dpk_doc_chunk/__init__.py,sha256=dENM5wNH4Xils3v7SAh-xc5BVR5awJltaqjI-SEJhQU,25
dpk_doc_chunk/chunkers.py,sha256=4CU4n7WyunGYBOZIAxnySztgUsGCgO-OtceFIzT0S-g,5277
dpk_doc_chunk/local.py,sha256=844l6aRdjtljqoAJM7RlP_UdB3M4md8-a2cslajWl98,1475
dpk_doc_chunk/local_python.py,sha256=eLLEULsv_jeRVfuViM10spWIDS0IGNPMKxtcP7CuDW0,2638
dpk_doc_chunk/transform.py,sha256=2ddhchis3_q27a12dopn4SboQPRm1brQpGsQnth0KMQ,11732
dpk_doc_chunk/transform_python.py,sha256=vgo4uJLpQRVo54Ne1BSSMZP-GKhSpb4XvzSjNAbUzhA,2677
dpk_doc_chunk/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_doc_chunk/ray/local.py,sha256=f_btcY2hxDbO_9JjDh8tQiE9dCSrxTm3Sh55nDG4TJM,2067
dpk_doc_chunk/ray/s3.py,sha256=GtfETyPL2JBjy59K6z0QDojvQ3co-R6OVSwrbLE9GzU,2020
dpk_doc_chunk/ray/transform.py,sha256=J2-FmoFsLi1DkRZYvbFiUVg_v2Eh31LjTmiaGyZo7zI,3214
dpk_doc_id/__init__.py,sha256=x-q6Vv8zqM58pO0cWX3IMj1cPhRF66d0NY36tD9iWZA,106
dpk_doc_id/local.py,sha256=rQU6iCA8tn4vjF_veIxtI7tiWjxfj_ycO5dzmKNkj9E,2188
dpk_doc_id/local_python.py,sha256=3KtwOXRi6qJtxzRqYRKWEoUK2jFmSb9llgOgtHQRto8,2209
dpk_doc_id/transform.py,sha256=5PqGPqEjNP8bsxDwg8POsf8oITWK0TerMHi5EgUyJ48,6679
dpk_doc_id/transform_python.py,sha256=kSpdim9Et9tUck0ICzx5f8Quu4R5IOQNGYA9ukgid9I,5694
dpk_doc_id/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_doc_id/ray/local.py,sha256=HLt7JSSnuC6whFku47V5ikPInWbDQRHQhFwHYijYrwY,2261
dpk_doc_id/ray/s3.py,sha256=CT4H_bbLiVfzWlIvM_phFMgwVF6r_1z5Pby0K6-rekg,2251
dpk_doc_id/ray/transform.py,sha256=_uZKBeVfeUbu7Ws5p06YUZCG9J58QGpbS2oZz_jU_M8,5513
dpk_doc_id/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_doc_id/spark/local.py,sha256=O2zhDeglaE-jgSIiNnq4zTFwY1ZrDJM3gAxK4RhuTWs,2118
dpk_doc_id/spark/transform.py,sha256=85hWlWR2feDAdDxGL-BrRP5uA1z4PBJzUhiNCv2Kjnk,7896
dpk_doc_quality/__init__.py,sha256=x-q6Vv8zqM58pO0cWX3IMj1cPhRF66d0NY36tD9iWZA,106
dpk_doc_quality/cc_net_prepro.py,sha256=B9lt_2ZFVsORqXHdepNQ3B-wd3CT_9wNrC41Qcedtg0,4929
dpk_doc_quality/doc_Gopher_statistics.py,sha256=KxZpWjXKX5l9FkQnyLzwDb3fmdG-8awoGbKWnleFtPI,6530
dpk_doc_quality/doc_c4_statistics.py,sha256=r1GPFg0mmQIqtA9Pdt3F3hi3FpwugOP3Cey-aXAjFpg,6068
dpk_doc_quality/local.py,sha256=GYVZIsQqq4ICaJUIh7G37CbDDSUXZCZUIBxuGG2O83M,1731
dpk_doc_quality/local_python.py,sha256=UVeXbnWd3cORbGs3uhVRO5s7zUvrzGUvYZDQAyZ9VE4,2646
