~T{7~=3?X=NzJ;!l>a=oo_!E4;jyHoGVL&xOZoA|9dlK%Ov@3GhKP-eV7oBzEn!QZeS zyym0E`QtwBH6IA?G4bi0(y#k{*yW?QgLRxdSMVN3*|GVaI6L~?+xEZD%a3=+ zL*ndB?D+qU-yYJoJYNyV>p75d)9U~8%K5ggFL}CNE6!Lqlt&X^&Ffq0$z$@-lhj|^ zk9$ArO7Xh>{c`IZ^1xl|AFuUs{-m}4ZH@1_`@zfpuA*n-e=pnTmh)}hA1}KSZ~m_6 zmp-+ZYR|tAyZx24^h@t=%bw2N4}0E)lRev3XP#Tmw{?HK^vI62>dd!wzjOD4S3G9V z;Y1I-CH0$2gIB%b`5^8~jaPW(A#s|WzxjyH zbtV0d_AEZ*b>3XkzrHj$-g*UJm(d7+*aO~Cuk_2#XO#U-WWuYSq-VVH@SF5K<2873iBt0LrRF2`#;9NWXVlf3$V9)m zUYHNQNv9KEgLkxNdcM?ng?G1g<%n1E^2928Ezw5({#}_L(IdTz)AH174dTQn(=RT5 zi<_NKjPP2b;oWWhGV@>c)}`j(k=J$~h0FO%zw$3mdcM?rgp0r4-?~oizZ4DAFTIM( z>SxCW=5nUVjTOyJg3C z+4=gUodBaj z>AdvIe=pUZN4<*E?EX?({!5R$t&^EA*mhn&y6#^b@+>~_ieIlw_`KwJ#U*+buju{x ztJdAZtG*Jaw2rS!_`KwJ=n2njhoEH|F2At*_I+O@NnPeP2>O z{@dqX!vEuykIaAR+3`zY{geR@UafdV@0Z3aKI6P}{i>J6W4xE5R~+p5y{+%Tsm?ME z&R@O7%bszv>r2f?^r|hrM(?ZZmHhOp-jH|cS-f`s>MdUWD_)g7uMRlKkC%S&?zVm+ zzaB1Ib`viy^P}tVI=(F6AUGbpqyLIq&KoXYZW9Op#V20jzm&X$m;cH~{Mhm36nR2m zJb397FTJ0*e7W6t&4bJbcUwoXe>t!d0*}0-JzuJR)lu@1_EO>$b<^+PHD2+GUd1cp zaw+YoU;e9Ahg=%3I4nM2x_;TS{HwM9()24{(erNWgt#xouK6!L{#rQkck0Xeix;2x zti9Cy%Z}NvxOFLZ%tGl`-6$?=?RWm_E#BSMNvvD(XUA9PBtIT@tIojfxbs(U@$9xv z!f$Om-jA;T7mxUiQ{1w>K4~YwD=t~TqG#Ke#>;=L)A3_^H!iDlYU`q z!=7<_k3(K^{_5?>%U`dzPIjrh{FFWO<4dof@m{+B@>_ak*X)^pUyA>-XLW}8f;_c4 zC;7!IyzF?l^)u{u{_5?>D-W?}$5-bhKOTIeelOjg`R#+PkBIM!UJ5t;iofEt`S1O3 z%TufSGhQ6#3Haz+YdrYFYVF7?|KiQR%XjvFSN&~`D_-`DH~$WB{d;Sx>(zMS#lvp> zJ6`hBrPR@Q#b5qQzv8oewK_LmJUHoBeaRkHZ}E!H>J4^1#;Z%=<-g+9_14KeKV#>{ zXH{k*Yc9{R^=o&4*KP<{8zj(98ygPxt|x>Z{o>~*(w5_L5F znm;&ibzb>JJ*m!M-|`VZU!9jd(<454X}5L4OX0| zdBq`I^onnFz0!~P%$|2!KY~|YqIcJ=+Tz7?9bS1?KH}G_a*})G#m%noho4=yY`cE7 z7BBy$U-cwTPh(*uWfOA>}Qp2yy6x6eXw-``d;0R=>xBPgHIi4o8DLF z#!J7r*zd^gJma-mJM!{Z_Kf$^@(~{KXsjdIHM?I;ujC!|yW9E^yjuC#xVV0`7B9W= zTXC9w+kYwXO8&*Ao}^cHzM4KqdFfYuWuBnEvfiu2y^`gh%`Enaa* z{?W2$`d^ik+<58FIu8G3*T%zjtG0M|TPF~g&3iA^p6NGwJ#68>6g%$P{OtEO)y@2t zJ*%snzk17_`KSCNFKHdWG+yx-r~2d4c-52Q)q|~T@>1g!UiPfs5T`FCZjJs+pIUZp z94^IwKCVW7e7{aUD|vQm%J+v<2J8Y)vibX<)`f0^P@}4NAyOoIN7yv zSyiv(#(`ISl7HE=^H*>2?zT=spTC`L`}@)L|KgQz*t7RV#V`44bz;2q$bQ8u{Hy07 zdcr&E_x-J(VLi+FtG9UN8+sD>?;_)28 z`i}XL__cc6!izKZTyzx7Jzs}k9k#lDafnwRgioGY zm2Z@r|C%qTr}!;B^WX9M)wc1nXWaZ)9;RpKuf|DU@{3pI4dNBQwcmBCws`54J)0j@ zd|nlBkQ=XfB_98?t)FzSddV`+jt3Dd*{vGwJepF9B*g6~i zuS?n`$ICD2m*3)+ubjUsH~I0%zx;Q%buxL_`K$Bdk#Dv4!%P3Ga*~_A@Zc1uydUeh z>sD>?s;}5JUhVbP30IF>r+DcZr~JDMcc)+PFJ2t-E<09Ntw;89iSde8^3eNRKi~YJ zW&7p5tg{y{zr@Fm>02G*{B;PQmz4bKMe9{s`=7sR-7UQID&MNBF4ceKS9KNr%14f` ztJy9&{jytp;+1;((&Cl;I>ssdm&VIp`LVpTZQTy&+d7`}R9SN@f6_S-X%dT&&mS}i_} z>cFeM;=k7G=v&Kw)m!{v?042}yz&q(^@e!0ZJoe8!uhjuostW$IJDdPnYgsx=P(ZH z&egc_%17o4>{+~4NAqLj(nn{VzbAMrPJL_ZEc|sHvX@Ib^73ExqdY{q;5ucprtc;pqY!h7Ji?AUm$%8ggupngt!pkMxLJX|-9-|XAu z7H@H;eynv_>l{~GCtB5y@ybW$3+>mws&}$~W?g!}KX$^JDfb53lCOc-be8 za3217x8I6eyS_aR+cMiDuRN^2+J{f8&UD=}pb?bZ{Fh%|hm+spRX^`?ye;;@D<9$9 zhsSybKX!aIzoizu{MLGg_{4tI(av-IYAs&z%6wtWN7gsQ?R(Mxs=TA$rru~DhKnEb z^VK-XJL;Fc@>_c4xAdy+++{r2hkj>m@zO6pWzV+Fm(*Y8Q>(=-yzEr{#D2|x#b?J? z<797m*(3dlOZ56t>{h*LeDt$Qi}xx#^rxOQALPfooVNJ(+xb*l(Ro9$tl$ zoOnljjy~(Tiug?bu3xRiE5GpH*z+NrHQ!&=j_GCOr9btgIKAKc74ov{^s`D!Zu;GA zU2^Np;ud~+_!n~?zt>N{dfva}BsY5&rxKs*y%poo!aFb7%Ox9m#a;0#^M31g&3L@L zxB2(tWzY1do|J#tb;hCI+nS&7c?t2#N9re><_GF5cD}kj)9>}x#{-voN}M(htL7#8 zCBOA&`8V^UsyiHa-SgHm{}#EgqF4H5*ZkQ$(Kh|NZhq1(Azu3B$LeVFq}X*mAH};0 zCpqzsoa4M#To%7}TYAuDbM^)={n9Hg@kuK$iEp#>jq>3g>nptcHoR45?Y7>N>&Jd) z-6k*n@>i|;%JUWRjQ!8bbxJP046W=&;{QG*ZYf?e#K$+lzE_5{%wnL<29cZpTuGF-3Q_0*Sp1e*|T`0#qIfuZR67x`_S*0 zkJxSWTX9OADV{HeTk}}F^d?S+uj)w8&)CDNyyU;yI)QwoPL_xFIWCT`7Pm%wW~bI6 z#Vh_RPZ^IsI_vz!OTX+{yxO8q+~)u6ogb`1jF){{e~ukjU8SCMd^J0!54`FPJmNF% z52NQxiO=lVyvY2XUe#Objn(x##wl@WZ1J)OcCt##p6ORTiBp_bPugbpu3wE;d=_`L z>{y+_f90c9<1=0y=0oxkeT!qO+cW=Vr}Qe{zMuH4-jcsov14-bzpL=vPm5EXLEq{S z*Xd`KmfZZ1-qDACxxQZ}j)`mRVRpVzKD_kBU)i&|%KVo-ujaS7@yfrr zqtC;Bdv@mGU-Y)E>bK7*e){@(QZ}SKJ&f1Q=@~V16z0AJ(xABm- zc3UUZ-|W2Xnf`F{XL`nMzxXvP-zXP-;H59z$wyUZ*w4?${$}4Ed3Rfvm>$JvEnf2^ zc0D^M`S6NY^tOdNZRyuIv>eyZDlK01vv{k%GCvZZ@$MGq<-g)k`0D)y_G~=Z!zy|u zC;f`E{PV-Ezp`U>wCh%F@v`USp?W?hF43?2>$=sr$t})WzhKwuWxV{@__%%*Zu0V9 z@majGE-7A%SF6Y8-PSb}|1G~Y@8#F(5#zLqUdc&r@rwTNsiSR+Tf0pUYqfaUvATI5 z9<8{=Z`Y#yOj^9=bLK~x@74Df{&o2ORoaiz8mG^CocsUq(p&V%e-Gd3T*u!F-?!3= z<8#x!C>`Ek2#0yRIQ6~k|2VDv{Qboq=iY;te(5diRfmV2^ANq#ch#Az)s=YF8>uf2 z`_9?ox7M$UQ+{R_b8Gc8>G0CiE}Y3f#m#TO-H+3EdywCu^=-GNtV;B0F4DSVT z$T`O6{r2qCgI1kkJ8jK>*~KdHdAGG^pX;>p(u2NT>l*a!car(@{ak1Ko^>|iAM)|v zUF5djyk*;bL4Kld{;NKl5b-&Y@Up{Q_~`5k*!XR+VGuAAfH`*WR7xPg~m#96%b%x-a8&!cDg zYxewvmp${taBQhBn)<@Jta+4inoyN56=~$9C-Zr&_hX}H>mAKJi9NjZCKK(%%YVfk z`ZEv4g*WQ}o;x)8cOtZxih`G2idXa;`&CEQIyAq%yBiSr-wfCPI6uD0tNy>J01bS-&wq@cg^dB#Q z7O!eOR$VDR>u2nLwrz5byz0k?TbDR|>Z$VMRe9wjad{t3?=i%Gt8P|jx~`AP{D0|J zJ&8B|%U^50zhxZgpZ&9s*@^MeQ|gOmT|=H7^DaA{oo|#6Fa5|X>S6IZ^;Gj53BUQ` zZX0`^a~rSuK2G}Mr=BzHJD2<Cb+3Gds6FFsnXCx$x5OSEJv=W$*FV zx|RBa{g3_4zKxgs{FYwnIr=nDvYu7X_u0oPy!89E=vN&*a;vM&`>jjMWAEkqS-I&K zZ{#lh?IZug-j;r|UB9EFpIJG{Mb2I4Y5dpvBs->O{;M@lGG6+fwH0s++Cr;1;j=!7N;- zm0)mvKYAo^*Of5=InU+cUz z@1e)E;&go#gR$w(EVu+4;tC$IE}C-^0G^>F_A+@AbB& zuBzwVtJGC3pOKe-W2fcES*NRd3%7bxoYU{D?I~XG=cIlVpG)uZ6<&U?zu9?rTbIyt z`(ZxVl7E~0yP6#vfBL|yjx@iser2AZ6|c99lYaC&YfDb~SAB&$^WXAg^QP#z;5qip#dG z*NJobJ9WQv?