File size: 29,991 Bytes
0b4a16b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 73
},
"id": "FaSiqVnTItLq",
"outputId": "1ef8a78c-7421-41eb-8cf4-db8426edeed9"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <input type=\"file\" id=\"files-a9b68a68-38ec-4a0a-8037-171b8cfec796\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-a9b68a68-38ec-4a0a-8037-171b8cfec796\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script>// Copyright 2017 Google LLC\n",
"//\n",
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"// you may not use this file except in compliance with the License.\n",
"// You may obtain a copy of the License at\n",
"//\n",
"// http://www.apache.org/licenses/LICENSE-2.0\n",
"//\n",
"// Unless required by applicable law or agreed to in writing, software\n",
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"// See the License for the specific language governing permissions and\n",
"// limitations under the License.\n",
"\n",
"/**\n",
" * @fileoverview Helpers for google.colab Python module.\n",
" */\n",
"(function(scope) {\n",
"function span(text, styleAttributes = {}) {\n",
" const element = document.createElement('span');\n",
" element.textContent = text;\n",
" for (const key of Object.keys(styleAttributes)) {\n",
" element.style[key] = styleAttributes[key];\n",
" }\n",
" return element;\n",
"}\n",
"\n",
"// Max number of bytes which will be uploaded at a time.\n",
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
"\n",
"function _uploadFiles(inputId, outputId) {\n",
" const steps = uploadFilesStep(inputId, outputId);\n",
" const outputElement = document.getElementById(outputId);\n",
" // Cache steps on the outputElement to make it available for the next call\n",
" // to uploadFilesContinue from Python.\n",
" outputElement.steps = steps;\n",
"\n",
" return _uploadFilesContinue(outputId);\n",
"}\n",
"\n",
"// This is roughly an async generator (not supported in the browser yet),\n",
"// where there are multiple asynchronous steps and the Python side is going\n",
"// to poll for completion of each step.\n",
"// This uses a Promise to block the python side on completion of each step,\n",
"// then passes the result of the previous step as the input to the next step.\n",
"function _uploadFilesContinue(outputId) {\n",
" const outputElement = document.getElementById(outputId);\n",
" const steps = outputElement.steps;\n",
"\n",
" const next = steps.next(outputElement.lastPromiseValue);\n",
" return Promise.resolve(next.value.promise).then((value) => {\n",
" // Cache the last promise value to make it available to the next\n",
" // step of the generator.\n",
" outputElement.lastPromiseValue = value;\n",
" return next.value.response;\n",
" });\n",
"}\n",
"\n",
"/**\n",
" * Generator function which is called between each async step of the upload\n",
" * process.\n",
" * @param {string} inputId Element ID of the input file picker element.\n",
" * @param {string} outputId Element ID of the output display.\n",
" * @return {!Iterable<!Object>} Iterable of next steps.\n",
" */\n",
"function* uploadFilesStep(inputId, outputId) {\n",
" const inputElement = document.getElementById(inputId);\n",
" inputElement.disabled = false;\n",
"\n",
" const outputElement = document.getElementById(outputId);\n",
" outputElement.innerHTML = '';\n",
"\n",
" const pickedPromise = new Promise((resolve) => {\n",
" inputElement.addEventListener('change', (e) => {\n",
" resolve(e.target.files);\n",
" });\n",
" });\n",
"\n",
" const cancel = document.createElement('button');\n",
" inputElement.parentElement.appendChild(cancel);\n",
" cancel.textContent = 'Cancel upload';\n",
" const cancelPromise = new Promise((resolve) => {\n",
" cancel.onclick = () => {\n",
" resolve(null);\n",
" };\n",
" });\n",
"\n",
" // Wait for the user to pick the files.\n",
" const files = yield {\n",
" promise: Promise.race([pickedPromise, cancelPromise]),\n",
