tomos 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7c74f281acc538880271bcdb2face54257d5f9bcf052545ed2fc1dd14a3fd14d
+  data.tar.gz: 6e5ad11384eb2a1a201abb3c9ecf0a2cc3fb4fbebcb06bd3894ab339a5b20c05
+SHA512:
+  metadata.gz: 2b760a8366624a206bac3263b00ec5e741ac95af3d4e1022f3ac92ba5607bd9d70cf9b867c3fba5779faee89eab77f81f1d8675770d0ac16e02f84f0bf04a50d
+  data.tar.gz: 1320c81c79e91005731657752acb25f2b8e4449bb22e413489b3de4a137826ee85d1d08c836818eae3146003441388963cf789c46682219cefb1ab490284a5a0

data/Cargo.lock

@@ -0,0 +1,825 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "getrandom",
+ "once_cell",
+ "version_check",
+ "zerocopy",
+]
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.102"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
+
+[[package]]
+name = "auto_enums"
+version = "0.8.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65398a2893f41bce5c9259f6e1a4f03fbae40637c1bdc755b4f387f48c613b03"
+dependencies = [
+ "derive_utils",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
+[[package]]
+name = "bindgen"
+version = "0.69.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools 0.12.1",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bit-set"
+version = "0.5.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0700ddab506f33b20a03b13996eccd309a48e5ff77d0d95926aa0210fb4e95f1"
+dependencies = [
+ "bit-vec",
+]
+
+[[package]]
+name = "bit-vec"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb"
+
+[[package]]
+name = "bitflags"
+version = "2.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843867be96c8daad0d758b57df9392b6d8d271134fce549de6ce169ff98a92af"
+
+[[package]]
+name = "bstr"
+version = "1.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "63044e1ae8e69f3b5a92c736ca6269b8d12fa7efe39bf34ddb06d102cf0e2cab"
+dependencies = [
+ "memchr",
+ "regex-automata",
+ "serde",
+]
+
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+
+[[package]]
+name = "core_maths"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77745e017f5edba1a9c1d854f6f3a52dac8a12dd5af5d2f54aecf61e43d80d30"
+dependencies = [
+ "libm",
+]
+
+[[package]]
+name = "derive_utils"
+version = "0.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "362f47930db19fe7735f527e6595e4900316b893ebf6d48ad3d31be928d57dd6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "displaydoc"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "fancy-regex"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2"
+dependencies = [
+ "bit-set",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasip2",
+]
+
+[[package]]
+name = "glob"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "icu_collections"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c6b649701667bbe825c3b7e6388cb521c23d88644678e83c0c4d0a621a34b43"
+dependencies = [
+ "displaydoc",
+ "potential_utf",
+ "yoke",
+ "zerofrom",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locale"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "532b11722e350ab6bf916ba6eb0efe3ee54b932666afec989465f9243fe6dd60"
+dependencies = [
+ "icu_collections",
+ "icu_locale_core",
+ "icu_locale_data",
+ "icu_provider",
+ "potential_utf",
+ "tinystr",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locale_core"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "edba7861004dd3714265b4db54a3c390e880ab658fec5f7db895fae2046b5bb6"
+dependencies = [
+ "displaydoc",
+ "litemap",
+ "serde",
+ "tinystr",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locale_data"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1c5f1d16b4c3a2642d3a719f18f6b06070ab0aef246a6418130c955ae08aa831"
+
+[[package]]
+name = "icu_provider"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85962cf0ce02e1e0a629cc34e7ca3e373ce20dda4c4d7294bbd0bf1fdb59e614"
+dependencies = [
+ "displaydoc",
+ "icu_locale_core",
+ "serde",
+ "stable_deref_trait",
+ "writeable",
+ "yoke",
+ "zerofrom",
+ "zerotrie",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_segmenter"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a807a7488f3f758629ae86d99d9d30dce24da2fb2945d74c80a4f4a62c71db73"
+dependencies = [
+ "core_maths",
+ "icu_collections",
+ "icu_locale",
+ "icu_provider",
+ "icu_segmenter_data",
+ "potential_utf",
+ "utf8_iter",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_segmenter_data"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ebbb7321d9e21d25f5660366cb6c08201d0175898a3a6f7a41ee9685af21c80"
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "itertools"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+
+[[package]]
+name = "libc"
+version = "0.2.182"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
+
+[[package]]
+name = "libloading"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7c4b02199fee7c5d21a5ae7d8cfa79a6ef5bb2fc834d6e9058e89c825efdc55"
+dependencies = [
+ "cfg-if",
+ "windows-link",
+]
+
+[[package]]
+name = "libm"
+version = "0.2.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
+
+[[package]]
+name = "litemap"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
+
+[[package]]
+name = "magnus"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b36a5b126bbe97eb0d02d07acfeb327036c6319fd816139a49824a83b7f9012"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+
+[[package]]
+name = "magnus-macros"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "47607461fd8e1513cb4f2076c197d8092d921a1ea75bd08af97398f593751892"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "memchr"
+version = "2.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+
