spellkit 0.1.0.pre.1

data/ext/spellkit/Cargo.lock

@@ -0,0 +1,402 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "allocator-api2"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
+
+[[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",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2261d10cca569e4643e526d8dc2e62e433cc8aba21ab764233731f8d369bf394"
+
+[[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 = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9"
+
+[[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 = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "equivalent"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
+
+[[package]]
+name = "foldhash"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"
+
+[[package]]
+name = "glob"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
+
+[[package]]
+name = "hashbrown"
+version = "0.15.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
+dependencies = [
+ "allocator-api2",
+ "equivalent",
+ "foldhash",
+]
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
+
+[[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 = "0.2.176"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "58f929b4d672ea937a23a1ab494143d968337a5f47e56d0815df1e0890ddf174"
+
+[[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 = "magnus"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d87ae53030f3a22e83879e666cb94e58a7bdf31706878a0ba48752994146dab"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+
+[[package]]
+name = "magnus-macros"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5968c820e2960565f647819f5928a42d6e874551cab9d88d75e3e0660d7f71e3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
+
+[[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 = "proc-macro2"
+version = "1.0.101"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rb-sys"
+version = "0.9.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f900d1ce4629a2ebffaf5de74bd8f9c1188d4c5ed406df02f97e22f77a006f44"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef1e9c857028f631056bcd6d88cec390c751e343ce2223ddb26d23eb4a151d59"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+
+[[package]]
+name = "rb-sys-env"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
+
+[[package]]
+name = "regex"
+version = "1.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b5288124840bee7b386bc413c487869b360b2b4ec421ea56425128692f2a82c"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "833eb9ce86d40ef33cb1306d8accf7bc8ec2bfea4355cbdebb3df68b40925cad"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "caf4aa5b0f434c91fe5c7f1ecb6a5ece2130b02ad2a590589dda5146df959001"
+
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "ryu"
+version = "1.0.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
+
+[[package]]
+name = "seq-macro"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
+
+[[package]]
+name = "serde"
+version = "1.0.227"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "80ece43fc6fbed4eb5392ab50c07334d3e577cbf40997ee896fe7af40bba4245"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.227"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a576275b607a2c86ea29e410193df32bc680303c82f31e275bbfcafe8b33be5"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.227"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "51e694923b8824cf0e9b382adf0f60d4e05f348f357b38833a3fa5ed7c2ede04"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.145"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "402a6f66d8c709116cf22f558eab210f5a50187f702eb4d7e5ef38d9a7f1c79c"
+dependencies = [
+ "itoa",
+ "memchr",
+ "ryu",
+ "serde",
+ "serde_core",
+]
+
+[[package]]
+name = "shell-words"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "spellkit"
+version = "0.1.0"
+dependencies = [
+ "hashbrown",
+ "magnus",
+ "regex",
+ "serde",
+ "serde_json",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ede7c438028d4436d71104916910f5bb611972c5cfd7f89b8300a8186e6fada6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "tinyvec"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa5fdc3bce6191a1dbc8c02d5c8bffcf557bafa17c124c5264a458f1b0613fa"
+dependencies = [
+ "tinyvec_macros",
+]
+
+[[package]]
+name = "tinyvec_macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
+
+[[package]]
+name = "unicode-normalization"
+version = "0.1.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5033c97c4262335cded6d6fc3e5c18ab755e1a3dc96376350f3d8e9f009ad956"
+dependencies = [
+ "tinyvec",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "45e46c0661abb7180e7b9c281db115305d49ca1709ab8242adf09666d2173c65"

data/ext/spellkit/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "spellkit"
+version = "0.1.0"
+edition = "2021"
+authors = ["Chris Petersen <chris@petersen.io>"]
+license = "MIT"
+description = "Fast, safe typo correction for search-term extraction"
+
+[lib]
+name = "spellkit"
+crate-type = ["cdylib"]
+
+[dependencies]
+magnus = { version = "0.7", features = ["rb-sys"] }
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+hashbrown = "0.15"
+unicode-normalization = "0.1"
+regex = "1.11"
+
+[dev-dependencies]

data/ext/spellkit/extconf.rb

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

data/ext/spellkit/src/guards.rs

@@ -0,0 +1,57 @@
+use hashbrown::HashSet;
+use regex::Regex;
+
+#[derive(Debug, Clone)]
+pub struct Guards {
+    protected_set: HashSet<String>,
+    protected_patterns: Vec<Regex>,
+}
+
+impl Guards {
+    pub fn new() -> Self {
+        Self {
+            protected_set: HashSet::new(),
+            protected_patterns: Vec::new(),
+        }
+    }
+
+    pub fn load_protected(&mut self, content: &str) {
+        for line in content.lines() {
+            let trimmed = line.trim();
+            if !trimmed.is_empty() && !trimmed.starts_with('#') {
+                self.protected_set.insert(trimmed.to_string());
+                self.protected_set.insert(trimmed.to_lowercase());
+            }
+        }
+    }
+
+    pub fn add_pattern(&mut self, pattern: &str) -> Result<(), String> {
+        match Regex::new(pattern) {
+            Ok(regex) => {
+                self.protected_patterns.push(regex);
+                Ok(())
+            }
+            Err(e) => Err(format!("Invalid regex pattern: {}", e)),
+        }
+    }
+
+    pub fn is_protected(&self, word: &str) -> bool {
+        let lower = word.to_lowercase();
+
+        if self.protected_set.contains(word) || self.protected_set.contains(&lower) {
+            return true;
+        }
+
+        for pattern in &self.protected_patterns {
+            if pattern.is_match(word) {
+                return true;
+            }
+        }
+
+        false
+    }
+
+    pub fn is_protected_normalized(&self, word: &str, normalized: &str) -> bool {
+        self.is_protected(word) || self.is_protected(normalized)
+    }
+}