diff options
| author | J08nY | 2022-10-04 14:40:33 +0200 |
|---|---|---|
| committer | J08nY | 2022-10-04 14:41:18 +0200 |
| commit | 9763c1d8a61b75112efddbbe61a4642e1e4b46ce (patch) | |
| tree | 50b0f62658d7968c7954e8d3eca8fbbf2f4cfd74 | |
| parent | 83c30715731ba39091f6c7cb1f4d6c6d1590731e (diff) | |
| download | sec-certs-9763c1d8a61b75112efddbbe61a4642e1e4b46ce.tar.gz sec-certs-9763c1d8a61b75112efddbbe61a4642e1e4b46ce.tar.zst sec-certs-9763c1d8a61b75112efddbbe61a4642e1e4b46ce.zip | |
Add final-run logs.
| -rw-r--r-- | notebooks/final_run.ipynb | 789 |
1 files changed, 700 insertions, 89 deletions
diff --git a/notebooks/final_run.ipynb b/notebooks/final_run.ipynb index 6a1b817b..8b982523 100644 --- a/notebooks/final_run.ipynb +++ b/notebooks/final_run.ipynb @@ -2,10 +2,8 @@ "cells": [ { "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, + "execution_count": 1, + "metadata": {}, "outputs": [], "source": [ "from sec_certs.dataset import CCDataset\n", @@ -16,74 +14,159 @@ }, { "cell_type": "code", - "execution_count": null, - "outputs": [], + "execution_count": 2, + "metadata": { + "pycharm": { + "name": "#%%\n" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "True\n", + "True\n" + ] + } + ], "source": [ "# A directory with a dump of the documents that will enrich the dataset.\n", "doc_dump_dir = Path(\"cc_certs_03_10_2022\")\n", + "print(doc_dump_dir.exists())\n", "\n", "# An output directory for the dataset.\n", - "dataset_dir = Path(\"cc_03_10_2022\")" - ], + "dataset_dir = Path(\"cc_03_10_2022\")\n", + "print(dataset_dir.exists())" + ] + }, + { + "cell_type": "code", + "execution_count": 3, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tesseract 5.2.0\n", + " leptonica-1.82.0\n", + " libgif 5.2.1 : libjpeg 8d (libjpeg-turbo 2.1.3) : libpng 1.6.38 : libtiff 4.4.0 : zlib 1.2.12 : libwebp 1.2.4 : libopenjp2 2.5.0\n", + " Found AVX2\n", + " Found AVX\n", + " Found FMA\n", + " Found SSE4.1\n", + " Found OpenMP 201511\n", + " Found libarchive 3.6.1 zlib/1.2.12 liblzma/5.2.5 bz2lib/1.0.8 liblz4/1.9.3 libzstd/1.5.2\n", + " Found libcurl/7.85.0 OpenSSL/1.1.1q zlib/1.2.12 brotli/1.0.9 zstd/1.5.2 libidn2/2.3.3 libpsl/0.21.1 (+libidn2/2.3.0) libssh2/1.10.0 nghttp2/1.50.0\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "pdftotext version 22.09.0\n", + "Copyright 2005-2022 The Poppler Developers - http://poppler.freedesktop.org\n", + "Copyright 1996-2011, 2022 Glyph & Cog, LLC\n" + ] + } + ], "source": [ "# Print tool versions\n", "subprocess.run([\"pdftotext\", \"-v\"])\n", "subprocess.run([\"tesseract\", \"-v\"]);" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 4, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, + }, "outputs": [], "source": [ "# Create the dataset\n", "dset = CCDataset(root_dir=dataset_dir, name=\"cc\", description=\"Final run on 03.10.2022\")" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 5, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:06<00:00, 3.01s/it]\n", + "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:02<00:00, 1.00s/it]\n", + "The CSV cc_03_10_2022/web/cc_products_active.csv contains 8 duplicates by the primary key.\n", + "The CSV cc_03_10_2022/web/cc_products_archived.csv contains 10 duplicates by the primary key.\n", + "When merging certificates with dgst b26ce64e0c677e3d, the following mismatch occured: Attribute=security_level, self[security_level]={'ALC_DVS.1', 'EAL2+'}, other[security_level]={'EAL2'}\n", + "When merging certificates with dgst 7f043162f88a1c3a, the following mismatch occured: Attribute=not_valid_after, self[not_valid_after]=2024-09-19, other[not_valid_after]=2024-09-18\n", + "When merging certificates with dgst 109eb2158ca6a2f9, the following mismatch occured: Attribute=security_level, self[security_level]={'ADV_IMP.2', 'EAL4+', 'AVA_VLA.4', 'ATE_DPT.2', 'AVA_MSU.3'}, other[security_level]={'ADV_DVS.2', 'AVA_MSU.3', 'EAL5+', 'AVA_VLA.4'}\n", + "When merging certificates with dgst c437d26a62a22c39, the following mismatch occured: Attribute=not_valid_after, self[not_valid_after]=2019-11-19, other[not_valid_after]=2018-05-07\n" + ] + } + ], "source": [ "# Get the metadata\n", "dset.get_certs_from_web()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Duplicate entry in PP dataset: ('Protection Profile for Enterprise Security Management Policy Management', 'https://www.commoncriteriaportal.org/files/ppfiles/PP_ESM_PM_V1.4.pdf')\n", + "Duplicate entry in PP dataset: ('Stateful Traffic Filter Firewall Extended Package for Network Device Protection Profile', 'https://www.commoncriteriaportal.org/files/ppfiles/PP_ND_TFFWEP_V1.0.pdf')\n", + "Duplicate entry in PP dataset: ('Stateful Traffic Filter Firewall Extended Package for Network Device Protection Profile', 'https://www.commoncriteriaportal.org/files/ppfiles/PP_ND_TFFWEP_V1.0.pdf')\n", + "Duplicate entry in PP dataset: ('Public Key-Enabled Application Family of Protection Profiles', 'https://www.commoncriteriaportal.org/files/ppfiles/PP_VID3004-PP.pdf')\n", + "Duplicate entry in PP dataset: ('Protection Profile for Wireless Local Area Network (WLAN) Access Systems', 'https://www.commoncriteriaportal.org/files/ppfiles/PP_WLAN_AS_V1.0.pdf')\n", + "Duplicate entry in PP dataset: ('PC Client Specific Trusted Platform Module Family 1.2; Level 2, Version 1.1', 'https://www.commoncriteriaportal.org/files/ppfiles/pp0030b.pdf')\n", + "Duplicate entry in PP dataset: ('Protection Profile for Enterprise Security Management Access Control', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_esm_ac_v2.1.pdf')\n", + "Duplicate entry in PP dataset: ('U.S. Government Protection Profile Intrusion Detection System - System for Basic Robustness Environments, Version 1.7', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_ids_sys_br_v1.7.pdf')\n", + "Duplicate entry in PP dataset: ('Network Device Protection Profile Extended Package SIP Server', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_nd_sip_ep_v1.1.pdf')\n", + "Duplicate entry in PP dataset: ('Network Device Protection Profile Extended Package VPN Gateway', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_nd_vpn_gw_ep_v1.1.pdf')\n", + "Duplicate entry in PP dataset: ('Extended Package for Secure Shell (SSH), Version 1.0', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_ssh_ep_v1.0.pdf')\n", + "Duplicate entry in PP dataset: ('Protection Profile for Software Full Disk Encryption', 'https://www.commoncriteriaportal.org/files/ppfiles/pp_swfde_v1.1.pdf')\n", + "Duplicate entry in PP dataset: ('Smart Card Security User Group - Smart Card Protection Profile, Version 3.0', 'https://www.commoncriteriaportal.org/files/ppfiles/scsugpp.pdf')\n" + ] + } ], + "source": [ + "# Process the profiles?\n", + "dset.process_protection_profiles()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, + }, "outputs": [], "source": [ "# Enrich the dataset with the pre-downloaded PDFs (collected over multiple runs to fill in the timeouts and disappearances).