sanscript 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 348f8d72cc3d76ba760a4225a4f784324294474a
-  data.tar.gz: f3a1215ad14dc3778795dc0f6563345aaa3015fe
+  metadata.gz: dd5f98881a344f630109b020f7614bf3c860a919
+  data.tar.gz: e3a1353bf994c3aabee9b779cc35e70c98f70bb3
 SHA512:
-  metadata.gz: c8eae2315a8d3a68ce1a873585ab752902287a027a6d45961fef77ad0174d3646d7c7c36107a5879b5b8b36c10afef93428b34098b2ae86dfb6026bb4d644e94
-  data.tar.gz: 1997c7bb6d11f4b139eb5cde903bc17bffb786bcad236351100e55248d57945fbd19e7cf83f409af357c4c36d1dfb43fbb5adc5a0c2997e66622ed1576bb1921
+  metadata.gz: 925e8af64d8eeed22da8b35ffa3b569b80da03956b419bc5055c7bfafc6e52f80dffbdf810f7c538ef50ec103df9431c334295f84811f861d5a78d88a30dc2c5
+  data.tar.gz: 82d5cba98f7a7f38899df4bdc20a72597882743ed7fc2a484da9c2d96097dea075cbcfa433b3db20a0ef15075a962d0022851c250a80f337e218d4f2411dc31d

data/.gitignore

@@ -7,3 +7,6 @@
 /pkg/
 /spec/reports/
 /tmp/
+/rust/target
+/rust/Makefile
+/rust/libsanscript.*

data/.rubocop.yml

@@ -1,3 +1,4 @@
+require: rubocop-rspec
 AllCops:
   TargetRubyVersion: 2.3
 

data/README.md

@@ -1,9 +1,11 @@
 # Sanscript.rb
 
+[![Gem Version](https://badge.fury.io/rb/sanscript.svg)](https://badge.fury.io/rb/sanscript)
+[![Dependency Status](https://gemnasium.com/badges/github.com/ubcsanskrit/sanscript.rb.svg)](https://gemnasium.com/github.com/ubcsanskrit/sanscript.rb)
 [![Build Status](https://travis-ci.org/ubcsanskrit/sanscript.rb.svg?branch=master)](https://travis-ci.org/ubcsanskrit/sanscript.rb)
-[![Code Climate](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/badges/gpa.svg)](https://codeclimate.com/github/ubcsanskrit/sanscript.rb)
 [![Test Coverage](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/badges/coverage.svg)](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/coverage)
-[![Dependency Status](https://gemnasium.com/badges/github.com/ubcsanskrit/sanscript.rb.svg)](https://gemnasium.com/github.com/ubcsanskrit/sanscript.rb)
+[![Code Climate](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/badges/gpa.svg)](https://codeclimate.com/github/ubcsanskrit/sanscript.rb)
+[![Inline docs](http://inch-ci.org/github/ubcsanskrit/sanscript.rb.svg?branch=master)](http://inch-ci.org/github/ubcsanskrit/sanscript.rb)
 
 This gem is starting off as a mostly-straightforward port of [learnsanskrit.org's Sanscript.js](https://github.com/sanskrit/sanscript.js), and will go from there. It also incorporates transliteration scheme detection based on [learnsanskrit.org's Detect.js](https://github.com/sanskrit/detect.js).
 
@@ -33,7 +35,7 @@ Documentation is provided in YARD format and available online at [rubydoc.info](
 
 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.
 
-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 tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+To install this gem onto your local machine, run `bundle exec rake install`.
 
 ## Contributing
 

data/Rakefile

@@ -5,3 +5,9 @@ require "rspec/core/rake_task"
 RSpec::Core::RakeTask.new(:spec)
 
 task default: :spec
+
+task :compile do
+  Dir.chdir("#{File.dirname(__FILE__)}/rust")
+  require "./extconf.rb"
+  sh "make clean && make && make install" if File.exist?("Makefile")
+end

data/lib/sanscript/detect.rb

@@ -49,8 +49,6 @@ module Sanscript
                      :RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
                      :RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
 
-    module_function
-
     # @!method detect_scheme(text)
     #   Attempts to detect the encoding scheme of the provided string.
     #
@@ -70,5 +68,23 @@ module Sanscript
       extend Ruby2x
     end
     # :nocov:
+
+    # Rust FFI
+    class << self
+      begin
+        require "ffi"
+        extend FFI::Library
+        ffi_lib Dir.glob(File.join(GEM_ROOT, "rust/libsanscript.*")).first
+        attach_function :_rust_detect, :detect, [:string], :int
+        RUST_SCHEMES = %i[devanagari bengali gurmukhi gujarati oriya tamil telugu kannada malayalam iast kolkata itrans slp1 velthuis hk].unshift(nil).freeze
+        private_constant :RUST_SCHEMES
+        def rust_detect_scheme(text)
+          RUST_SCHEMES[_rust_detect(text)]
+        end
+        alias detect_scheme rust_detect_scheme
+      rescue LoadError
+        alias detect_scheme ruby_detect_scheme
+      end
+    end
   end
 end

data/lib/sanscript/detect/ruby24.rb

@@ -9,7 +9,7 @@ module Sanscript
       #
       # @param text [String] a string of Sanskrit text
       # @return [Symbol, nil] the Symbol of the scheme, or nil if no match
-      def detect_scheme(text)
+      def ruby_detect_scheme(text)
         text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
 