~i5Pq+P<1*ZONX>wVGhZO_h^mzH_|chm!3dK&AD%oF^6PNQ#j|K&ao zW4F_8;}x$w$4=ekIrky@t$Ok*oUWf1a1e~V^c&uKUM5~8|9a1^-rrbNzvSLUZ@A@K z@mc+>4pBd^qHp?@NBO0C7?;*OLH^xme8f5ZwMjqZ!+YK37l+G#*>&_>-;;bVyp!U+ zAQoQnN*-p<^!l)KZRWvaoPMF>Nq68Cuhh@tvw09s{>y$R#X2b#UUrGsbEDMH^?oqF zwO^gh?@!)nk^^|@_p4hMOkJr?=C{#zJs(_6&m-?IhnIf$eY>8U#gA*7J!r+fK5Fy* z#VcOX@2+#UVV$GaZ|Ipn%U}ANkF-lfK791#Jy|^bm0d^A%l&&fcdc4u}2L$8YvJ3$OV6E0J64`;yUT%@66F9k{+z&-)iI|K*1`)sO0Ebq4#k4kAwJ zZ&qURnJ=(k-(Rpz-<~TO2k&#>=NGf{($D>^OG>}=nmjB%`(5aIPTX?cteoT;^?NUJ zTVJKelAaH??{_}GBkT9R{VsORoAf&? zFF$3!iN9O)dHB7~dHns}9>QJYq8>AD;@@oCv;+e<1pCw;g6&5Kk6-esPCKU zzfJNXkNE=q;1s7a-}ifcW!HJ0WIfOGmuc%Ryz-Iy$a`1v%_m)d$3KZ4qfhp}-0#V# zGv4n!m2bqSKj{0#siwYqkn_bk^T%29F#Ymhbu#(C6&~FDHF>ChFG}6rCja17Z_w9= zozrt}@wi3L{MUOO*7xf7D8+->@JHUPSFq>OU-D7a8z1-as5(PD6W3?sBoAKm8-8aV zyzg8`yop;|TKU+#uw@;n$>+1_8881$-10od`;rx>Qg1Z+RacrfCEhjh-nh=v;-v@q zck6ns->nPRG5&i{XMH#4IbWPNezS0r1Fv|6m!9a&_np<3-gA$gmmN4R-p!_GyyTLP z$Q${^E$vbL%&v1@+eP2{HLkO?XZQwd|Tc_0uN(;H6)2Oa4th z^*q7%7;64+J|Qn9Ue|L(_4F>|bnaomtKJ|N|4p7@&-MFP*5|@o{_8pM!|=&d)@{X! zb8+Lv`PIm29n$-B;!yloy;bk+>~kGHb(VOb-g3WorjPrN`i(uSqZ|K?-Fi=_-d|C7 z$j7+(v-_M0vu;a{tF7;PkXHOjy|G2F-jA*NO5Guz$1a+WzK4^L(uQ zGkRpl6}K}!rSDniNqEI)^@cjwI+o`qw$%~Vn-iZ7u>mcvTHm=ByEqrmZTH2yi=5G;{BsD;G3z*Gd=soLpE&0Z}#-^UMo+A&rP8{I3?q|I3x^;i`fV}HD zLilhseDtag!Flfb>9+C1OTXe3KUN=__oZdm^0K;m`uAq>vg6&>N67lKJQI61Pw-q& z{;m0e`op@2{C3;8-_>!vyRF}me$`9zt$JVml=||R);yxd!8q;Hum1Q=zuVpa#mn#L z`F`Y-ht(D0mh}yFv${H*jXk(dyt;eB=kJJDU7vX6``hLV$Hb|Y=VeEH;ja2gJT`vM z-|hTcc z@#D5nKfAPTk`G??tUfd^6sP&4`G4k3^}Hg&&Fk5>`Mz9?KvL%;HedLZ+nvTO4J@hbW0n0eA6Z9NY?GuFx5ySBq4}_RQ48Nu zJ#9SXv$mbQl^|K-2N@2qeyxjA0(IeDb!JJDOk z<3X=2`Pe!S zeVZ4`=dHWH#Qf#!kuWdC0f>{zJGA?D>~0rc^LBN#_uZ{?sH^yI>P+uj zPWwF$yzGxXoA2zyuU<4i5TC~SgCB?oZL$yEUAP9lTGxsymEB>galpH1VscSM+B*+nL8>WfeM{+joS)1IHGOWUL$ zyz+1Ag~PscHS?sQ&f2nF>pjlbs<*`XHpvGsd;9gR3%2jA=L_{7hIx|tgZwLBnIGzB zHhtrbUh6#~^CRoe)-{rE>%E59b7Rlezxt@n_ZP3Yn)9($C>oxLj6PLc7#_QApIKVG@+3ZaHhNV@9{y;1CVBaj1~pTfUz)4c95V!OPy{4fZ_vag%S&d*jb7`kr=O69336f82{*^5+MAyYf)< zUhi>)+w&#!=B7XQJ9mqhUVk;5``(%_9HQ6lPqRPy$oE(3`;q!xvaQ`dc5rlZCyUa6N8XU&7QyoaQ1;jj0QTt6M)AQ0X!M<4VnZ{k-M z5BZ4R>v@0T+hO1P)7Cu1{RT1aY}5Vmn%_ijd1v!HP@KYTK4`ux&gu8gKwj}i&qO!Bs(j== zcLsLiM&wX$?6!WQyk!0`_;LAb>WmtPkNfq9wDq1|@AdqD@zU?tyS(OgRX@jH5Aoxg zCnYb{yqEvB^mBf~=Ow_)f5TgG)%zRCKl1M(oYpO^f7I^;smt{L{9VttMIQQ9cSK&? z@(#Q8yCdoj@v5HhivzRi8SnMh$9(Y9;xHdD|25CoM*n5kzmop+e?E;qe`oTDSM;mi z5U-Mt+rw~Jcg^;Jf15XEyVkMv|NPzWerx2t3Xk<2^_IN4@5k$VcJfr>nD>?VdHp*L zcTe{6JL0vz!SC>SzF^%|D=*8tS>LI8+WVqg#z+0~e&25A(l=i9q_`?x;f?>wtB1jE z%bvquc~}20AMLx}OCIsrdJg?XpVp_2>IwC+Jf*yX$<1ecIGZ z)*p|5+V^ii$Z>Ia7LN9cAH4FB`a)eP-bR1wW#8-G5})fiKmPlDTx$ONisHQU)9|uq zcId306;A=1c@jIBZk+=!{faLq>MQHe?c=ULyne6GxJ=Kx>+-92kBLXV zPj5x~28`nis0uUQ?`hb~;{inGcFL z@~}4bv^ceW(z$&f>0q9$-nh!~cLwm99phz>^eaw_U!Je*BY*V0C2x&&rg&ZJlwZ$v z?(>>rzO~cw;^dDw#bfn`x+?yS)B4W#N8yT}i*HB!;|FE;=85k6*1%45gjamNj=Ztk zW_}wxJ(>?CK6~H&=7;^d?az8E&TaT`8As!LLacYTd*uC_o@zOTXqv=K1l@CJ(7A!;7!p*HL%;LB>O!z3&%D8kvDqWV!uyfzjgc%bDsPhdug+L=vUm7KX#GZyw1EZ^ZcuDUj2DL?~rN$LyhRq`+W9v^p}tLXobxK_`{`Aa*~2QPoZ z`+k?Z>S1v?erbMq^`r1bzsKm`bEX#m75C1*j)(UvUGDn5GWCY_9P{1p^z-DIr{TPb zT_4$Z{QMx^$w%HZcE5JVAH2KHQF%k$BA<9|oho{xPkHGWzZS=i@n_@H%#Yd8FXg`E zc-Q#uqrMSO%nLs0@*IDVHhSaF^?t0nLLL&o_^)x3f8RCNss8bj<7=JEyionC{-aOv zsr|U0|0JzE<-G^*Db@Ri;ywFu|5Nh4?fve@pX3R8j^BA6Dh{bH)LZ7q>dIsI)t|=i z?CU#t#b@Kr{vJl($)Db1pl9o_xXlaIpJV-1>(lJW{ol48Pxa@1^!uxwkNtU{q2_m~ zE9G6>o(n!r-o1+dTF)|XwC&$@u{dy0LUo`g9&itWY`AA(Ay%u-kwDpXNPx05|<32tu+z0k8FSCzx+x5sB z`?9_$&S-0$Huh`&Q*~7IexT>9;~e>O?B{G+9(f-`Pw%JwFm3AKipR0*%0J<2H#tAt zRY%He`y6LS?%(d{<9@#wIq)XmsvE0rkdIO~9{F?jd(Ke52c39k9jxjWb@&IluYCWN zY`-gfykE|J)B)lazm0yyU-8zw;EEq7F3VHqgY|n2?(?pAZtEAXe1vy=ew6v(!Si10 zRMw}W$7B5Z5dEt^TjG{=dh=mzegEfOuLs~Y?&382ik$5B5IxF6ht$dH#+JOrZmVwI z#eQxZ|95>HFaI^Z(XV{OAFa<+zKQ=H#NWg#`rX3cqJQ;wy{C0`$K!yPUU#{__-X#e zz7wz6wLJXfajuKLYkrt~)Z+hDe_ZE$e$?*hGxDl~-j6)i>*9~?ao_*+&vQJj=Lxk= zo%*}&bKbqQ?aUv%@<7&Gyw__TvhwO*cDZlT)_N?vR!6l-_{QPI%a86y&ddvIJ5M&pz+PjaPi;SK{+;hyT~pM*sEi8uMrQNS;dksyaoUvOcRm zQGdq%tsB+*Oze)lpSK-(#i!V%dQcrH?%v#VetAkAUGZD}lsMJ+^G6vsdH$~L9ZirPt3Z_#0l2SG?k%A9NmZ+Wg(T?if8^MbG%v*X-W>vDQoO+J47j!TaUT zCmyroWAZLOZA+Y~c|+`3J?Zzes=i>)?l;PDSKIE7S02jq6Z1H7TL<^vggEK z>j1`0{L>G=@%^rM{+>8q@k;&7kHzW4oth6v?^RdEZ=ZU8^pkEc^?l)Q#(wTfkEiZ~ z*L;Eh((l8_nfPozC$Eab^m-G!rdRWdCjZJu=c+I9%Io(#A3Kvzj?v#CdDlFlc;nCZ ztD|dPC{EXUUB>a09^Tb{yzKcK;f)>F^MKgz7X4X|6Sw5u(z`l}UVSfZ3#Yu~{_l!! z?AQI|qX&^Eyy`oCim$~_&HtZ1?$;TIs<+thx$_WiyzJRLF!O_h^$m86Gwqc;6nj7B z{Hn*qKlgFpbG77ibo{6P~Qs8keUTk0%+2o3t(dtv+kX2Y2>82l`cSq@EO) z<(VgsJJ*wN;9=MFzGc2&zpE2_so$w>Xa0=5>H&F)UaeasE{Rhcz5Uxh9_*VQz3+1N z_cjbOUik8>^#1QQ~nwI#Q)@n{k&SoOFVa7#V>xtkI3_`+mZL5g^OOz6L2L? zZ;8W)w2j{JsXwi=Z@u4XzE8)0qgU^#h|lurrcRC?i!=FEJ?VVcANCo?wAMS^=g$6} zM*3w}?96lN_oJ5&BX8;j_0xeKANS+@*SNGl%ypR$SKT2lw|>0c)d#P7LmmJ1$hq&W zdB69PTILT=ANS)|iCa%nj~uhkWnHJ93ty$bcBT(r@hbI!xN1IEa;uyFJaQ*4^W#JG z=sm(a&#$))*|F*b)!xJ*Thce&lLz z`J-R+h2$gO2fJXIJ0hAH3o-JATmRkw?_U<~>{Dl{j_$Nk9LF zU*lC@v!6Red+Dw4iks@)_^CPypLMMASL;0Ta`er<<*oLMeLP+&!