nlm-ingestor

View on PyPIReverse Dependencies (0)

0.1.5 nlm_ingestor-0.1.5-py3-none-any.whl

Wheel Details

Project: nlm-ingestor
Version: 0.1.5
Filename: nlm_ingestor-0.1.5-py3-none-any.whl
Download: [link]
Size: 716202
MD5: 1a3288e9c04e7450b3796d1bad705585
SHA256: 804540b921c82113c962972eec8ca750f05f4307c9580fe6aba4da43240ebcfc
Uploaded: 2024-01-26 21:17:19 +0000

dist-info

METADATA

Metadata-Version: 2.1
Name: nlm-ingestor
Version: 0.1.5
Summary: Parsers and ingestors for different file types and formats
Author: Ambika Sukla
Author-Email: ambika.sukla[at]nlmatics.com
Home-Page: https://github.com/nlmatics/nlm-ingestor
License: Apache License 2.0
Classifier: Development Status :: 5 - Production/Stable
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Legal Industry
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3 :: Only
Requires-Dist: flask
Requires-Dist: flask-restful
Requires-Dist: flask-jsonpify
Requires-Dist: gunicorn
Requires-Dist: werkzeug
Requires-Dist: tika
Requires-Dist: bs4
Requires-Dist: nltk
Requires-Dist: python-magic
Requires-Dist: numpy
Requires-Dist: tqdm
Requires-Dist: symspellpy (==6.7.0)
Requires-Dist: pandas (==1.2.4)
Requires-Dist: mistune (==2.0.3)
Requires-Dist: lxml (==4.9.1)
Requires-Dist: unidecode
Requires-Dist: nlm-utils
Description-Content-Type: text/markdown
License-File: LICENSE.txt
License-File: NOTICE.txt
[Description omitted; length: 7187 characters]