" response: {\n",
" action: 'starting',\n",
" }\n",
" };\n",
"\n",
" cancel.remove();\n",
"\n",
" // Disable the input element since further picks are not allowed.\n",
" inputElement.disabled = true;\n",
"\n",
" if (!files) {\n",
" return {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
" }\n",
"\n",
" for (const file of files) {\n",
" const li = document.createElement('li');\n",
" li.append(span(file.name, {fontWeight: 'bold'}));\n",
" li.append(span(\n",
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
" `last modified: ${\n",
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
" 'n/a'} - `));\n",
" const percent = span('0% done');\n",
" li.appendChild(percent);\n",
"\n",
" outputElement.appendChild(li);\n",
"\n",
" const fileDataPromise = new Promise((resolve) => {\n",
" const reader = new FileReader();\n",
" reader.onload = (e) => {\n",
" resolve(e.target.result);\n",
" };\n",
" reader.readAsArrayBuffer(file);\n",
" });\n",
" // Wait for the data to be ready.\n",
" let fileData = yield {\n",
" promise: fileDataPromise,\n",
" response: {\n",
" action: 'continue',\n",
" }\n",
" };\n",
"\n",
" // Use a chunked sending to avoid message size limits. See b/62115660.\n",
" let position = 0;\n",
" do {\n",
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
" const chunk = new Uint8Array(fileData, position, length);\n",
" position += length;\n",
"\n",
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
" yield {\n",
" response: {\n",
" action: 'append',\n",
" file: file.name,\n",
" data: base64,\n",
" },\n",
" };\n",
"\n",
" let percentDone = fileData.byteLength === 0 ?\n",
" 100 :\n",
" Math.round((position / fileData.byteLength) * 100);\n",
" percent.textContent = `${percentDone}% done`;\n",
"\n",
" } while (position < fileData.byteLength);\n",
" }\n",
"\n",
" // All done.\n",
" yield {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
"}\n",
"\n",
"scope.google = scope.google || {};\n",
"scope.google.colab = scope.google.colab || {};\n",
"scope.google.colab._files = {\n",
" _uploadFiles,\n",
" _uploadFilesContinue,\n",
"};\n",
"})(self);\n",
"</script> "
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saving words.txt to words (1).txt\n"
]
}
],
"source": [
"# Cell 1\n",
"from google.colab import files\n",
"uploaded = files.upload() # select words.txt from your PC\n"
]
},
{
"cell_type": "code",
"source": [
"\"\"\"\n",
"=============================================================================\n",
" FULL PERMUTATION MISSPELLINGS GENERATOR (Google Colab Edition)\n",
"=============================================================================\n",
"\n",
"Purpose:\n",
" Generate ALL possible letter permutations of each word from words.txt\n",
" and write them as misspelling=correction pairs.\n",
"\n",
"⚠️ WARNING — READ BEFORE RUNNING ⚠️\n",
" This is computationally EXTREME. A single 10-letter word has 3,628,800\n",
" permutations. A 12-letter word has 479,001,600. For 466k words, the full\n",
" output could be PETABYTES. You WILL need to limit word length.\n",
"\n",
"=============================================================================\n",
" HOW TO USE ON GOOGLE COLAB\n",
"=============================================================================\n",
"\n",
"1. Open Google Colab → https://colab.research.google.com\n",
"2. Create a new notebook (Python 3)\n",
"\n",
"3. Upload your words.txt:\n",
" ─────────────────────────────────────\n",
" # CELL 1: Upload words.txt\n",
" from google.colab import files\n",
" uploaded = files.upload() # click \"Choose Files\" → select words.txt\n",
" ─────────────────────────────────────\n",
"\n",
"4. Copy-paste this ENTIRE script into a new cell and run it.\n",
"\n",
"5. Download the result:\n",
" ─────────────────────────────────────\n",
" # CELL 3: Download the output\n",
" files.download('misspellings_permutations.txt')\n",
" ─────────────────────────────────────\n",