         # Brahmic schemes are all within a specific range of code points.

data/lib/sanscript/detect/ruby2x.rb

@@ -8,7 +8,7 @@ module Sanscript
       #
       # @param text [String] a string of Sanskrit text
       # @return [Symbol, nil] the Symbol of the scheme, or nil if no match
-      def detect_scheme(text)
+      def ruby_detect_scheme(text)
         text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
 
         # rubocop:disable Style/CaseEquality

data/lib/sanscript/version.rb

@@ -1,5 +1,8 @@
 # frozen_string_literal: true
 module Sanscript
   # The version number
-  VERSION = "0.5.0"
+  VERSION = "0.6.0"
+
+  GEM_ROOT = Pathname.new(File.realpath(File.join(__dir__, "..", "..")))
+  private_constant :GEM_ROOT
 end

data/rust/Cargo.lock

@@ -0,0 +1,93 @@
+[root]
+name = "sanscript"
+version = "0.1.0"
+dependencies = [
+ "lazy_static 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
+ "libc 0.2.15 (registry+https://github.com/rust-lang/crates.io-index)",
+ "regex 0.1.73 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "aho-corasick"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "memchr 0.1.11 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "kernel32-sys"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
+ "winapi-build 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "lazy_static"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "libc"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "memchr"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "libc 0.2.15 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "regex"
+version = "0.1.73"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "aho-corasick 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)",
+ "memchr 0.1.11 (registry+https://github.com/rust-lang/crates.io-index)",
+ "regex-syntax 0.3.4 (registry+https://github.com/rust-lang/crates.io-index)",
+ "thread_local 0.2.6 (registry+https://github.com/rust-lang/crates.io-index)",
+ "utf8-ranges 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "thread-id"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
+ "libc 0.2.15 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "thread_local"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "thread-id 2.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "utf8-ranges"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "winapi"
+version = "0.2.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "winapi-build"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+

data/rust/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "sanscript"
+version = "0.1.0"
+authors = ["Tim Bellefleur <nomoon@phoebus.ca>"]
+
+[dependencies]
+libc = "*"
+lazy_static = "*"
+regex = "*"
+
+[lib]
+crate-type = ["dylib"]

data/rust/extconf.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+require "mkmf"
+unless !system("cargo --version") || !system("rustc --version")
+  create_makefile("sanscript")
+  File.write("Makefile", "all:\n\tcargo build --release\n\nclean:\n\trm -rf target\n\ninstall:\n\tmv target/release/libsanscript.* .\n\trm -rf target\n")
+end

