sanscript 0.8.0 → 0.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4abcaa011331a5fcdcb8e27184883850c6815b1e
-  data.tar.gz: 213abc61320426da678cabe812b59902c2d8833b
+  metadata.gz: c50d574983e399ea044b60c2d8ece2a624d561ca
+  data.tar.gz: 7b8b068883034401079c3671f6ca60b9f777d5df
 SHA512:
-  metadata.gz: ef7b9677ab085c54cbd0511a15d212b85776c43190bb82ca9a51000a83dbfecd257fbed6a347a31bd585407b32fddb2941c7c92bc06f8ebec7d1ac32f169933d
-  data.tar.gz: f158c34ec94e52d29b66caf5e6914f2c94db14d6e0523b791b1c0a739c4c53fcbb60d8f649f9b8c1d1a5d7c1b706546c3bab7ca7947613df64067cf108cd42d6
+  metadata.gz: 39a77f3cc096bb673ad499539f7e8bae0e6300c5401c091391b3dd1e3305f8d7ec278d5dd16b19cf8a9ac1e4144bd3f606ff07e5d1028f198b499585bab893e9
+  data.tar.gz: 8b9a1fbe21223ca924c62e83c487cd3ea2be68735cee2207b66970644f6a3a8c307173b8287c916286bcddc1e989867abd775b4a43e4a31b14c36bf2882b29d8

data/.travis.yml

@@ -1,15 +1,24 @@
 sudo: false
 language: ruby
 rvm:
+  - 2.4.0
   - 2.3.3
-  - 2.2
-  - 2.4.0-preview3
+  - 2.2.6
+  - ruby-head
+env:
+  - RUST=yes
+  - RUST=no
+
 matrix:
   allow_failures:
-  - rvm: 2.4.0-preview3
+  - rvm: ruby-head
+
+before_install:
+  - if [[ "$RUST" == "yes" ]]; then curl https://sh.rustup.rs -sSf | sh -s -- -y --default-toolchain stable; export PATH="$HOME/.cargo/bin:$PATH"; fi
+
+script:
+  - if [[ "$RUST" == "yes" ]]; then bundle exec rake SPEC_OPTS="--format p"; else bundle exec rake spec SPEC_OPTS="--format p"; fi
 
-before_install: gem install bundler -v 1.13.6
-script: bundle exec rake spec SPEC_OPTS="--format p"
 addons:
   code_climate:
     repo_token: b4319eb676f021fb9473aa342324abd74f58d146e174f3cdf57f103bab052f25

data/README.md

@@ -3,7 +3,7 @@
 [![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)
-[![Test Coverage](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/badges/coverage.svg)](https://codeclimate.com/github/ubcsanskrit/sanscript.rb/coverage)
+[![Coverage Status](https://coveralls.io/repos/github/ubcsanskrit/sanscript.rb/badge.svg?branch=master)](https://coveralls.io/github/ubcsanskrit/sanscript.rb?branch=master)
 [![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)
 

data/Rakefile

@@ -13,3 +13,11 @@ begin
 rescue LoadError
   nil
 end
+
+# Ensure missing Rubocop development dependency doesn't kill gem install.
+begin
+  require "rubocop/rake_task"
+  RuboCop::RakeTask.new
+rescue LoadError
+  nil
+end

data/lib/sanscript.rb

@@ -25,9 +25,11 @@ module Sanscript
     Detect.detect_scheme(text)
   end
 
-  # Transliterates a string, optionally detecting its source-scheme first.
+  # Transliterates a string from one scheme to another.
+  # Proxy for {Transliterate.transliterate}
   #
   # @overload transliterate(text, from, to, **opts)
+  #   Transliterates a string from one scheme to another.
   #   @param text [String] the String to transliterate
   #   @param from [Symbol, nil] the name of the scheme to transliterate from, or Nil to detect
   #   @param to [Symbol] the name of the scheme to transliterate to
@@ -40,6 +42,7 @@ module Sanscript
   #   @raise [SchemeNotSupportedError] if a provided transliteration scheme is not supported
   #
   # @overload transliterate(text, to, **opts)
+  #   Transliterates a string, detecting its source-scheme first.
   #   @param text [String] the String to transliterate
   #   @param to [Symbol] the name of the scheme to transliterate to
   #   @option opts [Symbol] :default_scheme a default scheme to fall-back to if detection fails

data/lib/sanscript/benchmark.rb

@@ -1,17 +1,17 @@
 # frozen_string_literal: true
 
 module Sanscript
-  # :nocov:
   begin
     require "benchmark/ips"
   rescue LoadError
+    #:nocov:
     module ::Benchmark
       def self.ips(*)
         raise NotImplementedError, "You must install the `benchmark-ips` gem first."
       end
     end
+    #:nocov:
   end
-  # :nocov:
 
