diff --git a/pkgs/development/python-modules/tokenizers/Cargo.lock b/pkgs/development/python-modules/tokenizers/Cargo.lock index a0324bff8aba..aa12731f49c2 100644 --- a/pkgs/development/python-modules/tokenizers/Cargo.lock +++ b/pkgs/development/python-modules/tokenizers/Cargo.lock @@ -13,57 +13,58 @@ dependencies = [ [[package]] name = "anstream" -version = "0.6.13" +version = "0.6.15" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d96bd03f33fe50a863e394ee9718a706f988b9079b20c3784fb726e7678b62fb" +checksum = "64e15c1ab1f89faffbf04a634d5e1962e9074f2741eef6d97f3c4e322426d526" dependencies = [ "anstyle", "anstyle-parse", "anstyle-query", "anstyle-wincon", "colorchoice", + "is_terminal_polyfill", "utf8parse", ] [[package]] name = "anstyle" -version = "1.0.6" +version = "1.0.8" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8901269c6307e8d93993578286ac0edf7f195079ffff5ebdeea6a59ffb7e36bc" +checksum = "1bec1de6f59aedf83baf9ff929c98f2ad654b97c9510f4e70cf6f661d49fd5b1" [[package]] name = "anstyle-parse" -version = "0.2.3" +version = "0.2.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c75ac65da39e5fe5ab759307499ddad880d724eed2f6ce5b5e8a26f4f387928c" +checksum = "eb47de1e80c2b463c735db5b217a0ddc39d612e7ac9e2e96a5aed1f57616c1cb" dependencies = [ "utf8parse", ] [[package]] name = "anstyle-query" -version = "1.0.2" +version = "1.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e28923312444cdd728e4738b3f9c9cac739500909bb3d3c94b43551b16517648" +checksum = "6d36fc52c7f6c869915e99412912f22093507da8d9e942ceaf66fe4b7c14422a" dependencies = [ - "windows-sys", + "windows-sys 0.52.0", ] [[package]] name = "anstyle-wincon" -version = "3.0.2" +version = "3.0.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1cd54b81ec8d6180e24654d0b371ad22fc3dd083b6ff8ba325b72e00c87660a7" +checksum = "5bf74e1b6e971609db8ca7a9ce79fd5768ab6ae46441c572e46cf596f59e57f8" dependencies = [ "anstyle", - "windows-sys", + "windows-sys 0.52.0", ] [[package]] name = "autocfg" -version = "1.2.0" +version = "1.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f1fdabc7756949593fe60f30ec81974b613357de856987752631dea1e3394c80" +checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0" [[package]] name = "base64" @@ -79,15 +80,21 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a" [[package]] name = "bitflags" -version = "2.5.0" +version = "2.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1" +checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de" + +[[package]] +name = "byteorder" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" [[package]] name = "cc" -version = "1.0.94" +version = "1.1.8" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "17f6e324229dc011159fcc089755d1e2e216a90d43a7dea6853ca740b84f35e7" +checksum = "504bdec147f2cc13c8b57ed9401fd8a147cc66b67ad5cb241394244f2c947549" [[package]] name = "cfg-if" @@ -97,9 +104,9 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" [[package]] name = "colorchoice" -version = "1.0.0" +version = "1.0.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7" +checksum = "d3fd119d74b830634cea2a0f58bbd0d54540518a14397557951e79340abc28c0" [[package]] name = "console" @@ -111,7 +118,7 @@ dependencies = [ "lazy_static", "libc", "unicode-width", - "windows-sys", + "windows-sys 0.52.0", ] [[package]] @@ -135,15 +142,15 @@ dependencies = [ [[package]] name = "crossbeam-utils" -version = "0.8.19" +version = "0.8.20" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "248e3bacc7dc6baa3b21e405ee045c3047101a49145e7e9eca583ab4c2ca5345" +checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80" [[package]] name = "darling" -version = "0.20.8" +version = "0.20.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "54e36fcd13ed84ffdfda6f5be89b31287cbb80c439841fe69e04841435464391" +checksum = "6f63b86c8a8826a49b8c21f08a2d07338eec8d900540f8630dc76284be802989" dependencies = [ "darling_core", "darling_macro", @@ -151,9 +158,9 @@ dependencies = [ [[package]] name = "darling_core" -version = "0.20.8" +version = "0.20.