WHEEL

Wheel-Version: 1.0
Generator: bdist_wheel (0.42.0)
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
nlm_ingestor/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
nlm_ingestor/file_parser/__init__.py sha256=0Ig0YC3ASwLxB7pbqXAc9jnlEQjBCvT_WQ32tjuoYnk 336
nlm_ingestor/file_parser/file_parser.py sha256=AVlu8LWvP-TnOKpNJdtrZL-QTUxKuEt7Zc2SdcbUIZg 230
nlm_ingestor/file_parser/markdown_parser.py sha256=h5edo1IgijrEy25pC8L28mGyk91-mntA4nhnxmqCG5g 5337
nlm_ingestor/file_parser/parser_factory.py sha256=Ulg39ig-Tys7SBaFOPPnsL58WGNZuCo-178vcQ07HDc 888
nlm_ingestor/file_parser/tika_parser.py sha256=M5ZRg7JQZYEWtUWXaHy2V7p2LKzwY_kGVxDF_1nDuJM 1794
nlm_ingestor/ingestion_daemon/__init__.py sha256=yR8nhu1lFSOHpygqRJqFZzKdV95h5K5Bao5_1bu_8HA 864
nlm_ingestor/ingestion_daemon/__main__.py sha256=slIpe7dP1y6r7q2EcwtmmYzi5xZB9IhneR_wNibrwbw 2509
nlm_ingestor/ingestion_daemon/config.py sha256=M-ubOueg1cFxYTq3u7yHbPKjZmSXojbjftw92Y1CtqA 870
nlm_ingestor/ingestor/__init__.py sha256=F-4PMYNwVogsc6QOSBa9uc5yn6pzDL_AbNWR90xvR8M 502
nlm_ingestor/ingestor/block.py sha256=4TICk3os8qxe36y6Mc0rvhbEAI-ArVaWuLT3euoQE20 2564
nlm_ingestor/ingestor/data_loader.py sha256=tgMmziDlZGMU4sE3hjbiojj_4BbGBSRGvokUwIL2Tcc 5283
nlm_ingestor/ingestor/formatter.py sha256=UBXuuFb6Ke7-ah0wvz42WrEAgGVHZzPy0leC8naNZPg 808
nlm_ingestor/ingestor/html_ingestor.py sha256=hApl7jIYPVjtGUDNP_lWGYe8vTJS4vdbpX-wT5Xa09M 13417
nlm_ingestor/ingestor/ingestor_api.py sha256=2m-1-ENwREdrf7HyS4ayKIfEN2FA5cnU8Sk0Rsnsax8 2862
nlm_ingestor/ingestor/line_parser.py sha256=dDNuv7SpLYW0Brrh_YdiLp6fze1U5hHi4DVj4Cub064 31239
nlm_ingestor/ingestor/patterns.py sha256=1KHkEcqzZFPJppAR8YslMfRost_7otMO64rHf4i1Xc8 2993
nlm_ingestor/ingestor/pdf_ingestor.py sha256=3WnrsEtKdIbuUidvoP1jDUws8Yy3hkJjjkps3U-38z8 13350
nlm_ingestor/ingestor/processors.py sha256=SXjicUC7r0oFB4h6qFIeXVY1hYyj77RLv1LrA9cagRA 47221
nlm_ingestor/ingestor/processors_utils.py sha256=Ik_XI5TdxWYbyaG6YOZqbcMc10O3D-gEofN4FFdbiQU 1385
nlm_ingestor/ingestor/sec_html_ingestor.py sha256=rKnDSvcQpJZKItIkoxY4gz40M-HK-TMuwOPPWg_v6UM 9633
nlm_ingestor/ingestor/styling_utils.py sha256=dhjxX5Sf3R0DUrelvQpeZlyQNtHxPf8zjRDMJlOhIEE 26228
nlm_ingestor/ingestor/table_builder.py sha256=24-Ov_sqeDk8LZ2eSPC_mYiiQSXMPTTw7APvhAXx4ow 8195
nlm_ingestor/ingestor/table_parser.py sha256=qr7lExdFkcldC-NiBK5WZPWJglqZ7hgaxAcnZkX1rFs 16796
nlm_ingestor/ingestor/text_ingestor.py sha256=QRjmjmHYn3jfKyUG40JThh4DKYp4de3btZ3YS6-dI08 3807
nlm_ingestor/ingestor/xml_ingestor.py sha256=aTcne6JhtCGoWDhStmM7MfzIM4WrkjV9XTZqEmiI_qs 6590
nlm_ingestor/ingestor/visual_ingestor/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
nlm_ingestor/ingestor/visual_ingestor/block_renderer.py sha256=XNHLTaqyzBHRNo8xgFlxfW18GOGjeUO0yAYBDGjWqAQ 18418
nlm_ingestor/ingestor/visual_ingestor/indent_parser.py sha256=PQsny7v4DdND9ChrIiD2S5eZ8RTq2HjVpF2T-dNQnV8 43531
nlm_ingestor/ingestor/visual_ingestor/new_indent_parser.py sha256=EoMWwSJSPlP52b7q6o7s66uJgLmXkPoft8D1Xmd5xOE 12207