\n", + "dset.reports_pdf_dir.mkdir(parents=True, exist_ok=True)\n", + "dset.targets_pdf_dir.mkdir(parents=True, exist_ok=True)\n", "for cert in dset:\n", " report_pdf = doc_dump_dir / \"report\" / \"pdf\" / f\"{cert.dgst}.pdf\"\n", " if report_pdf.exists():\n", @@ -91,111 +174,639 @@ " cert.state.report_download_ok = True\n", " target_pdf = doc_dump_dir / \"target\" / \"pdf\" / f\"{cert.dgst}.pdf\"\n", " if target_pdf.exists():\n", - " shutil.copy(target_pdf, cert.state.target_pdf_path)\n", - " cert.state.target_download_ok = True" - ], + " shutil.copy(target_pdf, cert.state.st_pdf_path)\n", + " cert.state.st_download_ok = True" + ] + }, + { + "cell_type": "code", + "execution_count": 8, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Downloading reports: 0%| | 0/15 [00:00<?, ?it/s]Cert dgst: e27eb9efbd67c4f7 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/Document%20SAFER%20Blue%202%20Security%20Target%20V1.10_???.pdf, code: nok\n", + "Cert dgst: 8ac22970bd8042d2 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid4016b-vr.pdf, code: nok\n", + "Cert dgst: 82fcce2db9ef6063 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/emCA%20Certification%20Report%20v1.0.pdf, code: nok\n", + "Cert dgst: d79ecebfe21f2144 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid10024a-vr.pdf, code: nok\n", + "Cert dgst: 305af0eec85bb856 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/[KECS-CR-13-28]%20AhnLab%20TrusGuard%20V2.2(??).pdf, code: nok\n", + "Cert dgst: a90d78924e91dc6c failed to download report from https://www.commoncriteriaportal.org/files/epfiles/ANSSI-CC_2010-03en1.pdf, code: nok\n", + "Cert dgst: 02482228eb547c15 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid4016a-vr.pdf, code: nok\n", + "Downloading reports: 47%|███████████████████████████████████████████████▏ | 7/15 [00:01<00:01, 6.99it/s]Cert dgst: ace7ea6d7f58dbb1 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/0308a_pdf.pdf, code: nok\n", + "Cert dgst: 391c8b9254ed6ed9 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/silverpeak-v31-cert-eng.pdf, code: nok\n", + "Cert dgst: 811ca609aebe2e96 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid10355-vr.pdf, code: nok\n", + "Cert dgst: d0d0dfe4860db6be failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid1023-vr.pdf, code: nok\n", + "Cert dgst: 6af4a27251001715 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid10491-vr, code: nok\n", + "Cert dgst: 7d074a56ee50aec4 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/st_vid3012a-vr.pdf, code: nok\n", + "Cert dgst: 1a8ac8fbe5bfcda9 failed to download report from https://www.commoncriteriaportal.org/files/epfiles/SERTIT-017_CR_Thinklogical_VX160_KVM_Matrix_switch_v1.01.pdf, code: nok\n", + "Downloading reports: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:03<00:00, 4.99it/s]\n", + "Downloading targets: 0%| | 0/14 [00:00<?, ?it/s]Cert dgst: e27eb9efbd67c4f7 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/Document%20SAFER%20Blue%202%20Security%20Target%20V1.10_???.pdf, code: nok\n", + "Cert dgst: 305af0eec85bb856 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/CC-TG22-???????_??.pdf, code: nok\n", + "Cert dgst: a90d78924e91dc6c failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/ANSSI-CC-cible_2010-03en1.pdf, code: nok\n", + "Cert dgst: 02482228eb547c15 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/st_vid4016a-st.pdf, code: nok\n", + "Downloading targets: 29%|████████████████████████████▊ | 4/14 [00:01<00:02, 3.99it/s]Cert dgst: 811ca609aebe2e96 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/st_vid10355-st.pdf, code: nok\n", + "Cert dgst: 391c8b9254ed6ed9 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/silverpeak-v31-sec-eng.pdf, code: nok\n", + "Cert dgst: 6af4a27251001715 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/st_vid10491-st, code: nok\n", + "Cert dgst: 1a8ac8fbe5bfcda9 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/ThinklogicalSecurityTarget_3_6_VX1601.pdf, code: nok\n", + "Downloading targets: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 14/14 [00:03<00:00, 4.65it/s]\n" + ] + } + ], "source": [ "# Try to download last missing (or ones not present in the pre-downloaded)\n", "dset.download_all_pdfs(fresh=False)" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 9, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" + }, + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Converting reports to txt: 2%|█▋ | 95/5112 [00:07<06:21, 13.17it/s]Error when converting pdf->txt: poppler error creating document\n", + "Converting reports to txt: 2%|██ | 115/5112 [00:08<06:00, 13.86it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/bfc86f14e2484335.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/bfc86f14e2484335.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: bfc86f14e2484335 failed to convert report pdf->txt\n", + "Converting reports to txt: 4%|███▏ | 181/5112 [00:11<04:31, 18.14it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/1ee7ecee9e7e131c.pdf\n", + "Converting reports to txt: 4%|███▍ | 194/5112 [00:12<05:14, 15.65it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/d8c205b4924f91b3.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/20874d4fa6e4c878.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/f8a79eb20ade29af.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3477723044183b31.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/82c24f729c2e0092.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b3757b6bb5f884d4.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/0f9468a2e263d3a3.pdf\n", + "Converting reports to txt: 4%|███▋ | 206/5112 [00:27<05:55, 13.79it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/66bbd8fb83f0abbb.pdf\n", + "Converting reports to txt: 4%|███▌ | 207/5112 [00:48<1:18:01, 1.05it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/e1daa354ae5a61fd.pdf\n", + "Converting reports to txt: 4%|███▌ | 208/5112 [04:37<12:22:36, 9.09s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/7a0e44767b51f0c4.pdf\n", + "Converting reports to txt: 4%|███▌ | 210/5112 [04:50<11:56:08, 8.77s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/051066781c36ad55.pdf\n", + "Converting reports to txt: 4%|███▋ | 211/5112 [05:08<12:55:52, 9.50s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/03bce905b71945aa.pdf\n", + "Converting reports to txt: 4%|███▋ | 212/5112 [05:09<11:42:39, 8.60s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/0286c223fc4e626a.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/559e4549a852aab2.pdf\n", + "Converting reports to txt: 4%|███▊ | 216/5112 [05:19<7:48:52, 5.75s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/c5e25f90c7006546.pdf\n", + "Converting reports to txt: 4%|███▊ | 218/5112 [06:39<24:17:02, 17.86s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/744a7a202d909323.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/449c74a92ebb61a4.pdf\n", + "Converting reports to txt: 4%|███▋ | 220/5112 [41:28<455:51:29, 335.46s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/c80801f9a71b030e.pdf\n", + "Converting reports to txt: 6%|█████▊ | 332/5112 [41:37<2:39:36, 2.00s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/852cad2f53bda148.pdf\n", + "Converting reports to txt: 7%|██████ | 347/5112 [41:38<1:49:37, 1.38s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b0deb8e9d0026b64.pdf\n", + "Converting reports to txt: 7%|██████ | 348/5112 [41:53<2:21:55, 1.79s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/56be1d745bbb4994.pdf\n", + "Converting reports to txt: 9%|███████▊ | 438/5112 [42:04<14:48, 5.26it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/af6767c887ae930a.pdf\n", + "Converting reports to txt: 9%|████████ | 453/5112 [42:22<11:43, 6.62it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/d2f75cdaeb322e7f.pdf\n", + "Converting reports to txt: 9%|███████▉ | 454/5112 [42:34<1:17:44, 1.00s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/d7300e1bfafed26e.pdf\n", + "Converting reports to txt: 9%|███████▉ | 457/5112 [44:00<5:15:52, 4.07s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/7015af58766db091.pdf\n", + "Converting reports to txt: 9%|███████▉ | 463/5112 [45:54<10:28:38, 8.11s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/85328590c0d7273f.pdf\n", + "Converting reports to txt: 9%|████████▏ | 472/5112 [45:59<5:49:23, 4.52s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/e56e14e8cbf89e3c.pdf\n", + "Converting reports to txt: 9%|████████▎ | 474/5112 [46:03<5:22:17, 4.17s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/4844355021ea22f1.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/21a1deda31c3e213.pdf\n", + "Converting reports to txt: 9%|████████▎ | 475/5112 [46:09<5:35:16, 4.34s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/d8aff63d56506605.pdf\n", + "Converting reports to txt: 9%|████████▏ | 476/5112 [46:47<10:25:46, 8.10s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/aca070da96add3b6.pdf\n", + "Converting reports to txt: 9%|████████▍ | 485/5112 [47:21<6:41:42, 5.21s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/c8982f2e8de39b22.pdf\n", + "Converting reports to txt: 10%|████████▍ | 487/5112 [47:22<5:36:04, 4.36s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/977b04d04def60a7.pdf\n", + "Converting reports to txt: 10%|████████▌ | 492/5112 [47:56<6:50:08, 5.33s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/6eeed6fefb1f0243.