autocorrect-rb 2.5.6.pre1-aarch64-linux

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: bc119f6317b778e10540c371c025bf14c89e66604acb2e3d7374f4a3c13c8eb6
+  data.tar.gz: 50ff079ddacc56475ef9de4e7ca63afddc34a3b9935cd4d913277b9fd3975b95
+SHA512:
+  metadata.gz: 83601e1a1158968a7736c57498ecb077b20493c9b3ff02bdeb06b576ebd11cf612326818b1828a28ba3f00e95a0cc0a83f6a00677ec550118a2d3ab64b032ad9
+  data.tar.gz: 4f2aee8dad27274cabcf475e1e1d0e5f48cdd174577a3749476bca4f4967f74c655518c65d879cf4a9a71682fd57369c809eb8fa4ad8f6f746406eaa87d7bb32

data/README.md

@@ -0,0 +1,125 @@
+# AutoCorrect for Ruby
+
+<a href="https://rubygems.org/gems/autocorrect-rb"><img src="https://img.shields.io/gem/v/autocorrect-rb?color=1&label=Gem" alt="Gem Version"></a>
+
+The Native Ruby version of [AutoCorrect](https://github.com/huacnlee/autocorrect).
+
+- Rust - [autocorrect](https://github.com/huacnlee/autocorrect)
+- Ruby - [autocorrect-rb](https://github.com/huacnlee/autocorrect/tree/main/autocorrect-rb)
+- Go - [autocorrect-go](https://github.com/longbridgeapp/autocorrect)
+- Python - [autocorrect-py](https://github.com/huacnlee/autocorrect/tree/main/autocorrect-py)
+- Node.js - [autocorrect-node](https://github.com/huacnlee/autocorrect/tree/main/autocorrect-node)
+- JavaScript (Browser) - [autocorrect-wasm](https://github.com/huacnlee/autocorrect/tree/main/autocorrect-wasm)
+- Java - [autocorrect-java](https://github.com/huacnlee/autocorrect/tree/main/autocorrect-java)
+
+## Installation
+
+```bash
+$ bundle add autocorrect-rb
+```
+
+## Usage
+
+```rb
+require('autocorrect-rb')
+
+out = AutoCorrect.format('Hello你好.')
+puts out
+# Hello 你好。
+
+out = AutoCorrect.format_for("title = 'Hello你好。'", 'rb')
+puts out
+# title = 'Hello 你好。'
+
+result = AutoCorrect.lint_for("title = 'Hello你好。'", 'rb')
+puts result
+# {
+#   filepath: 'rb',
+#   lines: [
+#     { l: 1, c: 13, new: "'Hello 你好。'", old: "'Hello你好。'", severity: 1 }
+#   ],
+#   error: ''
+# }
+
+config_str = %({ textRules: { "你好hello": 0 } })
+AutoCorrect.load_config(config_str)
+out = AutoCorrect.format('Hello你好.')
+puts out
+# Hello 你好。
+out = AutoCorrect.format('你好hello')
+puts out
+# 你好hello
+
+# Ignorer, if /path/to/workdir contains .autocorrectignore or .gitignore
+ignorer = AutoCorrect::Ignorer.new("/path/to/")
+ignorer.ignored?("README.md")
+```
+
+## Benchmarks
+
+🎊 Rust version is ~3.5x faster than the Ruby (pure) version.
+
+> NOTE: In this case Rust version has more complex rules.
+
+### Rust version
+
+```bash
+Warming up --------------------------------------
+     format 50 chars    11.348k i/100ms
+    format 100 chars     6.033k i/100ms
+    format 400 chars     1.772k i/100ms
+         format_html   545.000  i/100ms
+Calculating -------------------------------------
+     format 50 chars    111.904k (± 3.1%) i/s -    567.400k in   5.075674s
+    format 100 chars     58.684k (± 2.1%) i/s -    295.617k in   5.039837s
+    format 400 chars     17.266k (± 2.9%) i/s -     86.828k in   5.033234s
+         format_html      5.448k (± 1.5%) i/s -     27.250k in   5.002853s
+```
+
+```
+1000 ms / 111904 i/s = 0.008 ms
+```
+
+### Pure [Ruby version](https://rubygems.org/gems/auto-correct/versions/1.0.0) result:
+
+```bash
+Warming up --------------------------------------
+     format 50 chars     3.167k i/100ms
+    format 100 chars     1.588k i/100ms
+    format 400 chars   496.000  i/100ms
+         format_html   166.000  i/100ms
+Calculating -------------------------------------
+     format 50 chars     31.589k (± 2.5%) i/s -    158.350k in   5.016131s
+    format 100 chars     16.122k (± 1.2%) i/s -     80.988k in   5.024082s
+    format 400 chars      4.946k (± 2.6%) i/s -     24.800k in   5.017711s
+         format_html      1.659k (± 1.7%) i/s -      8.300k in   5.003164s
+```
+
+### Rust version VS Purge Ruby Version
+
+| Test Case   | Duration (Rust) | Duration (Pure Ruby) | Speedup |
+| ----------- | --------------- | -------------------- | ------- |
+| Foramt 50   | 0.008ms         | 0.031ms              | ~3.8x   |
+| Format 100  | 0.017ms         | 0.062ms              | ~3.6x   |
+| Format 400  | 0.052ms         | 0.2ms                | ~3.8x   |
+| Format HTML | 0.183ms         | 0.67ms               | ~3.6x   |
+
+> 🎈 Rust version about 3.5 ~ 3.8x fast then Ruby (pure version).
+> 
+> By this result, we can see the Ruby version is also fast, but the Rust version is more better.
+
+## Know issues
+
+Bundler install error:
+
+```
+Could not find gem 'autocorrect-rb' with platform 'ruby' in rubygems repository https://rubygems.org/ or installed locally.
+```
+
+To fix this you can run:
+
+```bash
+$ bundle lock --remove-platform ruby
+```
+
+Because of autocorrect-rb not release the gem for `platform: ruby`, but your `Gemfile.lock` specialed that. This command will remove `ruby` platform from your `Gemfile.lock`

