Spaces:
Running
Running
File size: 44,845 Bytes
8299003 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 | {
"cells": [
{
"cell_type": "markdown",
"id": "title-cell",
"metadata": {},
"source": [
"# SEC Filing Processor\n",
"## Morningstar RAG Pipeline — Phase 2b\n",
"\n",
"This notebook processes **Apple SEC filings** (10-K, 10-Q, 8-K) from raw HTML into structured JSON, following the same pattern as `01_pdf_processing.ipynb` for Morningstar PDFs.\n",
"\n",
"### Why a separate processor?\n",
"\n",
"| | Morningstar PDFs | SEC HTML filings |\n",
"|---|---|---|\n",
"| Input format | PDF | HTML (`.htm`) |\n",
"| Page numbers | Yes | No — HTML has no pages |\n",
"| Noise filter | Page-based (remove pages 13-14) | Cover-section boilerplate |\n",
"| Metadata | company, ticker, doc_type | fiscal_year, accession, filing_date |\n",
"| Docling model | DocLayNet layout detection | HTML structure parsing |\n",
"\n",
"Both use the **same Docling converter** and both save a `_docling.json` — so **HybridChunker in Phase 3 works identically** for PDFs and HTML.\n",
"\n",
"### Filings we are processing\n",
"| Type | Count | Description |\n",
"|---|---|---|\n",
"| 10-K | 3 | Annual reports (2023, 2024, 2025) — large |\n",
"| 10-Q | 6 | Quarterly reports — medium |\n",
"| 8-K | 5 | Current reports / earnings releases — small |\n",
"\n",
"### Steps in this notebook\n",
"```\n",
"STEP 1 — Imports & Paths\n",
"STEP 2 — Configure Docling for HTML\n",
"STEP 3 — Parse One Filing (8-K demo — fastest to run)\n",
"STEP 4 — Inspect Raw Output\n",
"STEP 5 — Extract Sections + Boilerplate Detection\n",
"STEP 6 — Extract Tables\n",
"STEP 7 — Attach Metadata\n",
"STEP 8 — Save JSON + _docling.json\n",
"STEP 9 — Batch Process All SEC Filings\n",
"STEP 10 — Verify Output\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "step1-hdr",
"metadata": {},
"source": [
"## STEP 1 — Imports & Paths"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "step1-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Project root : /home/pushkardeshpand/Documents/Morningstar RAG Pipeline\n",
"Raw SEC dir : /home/pushkardeshpand/Documents/Morningstar RAG Pipeline/data/raw/sec_filings/AAPL\n",
"Output dir : /home/pushkardeshpand/Documents/Morningstar RAG Pipeline/data/processed/sec_filings/AAPL\n",
"\n",
"10-K (3): ['2023', '2024', '2025']\n",
"10-Q (6): ['2024_Q3', '2025_Q1', '2025_Q2', '2025_Q3', '2026_Q1', '2026_Q2']\n",
"8-K (5): ['2026-01-02', '2026-01-29', '2026-02-24', '2026-04-20', '2026-04-30']\n"
]
}
],
"source": [
"import re\n",
"import json\n",
"import sys\n",
"import time\n",
"from pathlib import Path\n",
"from datetime import datetime, timezone\n",
"\n",
"# ── Project paths ──────────────────────────────────────────────────────────────\n",
"NOTEBOOK_DIR = Path().resolve()\n",
"PROJECT_ROOT = NOTEBOOK_DIR.parent\n",
"SRC_DIR = PROJECT_ROOT / \"src\"\n",
"RAW_SEC_DIR = PROJECT_ROOT / \"data\" / \"raw\" / \"sec_filings\" / \"AAPL\"\n",
"SEC_OUT_DIR = PROJECT_ROOT / \"data\" / \"processed\" / \"sec_filings\" / \"AAPL\"\n",
"\n",
"sys.path.insert(0, str(SRC_DIR))\n",
"\n",
"print(f\"Project root : {PROJECT_ROOT}\")\n",
"print(f\"Raw SEC dir : {RAW_SEC_DIR}\")\n",
"print(f\"Output dir : {SEC_OUT_DIR}\")\n",
"print()\n",
"\n",
"# Inventory the raw filings\n",
"for doc_type in [\"10-K\", \"10-Q\", \"8-K\"]:\n",
" type_dir = RAW_SEC_DIR / doc_type\n",
" if not type_dir.exists():\n",
" continue\n",
" periods = sorted(p.name for p in type_dir.iterdir() if (p / \"filing.htm\").exists())\n",
" print(f\"{doc_type:5s} ({len(periods)}): {periods}\")"
]
},
{
"cell_type": "markdown",
"id": "step2-hdr",
"metadata": {},
"source": [
"## STEP 2 — Configure Docling for HTML\n",
"\n",
"Docling handles HTML natively — the same `DocumentConverter` used for PDFs works for `.htm` files.\n",
"\n",
"For HTML, Docling:\n",
"- Parses `<h1>`–`<h6>` tags → `SectionHeaderItem` (heading hierarchy preserved automatically)\n",
"- Parses `<table>` tags → `TableItem` with structure reconstruction via TableFormer\n",
"- Parses `<p>`, `<div>` text → `TextItem`\n",
"- No OCR, no layout detection (not needed for HTML)\n",
"\n",
