tokenizers 0.4.4-x86_64-linux → 0.5.0-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b88bb25f3eadd64cedfd9c8317860633ab63de8e9a60aac52c9e30ca21a833cc
-  data.tar.gz: cb5b774c4bffd0b99ec81d0b62435958bf9247c72a97bb45c9d05c2522875166
+  metadata.gz: 73c92c500a274ba952cfd529fc69f96613e19f2dc2acb0e608eba84e6477442f
+  data.tar.gz: da18d3aa30c01ae75b8b50c1fa675fd6a32acabe3f14c5a30802b6078c9801e4
 SHA512:
-  metadata.gz: f4601407275a2d5090f432db8e5afe8141560dad900eaf2b31d3470e2db1ba306f312321f64c2cf977057c1fd3087ce05878ffb5108427ff4efa360006ae6940
-  data.tar.gz: 742cfe7334a7944a839fdf4e80405bfc27f6fd7a9836f4de93aaaf5fadf5b638a41dcdb95e5d0e2486e339b76df10f82b33d9cc53c83c7bedce926c9099a88e1
+  metadata.gz: 544f43731aba4981487a1e14a13b76dd627ec60e6c68f808d47b4b721a0153fe427402e845e7595ca729ab877008b6a452b32b95a851bfb1236b273c3e64d10b
+  data.tar.gz: 38ca9c1e9dd511f0a875de4ba83df3015186c9e609d740525da9ee7660db70e90e1f539c20e38c43ae44fbe7df09e8ffc0781de8e7826fbe0f7a8f5c86bd6125

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.5.0 (2024-05-21)
+
+- Updated Tokenizers to 0.19.1
+- Replaced `add_prefix_space` with `prepend_scheme` and `split` options for `Metaspace` decoder and pre-tokenizer
+- Dropped support for Ruby < 3.1
+
 ## 0.4.4 (2024-02-27)
 
 - Updated Tokenizers to 0.15.2

data/Cargo.lock

@@ -40,7 +40,7 @@ dependencies = [
  "regex",
  "rustc-hash",
  "shlex",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
@@ -135,9 +135,9 @@ dependencies = [
 
 [[package]]
 name = "darling"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b750cb3417fd1b327431a470f388520309479ab0bf5e323505daf0290cd3850"
+checksum = "54e36fcd13ed84ffdfda6f5be89b31287cbb80c439841fe69e04841435464391"
 dependencies = [
  "darling_core",
  "darling_macro",
@@ -145,58 +145,58 @@ dependencies = [
 
 [[package]]
 name = "darling_core"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "109c1ca6e6b7f82cc233a97004ea8ed7ca123a9af07a8230878fcfda9b158bf0"
+checksum = "9c2cf1c23a687a1feeb728783b993c4e1ad83d99f351801977dd809b48d0a70f"
 dependencies = [
  "fnv",
  "ident_case",
  "proc-macro2",
  "quote",
  "strsim",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "darling_macro"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4aab4dbc9f7611d8b55048a3a16d2d010c2c8334e46304b40ac1cc14bf3b48e"
+checksum = "a668eda54683121533a393014d8692171709ff57a7d61f187b6e782719f8933f"
 dependencies = [
  "darling_core",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "derive_builder"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d67778784b508018359cbc8696edb3db78160bab2c2a28ba7f56ef6932997f8"
+checksum = "0350b5cb0331628a5916d6c5c0b72e97393b8b6b03b47a9284f4e7f5a405ffd7"
 dependencies = [
  "derive_builder_macro",
 ]
 
 [[package]]
 name = "derive_builder_core"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c11bdc11a0c47bc7d37d582b5285da6849c96681023680b906673c5707af7b0f"
+checksum = "d48cda787f839151732d396ac69e3473923d54312c070ee21e9effcaa8ca0b1d"
 dependencies = [
  "darling",
  "proc-macro2",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "derive_builder_macro"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebcda35c7a396850a55ffeac740804b40ffec779b98fffbb1738f4033f0ee79e"
+checksum = "206868b8242f27cecce124c19fd88157fbd0dd334df2587f36417bafbc85097b"
 dependencies = [
  "derive_builder_core",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
@@ -350,9 +350,9 @@ checksum = "b8dd856d451cc0da70e2ef2ce95a18e39a93b7558bedf10201ad28503f918568"
 
 [[package]]
 name = "magnus"
-version = "0.6.2"
+version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4778544796676e8428e9c622460ebf284bea52d8b10db3aeb449d8b5e61b3a13"
+checksum = "b1597ef40aa8c36be098249e82c9a20cf7199278ac1c1a1a995eeead6a184479"
 dependencies = [
  "magnus-macros",
  "rb-sys",
@@ -368,7 +368,7 @@ checksum = "5968c820e2960565f647819f5928a42d6e874551cab9d88d75e3e0660d7f71e3"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
@@ -394,9 +394,9 @@ checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
 [[package]]
 name = "monostate"
-version = "0.1.9"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15f370ae88093ec6b11a710dec51321a61d420fafd1bad6e30d01bd9c920e8ee"
+checksum = "a20fffcd8ca4c69d31e036a71abc400147b41f90895df4edcb36497a1f8af8bf"
 dependencies = [
  "monostate-impl",
  "serde",
@@ -404,13 +404,13 @@ dependencies = [
 
