textkit: token counting and the two segmenters

Cargo.lock

@@ -2,6 +2,53 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "aho-corasick"
+version = "1.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c982642fa9e8606056828ee9a8505737230110bb1099153c79efe865c59d12ba"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470"
+
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
+[[package]]
+name = "bit-set"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08807e080ed7f9d5433fa9b275196cfc35414f66a0c79d864dc51a0d825231a3"
+dependencies = [
+ "bit-vec",
+]
+
+[[package]]
+name = "bit-vec"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e764a1d40d510daf35e07be9eb06e75770908c27d411ee6c92109c9840eaaf7"
+
+[[package]]
+name = "bstr"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6bb31b46c14244e20ee9984b11bf5c992b91fb6939fea616e3512c8baecdbe5f"
+dependencies = [
+ "memchr",
+ "regex-automata",
+ "serde_core",
+]
+
 [[package]]
 name = "corpus-core"
 version = "0.1.0"
@@ -18,12 +65,29 @@ version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d0881ea181b1df73ff77ffaaf9c7544ecc11e82fba9b5f27b262a3c73a332555"
 
+[[package]]
+name = "fancy-regex"
+version = "0.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72cf461f865c862bb7dc573f643dd6a2b6842f7c30b07882b56bd148cc2761b8"
+dependencies = [
+ "bit-set",
+ "regex-automata",
+ "regex-syntax",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
 [[package]]
 name = "memchr"
 version = "2.8.3"
@@ -68,6 +132,41 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "regex"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad8553b9b26413251cbf30e620595c7a41b3887f03da04579c0e6b0d6a06b4b2"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6f6ff9a378485b298a5286656da665ba74413d36db0979633275d2e708145d4"
+
+[[package]]
+name = "rustc-hash"
+version = "2.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b1e7f9a428571be2dc5bc0505c13fb6bf936822b894ec87abf8a08a4e51742d"
+
 [[package]]
 name = "schemars"
 version = "1.2.2"
@@ -158,6 +257,13 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "textkit"
+version = "0.1.0"
+dependencies = [
+ "tiktoken-rs",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.20"
@@ -178,6 +284,21 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "tiktoken-rs"
+version = "0.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "027853bbf8c7763b77c5c595f1c271c7d536ced7d6f83452911b944621e57fc2"
+dependencies = [
+ "anyhow",
+ "base64",
+ "bstr",
+ "fancy-regex",
+ "lazy_static",
+ "regex",
+ "rustc-hash",
+]
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.26"