data/Rakefile

@@ -0,0 +1,97 @@
+# autocorrect: false
+require "rubygems"
+
+begin
+  require "bundler/setup"
+rescue LoadError
+  puts "You must `gem install bundler` and `bundle install` to run rake tasks"
+end
+
+require "bundler/gem_tasks"
+require "rubygems/package_task"
+require "rake/testtask"
+require "rake/extensiontask"
+require "bundler"
+
+CROSS_PLATFORMS = %w[
+  aarch64-linux
+  arm64-darwin
+  x64-mingw32
+  x86_64-darwin
+  x86_64-linux
+]
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+spec = Bundler.load_gemspec("autocorrect-rb.gemspec")
+
+# Make a autocorrect-rb-0.0.0.gem
+# Disable release gem for platform: ruby, because autocorrect rust source build is complex.
+# Gem::PackageTask.new(spec).define
+
+# Make a native gem, eg. autocorrect-rb-0.0.0-x86_64-linux.gem
+Rake::ExtensionTask.new("autocorrect", spec) do |ext|
+  # Compile output autocorrect.so into lib/autocorrect/autocorrect.so
+  ext.lib_dir = "lib/autocorrect"
+  ext.source_pattern = "*.{rs,toml}"
+  ext.cross_compile = true
+  ext.cross_platform = CROSS_PLATFORMS
+end
+
+task :bench do
+  require "benchmark/ips"
+  require "./lib/autocorrect-rb"
+
+  html = open("./test/fixtures/example.txt").read
+
+  Benchmark.ips do |x|
+    x.report("format 50 chars") do |n|
+      n.times do
+        AutoCorrect.format("【野村：重申吉利汽车(00175)“买入”评级 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称")
+      end
+    end
+    x.report("format 100 chars") do |n|
+      n.times do
+        AutoCorrect.format("【野村：重申吉利汽车(00175)“买入”评级 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称，【野村：重申吉利汽车(00175)“买入”评�� 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称")
+      end
+    end
+    x.report("format 400 chars") do |n|
+      n.times do
+        AutoCorrect.format("【野村：重申吉利汽车(00175)“买入”评级 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称，上调吉利汽车(00175)目标价12.58%，由15.9港元升至17.9港元，并维持吉汽为行业首选股，重申对其“买入”评级，坚信吉汽长远可成为行业赢家。 该行称，随着公司销量持续复苏及产品组合改善，预计今年销量可达148万辆，同比升9%，较公司原定目标销量141万辆为高。 该行又称称，上调公司今明两年每股盈利预测各13%及升毛利率0.1个百分点，以反映销量较预期高2%及产品组合改善，主要是由领克品牌带动。公司自去年8月开始已持续投资领克品牌及进行市场推广，带动领克销量环比有所改变，��期今明两年领克将占整体销量的11%及14%。 该行表示，由于低端国产车品牌在欠缺新车款及科技下，行业整合度将提升。另外，公司从去年第二季到12月为止，一��都积极推动经销商去库存，这将有利公司今年利润率复苏。")
+      end
+    end
+
+    x.report("format_html") do |n|
+      n.times do
+        AutoCorrect.format_for(html, "text.html")
+      end
+    end
+  end
+end
+
+task :memory do
+  require "memory_profiler"
+  require "./lib/autocorrect-rb"
+
+  html = open("./test/fixtures/example.txt").read
+
+  report = MemoryProfiler.report do
+    20_000.times do
+      AutoCorrect.format("【野村：重申吉利汽车(00175)“买入”评级 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称，【野村：重申吉利汽车(00175)“买入”评�� 上调目标价至17.9港元】智通财经APP获悉，野村发布报告称")
+      AutoCorrect.format_for(html, "text.html")
+    end
+  end
+
+  GC.start
+  report.pretty_print
+
+  puts "------------------------- Result Guide -------------------------"
+  puts "If [Total retained] have any bytes, there will have memory leak."
+end
+
+task test: :compile
+task default: %i[test]