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9c2cf1c23a687a1feeb728783b993c4e1ad83d99f351801977dd809b48d0a70f" +checksum = "95133861a8032aaea082871032f5815eb9e98cef03fa916ab4500513994df9e5" dependencies = [ "fnv", "ident_case", @@ -165,9 +172,9 @@ dependencies = [ [[package]] name = "darling_macro" -version = "0.20.8" +version = "0.20.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a668eda54683121533a393014d8692171709ff57a7d61f187b6e782719f8933f" +checksum = "d336a2a514f6ccccaa3e09b02d41d35330c07ddf03a62165fcec10bb561c7806" dependencies = [ "darling_core", "quote", @@ -207,9 +214,9 @@ dependencies = [ [[package]] name = "either" -version = "1.11.0" +version = "1.13.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a47c1c47d2f5964e29c61246e81db715514cd532db6b5116a25ea3c03d6780a2" +checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0" [[package]] name = "encode_unicode" @@ -219,9 +226,9 @@ checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f" [[package]] name = "env_filter" -version = "0.1.0" +version = "0.1.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a009aa4810eb158359dda09d0c87378e4bbb89b5a801f016885a4707ba24f7ea" +checksum = "4f2c92ceda6ceec50f43169f9ee8424fe2db276791afde7b2cd8bc084cb376ab" dependencies = [ "log", "regex", @@ -229,9 +236,9 @@ dependencies = [ [[package]] name = "env_logger" -version = "0.11.3" +version = "0.11.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "38b35839ba51819680ba087cd351788c9a3c476841207e0b8cee0b04722343b9" +checksum = "e13fa619b91fb2381732789fc5de83b45675e882f66623b7d8cb4f643017018d" dependencies = [ "anstream", "anstyle", @@ -242,12 +249,12 @@ dependencies = [ [[package]] name = "errno" -version = "0.3.8" +version = "0.3.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a258e46cdc063eb8519c00b9fc845fc47bcfca4130e2f08e88665ceda8474245" +checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba" dependencies = [ "libc", - "windows-sys", + "windows-sys 0.52.0", ] [[package]] @@ -261,9 +268,9 @@ dependencies = [ [[package]] name = "fastrand" -version = "2.0.2" +version = "2.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "658bd65b1cf4c852a3cc96f18a8ce7b5640f6b703f905c7d74532294c2a63984" +checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a" [[package]] name = "fnv" @@ -273,9 +280,9 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" [[package]] name = "getrandom" -version = "0.2.14" +version = "0.2.15" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "94b22e06ecb0110981051723910cbf0b5f5e09a2062dd7663334ee79a9d1286c" +checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7" dependencies = [ "cfg-if", "libc", @@ -321,13 +328,19 @@ checksum = "b248f5224d1d606005e02c97f5aa4e88eeb230488bcc03bc9ca4d7991399f2b5" [[package]] name = "instant" -version = "0.1.12" +version = "0.1.13" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c" +checksum = "e0242819d153cba4b4b05a5a8f2a7e9bbf97b6055b2a002b395c96b5ff3c0222" dependencies = [ "cfg-if", ] +[[package]] +name = "is_terminal_polyfill" +version = "1.70.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf" + [[package]] name = "itertools" version = "0.11.0" @@ -354,27 +367,27 @@ checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" [[package]] name = "lazy_static" -version = "1.4.0" +version = "1.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646" +checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe" [[package]] name = "libc" -version = "0.2.153" +version = "0.2.155" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd" +checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c" [[package]] name = "linux-raw-sys" -version = "0.4.13" +version = "0.4.14" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "01cda141df6706de531b6c46c3a33ecca755538219bd484262fa09410c13539c" +checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89" [[package]] name = "lock_api" -version = "0.4.11" +version = "0.4.12" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3c168f8615b12bc01f9c17e2eb0cc07dcae1940121185446edc3744920e8ef45" +checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17" dependencies = [ "autocfg", "scopeguard", @@ -382,9 +395,9 @@ dependencies = [ [[package]] name = "log" -version = "0.4.21" +version = "0.4.22" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c" +checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24" [[package]] name = "macro_rules_attribute" @@ -404,9 +417,9 @@ checksum = "b8dd856d451cc0da70e2ef2ce95a18e39a93b7558bedf10201ad28503f918568" [[package]] name = "matrixmultiply" -version = "0.3.8" +version = "0.3.