"The resulting `DoclingDocument` object is identical in structure to the one produced from a PDF — so **HybridChunker works on both without any changes**."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "step2-code",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"I0000 00:00:1782117419.440624 3132948 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"I0000 00:00:1782117419.473381 3132948 cpu_feature_guard.cc:227] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"I0000 00:00:1782117420.228651 3132948 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Docling converter ready.\n",
" Table structure : True\n",
" OCR : False\n",
" Picture images : False\n"
]
}
],
"source": [
"import warnings\n",
"warnings.filterwarnings(\"ignore\")\n",
"\n",
"from docling.document_converter import DocumentConverter, PdfFormatOption\n",
"from docling.datamodel.pipeline_options import PdfPipelineOptions\n",
"from docling.datamodel.base_models import InputFormat\n",
"\n",
"opts = PdfPipelineOptions()\n",
"opts.do_table_structure = True # reconstruct <table> rows/columns\n",
"opts.do_ocr = False # HTML — no OCR needed\n",
"opts.generate_picture_images = False # skip figure extraction\n",
"\n",
"converter = DocumentConverter(\n",
" format_options={\n",
" InputFormat.PDF: PdfFormatOption(pipeline_options=opts)\n",
" }\n",
")\n",
"\n",
"print(\"Docling converter ready.\")\n",
"print(f\" Table structure : {opts.do_table_structure}\")\n",
"print(f\" OCR : {opts.do_ocr}\")\n",
"print(f\" Picture images : {opts.generate_picture_images}\")"
]
},
{
"cell_type": "markdown",
"id": "step3-hdr",
"metadata": {},
"source": [
"## STEP 3 — Parse One Filing (8-K Demo)\n",
"\n",
"We start with a recent 8-K (earnings press release) — it is the smallest filing type and parses quickly.\n",
"\n",
"After this walkthrough, STEP 9 will batch-process **all 14 filings** automatically.\n",
"\n",
"> **Note on processing time:**\n",
"> - 8-K: ~10–30 seconds (small — earnings release text)\n",
"> - 10-Q: ~1–3 minutes (medium — quarterly financial statements)\n",
"> - 10-K: ~5–15 minutes per file (large — full annual report with 60+ tables)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "step3-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filing : filing.htm\n",
"Size : 37 KB\n",
"Form type : 8-K\n",
"Filing date : 2026-04-30\n",
"Accession : 0000320193-26-000011\n",
"\n",
"Parsing with Docling (this may take 10–30 seconds for an 8-K)...\n",
"\n",
"Parsing complete in 0.1s\n",
"Document type : DoclingDocument\n",
"Tables found : 14\n"
]
}
],
"source": [
"# Use the most recent 8-K as the demo filing\n",
"HTM_PATH = RAW_SEC_DIR / \"8-K\" / \"2026-04-30\" / \"filing.htm\"\n",
"\n",
"with open(RAW_SEC_DIR / \"8-K\" / \"2026-04-30\" / \"metadata.json\") as f:\n",
" file_meta = json.load(f)\n",
"\n",
"print(f\"Filing : {HTM_PATH.name}\")\n",
"print(f\"Size : {HTM_PATH.stat().st_size / 1024:.0f} KB\")\n",
"print(f\"Form type : {file_meta['form']}\")\n",
"print(f\"Filing date : {file_meta['filing_date']}\")\n",
"print(f\"Accession : {file_meta['accession']}\")\n",
"print()\n",
"print(\"Parsing with Docling (this may take 10–30 seconds for an 8-K)...\")\n",
"\n",
"start = time.time()\n",
"result = converter.convert(str(HTM_PATH))\n",
"doc = result.document\n",
"elapsed = time.time() - start\n",
"\n",
"print(f\"\\nParsing complete in {elapsed:.1f}s\")\n",
"print(f\"Document type : {type(doc).__name__}\")\n",
"print(f\"Tables found : {len(doc.tables)}\")"
]
},
{
"cell_type": "markdown",
"id": "step4-hdr",
"metadata": {},
"source": [
"## STEP 4 — Inspect Raw Output\n",
"\n",
"Let's see what element types Docling produced from the HTML."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "step4-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Element types in document:\n",
" TextItem 36\n",
" TableItem 14\n",
" PictureItem 1\n",
"\n",
"First 12 elements:\n",
"----------------------------------------------------------------------\n",
" [TableItem ] lvl=1 \"\"\n",
" [TextItem ] lvl=1 \"UNITED STATES\"\n",
" [TextItem ] lvl=1 \"SECURITIES AND EXCHANGE COMMISSION\"\n",
" [TextItem ] lvl=1 \"Washington, D.C. 20549\"\n",
" [TableItem ] lvl=1 \"\"\n",
" [TextItem ] lvl=1 \"FORM 8-K\"\n",
" [TextItem ] lvl=1 \"CURRENT REPORT\"\n",
" [TextItem ] lvl=1 \"Pursuant to Section 13 OR 15(d) of The Securities Exchange Act of 1934\"\n",
" [TextItem ] lvl=1 \"April 30, 2026\"\n",