data/ext/autocorrect/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+edition = "2021"
+name = "autocorrect-rb"
+version = "2.5.5"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[lib]
+crate-type = ["cdylib"]
+name = "autocorrect"
+
+[dependencies]
+autocorrect = "2"
+magnus = "0.4"

data/ext/autocorrect/extconf.rb

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

data/ext/autocorrect/src/lib.rs

@@ -0,0 +1,151 @@
+use magnus::{define_class, function, method, Error, Module, Object};
+
+#[derive(Debug, Clone)]
+pub struct LineResult {
+    line: usize,
+    col: usize,
+    new: String,
+    old: String,
+    severity: usize,
+}
+
+impl LineResult {
+    pub fn line(&self) -> usize {
+        self.line
+    }
+
+    pub fn col(&self) -> usize {
+        self.col
+    }
+
+    pub fn get_new(&self) -> String {
+        self.new.clone()
+    }
+
+    pub fn old(&self) -> String {
+        self.old.clone()
+    }
+
+    pub fn severity(&self) -> usize {
+        self.severity
+    }
+
+    pub fn inspect(&self) -> String {
+        format!("{:?}", self)
+    }
+
+    pub fn to_hash(&self) -> Result<magnus::RHash, Error> {
+        let hash = magnus::RHash::new();
+        hash.aset("line", self.line())?;
+        hash.aset("col", self.col())?;
+        hash.aset("new", self.get_new())?;
+        hash.aset("old", self.old())?;
+        hash.aset("severity", self.severity())?;
+        Ok(hash)
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct LintResult {
+    pub filepath: String,
+    pub lines: Vec<LineResult>,
+    pub error: String,
+}
+
+impl LintResult {
+    pub fn filepath(&self) -> String {
+        self.filepath.clone()
+    }
+
+    pub fn lines(&self) -> Vec<LineResult> {
+        self.lines.clone()
+    }
+
+    pub fn error(&self) -> String {
+        self.error.clone()
+    }
+
+    pub fn inspect(&self) -> String {
+        format!("{:?}", self)
+    }
+
+    pub fn to_hash(&self) -> Result<magnus::RHash, Error> {
+        let hash = magnus::RHash::new();
+        hash.aset("filepath", self.filepath())?;
+        hash.aset(
+            "lines",
+            self.lines()
+                .iter()
+                .map(|l| l.to_hash().unwrap())
+                .collect::<Vec<magnus::RHash>>(),
+        )?;
+        hash.aset("error", self.error())?;
+        Ok(hash)
+    }
+}
+
+#[magnus::wrap(class = "AutoCorrect::Ignorer")]
+pub struct Ignorer {
+    core: autocorrect::ignorer::Ignorer,
+}
+
+impl Ignorer {
+    pub fn new(work_dir: String) -> Self {
+        Ignorer {
+            core: autocorrect::ignorer::Ignorer::new(&work_dir),
+        }
+    }
+
+    fn is_ignored(&self, path: String) -> bool {
+        self.core.is_ignored(&path)
+    }
+}
+
+pub fn format(input: String) -> String {
+    autocorrect::format(&input)
+}
+
+pub fn format_for(input: String, filename_or_ext: String) -> String {
+    autocorrect::format_for(&input, &filename_or_ext).out
+}
+
+pub fn lint_for(input: String, filename_or_ext: String) -> magnus::RHash {