dpk_doc_quality/transform.py,sha256=qVPjaWssgfQl9A1bWNHzc5GgGGvfDUcX0Y8QoRCc-Ok,10904
dpk_doc_quality/transform_python.py,sha256=hM7dOOVE0OWYcoIyyhDamTD63Zbzr78O7t0c5G26sSU,3315
dpk_doc_quality/utils.py,sha256=n8vHmiLLAtO45_7S8lnseH4sUmyPrhBNIPuUEOhCqfI,2264
dpk_doc_quality/ldnoobw/de,sha256=6-RNd3KJc5Dif3vsQS_c3w78KU5NsVf4SHxM2NT6vVU,534
dpk_doc_quality/ldnoobw/en,sha256=r4UezvHV8hLKuhczmxKsOcwv7314x0h29nI3ZE_O6L0,3777
dpk_doc_quality/ldnoobw/es,sha256=BzM0JhzC58CDOfrv0vGfliPoJAoKwY_iomw2i4l0ls4,617
dpk_doc_quality/ldnoobw/fr,sha256=eXY6cF4IJWs5OVKFK7Y6qQP0SF4O8C9wc19eUO__ITw,793
dpk_doc_quality/ldnoobw/ja,sha256=-DxNCEPqZHTBe_Fx7dcrYWs69AP4YT8s3hvYQfr28xY,2339
dpk_doc_quality/ldnoobw/pt,sha256=Be9SSwu3-D-HJX9uxNq_cOFri7aTD3afuT3q9gj_GW0,629
dpk_doc_quality/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_doc_quality/ray/local.py,sha256=nN32AfJN41wE3Trenwz6g1LcoJbzSZJ7-GvUIy6zig8,2435
dpk_doc_quality/ray/s3.py,sha256=s41OEMKU6tyDXftnLpQFIrkHm_VPoXA9antgbHS7pBQ,2706
dpk_doc_quality/ray/transform.py,sha256=xuJFFAKMkIaNdMN5jEBJGoFRcj9bgkm2G81ffUd5hPM,1713
dpk_hap/__init__.py,sha256=x-q6Vv8zqM58pO0cWX3IMj1cPhRF66d0NY36tD9iWZA,106
dpk_hap/local.py,sha256=OCR7K03RkK_fobGYbIkrknEG1l3YI32_Gc5UPMW-5Jw,1858
dpk_hap/local_python.py,sha256=jGzAL9fyeAoRnoikiZx0M-I3kKGNCgup0eH02r0CLlw,2021
dpk_hap/transform.py,sha256=1R0mQpOTnaQ3RTaeK9pWqlrPHwhUCeAb1bn716QheRo,7105
dpk_hap/transform_python.py,sha256=LnRq43e774V6mDQPwk5TbvGaCJeI7Of-imjgoPt0ZSE,2411
dpk_hap/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_hap/ray/local.py,sha256=9n6rAkd6gHKKURc0XZWtW08noYzBGOE0Q7B7v6HYLz0,2033
dpk_hap/ray/s3.py,sha256=TDR76lOcfyj0Ty-5msWCvfxnYpiV-RHVwv_QYWGnELY,2151
dpk_hap/ray/transform.py,sha256=s00JUk3oAyBunZMizc_vrSyg7CgH4uK34P6bB23-WKg,1513
dpk_html2parquet/__init__.py,sha256=3KmYJRl2lrHqrmY38_weBGYBphvQ9KDwRVQblLQebe4,105
dpk_html2parquet/local.py,sha256=IP_n6APkuybtHmeykhYP-QqlOsBnu7VcOa2N1T30LCc,1592
dpk_html2parquet/local_python.py,sha256=FDI5lfc9h-Z-B10asIyYMhoYvDHBU0EWByCFuc4RMl0,1950
dpk_html2parquet/transform.py,sha256=f6BkeRIDPP99_IOQVYQ3Qb0td3Zo-Z8vat3pFYZtMaE,10627
dpk_html2parquet/transform_python.py,sha256=jSaQQZgcq1AnedN_X5GEJjQlDGH98hjiIdgaX7DWgs4,2559