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/62313881916550ca.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/6f8d7a6a1dea6a3a.pdf\n", + "Converting reports to txt: 10%|████████▌ | 495/5112 [49:13<13:25:37, 10.47s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/e6cffd14e732a030.pdf\n", + "Converting reports to txt: 10%|████████▌ | 499/5112 [50:08<15:02:09, 11.73s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/47913a485c3c8a18.pdf\n", + "Converting reports to txt: 10%|████████▌ | 501/5112 [50:09<11:42:57, 9.15s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b0b7b073ca2dfe5f.pdf\n", + "Converting reports to txt: 10%|████████▋ | 502/5112 [50:14<10:47:14, 8.42s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/60f3bd10ee9be85b.pdf\n", + "Converting reports to txt: 10%|████████▋ | 503/5112 [50:54<17:36:40, 13.76s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/5c3806bf79eeab7f.pdf\n", + "Converting reports to txt: 10%|████████▊ | 511/5112 [52:08<13:44:26, 10.75s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/4c9468f20fdb04f7.pdf\n", + "Converting reports to txt: 10%|████████▉ | 516/5112 [52:09<8:18:32, 6.51s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/9ee9f3c598318ae5.pdf\n", + "Converting reports to txt: 11%|█████████▍ | 543/5112 [52:29<1:56:00, 1.52s/it]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/afde7a688dcc5c83.pdf\n", + "Converting reports to txt: 17%|███████████████▏ | 850/5112 [53:26<07:47, 9.11it/s]Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/98668cafb8dda26f.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/4de4a9f436958574.pdf\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/02958808b57334f0.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/98668cafb8dda26f.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 98668cafb8dda26f failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/4de4a9f436958574.pdf, using garbage: pdftoppm failed: 1\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/02958808b57334f0.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 02958808b57334f0 failed to convert report pdf->txt\n", + "Cert dgst: 4de4a9f436958574 failed to convert report pdf->txt\n", + "Converting reports to txt: 22%|████████████████████ | 1139/5112 [53:48<04:11, 15.78it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/9903c89cbb35eec1.pdf\n", + "Converting reports to txt: 24%|█████████████████████▋ | 1234/5112 [53:55<04:44, 13.62it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/1faf7bf1f74a1851.pdf\n", + "Converting reports to txt: 28%|████████████████████████▊ | 1409/5112 [54:08<04:12, 14.66it/s]Error when converting pdf->txt: poppler error creating document\n", + "Converting reports to txt: 28%|█████████████████████████ | 1427/5112 [54:09<04:11, 14.66it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/422dc5758723c7d1.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/422dc5758723c7d1.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 422dc5758723c7d1 failed to convert report pdf->txt\n", + "Converting reports to txt: 32%|████████████████████████████▍ | 1615/5112 [54:22<03:35, 16.21it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b93dfa0a8ec3609c.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/6ed5861434d5fed9.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/209e2d18e1fa0cca.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3df01446a2b92093.pdf\n", + "Converting reports to txt: 35%|███████████████████████████████▏ | 1770/5112 [54:38<06:44, 8.26it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3e5591d086a54905.pdf\n", + "Converting reports to txt: 36%|████████████████████████████████▌ | 1852/5112 [54:44<04:35, 11.85it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/d3568613c552f9e8.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/d3568613c552f9e8.pdf, using garbage: pdftoppm failed: 99\n", + "Converting reports to txt: 38%|██████████████████████████████████▏ | 1941/5112 [54:53<04:42, 11.24it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/822e5f25e7c4631e.pdf\n", + "Converting reports to txt: 38%|██████████████████████████████████▌ | 1965/5112 [55:00<11:07, 4.71it/s]Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/2d05e976e1adf696.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/2d05e976e1adf696.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 2d05e976e1adf696 failed to convert report pdf->txt\n", + "Converting reports to txt: 41%|█████████████████████████████████████▏ | 2112/5112 [55:09<03:26, 14.54it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/69d373903e9635ef.pdf\n", + "Converting reports to txt: 42%|█████████████████████████████████████▊ | 2146/5112 [55:13<04:25, 11.18it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/ae1b80e9cccec491.pdf\n", + "Converting reports to txt: 43%|██████████████████████████████████████▎ | 2178/5112 [55:25<11:34, 4.22it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/21d5f1b05e1ba491.pdf\n", + "Converting reports to txt: 47%|█████████████████████████████████████████▉ | 2383/5112 [55:53<03:52, 11.72it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3f8cee6d5bee5397.pdf\n", + "Converting reports to txt: 56%|██████████████████████████████████████████████████▋ | 2879/5112 [56:42<04:16, 8.72it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/7e32023021d5aad2.pdf\n", + "Converting reports to txt: 59%|████████████████████████████████████████████████████▉ | 3010/5112 [56:58<03:20, 10.50it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b43100f226a61f53.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/b43100f226a61f53.pdf, using garbage: pdftoppm failed: 99\n", + "Converting reports to txt: 75%|███████████████████████████████████████████████████████████████████▌ | 3836/5112 [58:04<01:24, 15.13it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/6db03eff148934a4.pdf\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/f9c8da9deff77ab5.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/03cc150ce40cf816.pdf\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Error during OCR of cc_03_10_2022/certs/reports/pdf/f9c8da9deff77ab5.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: f9c8da9deff77ab5 failed to convert report pdf->txt\n", + "Converting reports to txt: 76%|████████████████████████████████████████████████████████████████████▌ | 3896/5112 [58:08<01:13, 16.65it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3570791ff9c92912.pdf\n", + "Converting reports to txt: 77%|█████████████████████████████████████████████████████████████████████▍ | 3947/5112 [58:11<01:21, 14.22it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/ed886279d0d61096.pdf\n", + "Converting reports to txt: 86%|█████████████████████████████████████████████████████████████████████████████▍ | 4399/5112 [58:56<00:59, 11.91it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/c763b37bb95517e9.pdf\n", + "Converting reports to txt: 86%|█████████████████████████████████████████████████████████████████████████████▋ | 4416/5112 [58:57<00:54, 12.77it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/40640508ac3a37f2.pdf\n", + "Converting reports to txt: 87%|██████████████████████████████████████████████████████████████████████████████ | 4433/5112 [58:59<00:50, 13.40it/s]Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/7147c2f70d983d57.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/7147c2f70d983d57.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 7147c2f70d983d57 failed to convert report pdf->txt\n", + "Converting reports to txt: 95%|█████████████████████████████████████████████████████████████████████████████████████▎ | 4843/5112 [59:31<00:22, 12.22it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/3ad7749ef678ce95.pdf\n", + "Converting reports to txt: 96%|██████████████████████████████████████████████████████████████████████████████████████ | 4888/5112 [59:34<00:14, 15.80it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/1683817e5db17d9c.