"\n",
"=============================================================================\n",
" OR: Use Google Drive for large files\n",
"=============================================================================\n",
"\n",
" # Mount Google Drive (you get 15 GB free)\n",
" from google.colab import drive\n",
" drive.mount('/content/drive')\n",
"\n",
" # Then set OUTPUT_PATH below to:\n",
" OUTPUT_PATH = '/content/drive/MyDrive/misspellings_permutations.txt'\n",
"\n",
"=============================================================================\n",
" CONFIGURATION — Adjust these before running!\n",
"=============================================================================\n",
"\"\"\"\n",
"\n",
"import os\n",
"import sys\n",
"import time\n",
"import math\n",
"from itertools import permutations\n",
"\n",
"# ── CONFIGURATION ───────────────────────────────────────────────────────────\n",
"\n",
"WORDS_PATH = 'words.txt' # path to your words.txt\n",
"OUTPUT_PATH = 'misspellings_permutations.txt' # output file path\n",
"\n",
"MIN_WORD_LEN = 3 # skip words shorter than this\n",
"MAX_WORD_LEN = 7 # ⚠️ CRITICAL: max word length to permute\n",
" # 7 → max 5,040 perms/word (manageable)\n",
" # 8 → max 40,320 perms/word (large)\n",
" # 9 → max 362,880 perms/word (very large)\n",
" # 10 → max 3,628,800 perms/word (EXTREME)\n",
" # Increase at your own risk!\n",
"\n",
"ONLY_ALPHA = True # only process pure-alphabetical words\n",
"BATCH_LOG = 5000 # print progress every N words\n",
"\n",
"# ── ESTIMATION TABLE ────────────────────────────────────────────────────────\n",
"# Here's roughly how big the output gets at each MAX_WORD_LEN setting,\n",
"# assuming ~200k qualifying words at each length bracket:\n",
"#\n",
"# MAX_WORD_LEN │ Perms per word (worst) │ Rough output size\n",
"# ─────────────┼────────────────────────┼──────────────────\n",
"# 5 │ 120 │ ~200 MB\n",
"# 6 │ 720 │ ~1-2 GB\n",
"# 7 │ 5,040 │ ~5-15 GB\n",
"# 8 │ 40,320 │ ~50-150 GB\n",
"# 9 │ 362,880 │ ~500 GB - 1 TB\n",
"# 10 │ 3,628,800 │ ~5-50 TB ← won't fit anywhere\n",
"#\n",
"# Google Colab free tier gives you:\n",
"# • ~78 GB disk on the VM (temporary, lost on disconnect)\n",
"# • 15 GB Google Drive (persistent)\n",
"# • Colab Pro: 225 GB disk, longer runtimes\n",
"#\n",
"# RECOMMENDATION: Start with MAX_WORD_LEN = 6 or 7, see the size,\n",
"# then increase if you have space.\n",
"# ────────────────────────────────────────────────────────────────────────────\n",
"\n",
"\n",
"def estimate_output(words):\n",
" \"\"\"Estimate total permutations and file size before generating.\"\"\"\n",
" total_perms = 0\n",
" for w in words:\n",
" n = len(w)\n",
" # Account for duplicate letters: n! / (c1! * c2! * ...)\n",
" freq = {}\n",
" for ch in w.lower():\n",
" freq[ch] = freq.get(ch, 0) + 1\n",
" unique_perms = math.factorial(n)\n",
" for count in freq.values():\n",
" unique_perms //= math.factorial(count)\n",
" total_perms += unique_perms - 1 # subtract the original word\n",
"\n",
" # Estimate ~15 bytes per line (avg) → \"typo=word\\n\"\n",
" avg_bytes_per_line = 15\n",
" est_bytes = total_perms * avg_bytes_per_line\n",
" est_gb = est_bytes / (1024 ** 3)\n",
"\n",
" return total_perms, est_gb\n",
"\n",
"\n",
"def generate_unique_permutations(word):\n",
" \"\"\"\n",
" Generate all unique permutations of a word's letters,\n",
" excluding the original word itself.\n",
"\n",
" Uses set() to deduplicate (handles repeated letters efficiently).\n",
" \"\"\"\n",
" lower = word.lower()\n",
" perms = set(''.join(p) for p in permutations(lower))\n",
" perms.discard(lower) # remove the correctly-spelled word\n",
" return perms\n",
"\n",
"\n",
"def is_pure_alpha(word):\n",
" return word.isalpha()\n",
"\n",
"\n",
"def main():\n",
" if not os.path.exists(WORDS_PATH):\n",
" print(f\"ERROR: '{WORDS_PATH}' not found!\")\n",
" print(\"Make sure you uploaded words.txt or set WORDS_PATH correctly.\")\n",