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7574c1cf36da4798ab73da5b215bbf444f50718207754cb522201d78d1cd0ff2" +checksum = "9380b911e3e96d10c1f415da0876389aaf1b56759054eeb0de7df940c456ba1a" dependencies = [ "autocfg", "rawpointer", @@ -414,9 +427,9 @@ dependencies = [ [[package]] name = "memchr" -version = "2.7.2" +version = "2.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6c8640c5d730cb13ebd907d8d04b52f55ac9a2eec55b440c8892f40d56c76c1d" +checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" [[package]] name = "memoffset" @@ -435,9 +448,9 @@ checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a" [[package]] name = "monostate" -version = "0.1.12" +version = "0.1.13" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a20fffcd8ca4c69d31e036a71abc400147b41f90895df4edcb36497a1f8af8bf" +checksum = "0d208407d7552cd041d8cdb69a1bc3303e029c598738177a3d87082004dc0e1e" dependencies = [ "monostate-impl", "serde", @@ -445,9 +458,9 @@ dependencies = [ [[package]] name = "monostate-impl" -version = "0.1.12" +version = "0.1.13" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "bf307cbbbd777a9c10cec88ddafee572b3484caad5cce0c9236523c3803105a6" +checksum = "a7ce64b975ed4f123575d11afd9491f2e37bbd5813fbfbc0f09ae1fbddea74e0" dependencies = [ "proc-macro2", "quote", @@ -479,9 +492,9 @@ dependencies = [ [[package]] name = "num-complex" -version = "0.4.5" +version = "0.4.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "23c6602fda94a57c990fe0df199a035d83576b496aa29f4e634a8ac6004e68a6" +checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495" dependencies = [ "num-traits", ] @@ -497,9 +510,9 @@ dependencies = [ [[package]] name = "num-traits" -version = "0.2.18" +version = "0.2.19" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a" +checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841" dependencies = [ "autocfg", ] @@ -555,9 +568,9 @@ dependencies = [ [[package]] name = "parking_lot" -version = "0.12.1" +version = "0.12.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f" +checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27" dependencies = [ "lock_api", "parking_lot_core", @@ -565,22 +578,22 @@ dependencies = [ [[package]] name = "parking_lot_core" -version = "0.9.9" +version = "0.9.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4c42a9226546d68acdd9c0a280d17ce19bfe27a46bf68784e4066115788d008e" +checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8" dependencies = [ "cfg-if", "libc", "redox_syscall", "smallvec", - "windows-targets 0.48.5", + "windows-targets", ] [[package]] name = "paste" -version = "1.0.14" +version = "1.0.15" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "de3145af08024dea9fa9914f381a17b8fc6034dfb00f3a84013f7ff43f29ed4c" +checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" [[package]] name = "pkg-config" @@ -590,21 +603,24 @@ checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec" [[package]] name = "portable-atomic" -version = "1.6.0" +version = "1.7.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7170ef9988bc169ba16dd36a7fa041e5c4cbeb6a35b76d4c03daded371eae7c0" +checksum = "da544ee218f0d287a911e9c99a39a8c9bc8fcad3cb8db5959940044ecfc67265" [[package]] name = "ppv-lite86" -version = "0.2.17" +version = "0.2.20" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de" +checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04" +dependencies = [ + "zerocopy", +] [[package]] name = "proc-macro2" -version = "1.0.81" +version = "1.0.86" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3d1597b0c024618f09a9c3b8655b7e430397a36d23fdafec26d6965e9eec3eba" +checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77" dependencies = [ "unicode-ident", ] @@ -750,18 +766,18 @@ dependencies = [ [[package]] name = "redox_syscall" -version = "0.4.1" +version = "0.5.