" [TextItem ] lvl=1 \"Date of Report (Date of earliest event reported)\"\n",
" [TableItem ] lvl=1 \"\"\n",
" [TextItem ] lvl=1 \"g325078g0426062022046a24.jpg\"\n"
]
}
],
"source": [
"from docling.datamodel.document import TextItem, SectionHeaderItem, TableItem\n",
"\n",
"# Count element types\n",
"type_counts = {}\n",
"for item, level in doc.iterate_items():\n",
" t = type(item).__name__\n",
" type_counts[t] = type_counts.get(t, 0) + 1\n",
"\n",
"print(\"Element types in document:\")\n",
"for t, n in sorted(type_counts.items(), key=lambda x: -x[1]):\n",
" print(f\" {t:30s} {n}\")\n",
"\n",
"print()\n",
"print(\"First 12 elements:\")\n",
"print(\"-\" * 70)\n",
"for i, (item, level) in enumerate(doc.iterate_items()):\n",
" if i >= 12:\n",
" break\n",
" text = getattr(item, \"text\", \"\")[:80]\n",
" itype = type(item).__name__\n",
" print(f\" [{itype:20s}] lvl={level} \\\"{text}\\\"\")"
]
},
{
"cell_type": "markdown",
"id": "step5-hdr",
"metadata": {},
"source": [
"## STEP 5 — Extract Sections + Boilerplate Detection\n",
"\n",
"SEC filings begin with a **cover section** containing administrative metadata — not financial content.\n",
"\n",
"This boilerplate includes:\n",
"- `UNITED STATES` / `SECURITIES AND EXCHANGE COMMISSION`\n",
"- `Commission File Number: 001-36743`\n",
"- `(Exact name of Registrant as specified in its charter)`\n",
"- Form checkboxes: `☒ ANNUAL REPORT PURSUANT TO SECTION 13(d)...`\n",
"\n",
"We tag these with `is_boilerplate: True` so downstream processes can identify them. We do **not** remove them from the `_docling.json` — HybridChunker handles the structure.\n",
"\n",
"> Unlike Morningstar PDFs where we removed entire pages, here we flag individual fragments because there are no page boundaries."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "step5-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Sections extracted : 36\n",
" Boilerplate : 7 (cover-section administrative text)\n",
" Content : 29\n",
" Headers : 0\n",
"\n",
"Section headers found:\n",
"\n",
"First 5 content sections:\n",
" [text ] parent=''\n",
" text='CURRENT REPORT'\n",
" [text ] parent=''\n",
" text='Pursuant to Section 13 OR 15(d) of The Securities Exchange Act of 1934'\n",
" [text ] parent=''\n",
" text='April 30, 2026'\n",
" [text ] parent=''\n",
" text='Date of Report (Date of earliest event reported)'\n",
" [text ] parent=''\n",
" text='g325078g0426062022046a24.jpg'\n"
]
}
],
"source": [
"_BOILERPLATE_EXACT = {\n",
" \"united states\",\n",
" \"securities and exchange commission\",\n",
" \"washington, d.c. 20549\",\n",
" \"(mark one)\",\n",
" \"or\",\n",
" \"for the transition period from to .\",\n",
" \"\\u2612\", \"\\u2610\",\n",
"}\n",
"\n",
"_BOILERPLATE_RE = re.compile(\n",
" r\"^(\"\n",
" r\"form \\d+[\\-/][a-z]+\"\n",
" r\"|commission file\"\n",
" r\"|irs employer\"\n",
" r\"|state or other\"\n",
" r\"|jurisdiction\"\n",
" r\"|\\(exact name\"\n",
" r\"|\\(zip code\"\n",
" r\"|indicate by check\"\n",
" r\"|securities registered\"\n",
" r\"|aggregate market value\"\n",
" r\"|number of shares\"\n",
" r\"|\\u2612|\\u2610\"\n",
" r\")\",\n",
" re.IGNORECASE,\n",
")\n",
"\n",
"def _is_boilerplate(text: str) -> bool:\n",
" t = text.strip().lower()\n",
" if t in _BOILERPLATE_EXACT: return True\n",
" if len(t) < 5: return True\n",
" if _BOILERPLATE_RE.match(text.strip()): return True\n",
" return False\n",
"\n",
"def clean_text(text: str) -> str:\n",
" if not text: return \"\"\n",
" text = text.replace(\"\\u00ad\", \"\").replace(\"\\u200b\", \"\")\n",
" text = re.sub(r\"[ \\t]+\", \" \", text)\n",
" text = re.sub(r\"\\n{3,}\", \"\\n\\n\", text)\n",
" return text.strip()\n",
"\n",
"\n",
"# Extract all sections\n",
"sections = []\n",
"current_header = \"\"\n",
"\n",
"for item, level in doc.iterate_items():\n",
" text = getattr(item, \"text\", None)\n",
" if not text or not text.strip():\n",
" continue\n",
" if isinstance(item, TableItem):\n",
" continue\n",
"\n",
" raw = text.strip()\n",
" is_hdr = isinstance(item, SectionHeaderItem)\n",
"\n",
" sections.append({\n",
" \"type\" : \"header\" if is_hdr else \"text\",\n",
" \"level\" : level,\n",
" \"text\" : raw,\n",
" \"cleaned_text\" : clean_text(raw),\n",
" \"page_num\" : None,\n",
" \"parent_header\" : current_header,\n",
" \"is_boilerplate\": _is_boilerplate(raw),\n",