+[[package]]
+name = "potential_utf"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b73949432f5e2a09657003c25bca5e19a0e9c84f8058ca374f49e0ebe605af77"
+dependencies = [
+ "serde_core",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "pulldown-cmark"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83c41efbf8f90ac44de7f3a868f0867851d261b56291732d0cbf7cceaaeb55a6"
+dependencies = [
+ "bitflags",
+ "memchr",
+ "unicase",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "rb-sys"
+version = "0.9.124"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c85c4188462601e2aa1469def389c17228566f82ea72f137ed096f21591bc489"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.124"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "568068db4102230882e6d4ae8de6632e224ca75fe5970f6e026a04e91ed635d3"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+
+[[package]]
+name = "rb-sys-env"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cca7ad6a7e21e72151d56fe2495a259b5670e204c3adac41ee7ef676ea08117a"
+
+[[package]]
+name = "regex"
+version = "1.12.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
+
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "seq-macro"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
+
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "shell-words"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc6fe69c597f9c37bfeeeeeb33da3530379845f10be461a66d16d03eca2ded77"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "stable_deref_trait"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
+
+[[package]]
+name = "strum"
+version = "0.27.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af23d6f6c1a224baef9d3f61e287d2761385a5b88fdab4eb4c6f11aeb54c4bcf"
+dependencies = [
+ "strum_macros",
+]
+
+[[package]]
+name = "strum_macros"
+version = "0.27.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7695ce3845ea4b33927c055a39dc438a45b059f7c1b3d91d38d10355fb8cbca7"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "synstructure"
+version = "0.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "text-splitter"
+version = "0.29.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2979ebb41243f6c8adc1c1adb76f35fe4e59ba2bc07f7863bb56bcc838798bf4"
+dependencies = [
+ "ahash",
+ "auto_enums",
+ "either",
+ "icu_provider",
+ "icu_segmenter",
+ "itertools 0.14.0",
+ "memchr",
+ "pulldown-cmark",
+ "strum",
+ "thiserror",
+ "tiktoken-rs",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tiktoken-rs"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a19830747d9034cd9da43a60eaa8e552dfda7712424aebf187b7a60126bae0d"
+dependencies = [
+ "anyhow",
+ "base64",
+ "bstr",
+ "fancy-regex",
+ "lazy_static",
+ "regex",
+ "rustc-hash",
+]
+
+[[package]]
+name = "tinystr"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42d3e9c45c09de15d06dd8acf5f4e0e399e85927b7f00711024eb7ae10fa4869"
+dependencies = [
+ "displaydoc",
+ "serde_core",
+ "zerovec",
+]
+
+[[package]]
+name = "tomos"
+version = "0.1.0"
+dependencies = [
+ "magnus",
+ "rb-sys",
+ "text-splitter",
+ "tiktoken-rs",
+]
+
+[[package]]
+name = "unicase"
+version = "2.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbc4bc3a9f746d862c45cb89d705aa10f187bb96c76001afab07a0d35ce60142"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "utf8_iter"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
+
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "wasip2"
+version = "1.0.2+wasi-0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9517f9239f02c069db75e65f174b3da828fe5f5b945c4dd26bd25d89c03ebcf5"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "wit-bindgen"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7249219f66ced02969388cf2bb044a09756a083d0fab1e566056b04d9fbcaa5"
+
+[[package]]
+name = "writeable"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
+
+[[package]]
+name = "yoke"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72d6e5c6afb84d73944e5cedb052c4680d5657337201555f9f2a16b7406d4954"
+dependencies = [
+ "stable_deref_trait",
+ "yoke-derive",
+ "zerofrom",
+]
+
+[[package]]
+name = "yoke-derive"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b659052874eb698efe5b9e8cf382204678a0086ebf46982b79d6ca3182927e5d"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zerocopy"
+version = "0.8.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a789c6e490b576db9f7e6b6d661bcc9799f7c0ac8352f56ea20193b2681532e5"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f65c489a7071a749c849713807783f70672b28094011623e200cb86dcb835953"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "zerofrom"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5"
+dependencies = [
+ "zerofrom-derive",
+]
+
+[[package]]
+name = "zerofrom-derive"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zerotrie"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a59c17a5562d507e4b54960e8569ebee33bee890c70aa3fe7b97e85a9fd7851"
+dependencies = [
+ "displaydoc",
+]
+
+[[package]]
+name = "zerovec"
+version = "0.11.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c28719294829477f525be0186d13efa9a3c602f7ec202ca9e353d310fb9a002"
+dependencies = [
+ "serde",
+ "yoke",
+ "zerofrom",
+ "zerovec-derive",
+]
+
+[[package]]
+name = "zerovec-derive"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eadce39539ca5cb3985590102671f2567e659fca9666581ad3411d59207951f3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]

data/Cargo.toml

@@ -0,0 +1,6 @@
+[workspace]
+members = ["ext/tomos"]
+resolver = "2"
+
+[profile.release]
+strip = true

