xre 0.3.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 6f016c5f913f154b6bb94e3bd8ebe17e01c540ba11b53b58e57aa1ce3198ec20
+  data.tar.gz: dca10ca30f92d2530a85b9d90a7e42a36d3324bd1447499b779fcd9be8cf925e
+SHA512:
+  metadata.gz: 4527e85bdb47b7c2425e3bf3df994c6f30f2f3ea221f6dbd87d11bab361836487fe06bb53c9103c398486028f2aa62ed28f0881e5b5b8e3ab89fd8c1a3bee8f4
+  data.tar.gz: 7ea058c2c310383719a1a835383c4ceb3ec3c82416089076082674613a4ddaa5606ff4f9a8e5a4295d518e60655fcd104549c6923c74b72182450693ce857116

data/Cargo.lock

@@ -0,0 +1,348 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "bindgen"
+version = "0.69.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1"
+
+[[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 = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "clang-sys"
+version = "1.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67523a3b4be3ce1989d607a828d036249522dd9c1c8de7f4dd2dae43a37369d1"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+
+[[package]]
+name = "either"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11157ac094ffbdde99aa67b23417ebdd801842852b500e395a45a9c0aac03e4a"
+
+[[package]]
+name = "glob"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
+
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+
+[[package]]
+name = "libc"
+version = "0.2.153"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
+
+[[package]]
+name = "libloading"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c2a198fb6b0eada2a8df47933734e6d35d350665a33a3593d7164fa52c75c19"
+dependencies = [
+ "cfg-if",
+ "windows-targets",
+]
+
+[[package]]
+name = "magnus"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fc7a31fb0b64761e3cd09a6975577601fccc5f08b8fc9245064fc4f71ed6a9d"
+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 = "2.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c8640c5d730cb13ebd907d8d04b52f55ac9a2eec55b440c8892f40d56c76c1d"
+
+[[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 = "1.0.79"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e835ff2298f5721608eb1a980ecaee1aef2c132bf95ecc026a11b7bf3c01c02e"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rb-sys"
+version = "0.9.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eb81203e271055178603e243fee397f5f4aac125bcd20036279683fb1445a899"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9de9403a6aac834e7c9534575cb14188b6b5b99bafe475d18d838d44fbc27d31"
+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 = "1.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c117dbdfde9c8308975b6a18d71f3f385c89461f7b3fb054288ecf2a2058ba4c"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adad44e29e4c806119491a7f06f03de4d1af22c3a680dd47f1e6e179439d1f56"
+
+[[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 = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
+
+[[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 = "syn"
+version = "2.0.58"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44cfb93f38070beee36b3fef7d4f5a16f27751d94b187b666a5cc5e9b0d30687"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+
+[[package]]
+name = "unicode-segmentation"
+version = "1.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
+
+[[package]]
+name = "windows-targets"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7dd37b7e5ab9018759f893a1952c9420d060016fc19a472b4bb20d1bdd694d1b"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"
+
+[[package]]
+name = "xre"
+version = "0.1.0"
+dependencies = [
+ "magnus",
+ "regex",
+ "unicode-segmentation",
+]

data/Cargo.toml

@@ -0,0 +1,10 @@
+# This Cargo.toml is here to let externals tools (IDEs, etc.) know that this is
+# a Rust project. Your extensions dependencies should be added to the Cargo.toml
+# in the ext/ directory.
+
+[workspace]
+members = ["./ext/xre"]
+resolver = "2"
+
+[profile]
+release.lto = true

data/ext/xre/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "xre"
+version = "0.1.0"
+edition = "2021"
+authors = ["barseek <sergey.b@hey.com>"]
+license = "MIT"
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+magnus = "0.6.2"
+regex = "1.10.4"
+unicode-segmentation = "1.11.0"

data/ext/xre/extconf.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+require "mkmf"
+require "rb_sys/mkmf"
+
+create_rust_makefile("xre")