" sys.exit(1)\n",
"\n",
" # ── Read words ──────────────────────────────────────────────\n",
" print(f\"Reading words from: {WORDS_PATH}\")\n",
" with open(WORDS_PATH, 'r', encoding='utf-8', errors='replace') as f:\n",
" raw_words = [line.strip() for line in f if line.strip()]\n",
"\n",
" print(f\"Total raw entries: {len(raw_words):,}\")\n",
"\n",
" # Filter\n",
" words = []\n",
" for w in raw_words:\n",
" if ONLY_ALPHA and not is_pure_alpha(w):\n",
" continue\n",
" if len(w) < MIN_WORD_LEN or len(w) > MAX_WORD_LEN:\n",
" continue\n",
" words.append(w)\n",
"\n",
" print(f\"Filtered to {len(words):,} words (alpha-only, len {MIN_WORD_LEN}-{MAX_WORD_LEN})\")\n",
"\n",
" if len(words) == 0:\n",
" print(\"No words matched the filter. Adjust MIN/MAX_WORD_LEN.\")\n",
" sys.exit(1)\n",
"\n",
" # ── Estimate ────────────────────────────────────────────────\n",
" print(\"\\nEstimating output size (this may take a moment)...\")\n",
" total_perms, est_gb = estimate_output(words)\n",
" print(f\" Estimated permutations : {total_perms:,}\")\n",
" print(f\" Estimated file size : {est_gb:.2f} GB\")\n",
"\n",
" # Safety check\n",
" if est_gb > 70:\n",
" print(f\"\\n⚠️ WARNING: Estimated output ({est_gb:.1f} GB) exceeds Colab disk (~78 GB).\")\n",
" print(\" Reduce MAX_WORD_LEN or the script will crash when disk fills up.\")\n",
" print(\" Aborting. Set MAX_WORD_LEN lower and re-run.\")\n",
" sys.exit(1)\n",
"\n",
" print(f\"\\nProceeding with generation → {OUTPUT_PATH}\")\n",
" print(\"=\" * 60)\n",
"\n",
" # ── Generate ────────────────────────────────────────────────\n",
" start = time.time()\n",
" total_written = 0\n",
"\n",
" with open(OUTPUT_PATH, 'w', encoding='utf-8') as out:\n",
" out.write(\"# Auto-generated FULL PERMUTATION misspellings\\n\")\n",
" out.write(f\"# Config: word length {MIN_WORD_LEN}-{MAX_WORD_LEN}\\n\")\n",
" out.write(\"# Format: misspelling=correction\\n\\n\")\n",
"\n",
" for idx, word in enumerate(words):\n",
" perms = generate_unique_permutations(word)\n",
"\n",
" for typo in sorted(perms):\n",
" out.write(f\"{typo}={word}\\n\")\n",
" total_written += 1\n",
"\n",
" # Progress\n",
" if (idx + 1) % BATCH_LOG == 0:\n",
" elapsed = time.time() - start\n",
" pct = (idx + 1) / len(words) * 100\n",
" rate = (idx + 1) / elapsed if elapsed > 0 else 0\n",
" cur_size = os.path.getsize(OUTPUT_PATH) / (1024 ** 3)\n",
" print(f\" [{pct:5.1f}%] {idx+1:>7,}/{len(words):,} words |\"\n",
" f\" {total_written:>12,} lines | {cur_size:.2f} GB |\"\n",
" f\" {rate:.0f} words/sec\")\n",
"\n",
" elapsed = time.time() - start\n",
" final_size = os.path.getsize(OUTPUT_PATH) / (1024 ** 3)\n",
"\n",
" print()\n",
" print(\"=\" * 60)\n",
" print(f\" ✅ DONE in {elapsed:.1f}s ({elapsed/60:.1f} min)\")\n",
" print(f\" Words processed : {len(words):,}\")\n",
" print(f\" Lines written : {total_written:,}\")\n",
" print(f\" Output file : {OUTPUT_PATH}\")\n",
" print(f\" File size : {final_size:.2f} GB\")\n",
" print(\"=\" * 60)\n",
"\n",
"\n",
"if __name__ == '__main__':\n",
" main()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Et0QfIxpJz_5",
"outputId": "e7e72965-f709-45c0-ae56-abf76b89d714"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Reading words from: words.txt\n",
"Total raw entries: 466,550\n",
"Filtered to 125,414 words (alpha-only, len 3-7)\n",
"\n",
"Estimating output size (this may take a moment)...\n",
" Estimated permutations : 173,110,626\n",
" Estimated file size : 2.42 GB\n",
"\n",
"Proceeding with generation → misspellings_permutations.txt\n",
"============================================================\n",
" [ 4.0%] 5,000/125,414 words | 5,810,553 lines | 0.08 GB | 898 words/sec\n",
" [ 8.0%] 10,000/125,414 words | 11,972,245 lines | 0.18 GB | 781 words/sec\n",
" [ 12.0%] 15,000/125,414 words | 19,094,747 lines | 0.28 GB | 775 words/sec\n",
" [ 15.9%] 20,000/125,414 words | 26,800,249 lines | 0.39 GB | 721 words/sec\n",