data/ext/tomos/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "tomos"
+version = "0.1.0"
+edition = "2021"
+license = "MIT"
+publish = false
+
+[lib]
+name = "tomos"
+crate-type = ["cdylib"]
+
+[dependencies]
+text-splitter = { version = "0.29", features = ["tiktoken-rs", "markdown"] }
+tiktoken-rs = "0.9"
+magnus = "0.8"
+rb-sys = { version = "0.9", features = ["stable-api-compiled-fallback"] }

data/ext/tomos/extconf.rb

@@ -0,0 +1,4 @@
+require "mkmf"
+require "rb_sys/mkmf"
+
+create_rust_makefile("tomos/tomos")

data/ext/tomos/src/lib.rs

@@ -0,0 +1,89 @@
+use magnus::{function, method, prelude::*, Error, Ruby};
+use text_splitter::{ChunkConfig, MarkdownSplitter, TextSplitter};
+use tiktoken_rs::get_bpe_from_model;
+
+type RbResult<T> = Result<T, Error>;
+
+fn build_chunk_config(
+    ruby: &Ruby,
+    model: &str,
+    capacity: usize,
+    overlap: usize,
+) -> RbResult<ChunkConfig<tiktoken_rs::CoreBPE>> {
+    let bpe = get_bpe_from_model(model).map_err(|e| {
+        Error::new(
+            ruby.exception_arg_error(),
+            format!("unrecognized tiktoken model '{model}': {e}"),
+        )
+    })?;
+
+    let config = ChunkConfig::new(capacity)
+        .with_overlap(overlap)
+        .map_err(|e| {
+            Error::new(
+                ruby.exception_arg_error(),
+                format!("invalid chunk config: {e}"),
+            )
+        })?
+        .with_sizer(bpe);
+
+    Ok(config)
+}
+
+/// Splits unstructured text along Unicode boundaries (sentences, words,
+/// grapheme clusters). Works well on transcripts and content with no
+/// paragraph or section structure.
+#[magnus::wrap(class = "Tomos::Text", free_immediately, size)]
+struct RbText {
+    splitter: TextSplitter<tiktoken_rs::CoreBPE>,
+}
+
+impl RbText {
+    fn new(ruby: &Ruby, model: String, capacity: usize, overlap: usize) -> RbResult<Self> {
+        let config = build_chunk_config(ruby, &model, capacity, overlap)?;
+        Ok(Self {
+            splitter: TextSplitter::new(config),
+        })
+    }
+
+    fn chunks(&self, text: String) -> Vec<String> {
+        self.splitter.chunks(&text).map(str::to_owned).collect()
+    }
+}
+
+/// Splits CommonMark/GFM markdown along structural boundaries (headings,
+/// code fences, list items, block elements) in addition to the Unicode
+/// levels that `RbText` uses. Degrades gracefully to plain-text splitting
+/// when the input contains no markdown structure.
+#[magnus::wrap(class = "Tomos::Markdown", free_immediately, size)]
+struct RbMarkdown {
+    splitter: MarkdownSplitter<tiktoken_rs::CoreBPE>,
+}
+
+impl RbMarkdown {
+    fn new(ruby: &Ruby, model: String, capacity: usize, overlap: usize) -> RbResult<Self> {
+        let config = build_chunk_config(ruby, &model, capacity, overlap)?;
+        Ok(Self {
+            splitter: MarkdownSplitter::new(config),
+        })
+    }
+
+    fn chunks(&self, text: String) -> Vec<String> {
+        self.splitter.chunks(&text).map(str::to_owned).collect()
+    }
+}
+
+#[magnus::init]
+fn init(ruby: &Ruby) -> RbResult<()> {
+    let module = ruby.define_module("Tomos")?;
+
+    let text = module.define_class("Text", ruby.class_object())?;
+    text.define_singleton_method("new", function!(RbText::new, 3))?;
+    text.define_method("chunks", method!(RbText::chunks, 1))?;
+
+    let markdown = module.define_class("Markdown", ruby.class_object())?;
+    markdown.define_singleton_method("new", function!(RbMarkdown::new, 3))?;
+    markdown.define_method("chunks", method!(RbMarkdown::chunks, 1))?;
+
+    Ok(())
+}

data/lib/tomos/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Tomos
+  VERSION = "0.1.0"
+end

data/lib/tomos.rb

@@ -0,0 +1,4 @@
+# frozen_string_literal: true
+
+require "tomos/version"
+require "tomos/tomos"

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification
+name: tomos
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Dan Frenette
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rb_sys
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+email:
+- dan.r.frenette@gmail.com
+executables: []
+extensions:
+- ext/tomos/extconf.rb
+extra_rdoc_files: []
+files:
+- Cargo.lock
+- Cargo.toml
+- ext/tomos/Cargo.toml
+- ext/tomos/extconf.rb
+- ext/tomos/src/lib.rs
+- lib/tomos.rb
+- lib/tomos/tomos.bundle
+- lib/tomos/version.rb
+homepage: https://github.com/danfrenette/tomos
+licenses:
+- MIT
+metadata: {}
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 4.0.1
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 4.0.3
+specification_version: 4
+summary: Token-aware text chunking for RAG pipelines, powered by Rust
+test_files: []