(Hyg%bw|19U1+2 z&d~CFMI1VY_eR`)+_|pOnr}4z{y{%}wmJ*%E^>&&z89JJbWHr+;-5_(iv6meEAFym z>pA?To%w^8z0q&#t6JX(xB1XbxVPA^ddhel)zP@mj9ItGyW9FMcI>^4bkochLM*( zVuw{H@MHRBubB_B@0)NPb6&Gf@P7F2itE&U@XC+Yb3TfE(TDsiE}I9|{3!OV&N#?V zANPLPLw(Ki=!D zUm-6I>l~hgHFg|7eUka0xMe<7{*ZWo_I10FS3dgfaC>gXuK987_vUdw?<)1=7Co1p zXPx%Wo@aM$o&G!WnvaQ_>V@!IpYhy8KEhpbIC;x_q3W}JA0O{am{&G=@U*0F=LlZ$ zie2C9a@Bl2dFj;rRX#EfE%QL}+IXnL<*}OgS{HTyw?p@0FL z534_#I)q-;BjR@IXZgGSy|4SZFS{boi;}*bJ^IHhUhTUa?DzQnY$s0RYu2gc+r(${ zh(pe2zZI|D@9j{$dM|kSt8r$(nHQEH(x3bqo~o;iNBC=gWV}+Rp6z)9UjB<)oKF2= zy@Q{Y-cnCpnJ*QOyS`8Haki6h)Wyee*8A+yYt>Ww z>%E`^S*Wd~W;5DK4uY z%oiW^uCsZ-qmAd`mdDc7yj9bAR)r%m-_IBkNZ5ct{@FQa_syRoxsrulT%A z|98zd4#3F!8(l8>lHQ6ZersJvoNC#B_+Gd^NGs02ZMz&fUUeHUd*;W(d_f&)9^Ck6 z>PF*nOkQs6S6ok9_OZ`+@E>x#s@!jSp8JTK_any;pT(6!{8b&ye#LF`2lGPq?0t}m zNACNka=+*2TltCJjYG!k?CVxWb>tPFty_^d`KR*ik1`%V>Ftf}*!w&C zJ{-BcH0qjkIF-y?n6j=#&-2lj0IKJ4Rkw%^ZT&)H3{M z^|Sl7JN~%uuJc)kkU!Yrfqnjp<`PdywrFKX|Vqr+VXqzHNPSOMX!|w&>OT;F$PS&wu4<`c=QMqgNE~ zt)GUM9LYzXcT}8?em!R}-#tF=$XC0+a|?LSU?YX6toSDtnCkFLJi-g|cL*6#nqcK?5VsbBc>Ki&Ij&tLrF z7oXkWy`P@{>E}ydxc)Cc_w4@;-}vIQ)}NpFpF3^;`oH|uKlwj?{2%}GU;NpR|I?>8 z{?T9jr~mxJzy7ly|C7J@kN@G%|Ki{O_&@!V??030#r?m3V*mF}?B74zpW)BwKil<6 zf9BEOfB(O`P0XRcR~o#(Kk4sB;O|G^??>S8{0OLb)FETtv)e9fi14c4%}dpJwl9Sm zFRlmCC;m&}#DRCT=j(9q($;w{T(reuz2E%otKnP}>!jFt#VPAtT6#a(!D0vS;<~qW z0KEKqF|3o~j=cDATW>KQCp%i?0ABViPT^eyu%Z_(jC!=Ti z>C$-FGd<&^Z}E9`Zu*svuA*Ph-SMx^Nq)Sz#<=XfOKI`4SNav7jf3-6=Pr(|li=mI zyX&Nla_w!e+yM-5*x=MYyF4@Z^$NS#akJGF5*h{l( zyy^*Y`ZvN~$6r2N%k9M@PO)eDUJmFMf${QJ`8Mw(pZ$HyTf~3u!+7b_x(2^>{Ixrt z^a4EMlywdDhU1fp|Jq{V;lK3Du3x*u$uGbwKGUmwyxS%Rcun!};~`AI z@#5mY_~qki0bWxuy!6R$aoSdI8JE|*%`~Uu#l>&6_D>`5=M)4l{c72@JZ1mqyxrL^ z$7?<)FI{@QL4WcQ|J`j-i8h<7HuQ^^UbU;or%^9>af!qHx8l`>>30_%?-8=+aeP+a zreAzodbYhfC;9R6-}_rXvPFO8QTandin z8<$JbFTJX-F1>zc&+M0;>3wy*lAoR8qSx!q8JE@K<*)RL`?6?T{qBmmgp*wxhfCo; zrC+?4l85LEFE093ckpZHuilQl_{@W~^3|pBidR~CU!9ZuqkidATYl_<#aq1WRegn5 z+;-mLxRsCa%0F8A<=2^eDtcd|5AwY%0Kea75!>21Q@S8dmTR97lK(Bc*P_6NK5Z^UR}B7|KOls z`DnLwp7P&p_r2@>9eH=*qE~fQaj%Q|Ome*J883a~t~`8Uy!gZ|bytnch49j!xU9Vt zPHMu#Kh+ucwtfb?cK+%uUi#f_ok%{ax?^?F$d6aNqF3)h+kYXrHQ&d@e&u2MW$!gU ziw;1^zjXld*!$k>d{Mj?#6HE#f8{0mf1!iLcHpH~{wp7`@5QiAii?;2r=_J|yy7wa?zYp{u6ShR6_3R$$5&)~nastr^`rdv z*Rw5-z3kc*_u*y7@-9D?kDRw6`%?6b7mxgVKiu~BQCR;kUipYV?}gX)`lOv;s7eL?bW$QUh^VxnqRNZ zNq)Sz#AWjZb%%Ms>sD>?vR`ren_DNcPFd%z3L3d_$h+QKc@SRy>$vk*#U{V_9A5uk zT$7(xdw@-RUX^c@8?XE;KL1X*+4*?gs@o$keTrA=EAxjse^KC) zKl)6(^6w5e{=6vO3u2GF;j4N>eR(N%jaR<$JALwy)_E@s*kU_yh|lJ~^s4@lkNNRp zm?bV=@tNI(pQBpvvS)sbn;pwbtLqsr4)ebU(XZBc zjN`T1HeUW~{zt#&54P!lHBR#4HD9oPgHQZ&T)QeaUh?1H`bfyT;?*wu*+D;Ry}x+* zCqJfN^CbD$d9GWHnA~HWvYxZLK1Y4v<(Kj2bGp68>xcZ-1TNPh0LU z`SHj{|9^S+l4RMDorl_+XrfV#YE1LHp~O(`weZN| zh37>dNURSYv+cZbblsnYBe>MT@-RI=6}#T!4UepTo%)EqudCT1IlT1uJbGr&@H+3Q z;N`#au6jY8@GSG7K3o-d=`DEF4f3wM1aF%v8Mz{{SKceYa>fcW#G@ZJ)8k5~S|pYaX$E{?x-qeXVW3kUxdulO(hF9PdM zG2s<|+3%^3OX&B`8!UDJUi!l)55cS6m#3V!7|aqEUU3*c>w@BTU9k8s@QO$D%WvtG zT^srPYVhGDzc}@>46KmM&+8)mvgGiJL-65Q&-*z4srWIx&w`7; zsuSQhA77rW^|s)Zf8m8w-N4@0L-=Kh_ju)9JWF1(|I1gew*{~Ki#PYa9+rnl3@`tb zU)2ppJo6#FZ>JSGL3E z&ya`cx6WG}FdXa|UgJ~6E5GVH%e$+`r@cASFaL!PZ>C@RHZS}8tg;O+z9`@FU-8R) ztb*$jxEUd_+%y5H>k;e|t=oqp|~9mhlEgO`5Uuk~Ledw=MCXFU&IdSt)i z6TDBY-p8AJADY3NpGur!Z}iKa=~;Z@$F^73Graus82!>Wd*;{X!+fna!pm;qR1eBa z&oU2B4X-#QFCBuDy|1Rvy}a~GZ}h3}&W`DSfBkCP@bcdmeIV!=<)_tf-6b!){8Jy+ zdP>FP;J@oWtL%qYzG2Tsc z_m9C}c`4hg%>uk|SZ9!j@GEi5`K#e1FZsnKdDprMzTy1UM|j06_~8Gb4}|z7{jZ7} zUinuZV#oG7Z&jS+E*yRAk&o~VdKJ&=d^cEZEct_1T;j*_RGqgNzP-3`@JoJ+XYgNs zy}y37ZFu3NU-_4PJH8sey}Wz8^eSG#D}L{_ripL-J zaVCDbzi!oScw6w%v-m~N_?G^b^H;+S@1AFfSF7T>OAqkUr+6j*ic^lSjvrpQ=vka9 z|Bb!hHE*lzhc|h*{w|?Bv+IPvC>f>->KpYf6hKWLH@;l(#z2H(#z_KfU&60yIv81S;^@QLjdoPVAX-{9xp z`hgd|aF6#e@Kv1tIC$l!W47C(A9&&5w|^E~{~@E}ZSfDh;tyP@hf2@YGlycaIl;6rWFh2+y9)%fyhrRy25zeVnGw|Bu=BJwiOw`Qz;Mev)5& z-p48Sj8F1o=dXqsUU7&$%SW%GXZEbFsOuI3Ol~+*2W`Q*@#9tXxmO3g^b5CoS6s#` zUqs)l#w~ac!69D7o*RCJhu~NHd0S;0UiJzP{LeBE;uO8pv%1Oov*U&rpG-V1-i%+t z>HOJo-6bFS=}SC5^>Kwhj`Qxi&no-jV8`rM-sQLUn-|Ajzbf8iACjwsg4g#&i$Ak} ze!B{8a)vK%r{EQr*|WISa(v9ndOzWXL%%gVqwuri!xO=aKhPupR4?@4q;K}Vnuh6j zhqwGRcFlhqzg-O{dEwRHu&#gV;|x4=nwip%KnY6pM4(Sg-^YYZ=8Y;uXO(GxbBjV z{O}s-G5X!$7SHaw-|YM0m2c!Famx2MjQpD&v;Wy~k`LY=^s(oVksjrxXJh{+FZG&%4|Ad#^!N-2Lp9L5HogdNHO9(IhCcl;*Pr++_pB;bwUFSUtFFQ`0+LC_?ckH>f z;GY-K*GmSkxT7A#qr@li3!jAF`R?=ePrLk4a*E61v^XU`o%)cKADf@cBlu<#z)ODp zXL%Q1`hF_*EM7eydaQoztFhhmW1k9MaW{Ucz8AL|zQyiW#m%1OUvUUN@k&3|wm5Z+ z{#U^dFTK5t{5_+7mAJgRUBgR1c%;77&x70kI=`*?AwU16XL(1w7N_+&oWB}sc@-Y3TUs?GHZg#LLUiQgP6OXt56#c4y%N|w(8hOdjKH(Lo^<%|p z>k6)04K}$CLyy)Kif33)!KYWlx0e@Q_6+xF;BOyiq~CqKa{d0kvu=}DoD!e)C)qPz z<@{Ok+$R_L`R}e?D7zMy&5QhX-~DGh4ln*3e!-8MxFsL6=h<*PR33Qw@3TIx#H*|q zvhU*04}HL7=fTT9`Dq`xH|r_zugWt_JG}f--bp{Qc$NN@`EdPeBfQ7{T5^87sf+lp z^H#&RmlqEHd+g(k#Odneuy206D$jyfd`_KEejA)ky)T~e_x=3Mz6~$=>Fp3b%TLiO zdvB}8EqK|px=4MGUsWE;Jj|}gyX1qHe)+9BP`$w3kHO0h?z-=+`{AWu`6l0kt$f6P zoi{6<`{aU`e#Im2HCPYDv*hXf?mO%8yYT8as|R}@2Ihr&OcZ`w6f3izn-6$V>Wl>g4&5JWL{Z>4#p$C-o6K zHZQa5@hR5&RD!kpX09k&AuOAc~w0~zrH7`{&n8$xbBh#HtG*dQzxH?&uPXn%RsYUvs1KA2UV6eO*mLUNdauxa_VB>R zOmiB%tq+md>9cI7kJDadoBx`han(9M;Z487dsnRoAN~yII>^3SQh4brb}An={7V1E zd0&0E`S-%hp2aKgPk!772Ks#}c*UvIebs+fAMxv&pZQh!l@gL4pM)#xD7CJlPx(~z zt6q2(``zpLl>O%AD<^M(o%9OK=< z{Ffq;Q~p&Suw!