   # Benchmark/testing module.
   module Benchmark

data/lib/sanscript/detect.rb

@@ -1,67 +1,10 @@
 # frozen_string_literal: true
+require "sanscript/detect/constants"
 
 module Sanscript
   # Transliteration scheme detection module.
   # Developed from code available @ https://github.com/sanskrit/detect.js
   module Detect
-    # Match any character in the block of Brahmic scripts
-    # between Devanagari and Malayalam.
-    RE_BRAHMIC_RANGE = /[\u0900-\u0d7f]/
-
-    # Match each individual Brahmic script.
-    RE_BRAHMIC_SCRIPTS = {
-      devanagari: /\p{Devanagari}/,
-      bengali: /\p{Bengali}/,
-      gurmukhi: /\p{Gurmukhi}/,
-      gujarati: /\p{Gujarati}/,
-      oriya: /\p{Oriya}/,
-      tamil: /\p{Tamil}/,
-      telugu: /\p{Telugu}/,
-      kannada: /\p{Kannada}/,
-      malayalam: /\p{Malayalam}/,
-    }.freeze
-
-    # Match on special Roman characters
-    RE_IAST_OR_KOLKATA_ONLY = /[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻ]/i
-
-    # Match on Kolkata-specific Roman characters
-    RE_KOLKATA_ONLY = /[ēō]/i
-
-    # Match on ITRANS-only
-    RE_ITRANS_ONLY = /ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a/
-
-    # Match on SLP1-only characters and bigrams
-    RE_SLP1_ONLY = /[fFxXEOCYwWqQPB]|kz|N[kg]|tT|dD|S[cn]|[aAiIuUeo]R|G[yr]/
-
-    # Match on Velthuis-only characters
-    RE_VELTHUIS_ONLY = /\.[mhnrlntds]|"n|~s/
-
-    # Match on chars shared by ITRANS and Velthuis
-    RE_ITRANS_OR_VELTHUIS_ONLY = /aa|ii|uu|~n/
-
-    # Match on characters available in Harvard-Kyoto
-    RE_HARVARD_KYOTO = /[aAiIuUeoRMHkgGcjJTDNtdnpbmyrlvzSsh]/
-
-    # Match ##...## or {#...#} control blocks.
-    RE_CONTROL_BLOCK = /(?<!\\)##.*?(?<!\\)##|(?<!\\)\{#.*?(?<!\\)#\}/
-
-    private_constant :RE_BRAHMIC_RANGE, :RE_BRAHMIC_SCRIPTS, :RE_IAST_OR_KOLKATA_ONLY,
-                     :RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
-                     :RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
-
-    # @!method detect_scheme(text)
-    #   Attempts to detect the encoding scheme of the provided string.
-    #
-    #   Uses the most efficient implementation for your ruby version
-    #   (either {Ruby2x#ruby_detect_scheme} or {Ruby24#ruby_detect_scheme})
-    #   at first, which may be then overriden by the Rust native extension
-    #   (see {Sanscript#rust_enable!} and {Sanscript#rust_disable!}})
-    #
-    #   @param text [String] a string of Sanskrit text
-    #   @return [Symbol, nil] the Symbol of the scheme, or nil if no match
-
-    # @!visibility private
-    # :nocov:
     if Regexp.method_defined?(:match?)
       require "sanscript/detect/ruby24"
       extend Ruby24
@@ -69,9 +12,19 @@ module Sanscript
       require "sanscript/detect/ruby2x"
       extend Ruby2x
     end
-    # :nocov:
-    class << self
-      alias detect_scheme ruby_detect_scheme
-    end
+
+    # @!method detect_scheme(text)
+    # Attempts to detect the encoding scheme of the provided string.
+    #
+    # Uses the most efficient implementation for your ruby version
+    # (either {Ruby2x#ruby_detect_scheme} or {Ruby24#ruby_detect_scheme})
+    # at first, which may be then overriden by the Rust native extension
+    # (see {Sanscript.rust_enable!} and {Sanscript.rust_disable!})
+    #
+    # @param text [String] a string of Sanskrit text
+    # @return [Symbol, nil] the Symbol of the scheme, or nil if no match
+    # @!scope module
+    # @!visibility public
+    singleton_class.send(:alias_method, :detect_scheme, :ruby_detect_scheme)
   end
 end

