docling-parse 7.7.0__cp313-cp313-win_arm64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- docling_parse/__init__.py +42 -0
- docling_parse/pdf_parser.py +1546 -0
- docling_parse/pdf_parsers.cp313-win_arm64.pyd +0 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-0 +134 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-1 +145 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-2 +146 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-3 +151 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-4 +152 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-5 +152 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-6 +152 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-7 +150 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/B5-H +331 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/B5-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/B5pc-H +335 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/B5pc-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS-EUC-H +488 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS-EUC-V +536 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS1-H +235 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS1-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS2-H +158 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/CNS2-V +74 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETHK-B5-H +1326 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETHK-B5-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETen-B5-H +341 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETen-B5-V +89 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETenms-B5-H +77 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/ETenms-B5-V +97 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKdla-B5-H +1132 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKdla-B5-V +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKdlb-B5-H +1014 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKdlb-B5-V +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKgccs-B5-H +647 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKgccs-B5-V +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKm314-B5-H +637 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKm314-B5-V +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKm471-B5-H +787 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKm471-B5-V +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKscs-B5-H +1329 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/HKscs-B5-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UCS2-H +16990 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UCS2-V +88 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF16-H +19146 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF16-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF32-H +19144 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF32-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF8-H +19209 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/UniCNS-UTF8-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/cid2code.txt +19290 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-0 +109 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-1 +117 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-2 +165 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-3 +165 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-4 +195 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/Adobe-GB1-5 +200 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GB-EUC-H +171 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GB-EUC-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GB-H +164 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GB-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBK-EUC-H +4271 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBK-EUC-V +95 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBK2K-H +5323 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBK2K-V +116 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBKp-EUC-H +4270 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBKp-EUC-V +95 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBT-EUC-H +2430 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBT-EUC-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBT-H +2423 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBT-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBTpc-EUC-H +2432 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBTpc-EUC-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBpc-EUC-H +173 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/GBpc-EUC-V +96 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UCS2-H +14319 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UCS2-V +99 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF16-H +14383 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF16-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF32-H +14381 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF32-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF8-H +14586 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/CMap/UniGB-UTF8-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-GB1-5/cid2code.txt +30370 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Identity-0/CMap/Identity-H +337 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Identity-0/CMap/Identity-V +71 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-EUC-H +724 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-EUC-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-H +716 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-RKSJ-H +726 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-RKSJ-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78-V +102 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78ms-RKSJ-H +816 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/78ms-RKSJ-V +153 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/83pv-RKSJ-H +312 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90ms-RKSJ-H +257 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90ms-RKSJ-V +154 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90msp-RKSJ-H +255 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90msp-RKSJ-V +153 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90pv-RKSJ-H +353 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/90pv-RKSJ-V +127 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Add-H +725 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Add-RKSJ-H +736 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Add-RKSJ-V +133 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Add-V +133 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-0 +111 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-1 +111 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-2 +113 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-3 +114 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-4 +138 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-5 +157 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-6 +168 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Adobe-Japan1-7 +166 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/EUC-H +205 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/EUC-V +103 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Ext-H +755 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Ext-RKSJ-H +766 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Ext-RKSJ-V +115 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Ext-V +115 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/H +198 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Hankaku +86 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Hiragana +84 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Katakana +78 