" })\n",
"\n",
" if is_hdr:\n",
" current_header = raw\n",
"\n",
"boilerplate = [s for s in sections if s[\"is_boilerplate\"]]\n",
"content = [s for s in sections if not s[\"is_boilerplate\"]]\n",
"headers = [s for s in sections if s[\"type\"] == \"header\"]\n",
"\n",
"print(f\"Sections extracted : {len(sections)}\")\n",
"print(f\" Boilerplate : {len(boilerplate)} (cover-section administrative text)\")\n",
"print(f\" Content : {len(content)}\")\n",
"print(f\" Headers : {len(headers)}\")\n",
"print()\n",
"print(\"Section headers found:\")\n",
"for h in headers:\n",
" print(f\" [H{h['level']}] {h['text'][:80]}\")\n",
"print()\n",
"print(\"First 5 content sections:\")\n",
"for s in content[:5]:\n",
" print(f\" [{s['type']:6s}] parent='{s['parent_header'][:40]}'\")\n",
" print(f\" text='{s['text'][:100]}'\")"
]
},
{
"cell_type": "markdown",
"id": "step6-hdr",
"metadata": {},
"source": [
"## STEP 6 — Extract Tables\n",
"\n",
"SEC filings contain financial statement tables — balance sheets, income statements, cash flow statements.\n",
"\n",
"Same approach as Morningstar PDFs:\n",
"- `export_to_dataframe(doc)` → structured data\n",
"- `export_to_markdown(doc)` → markdown for LLM context\n",
"- `is_atomic = True` → never split these in chunking"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "step6-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tables extracted: 14\n",
"\n",
" # Rows Cols Headers\n",
"------------------------------------------------------------\n",
" 0 2 3 ['0', '1', '2']\n",
" 1 2 3 ['0', '1', '2']\n",
" 2 2 3 ['0', '1', '2']\n",
" 3 3 15 ['0', '1', '2']\n",
" 4 2 6 ['0', '1', '2']\n",
" 5 2 6 ['0', '1', '2']\n",
" 6 2 6 ['0', '1', '2']\n",
" 7 2 6 ['0', '1', '2']\n",
" 8 2 3 ['0', '1', '2']\n",
" 9 9 9 ['0', '1', '2']\n",
" 10 2 3 ['0', '1', '2']\n",
" 11 2 3 ['0', '1', '2']\n",
" 12 5 9 ['0', '1', '2']\n",
" 13 6 18 ['0', '1', '2']\n",
"\n",
"First table preview (markdown format — what LLM receives):\n",
"=======================================================\n",
"| | | | | | | | | | | | | | | | | | |\n",
"|-------|-------|-------|----------------|----------------|----------------|----|----|----|------------|------------|------------|------------|------------|------------|------------------------------------------------|------------------|------------------|\n",
"| Date: | Date: | Date: | April 30, 2026 | April 30, 2026 | April 30, 2026 | | | | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. | Apple Inc. |\n",
"| | | | | | | | | | | | | | | | | \n",
"=======================================================\n"
]
}
],
"source": [
"tables = []\n",
"\n",
"for i, table in enumerate(doc.tables):\n",
" try:\n",
" df = table.export_to_dataframe(doc)\n",
" markdown = table.export_to_markdown(doc)\n",
"\n",
" if df.empty or len(df) < 2:\n",
" continue\n",
"\n",
" tables.append({\n",
" \"index\" : i,\n",
" \"page_num\" : None,\n",
" \"markdown\" : markdown,\n",
" \"headers\" : list(df.columns.astype(str)),\n",
" \"rows\" : len(df),\n",
" \"cols\" : len(df.columns),\n",
" \"data\" : df.fillna(\"\").values.tolist(),\n",
" \"is_atomic\": True,\n",
" })\n",
" except Exception as e:\n",
" print(f\" Warning: table {i} skipped — {e}\")\n",
"\n",
"print(f\"Tables extracted: {len(tables)}\")\n",
"print()\n",
"print(f\"{'#':>3} {'Rows':>4} {'Cols':>4} Headers\")\n",
"print(\"-\" * 60)\n",
"for t in tables:\n",
" print(f\"{t['index']:>3} {t['rows']:>4} {t['cols']:>4} {t['headers'][:3]}\")\n",
"\n",
"if tables:\n",
" print()\n",
" print(\"First table preview (markdown format — what LLM receives):\")\n",
" print(\"=\" * 55)\n",
" print(tables[13][\"markdown\"][:1000])\n",
" print(\"=\" * 55)"
]
},
{
"cell_type": "markdown",
"id": "step7-hdr",
"metadata": {},
"source": [
"## STEP 7 — Attach Metadata\n",
"\n",
"Every chunk from this document will carry metadata that enables filtered retrieval:\n",
"\n",
"```python\n",
"# Retrieve only Apple 10-K chunks\n",
"vectorstore.query(query, filter={\"doc_type\": \"10-K\", \"ticker\": \"AAPL\"})\n",
"\n",
"# Retrieve only the 2024 annual report\n",
"vectorstore.query(query, filter={\"doc_type\": \"10-K\", \"fiscal_year\": \"2024\"})\n",
"\n",
"# Retrieve all Apple financial data (any doc type)\n",