dpk_html2parquet/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_html2parquet/ray/local_ray.py,sha256=V3PlLx7hKVBM8ad6tomdOVw0F3uULlIj-lzKXvyRC8o,2181
dpk_html2parquet/ray/s3_ray.py,sha256=UAytiSJ1gQjj7kStr7vhv5aaB5i4xW5OLhRnyUympOs,2061
dpk_html2parquet/ray/transform.py,sha256=WpPtPJMDXgiOAunXb5MkXd9rleGYnnfTgOoHIFZiPQo,2535
dpk_lang_id/lang_models.py,sha256=ZniqCjUwVKiL5DSY--Z7NfFcMEf0cWHUGyR745i9Hl8,1891
dpk_lang_id/local.py,sha256=y5aSAZXAP8kXLsxjXAWBFqEYsa6i8b0OQFeNOL-lDNk,1933
dpk_lang_id/local_python.py,sha256=vkuY_Ncx3XSNYAyWOIlju6tMYaM_mE-F7ZfOSwR3vCA,2334
dpk_lang_id/nlp.py,sha256=hdqabpC9PCBPJn0OnGP1waMf3Idf2oJukFFcBFl1tXo,1863
dpk_lang_id/transform.py,sha256=tEDGLBlCJDO0TylxtCl7UX5ygoBwCmOXljsQuhhCkzM,6761
dpk_lang_id/transform_python.py,sha256=gftOqpfT7KeXqT0xArKrIjTjFuT1hAhiP0hdwkwOteY,2634
dpk_lang_id/ray/local.py,sha256=h3g_-Gzuf_Z8-w0tl4d6snoup1ghOrUxiqQSfAOSt6I,2691
dpk_lang_id/ray/s3.py,sha256=MHMTXMwE0_5QYsVouphZ4a-NiuJ7mOFf1JBmR3HWihI,2634
dpk_lang_id/ray/transform.py,sha256=ERQBTNT4UxpbpK6BmReyBH5UT9Vvswex0ET6DiY-9Ac,1751
dpk_pdf2parquet/.dockerignore,sha256=3QTY9fGeIxLthVOMrrg2t3LSQW_3TA17yNwpNZG_D2U,59
dpk_pdf2parquet/.gitignore,sha256=a5B6rgjYJDVdI93RQR68DlACWl_wqkNANnTmnoS2Jg0,428
dpk_pdf2parquet/__init__.py,sha256=dENM5wNH4Xils3v7SAh-xc5BVR5awJltaqjI-SEJhQU,25
dpk_pdf2parquet/local.py,sha256=UqNHMn6Mp02H5fQ5_2EP-DlQgLX2k1jNItIA4mugFrA,1613
dpk_pdf2parquet/local_python.py,sha256=beqmCQ6lmEaIYPiQcWolR9AFeHY7mDGQ09SQ8b55Vx4,2270
dpk_pdf2parquet/transform.py,sha256=PdWTiBOl-xJVlMBsGsvvc4QVVnQSCzaOSRXjprGU2Ng,20716
dpk_pdf2parquet/transform_python.py,sha256=-vCTPXJn_UBIZyEn5oIzzI5wGHLNBlzw0hUBJD1HB8s,2561
dpk_pdf2parquet/ray/.dockerignore,sha256=3QTY9fGeIxLthVOMrrg2t3LSQW_3TA17yNwpNZG_D2U,59
dpk_pdf2parquet/ray/.gitignore,sha256=a5B6rgjYJDVdI93RQR68DlACWl_wqkNANnTmnoS2Jg0,428
dpk_pdf2parquet/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_pdf2parquet/ray/local_ray.py,sha256=So5wwsnIsOLHqFav_kprlCF9gyfq_VCvS1uJtLfP86M,2246
dpk_pdf2parquet/ray/s3_ray.py,sha256=IQauqhMHOfg0bPPjHCAT3CQ5qEg4w1lYJZyt70r0l6A,2170
dpk_pdf2parquet/ray/transform.py,sha256=1fH2mjqaAL2e6oSBiHpxeYfJ9Q2zumrdzkyOv8anIX4,3920
dpk_text_encoder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_text_encoder/local.py,sha256=TdbVtESTaDavHB7gf0VW97mfCbTzh8dxdcTI_4-gi-E,1911