data/ext/xre/src/lib.rs

@@ -0,0 +1,25 @@
+mod regex_list;
+
+use magnus::{function, method, prelude::*, Error, Ruby};
+use regex_list::RegexList;
+
+#[magnus::init]
+fn init(ruby: &Ruby) -> Result<(), Error> {
+    let module = ruby.define_module("Xre")?;
+    let regex_list = module.define_class("RegexList", ruby.class_object())?;
+    regex_list.define_singleton_method("new", function!(RegexList::new, 1))?;
+    regex_list.define_singleton_method(
+        "build_from_strings",
+        function!(RegexList::build_from_strings, 1),
+    )?;
+    regex_list.define_method(
+        "__captures_with_context",
+        method!(RegexList::captures_with_context, 2),
+    )?;
+    regex_list.define_method(
+        "__captures_without_context",
+        method!(RegexList::captures_without_context, 1),
+    )?;
+    regex_list.define_method("__targets", method!(RegexList::targets, 0))?;
+    Ok(())
+}

data/ext/xre/src/regex_list/utils.rs

@@ -0,0 +1,87 @@
+use std::iter::Enumerate;
+use std::ops::Range;
+use std::str::CharIndices;
+use unicode_segmentation::UnicodeSegmentation;
+
+pub fn find_char_index(iterator: &mut Enumerate<CharIndices>, byte_start: usize) -> usize {
+    iterator
+        .find_map(|(idx, (byte_index, _))| (byte_index >= byte_start).then_some(idx))
+        .unwrap_or_default()
+}
+
+pub fn string_range_with_radius(subject: &str, range: Range<usize>, radius: usize) -> String {
+    let l_text = subject[..range.start]
+        .graphemes(true)
+        .rev()
+        .take(radius)
+        .take_while(|g| *g != "\n")
+        .collect::<String>()
+        .chars()
+        .rev()
+        .collect::<String>();
+    let r_text = subject[range.end..]
+        .graphemes(true)
+        .take(radius)
+        .take_while(|g| *g != "\n")
+        .collect::<String>();
+    format!("{}{}{}", l_text, &subject[range], r_text)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_string_range_with_radius_when_subject_is_too_small() {
+        let subject = "abc";
+        let range = 1..2;
+        let radius = 5;
+        assert_eq!(string_range_with_radius(subject, range, radius), "abc");
+    }
+
+    #[test]
+    fn test_string_range_with_radius() {
+        let subject = "abc def ghi";
+        let range = 4..7;
+        let radius = 5;
+        assert_eq!(
+            string_range_with_radius(subject, range, radius),
+            "abc def ghi"
+        );
+    }
+
+    #[test]
+    fn test_string_range_with_radius_with_non_byte_chars() {
+        let subject = "👨asdf👩asdf👧asdf👦";
+        let range = 13..15;
+        let radius = 5;
+        assert_eq!(
+            string_range_with_radius(subject, range, radius),
+            "sdf👩asdf👧asd"
+        );
+    }
+
+    #[test]
+    fn find_char_index_when_byte_exists() {
+        let subject = "abc def ghi";
+        let mut chars_iterator = subject.char_indices().enumerate();
+        let byte_start = 4;
+        assert_eq!(find_char_index(&mut chars_iterator, byte_start), 4);
+    }
+
+    #[test]
+    fn find_char_index_with_non_byte_chars() {
+        let subject = "👨asdf👩asdf";
+        let mut chars_iterator = subject.char_indices().enumerate();
+        let byte_start = 7;
+        assert_eq!(find_char_index(&mut chars_iterator, byte_start), 4);
+    }
+
+    #[test]
+    fn find_char_index_when_byte_does_not_exist() {
+        let subject = "abc def ghi";
+        let mut chars_iterator = subject.char_indices().enumerate();
+        let byte_start = 100;
+        assert_eq!(find_char_index(&mut chars_iterator, byte_start), 0)
+    }
+}

data/ext/xre/src/regex_list.rs

@@ -0,0 +1,139 @@
+mod utils;
+
+use magnus::{exception, Error};
+use regex::{escape, Match, Regex, RegexBuilder};
+use unicode_segmentation::UnicodeSegmentation;
+use utils::*;
+
+#[magnus::wrap(class = "Xre::RegexList")]
+pub struct RegexList {
+    targets: Vec<Regex>,
+}
+
+impl RegexList {
+    pub fn new(targets: Vec<String>) -> Result<Self, Error> {
+        Ok(Self {
+            targets: targets
+                .iter()
+                .map(|r| regex(r))
+                .collect::<Result<Vec<Regex>, Error>>()?,
+        })
+    }
+
+    pub fn build_from_strings(targets: Vec<Vec<String>>) -> Result<Self, Error> {
+        let targets = targets
+            .iter()
+            .map(|t| combine_into_regex_like(t))
+            .collect::<Vec<String>>();
+
+        Self::new(targets)
+    }
+
+    pub fn targets(&self) -> Vec<String> {
+        self.targets
+            .iter()
+            .map(|r| r.as_str().to_string())
+            .collect()
+    }
+
+    pub fn captures_with_context(
+        &self,
+        subject: String,
+        radius: usize,
+    ) -> Result<Vec<(String, usize, String)>, Error> {
+        Ok(self
+            .targets
+            .iter()
+            .map(|t| captures_with_context(t, &subject, radius))
+            .collect::<Result<Vec<Vec<(String, usize, String)>>, Error>>()?
+            .into_iter()
+            .flatten()
+            .collect())
+    }
+
+    pub fn captures_without_context(&self, subject: String) -> Result<Vec<(String, usize)>, Error> {
+        Ok(self
+            .targets
+            .iter()
+            .map(|t| captures_without_context(t, &subject))
+            .collect::<Result<Vec<Vec<(String, usize)>>, Error>>()?
+            .into_iter()
+            .flatten()
+            .collect())
+    }
+}
+
+fn fuzzy_escape(grapheme: &str) -> String {
+    match grapheme {
+        " " | "\u{00A0}" | "_" | "-" => "[ \u{00A0}_-]?".to_string(),
+        "'" | "‘" | "’" => "['‘’]".to_string(),
+        c => escape(c),
+    }
+}
+
+fn combine_into_regex_like(targets: &Vec<String>) -> String {
+    let mut targets = targets
+        .iter()
+        .map(|t| t.graphemes(true).map(|g| fuzzy_escape(g)).collect())
+        .collect::<Vec<String>>();
+
+    targets.sort_unstable_by(|a, b| b.len().cmp(&a.len()));
+
+    format!("(?im:({}))", targets.join("|"))
+}
+
+fn regex(target: &str) -> Result<Regex, Error> {
+    RegexBuilder::new(target)
+        .multi_line(true)
+        .build()
+        .map_err(|_| Error::new(exception::arg_error(), format!("Invalid regex: {}", target)))
+}
+
+fn captures_with_context(
+    target: &Regex,
+    subject: &str,
+    radius: usize,
+) -> Result<Vec<(String, usize, String)>, Error> {
+    let mut chars_iterator = subject.char_indices().enumerate();
+
+    let captures = captures(target, subject)?;
+
+    captures
+        .iter()
+        .map(|m| {
+            Ok((
+                m.as_str().trim().to_string(),
+                find_char_index(&mut chars_iterator, m.start()),
+                string_range_with_radius(subject, m.start()..m.end(), radius),
+            ))
+        })
+        .collect()
+}
+
+fn captures_without_context(target: &Regex, subject: &str) -> Result<Vec<(String, usize)>, Error> {
+    let mut chars_iterator = subject.char_indices().enumerate();
+
+    let captures = captures(target, subject)?;
+
+    captures
+        .iter()
+        .map(|m| {
+            Ok((
+                m.as_str().trim().to_string(),
+                find_char_index(&mut chars_iterator, m.start()),
+            ))
+        })
+        .collect()
+}
+
+fn captures<'a>(target: &'a Regex, subject: &'a str) -> Result<Vec<Match<'a>>, Error> {
+    target
+        .captures_iter(subject)
+        .map(|m| {
+            m.get(0).ok_or(Error::new(
+                exception::runtime_error(),
+                "No capture group found",
+            ))
+        })
+        .collect::<Result<Vec<Match>, Error>>()
+}

data/lib/xre.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require_relative "xre/xre"
+
+module Xre
+  class RegexList
+    def captures(text, context_radius: nil)
+      if context_radius
+        __captures_with_context(text, context_radius)
+      else
+        __captures_without_context(text)
+      end
+    end
+
+    def inspect
+      "#<Xre::RegexList targets=#{__targets}"
+    end
+
+    private :__captures_with_context, :__captures_without_context, :__targets
+  end
+end