 [[package]]
 name = "monostate-impl"
-version = "0.1.9"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
+checksum = "bf307cbbbd777a9c10cec88ddafee572b3484caad5cce0c9236523c3803105a6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
@@ -489,18 +489,18 @@ checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.68"
+version = "1.0.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b1106fec09662ec6dd98ccac0f81cef56984d0b49f75c92d8cbad76e20c005c"
+checksum = "3d1597b0c024618f09a9c3b8655b7e430397a36d23fdafec26d6965e9eec3eba"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.33"
+version = "1.0.36"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
 dependencies = [
  "proc-macro2",
 ]
@@ -537,9 +537,9 @@ dependencies = [
 
 [[package]]
 name = "rayon"
-version = "1.8.0"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c27db03db7734835b3f53954b534c91069375ce6ccaa2e065441e07d9b6cdb1"
+checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
 dependencies = [
  "either",
  "rayon-core",
@@ -558,9 +558,9 @@ dependencies = [
 
 [[package]]
 name = "rayon-core"
-version = "1.12.0"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ce3fb6ad83f861aac485e76e1985cd109d9a3713802152be56c3b1f0e0658ed"
+checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
 dependencies = [
  "crossbeam-deque",
  "crossbeam-utils",
@@ -568,18 +568,18 @@ dependencies = [
 
 [[package]]
 name = "rb-sys"
-version = "0.9.89"
+version = "0.9.97"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d197f2c03751ef006f29d593d22aa9068c9c358e04ca503afea0329c366147c"
+checksum = "47d30bcad206b51f2f66121190ca678dce1fdf3a2eae0ac5d838d1818b19bdf5"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.89"
+version = "0.9.97"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b50caf8fd028f12abe00d6debe2ae2adf6202c9ca3caa59487eda710d90fa28"
+checksum = "3cbd92f281615f3c2dcb9dcb0f0576624752afbf9a7f99173b37c4b55b62dd8a"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -587,7 +587,7 @@ dependencies = [
  "quote",
  "regex",
  "shell-words",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
@@ -598,33 +598,27 @@ checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
 
 [[package]]
 name = "regex"
-version = "1.9.5"
+version = "1.10.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "697061221ea1b4a94a624f67d0ae2bfe4e22b8a17b6a192afb11046542cc8c47"
+checksum = "c117dbdfde9c8308975b6a18d71f3f385c89461f7b3fb054288ecf2a2058ba4c"
 dependencies = [
  "aho-corasick",
  "memchr",
  "regex-automata",
- "regex-syntax 0.7.5",
+ "regex-syntax",
 ]
 
 [[package]]
 name = "regex-automata"
-version = "0.3.8"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c2f401f4955220693b56f8ec66ee9c78abffd8d1c4f23dc41a23839eb88f0795"
+checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-syntax 0.7.5",
+ "regex-syntax",
 ]
 
-[[package]]
-name = "regex-syntax"
-version = "0.7.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dbb5fb1acd8a1a18b3dd5be62d25485eb770e05afb408a9627d14d451bae12da"
-
 [[package]]
 name = "regex-syntax"
 version = "0.8.2"
@@ -672,7 +666,7 @@ checksum = "4eca7ac642d82aa35b60049a6eccb4be6be75e599bd2e9adb5f875a737654af2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
@@ -724,20 +718,9 @@ checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
 [[package]]
 name = "syn"
-version = "1.0.109"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
-dependencies = [
- "proc-macro2",
- "quote",
- "unicode-ident",
-]
-
-[[package]]
-name = "syn"
-version = "2.0.38"
+version = "2.0.59"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e96b79aaa137db8f61e26363a0c9b47d8b4ec75da28b7d1d614c2303e232408b"
+checksum = "4a6531ffc7b071655e4ce2e04bd464c4830bb585a61cabb96cf808f05172615a"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -761,24 +744,24 @@ checksum = "10712f02019e9288794769fba95cd6847df9874d49d871d062172f9dd41bc4cc"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.38",
+ "syn",
 ]
 
 [[package]]
 name = "tokenizers"
-version = "0.4.4"
+version = "0.5.0"
 dependencies = [
  "magnus",
  "onig",
  "serde",
- "tokenizers 0.15.2",
+ "tokenizers 0.19.1",
 ]
 
 [[package]]
 name = "tokenizers"
-version = "0.15.2"
+version = "0.19.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3dd47962b0ba36e7fd33518fbf1754d136fd1474000162bbf2a8b5fcb2d3654d"
+checksum = "e500fad1dd3af3d626327e6a3fe5050e664a6eaa4708b8ca92f1794aaf73e6fd"
 dependencies = [
  "aho-corasick",
  "derive_builder",
@@ -796,7 +779,7 @@ dependencies = [
  "rayon",
  "rayon-cond",
  "regex",
- "regex-syntax 0.8.2",
+ "regex-syntax",
  "serde",
  "serde_json",
  "spm_precompiled",
@@ -823,9 +806,9 @@ dependencies = [
 
 [[package]]
 name = "unicode-segmentation"
-version = "1.10.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1dd624098567895118886609431a7c3b8f516e41d30e0643f03d94592a147e36"
+checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
 
 [[package]]
 name = "unicode-width"