*Ee#P$pOy^5 zaqh1B&$b_4IHTYGd2qtbuMfdJ8;*y{v&U@X75LnTNl~Xdd|gL!W!8^WYVK zqtE{9FXO8BzMX$5dB5v($*?9|x~-p8A6}h^UyAR~`m|7A z3kI(|3NQWfTig0saPs@PQNEE5Uim~G(!Y^!PW|;Y{JOq(M$hcSecn7_uHWFLC+pmK zANVZK@>}@JZpS>#1?p?0fmhx0V#rUAg*SP*C2lPnr{QIXhv*BRik`Rd=Zf3v2X^r_ zQ##clc=4<7i2iBxoUxt8c71QdbyI^=Wi*^iGMv&}Esq#t zy}s7s|NjHt9}K;1r;O3>_RFzd@8{@GznA@Ou@AiJ{KO}Jr_U%}R~^jX7lT{+r7wAD z{~j>D6}=aqG*7XQ>EY8aKlC00JBH7Dh3fqG`}EMhQb2fr9Qmzx#;%)sNF3|qyy{!x zm(O#(`+eoZCfHf>MP7K-J*fi=pZ<>d;0F^xd5{Quyw8F=csF&gKD4|fAFpQD@Y0j` zllr%(9;`kV{D;iTYH=D~{!72=BX*5Hde4x4Pr>baac|anfR}viGx4e7RrE^V>f^>9 z+9Dr#_1p01)CK48$u2*=iaznrMPQbgd%WVVJj0&l8~hn=+v*7Ss|QT>3;FOPyee^6 z|Fyo4gm*ZPzq`+5@ZJ)KobUBkZ){ z)t?owUH{Fbc)YXsc;zMW=rnL{zZ#?bTmN5#{nmXRPxNo~By!S=IKyt`Bl_jX;&gat zlegXHTM6?B7r`qZCH~@1{j)xVfY*8K{}Dv|ULOH3`Ppae`5a!g{pG-|ztfIm`+Jq; zF>VGgJA^}C3U2Gc{MX-Et@qH(*JH^1U7i7N{7`@W9DVjr`nbFJg;&0x{om!;m$(*Q zb}T-t_mhA5bG^6X{b<);LiTU-O!C6Xj^VXlB;TI;c#3tE)$|N6|D)&NDu4ZS;8Z`f zXTe?9k7=0xXUQA+qhI{L#$V)k?7QL3hwPsoXas~8&*+gqeBvBCw%%Ruo2`OxFDJb0 zS${^|hhM$SJe+o;F^BVSF1;^E@JOCR#7}u@6zYN%Z_*TK}(;q>LhVYd^1m%#_`bS!+Y%Gic`k) zZM^5+60e$h8E3Ee6JGtNL+~aqiA(I-SnoC9pYP?m+4T)CIe!qj#i#U>tKLmK^Sur4 zM_2t{_nTDpf_Ev`S`Bq zU3x#f^u?YtZm0fQLVYapy7^v*K7e|IUtAj3UC)P?ob-c7^WW%CU)J}bm*bavy!1^c0Re=_u4dS>V9D)V;N{9bxLyocb>e`crNtHZ1KY2mvxfN%JGc=<2f-owy$|7grd zTlp7-|+E|emcD5?E{zhyS+!)^dX)1=z@Mv4}@1f($`3ws`}4+4A!~X!S^J_ zqumBxaVq`S4S%+NWWC7wk0#*v{2=n<8HrQ%ec!wI#olk#&BpIp%C2S?^jj-&iiGqp9s>|ib7uc<-gAc?iT#slhm(M{}+DO zwOseL553?)c;(IKkym~6>Db#a-P$S)6z&-95; z;8*H@>k9JG>~U<5H~n;V0lwjT9PN~OS;b%X#sM$?-SuI;$58KY(7QY>9`Elv>o&aX zSl&sz(r1=`y-!*7g6n6+x0kEr?c)gCc>l|>zuv2}4lG{tbjpDfc#Xii>EIgBb@!#+#>)OSy@Mdw``L3T`ujC^y z{YHP*JzL_|_7~B6&j`2stTMvO4})hr4P4$ks{YmIW50D$^J2ZJc;*krd2O~2ye;xY zZ}RLp_-_AZ96x8>5YMVUj_YT`x0h#+7jORcz<2mfaDFjH^+Ua1$Pf1Sopl@DCh%JEp|!K=OtzRJ7d&uy<){?2Y^#kZeFc*&diTJ?_iuH+&0QTFrmT1RuA{c~p7 zhL?Un=|i&c#oNEjcJfj6ar84vzq0_kM-F(!=h&%!6@I)$ujlAlzG|n;2mJRu?&62x zWrv5z|7?uxdi(3KU4E?&{w(K*e^$S??%U@2kn4w$Tc0NSs&ymlzsWO>>i%txPstPc61U2ZqtEKQf0Xn1 zD?XOGu-0AFP5RX4^U|pIcz61=&fV36@TXpCsVmy^%)<{dUK-b3&xbehNglP%S$(@t z2M%%C_ZoWgaQkU+dY{96?|SZ~_LEDzl8?Nnl6<_$zlqD@bkz$lcX;{#Z21}9#24{M zovZ&^bzpFN-@Ew7rS$bpp9}9X`bi$Wxyp8U2K{dAx9523jAj0x3cUCgUYYvnoVp0# zFjl`^yv8@gJNIpqeM+wAOWmG0d=(zu!mnD^k+xIL*IyQ=CWH5uIPl85^d&w8=l0(R zzVch~m_4-Mf9nC0?SS_fdD&y~s=R}5H2$majCaMJ^);)%GaJu>SKh!EeiHonVe~G3 zD(jEco_vz{~%RL;hM9VYlMf z)i}P1W3l^sKW%^i*|yw7lhaP(_k zt4KMw|oA_M$DEapsJI1GrU#`L{ z;pMmT4nLJ|gI7IVb&>T2cFj&^RWQ8bmAq@6FY6@y+4tzgDRH{vW8vNPf8b`r4X=Cz zr+!TAm)+tO)(gEyx}Ew!1}|R4PiDalFS+od*fUw2sTg&_(BzWoLkAveh z#`a0Z*sC~IJX-u#XT<)e{XQkU;tYF!6`c4Zy{d=lKYgucexBvJHt7f6W8@4!I!CWt z@KoKO_n3b^**6^FdJ-m#bXoH+J2Um(KJY9<2{uc>O&k_i_K(MtJp~QunHh)U}nD z)Iq!c2i~=vGG9N=I4j;m-e;J=dO9CUvcI*@YVlWOy1d&hvehU z_f^#Ucr;$7j$}8UbC(>CwZG&DPI{JygGc_6pIZ2p_tWY<;8X5nz4(~zHpyp?7w-t) zD!Wzhhj&z+Xq}0kPr)aCiGQ>BGraW5eDTqt#r3|~zm0xdM)$7=UicUCu;XLo#IyA6)bptiidQ8*;bHYYmVUvD z+)v!{9P|3v@Zp71Js6zU@2mfePsXmjw^V=s3%*)sd2B%UJP%&;&3^TD)C0kHX20?< zJ&NZ>_I%IdAN?@Au`_)ed8Yg_@yYiZyr)!gI(*Z0wVvYsj}GjP2a@LpeViaprSA7W zH{9xkel^bDlBX(fx!)a+yZCPMiOep=aJ;HKYD2;`;&pw z`xyN6j5oracvj!*R`2cm?z8HbUEJxW@TL#a63^@VR+GScOAL7FS3gF6jXldt zO&qh1ByO{3_|4y254`Y>J>J+QzpTFVXZ^LH>VABr^3iN|d)Kt?@y2g`FUNW)KdyfI z%Ync0baJ;zTs`B^csNO}tVso#orp zI6m$77538)?=f=ANBFb2YZSlfzmMy@ztYnW(D(5kVy(}}&zG`)c+k-x$v*V^UhoDt|Fs^*Z@1(p@w)yW z2mWZ3-`KtFOWCn$hu8ZD{PT|ne(QefC4H=Jox%D(KIwk$KigRH4Se-pKL6d-`%RoS zhL@O^x?WtW`%eO#JnU?*XZ2G07wp{n13&Jmms;$-`dsce3EcYL%yHGycc(6{J`Y~zewWtcUC$>Uzmq4$CnG-% zpKkbu{)YECyf15=MPI1JUhb0PvG(uripQTszUb5Y8|vWdPqO=C&VMYqzwLA2<-dtD z;`2H7ynm0w{#x&57qjT`uK9o$Kfr@i@7-Pvy`6tE#+!c{WB>axT0d;ZY`4ij@X`xC ziL;5%`q20U{O91l`G0@lcTkqri z&5-{p`aS%wvE75a$KUbk>Swrbo8+^{8~x%NTk`Aq^MP;s+u%&x;G#(M6Mv-(k47qyO1by4j3 zD*0(+-`Q^Z0Q&Lb!7=xT`%-oeuly^Hs&9JajQr=|>lv$F3ZJx|CQhpxo9~-hM^F5( z_0^h(_HIA$dftnH&-YI7s_i=a;Z1#ij^CcGkA6DN)Bmad-KF%|b{}|uXUJJ`RXz!h z+u+))qXhTu^|($wT=5P6RzL9D-Qyp96W;fR++|<#W!?{N>Ycf_JG_0~^Y>W#*4@zr{6d)$xbvge-+ zdAHLT#hKy}>fV<*E>FdN&4=}reVr^%b@}RNxsQC%-th-sd~$~u&$x|!-pIGv_Py_O z^!n!gtKfLY;(z1Y!>dn~ywl@%TX>`KoNalw-pi6_XYtd!CIVjh=-);!iL3I_)phoV zCyUcv-`)Ofi_=}dM?Swxj>p;$uY953^hX05F(;!pAv|I~-4Z+=ku8Smn^A7uXc z(PQIH-tnGT)$8%obL#mU_Iy3$tvD8Yc;mm11>hS#hkp58;#KjE@Gak)lvnh(TKv3U z4gAF)tt;Uz;gkHJ$!p@XJoOF5|Hh}o%YTnU?pnY7cVpW+i$2F8ar*!L=W+b}e`n;c zALc&t7Q6MlcA<~w)9Y!-X??_dWt+J4%N)ly__HzR=@aOS)cfN<8rN4}r9JWoUhztt z3Xjmg>dCJMb{k%G8$I8KPuKcU4=#1IxZfth`(EUDmJ$DpA6^A#y}uEh{%=md9@kZz zbDuWZhkoG|H|RNWxA&*HMUbn}nn zIKI{3*2kn@@t{rifj9Z0_~a+S#s895&(~vr3+^8KuJAyz)K%^Q1pBbUy@&M z|7PIn;n9cdY$tAQM*0??@Qh1O1HADg-y2lN;Z--mWqpA?;~)C4<)7|*X?*+Vmt1`u zk$-?UcV$U~!pYvn)^?jAPf1Be&9{EVz`oqZo>oNB53jK|n^dZHo z;#KNG@%>ruV;=dH+V*P2zx&yUgIO?;hgwa-*52T$Hwis zhk;A~m3;hDJZ_0oJ$-<#&w)SDr}=wqJoh~h-Zt>^JGk)%_In#Yz4~p=k6n8&tM~=~ zxbOLoeH>nP{Ncc{rOv(iVr<{Wf3LE=r9Ncm;&}Df>6;%vHm(tqwjXKC7FX`_*&WWj`gykiWjSsgLtf_9tFdofjT`oA}gIH|gJ2{m2gR zH0x29LJhC@l6dUznYHw7@C$z2@ho`Ni#_u*yZ^%ba>%RhwNBRlEI9NTvtGRgr#RiO z#(B2&D~&C7QatR(yZI4E+B^E}_4_=}kDj*3cfKC`@n*aO&%(2-kE#DR3vV`k@RAQd z3Qqa<{J#g@o5X4QYoCn$jUC56Dh{+9_q(WyID_2yuzRL>FAwbZ{qTw=DvG>t>-_|1l02)Px@E%hd=1Y z=}W2~)J6ER_YdoPSjXJ=k>K3>m_1(gd2m-BE^)bE5BcB!