gyokusai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gyokusai/config.py,sha256=yg0gOEhsKTayZOwGN-zASIvbSNstZwr2QWQ0YarXt3g,159
gyokusai/data/archive_data.py,sha256=pY5v7Jhgxsocc_Qm5w-KZh-M8k7P05DW0A03QU4Snn0,3627
gyokusai/deduplication/deduplicate.py,sha256=pyUfILY6Pl7xCjZnnYTSFxlYxuwSwdRVzAIUHR1QeyM,4782
gyokusai/encoding.py,sha256=SgE1LnLH6EjFq8_uXUgK1bc3_E3r2RyJD_x1l9b9nbg,457
gyokusai/engine.py,sha256=4itItFfSkaFCMn8mhvM0xAV4M8OsLRKKQIvpbhtx3Do,682
gyokusai/factories/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gyokusai/factories/embedding.py,sha256=izhFoVKmOQ8fWS_jC-LL7PWwMZW7UqNd1p4-WIcfmfs,3078
gyokusai/factories/generation.py,sha256=7qV28EkOAYW8avYkJ7-LS6TbhdudZ-QDOiRLUbYO030,3459
gyokusai/factories/ocr.py,sha256=Z3I9V78E1Pjj5kGOegYdV69SIaduSHQxyENESaY-iQU,4745
gyokusai/filters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gyokusai/filters/c4/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gyokusai/filters/c4/badwords.py,sha256=tcwrUCMZaaiQb4s6r88Qe7ffVmMRqMCY7YEL-bfo7hc,1017
gyokusai/filters/c4/dedupe.py,sha256=Pi1RVzsWS34VaE2htckxedydBJHVVWfnBfGqkTXQg8Y,1759
gyokusai/filters/config.py,sha256=Z1_CpJd6qU400-t6088m1xvcfy84lff4AGREkLt_yWk,104
gyokusai/filters/filters.py,sha256=QeID-oOU71eWWQb2lNa_Hjdo7PsK0cwmPkhhp-lxoKU,4447
gyokusai/filters/regexes.py,sha256=qUx3Eq0RSptpyHkPq5DajpG3h7Lv6ngcX0lHKEL4LyQ,42
gyokusai/filters/tokenize.py,sha256=6Gg4C1PQ1w8YfjQLKTf6cy5mFxpNXHHPVRrYoVmw1a4,1075
gyokusai/filters/url_blacklist.py,sha256=GcRJkLX7HqiAfn2ZfAUMVvWRMHbTkbXC0EVz4stOEko,2911
gyokusai/filters/utils.py,sha256=-2od4Lh9vtSuBmQM7nU4j5IFb3WQTOenu9b6_qZw6bg,658
gyokusai/language_id/lang_id.py,sha256=LT_kOVzoDzPTxmzAgkz6sfwmg1_5GRAMZaRT6nPPVsk,1094
gyokusai/loader.py,sha256=8F0ob1R_VLCQcmVZGXQJ0VvPyUCIIqOl2DdGn3pYLVE,2822
gyokusai/parsers/html.py,sha256=bNrxae_OHcD8AKad2bBS3vSSBzy35GQyM4OXqHN24r8,1522
gyokusai/parsers/math.py,sha256=-TdTd7tiUuRpKubgrYQ-GUu4kJ-j-FYaeYr5GFAWYyw,3084
gyokusai/parsers/pdf.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gyokusai/parsers/warc.py,sha256=9N4N4k90yDaDi_fFlz3i3JPRp8s0OehFzShzdMk2BUM,1035
gyokusai/pii/pii.py,sha256=mAK2560pOkgJXSE_kei2J9Ue1Wu0tNtxlCo-5LbafsI,1143
gyokusai/pipelines/personas.py,sha256=dfLI6LU3gdjTqfvzzmSMsCPgGD5jRYf0oqY-hdP738c,2273
gyokusai/pipelines/stackexchange.py,sha256=vzjQRDIN-ZvV5qAEWFHsqF6eYijiYwWKNQ8VCRwZSbI,3789
gyokusai/utils.py,sha256=B1jeBf6vSIsVW1Q4Fbpqkb3BK56hr8bzjK74jjJOv00,1731
gyokusai/word_lists/badwords_en.txt,sha256=r4UezvHV8hLKuhczmxKsOcwv7314x0h29nI3ZE_O6L0,3777
gyokusai-0.1.1.dist-info/WHEEL,sha256=r-Se0i_n47Mj8pdnVuq7W628oP9YAKMaTjp4l3lQcns,81
gyokusai-0.1.1.dist-info/METADATA,sha256=7gQAxlo-J9JQHHWr77cJCkXTZsFRQSBJu3IIvy9qVLI,1588
gyokusai-0.1.1.dist-info/RECORD,,
