autocorrect-rb 2.1.1.beta1-x86_64-darwin → 2.1.2.beta4-x86_64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 651a37d878b3b87f6570cbc9445d4668403cb72844b7ed1a6a5803587edad1ad
-  data.tar.gz: 609f760e0f1b625214091f66f2d7764b05f3821ec4e84777546f6a940d0f9319
+  metadata.gz: ce9de2eae2914cae8b0c123aa2cd20bee5d43f39756af796a5f41bf899db67c7
+  data.tar.gz: c0e6608734f67a3e91d093351238b78e3c1fed9766d12f6acf559028c7ea1396
 SHA512:
-  metadata.gz: e9b87ccf96ff85e541e1454f6a4ed7127aeec7e846b9ae922357d85b224744041318413e2366510adda552c65e98ead2f7e4719fab456a5cc3c60136ff8174e7
-  data.tar.gz: b1b4d1e7ac8ba1863ca802976a527af3bde0cd06d4bc457a96bd7ba63d5966cb83ee2d4a34fc7317dd6df05d19ff9554d9c087c68658f02b571ce91cc86016da
+  metadata.gz: c68cb0111a38f58e3d453e847c5769d359c18e58d16ffae7fac8cb745c3c20bbf32aeb99f5887c552b4b9a88df6cbc7634b4752644a84973a3f08f7f80be09a4
+  data.tar.gz: c8023f1028743a7fbb745da579308cc0c1ddf31910a8d784129ae158f21cff4ebda05b04e133d517d1500693e1e6e2dc61fe5849381a214248f82019ed4e2c9a

data/README.md

@@ -1,9 +1,9 @@
-# AutoCorrect for Node.js
+# AutoCorrect for Ruby
 
-The Native Node.js version of [AutoCorrect](https://github.com/huacnlee/autocorrect) built on [NAPI.RS](https://napi.rs).
+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-py)
+- 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)
@@ -12,28 +12,65 @@ The Native Node.js version of [AutoCorrect](https://github.com/huacnlee/autocorr
 ## Installation
 
 ```bash
-$ yarn add autocorrect-node
+$ bundle add autocorrect-rb
 ```
 
 ## Usage
 
-```js
-const autocorrect = require('autocorrect-node');
-
-const out = autocorrect.format('Hello你好.');
-console.log(out);
-// Hello 你好。
-
-out = autocorrect.formatFor("let title = 'Hello你好。'", 'js');
-// let title = 'Hello 你好。'
-
-const result = autocorrect.lintFor("let title = 'Hello你好。'", 'js');
-console.log(result);
-// {
-//   filepath: 'js',
-//   lines: [
-//     { l: 1, c: 13, new: "'Hello 你好。'", old: "'Hello你好。'", severity: 1 }
-//   ],
-//   error: ''
-// }
+```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_lor("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: ''
+# }
+```
+
+## Benchmarks
+
+🎊 Rust version is 3x 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
+```
+
+### 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
 ```

data/Rakefile

@@ -7,6 +7,7 @@ rescue LoadError
 end
 
 require "bundler/gem_tasks"
+require "rubygems/package_task"
 require "rake/testtask"
 require "rake/extensiontask"
 require "bundler"
@@ -19,22 +20,57 @@ CROSS_PLATFORMS = %w[
   x86_64-linux
 ]
 
-spec = Bundler.load_gemspec("autocorrect-rb.gemspec")
-
 Rake::TestTask.new(:test) do |t|
   t.libs << "test"
   t.libs << "lib"
   t.test_files = FileList["test/**/*_test.rb"]
 end
 
-Rake::ExtensionTask.new("autocorrect") do |ext|
-  ext.gem_spec = spec
+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 build: :compile
+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 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，预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，一直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 test: :compile
-task default: %i[compile test]
+task default: %i[test]

data/ext/autocorrect/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+edition = "2021"
+name = "autocorrect-rb"
+version = "2.1.1"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[lib]
+crate-type = ["cdylib"]
+name = "autocorrect"
+
+[dependencies]
+autocorrect = {path = "../../../autocorrect", version = ">=1.0.0"}
+magnus = "0.3"

data/ext/autocorrect/extconf.rb

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

data/ext/autocorrect/src/lib.rs

@@ -0,0 +1,125 @@
+use magnus::{define_class, function, Error, 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)
+    }
+}
+
+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.clone() as usize,
+            })
+            .collect::<_>(),
+        error: result.error,
+    }
+    .to_hash()
+    .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))?;
+
+    Ok(())
+}

data/lib/autocorrect-rb.rb

@@ -3,10 +3,5 @@ begin
   ruby_version = /(\d+\.\d+)/.match(::RUBY_VERSION)
   require_relative "autocorrect/#{ruby_version}/autocorrect"
 rescue LoadError
-  # fall back to the extension compiled upon installation.
-  # use "require" instead of "require_relative" because non-native gems will place C extension files
-  # in Gem::BasicSpecification#extension_dir after compilation (during normal installation), which
-  # is in $LOAD_PATH but not necessarily relative to this file
-  # (see https://github.com/sparklemotion/nokogiri/issues/2300 for more)
   require "autocorrect/autocorrect"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: autocorrect-rb
 version: !ruby/object:Gem::Version
-  version: 2.1.1.beta1
+  version: 2.1.2.beta4
 platform: x86_64-darwin
 authors:
 - Jason Lee
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-10-12 00:00:00.000000000 Z
+date: 2022-10-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -34,6 +34,9 @@ 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.bundle
 - lib/autocorrect/3.0/autocorrect.bundle