=P_RWpE2qOH1A!plQ!80 zUUqgG^0UL9dJwNXhc6%EueVp@{IX;5PW}A;INoOYz>6R3`dC}yQu}4(&UnTzQXidz zn?JYk?7Hs5TyI`4g&*D)dDvlizIfGsF^=B^*HzX753%e1x8t}zP`$r2tA64AVQ?Qa zCjaP9_2Au-hi_xw>L>5zRGsnj+~?A~x#hFhFS}O9g*W0);`8Bp;GkD^59&FywFgud&Z_`pjGU8uTdN*7xnq)5QVZBLKYYS-kpq;HOvXDB|-KzL9y@5})*| z^hxe{`r{vlH~JBux_+GgYWP*Xw{L&^*?Szf*JGY)-TOth#f7RLvcEm@XNR}mQ%O8l z$6bk2$v?Nzr?}OUkGJ^48^65}uDhlYUh^NGQ1xl@Zx0ToA&RIzreqFFkp=@|E}9GjDf1{qc9h`#VE!e5fZ6ZRuyIhm7zZQa4;( z=lbCHy_V^C2fX6*E)Q8pk&pCcZ`DWtG;q={{!#I%?7GeIffs)cUUB#)akk=9_=P+q z-{MzQ4?l~(&Ep(sTfN6euBDhiY zMtSypJ+^!51^xC~Cshx+Ui@p5eBhNg=p}VJ9=#>r-i9~dq|bBEr_4N5oI3VN0Pe)t z<9!}E*)`q~9!$UVy6NYr_w}XI7ur4T@|*Cgi_(wOZ)V5(SGU(=J`PzQZL#a(Rhg&D z1G_^4c#i`|{rx$8r@Y6}%tQPW?sM>7!5!X-m$jegzV3I27>~9aUUB8aAzx2FG-tjDTzI-cAZK(&XleSOCywu-)$1~jb zj>kXxZg|cAA#&?uc`qsbN_7K$-~MKtkB^)azt5lKK7W|e{o92<@UrKfzv9W~9nUEK z7<|4LTJLR?9bXvV{_*gdfBFrttoP*7U)`?y>pR@Uuf3;njz9P0Y5l(HySwlH`H#H~ zFMm7sA;GgT;u|e}x)%Fo&(;+xAIZO|tIDp~4Lcf7dHkR7(r@Bw@#fTp){FG5d>_gF zTGtlujE|4#>z@cOe@mQ#SAJoy>fb}^!7YBxpSQ&6?bOF}jkDRab*xvBGkNv!MYdzl z>f5RVclL{C=o9E4)VkD|h0Fb<-(zt7n~XmlV-KH_e{aJhi#MkpuJ>}xn^9doOCE-o zJos<$`hQN=6~yDR-|&uG_WkFXFL>KzA9%$pbq(GdUMWs(sROs`fy;WSeoxu2e(Z~J z-ZZG;RsZ47$)oMJkvH`K{oY=U{nktBy(N9kX#nm7ftNj72g!Rmm1jO5_zGv@Sr2dI z=PmwD@A_bPi@s<5ox7bl?|c(paVqlP>dU47sNTJjf5hcyV;^A-hmJ!b^`%Qf)uBju$wc=Uz+zaU!Uh(JDUkidi<4<_A`kq~%ugCfHzn!vu%;^5@ z!XNW2KKCIXUS*wIo}t&O1I4E=#&uWMW2ATM6s6b0INmPxf%m=0k+=h=zTK6+&DA*X z9GvI$BYXDCyX}F3sTj~XNeg0+ee4H`)tm5<}FiQ-0)iKA& z&5y-t{paB8vEP0@&bQ8@e|OG2ox@+Ijn8n(r!Dx~6Zz1uyn75j{TO|%Cjz(Df7vtt zgZHWHSH1ew^vXWjvw8teJkWmUuRg-dZV!DRV%O|ketv3r#VvLX|LQo&Prq>DmGaV4 zwP*Iqe#K|_&5LUgtfP5nl0$Ugf3Mp9<1}173dmmVTco zUU5o%hW}}4_s#cHj?p8$|Jw2q{Nnag(KG*jKl&A~^fjI;UO2@o`RS?X6%P8PN4!e? zOYhEKeS}v$7O&{r@zrsXA0B*zKIxf#JI{5ij&QK&V;@N5WBZ-ADo%34LBGd7j)>3l zu=8BE>Ilc)f7$a><A8BTu7zRkzi&)Pai;en4{|F!T9 zdX|r#YP@2{^eYcNRlIl=exVP|&e!qKua}hn(kK0j*GA`k{oUq23dgYzS;Z-Q!}0l% zJWN7(*fT$d8_#^$-R3{*F1$~zE}{u|`7iy-M~*vx^${L%8D946`06;x4-dTTn0}r2 zR7QC53U)0%8^yELalNv?yZ|qf^GMWeHuRh*|SDobe z>Nv>{5B;)Zc%Q0%#U-OSZTqRzN%RYs^@XPvr|z<6c5HOsQyJ;^*asqizv-#fMf3%) zc*TyN2fzK!UwwpE9EQ($3~uwVdfb9ny?|%POOCIuSMnF0ogVRMd5QjAx9SKlJGFkK zZ?`J0yX1zK9_3%#j^B0tYWv|4kLcC*Q_D;6idT4sc(t1T?voc@`A3|>FZs3kxbJ?m zABPvN=Y2?Q8*b;#j^{r4;1HkwwZtoN310qdKJJ^hRgS~MZuu{s<@hRi?voQ9c&&r7 z@B6M_?Kr&bS>BbGo=RM%7kJsR5l(r^`Kyoc((kbkMB1YUXA@%?qHZo|WW@n-Rg zov(^-FE_k!!ONcC>-#I#-iDX|?(sUlHp(~B!?U+%xb1&)#oE8Y+xo!4uH_-T(($#? zzWIJA9z~yUzZJJKFRS9FUpVC<_Ds*K;@is&FI?g>y_$#pb*pZ}%RliA_5M@MNAyUq z){$yHR#oUu?!wc@0db1|vhO-?cl~OcaO`oi=hg7sCojC>75{x|dNmL5@?Rr+mY<$V z+=3S#`Zd~bepVmhm5OuP7U%%Qmy!@0s`@bpH3(d!B`1bO`EAPVF`#96~A=~@wSKEdco?~!{ zSKgOp=d0n{%L^}iWxp?jyW&>1_t&qsy~hh5{k{m!((mH9;T5mwS^Z1j&x4cQuclY> z!g~xJxZtH{$IXlDR~zBQH}Gfp)JOQGz#eSKEe{{`f82;xgQ;;oHj#FMgGHwe>#E{OuXv4DI)8P%>=oY- zw`@N(y!g6Nw0f*Ue$j0a>L7i{r*0yY{Sb=#U*++ng{2v zf^RP;`RSLx_CC&hs`Uc>!Y5wIzx2DGuhq8cmtWGac+9@#CFiY%lf3ZKFCJxtlOMBt z*RM9hOK<8VcFmr}XY;ZePV&MFCw=Na!@WArJzjX|aqqYMnjN@)wUK`LC7uO0zlGm< zu3HuFu@A}rC?kFa_fySB`f~i49m9=RuWHw2m(lAnBm0H#MfSJFKYP6Vm*47R(fi_X z+aB*BdW2V>Qv7}@c=;Up-(SDl zHoWY3ACJZ9r>0+cj?t$&L41B{@rr)MWjqUh^Rb%!?&W3Ac(Hgzuj(Y{?XO>L8xHyC z!#)teX&zR?b(g&GvS&P*|H?;C&42MK^*ueChr8x$wf*$VZslM0EPfsPYRJA?UU=E7 z`p^5o^6yjQ8}!S6=~bM5YWawtic{8&*!Ndk$9j9&Gkc|9yqO=f_w^8dSz>tQU;YXw zK5ag}eD!);d%WsEd{X@4-|Hd#vc&MJfA`;$d@6PfHN4_4`(@8Bx-*}~2roUdU-`)B z`0A+PrCJ-aMn zqjz?{x_;r6Z}I3uaI%9{agrMjdQLdR9A~^A?r{=%(i(iS;{MbAk zGY|OoYWk*MIQc7m<6Cf=ht=`YFI?gl{w$uYrq8{+^eg|;AHD(is`|VOFa6@n@~(Jo z-Ej4|MZfG7E^$hHruY4Pt+ov>{fb-iFFt8LoWB}Q@{%83@tNPs!=>Nu$~8xL=}-RQ zx9r*RHBr8i8eVaTe#K|F<>NP3uK63h@(umUyS5!)6XhGJ;pLzFmH&#@Z?0JTH+b<4 z`4?Y?o1WK3`{w^Iuvd8L*=RpMUllj~!aute-U$I|(Sljr9^VdT5POD? zURS|$pPcaG6?hdsN#FO~XO-jd;v4iVUdc~ozpDVdLr!?vExha*Uh!L8yW@7#@8080 zJo5K*wm<6w0(~E|?YePvouA|ukMWN1jqRtwXMKhKUAGR>At|}#8SyIXzuPHz)xoRb z+sg~@9r|rQ8+bSGe>;DFpH;TWAKqBFg0orYHy^9ux=T)Y#be1M+v?#}aSl{(`WyHa{mQq`gV*9`$|YA$BZJ zt%h$eFTCtoe=>2Z>Op#@|NVVd*@kzYkHlsAway|wyKWVn!tq-WIȨPE*tPZV#tzm) zIwXb{Z&DWoZ}BU3&5m8S8g6paFTMe{zPoXcdsV#Rulm0C*GP(Q$W!KJHJs$7Uw$cW z!S`(7ZZ9+9A&$GxDkHr7QoM?OTkN>v6?=ExDmckWZuZPxkA0jWALE(oV)0v?bHCX~ zc-gIZbm~KLdd8#8$LzT7k`G>f%bwK*^hmF8-*vy)_rrVaL(=_wSJr#wC;r=V{`@k-aNgLFt*atE*V(AaI&gK*RHYB^b_}KJH_R z#IL7P|I)Ai1-`uR+o_N6?Y9hO@*R8q;*IjK`q#RGd6^v6o#Md@2YZE=-@+?jt?s|% z=fCm|{ITy^A7$rvPUNHq=vO{E_8};{#;f;w#xGqzDZIDDA}@RPK7;<1QC;{{@-KT% ze#JA4^_~tpH&1U(;N&~VE&uY%ecqLS&CBGl?i3GRaY|lQ?>_J2Qhlvcww-5mpKkD7w6g{A9(3E{Hp3*^^j3qhIbK|B__P|6hAJ!|FOS5wYHy% z|H?<~)q5MS2HvJ``Bd=IZ+J%4zv8q$UKz%szwGT{r1K2%D;G|_@oZT zv+(If;nx3WKlXt@{R1EU;v4LKb-ZxMOX15Ems1~A+a>roGD)MTi3bIDkHho zIqHK~!AZ~j)%mO7+sjFQc;KdQ{6n1pzkUaQK4gAezkkjw+k3pn$i2_I;uinLPiDdK zP&we0kLU@%l83yfBW^$R{O)2ljAUD$)$`Kuv@mtCrVcKR(IZC%B@xPBGf8NI z6JGg6op9>oO!<}_Kg<4cbiJSO;t6;py&AK>JvIFvqd)!&?;o0+O zacnVoZ;1=9{E~iby{Cd-;Tebi)-9IW0k8Oc44&|g?KHLvf99jD`q|?Ze_sro^>;V$ z4s}G~&Uvfg-{a+{FM~rL=aX#zMMilF@8A!!re(p9Vi($?s>!Nj`cZw|+(Jx!x0vUTquO-p~2NG4tX%vyAZS=a7?K!x{Uo zINgIs{GxC6Jqy0Q9PrYwJgc7p*J&(FTv&So~avM?|!q73J{mD=D{Ym-QeeQbBEc?mHKA#0|cyZ+&@e04pcJ-yr(=52|k^|l! z1*g1=Ph?