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/b762fcb2983aa148.pdf\n", + "Converting reports to txt: 96%|██████████████████████████████████████████████████████████████████████████████████████▍ | 4911/5112 [59:36<00:15, 12.93it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/cc681ca95621a6db.pdf\n", + "Converting reports to txt: 96%|██████████████████████████████████████████████████████████████████████████████████████▋ | 4924/5112 [59:37<00:14, 12.83it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/889693d2b11bdfaf.pdf\n", + "Converting reports to txt: 97%|██████████████████████████████████████████████████████████████████████████████████████▉ | 4941/5112 [59:38<00:13, 12.37it/s]Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/876cb2fe02017f3f.pdf\n", + "Converting reports to txt: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 5112/5112 [59:57<00:00, 1.42it/s]\n", + "Converting targets to txt: 2%|██ | 116/5034 [00:26<18:20, 4.47it/s]Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/bfc86f14e2484335.pdf\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/bfc86f14e2484335.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: bfc86f14e2484335 failed to convert security target pdf->txt\n", + "Converting targets to txt: 10%|█████████▎ | 518/5034 [02:36<21:29, 3.50it/s]Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/4c9468f20fdb04f7.pdf\n", + "Converting targets to txt: 10%|█████████▍ | 525/5034 [02:41<32:08, 2.34it/s]Error during OCR of cc_03_10_2022/certs/targets/pdf/4c9468f20fdb04f7.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 4c9468f20fdb04f7 failed to convert security target pdf->txt\n", + "Converting targets to txt: 21%|███████████████████ | 1066/5034 [05:00<10:51, 6.09it/s]Error when converting pdf->txt: poppler error creating document\n", + "Converting targets to txt: 21%|███████████████████▏ | 1074/5034 [05:01<10:50, 6.08it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/a2b962c7f1d2bc56.pdf\n", + "Converting targets to txt: 21%|███████████████████▎ | 1081/5034 [05:02<10:34, 6.23it/s]Error during OCR of cc_03_10_2022/certs/targets/pdf/a2b962c7f1d2bc56.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: a2b962c7f1d2bc56 failed to convert security target pdf->txt\n", + "Converting targets to txt: 28%|█████████████████████████▎ | 1414/5034 [06:30<13:27, 4.48it/s]Error when converting pdf->txt: poppler error creating document\n", + "Converting targets to txt: 28%|█████████████████████████▍ | 1422/5034 [06:33<17:06, 3.52it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/422dc5758723c7d1.pdf\n", + "Converting targets to txt: 28%|█████████████████████████▌ | 1429/5034 [06:35<15:29, 3.88it/s]Error during OCR of cc_03_10_2022/certs/targets/pdf/422dc5758723c7d1.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 422dc5758723c7d1 failed to convert security target pdf->txt\n", + "Converting targets to txt: 31%|████████████████████████████▎ | 1583/5034 [07:15<16:44, 3.44it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/063d3805a3b12930.pdf\n", + "Converting targets to txt: 33%|█████████████████████████████▌ | 1653/5034 [07:31<11:11, 5.03it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/2f4a41e8a5dfac6a.pdf\n", + "Converting targets to txt: 33%|██████████████████████████████ | 1684/5034 [07:36<10:06, 5.52it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/504258938266b87f.pdf\n", + "Converting targets to txt: 36%|███████████████████████████████▉ | 1789/5034 [08:01<11:47, 4.59it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/de85ff4c31069f12.pdf\n", + "Converting targets to txt: 37%|█████████████████████████████████ | 1851/5034 [08:16<12:16, 4.32it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/d3568613c552f9e8.pdf\n", + "Converting targets to txt: 37%|█████████████████████████████████▏ | 1855/5034 [08:17<12:45, 4.15it/s]Error during OCR of cc_03_10_2022/certs/targets/pdf/d3568613c552f9e8.pdf, using garbage: pdftoppm failed: 99\n", + "Converting targets to txt: 40%|████████████████████████████████████ | 2018/5034 [08:56<13:00, 3.86it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/b4bc79d8a558c7cf.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/09b43147f1307352.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/ce987167d42db722.pdf\n", + "Converting targets to txt: 40%|████████████████████████████████████▏ | 2022/5034 [08:58<13:34, 3.70it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/c16a92b40550193d.pdf\n", + "Converting targets to txt: 40%|███████████████████████████████████▌ | 2034/5034 [10:13<2:34:56, 3.10s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/2ff761edd4ed9b72.pdf\n", + "Converting targets to txt: 41%|███████████████████████████████████▉ | 2054/5034 [12:03<2:20:59, 2.84s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/9e4d3347efd95ec9.pdf\n", + "Converting targets to txt: 43%|███████████████████████████████████████ | 2185/5034 [12:42<13:25, 3.54it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/ad9ea5a4acf9ac53.pdf\n", + "Converting targets to txt: 44%|██████████████████████████████████████▎ | 2194/5034 [14:51<4:20:08, 5.50s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/28922ef97b2dfaa0.pdf\n", + "Converting targets to txt: 44%|█████████████████████████████████████▉ | 2196/5034 [17:07<17:33:53, 22.28s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/5c715225c805354f.pdf\n", + "Converting targets to txt: 68%|█████████████████████████████████████████████████████████████▌ | 3446/5034 [23:37<06:33, 4.04it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/731102b849e8d104.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/f65cab49ea5422dd.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/863d91c6a2b8e77a.pdf\n", + "Converting targets to txt: 77%|█████████████████████████████████████████████████████████████████████ | 3862/5034 [25:32<04:09, 4.69it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/18e5179ba124af1d.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/bc31fd0273ab72f8.pdf\n", + "Converting targets to txt: 79%|██████████████████████████████████████████████████████████████████████▉ | 3971/5034 [26:03<05:13, 3.39it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/5dfeb0219325989b.pdf\n", + "Converting targets to txt: 79%|███████████████████████████████████████████████████████████████████████ | 3975/5034 [26:05<05:21, 3.29it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/22617e916bad6f53.pdf\n", + "Converting targets to txt: 79%|███████████████████████████████████████████████████████████████████████ | 3978/5034 [26:06<05:33, 3.17it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/6344672e3178f63e.pdf\n", + "Converting targets to txt: 80%|███████████████████████████████████████████████████████████████████████▊ | 4014/5034 [32:17<44:48, 2.64s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/483dc36fcf11b257.pdf\n", + "Converting targets to txt: 80%|██████████████████████████████████████████████████████████████████████▎ | 4024/5034 [33:13<1:15:50, 4.51s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/5885f28f042038c1.pdf\n", + "Converting targets to txt: 80%|████████████████████████████████████████████████████████████████████████▎ | 4048/5034 [33:36<16:35, 1.01s/it]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/7b08ad74a882337c.pdf\n", + "Converting targets to txt: 87%|██████████████████████████████████████████████████████████████████████████████▎ | 4380/5034 [36:12<02:11, 4.97it/s]Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/7147c2f70d983d57.pdf\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/7147c2f70d983d57.