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4722d768eff46b75989dd134e5c353f0d6296e5aaa3132e776cbdb56be7731aa" +checksum = "2a908a6e00f1fdd0dfd9c0eb08ce85126f6d8bbda50017e74bc4a4b7d4a926a4" dependencies = [ - "bitflags 1.3.2", + "bitflags 2.6.0", ] [[package]] name = "regex" -version = "1.10.4" +version = "1.10.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c117dbdfde9c8308975b6a18d71f3f385c89461f7b3fb054288ecf2a2058ba4c" +checksum = "4219d74c6b67a3654a9fbebc4b419e22126d13d2f3c4a07ee0cb61ff79a79619" dependencies = [ "aho-corasick", "memchr", @@ -771,9 +787,9 @@ dependencies = [ [[package]] name = "regex-automata" -version = "0.4.6" +version = "0.4.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea" +checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df" dependencies = [ "aho-corasick", "memchr", @@ -782,9 +798,9 @@ dependencies = [ [[package]] name = "regex-syntax" -version = "0.8.3" +version = "0.8.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "adad44e29e4c806119491a7f06f03de4d1af22c3a680dd47f1e6e179439d1f56" +checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b" [[package]] name = "rustc-hash" @@ -794,22 +810,22 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2" [[package]] name = "rustix" -version = "0.38.32" +version = "0.38.34" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "65e04861e65f21776e67888bfbea442b3642beaa0138fdb1dd7a84a52dffdb89" +checksum = "70dc5ec042f7a43c4a73241207cecc9873a06d45debb38b329f8541d85c2730f" dependencies = [ - "bitflags 2.5.0", + "bitflags 2.6.0", "errno", "libc", "linux-raw-sys", - "windows-sys", + "windows-sys 0.52.0", ] [[package]] name = "ryu" -version = "1.0.17" +version = "1.0.18" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e86697c916019a8588c99b5fac3cead74ec0b4b819707a682fd4d23fa0ce1ba1" +checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f" [[package]] name = "scopeguard" @@ -819,18 +835,18 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" [[package]] name = "serde" -version = "1.0.198" +version = "1.0.205" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9846a40c979031340571da2545a4e5b7c4163bdae79b301d5f86d03979451fcc" +checksum = "e33aedb1a7135da52b7c21791455563facbbcc43d0f0f66165b42c21b3dfb150" dependencies = [ "serde_derive", ] [[package]] name = "serde_derive" -version = "1.0.198" +version = "1.0.205" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e88edab869b01783ba905e7d0153f9fc1a6505a96e4ad3018011eedb838566d9" +checksum = "692d6f5ac90220161d6774db30c662202721e64aed9058d2c394f451261420c1" dependencies = [ "proc-macro2", "quote", @@ -839,11 +855,12 @@ dependencies = [ [[package]] name = "serde_json" -version = "1.0.116" +version = "1.0.122" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3e17db7126d17feb94eb3fad46bf1a96b034e8aacbc2e775fe81505f8b0b2813" +checksum = "784b6203951c57ff748476b126ccb5e8e2959a5c19e5c617ab1956be3dbc68da" dependencies = [ "itoa", + "memchr", "ryu", "serde", ] @@ -868,15 +885,15 @@ dependencies = [ [[package]] name = "strsim" -version = "0.10.0" +version = "0.11.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623" +checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" [[package]] name = "syn" -version = "2.0.60" +version = "2.0.72" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "909518bc7b1c9b779f1bbf07f2929d35af9f0f37e47c6e9ef7f9dddc1e1821f3" +checksum = "dc4b9b9bf2add8093d3f2c0204471e951b2285580335de42f9d2534f3ae7a8af" dependencies = [ "proc-macro2", "quote", @@ -885,36 +902,37 @@ dependencies = [ [[package]] name = "target-lexicon" -version = "0.12.14" +version = "0.12.16" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e1fc403891a21bcfb7c37834ba66a547a8f402146eba7265b5a6d88059c9ff2f" +checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1" [[package]] name = "tempfile" -version = "3.10.1" +version = "3.12.