#|-fiL*{mWx_-G8?I@RB?EbUO|Fm6v`swwrYo^W*y2aNQ*jc~b|f^Vso5 zpZGKVn;+NTb^qD+m%M#QrccLDgSYr(;#ae7`aIY1``PgA<$+hc3f}trZQ@eu1o~$0 z%l&;uc*WP~Oa9Tn+0;eW8_dsp(eHj9XWfREJ?gv0o?Ghv(rffx`ZrIr;@isw@B4im z;g|8#`aYRHrTNJ5!fn3x_n&PWUUeP0)%&TJ;HKx|SLz1#?S8Z2BoFzLUn(D^K052K z8^tr%uQtNVp4EfKQy+-%XZcwCQa`MMdyhALcD%Spucc@F%6zzfRlLVOBo9AU_nto; z`{k*IPmZ(K`AI+T4Lrr0@GE_2c~|{#8t1cv_B*-0P5yzG|L)^-^3M5_fv4lq=HWQ@ z*Y_YMhxOOf$ zA4k94emtXYIQcK|vSa?sPT6z%vQ3|oe(}#$aKlT#$37IKUlTu-m#VK*JS*pqtLFa+ zuYSb`L;fxHEAKYEN?+@+7*3jimpxm*7JoC=I`>Dx33pozH@xhb-r|?|ggQdM?yY($ zJoHU|Goh1>@X{|{96jQXg_mB%Z+`wFdY(OQ!ArmVICU-kR=t}%RO?9WUz~Qo$<$in zlzh=o^3f(Pf0q6F8}ON*y3r!P!22w?;ECNNqK76C_wKYHR zip#$nocdDxyc2)5{$KH1J>~pa`ycSCciFG^WBDsyB~FWPt7#eD_o7$vD*flOZ#+X^ zT7Sd5;2q+?tn&bG;?#BuZt*Dn4EeaFo@mFM*B1N0ORvud4*W?SSpC@e@A7!rvp6F! zg@1@oO`V^5vFW?>|Jl_|zi{IHJDyc`td4+}|E`8tKBCXWBmAlSS63T@=(1G%zmBU`h7Dx*YUl6#VdX*4<}CHm-T%H{yG<`yQSIV z#UtUh?j5|%dKq3NkKO%*xsJfgF7ZnJSbdFMpM!rd_y2O>rKe*b`q1YHZ>;yO;OEDu zoR43+&$!EcKj9T`@yX!u{$%kb-Hw|elKpH%?E%kNSz)Zf*NUi+uPCobcUtKcLjy!87#xO{IgIQy@& zAHQBL@9y!+NBYkC8?OdVJbF82J3OT6TdsnCuV4Nszvx%t8TwV3hvoWq@E(WWn!Fo( zt~`Wa$w$@^IDA#B6#RgT^u`B7q`t`mS|gdOnQvUZ1?e4|v~;+^K)9oAmTI{C%_fKW5Hf z0pq`v5nlFeq&M+LeRvx4;(Z76QhdXC$#4JiQB(ZB$BSR#(TT^Em(rK5ZT9azQ-Jy! zA;`&p=@Wlc|KeHdVEb3I>pfom$5S7ZB+pv!rFZd4zst7#EzW<_+t9&<+tj>Q_ko2Q-FDZ z5b)A3`=n=aS^lvusBTghiqrhUeIFpgqn<*p=(Ttfe6j25Us+F)cUIT$^FF2<9;3K@ z8pri}`d{RH{yeUp_b2_zFYFS|XTf8{yToUs_p|uHG1tw89A5q_AH|;Q`>*=4{I~kD zvjMtC9(c+Ba_D6{W&GI~>-#t2mpUkZ-&XnT@h0BtOV#%mqTlxEz<=|_80-7N?BD%n z#ZNx|8~^itXSmh-+g}Zw?Jvhzbs>H-Yu#)9;XMXN))VlkExg(KzIE^7AL7+MPno}# z`+DA`M|exF$d`DGKhvW=R#QLx_niON8RP%cz6ZX?OE2P=b>P@<|E~krA^y9iztyZe z%pSks4L<$nEpbUaf^+-zz{}1X9ly@=^VrWW39H$DBWF{SPlb$)3Y2 zx8UHf9lqEzeT(1qzAW7C-zNEx2j1`nJfq?-obnJqRyV4fKj^Q4Rb8ph;4hbk4X->z zzv}qJDLkX%wmJ~cz_amce#}p1!%H6TYk1!%@#vg9D=)EY?~~$Vt@L?mMc(mz`jwCH zU+bXJV-Ihp=X3IK@h!YcKj)6eU3@pZ{Fgnx>aRuf-elDa@)19dy;r`q{^Y(F2e=b} zT<;Hj^**8gjQ2s+`KNK7eB7dUeqDdp0lyT-+<*7@N8g0^IB>M+mtHFmgT`gWk-r^bJbk;*Vzr`cXgE}~4#p^@n zvF7!j`G41k$ss<6_w!HussE25_gisUKT|$?*YbYX`@?%2cZdOL_eJmiN2f4_@{d`^2AH^x8ik zxZ2+ZpT0);a+?+3etzJ^i;lsCKPUh4=azUy&n^1y;T;X1#<$qZ{<)XhhL?V$Cw)5l z-PA+!QQ}wGF~6OKSKKw9@Uq9$3-IcBHesM&CnHM-^`Gx$}=nV3rtryy_!$uXq){2%kQV`d40VAN6r-^LEU({O)<< ztjGW9`S@h|6L6i?L->^XH`}FG^W=VykK|!bBp-X;=VAKQw@Z93{`?pH^>gIsrhZJF z)!g@C(!Be#;MJF~PLEIG$KfIMe+lu$;1|E-=bDe?v1xF_OAm14ho}B}&Z~ZizP-nC z4$rJUZS-ArC3~4AZo|ue)E^D4|wT!Z@1wc z`Wjb%Gvw~p^G{=Y8hgEOD&c(=x#O>ucN34#SL3+8M!jF?x>@Y?p?G6&_@RDlPhGTy zKk8?l#VLIsanAhR_uNYzCm%kr_uu3d?2CjQh4rrF1&|6&P<%DcpM&G zbr5{|b@&KAb>H(YeH>o#+4>JY`SF+scw6wEt)s|4uf}=Htq<<;rk?HUT>4DjZSimU z$$HGR-v_4O=g|+m(O2;abuT+kUAUcc-D>ff|KbIqN;(z1E!26?tOMe0${kfj}(~Rk>7Y~D1o%M|cd87;A zl~1xh*#2bTuXL~R^ouB(uehv?RQ#WRQ9|>kX23~O)-VcH|^>68sy^Fin zPxkLSWPa*8?}M1v65x@4ftNjpKa^hJP5wPxjd?KY>nykaE1s$c#p&qT|LHy_&x&77 z9mucsC)=2pN7ml`kE36B;Y?nwb;97N{*?S2KD`<7kOREN`$c(_GvF0h$@wgDo-(Em zwvMk}>hf{wq_XeCyXopAc*QGt;iSjdarnQA`P5OZsPW3|gQuVW<-*eVc z^ws-S@Z-_Pu{|l;R^N+a&vQz?ap7 z@F!2PgQ|!5zj>TR;qa0x`t{!H7Cqum=in=Q{v`8aoydrf&w`U2@QO41m|Z3h;nU5! zLh`PDPrY|VukJtF2rr&TFL)!~s~)g^pT4C!_?&qVx7(=?q~gBkTpB+)j*;(0Ms~@5 z_36^b(g&#bRN%Tap8K8;uecn&mft4Ns0*)>f2uB|_xqkR%W-(=C;o>=!Yw}4`~23? zqW?F4C#lbZ?5pM2<5joyAvb=gFS&Vd1MiTB`MWsq)la+pUU=KUSN)i*1H;Q-)kVfy zSHR2M=kmzDS^{|4Gd=Cr>+kA7ae8)~(8G&Y>C>>=#AEBf_(s(S^op;z@2n%d zhdw0azq>fy5}%qnH@p(xZ02iLoaBNRze;{7K8Y`WHs(WJuPWuKBULKs^k9>fc&FV&CpN8(?z5`;&pU>bul?*2jA6`K*r6zsYs8!Fx*{c=_M& z4ZOu4@TXVVZ_GU0T#fzma>X(A6ZUx7Z|Xq!8s3=rWIgGu-@(qsfyYJh@Tb8` zPIZ3oukTUc^JLfXg6Ik^@UaR zD?YPh?~5h=T3=}5b@H*gp?QBLbyelH{rp~fn|{S-{r0RMd0$68%%0EmDnIe($q@dx+4v_ALGCzt%0IED9b$wTtb`SXEi(|7(L z_~6{%f3|IS#pmQB?`hDlcy+!S_^da)m4DrDHk{-kpZF~Q(sS|=`!%ZXOW*1Ralm~& zXO^+#>O-PqMtT;f6OXz+tvL19eEez>#pgAmmR7XdgKq^=!wVbVEV1TNAg$o zvE1*j=U!?*yz)uxu>5iN9&~+A65kM~USxjU=Tdm?doH}c0oCzI5r? zdK><7-}4{)IJ~WoC&T?GV_V;SOFZ7vk8NL!p9jT7JS@%n$H>XgTd>+p(GFNd6X;}(5g#XrygD>$-! z1z#Wgr~CWmZTEqfotbZa*-wHm_Iik)-ilBEdmQJljXliTkA{~$i&M$NwT>M-X21IH zTkQ34J#gQM*Rf}IQt!=rUc1o8^X0?nx9a`m(X+ml_wDFC$MxSU4=27=yxL!vcu@Aw zpWgK}z$;!nAA0h>>z4SsiNC)Y$8X}t=jibeKd<#OeXw^e|2MrqyzF_0mwu|>9^7~q zf4&jVg4?=8y}!bKzNviQ_xbSBZ}^_R^Evso#V@yi=&vQXik{EGSMz~4wsGF~E$(-| zAH4i0yg*;-oVb*qw|IUJbPd6YBdy|)fyX-P`U#+VoPT^5a z9}{mD#}c>B*ZsA?>gM`h;j^*7zBlsvtatbWUiO^lSD!;%)u&>=(YL(YuZP_1Uw=Tq zzUgaU+RpcQ#jEr+&cVrkx4#>>Y@f4TdA9ub9qQ=2+!|i?4DW{n7d^>0;&J=?aeT|z z={@t*j^lWn?E^1+4v*wt=kTX3_KPpyTn{|^{rd9N&zp@`!W&-YeXFYT6Q8ewkDgoh z_rzs=9sIKR7=2quV?USjV|d>m`l|X=eEvoBnEvGU$=E)tYxOPFdx_6y@jHEbam;*p zZ@&I6DLL9Z{&)_&>`$NR#lWX8Q}1JaH1_Lb7T*Z}>gjWA_-Eo;&C{RezWPRoY`1s( zfj2neA^+ie$Z?x-OI#AS>~G1l#W%#icP#!lzCFA@9=Pi7R)09Q^)V_A#eVr`W3R#6 zzZlom`YAq&hr})#KKG3U{*D*GD?XDW_Uyfkb8y{8zv`o_@ag{B%nyA0;ya4>yO26#+_k;U1Mtu(bi!FA0o4%ELe^VdHQ}TJ6>;tcSq<>}o_ooAQ3yyQ_SY3FC z|K6l7r2opR&vU)|Um8BV`}hp^$B{Su0lzGL@A7P8*Wn-XbMw6p&$$$Cc-bF*fnQk< zOnk2Q&hSM2bUY*Ta?1|HvFxwEU&wzR8#lZ^h#up=>IMB*c}QR9kh>+meH?a8FE58Y zcvgoac}f1kzs`x%H}T^`Ms}jlTXo4@dU#j+;XMvq)jtiN*RQI2Cp@J3m++?#B3_-Z z$Nl7O@5$q97yG^ry!0v$rEj&V^Z2Q}``dv>-JqX&F<#sr_<^?#`Rng?eK5AIAJK2+ zp~S1J|1-|Jx*j8*U3Ev@zs>O>4?ZAXsTUG&;n?8HxFsH)lZTzxlfU@8|C@YqUb)AM z5B$46^l{3FC*l#odHc6Ho_yOApR6BNUF<&X!XJ3qGyU@8=(qam!E+lPp)Y$C+;CRE zCUr-x16~+z_4VKDLlSX|e$!9JtK^mHOGmHxbH5(dYo6dqDOv=XH*@@ZZ3!L%TM0p z-T80T`{5Pp!4`d9Wu5dk>)+<3zK{3ir(J#v-e-NtBJaiy^>yUmjXx&;uv_u0siW{P zd|92Pp5`~6OOAIvBc5{%-apKkxC&nnU%tH_#}B_5qxCX8x%gwxecEIncw6KXxAfcp zB>R6hMs>lKytKuxd+fU7o$3kk>i2S=cHs}a;?