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 7147c2f70d983d57 failed to convert security target pdf->txt\n", + "Converting targets to txt: 90%|████████████████████████████████████████████████████████████████████████████████▉ | 4525/5034 [36:56<02:32, 3.33it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/931e1b2a68a1bcd2.pdf\n", + "Converting targets to txt: 92%|██████████████████████████████████████████████████████████████████████████████████▌ | 4615/5034 [37:15<01:37, 4.31it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/16229c97ce083e8c.pdf\n", + "Converting targets to txt: 99%|████████████████████████████████████████████████████████████████████████████████████████▉ | 4977/5034 [38:46<00:13, 4.22it/s]Error when converting pdf->txt: poppler error creating page\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/a552244ec3ca8f60.pdf\n", + "Converting targets to txt: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 5034/5034 [40:44<00:00, 2.06it/s]\n", + "Converting reports to txt: 0%| | 0/8 [00:00<?, ?it/s]Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/4de4a9f436958574.pdf\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/02958808b57334f0.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/bfc86f14e2484335.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/2d05e976e1adf696.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/f9c8da9deff77ab5.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/98668cafb8dda26f.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/422dc5758723c7d1.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/reports/pdf/7147c2f70d983d57.pdf\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/02958808b57334f0.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 02958808b57334f0 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/bfc86f14e2484335.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: bfc86f14e2484335 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/f9c8da9deff77ab5.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: f9c8da9deff77ab5 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/422dc5758723c7d1.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 422dc5758723c7d1 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/7147c2f70d983d57.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 7147c2f70d983d57 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/98668cafb8dda26f.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 98668cafb8dda26f failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/2d05e976e1adf696.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 2d05e976e1adf696 failed to convert report pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/reports/pdf/4de4a9f436958574.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 4de4a9f436958574 failed to convert report pdf->txt\n", + "Converting reports to txt: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:01<00:00, 7.98it/s]\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Converting targets to txt: 0%| | 0/5 [00:00<?, ?it/s]Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/bfc86f14e2484335.pdf\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/422dc5758723c7d1.pdf\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Error when converting pdf->txt: poppler error creating document\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/4c9468f20fdb04f7.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/a2b962c7f1d2bc56.pdf\n", + "Detected garbage during conversion of cc_03_10_2022/certs/targets/pdf/7147c2f70d983d57.pdf\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/a2b962c7f1d2bc56.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: a2b962c7f1d2bc56 failed to convert security target pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/7147c2f70d983d57.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 7147c2f70d983d57 failed to convert security target pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/bfc86f14e2484335.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: bfc86f14e2484335 failed to convert security target pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/422dc5758723c7d1.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 422dc5758723c7d1 failed to convert security target pdf->txt\n", + "Error during OCR of cc_03_10_2022/certs/targets/pdf/4c9468f20fdb04f7.pdf, using garbage: pdftoppm failed: 1\n", + "Cert dgst: 4c9468f20fdb04f7 failed to convert security target pdf->txt\n", + "Converting targets to txt: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:01<00:00, 4.99it/s]\n" + ] } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + ], "source": [ "# Convert all\n", "dset.convert_all_pdfs()" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 5, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" + }, + "scrolled": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Extracting report metadata: 0%| | 0/5104 [00:00<?, ?it/s]Failed to read metadata of certs/reports/pdf/1e91595cd5e7fece.pdf, error: Unexpected escaped string: b'\\x83'\n", + "Failed to read metadata of certs/reports/pdf/451e0806dfcfd29d.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 11%|██████████ | 574/5104 [00:02<00:15, 288.04it/s]Failed to read metadata of certs/reports/pdf/e51bbdd7e3705d61.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 17%|███████████████▍ | 879/5104 [00:06<00:48, 86.25it/s]PdfReadWarning: Multiple definitions in dictionary at byte 0x59564 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x59571 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5957e for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5a3f9 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5a406 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5a413 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5b802 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5b80f for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5b81c for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5c501 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5c50e for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5c51b for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5e732 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5e73f for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x5e74c for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x610ef for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x610fc for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x61109 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x75219 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x75226 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x75233 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x78a0e for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x78a1b for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x78a28 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x798c6 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x798d3 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x798e0 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7d599 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7d5a6 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7d5b3 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7e69a for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7e6a7 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7e6b4 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7f838 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7f845 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x7f852 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x80238 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x80245 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x80252 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x810a5 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x810b2 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x810bf for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x82211 for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x8221e for key /Im21 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x8222b for key /Im21 [generic.py:590]\n", + "Extracting report metadata: 26%|███████████████████████ | 1339/5104 [00:09<00:25, 147.71it/s]Failed to read metadata of certs/reports/pdf/dc54e899ab191a2a.