" [ 19.9%] 25,000/125,414 words | 35,047,153 lines | 0.51 GB | 690 words/sec\n",
" [ 23.9%] 30,000/125,414 words | 42,273,166 lines | 0.62 GB | 695 words/sec\n",
" [ 27.9%] 35,000/125,414 words | 48,702,338 lines | 0.71 GB | 692 words/sec\n",
" [ 31.9%] 40,000/125,414 words | 55,295,151 lines | 0.81 GB | 703 words/sec\n",
" [ 35.9%] 45,000/125,414 words | 62,710,327 lines | 0.92 GB | 690 words/sec\n",
" [ 39.9%] 50,000/125,414 words | 69,722,485 lines | 1.02 GB | 690 words/sec\n",
" [ 43.9%] 55,000/125,414 words | 76,146,526 lines | 1.12 GB | 674 words/sec\n",
" [ 47.8%] 60,000/125,414 words | 81,994,038 lines | 1.20 GB | 686 words/sec\n",
" [ 51.8%] 65,000/125,414 words | 88,058,594 lines | 1.29 GB | 683 words/sec\n",
" [ 55.8%] 70,000/125,414 words | 94,651,291 lines | 1.39 GB | 688 words/sec\n",
" [ 59.8%] 75,000/125,414 words | 101,636,647 lines | 1.49 GB | 679 words/sec\n",
" [ 63.8%] 80,000/125,414 words | 107,086,424 lines | 1.57 GB | 691 words/sec\n",
" [ 67.8%] 85,000/125,414 words | 114,898,717 lines | 1.68 GB | 678 words/sec\n",
" [ 71.8%] 90,000/125,414 words | 123,278,791 lines | 1.80 GB | 675 words/sec\n",
" [ 75.7%] 95,000/125,414 words | 129,821,900 lines | 1.90 GB | 669 words/sec\n",
" [ 79.7%] 100,000/125,414 words | 136,429,269 lines | 2.00 GB | 673 words/sec\n",
" [ 83.7%] 105,000/125,414 words | 143,342,171 lines | 2.10 GB | 667 words/sec\n",
" [ 87.7%] 110,000/125,414 words | 150,701,210 lines | 2.21 GB | 666 words/sec\n",
" [ 91.7%] 115,000/125,414 words | 157,479,616 lines | 2.31 GB | 665 words/sec\n",
" [ 95.7%] 120,000/125,414 words | 165,619,673 lines | 2.43 GB | 662 words/sec\n",
" [ 99.7%] 125,000/125,414 words | 172,558,768 lines | 2.53 GB | 661 words/sec\n",
"\n",
"============================================================\n",
" ✅ DONE in 189.5s (3.2 min)\n",
" Words processed : 125,414\n",
" Lines written : 173,110,626\n",
" Output file : misspellings_permutations.txt\n",
" File size : 2.53 GB\n",
"============================================================\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# If saved to VM disk:\n",
"files.download('misspellings_permutations.txt')\n",
"\n",
"# If saved to Google Drive: just access it from drive.google.com\n",
"\n"
],
"metadata": {
"id": "y9jWxvv8LWoH",
"outputId": "d8d754d3-234e-4020-bcc7-a19f3fc5fb26",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"\n",
" async function download(id, filename, size) {\n",
" if (!google.colab.kernel.accessAllowed) {\n",
" return;\n",
" }\n",
" const div = document.createElement('div');\n",
" const label = document.createElement('label');\n",
" label.textContent = `Downloading \"${filename}\": `;\n",
" div.appendChild(label);\n",
" const progress = document.createElement('progress');\n",
" progress.max = size;\n",
" div.appendChild(progress);\n",
" document.body.appendChild(div);\n",
"\n",
" const buffers = [];\n",
" let downloaded = 0;\n",
"\n",
" const channel = await google.colab.kernel.comms.open(id);\n",
" // Send a message to notify the kernel that we're ready.\n",
" channel.send({})\n",
"\n",
" for await (const message of channel.messages) {\n",
" // Send a message to notify the kernel that we're ready.\n",
" channel.send({})\n",
" if (message.buffers) {\n",
" for (const buffer of message.buffers) {\n",
" buffers.push(buffer);\n",
" downloaded += buffer.byteLength;\n",
" progress.value = downloaded;\n",
" }\n",
" }\n",
" }\n",
" const blob = new Blob(buffers, {type: 'application/binary'});\n",
" const a = document.createElement('a');\n",
" a.href = window.URL.createObjectURL(blob);\n",
" a.download = filename;\n",
" div.appendChild(a);\n",
" a.click();\n",
" div.remove();\n",
" }\n",
" "
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"download(\"download_10941777-78c6-4833-b8e6-093feee02e11\", \"misspellings_permutations.txt\", 2721877361)"
]
},
"metadata": {}
}
]
}
]
} |