=JH)t4xKtiDg2YS#nDmN-rCO<$It zJ?Fx3-^#!IDfaArmHz92OFlYBzvt-nCV25jeOdgw-XFYlyf*LTI1XIZm;JM`Z5`Np z;1zuFO=BzWof7fj!Kwa#$+j{_f`sgAOq+}!^i!@2kN@Umw(laIEn+w#|&>w!!DIcK}Y zj`cOl4^HF!`oAik*Dmz&{H&j_SMO@RAd{jRN&xjpV-TMc@o%y_Yf0F+k zA{QQ=x>bHsKlJo-ZoU}jUtNz;f1?L?kKb0jewq7U%D(AW+!UYHH}Xw*viK|h;8WtZ zINo}2na4KC2VU_xcDJ2|yw(-?qwkC1A?MG=c~uw1j@4E2@fJH^7fl@@Zamg>?D0mw z<;OoAcv|`#;x4_ai(B~DP3&L`|GK%#^;wT9zW!MF_RoP=9>NPgik!(q^mr9LHM}zG z4eCO1uD%z`PxjBf)Hb~0hk8)HjovzY%!p6xYaF82tLw}Yd*vsW!nc1eyyW6f!Cn13 z{g}jE`N{kJ^`30vvA$P*KYkWH!~5gtCHdl@d5caa*Io6`n?`F&cDr=d6B2y>TmFucHz%nzwmxIaO~^+#(&{c_v%}wZc-oO zm(%?HAb9EbcL&b;|5m}RPAL8qyyxI=v2*s_)JyS;_KVzC{J)f%;XOtkcAR6rKUytj1{2cGxPPy-F_MH4{9YsH~>^XXphv8L-0_{#*IjJj(Otxjpj7b2I;? z5BTDr-a|V7!_b#}TlG@x7cYCmHy#_ocd4V7~ZAcI|uKXou`gCXFkL`|KG0s8-IOl*zlTn`Ej>S zMs7IO35EB1%+EpHlsW@1t3KzYaGFfe|@ytM>)CI`O3 zp8LREyg7D#bDjOM>)Osd==(H0ML*{>u4^wcdR}|v54_^DxRv^-#g4DO7;^T+pDlSu zUM-ybH+ksH|MR|D^#MHhk>S>Q&hHF7)gLEcc;Xg)o_{mWt8Mn1^YD)PdnN4ov2oq? zJo8MiS?|TGs($l*D*9r-!GCi#=HU=KP&d_k!7s=0`o0f)x=XHiwI5!*nO^zduZEmw z`n?|8n=x_vtX@z@wn;zmwt=Jm?ppXH9C$bzPX{Jr2gX1tU>_tOb4 zdnRY<0DUTU*{_HEzQ^u+3*vG4?~jAiJno-+scm@41^2&+yvZZ=o?ZM_eYlBJUySqB zLtE-Y^?$wZB7S?$W8;QbK70|m!;koF%llUCI>&>r$G+A1-p8@NIL&*6<`rIiLmuwI zm3rY2eX-v|^6nM?&3XC+)2#QxX@oca=6iD+{o%_Q=~sNxx2rfTz8}YYdCW8;yz)`< ft@q5Tf0aJY&Go?1jj{8Ce3b1Tem2c}-mU$AQK7Sm literal 23344 zcmeI43ABx6`~S~8>~r=$d!F|``wm1aY2gyAvsC?OG*lw=Ut}# zzh2j}MS})ObfvT}M{`?J#Wej>mOSzI@&Bs`G-_~jb2Z^*X4W&!aeW2z!~dg0a#A|4 zU;Uq2p?W1JC+iiTVfvM0DxFtnT#4c&y;hM_H7BX+)l_|9Iz6k-r=+BC16iiM)MRsc zQbp6E9ORWEkN>;JJDWDEuVOO945Qx-|9(7e%;{z2|NV73s!2&h(*ON+HO=X967YX< zxx7y#Ox*v)W&gFO|9M@N;jtv^WsxM)>uN^$*T?_&>#U*)&3gBrCodWO^Rxd`kN$h{ zI33n={NELi|EaihKO>rhkLaY2iGKR%9HEa{Q}i)yE;hG*^uyMV+R;WGKFmaH=gste zrC1-+F{pXw;O3cjob`1)G<49lpvy?FEn1cM2vfJx|{ki|08` z%ypb_;xqnALm$2&9n=VYCqtjlGX1B6n|bF-@r~S$4LpokF1VSwe-!I+rlV>V^_2?0 zYUWHjc-XDez{4DzWX55`>{;q78`53}?l==i%B`hux4ADD(@NY*-!?P8E5$Moxt@np zI|*{s_otXRI6=YT_{jBgUiY7D;+726>ydI9W?pIFFip5x{O7o2Tk)&M32=d@G3!F{ zmntn34~d_O?p#NT6;~bS%f;RKD+BueY&7BtCPQVX_JUM!+P-p_$2s6|R>`sQpzlkz z9_w*Cz+sw}2HmgCYG0rKqgduG`RC#8%(n8cpO-k>t$y|TN{3oC6P6~K=ToixT+bb( zn!Kf0M|ob>fsTJ3cv<)|A^DJXs;|$n#v^gpdC0TYnXD%{|H#|{59X}1!P#SYsqqE5s7(Jq|FsS3{|!qsP_5LC z)Mu7coat(65nT&!YF=w~I>vUKH2xgy2ni zN-i^B2Y6a}xsdqw=80!o?dx_@!Oi~QGWp8_uMS#oygbHaTI)#KQLCcTR0pQ3bj{2{ z9a=?WI!avpNaH+ut@C>PPVh9EyR7vzjTfejCl}nzq-@mY#HE@1=a}(jgO@$!b&*=$ zlm{J;Z1_sgKYDjVCq|su+b;5IHXfLHyu$f6oVf1c8Lr1b^V(nW^LtJgpyU^oU&>qH z#sp7`v)327(RudjLrah3LS0?6z>d?c``2syf*oHTNFVMioeO%AlejewyZ?+qav3edazV7Cg1)?as43XdiiXWzHXNG;Q?B@`>N)V6k1b>_YF2 zRUi7GqYF(21}?XH-U%N5xscUg%>p&j0QmN@4vd*z=hJa@otRtux7}lVI?VMh>nP)= z$&8*}NBXr{?QiJ#VfJ+oXF$!eC9 z(}7XzROFmk&jHLqC5me6{x%Hb1UN8&1D1)AoCkXSQdZ6-+rgLB^P4>6fzwkn1e*Mm zY4>G=(=^zLIrJ#BJrl>&ZM(9OrNUm(hZ}g{c~%_tWkHnVz&g!5y;!EE|EUuvInW*} z&N_cia2itG*fOpzh0=kwl%>^&@}O49;FBT5IUq44c%eAKXi9{!PEc$pB5pW%f#zYSS*L1s%&qM(@pgfdO;ZYDiCJ&`_jmrr_L?1SYs@Tsac}^? zr(9jw{{|-r*PYyWCwTkud!BS*r{mIHHGhg?gZILsNRtp2^}pft(r_Nu^sY4f zv(;{d)n(gr5#nPIEhd+IA@QphbP+Wf#*#>rsb8#eVfxl?RqFo`#L*6iI#xRsg8J)b zT8S9iSHFc$dCYk)*7=&=c(R=jjlX*<^wJ==`8z0#=O5hr?uMQLtnYOo=kgnFEK|)d z^kM9mYJfgeY*6>dj5`xp(MSE{fSSdGN5jbYqt&+^D4%*hAskt;ajmau1mCOXE978F zKNScMRIi6ucrc>uKfcdgU;|I1jT>jvUjNA5ENbQzG~@P}>jUtquuP@i&zbyH%hYfG`9YZs4g9b@)v17r2(ZfcR z%|oqv#dxMDir#9vn_X5uT(1n=mwSiX%qxITc%E+9@2LIk=S~-e0l_j()29yQ0wThSB_3)|I4IZcNSeCtV%j2s>^d6&F|t$a%yK6W>wnfkEUtg}3|T$knH zJ6e@p5BjXU=--E4RCum{mX;4YyNoa0=%zT@sBU(7afb8kglg?fnh(7k^QQk}TL5#5 zM=bo-9mZ#cbw{=w5XR87E6FWm0etrPgYAM1BB(d)uFa1uj-k`~;jN-Sx$x9)%c@o$ zA4IP%Jytz_#gDnqoaxZ}y#P+-oL@TOyH%Srt2p)DWu=;w-^4fvO@I` z64=#0yIBC4mlo5l0njAof43@uhTGLhA_$)D==;YbUVK!tPWc*Ng)pvJ;+f~4^?|#c zmXGf5?+KsEiDJ)(rH-#26~Umls*JnXCV+LjHg6l089-<6oRhgPg~6xq3}VRAY6k+R z1E{z2qoJvHM(|SI-I1B}`;oh8lR%j%jkkVU7zYj3)2L(s6y(EeM|iAu^yiNPaG383 z;5NFt?#M!1YSXts)4Y`hBy% zPtMEVcMagCIPPrx zaM~3YK6@zrwJ9(9OdLIU0cC65@MI7-RIl`n?|DB)zjmzq>heL<-WRI>*rEX1azeuh zaG?E|Szq<&$Nl!-(=WGRo9wJ_6^7j~YLJLq1y6X^AJC-)5i;<=(FMS5`T@77}4t6 zZFLtF;g&n)^=Jn11Z@dY99pI2EkgZR^Pdij!ZD@1b}M z>i$qp!`s8?Uby4CEe(TMzp#Ig{N4FDZ+m`!r5sv-q zBe%hYtaJ2!bhJc?k`E{FR*yk>GmgX%8vnxeefZ|=@3vg(}>mT3RD1m~Vlb@;C(T`Cr zzDw+!974bQ`}U5Ejid3ot`9GF227j^&@+E`jZS6bXg%>~U(L4zcz$e?pV!mhm$t@p z9&cV8N39N{UP}xwflr^`_w}edA{e|f>&4xN!?^8Ck53w%i{keB7u)X}7ebE*-|e*X zs2}aWs^~pdltA<1yN*0c@5B4X&)GYEP7o*i`kt!yS^;KNS>3K;uQ*Nx4h?VhZ4|FP zm^-`jee^nQdtmg1d+2?nT>rI;LPfZ|v{!Wh6ZE)jY+n^;47oq|{_uQ<7`hMXSZ?$0 zh2Uuv`!KP=%a1Jc7Gd6X11W=LaHPzjRqaPduw=s>-w#?@h}v1db}6~F2zRMv(KmtQ zg#+GCYv#kj^1*5=m&f3oab)|nsR;xpoOOMlpTPVQYQYuZKD8W9Me)_xd1dlPCh+Ye z=}mtM7UJnTOMCZQ7etMB-hJDCO95Kmm~s28Dy1=CO`EE#GO6DWuB2RE8pqh%Z+Z2h zP7y5S$6l|iL(#vtNeaGMqODlgu6`G@Dn7>n! zt)p-Z&6QFtPW8FrVA7u)g|`TI5{{+$SQ17XZX^B5^HBz5=@yTX>x5ruu9IqU4dEb~ zr)3xplwolw;V8n1G(WjoEaR5`Bu;YOlMGN&ta!=1<$lIgCxpwT7`~Ve&4-dLZYaD= z#xERe83#1e;(OAr%t!M#;gsoy?_4gHcxdjFV&Zg-AIbXAT> zP43rmxl%0Sk$A{;(w@XkIHrtCxY=LxFZ0*j^;(=H?!x~hKhlnHG3j4E*K2-|2F6U! zfnFBmKFx=6nSLqWCG!wI^VfI_Ka>7= zIPJ0wuS&&Q!xJ?hOojBv*zKgl@TOFBXYP|>M z`pED{nUCg=>5#li{^ywdN!&C)%mw2?%9HRz%`IIPUzB_Z50!PI=xLY2bn7}9x8_w@ zh9jn!`K5xFL+ez-2lFgWC>%|Ar>q;{kD8yQ7|xb!