text_curation/__init__.py,sha256=4GMgEQ0cLhQHljKm3U-VR-JWAvYqzWB5NvVA5ravZC0,326
text_curation/_api.py,sha256=lxPVlNErhwdh7kSHPR8ZXyQ_XdByJCJI3FZAUkrVl9M,232
text_curation/curator.py,sha256=np-zd3DyUwsUhybgJHdi_sVf7-k6TTOzIen3dlI0HSk,1777
text_curation/registry.py,sha256=9HJw_oB4sh-7C4TvCLhoBDXmhhlYvonm3vVC3dyldNY,1129
text_curation/analysis/__init__.py,sha256=cTuNqoZWEi_AilNqNSeGwwH64kOfNPst8IHgrCCaLeA,419
text_curation/analysis/base.py,sha256=VU3aIuD2iRLuWV4kNzQ3xds2eXwXGGt8s8uzIMKT9ac,788
text_curation/analysis/fingerprint.py,sha256=vxlof8tHKFiNbAvJsRLFpucbR7VZgJB0n1PtdXe58Ys,914
text_curation/analysis/quality.py,sha256=hxVgyzKSx17K2pTQwU34f3xq-j2LZnPBFCjteYyS_tQ,2471
text_curation/analysis/token_stats.py,sha256=30df5uyqqRQ6GHyuZCM5oeqYo_11JEy6eVmbfiRunpY,1339
text_curation/blocks/__init__.py,sha256=YXkHtFQkfeFAix-O5FpI1a8FSQ_le2XllZzSdyrdJNE,821
text_curation/blocks/base.py,sha256=WaIZhL3A5lnBxWS3Jp0CQ4Nc5Aucqfnjf61iHdmCMSA,1200
text_curation/blocks/normalization.py,sha256=riY4puBl9sHmpI8Ul1e7A6i8F7pl9Zi0hW8KdrqITm0,2916
text_curation/blocks/redaction.py,sha256=zFuE817m1grR2Y7l2iKKbn9-16hRt8_5isFE81OE3g8,1706
text_curation/blocks/deduplication/__init__.py,sha256=grskmfQ37mefA3HP6148LPK8ZCsd-k6HcqBaObRP3Dc,109
text_curation/blocks/deduplication/exact_paragraph.py,sha256=KG2WWILppDt95vI9duAUKSWI1bq4BoWNw5h6PfMTeRg,1469
text_curation/blocks/filtering/__init__.py,sha256=u1OhwxVHciHxDpfRp0IFRRneKqfjRzaqevykwZgbkG4,114
text_curation/blocks/filtering/signal_based.py,sha256=Z4JZlMFxexpWHOrPGSFBM47J6oqxoxgT0-fJ6yptq_A,2779
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=gC3x-5bKuCpGHcKx_kXeiEDPtABb-6v0uWMTw51Haic,810
text_curation/core/document.py,sha256=kw4o_Iy3o-HxXt5CrqyocoU35iSYTGBmAK72fF9V9CY,1951
text_curation/core/pipeline.py,sha256=2UlHgpprgAWUwEe4x9o5HlbyfttY8zGuEKGy9Cjc_Kg,2239
text_curation/core/report.py,sha256=fftEGckNTOzOu4-fQ4H8sSGdPKI-twIRW0Nl2d6UkEU,1636
text_curation/core/reproducibility.py,sha256=YgC733O5YzI2J_Oyr13jJ-pwTtmEzK7MDI4xGtXN3TE,907
text_curation/core/signals.py,sha256=0a_apLqQh8-MEOJoVIm04Hh2TNde-nj4XDI8Baz-zdI,836
text_curation/datasets/__init__.py,sha256=dSK-Ejv8hMDPJ9HCilezMmBpCqcZ13yylFp--jILOQw,250
text_curation/datasets/deduplication.py,sha256=7w_gp8KPD3KadUSdzj7BPbi5Bi_3NNUJ38F3qD8pKnI,2786
text_curation/datasets/filtering.py,sha256=Nk6v7zH7aFSbXVsv-uBLxNdiJJM3vMS2zGGJ4pS_Wjg,1909
text_curation/datasets/pretty.py,sha256=LF2gGS1kx37DafP20qniCwSZi2626IGEySJICXYWx8Q,2079
text_curation/datasets/advanced/__init__.py,sha256=XIYU3ZtG0NeNEoiZ7kqMETXaynJujxnj7j9yhPug8zI,217
text_curation/datasets/advanced/decontamination.py,sha256=tGGT6R7UmSzF_8F2MgvrClnzPGp8oCvhgP7UaW03RRY,2510
text_curation/datasets/advanced/hash_dedup.py,sha256=hRgzxZ8vtmS7CJ3UReMEU-dE_gYM4QA63jzVBfyxAGw,2656
text_curation/datasets/advanced/minhash.py,sha256=Okt7ob0sep5BSWDpwCSSsRYDoPhnLVqB5hzd7v3-7IE,3181
text_curation/profiles/__init__.py,sha256=pgH-_XE068vWKNGsc2ID5qHkQn_v4hD9hKL9NNylV-w,792
text_curation/profiles/base.py,sha256=475gyDH16Q-zEA7ZkPqTjnjCKIdYoiIV3vH64YH0RGM,2638
text_curation/profiles/llm_pretrain_v1.py,sha256=AHcc49bGHmJDqE1FwnIaRwInoxdPI7-CgBbPgVYPnjo,1003
text_curation/profiles/web_common_v1.py,sha256=NfRlH0yc9vRAvHDoF30nilkKnYoLKHbQldPcbCuJxzA,2219
text_curation/profiles/pretraining/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
text_curation/profiles/pretraining/web_pretrain_v1.py,sha256=clDCcg0srG4Mw6mIsQ3F7xwy3s62PEOZLbQyz3_2uQw,1567
text_curation/reports/__init__.py,sha256=8UVSCS4DRU1I68VC4fT5qkoIpxXnxlFC4iEVh2wtU_E,823
text_curation/reports/aggregate.py,sha256=MAB5dZNYANtjaq3-5CJEGIfCooJ4OBR1fn0Bgd32yII,1315
text_curation/reports/manifest.py,sha256=8-gt5sratIF1sug_znyhksMc5MuDBsxCXB3ui2C13Pk,1766
text_curation/reports/summary.py,sha256=_mBXzgh-fSXAr026ZAEofv3mGRKPVwWAnkGOtW_3lY8,4649
text_curation-1.6.0rc0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
text_curation-1.6.0rc0.dist-info/METADATA,sha256=fmmhSZ3yrQZkQzP_h39cziO7BJwGaloNGxa3u4JB0Vc,24241
text_curation-1.6.0rc0.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
text_curation-1.6.0rc0.dist-info/top_level.txt,sha256=FwtBDRuMEe_hQ5mg-uAVK0Erp8tVpxcjfo65fYueU94,14
text_curation-1.6.0rc0.dist-info/RECORD,,