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 34%|██████████████████████████████ | 1742/5104 [00:11<00:20, 165.40it/s]Failed to read metadata of certs/reports/pdf/a62c55533f4e1636.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/reports/pdf/d3568613c552f9e8.pdf, error: EOF marker not found\n", + "Extracting report metadata: 37%|████████████████████████████████▉ | 1912/5104 [00:12<00:19, 165.35it/s]Failed to read metadata of certs/reports/pdf/ea5ffdcf17f6ecf4.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 45%|███████████████████████████████████████▍ | 2290/5104 [00:14<00:16, 173.82it/s]Failed to read metadata of certs/reports/pdf/1c5deb472a197eb6.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/reports/pdf/0f3295c420339dd2.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 50%|███████████████████████████████████████████▉ | 2551/5104 [00:15<00:12, 197.33it/s]Failed to read metadata of certs/reports/pdf/6be07dff9c4ed819.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 56%|█████████████████████████████████████████████████ | 2849/5104 [00:16<00:10, 224.61it/s]Failed to read metadata of certs/reports/pdf/b43100f226a61f53.pdf, error: EOF marker not found\n", + "Extracting report metadata: 61%|█████████████████████████████████████████████████████▋ | 3115/5104 [00:17<00:08, 233.73it/s]Failed to read metadata of certs/reports/pdf/be0806db6fd6bbe8.pdf, error: 'NumberObject' object is not subscriptable\n", + "Failed to read metadata of certs/reports/pdf/35ac4cfd1f62df75.pdf, error: 'NumberObject' object is not subscriptable\n", + "Failed to read metadata of certs/reports/pdf/aaf48074ea1b4bf4.pdf, error: invalid literal for int() with base 10: b'n'\n", + "Failed to read metadata of certs/reports/pdf/206662b82595265b.pdf, error: 'NumberObject' object is not subscriptable\n", + "Failed to read metadata of certs/reports/pdf/989b106f5e63b4d1.pdf, error: invalid literal for int() with base 10: b'n'\n", + "Failed to read metadata of certs/reports/pdf/0160f6becf137107.pdf, error: 'NumberObject' object is not subscriptable\n", + "Extracting report metadata: 65%|████████████████████████████████████████████████████████▊ | 3294/5104 [00:18<00:08, 215.65it/s]Failed to read metadata of certs/reports/pdf/9558a9eaadae855e.pdf, error: PDF metadata unavailable\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Extracting report metadata: 72%|███████████████████████████████████████████████████████████████ | 3657/5104 [00:22<00:12, 118.13it/s]Failed to read metadata of certs/reports/pdf/9114f0f9938e558c.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/reports/pdf/08b09322ee9df0af.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 77%|███████████████████████████████████████████████████████████████████▊ | 3935/5104 [00:23<00:07, 163.39it/s]Failed to read metadata of certs/reports/pdf/518b3066ebfabcd3.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 85%|██████████████████████████████████████████████████████████████████████████▊ | 4339/5104 [00:25<00:04, 180.47it/s]Failed to read metadata of certs/reports/pdf/d455e5408b744b44.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 100%|████████████████████████████████████████████████████████████████████████████████████████| 5104/5104 [00:32<00:00, 158.98it/s]\n", + "Extracting target metadata: 2%|█▍ | 78/5029 [00:01<01:06, 74.44it/s]PdfReadWarning: Multiple definitions in dictionary at byte 0x724b1 for key /Im312 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x724cf for key /Im312 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x724de for key /Im312 [generic.py:590]\n", + "Failed to read metadata of certs/targets/pdf/d47a03be1cb342b1.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/5af5a1b535422b51.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/21d6eff0bfe3971f.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 4%|███▉ | 219/5029 [00:04<01:47, 44.54it/s]Failed to read metadata of certs/targets/pdf/eee469bd6d07f8db.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 6%|█████▋ | 317/5029 [00:08<02:52, 27.27it/s]Failed to read metadata of certs/targets/pdf/c62b878b1ac43df9.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/4c017087976d05eb.pdf, error: EOF marker not found\n", + "Extracting target metadata: 7%|██████ | 339/5029 [00:09<03:04, 25.42it/s]Failed to read metadata of certs/targets/pdf/0dc53ac916660b90.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/e676143c80802a59.pdf, error: EOF marker not found\n", + "Failed to read metadata of certs/targets/pdf/e6e8add5e4db2d9d.pdf, error: EOF marker not found\n", + "Failed to read metadata of certs/targets/pdf/1c9bd4db3d8388f7.pdf, error: EOF marker not found\n", + "Extracting target metadata: 7%|██████▌ | 364/5029 [00:10<03:06, 25.06it/s]Failed to read metadata of certs/targets/pdf/4bede5d2af4cb11f.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 9%|████████ | 452/5029 [00:13<02:44, 27.77it/s]Failed to read metadata of certs/targets/pdf/d2f75cdaeb322e7f.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 10%|████████▌ | 478/5029 [00:14<02:48, 26.97it/s]Failed to read metadata of certs/targets/pdf/c9b0cae8b5784d2d.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/af6767c887ae930a.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 10%|█████████▏ | 515/5029 [00:15<02:32, 29.60it/s]Failed to read metadata of certs/targets/pdf/42d2e68c29d9eef7.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 12%|██████████▊ | 605/5029 [00:17<02:00, 36.65it/s]Failed to read metadata of certs/targets/pdf/44f1f74c09e634cb.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 13%|███████████▌ | 648/5029 [00:18<01:54, 38.12it/s]PdfReadWarning: Multiple definitions in dictionary at byte 0x2ee44 for key /Im59 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x6f7cf for key /Im215 [generic.py:590]\n", + "Extracting target metadata: 19%|█████████████████▍ | 975/5029 [00:32<02:32, 26.58it/s]Failed to read metadata of certs/targets/pdf/3183166f4cb1c37c.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/b224a05ad0f1ec6b.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/0cb80431100b4bd4.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 21%|██████████████████▊ | 1060/5029 [00:33<01:32, 43.08it/s]Failed to read metadata of certs/targets/pdf/14ddeb255e0a1cd2.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 23%|████████████████████▍ | 1157/5029 [00:34<01:06, 58.27it/s]Failed to read metadata of certs/targets/pdf/0c5a0893bb4f17dc.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/c13a0ff38bf1cf86.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 25%|█████████████████████▉ | 1237/5029 [00:35<00:59, 64.22it/s]Failed to read metadata of certs/targets/pdf/e84d854109fc9e59.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/e39bcd3ef3ba2f00.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 26%|███████████████████████▍ | 1321/5029 [00:37<01:12, 51.45it/s]Failed to read metadata of certs/targets/pdf/af478678c6464da0.