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/NWP-H +855 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/NWP-V +123 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/RKSJ-H +208 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/RKSJ-V +103 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/Roman +77 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UCS2-H +8868 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UCS2-HW-H +79 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UCS2-HW-V +277 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UCS2-V +273 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF16-H +14480 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF16-V +303 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF32-H +14478 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF32-V +303 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF8-H +14508 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS-UTF8-V +304 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF16-H +14483 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF16-V +303 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF32-H +14481 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF32-V +303 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF8-H +14511 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJIS2004-UTF8-V +304 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISPro-UCS2-HW-V +285 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISPro-UCS2-V +278 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISPro-UTF8-V +282 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISX0213-UTF32-H +14472 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISX0213-UTF32-V +299 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISX02132004-UTF32-H +14475 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/UniJISX02132004-UTF32-V +299 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/V +103 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/CMap/WP-Symbol +103 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/cid2code.txt +23491 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0208-jp04.txt +6893 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0208-jp90.txt +6889 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0212-jp04.txt +6085 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0212-jp90.txt +6081 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0213-jp04.txt +4378 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Japan1-7/jisx0213-jp90.txt +4379 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-0 +87 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-1 +94 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-2 +120 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-3 +121 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-4 +122 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-5 +123 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-6 +131 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-7 +149 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-8 +163 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/Adobe-KR-9 +165 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/UniAKR-UTF16-H +12594 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/UniAKR-UTF32-H +12588 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/CMap/UniAKR-UTF8-H +12686 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-KR-9/cid2code.txt +22931 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/Adobe-Korea1-0 +114 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/Adobe-Korea1-1 +149 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/Adobe-Korea1-2 +149 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-EUC-H +560 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-EUC-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-H +554 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-Johab-H +4343 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-Johab-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSC-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCms-UHC-H +774 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCms-UHC-HW-H +773 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCms-UHC-HW-V +91 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCms-UHC-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCpc-EUC-H +606 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/KSCpc-EUC-V +92 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UCS2-H +8723 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UCS2-V +93 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF16-H +8893 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF16-V +97 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF32-H +8891 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF32-V +97 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF8-H +8989 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/CMap/UniKS-UTF8-V +97 -0
- docling_parse/pdf_resources/cmap-resources/Adobe-Korea1-2/cid2code.txt +18529 -0
- docling_parse/pdf_resources/cmap-resources/LICENSE.md +28 -0
- docling_parse/pdf_resources/cmap-resources/README.md +353 -0
- docling_parse/pdf_resources/cmap-resources/VERSIONS.txt +207 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/Adobe-Japan2-0 +102 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/Hojo-EUC-H +160 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/Hojo-EUC-V +74 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/Hojo-H +160 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/Hojo-V +74 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UCS2-H +4434 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UCS2-V +73 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF16-H +4466 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF16-V +73 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF32-H +4460 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF32-V +73 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF8-H +4489 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/CMap/UniHojo-UTF8-V +73 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/cid2code.txt +6133 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/jisx0212-jp04.txt +6085 -0
- docling_parse/pdf_resources/cmap-resources/deprecated/Adobe-Japan2-0/jisx0212-jp90.txt +6081 -0
- docling_parse/pdf_resources/cmap-resources.txt +1 -0
- docling_parse/pdf_resources/encodings/macexpert.dat +165 -0
- docling_parse/pdf_resources/encodings/macroman.dat +207 -0
- docling_parse/pdf_resources/encodings/std.dat +149 -0
- docling_parse/pdf_resources/encodings/winansi.dat +220 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Arial.afm +2290 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Arial_Bold.afm +2290 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Arial_Bold_Italic.afm +1838 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Arial_Italic.afm +1875 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Georgia.afm +643 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Georgia_Bold.afm +643 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Georgia_Bold_Italic.afm +643 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Georgia_Italic.afm +643 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Times_New_Roman.afm +2249 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Times_New_Roman_Bold.afm +2247 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Times_New_Roman_Bold_Italic.afm +1847 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Times_New_Roman_Italic.afm +1823 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Trebuchet_MS.afm +754 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Trebuchet_MS_Bold.afm +747 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Trebuchet_MS_Bold_Italic.afm +734 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Trebuchet_MS_Italic.afm +735 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Verdana.afm +1489 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Verdana_Bold.afm +951 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Verdana_Bold_Italic.afm +951 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/Verdana_Italic.afm +951 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Courier-Bold.afm +342 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Courier-BoldOblique.afm +342 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Courier-Oblique.afm +342 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Courier.afm +342 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Helvetica-Bold.afm +2827 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Helvetica-BoldOblique.afm +2827 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Helvetica-Oblique.afm +3051 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Helvetica.afm +3051 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Times-Bold.afm +2588 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Times-BoldItalic.afm +2384 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Times-Italic.afm +2667 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/Times-Roman.afm +2419 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/ZapfDingbats.afm +225 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/times.afm +2599 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/timesbd.afm +2597 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/timesbi.afm +1843 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/timesi.afm +1819 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/verdanab.afm +951 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/duplicates/verdanai.afm +951 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/lucon.afm +722 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/slkscr.afm +277 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/slkscrb.afm +277 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/slkscre.afm +277 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/slkscreb.afm +277 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Courier-Bold.afm +6073 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Courier.afm +6073 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Helvetica-Bold.afm +8959 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Helvetica.afm +9195 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Times-Bold.afm +8690 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Times-Italic.afm +8748 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_Times-Roman.afm +8548 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_arial.afm +6396 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_verdana.afm +11752 -0
- docling_parse/pdf_resources/fonts/custom/Microsoft/undefined/php_verdanab.afm +14963 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmb10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy10.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy5.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy6.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy7.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy8.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbsy9.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx12.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx5.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx6.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx7.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx8.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbx9.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbxsl10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmbxti10.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmcsc10.afm +373 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmcsc8.afm +373 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmcsc9.afm +373 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmdunh10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmex10.afm +193 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmex7.afm +193 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmex8.afm +193 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmex9.afm +193 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmff10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmfi10.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmfib8.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cminch.afm +112 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmitt10.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi10.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi12.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi5.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi6.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi7.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi8.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmi9.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib10.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib5.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib6.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib7.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib8.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmmib9.afm +349 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr12.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr17.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr5.afm +362 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr6.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr7.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr8.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmr9.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsl10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsl12.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsl8.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsl9.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsltt10.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmss10.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmss12.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmss17.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmss8.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmss9.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssbx10.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssdc10.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssi10.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssi12.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssi17.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssi8.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssi9.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssq8.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmssqi8.afm +334 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy10.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy5.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy6.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy7.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy8.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmsy9.afm +211 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtcsc10.afm +186 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtex10.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtex8.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtex9.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmti10.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmti12.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmti7.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmti8.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmti9.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtt10.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtt12.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtt8.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmtt9.afm +187 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmu10.afm +371 -0
- docling_parse/pdf_resources/fonts/custom/TeX/cmvtt10.afm +372 -0
- docling_parse/pdf_resources/fonts/custom/TeX/euex10.afm +82 -0
- docling_parse/pdf_resources/fonts/custom/TeX/euex7.afm +82 -0
- docling_parse/pdf_resources/fonts/custom/TeX/euex8.afm +82 -0
- docling_parse/pdf_resources/fonts/custom/TeX/euex9.afm +82 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufb10.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufb5.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufb7.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufm10.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufm5.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eufm7.afm +128 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurb10.afm +232 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurb5.afm +232 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurb7.afm +232 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurm10.afm +168 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurm5.afm +231 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eurm7.afm +231 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusb10.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusb5.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusb7.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusm10.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusm5.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/eusm7.afm +72 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy10.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy5.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy6.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy7.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy8.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasy9.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lasyb10.afm +40 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lcircle1.afm +122 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lcirclew.afm +122 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lcmss8.afm +332 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lcmssb8.afm +332 -0
- docling_parse/pdf_resources/fonts/custom/TeX/lcmssi8.afm +332 -0
- docling_parse/pdf_resources/fonts/custom/TeX/line10.afm +142 -0
- docling_parse/pdf_resources/fonts/custom/TeX/linew10.afm +142 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam10.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam5.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam6.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam7.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam8.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msam9.afm +181 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm10.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm5.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm6.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm7.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm8.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/msbm9.afm +176 -0
- docling_parse/pdf_resources/fonts/custom/TeX/wncyb10.afm +438 -0
- docling_parse/pdf_resources/fonts/custom/TeX/wncyi10.afm +458 -0
- docling_parse/pdf_resources/fonts/custom/TeX/wncyr10.afm +438 -0
- docling_parse/pdf_resources/fonts/custom/TeX/wncysc10.afm +409 -0
- docling_parse/pdf_resources/fonts/custom/TeX/wncyss10.afm +438 -0
- docling_parse/pdf_resources/fonts/standard/Courier-Bold.afm +342 -0
- docling_parse/pdf_resources/fonts/standard/Courier-BoldOblique.afm +342 -0
- docling_parse/pdf_resources/fonts/standard/Courier-Oblique.afm +342 -0
- docling_parse/pdf_resources/fonts/standard/Courier.afm +342 -0
- docling_parse/pdf_resources/fonts/standard/Helvetica-Bold.afm +2827 -0
- docling_parse/pdf_resources/fonts/standard/Helvetica-BoldOblique.afm +2827 -0
- docling_parse/pdf_resources/fonts/standard/Helvetica-Oblique.afm +3051 -0
- docling_parse/pdf_resources/fonts/standard/Helvetica.afm +3051 -0
- docling_parse/pdf_resources/fonts/standard/Symbol.afm +213 -0
- docling_parse/pdf_resources/fonts/standard/Times-Bold.afm +2588 -0
- docling_parse/pdf_resources/fonts/standard/Times-BoldItalic.afm +2384 -0
- docling_parse/pdf_resources/fonts/standard/Times-Italic.afm +2667 -0
- docling_parse/pdf_resources/fonts/standard/Times-Roman.afm +2419 -0
- docling_parse/pdf_resources/fonts/standard/ZapfDingbats.afm +225 -0
- docling_parse/pdf_resources/glyphs/custom/MathematicalPi/MathematicalPi.dat +503 -0
- docling_parse/pdf_resources/glyphs/custom/MathematicalPi/MathematicalPi.dat.orig +503 -0
- docling_parse/pdf_resources/glyphs/custom/MathematicalPi/MathematicalPi.hex.dat +154 -0
- docling_parse/pdf_resources/glyphs/custom/MathematicalPi/MathematicalPi.uni.dat +349 -0
- docling_parse/pdf_resources/glyphs/custom/MathematicalPi/transform.py +26 -0
- docling_parse/pdf_resources/glyphs/custom/TeX/glyphs_01.dat +351 -0
- docling_parse/pdf_resources/glyphs/custom/TeX/glyphs_02.dat +70 -0
- docling_parse/pdf_resources/glyphs/custom/TeX/glyphs_03.dat +62 -0
- docling_parse/pdf_resources/glyphs/standard/additional.dat +149 -0
- docling_parse/pdf_resources/glyphs/standard/glyphlist.dat +4328 -0
- docling_parse/pdf_resources/glyphs/standard/missing.dat +307 -0
- docling_parse/pdf_resources/glyphs/standard/scripts.dat +5 -0
- docling_parse/pdf_resources/glyphs/standard/zapfdingbats.dat +247 -0
- docling_parse/py.typed +0 -0
- docling_parse/visualize.py +292 -0
- docling_parse-7.7.0.dist-info/METADATA +350 -0
- docling_parse-7.7.0.dist-info/RECORD +450 -0
- docling_parse-7.7.0.dist-info/WHEEL +5 -0
- docling_parse-7.7.0.dist-info/licenses/LICENSE +21 -0
- docling_parse-7.7.0.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
"""docling-parse: Extract text with coordinates from programmatic PDFs."""
|
|
2
|
+
|
|
3
|
+
import locale as _locale
|
|
4
|
+
import logging as _logging
|
|
5
|
+
|
|
6
|
+
_log = _logging.getLogger(__name__)
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
def _ensure_safe_numeric_locale() -> None:
|
|
10
|
+
"""Ensure LC_NUMERIC uses a period as decimal separator.
|
|
11
|
+
|
|
12
|
+
PDF coordinate parsing (both in QPDF's C library and in this
|
|
13
|
+
package's C++ layer) relies on '.' as the decimal separator.
|
|
14
|
+
Locales that use ',' (French, German, Portuguese, etc.) silently
|
|
15
|
+
corrupt every floating-point value extracted from a PDF.
|
|
16
|
+
|
|
17
|
+
This function is called at import time as a defence-in-depth
|
|
18
|
+
measure. The primary fix is in the C++ layer (from_chars), but
|
|
19
|
+
this protects against any locale-sensitive path we may have missed
|
|
20
|
+
— including QPDF's own atof() calls that we cannot patch.
|
|
21
|
+
|
|
22
|
+
See: https://github.com/docling-project/docling/issues/1455
|
|
23
|
+
"""
|
|
24
|
+
try:
|
|
25
|
+
current = _locale.getlocale(_locale.LC_NUMERIC)
|
|
26
|
+
# setlocale returns the *actual* locale string; checking the
|
|
27
|
+
# decimal point via localeconv is the most reliable test.
|
|
28
|
+
conv = _locale.localeconv()
|
|
29
|
+
if conv.get("decimal_point", ".") != ".":
|
|
30
|
+
_locale.setlocale(_locale.LC_NUMERIC, "C")
|
|
31
|
+
_log.info(
|
|
32
|
+
"docling-parse: overrode LC_NUMERIC from %s to 'C' "
|
|
33
|
+
"to prevent PDF coordinate corruption",
|
|
34
|
+
current,
|
|
35
|
+
)
|
|
36
|
+
except (_locale.Error, ValueError):
|
|
37
|
+
# If we can't query or set the locale, the C++ from_chars
|
|
38
|
+
# layer will still protect us.
|
|
39
|
+
pass
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
_ensure_safe_numeric_locale()
|