"vectorstore.query(query, filter={\"ticker\": \"AAPL\"})\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "step7-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Document metadata:\n",
" source : sec_edgar\n",
" doc_type : 8-K\n",
" ticker : AAPL\n",
" company : Apple Inc.\n",
" fiscal_year : 2026\n",
" filing_date : 2026-04-30\n",
" accession : 0000320193-26-000011\n",
" file_name : filing.htm\n",
" file_path : /home/pushkardeshpand/Documents/Morningstar RAG Pipeline/data/raw/sec_filings/AAPL/8-K/2026-04-30/filing.htm\n",
" license : public\n",
" access_level : public\n",
" parsed_at : 2026-06-22T08:41:12.684682+00:00\n",
" parser : docling\n",
" total_pages : 0\n",
" total_sections : 36\n",
" total_tables : 14\n",
" removed_pages : []\n"
]
}
],
"source": [
"doc_metadata = {\n",
" \"source\" : \"sec_edgar\",\n",
" \"doc_type\" : file_meta[\"form\"],\n",
" \"ticker\" : file_meta[\"ticker\"],\n",
" \"company\" : \"Apple Inc.\",\n",
" \"fiscal_year\" : file_meta[\"fiscal_year\"],\n",
" \"filing_date\" : file_meta[\"filing_date\"],\n",
" \"accession\" : file_meta[\"accession\"],\n",
" \"file_name\" : HTM_PATH.name,\n",
" \"file_path\" : str(HTM_PATH),\n",
" \"license\" : \"public\",\n",
" \"access_level\": \"public\",\n",
" \"parsed_at\" : datetime.now(timezone.utc).isoformat(),\n",
" \"parser\" : \"docling\",\n",
" \"total_pages\" : 0,\n",
" \"total_sections\" : len(sections),\n",
" \"total_tables\" : len(tables),\n",
" \"removed_pages\" : [], # HTML has no page numbers\n",
"}\n",
"\n",
"print(\"Document metadata:\")\n",
"for k, v in doc_metadata.items():\n",
" print(f\" {k:20s}: {v}\")"
]
},
{
"cell_type": "markdown",
"id": "step8-hdr",
"metadata": {},
"source": [
"## STEP 8 — Save JSON + `_docling.json`\n",
"\n",
"We save two files — same pattern as `pdf_processor.py`:\n",
"\n",
"| File | Purpose |\n",
"|---|---|\n",
"| `8-K_2026-04-30.json` | Structured JSON — sections, tables, metadata for inspection |\n",
"| `8-K_2026-04-30_docling.json` | Native DoclingDocument — loaded by HybridChunker in Phase 3 |\n",
"\n",
"The `_docling.json` is what enables HybridChunker to understand the full HTML heading hierarchy — headings, reading order, table positions — rather than working on a flat text list."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "step8-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Saved JSON : 8-K_2026-04-30.json (36.3 KB)\n",
"Saved _docling : 8-K_2026-04-30_docling.json (142.3 KB)\n",
"\n",
"What HybridChunker will see when it loads _docling.json:\n",
" Full document heading hierarchy preserved\n",
" 36 text sections\n",
" 14 tables (will be handled atomically)\n",
" All HTML <h1>-<h6> tags → SectionHeaderItem → heading_path metadata\n"
]
}
],
"source": [
"DOC_STEM = f\"{file_meta['form']}_{file_meta['filing_date']}\"\n",
"\n",
"SEC_OUT_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"out_path = SEC_OUT_DIR / f\"{DOC_STEM}.json\"\n",
"docling_path = SEC_OUT_DIR / f\"{DOC_STEM}_docling.json\"\n",
"\n",
"parsed = {\n",
" \"metadata\" : doc_metadata,\n",
" \"sections\" : sections,\n",
" \"tables\" : tables,\n",
"}\n",
"\n",
"# Save structured JSON\n",
"with open(out_path, \"w\") as f:\n",
" json.dump(parsed, f, indent=2, ensure_ascii=False, default=str)\n",
"print(f\"Saved JSON : {out_path.name} ({out_path.stat().st_size/1024:.1f} KB)\")\n",
"\n",
"# Save native DoclingDocument (required for HybridChunker)\n",
"with open(docling_path, \"w\") as f:\n",
" f.write(doc.model_dump_json())\n",
"print(f\"Saved _docling : {docling_path.name} ({docling_path.stat().st_size/1024:.1f} KB)\")\n",
"\n",
"print()\n",
"print(\"What HybridChunker will see when it loads _docling.json:\")\n",
"print(f\" Full document heading hierarchy preserved\")\n",
"print(f\" {len(sections)} text sections\")\n",
"print(f\" {len(tables)} tables (will be handled atomically)\")\n",
"print(f\" All HTML <h1>-<h6> tags → SectionHeaderItem → heading_path metadata\")"
]
},
{
"cell_type": "markdown",
"id": "step9-hdr",
"metadata": {},
"source": [
"## STEP 9 — Batch Process All SEC Filings\n",
"\n",
"Now use the `SECProcessor` class from `src/sec_processor.py` to process all 14 filings.\n",
"\n",
"> **Expected processing time:**\n",
"> - 8-K (×5) : ~10–30s each → ~2 min total\n",
"> - 10-Q (×6) : ~1–3 min each → ~10 min total\n",