data/rust/src/lib.rs

@@ -0,0 +1,100 @@
+extern crate libc;
+#[macro_use] extern crate lazy_static;
+extern crate regex;
+
+use libc::{c_char, int32_t};
+use std::ffi::CStr;
+use std::str;
+use regex::Regex;
+
+#[no_mangle]
+pub extern fn detect(s: *const c_char) -> int32_t {
+  let c_str = unsafe {
+    assert!(!s.is_null());
+
+    CStr::from_ptr(s)
+  };
+
+  lazy_static! {
+    // # Match escaped control characters
+    static ref RE_ESCAPED_CONTROL_CHAR: Regex = Regex::new(r"\\(?:\{#|\##|\#})").unwrap();
+
+    // # Match ##...## or {#...#} control blocks.
+    static ref RE_CONTROL_BLOCK: Regex = Regex::new(r"##.*?##|\{#.*?#\}").unwrap();
+
+    // Match any character in the block of Brahmic scripts
+    // between Devanagari and Malayalam.
+    static ref RE_BRAHMIC_RANGE: Regex = Regex::new(r"[\x{0900}-\x{0d7f}]").unwrap();
+
+    // Match on special Roman characters
+    static ref RE_IAST_OR_KOLKATA_ONLY: Regex = Regex::new(r"(?i)[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻ]").unwrap();
+
+    // Match on Kolkata-specific Roman characters
+    static ref RE_KOLKATA_ONLY: Regex = Regex::new(r"(?i)[ēō]").unwrap();
+
+    // Match on ITRANS-only
+    static ref RE_ITRANS_ONLY: Regex = Regex::new(r"ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a").unwrap();
+
+    // Match on SLP1-only characters and bigrams
+    static ref RE_SLP1_ONLY: Regex = Regex::new(r"[fFxXEOCYwWqQPB]|kz|N[kg]|tT|dD|S[cn]|[aAiIuUeo]R|G[yr]").unwrap();
+
+    // Match on Velthuis-only characters
+    static ref RE_VELTHUIS_ONLY: Regex = Regex::new(r"\.[mhnrlntds]|\x22n|~s").unwrap();
+
+    // Match on chars shared by ITRANS and Velthuis
+    static ref RE_ITRANS_OR_VELTHUIS_ONLY: Regex = Regex::new(r"aa|ii|uu|~n").unwrap();
+
+    // Match on characters available in Harvard-Kyoto
+    static ref RE_HARVARD_KYOTO: Regex = Regex::new(r"[aAiIuUeoRMHkgGcjJTDNtdnpbmyrlvzSsh]").unwrap();
+  }
+
+  let r_replaced_str = &RE_ESCAPED_CONTROL_CHAR.replace_all(c_str.to_str().unwrap(), "");
+  let r_str = &RE_CONTROL_BLOCK.replace_all(r_replaced_str, "");
+
+  // Brahmic schemes are all within a specific range of code points.
+  let brahmic_match = RE_BRAHMIC_RANGE.find(r_str);
+  if brahmic_match != None {
+    let brahmic_match = brahmic_match.unwrap();
+    let brahmic_codepoint = r_str.chars().nth(brahmic_match.0).unwrap() as u32;
+
+    if brahmic_codepoint < 0x0980 {
+      return 1;
+    } else if brahmic_codepoint < 0x0A00 {
+      return 2;
+    } else if brahmic_codepoint < 0x0A80 {
+      return 3;
+    } else if brahmic_codepoint < 0x0B00 {
+      return 4;
+    } else if brahmic_codepoint < 0x0B80 {
+      return 5;
+    } else if brahmic_codepoint < 0x0C00 {
+      return 6;
+    } else if brahmic_codepoint < 0x0C80 {
+      return 7;
+    } else if brahmic_codepoint < 0x0D00 {
+      return 8;
+    } else {
+      return 9;
+    }
+  }
+
+  // Romanizations
+  if RE_IAST_OR_KOLKATA_ONLY.is_match(r_str) {
+    if RE_KOLKATA_ONLY.is_match(r_str) {
+      return 11;
+    } else {
+      return 10;
+    }
+  } else if RE_ITRANS_ONLY.is_match(r_str) {
+    return 12;
+  } else if RE_SLP1_ONLY.is_match(r_str) {
+    return 13;
+  } else if RE_VELTHUIS_ONLY.is_match(r_str) {
+    return 14;
+  } else if RE_ITRANS_OR_VELTHUIS_ONLY.is_match(r_str) {
+    return 12;
+  } else if RE_HARVARD_KYOTO.is_match(r_str) {
+    return 15;
+  }
+  return 0;
+}

data/sanscript.gemspec

@@ -18,6 +18,7 @@ Gem::Specification.new do |spec|
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
+  spec.extensions    = Dir["rust/extconf.rb"]
 
   spec.required_ruby_version = "~> 2.2"
 
@@ -25,9 +26,12 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "rake", "~> 11.2"
   spec.add_development_dependency "rspec", "~> 3.5"
   spec.add_development_dependency "codeclimate-test-reporter", "~> 0.6"
+  spec.add_development_dependency "rubocop", "~> 0.41"
+  spec.add_development_dependency "rubocop-rspec", "~> 1.5"
   spec.add_development_dependency "pry", "~> 0.10"
   spec.add_development_dependency "benchmark-ips", "~> 2.6"
   spec.add_development_dependency "yard", "~> 0.9"
 
-  spec.add_runtime_dependency "ragabash", "~> 0.1"
+  spec.add_runtime_dependency "ragabash", "~> 0.2"
+  spec.add_runtime_dependency "ffi"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sanscript
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Tim Bellefleur
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-07-23 00:00:00.000000000 Z
+date: 2016-08-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -66,6 +66,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.41'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.41'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
@@ -114,19 +142,34 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: '0.2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: '0.2'
+- !ruby/object:Gem::Dependency
+  name: ffi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 
 email:
 - nomoon@phoebus.ca
 executables: []
-extensions: []
+extensions:
+- rust/extconf.rb
 extra_rdoc_files: []
 files:
 - ".codeclimate.yml"
@@ -150,6 +193,10 @@ files:
 - lib/sanscript/transliterate.rb
 - lib/sanscript/transliterate/schemes.rb
 - lib/sanscript/version.rb
+- rust/Cargo.lock
+- rust/Cargo.toml
+- rust/extconf.rb
+- rust/src/lib.rs
 - sanscript.gemspec
 homepage: https://github.com/ubcsanskrit/sanscript.rb
 licenses: