xre 0.5.0 → 0.5.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dd678fdce2f6470ed6b54353fcb9f6102838700e3274c37b69c288e6de43cf27
-  data.tar.gz: 0defab74ebf333046436672a1bc0ce464ff2ebe5c4691c134ab0f158c3cecd9a
+  metadata.gz: 93ba49bc70fd3401c2f77992616d79f1b0154546a5bd8179d73579c6e92a8c78
+  data.tar.gz: 171f4ac8e4ed4838c1933964bb67f0676931e47e3754e48a7a3b4fe2a77e8521
 SHA512:
-  metadata.gz: 13701511bdc2f5d4739338e129bc23a8dab87fe87ae3100f9bd1c5c22b91484a534665628178c214527d38a333e7b9635a7ce44c9b7b5177b7f7a3afdd88dbdf
-  data.tar.gz: fb203f0508485913aba5e9508a5104cae67f52d407605d96fdea6340a4f2f8d6a636b603e455195d29724dfa5d8fece0f50367529635f9491ff5006b6d22c006
+  metadata.gz: f607af2e3d89f47bd22024a7c6e97c5ec4d18ff2c17f53d20c4fa9da6f70db4ee63153ca2a05681bf883cfdb6017e0c049fe5e583df35b23deef023dd68d8693
+  data.tar.gz: c44b557ca39348ee05bcd4ac4787d4f8c8743c6323f56d5a141a5f25fd5bf8c602dece627dbe0587756217d641813c311038593a1d08016e82ebaf25b115bff3

data/Cargo.lock

@@ -65,9 +65,9 @@ dependencies = [
 
 [[package]]
 name = "either"
-version = "1.10.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "11157ac094ffbdde99aa67b23417ebdd801842852b500e395a45a9c0aac03e4a"
+checksum = "a47c1c47d2f5964e29c61246e81db715514cd532db6b5116a25ea3c03d6780a2"
 
 [[package]]
 name = "glob"
@@ -159,36 +159,36 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.79"
+version = "1.0.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e835ff2298f5721608eb1a980ecaee1aef2c132bf95ecc026a11b7bf3c01c02e"
+checksum = "3d1597b0c024618f09a9c3b8655b7e430397a36d23fdafec26d6965e9eec3eba"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.35"
+version = "1.0.36"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
 dependencies = [
  "proc-macro2",
 ]
 
 [[package]]
 name = "rb-sys"
-version = "0.9.90"
+version = "0.9.96"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55d933382388cc7a6fdfd54e222eca7994791ac4b9ce5c9e8df280c739d86bbe"
+checksum = "49afe6f8e47144fe597a228f5b817b11fbc53a4aaee436b7ad1c0a081a9dbd7c"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.90"
+version = "0.9.96"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebc5a7e3a875419baaa0d8cc606cdfb9361b444cb7e5abcf0de4693025887374"
+checksum = "bd0d280a17a2c69a63cd9ba3381970f4c25e6104bc771678d1a70f19cac920c5"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -260,9 +260,9 @@ checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
 [[package]]
 name = "syn"
-version = "2.0.57"
+version = "2.0.60"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "11a6ae1e52eb25aab8f3fb9fca13be982a373b8f1157ca14b897a825ba4a2d35"
+checksum = "909518bc7b1c9b779f1bbf07f2929d35af9f0f37e47c6e9ef7f9dddc1e1821f3"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -283,13 +283,14 @@ checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
 
 [[package]]
 name = "windows-targets"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7dd37b7e5ab9018759f893a1952c9420d060016fc19a472b4bb20d1bdd694d1b"
+checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
 dependencies = [
  "windows_aarch64_gnullvm",
  "windows_aarch64_msvc",
  "windows_i686_gnu",
+ "windows_i686_gnullvm",
  "windows_i686_msvc",
  "windows_x86_64_gnu",
  "windows_x86_64_gnullvm",
@@ -298,51 +299,58 @@ dependencies = [
 
 [[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
+checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
 
 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
+checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
 
 [[package]]
 name = "windows_i686_gnu"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
+checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
 
 [[package]]
 name = "windows_i686_msvc"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
+checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
 
 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
+checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
+checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
 
 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.52.4"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"
+checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
 
 [[package]]
 name = "xre"
 version = "0.1.0"
 dependencies = [
  "magnus",
+ "rb-sys",
  "regex",
  "unicode-segmentation",
 ]

data/README.md

@@ -1,35 +1,95 @@
-# xre
+# Xre
 
-some rust regexes for ruby
+This is a rust extension for finding all the matches in a text.
+It's a simple extension that is used in one part of our codebase and this extension makes it substantially faster.
 
-## Installation
+## Why?
 
-Install the gem and add to the application's Gemfile by executing:
+The main reason for this extension is that we have a unique use case where we need to find all captures
+with their respectful offsets in a large text and we need to do this for a huge number of regexes and texts.
+This is a slow operation in ruby since the regular `scan` does not provide the actual captures,
+but only the offsets. This extension provides the captures and offsets in a single call for a
+list of regexes to avoid the overhead of calling the regex engine multiple times.
 
-    $ bundle add xre
+Moreover, another part of the problem is that we also require the surrounding text of the capture
+with some radius, which is also not possible with the regular `scan` method without resorting to iterating
+the whole text multiple times.
 
-If bundler is not being used to manage dependencies, install the gem by executing:
+> 🤓
+> Another a bit more technical reason for why the rust extension is faster is that ruby strings are
+> indexed in characters(`O(n)`), but rust strings are indexed in bytes(`O(1)`). And with a careful
+> iteration over the characters on the rust side(see `regex_list.rs#captures_with_context` and `utils.rs#find_char_index`) as we go through the text we can avoid multiple(`n`)
+> `O(n)` operations that ruby would have to do, reducing the algorithmic complexity from
+> `O(n^2)` to `O(n)` for one regex, and from `O(m * n^2)` to `O(m * n)`(where `m` and `n` are the number
+> of regexes and the number of texts respectfuly) for multiple regexes.
 
-    $ gem install xre
+## Developing:
 
-## Usage
+The simplest way to develop the gem locally without reinstalling the gem is to just:
 
-todo
+1. change the
+   `gem "xre"` in the `Gemfile` to `gem "xre", path: "xre"`
+2. run `bundle install`
 
-## Development
+and you're good to go. Just change the code(then compile the rust code if you changed it, more on that below),
+go into `rails c` and hack away.
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+Another simple way is to:
 
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+1. change the gem code(then, once again, compile the rust code if you changed it)
+2. go into `rails c` or the console of your choosing
+3. run `require_relative "xre/lib/xre"`
 
-## Contributing
+all done.
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/vagab/xre. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/vagab/xre/blob/main/CODE_OF_CONDUCT.md).
+> 💡Note: _The following part of the readme assumes that you're in the `xre` directory inside `clearscope` project._
 
-## License
+### How to build rust code locally:
 
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+```bash
+rake compile # or just rake
+```
 
-## Code of Conduct
+sometimes you might need to clean the build:
 
-Everyone interacting in the xre project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/vagab/xre/blob/main/CODE_OF_CONDUCT.md).
+```bash
+rake clean && rake compile
+```
+
+you might need to install rust toolchain for that:
+
+```bash
+curl https://sh.rustup.rs -sSf | sh
+```
+
+### How to run tests:
+
+**Ruby tests:**
+
+```bash
+bundle exec rake spec
+```
+
+**Rust tests:**
+
+```bash
+cargo test # you will need rust toolchain for that
+```
+
+**Rust linting:**
+
+````bash
+# you will need rust toolchain for that
+cargo fmt # will format the code
+cargo clippy # will suggest improvements, not only style ones
+```
+
+## Publishing:
+
+The codebase includes `xre/Rakefile` which in turn defines a `gem:native`
+task that compiles the extension for the `x86_64-linux`, `x86_64-darwin`, and `arm64-darwin`
+and puts the compiled gems into `xre/pkg/` directory, from where one should
+`gem push xre-<version>-x86_64-linux.gem` to publish the gem.
+
+> Note: You will need a docker installed on your machine for that
+````

data/ext/xre/Cargo.toml

@@ -11,5 +11,6 @@ crate-type = ["cdylib"]
 