"> - 10-K (×3) : ~5–15 min each → ~30 min total\n",
">\n",
"> Total: **~45 minutes** on CPU. The batch runs sequentially — grab a coffee.\n",
"> Already-processed files are skipped automatically (`force=False`)."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "step9-code",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2026-06-22 14:17:09,896 INFO \n",
"── 10-K filings ────────────────────────────\n",
"2026-06-22 14:17:09,897 INFO Processing: 10-K_2023 (filing.htm)\n",
"2026-06-22 14:17:09,920 INFO Docling converter ready.\n",
"2026-06-22 14:17:09,923 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:17:10,112 INFO Going to convert document batch...\n",
"2026-06-22 14:17:10,112 INFO Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a\n",
"2026-06-22 14:17:10,113 INFO Processing document filing.htm\n",
"2026-06-22 14:17:11,163 INFO Finished converting document filing.htm in 1.24 sec.\n",
"2026-06-22 14:17:35,599 INFO Saved JSON : 10-K_2023.json (1213.1 KB)\n",
"2026-06-22 14:17:35,707 INFO Saved _docling : 10-K_2023_docling.json (5302.1 KB)\n",
"2026-06-22 14:17:35,707 INFO Sections: 1086 (boilerplate: 69) Tables: 66\n",
"2026-06-22 14:17:35,717 INFO Processing: 10-K_2024 (filing.htm)\n",
"2026-06-22 14:17:35,720 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:17:35,888 INFO Going to convert document batch...\n",
"2026-06-22 14:17:35,888 INFO Processing document filing.htm\n",
"2026-06-22 14:17:36,773 INFO Finished converting document filing.htm in 1.06 sec.\n",
"2026-06-22 14:17:59,804 INFO Saved JSON : 10-K_2024.json (1196.1 KB)\n",
"2026-06-22 14:17:59,920 INFO Saved _docling : 10-K_2024_docling.json (5167.8 KB)\n",
"2026-06-22 14:17:59,921 INFO Sections: 1077 (boilerplate: 70) Tables: 63\n",
"2026-06-22 14:17:59,928 INFO Processing: 10-K_2025 (filing.htm)\n",
"2026-06-22 14:17:59,944 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:00,130 INFO Going to convert document batch...\n",
"2026-06-22 14:18:00,131 INFO Processing document filing.htm\n",
"2026-06-22 14:18:01,064 INFO Finished converting document filing.htm in 1.14 sec.\n",
"2026-06-22 14:18:28,078 INFO Saved JSON : 10-K_2025.json (1204.9 KB)\n",
"2026-06-22 14:18:28,177 INFO Saved _docling : 10-K_2025_docling.json (5242.1 KB)\n",
"2026-06-22 14:18:28,178 INFO Sections: 1107 (boilerplate: 70) Tables: 62\n",
"2026-06-22 14:18:28,182 INFO \n",
"── 10-Q filings ────────────────────────────\n",
"2026-06-22 14:18:28,183 INFO Processing: 10-Q_2024_Q3 (filing.htm)\n",
"2026-06-22 14:18:28,184 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:28,332 INFO Going to convert document batch...\n",
"2026-06-22 14:18:28,333 INFO Processing document filing.htm\n",
"2026-06-22 14:18:28,998 INFO Finished converting document filing.htm in 0.82 sec.\n",
"2026-06-22 14:18:37,051 INFO Saved JSON : 10-Q_2024_Q3.json (597.8 KB)\n",
"2026-06-22 14:18:37,108 INFO Saved _docling : 10-Q_2024_Q3_docling.json (3212.1 KB)\n",
"2026-06-22 14:18:37,109 INFO Sections: 512 (boilerplate: 32) Tables: 39\n",
"2026-06-22 14:18:37,111 INFO Processing: 10-Q_2025_Q1 (filing.htm)\n",
"2026-06-22 14:18:37,114 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:37,201 INFO Going to convert document batch...\n",
"2026-06-22 14:18:37,202 INFO Processing document filing.htm\n",
"2026-06-22 14:18:37,563 INFO Finished converting document filing.htm in 0.45 sec.\n",
"2026-06-22 14:18:42,913 INFO Saved JSON : 10-Q_2025_Q1.json (564.1 KB)\n",
"2026-06-22 14:18:42,964 INFO Saved _docling : 10-Q_2025_Q1_docling.json (3025.9 KB)\n",
"2026-06-22 14:18:42,964 INFO Sections: 460 (boilerplate: 32) Tables: 37\n",
"2026-06-22 14:18:42,967 INFO Processing: 10-Q_2025_Q2 (filing.htm)\n",
"2026-06-22 14:18:42,969 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:43,076 INFO Going to convert document batch...\n",
"2026-06-22 14:18:43,076 INFO Processing document filing.htm\n",
"2026-06-22 14:18:43,498 INFO Finished converting document filing.htm in 0.53 sec.\n",
"2026-06-22 14:18:50,899 INFO Saved JSON : 10-Q_2025_Q2.json (615.4 KB)\n",
"2026-06-22 14:18:50,952 INFO Saved _docling : 10-Q_2025_Q2_docling.json (3159.3 KB)\n",
"2026-06-22 14:18:50,952 INFO Sections: 513 (boilerplate: 32) Tables: 37\n",
"2026-06-22 14:18:50,954 INFO Processing: 10-Q_2025_Q3 (filing.htm)\n",
