text_curation/__init__.py,sha256=4GMgEQ0cLhQHljKm3U-VR-JWAvYqzWB5NvVA5ravZC0,326
text_curation/_api.py,sha256=lxPVlNErhwdh7kSHPR8ZXyQ_XdByJCJI3FZAUkrVl9M,232
text_curation/curator.py,sha256=XexMu0MlDOi5cYgwabMmFx8dl0G2-qTIaYoqf1lvK1U,1776
text_curation/registry.py,sha256=9HJw_oB4sh-7C4TvCLhoBDXmhhlYvonm3vVC3dyldNY,1129
text_curation/blocks/__init__.py,sha256=YXkHtFQkfeFAix-O5FpI1a8FSQ_le2XllZzSdyrdJNE,821
text_curation/blocks/base.py,sha256=WaIZhL3A5lnBxWS3Jp0CQ4Nc5Aucqfnjf61iHdmCMSA,1200
text_curation/blocks/normalization.py,sha256=0D3mN2iNr1ydxfC3XirJ-VWHYLKb4c_T_IhUFmselYY,2891
text_curation/blocks/redaction.py,sha256=GrFs_XVFx15Xo770phhEQFx8TfzXJeAAN44iYE8Zjdw,1692
text_curation/blocks/deduplication/__init__.py,sha256=grskmfQ37mefA3HP6148LPK8ZCsd-k6HcqBaObRP3Dc,109
text_curation/blocks/deduplication/exact_paragraph.py,sha256=Rc-GkrL4yk_JqNa9IbWQ-5wJdL96kSoGIVkFfnESwNw,1600
text_curation/blocks/filtering/__init__.py,sha256=u1OhwxVHciHxDpfRp0IFRRneKqfjRzaqevykwZgbkG4,114
text_curation/blocks/filtering/signal_based.py,sha256=lpFQdGPwtTlaDjmb2D3EP6aO3gY5e72vPyKiBS-0K6s,2640
text_curation/blocks/formatting/__init__.py,sha256=7Kaj76JBHC0HF8kkWPsi8J1Hkv9TJOhNjLPEX7uyX5c,161
text_curation/blocks/formatting/code_safe.py,sha256=-Pe_CJJQl4kAeDJvPB5quQgbnWaHRa6Sd0hM36jhrZY,887
text_curation/blocks/formatting/paragraph.py,sha256=taqwf-cJdfKdYWd1iETNn7dTfowhnMMVXbFopNAXlWc,3317
text_curation/blocks/structure/__init__.py,sha256=ACAVbZoBszUpTon8VPpR_bvlbk0uJilKPkOk9oJ-zhQ,73
text_curation/blocks/structure/basic.py,sha256=QzM19qf1jEG11njwd42pCqxgRi1KiENuB9f1L708IAM,3697
text_curation/core/annotations.py,sha256=cLusps7qsOZ4OLuZ3s_KGppPtOhBpOuNtGaIWCXEbkE,810
text_curation/core/document.py,sha256=kw4o_Iy3o-HxXt5CrqyocoU35iSYTGBmAK72fF9V9CY,1951
text_curation/core/pipeline.py,sha256=5Vc-vsoj1dDqzlKLVa2rUqK5mdZPe6Jl9PZYyxPfk9M,2217
text_curation/core/report.py,sha256=fftEGckNTOzOu4-fQ4H8sSGdPKI-twIRW0Nl2d6UkEU,1636
text_curation/core/signals.py,sha256=0a_apLqQh8-MEOJoVIm04Hh2TNde-nj4XDI8Baz-zdI,836
text_curation/datasets/__init__.py,sha256=_AEPgS9uCVnAclJrl-ulOWnS1P73da5qNWhxVRvIsAI,226
text_curation/datasets/deduplication.py,sha256=fkk__DIuCxpjIfejvX7xMKPyQgWYjwq_OOXdVctk3QU,2556
text_curation/datasets/filtering.py,sha256=EVli1FiepF2TNS0B7LgiovK3mWruHreOKZ_lZ-OEw1k,1787
text_curation/datasets/pretty.py,sha256=L2FVlZpu6Bv3pYVvjygqbYRk2GDDmJ_nRomBMc0SDTk,2079
text_curation/profiles/__init__.py,sha256=CPa1akQaPyn_TanjVYe86jSih6ojH4oKbarqI4jVOLc,719
text_curation/profiles/base.py,sha256=VW6N0yx0KKBKt2Uu7TUeFdOyN-Bi_3dQswf6Q5uPV88,2637
text_curation/profiles/llm_pretrain_v1.py,sha256=AHcc49bGHmJDqE1FwnIaRwInoxdPI7-CgBbPgVYPnjo,1003
text_curation/profiles/web_common_v1.py,sha256=NfRlH0yc9vRAvHDoF30nilkKnYoLKHbQldPcbCuJxzA,2219
text_curation/reports/__init__.py,sha256=On8pfl9nCjM3a72rvYXjTJSRxu6sC1hbCQGW06Do_PU,764
text_curation/reports/aggregate.py,sha256=MAB5dZNYANtjaq3-5CJEGIfCooJ4OBR1fn0Bgd32yII,1315
text_curation/reports/summary.py,sha256=_mBXzgh-fSXAr026ZAEofv3mGRKPVwWAnkGOtW_3lY8,4649
text_curation-1.5.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
text_curation-1.5.0.dist-info/METADATA,sha256=6sT1yYRRQKzlxucWK4pUjIP3dDcATWD3SoD8H4m44bs,21978
text_curation-1.5.0.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
text_curation-1.5.0.dist-info/top_level.txt,sha256=FwtBDRuMEe_hQ5mg-uAVK0Erp8tVpxcjfo65fYueU94,14
text_curation-1.5.0.dist-info/RECORD,,