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1" +checksum = "04cbcdd0c794ebb0d4cf35e88edd2f7d2c4c3e9a5a6dab322839b321c6a87a64" dependencies = [ "cfg-if", "fastrand", + "once_cell", "rustix", - "windows-sys", + "windows-sys 0.59.0", ] [[package]] name = "thiserror" -version = "1.0.58" +version = "1.0.63" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "03468839009160513471e86a034bb2c5c0e4baae3b43f79ffc55c4a5427b3297" +checksum = "c0342370b38b6a11b6cc11d6a805569958d54cfa061a29969c3b5ce2ea405724" dependencies = [ "thiserror-impl", ] [[package]] name = "thiserror-impl" -version = "1.0.58" +version = "1.0.63" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c61f3ba182994efc43764a46c018c347bc492c79f024e705f46567b418f6d4f7" +checksum = "a4558b58466b9ad7ca0f102865eccc95938dca1a74a856f2b57b6629050da261" dependencies = [ "proc-macro2", "quote", @@ -923,7 +941,7 @@ dependencies = [ [[package]] name = "tokenizers" -version = "0.19.1-rc0" +version = "0.20.0-rc1" dependencies = [ "aho-corasick", "derive_builder", @@ -953,14 +971,13 @@ dependencies = [ [[package]] name = "tokenizers-python" -version = "0.19.1-rc0" +version = "0.20.0-rc1" dependencies = [ "env_logger", "itertools 0.12.1", "libc", "ndarray", "numpy", - "onig", "pyo3", "rayon", "serde", @@ -992,9 +1009,9 @@ checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202" [[package]] name = "unicode-width" -version = "0.1.11" +version = "0.1.13" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e51733f11c9c4f72aa0c160008246859e340b00807569a0da0e7a1079b27ba85" +checksum = "0336d538f7abc86d282a4189614dfaa90810dfc2c6f6427eaf88e16311dd225d" [[package]] name = "unicode_categories" @@ -1010,9 +1027,9 @@ checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce" [[package]] name = "utf8parse" -version = "0.2.1" +version = "0.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a" +checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" [[package]] name = "wasi" @@ -1026,126 +1043,99 @@ version = "0.52.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d" dependencies = [ - "windows-targets 0.52.5", + "windows-targets", +] + +[[package]] +name = "windows-sys" +version = "0.59.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b" +dependencies = [ + "windows-targets", ] [[package]] name = "windows-targets" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" dependencies = [ - "windows_aarch64_gnullvm 0.48.5", - "windows_aarch64_msvc 0.48.5", - "windows_i686_gnu 0.48.5", - "windows_i686_msvc 0.48.5", - "windows_x86_64_gnu 0.48.5", - "windows_x86_64_gnullvm 0.48.5", - "windows_x86_64_msvc 0.48.5", -] - -[[package]] -name = "windows-targets" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb" -dependencies = [ - "windows_aarch64_gnullvm 0.52.5", - "windows_aarch64_msvc 0.52.5", - "windows_i686_gnu 0.52.5", + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", "windows_i686_gnullvm", - "windows_i686_msvc 0.52.5", - "windows_x86_64_gnu 0.52.5", - "windows_x86_64_gnullvm 0.52.5", - "windows_x86_64_msvc 0.52.5", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", ] [[package]] name = "windows_aarch64_gnullvm" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8" - -[[package]] -name = "windows_aarch64_gnullvm" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" [[package]] name = "windows_aarch64_msvc" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc" - -[[package]] -name = "windows_aarch64_msvc" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" [[package]] name = "windows_i686_gnu" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e" - -[[package]] -name = "windows_i686_gnu" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" [[package]] name = "windows_i686_gnullvm" -version = "0.52.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" [[package]] name = "windows_i686_msvc" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406" - -[[package]] -name = "windows_i686_msvc" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" [[package]] name = "windows_x86_64_gnu" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e" - -[[package]] -name = "windows_x86_64_gnu" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" [[package]] name = "windows_x86_64_gnullvm" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc" - -[[package]] -name = "windows_x86_64_gnullvm" -version = "0.52.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" [[package]] name = "windows_x86_64_msvc" -version = "0.48.5" +version = "0.52.