`XioX;v!tIE+@*4P72S=xWf10>n8q$H_6=$7LNE zmyDy&mqfefA9Z1s>b8-~;tQJZxY2{bgTvxeirR#>=NZ0{YxS==iXHoi!mZ44SR9UV z+eN40OkQg|iaO0a?!eAB->u$cU>-3T1#avZ!VTr(A_Kh)Jj!Qspy=IGYwQ*W(;SU> zfZ8!G`x*;HnrSN zWI@)UtTW-B!v7enw$27)zFjW#G2FESgH$)3Ry40=p2bu3^A0OcG7jN*jH`Tkkn4nZ zD%x{&xf`9TDX>DHBNZ+=7l5KzrbjV` zFdD-B3XAyzsKuOx))`Tf7L$FLWB66eqsxgD zRQb6rp&~b4%AdQ%b7|6J>kf_v@p+Tt8SDlpy##|kJxW|k~_=@HzF67@<=jIb{ z29d)P@I#GuUcMKrh+0j0#D!$O!37S}Y%kv0!%X~2b3Njf%nQ9} zs_Z_#9HeiiY zIG~=d7ildOfeS(U*Id$N_*?+oJn8Iwl73K1VW9^?P&DlD+5`yh5HJd$6H%i!;Sh$sF=^fp zjyQs|PZ6T))Wf+Q%tt*?rqKUt^-T0Uf-CZvdL5YCz()kFE6Fr&u zQUr`c#)L2+TM>=`2xbw-is83*59HqdP!#9d2cDbxa{_4#YF9YiGluhbhkky0Yy@vH z*a~ChRW;)<>M{o-&iKs%{v&70$X8!ol@BqxG%} zz}B>&xZJlPO!+nA)#J`EK2oO_htXEyyvHS8QH#r*Qr$clHry}-zO8W#1YwByL~)rX z95K&4#;i`Z|a3?wC6Wv8m6)Pu(`8Z5RzH%CqXnF?;6EG^7Z=$X7rwg89>a zd23v=Aa=wRDN2AKCUdb{m|GJ6BFeXSQxsm6rdd%?&?&DWTv&35&`=zVKVOJr(UBf` zw-x1M&Wz_MQep5ktA|m-@F;?R1UU1t&+s$GOZSGMDB|8tL2PBf8Nf+iKru+(WnE~V zm5*BuPuo;l5ve$;^FoT4eELy|qL)D&gW%@dm8!-JM~h&BnFj@Z!Q@}VxSaCG8%KIX zz+u_pG4b`9co0|b?>YX^+l83+^pxpGA1**z^Jl&-IiwH-Gl+yF(0%L4J|8S7z$t<_ zU*4DiAC^T>VdJH?mDWZK*C;||&(ylDtH%uw%EyZ%T2B7)!#JAFsF8EVQwaazFKf5o zAI0j7-*Zl{OW@?Dru1Eiv`g*Ayu6M0UhTK;OO!1@oIy_!YIfW`an`sJAQ-cC#^EBA z`SiIl=d%k9Un|1La}_Ab$B&VUzFOHaD4O)v`!Td2T9Wl*94&5I5_qy<0Vbae5n@YV zWAo{gaWw&d&9}R3n_h%rZN4GGRDhY^>^f5Fvj{j0?-gO(+?}06t45I2ueNN zVb7sqF&x}8;mn$pe3T?Q)?rTqjFs*x#A8d>zaD!$j-l;u@J~8bfT$YItuYL{y9yz= z2o6;0vE})FF?@bY^Apk0aqL%EWO^K*o$?bhDZrP<3LkCzL_S8p`q`|n%SSQeDK+4H z)XtnYY|*9y6Ndy^{P6J$BNx#4Cn<24z|iGRLVgKsQfXP1k3AHvbHs`IJfLQpKrh3? zNMLyO&~=5_)Qo;r{u)Ow4sanF5p{f}s0h`&lq!5|Ndk&iwwP9gdUqbDp(Su{=?CdM zZsJsA-REQgR$%g2i1OTU5q9!CiqK7^;qC-%=kloQe8ab5n4mBs@%Ez+-}CsT^g;|E zDp`Zp7h}`j#6f?x&z$gl!tlvLC>pi8T_GN{E5cTQeO0>-&HODNTZwwkA6f!u*Q5|~ zD}nPX9M4vNH-J0TvbB}KloS1lU=jah?nQZ`XxGjx!paWU6S^uwOEtZTanxSEI{oER z1sIn4YGLVu7*4NKptKZH?wm@mgap#(tBe-mzvq)%R!x8A``_u4>ofR)@(*?!FsNsj zZUfagyAA2rt;?X!gL?MuQ~tgIo%{7D-?it!L7n?_=~lkge>mUzKb*hwKb)_p&TDt@ zHQ&2>PJR9N^4G7C9>M?4{OPg%{r}$)_&WlBN8s-W{Hq9vuUP9r7m7s(5xqzJ)1vzb z=hr$>mhtVR{KdbW4$%)T7+>vQbrR7f#Q!UPWbyfm9wFCBztW!Q4BDrihHu$deNA5x z{YC31SIoRFSUQQ!OWGBkNb5hBi~p?4WE#JClBKhWP9$-Vafx4C<}dBZIHh0FYh<4C zSadV(M^Cr(MA7yBI!=?vQ20I=%zGl%m#MjF*0O>ZO$B6FbWg#aQ zY+o*)Yv~Q5kBRQ1T-@!>+aWrR_U~p}`k1sckWXY=Yi62|X$&T49&}19^#AE44Iu1^&AEmBM8t=6H$Xe$~wfx=M z2cB)ln`G&M;&+!gicY3=rBusbE;^WgePmhV5M5916aCC>;;(fphowVmohQrE#YFcK zA3fXD$tSP<-MP4*Cz=WASK_37`DsQcb69znxQkC;`7BCfM8A}F zbX;?Bgbn!FmVa9O+M<6-{A3+|Z}d=E7qY%&AAsaX$IoT??Ax&L;I#a);*-_>S@M~( zU)5vj5TZ}9%&<4d(l@l<*9GOeZXOfAv>j}RCLf~K1u~2dBzi*@K2tX2dSRrHyS93h z981qRs_eky9G1UZbQ|r%&9MB*qC06nxYOt!qJMZT{X&n=4lPvWTE1Y>z4Y^>KNvr{ z9=G_8ZD9Fsx)Y*@iC)x;4cXG}wdczx!W4y{)?A$pSbucw=MIkAY1_})J=KI%c7aGMo( zt$XE~`R3vo7T(+@&n~d6SvAv)JJZss_+!}xbaudySO)VMwsT_BS%S!?r*pEd}Vk;r$beaN)`NXcU_XG04j zE~CS_EFEX|Lu%q4qo>jP2^-S`(0Yg)yV$qu0GX)Cne4@7W%nhYtJZB2(7K8POV#w- zdcnhL;5Pnrr=^#O-a@8yQsBIp_Qk3XycftH%z9w1HUGDaKbvjEeO<;k?t#va8*~#H zz+G^%aoT73mY+3o(0Yx_YESEvHjEms9MiNU$j5F_{X7MCBq z48Qh5`=_t@wN(@+mb#|rY5miM&3xk8Iuc!~61nd)?(`bJx8L~JNyp*w1T0@Unef@? zuU!34JmxX_tp`nb!PEOc`&!92%zjo6*j}6Lwe*K?l^pT37h4{_o1}s`luP@C838O+ zvPI>v*`HW|Eo_hu;fujF3ZmiZhY-m#$B)Fw^l0Cr4-Vim3@}rV^7GFNg0cMi;YrOv3h@&CGwzCxV)(boNJ7kpqF_sIa1tGaKeF!EUF3K$*F z1D1V?J!r|sW!fL2?A4?PYrV(^wjrPQf@LvV7|M-YZ=L<0JM#sd1IQ2|>A{lUs&Rh4n3p zzwwz*W1%OE10N^_D25|zN01^HHhypVyFl5&>2)dbQf~Zw#6W{4iP4AVoX8;hk=uLT z^Z-coBc+pGH%eaI?8WN6DspjjSu^tWTBH5wYL0#Q`iSLgFZw=@rWD11*sk*8V4hXu-(Pw(@hKQ4LlcCwNOK%y#H=e>~B1OG!VJ`ty6I5OT@=dVh%GdG|Pyqykv<;q4^((Ef$Y-`=(TBLqA9aebKf z{U>L;7bLLdAIfMQ#*V2srQY#F6iNlTw{#)cmfbmlv&t^qHH6MzPWd6WH{a5&8nO^U ze*bPor9QtUfwro<$r0FYz4e7X)uPyTV)JkByc5GWtRn?1-Kx~qXRCD~-+WbNCmxWG zpOjqnTNJhLsX$XAU-IlHNRf)-V{(`G-W;{YseQSkyCo3c`%T&Cm^j$>-6Uc8cE6Z$ z__4)7$^*Hz(=QZ2sX+H`4}xviVLy~ww)=1)l-hP~WgM56txdjjY6Pv=FkNK%r5m4p zpCU~<=eFXcR<+`IAfyyA+Ly<|T^PLv-1q6}wX~0f+{3q>38G;WHE2$8wE_#kX>CgTBc8bJxv$2Mp9xo!S{@7H4`s6+M85J}-wu7Vhu8SC z{dix6^PM2xU)J;EbB?IBA6xc?Yo3t#PdrGTUt;{c!dw2#7qTtCv-oSp|EhVym16N1 z3;z)RtN4Wf${mDP2yYRtAnnNKMDfcCACi6T;>VW$gj)#55ndwq$$9bnif>qWo}8Ed zgolW)S2&h%G3iIfA-qKHm-F&i;-opuH9q)f?qjq3(0cw!*8YBZEb)j>WxE+@~+e1*RWuadeHdSCz5V&Qng)1+VVX$xnP_)C7JJ-J`TFY8Cw zNyxT%s_-beUgzzi#b+gNGEe>ZqN$s4rC8=Mg~7trV$C^h*8XYjL(Q`|l<V(k6Rz#&7QP_9ShjHw$T0i8U4~DkoBj9>i{A)mk$z;qzxZc0 z&${MU*5}jBzWQv7TWKDWX8Ei2{L(F+BYaNyp6qAW{@)zqyH5JczWWTr&(f^@>blNB zhKXC6RUbj~yfkQTmu~sCC62;vqz=Fpm#(XjZtc^TdI>T=S?9VgM26+N*AsSF z{7$Zy{OWa;Z0ZJNS$s=;;lk;J!-mPW0yJ$vJXIf`|?=oJ_ujYTq4i% zGe2SWcS{`r#vQxGU+uDZj$EgG#k5bFjk6Bu$F$#-`H2&Eu>sg+_zLZ>CAak_%bnK# zdA1o}7C&&V@!>jAiZ_B^+kc+RH|But&~H<{1UAyz4ByDMxR&g_*+*W-B;X(Zv#1OYOr@agH#{|s!JXUGUC4#RN#b3N>j${3x)!``fc*Q6 z^#*&beFB=3WkT|&_X)U7J&Rm3uQc#-oan@Oo?r%e`Fm{G#2?^=(}?fcW9`FM6sR=y zTUu>%uk68k^Ld}k4Lt6`Dc*+e!9m)kzuQi)3&R2Q`-K;bquSGW*tbmk1bDx`$MU(3 zrd{GSX1WcJavRR$w>Z*$ywTo?jYJp9(Y{;du5I|V3mw$9@VA}Dzw1N>gEP0`OnJul z90c2#sm=h~bJw|{$3^>gjj#L!`?g)6A_}qJ7JIFI<~>x|f!#jCQ>gxk!aS|**rxE( zA`j&JU2IVHq7j2DH*|YG)4tF6vxCs}1AK_8G72Bi=S%jpOML<2K+O5v*8Y6$cP8I8 z*LR@(PdLO8I&+W$Hv|AGgb@kD&EKA2>WQH@LfE@~0A&{N()r zR4as_d+J0Vvn;esezk2qKz`bZ z3MA1!2BJwH4Go~gG*$6{e9J^hZrT$>jg`~mI~I5EIgck#vo z+{WjFaB#hWFx0O0W z^i&3$*!9%Sikqu0CwT33jhEB