nlm_ingestor/ingestor/visual_ingestor/order_fixer.py sha256=9pyq4-ZSFEwJEgqFXwIaqik3o8i2tH19ZKzIJIN4pYY 35169
nlm_ingestor/ingestor/visual_ingestor/style_utils.py sha256=RsBbBouYB3RVGHzy5W7ju70-510ycCy0kG-CCtVvOW4 10414
nlm_ingestor/ingestor/visual_ingestor/table_parser.py sha256=hQV5sq2Rgh2tFhOQE4vGblq3r5PXia08Cd6DS0UCCgI 51983
nlm_ingestor/ingestor/visual_ingestor/vi_helper_utils.py sha256=wJCoaDJVGw1RtgrMBClQVlsWgcP6gwitsqAuxOzA06E 4581
nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py sha256=qWGghz2qsKnB96ubTIujhkwAEsIC4u35h_EnwhVcMME 260408
nlm_ingestor/ingestor_models/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
nlm_ingestor/ingestor_models/symspell/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
nlm_ingestor/ingestor_utils/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
nlm_ingestor/ingestor_utils/de_duplicate_engine.py sha256=n5OzTsyY2iieBZYy3uRVHsTp_0VFkDiS3VuqM14TbE8 2435
nlm_ingestor/ingestor_utils/ing_named_tuples.py sha256=McGZY4FpanfFMPx3bxHgmtpi0en5ZETCPQtni1_gHbQ 321
nlm_ingestor/ingestor_utils/lru_cache.py sha256=aE2xC-YdlE2PnyCz6a7z2cxWsJ5DqITrkMOsEpzn5Dw 867
nlm_ingestor/ingestor_utils/ner_dict.py sha256=ZE_A3RYIVDp3wLas7xHOwK_c0rMewRmMoSgURisBK8E 10529
nlm_ingestor/ingestor_utils/objects.py sha256=WMp8ac5Du5GIOp7zrrotfSu8jt0Xntkodc4HVowcgWs 473
nlm_ingestor/ingestor_utils/parsing_utils.py sha256=EIqOcdqCYpJqXKY22SvyiRQoI-_HY1RrWFqPAE94LuY 6860
nlm_ingestor/ingestor_utils/spell_utils.py sha256=arKuuIhEAeEvR_mtxkEj-Y2RSwLTQxXd7-XBSySEYvQ 2932
nlm_ingestor/ingestor_utils/utils.py sha256=uxLdhaAFVcm2p7-MlyY4SJFzk3wx5KH70A_r3PqEhiE 10336
nlm_ingestor/ingestor_utils/word_splitter.py sha256=pZ7JKxTbXr-vDeyQBpb7NNzSdzOcqGSZHibHTPI3-ms 4130
nlm_ingestor/ingestor_utils/words.txt sha256=q8UWNhkQDMZ5vZubJdlMqaop7PIg4csrgB5a4EdMnxI 1101488
tests/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/run_ingestor_page_test.py sha256=dlCl6QDNDOVL_Bo_CiVdXWpnBxb8rmoWmSOTIjsox9U 8775
tests/run_ingestor_table_tests.py sha256=FFz0t-JAz_f6W6e6rDZlP2b0KjYL9NnQaLWIkWXEe8A 9577
tests/run_ingestor_test_full_doc.py sha256=8WELpu5t-6L5rr5iKabQtt_bzMGjuLmh_bRhaUOM3K8 8740
tests/run_ingestor_tests.py sha256=0Fl5sRqtyjGHgCup84i0uwZgujneD-nYFJrl1ewKvMM 9426
tests/test_line_parser.py sha256=fyiIZCGWBY1u1gW7651LRYvaSWSDelRlt7eDBNk-Cxs 24767
tests/test_processor.py sha256=62e9WJvqcg8JJnkJDlcJdpd_QL0uvvixXaVdOYg5VgQ 8786
tests/test_sent_tokenizer.py sha256=PEcOwKpTw5sUAbWuOyuI8v-Pyy5AweOtyG_4D2qxnfM 967
nlm_ingestor-0.1.5.dist-info/LICENSE.txt sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0 11357
nlm_ingestor-0.1.5.dist-info/METADATA sha256=AbV-6fDtJ5Db9QvRsDa4VmlCAabs5THdsTxhwGX-qNs 8384
nlm_ingestor-0.1.5.dist-info/NOTICE.txt sha256=o070FzCpRJwbLyeFAnJUBATGqeTYb_yShzjzeCPOaKw 568
nlm_ingestor-0.1.5.dist-info/WHEEL sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM 92
nlm_ingestor-0.1.5.dist-info/top_level.txt sha256=Pmu9ni08Vi6ZPdbTv-FAE1to2MD9WNewMVnPSmnvEDU 19
nlm_ingestor-0.1.5.dist-info/RECORD

top_level.txt

nlm_ingestor
tests