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 31%|███████████████████████████▉ | 1581/5029 [00:44<01:24, 40.86it/s]PdfReadWarning: Multiple definitions in dictionary at byte 0x21033 for key /Im67 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x21067 for key /Im67 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x21074 for key /Im68 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x21081 for key /Im69 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x2108e for key /Im67 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x210b5 for key /Im67 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x210cf for key /Im67 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x2111d for key /Im91 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3eb3f for key /Im111 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3eb4e for key /Im111 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ebf3 for key /Im121 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ec3e for key /Im133 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ec4d for key /Im135 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ec5c for key /Im137 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ec89 for key /Im135 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3eca7 for key /Im145 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ed10 for key /Im143 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x3ed1f for key /Im149 [generic.py:590]\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "PdfReadWarning: Multiple definitions in dictionary at byte 0x61908 for key /Im173 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x619e9 for key /Im200 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x61a16 for key /Im205 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x61b7e for key /Im220 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x9146a for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x91479 for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x91488 for key /Im325 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x91497 for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x915e1 for key /Im299 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x9160e for key /Im299 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0x9161d for key /Im365 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xad9f8 for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xada07 for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xada25 for key /Im324 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xadb24 for key /Im365 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xadb42 for key /Im299 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xadb51 for key /Im365 [generic.py:590]\n", + "PdfReadWarning: Multiple definitions in dictionary at byte 0xadb9c for key /Im364 [generic.py:590]\n", + "Failed to read metadata of certs/targets/pdf/bbcfe0aee7ea78ea.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/f0bd6a29eee94a2c.pdf, error: PDF metadata unavailable\n", + "Failed to read metadata of certs/targets/pdf/463ecd64b7506048.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 36%|████████████████████████████████ | 1815/5029 [00:47<00:49, 64.98it/s]Failed to read metadata of certs/targets/pdf/d3568613c552f9e8.pdf, error: EOF marker not found\n", + "Extracting target metadata: 42%|████████████████████████████████████▉ | 2089/5029 [00:50<00:36, 79.70it/s]UserWarning: startxref on same line as offset [pdf.py:1787]\n", + "Extracting target metadata: 44%|███████████████████████████████████████▎ | 2223/5029 [00:52<00:38, 73.68it/s]Failed to read metadata of certs/targets/pdf/4d2a177384b23fd6.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 59%|████████████████████████████████████████████████████ | 2945/5029 [01:12<00:46, 44.62it/s]Failed to read metadata of certs/targets/pdf/a83fe0ea2f391ee8.pdf, error: too many values to unpack (expected 2)\n", + "Extracting target metadata: 63%|████████████████████████████████████████████████████████▏ | 3178/5029 [01:17<00:43, 42.20it/s]Failed to read metadata of certs/targets/pdf/907433fbf9e00ce3.pdf, error: Could not find xref table at specified location\n", + "Extracting target metadata: 96%|█████████████████████████████████████████████████████████████████████████████████████▌ | 4837/5029 [01:40<00:02, 95.37it/s]Failed to read metadata of certs/targets/pdf/fc8d2eade14aa446.pdf, error: 'NumberObject' object is not subscriptable\n", + "Extracting target metadata: 98%|███████████████████████████████████████████████████████████████████████████████████████▌ | 4946/5029 [01:42<00:01, 72.77it/s]Failed to read metadata of certs/targets/pdf/a334142059d865a2.pdf, error: PDF metadata unavailable\n", + "Extracting target metadata: 100%|████████████████████████████████████████████████████████████████████████████████████████▊| 5021/5029 [01:43<00:00, 72.76it/s]Failed to read metadata of certs/targets/pdf/a552244ec3ca8f60.pdf, error: EOF marker not found\n", + "Extracting target metadata: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5029/5029 [01:45<00:00, 47.68it/s]\n", + "Extracting report frontpages: 8%|██████▉ | 404/5104 [00:01<00:12, 384.61it/s]WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/4844355021ea22f1.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/4844355021ea22f1.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/d8aff63d56506605.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/21a1deda31c3e213.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/aca070da96add3b6.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/d8aff63d56506605.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/aca070da96add3b6.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/21a1deda31c3e213.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/977b04d04def60a7.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/977b04d04def60a7.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/6eeed6fefb1f0243.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/6eeed6fefb1f0243.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/62313881916550ca.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/6f8d7a6a1dea6a3a.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/62313881916550ca.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/6f8d7a6a1dea6a3a.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/b0b7b073ca2dfe5f.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/47913a485c3c8a18.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/60f3bd10ee9be85b.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/47913a485c3c8a18.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/b0b7b073ca2dfe5f.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/60f3bd10ee9be85b.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/5c3806bf79eeab7f.txt\n", + "WARNING: multiple rules are matching same certification document: /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/reports/txt/5c3806bf79eeab7f.txt\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Extracting report frontpages: 100%|██████████████████████████████████████████████████████████████████████████████████████| 5104/5104 [00:13<00:00, 374.77it/s]\n", + "Extracting target frontpages: 100%|██████████████████████████████████████████████████████████████████████████████████████| 5029/5029 [00:18<00:00, 269.71it/s]\n", + "Extracting report keywords: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5104/5104 [08:49<00:00, 9.64it/s]\n", + "Extracting target keywords: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5029/5029 [32:59<00:00, 2.54it/s]\n", + "Fitting the CPE classifier: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 888243/888243 [00:02<00:00, 413368.35it/s]\n", + "Predicting CPE matches with the classifier: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5126/5126 [02:53<00:00, 29.56it/s]\n", + "parsing cpe matching (by NIST) dictionary: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 397693/397693 [00:26<00:00, 15145.61it/s]\n", + "Building-up lookup dictionaries for fast CVE matching: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 196860/196860 [00:09<00:00, 19964.38it/s]\n", + "Computing related CVES: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 704/704 [00:00<00:00, 79643.70it/s]\n", + "WARNING:root:There were total of 153 certificates skipped due to duplicity\n" + ] } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + ], "source": [ "# Analyze all\n", "dset.analyze_certificates()" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 6, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } - }, - { - "cell_type": "code", - "execution_count": null, - "outputs": [], + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Downloading reports: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 457/457 [01:40<00:00, 4.56it/s]\n", + "Downloading targets: 41%|██████████████████████████████████████████████████████████████▌ | 188/457 [01:13<03:08, 1.43it/s]ERROR:sec_certs.sample.certificate:Cert dgst: cert_4d38305c4a2ee035_update_d37e22d00eafccc0 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/0976ra1b_pdf.pdf, code: 408\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_bcac7e3f9f614ec6_update_531b2055de9b34f2 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/XSMART%20e-Passport%20V1.3_R4_ASE_LITE(ENG)_v1.0.1.pdf, code: 408\n", + "Downloading targets: 42%|███████████████████████████████████████████████████████████████▏ | 190/457 [01:22<08:11, 1.84s/it]ERROR:sec_certs.sample.certificate:Cert dgst: cert_a9004216663480de_update_f11191787e65fa44 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/0938ma1b_pdf.pdf, code: 408\n", + "ERROR:sec_certs.utils.helpers:Failed to download from https://www.commoncriteriaportal.org/files/epfiles/0915ma3b_pdf.pdf; HTTPSConnectionPool(host='www.commoncriteriaportal.org', port=443): Read timed out.