"2026-06-22 14:18:50,956 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:51,062 INFO Going to convert document batch...\n",
"2026-06-22 14:18:51,062 INFO Processing document filing.htm\n",
"2026-06-22 14:18:51,489 INFO Finished converting document filing.htm in 0.53 sec.\n",
"2026-06-22 14:18:59,275 INFO Saved JSON : 10-Q_2025_Q3.json (601.6 KB)\n",
"2026-06-22 14:18:59,327 INFO Saved _docling : 10-Q_2025_Q3_docling.json (3183.1 KB)\n",
"2026-06-22 14:18:59,327 INFO Sections: 506 (boilerplate: 32) Tables: 38\n",
"2026-06-22 14:18:59,330 INFO Processing: 10-Q_2026_Q1 (filing.htm)\n",
"2026-06-22 14:18:59,332 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:18:59,422 INFO Going to convert document batch...\n",
"2026-06-22 14:18:59,423 INFO Processing document filing.htm\n",
"2026-06-22 14:18:59,799 INFO Finished converting document filing.htm in 0.47 sec.\n",
"2026-06-22 14:19:05,928 INFO Saved JSON : 10-Q_2026_Q1.json (602.8 KB)\n",
"2026-06-22 14:19:05,991 INFO Saved _docling : 10-Q_2026_Q1_docling.json (3345.3 KB)\n",
"2026-06-22 14:19:05,992 INFO Sections: 474 (boilerplate: 32) Tables: 38\n",
"2026-06-22 14:19:05,994 INFO Processing: 10-Q_2026_Q2 (filing.htm)\n",
"2026-06-22 14:19:05,997 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:19:06,115 INFO Going to convert document batch...\n",
"2026-06-22 14:19:06,116 INFO Processing document filing.htm\n",
"2026-06-22 14:19:06,581 INFO Finished converting document filing.htm in 0.59 sec.\n",
"2026-06-22 14:19:17,686 INFO Saved JSON : 10-Q_2026_Q2.json (733.2 KB)\n",
"2026-06-22 14:19:17,759 INFO Saved _docling : 10-Q_2026_Q2_docling.json (3608.9 KB)\n",
"2026-06-22 14:19:17,760 INFO Sections: 610 (boilerplate: 32) Tables: 39\n",
"2026-06-22 14:19:17,763 INFO \n",
"── 8-K filings ────────────────────────────\n",
"2026-06-22 14:19:17,764 INFO Processing: 8-K_2026-01-02 (filing.htm)\n",
"2026-06-22 14:19:17,764 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:19:17,775 INFO Going to convert document batch...\n",
"2026-06-22 14:19:17,775 INFO Processing document filing.htm\n",
"2026-06-22 14:19:17,809 INFO Finished converting document filing.htm in 0.05 sec.\n",
"2026-06-22 14:19:17,890 INFO Saved JSON : 8-K_2026-01-02.json (22.8 KB)\n",
"2026-06-22 14:19:17,892 INFO Saved _docling : 8-K_2026-01-02_docling.json (60.0 KB)\n",
"2026-06-22 14:19:17,892 INFO Sections: 73 (boilerplate: 24) Tables: 2\n",
"2026-06-22 14:19:17,893 INFO Processing: 8-K_2026-01-29 (filing.htm)\n",
"2026-06-22 14:19:17,894 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:19:17,903 INFO Going to convert document batch...\n",
"2026-06-22 14:19:17,903 INFO Processing document filing.htm\n",
"2026-06-22 14:19:17,928 INFO Finished converting document filing.htm in 0.04 sec.\n",
"2026-06-22 14:19:17,973 INFO Saved JSON : 8-K_2026-01-29.json (36.4 KB)\n",
"2026-06-22 14:19:17,976 INFO Saved _docling : 8-K_2026-01-29_docling.json (142.3 KB)\n",
"2026-06-22 14:19:17,977 INFO Sections: 36 (boilerplate: 7) Tables: 14\n",
"2026-06-22 14:19:17,978 INFO Processing: 8-K_2026-02-24 (filing.htm)\n",
"2026-06-22 14:19:17,979 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:19:17,994 INFO Going to convert document batch...\n",
"2026-06-22 14:19:17,995 INFO Processing document filing.htm\n",
"2026-06-22 14:19:18,046 INFO Finished converting document filing.htm in 0.07 sec.\n",
"2026-06-22 14:19:18,170 INFO Saved JSON : 8-K_2026-02-24.json (30.7 KB)\n",
"2026-06-22 14:19:18,175 INFO Saved _docling : 8-K_2026-02-24_docling.json (132.1 KB)\n",
"2026-06-22 14:19:18,176 INFO Sections: 76 (boilerplate: 24) Tables: 8\n",
"2026-06-22 14:19:18,179 INFO Processing: 8-K_2026-04-20 (filing.htm)\n",
"2026-06-22 14:19:18,180 INFO detected formats: [<InputFormat.HTML: 'html'>]\n",
"2026-06-22 14:19:18,188 INFO Going to convert document batch...\n",
"2026-06-22 14:19:18,189 INFO Processing document filing.htm\n",
"2026-06-22 14:19:18,244 INFO Finished converting document filing.htm in 0.06 sec.\n",
"2026-06-22 14:19:18,322 INFO Saved JSON : 8-K_2026-04-20.json (24.0 KB)\n",
"2026-06-22 14:19:18,325 INFO Saved _docling : 8-K_2026-04-20_docling.json (57.9 KB)\n",
"2026-06-22 14:19:18,325 INFO Sections: 73 (boilerplate: 24) Tables: 2\n",