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" [[package]] -name = "windows_x86_64_msvc" -version = "0.52.5" +name = "zerocopy" +version = "0.7.35" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0" +checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0" +dependencies = [ + "byteorder", + "zerocopy-derive", +] + +[[package]] +name = "zerocopy-derive" +version = "0.7.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] diff --git a/pkgs/development/python-modules/tokenizers/default.nix b/pkgs/development/python-modules/tokenizers/default.nix index 36718c65513c..20438e8bc405 100644 --- a/pkgs/development/python-modules/tokenizers/default.nix +++ b/pkgs/development/python-modules/tokenizers/default.nix @@ -2,24 +2,32 @@ lib, stdenv, linkFarm, - buildPythonPackage, - cargo, - datasets, - huggingface-hub, - fetchFromGitHub, fetchurl, - libiconv, - numpy, - openssl, - pkg-config, - pytestCheckHook, + buildPythonPackage, + fetchFromGitHub, python, - pythonOlder, - requests, - rustPlatform, - rustc, - Security, + + # nativeBuildInputs + pkg-config, setuptools-rust, + rustPlatform, + cargo, + rustc, + + # buildInputs + openssl, + libiconv, + Security, + + # dependencies + huggingface-hub, + numpy, + + # tests + datasets, + pytestCheckHook, + requests, + tiktoken, }: let @@ -28,23 +36,23 @@ let test-data = linkFarm "tokenizers-test-data" { "roberta-base-vocab.json" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json"; - sha256 = "0m86wpkfb2gdh9x9i9ng2fvwk1rva4p0s98xw996nrjxs7166zwy"; + hash = "sha256-nn9jwtFdZmtS4h0lDS5RO4fJtxPPpph6gu2J5eblBlU="; }; "roberta-base-merges.txt" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt"; - sha256 = "1idd4rvkpqqbks51i2vjbd928inw7slij9l4r063w3y5fd3ndq8w"; + hash = "sha256-HOFmR3PFDz4MyIQmGak+3EYkUltyixiKngvjO3cmrcU="; }; "albert-base-v1-tokenizer.json" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-tokenizer.json"; - sha256 = "1hra9pn8rczx7378z88zjclw2qsdrdwq20m56sy42s2crbas6akf"; + hash = "sha256-biqj1cpMaEG8NqUCgXnLTWPBKZMfoY/OOP2zjOxNKsM="; }; "bert-base-uncased-vocab.txt" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt"; - sha256 = "18rq42cmqa8zanydsbzrb34xwy4l6cz1y900r4kls57cbhvyvv07"; + hash = "sha256-B+ztN1zsFE0nyQAkHz4zlHjeyVj5L928VR8pXJkgOKM="; }; "big.txt" = fetchurl { url = "https://norvig.com/big.txt"; - sha256 = "0yz80icdly7na03cfpl0nfk5h3j3cam55rj486n03wph81ynq1ps"; + sha256 = "sha256-+gZsfUDw8gGsQUTmUqpiQw5YprOAXscGUPZ42lgE6Hs="; }; "bert-wiki.json" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/anthony/doc-pipeline/tokenizer.json"; @@ -56,26 +64,24 @@ let }; "openai-gpt-vocab.json" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-vocab.json"; - sha256 = "0y40gc9bixj5rxv674br1rxmxkd3ly29p80x1596h8yywwcrpx7x"; + hash = "sha256-/fSbGefeI2hSCR2gm4Sno81eew55kWN2z0X2uBJ7gHg="; }; "openai-gpt-merges.txt" = fetchurl { url = "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-merges.txt"; - sha256 = "09a754pm4djjglv3x5pkgwd6f79i2rq8ydg0f7c3q1wmwqdbba8f"; + hash = "sha256-Dqm1GuaVBzzYceA1j3AWMR1nGn/zlj42fVI2Ui8pRyU="; }; }; in buildPythonPackage rec { pname = "tokenizers"; - version = "0.19.1"; + version = "0.20.0"; pyproject = true; - disabled = pythonOlder "3.7"; - src = fetchFromGitHub { owner = "huggingface"; repo = "tokenizers"; rev = "refs/tags/v${version}"; - hash = "sha256-sKEAt46cdme821tzz9WSKnQb3hPmFJ4zvHgBNRxjEuk="; + hash = "sha256-uuSHsdyx77YQjf1aiz7EJ/X+6RaOgfmjGqHSlMaCWDI="; }; cargoDeps = rustPlatform.importCargoLock { lockFile = ./Cargo.lock; }; @@ -100,14 +106,15 @@ buildPythonPackage rec { ]; dependencies = [ - numpy huggingface-hub + numpy ]; nativeCheckInputs = [ datasets pytestCheckHook requests + tiktoken ]; postUnpack = '' @@ -127,17 +134,23 @@ buildPythonPackage rec { "test_encode_special_tokens" "test_splitting" "TestTrainFromIterators" + # Those tests require more data "test_from_pretrained" "test_from_pretrained_revision" "test_continuing_prefix_trainer_mistmatch" ]; - meta = with lib; { + disabledTestPaths = [ + # fixture 'model' not found + "benches/test_tiktoken.py" + ]; + + meta = { description = "Fast State-of-the-Art Tokenizers optimized for Research and Production"; homepage = "https://github.com/huggingface/tokenizers"; - license = licenses.asl20; + license = lib.licenses.asl20; maintainers = [ ]; - platforms = platforms.unix; + platforms = lib.platforms.unix; }; }