dpk_text_encoder/local_python.py,sha256=7PnxN0aajmickBOq4LfsxJFPbeik6I4Jr5zmGus4d8o,1899
dpk_text_encoder/transform.py,sha256=pWekXVfQ7Spq3hWiP27hJGnOMaHD2HDwb33kVNKxOFc,5146
dpk_text_encoder/transform_python.py,sha256=-CAj5jc6MI8oS4CI6qakReb1haYJg5OayEQg8Gw2onc,2684
dpk_text_encoder/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dpk_text_encoder/ray/local.py,sha256=EQaUrkkhU8IXaI3KYdfwHpGUA_PxkOq9h21vUb-XuaU,2079
dpk_text_encoder/ray/s3.py,sha256=vW7CrGFvLZSHeVuc0ypiCKLDw1mnkLTzocPZJrzmSyg,2028
dpk_text_encoder/ray/transform.py,sha256=SRmBgg_r6cg9Yr0mFO5TMNIPWx99Lf-uEPsqO4I2ShE,2931
dpk_tokenization/local.py,sha256=JFtnIVbksslionjnOtHu3GgOqAdEJe0imyg56bUR_fM,1673
dpk_tokenization/local_long_doc.py,sha256=2csRJCDTcxFNErXFri0SS3FPCsu97LQiSPAFzH5yLSM,2140
dpk_tokenization/s3_long_doc.py,sha256=jvwaX-mmDUSoH6uc_AVoBhfvZtBHtDMcI3Z0DWKgZQ8,2153
dpk_tokenization/transform.py,sha256=j2Xm8hJKLd4uzsihTXvTsSuClBm9KIT1iPn0ondTji4,10706
dpk_tokenization/transform_python.py,sha256=4GEGbJSAPbAxf7qECJxFjm_jKj0gQ86FmhJn9scMvgE,2059
dpk_tokenization/utils.py,sha256=uJuozmA3hIGQHIFol3w_hT6Dw5J3dMu71or9bK0Pk6c,5475
dpk_tokenization/ray/local.py,sha256=NEj27OdWF0OEsAqqnP5FaFJum6GZs2ViWpowTI_LFb0,2000
dpk_tokenization/ray/s3.py,sha256=O1o2d4hDzS5BYuxEve7UnyCU9gkIjPZ-7HtsKpmBs7w,2171
dpk_tokenization/ray/transform.py,sha256=xO5nQdc52lOadMxxTXFLflt9s44ZVKsw9DVYJ_6L6ro,1330
dpk_web2parquet/config.py,sha256=8AN85NQziUQ6jButezmNXSFdAdJ41b76a4olTmyx-bI,3080
dpk_web2parquet/local.py,sha256=raW-mvoDGMzP3nP_H4QCwQP0SWat0VYDSPYsgB4naWg,1147
dpk_web2parquet/local_python.py,sha256=YIMvFU89eXGZIPP03UdzwFPR2_S788lOd7iAmk07eR4,2018
dpk_web2parquet/python_runtime.py,sha256=iX5Io_IrJzvMejP8Wg0KM91fdPmSLdCk0RIeETHFkr0,1713
dpk_web2parquet/transform.py,sha256=F6JklxecXT2QH-GQcxz4_zjCRY0RTr4JWdnA-zmp6v0,4843
dpk_web2parquet/utils.py,sha256=E0ZwdxxH3w1bGkcJ2HUjIsMZ38B5Ogyr5fFUM9jSU2w,1458
data_prep_toolkit_lang-1.0.0a0.dist-info/METADATA,sha256=uyYCGGeAXK4ChxQkfYGgQNaHBA5GAbS1NoJFYQH5iWo,7841
data_prep_toolkit_lang-1.0.0a0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
data_prep_toolkit_lang-1.0.0a0.dist-info/top_level.txt,sha256=8pDowSk_zLZ8C4ls2tOprvY3gr0CKLRncqt-gu4l-DA,144
data_prep_toolkit_lang-1.0.0a0.dist-info/RECORD,,