\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_73632a66aceeb90e_update_c6e93ff837a633e2 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/0915ma3b_pdf.pdf, code: nok\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_2a91f42389fda90d_update_475e73ebad1af7a2 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/XSMART%20e-Passport%20V1.4_ASE(BAC%20with%20AA)_ENG_V1.7.pdf, code: 408\n", + "ERROR:sec_certs.utils.helpers:Failed to download from https://www.commoncriteriaportal.org/files/epfiles/0945V2ma2b_pdf.pdf; HTTPSConnectionPool(host='www.commoncriteriaportal.org', port=443): Read timed out.\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_5103648897ba1b3a_update_a05293df88927dad failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/0945V2ma2b_pdf.pdf, code: nok\n", + "ERROR:sec_certs.utils.helpers:Failed to download from https://www.commoncriteriaportal.org/files/epfiles/0915ma1b_pdf.pdf; HTTPSConnectionPool(host='www.commoncriteriaportal.org', port=443): Read timed out.\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_73632a66aceeb90e_update_8ce0c847737c2de3 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/0915ma1b_pdf.pdf, code: nok\n", + "ERROR:sec_certs.utils.helpers:Failed to download from https://www.commoncriteriaportal.org/files/epfiles/anssi_cible_2016_20_lite.pdf; HTTPSConnectionPool(host='www.commoncriteriaportal.org', port=443): Read timed out.\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_fe46772a18258cb2_update_90d86c50dc8c1166 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/anssi_cible_2016_20_lite.pdf, code: nok\n", + "Downloading targets: 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 342/457 [02:44<00:38, 2.99it/s]ERROR:sec_certs.sample.certificate:Cert dgst: cert_5ab17f47ec6820f3_update_0cbfc8dd71545605 failed to download ST from https://www.commoncriteriaportal.org/files/epfiles/[ST]%20Samsung%20Multifunction%20MultiXpress%20X4300%20K4350_v1.4(???).pdf, code: nok\n", + "Downloading targets: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 457/457 [03:24<00:00, 2.23it/s]\n", + "Converting reports to txt: 0%| | 0/457 [00:00<?, ?it/s]WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_dbaf9789160ca414_update_05b659f9e1f5e5a6.pdf\n", + "WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_6785be05d030779b_update_bec315e0f592c9c3.pdf\n", + "Converting reports to txt: 16%|███████████████████████▊ | 74/457 [00:02<00:10, 35.50it/s]WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_b891647233f3f188_update_66d87388520b9048.pdf\n", + "Converting reports to txt: 90%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 410/457 [00:08<00:00, 47.76it/s]ERROR:sec_certs.utils.pdf:Error when converting pdf->txt: poppler error creating document\n", + "WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_8ba5d4d02ea73d3d_update_d879046e9be61396.pdf\n", + "ERROR:sec_certs.utils.pdf:Error during OCR of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_8ba5d4d02ea73d3d_update_d879046e9be61396.pdf, using garbage: pdftoppm failed: 1\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_8ba5d4d02ea73d3d_update_d879046e9be61396 failed to convert report pdf->txt\n", + "Converting reports to txt: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 457/457 [00:21<00:00, 21.21it/s]\n", + "Converting targets to txt: 36%|█████████████████████████████████████████████████████ | 163/448 [00:42<00:42, 6.71it/s]WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/targets/pdf/cert_09b43147f1307352_update_a1ff8f3d472941f7.pdf\n", + "Converting targets to txt: 74%|████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 333/448 [01:21<00:20, 5.51it/s]WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/targets/pdf/cert_bd5c7bb29151de01_update_070f8e523f3deba1.pdf\n", + "WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/targets/pdf/cert_ef9565620c399b7e_update_b169fd5fee2eb72b.pdf\n", + "Converting targets to txt: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 448/448 [04:58<00:00, 1.50it/s]\n", + "ERROR:sec_certs.utils.pdf:Error when converting pdf->txt: poppler error creating document\n", + "Converting reports to txt: 0%| | 0/1 [00:00<?, ?it/s]WARNING:sec_certs.utils.pdf:Detected garbage during conversion of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_8ba5d4d02ea73d3d_update_d879046e9be61396.pdf\n", + "ERROR:sec_certs.utils.pdf:Error during OCR of /home/jjan/dev/sec-certs/notebooks/cc_03_10_2022/certs/maintenances/reports/pdf/cert_8ba5d4d02ea73d3d_update_d879046e9be61396.pdf, using garbage: pdftoppm failed: 1\n", + "ERROR:sec_certs.sample.certificate:Cert dgst: cert_8ba5d4d02ea73d3d_update_d879046e9be61396 failed to convert report pdf->txt\n", + "Converting reports to txt: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.00s/it]\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Extracting report metadata: 0%| | 0/456 [00:00<?, ?it/s]ERROR:sec_certs.utils.pdf:Failed to read metadata of maintenances/reports/pdf/cert_d455e5408b744b44_update_16f77dbd34439401.pdf, error: PDF metadata unavailable\n", + "Extracting report metadata: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 456/456 [00:01<00:00, 452.87it/s]\n", + "Extracting target metadata: 56%|█████████████████████████████████████████████████████████████████████████████████▉ | 253/448 [00:06<00:04, 39.48it/s]ERROR:sec_certs.utils.pdf:Failed to read metadata of maintenances/targets/pdf/cert_bbc41d7d09e40c0c_update_784535cca61b58a7.pdf, error: too many values to unpack (expected 2)\n", + "Extracting target metadata: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 448/448 [00:09<00:00, 49.53it/s]\n", + "Extracting report frontpages: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 456/456 [00:01<00:00, 453.32it/s]\n", + "Extracting target frontpages: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 448/448 [00:02<00:00, 222.61it/s]\n", + "Extracting report keywords: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 456/456 [00:13<00:00, 34.93it/s]\n", + "Extracting target keywords: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 448/448 [03:05<00:00, 2.41it/s]\n" + ] + }, + { + "data": { + "text/plain": [ + "<sec_certs.dataset.common_criteria.CCDatasetMaintenanceUpdates at 0x7fcd979bb400>" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# And do maintenance updates as well\n", "dset.process_maintenance_updates()" - ], + ] + }, + { + "cell_type": "code", + "execution_count": 7, "metadata": { - "collapsed": false, "pycharm": { "name": "#%%\n" } - } + }, + "outputs": [], + "source": [ + "# Finally, dump it all\n", + "dset.to_json()" + ] }, { "cell_type": "code", "execution_count": null, + "metadata": {}, "outputs": [], - "source": [ - "# Finally, dump it all\n", - "dset.to_json()" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } + "source": [] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", - "version": 2 + "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", - "pygments_lexer": "ipython2", - "version": "2.7.6" + "pygments_lexer": "ipython3", + "version": "3.10.7" } }, "nbformat": 4, - "nbformat_minor": 0 -}
\ No newline at end of file + "nbformat_minor": 1 +} |