 [dependencies]
 magnus = "0.6.2"
+rb-sys = "0.9.96"
 regex = "1.10.4"
 unicode-segmentation = "1.11.0"

data/ext/xre/src/regex_list.rs

@@ -1,5 +1,7 @@
 mod utils;
 
+use std::cmp::Reverse;
+
 use magnus::{exception, Error};
 use regex::{escape, Match, Regex, RegexBuilder};
 use unicode_segmentation::UnicodeSegmentation;
@@ -23,7 +25,7 @@ impl RegexList {
     pub fn build_from_strings(targets: Vec<Vec<String>>) -> Result<Self, Error> {
         let targets = targets
             .iter()
-            .map(|t| combine_into_regex_like(t))
+            .map(|t| combine_into_regex_like(t as &[String]))
             .collect::<Vec<String>>();
 
         Self::new(targets)
@@ -71,13 +73,13 @@ fn fuzzy_escape(grapheme: &str) -> String {
     }
 }
 
-fn combine_into_regex_like(targets: &Vec<String>) -> String {
+fn combine_into_regex_like(targets: &[String]) -> String {
     let mut targets = targets
         .iter()
-        .map(|t| t.graphemes(true).map(|g| fuzzy_escape(g)).collect())
+        .map(|t| t.graphemes(true).map(fuzzy_escape).collect())
         .collect::<Vec<String>>();
 
-    targets.sort_unstable_by(|a, b| b.len().cmp(&a.len()));
+    targets.sort_unstable_by_key(|a| Reverse(a.len()));
 
     format!("(?im:({}))", targets.join("|"))
 }
@@ -130,7 +132,7 @@ fn captures<'a>(target: &'a Regex, subject: &'a str) -> Result<Vec<Match<'a>>, E
     target
         .captures_iter(subject)
         .map(|m| {
-            m.get(0).ok_or(Error::new(
+            m.get(1).ok_or(Error::new(
                 exception::runtime_error(),
                 "No capture group found",
             ))

data/lib/xre/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Xre
-  VERSION = "0.5.0"
+  VERSION = "0.5.5"
 end

data/lib/xre.rb

@@ -18,7 +18,7 @@ module Xre
     end
 
     def inspect
-      "#<Xre::RegexList targets=#{__targets} new"
+      "#<Xre::RegexList targets=#{__targets}"
     end
 
     private :__captures_with_context, :__captures_without_context, :__targets

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xre
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.5
 platform: ruby
 authors:
 - barseek
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-04-18 00:00:00.000000000 Z
+date: 2024-04-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: 0.9.96
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: 0.9.96
 description:
 email:
 - sergey.b@hey.com
@@ -42,21 +42,6 @@ files:
 - ext/xre/src/regex_list/utils.rs
 - lib/xre.rb
 - lib/xre/version.rb
-- tmp/arm64-darwin21/stage/Cargo.lock
-- tmp/arm64-darwin21/stage/Cargo.toml
-- tmp/arm64-darwin21/stage/ext/xre/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.lock
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/ext/xre/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.lock
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/ext/xre/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.lock
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/ext/xre/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.lock
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/Cargo.toml
-- tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/tmp/arm64-darwin21/stage/ext/xre/Cargo.toml
 homepage: https://github.com/vagab/xre
 licenses:
 - MIT
@@ -71,14 +56,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.0.0
+      version: '3.1'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: 3.3.11
 requirements: []
-rubygems_version: 3.4.10
+rubygems_version: 3.5.9
 signing_key:
 specification_version: 4
 summary: short summary, because RubyGems requires one.