+    let result = autocorrect::lint_for(&input, &filename_or_ext);
+
+    LintResult {
+        filepath: filename_or_ext,
+        lines: result
+            .lines
+            .iter()
+            .map(|l| LineResult {
+                line: l.line,
+                col: l.col,
+                new: l.new.clone(),
+                old: l.old.clone(),
+                severity: l.severity as usize,
+            })
+            .collect::<_>(),
+        error: result.error,
+    }
+    .to_hash()
+    .unwrap()
+}
+
+pub fn load_config(config_str: String) {
+    autocorrect::config::load(&config_str).unwrap();
+}
+
+#[magnus::init(name = "autocorrect")]
+fn init() -> Result<(), Error> {
+    let class = define_class("AutoCorrect", Default::default())?;
+    class.define_singleton_method("format", function!(format, 1))?;
+    class.define_singleton_method("format_for", function!(format_for, 2))?;
+    class.define_singleton_method("lint_for", function!(lint_for, 2))?;
+    class.define_singleton_method("load_config", function!(load_config, 1))?;
+
+    let ignorer_class = class.define_class("Ignorer", Default::default())?;
+    ignorer_class.define_singleton_method("new", function!(Ignorer::new, 1))?;
+    ignorer_class.define_method("ignored?", method!(Ignorer::is_ignored, 1))?;
+
+    Ok(())
+}

data/lib/autocorrect-rb.rb

@@ -0,0 +1,7 @@
+begin
+  # load the precompiled extension file
+  ruby_version = /(\d+\.\d+)/.match(::RUBY_VERSION)
+  require_relative "autocorrect/#{ruby_version}/autocorrect"
+rescue LoadError
+  require "autocorrect/autocorrect"
+end

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification
+name: autocorrect-rb
+version: !ruby/object:Gem::Version
+  version: 2.5.6.pre1
+platform: aarch64-linux
+authors:
+- Jason Lee
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2023-01-03 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rb_sys
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.18
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.18
+description: AutoCorrect is a linter and formatter to help you to improve copywriting,
+  correct spaces, words, punctuations between CJK (Chinese, Japanese, Korean).
+email:
+- huacnlee@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- Rakefile
+- ext/autocorrect/Cargo.toml
+- ext/autocorrect/extconf.rb
+- ext/autocorrect/src/lib.rs
+- lib/autocorrect-rb.rb
+- lib/autocorrect/2.7/autocorrect.so
+- lib/autocorrect/3.0/autocorrect.so
+- lib/autocorrect/3.1/autocorrect.so
+homepage: https://github.com/huacnlee/autocorrect
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.7'
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: 3.2.dev
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">"
+    - !ruby/object:Gem::Version
+      version: 1.3.1
+requirements: []
+rubygems_version: 3.3.22
+signing_key:
+specification_version: 4
+summary: AutoCorrect is a linter and formatter to help you to improve copywriting.
+test_files: []