"2026-06-22 14:19:18,331 INFO SKIP 8-K_2026-04-30 (already processed → 8-K_2026-04-30.json)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"============================================================\n",
"Batch complete in 2.1 minutes\n",
"============================================================\n",
"\n",
" Filing Sections Tables\n",
"------------------------------------------------------------\n",
" 10-K_2023-11-03 1086 66\n",
" 10-K_2024-11-01 1077 63\n",
" 10-K_2025-10-31 1107 62\n",
" 10-Q_2024-08-02 512 39\n",
" 10-Q_2025-01-31 460 37\n",
" 10-Q_2025-05-02 513 37\n",
" 10-Q_2025-08-01 506 38\n",
" 10-Q_2026-01-30 474 38\n",
" 10-Q_2026-05-01 610 39\n",
" 8-K_2026-01-02 73 2\n",
" 8-K_2026-01-29 36 14\n",
" 8-K_2026-02-24 76 8\n",
" 8-K_2026-04-20 73 2\n",
" 8-K_2026-04-30 36 14\n",
"\n",
" Total sections : 6639\n",
" Total tables : 459\n"
]
}
],
"source": [
"from sec_processor import SECProcessor\n",
"\n",
"processor = SECProcessor(output_dir=SEC_OUT_DIR)\n",
"\n",
"batch_start = time.time()\n",
"results = processor.process_all(raw_dir=RAW_SEC_DIR, force=False)\n",
"batch_elapsed = time.time() - batch_start\n",
"\n",
"print(f\"\\n{'='*60}\")\n",
"print(f\"Batch complete in {batch_elapsed/60:.1f} minutes\")\n",
"print(f\"{'='*60}\")\n",
"print(f\"\\n {'Filing':40s} {'Sections':>8} {'Tables':>6}\")\n",
"print(\"-\" * 60)\n",
"for r in results:\n",
" m = r[\"metadata\"]\n",
" stem = f\"{m['doc_type']}_{m['filing_date'] or m['fiscal_year']}\"\n",
" print(f\" {stem:40s} {m['total_sections']:>8} {m['total_tables']:>6}\")\n",
"\n",
"print(f\"\\n Total sections : {sum(r['metadata']['total_sections'] for r in results)}\")\n",
"print(f\" Total tables : {sum(r['metadata']['total_tables'] for r in results)}\")"
]
},
{
"cell_type": "markdown",
"id": "step10-hdr",
"metadata": {},
"source": [
"## STEP 10 — Verify Output\n",
"\n",
"Confirm all JSON and `_docling.json` files were created. Every `.json` must have a paired `_docling.json` — otherwise HybridChunker will skip it in Phase 3."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "step10-code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processed JSONs : 14\n",
"_docling.json : 14\n",
"\n",
"File JSON _docling Status\n",
"--------------------------------------------------------------------------------\n",
" 10-K_2023.json 1213 KB 5302 KB OK\n",
" 10-K_2024.json 1196 KB 5168 KB OK\n",
" 10-K_2025.json 1205 KB 5242 KB OK\n",
" 10-Q_2024_Q3.json 598 KB 3212 KB OK\n",
" 10-Q_2025_Q1.json 564 KB 3026 KB OK\n",
" 10-Q_2025_Q2.json 615 KB 3159 KB OK\n",
" 10-Q_2025_Q3.json 602 KB 3183 KB OK\n",
" 10-Q_2026_Q1.json 603 KB 3345 KB OK\n",
" 10-Q_2026_Q2.json 733 KB 3609 KB OK\n",
" 8-K_2026-01-02.json 23 KB 60 KB OK\n",
" 8-K_2026-01-29.json 36 KB 142 KB OK\n",
" 8-K_2026-02-24.json 31 KB 132 KB OK\n",
" 8-K_2026-04-20.json 24 KB 58 KB OK\n",
" 8-K_2026-04-30.json 36 KB 142 KB OK\n",
"\n",
"All 14 filings have paired _docling.json files.\n",
"HybridChunker will work for all documents in Phase 3.\n"
]
}
],
"source": [
"all_json = sorted(f for f in SEC_OUT_DIR.glob(\"*.json\") if not f.name.endswith(\"_docling.json\"))\n",
"all_docling = sorted(SEC_OUT_DIR.glob(\"*_docling.json\"))\n",
"\n",
"print(f\"Processed JSONs : {len(all_json)}\")\n",
"print(f\"_docling.json : {len(all_docling)}\")\n",
"print()\n",
"\n",
"missing_docling = []\n",
"print(f\"{'File':45s} {'JSON':>8} {'_docling':>10} Status\")\n",
"print(\"-\" * 80)\n",
"for jf in all_json:\n",
" dl = jf.with_name(jf.stem + \"_docling.json\")\n",
" has = dl.exists()\n",
" j_kb = jf.stat().st_size / 1024\n",
" dl_kb = dl.stat().st_size / 1024 if has else 0\n",
" status = \"OK\" if has else \"MISSING _docling.json\"\n",
" print(f\" {jf.name:43s} {j_kb:>6.0f} KB {dl_kb:>8.0f} KB {status}\")\n",
" if not has:\n",
" missing_docling.append(jf.name)\n",
"\n",
"if missing_docling:\n",
" print(f\"\\nWARNING: {len(missing_docling)} files missing _docling.json:\")\n",
" for f in missing_docling:\n",
" print(f\" {f}\")\n",
"else:\n",
" print(f\"\\nAll {len(all_json)} filings have paired _docling.json files.\")\n",
" print(\"HybridChunker will work for all documents in Phase 3.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e495e460-9995-4545-8aac-9ce2742f30eb",
"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": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|