data/lib/sanscript/detect/constants.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+module Sanscript
+  module Detect
+    # Constants for scheme detection
+
+    # Match any character in the block of Brahmic scripts
+    # between Devanagari and Malayalam.
+    RE_BRAHMIC_RANGE = /[\u0900-\u0d7f]/
+
+    # Match each individual Brahmic script.
+    RE_BRAHMIC_SCRIPTS = {
+      devanagari: /\p{Devanagari}/,
+      bengali: /\p{Bengali}/,
+      gurmukhi: /\p{Gurmukhi}/,
+      gujarati: /\p{Gujarati}/,
+      oriya: /\p{Oriya}/,
+      tamil: /\p{Tamil}/,
+      telugu: /\p{Telugu}/,
+      kannada: /\p{Kannada}/,
+      malayalam: /\p{Malayalam}/,
+    }.freeze
+
+    # Match on special Roman characters
+    RE_IAST_OR_KOLKATA_ONLY = /[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻ]/i
+
+    # Match on Kolkata-specific Roman characters
+    RE_KOLKATA_ONLY = /[ēō]/i
+
+    # Match on ITRANS-only
+    RE_ITRANS_ONLY = /ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a/
+
+    # Match on SLP1-only characters and bigrams
+    RE_SLP1_ONLY = /[fFxXEOCYwWqQPB]|kz|N[kg]|tT|dD|S[cn]|[aAiIuUeo]R|G[yr]/
+
+    # Match on Velthuis-only characters
+    RE_VELTHUIS_ONLY = /\.[mhnrlntds]|"n|~s/
+
+    # Match on chars shared by ITRANS and Velthuis
+    RE_ITRANS_OR_VELTHUIS_ONLY = /aa|ii|uu|~n/
+
+    # Match on characters available in Harvard-Kyoto
+    RE_HARVARD_KYOTO = /[aAiIuUeoRMHkgGcjJTDNtdnpbmyrlvzSsh]/
+
+    # Match ##...## or {#...#} control blocks.
+    RE_CONTROL_BLOCK = /(?<!\\)##.*?(?<!\\)##|(?<!\\)\{#.*?(?<!\\)#\}/
+
+    private_constant :RE_BRAHMIC_RANGE, :RE_BRAHMIC_SCRIPTS, :RE_IAST_OR_KOLKATA_ONLY,
+                     :RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
+                     :RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
+  end
+end

data/lib/sanscript/detect/rust.rb

@@ -3,7 +3,7 @@
 module Sanscript
   module Detect
     # Module stub for implementing `detect_scheme` method using Rust native extension.
-    # (Note: This module will only exist if the native extension is available and {Sanscript.load_rust!} has been run.)
+    # (Note: This module will only exist if the native extension is available and {Sanscript.rust_load!} has been run.)
     module Rust
       # @!method rust_detect_scheme(text)
       # Attempts to detect the encoding scheme of the provided string.

data/lib/sanscript/exceptions.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 module Sanscript
-  using ::Ragabash::Refinements
   # Error for when transliteration scheme is not supported.
   class SchemeNotSupportedError < StandardError
     def initialize(scheme = :unknown)

data/lib/sanscript/rust.rb

@@ -10,11 +10,9 @@ module Sanscript
     Thermite::Fiddle.load_module("init_rusty_sanscript",
                                  cargo_project_path: GEM_ROOT,
                                  ruby_project_path: GEM_ROOT)
-    #:nocov:#
     defined?(Sanscript::Rust) ? true : false
   rescue Fiddle::DLError
     false
-    #:nocov:#
   end
 
   # @return [bool] the enabled status of the Rust extension
@@ -26,12 +24,10 @@ module Sanscript
   # @return [bool] the enabled status of the Rust extension
   def rust_enable!
     return false unless RUST_AVAILABLE
-    # :nocov:
     Detect.singleton_class.class_eval do
       alias_method :detect_scheme, :rust_detect_scheme
     end
     @rust_enabled = true
-    # :nocov:
   end
 
   # Turns off Rust native extension.

data/lib/sanscript/transliterate/schemes.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 module Sanscript
-  using ::Ragabash::Refinements
   module Transliterate
     #  Schemes
     #  =======

data/lib/sanscript/version.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 module Sanscript
   # The version number
-  VERSION = "0.8.0"
+  VERSION = "0.8.1"
 
   GEM_ROOT = Pathname.new(File.realpath(File.join(__dir__, "..", "..")))
   private_constant :GEM_ROOT

data/sanscript.gemspec

@@ -23,9 +23,9 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = "~> 2.2"
 
   spec.add_development_dependency "bundler", "~> 1.13"
-  spec.add_development_dependency "rake", "~> 11.3"
+  spec.add_development_dependency "rake", "~> 12"
   spec.add_development_dependency "rspec", "~> 3.5"
-  spec.add_development_dependency "codeclimate-test-reporter", "~> 0.6"
+  spec.add_development_dependency "coveralls", "~> 0.8"
   spec.add_development_dependency "rubocop", "~> 0.43"
   spec.add_development_dependency "rubocop-rspec", "~> 1.7"
   spec.add_development_dependency "pry", "~> 0.10"

data/src/detect/ruby.rs

@@ -1,34 +1,33 @@
 use detect;
 
 use rb;
-use rb::{CallbackPtr, Value};
+use rb::{CallbackPtr, Value, RB_NIL};
 
 // Initialize all of the Ruby-specific static variables.
 lazy_static! {
   // Lookup table for Ruby Results
   static ref RUBY_RESULTS: [Value; 16] = [
-    rb::RB_NIL,                    // 0
-    rb::str_to_sym("devanagari"),  // 1
-    rb::str_to_sym("bengali") ,    // 2
-    rb::str_to_sym("gurmukhi"),    // 3
-    rb::str_to_sym("gujarati"),    // 4
-    rb::str_to_sym("oriya"),       // 5
-    rb::str_to_sym("tamil"),       // 6
-    rb::str_to_sym("telugu"),      // 7
-    rb::str_to_sym("kannada"),     // 8
-    rb::str_to_sym("malayalam"),   // 9
-    rb::str_to_sym("iast"),        // 10
-    rb::str_to_sym("kolkata"),     // 11
-    rb::str_to_sym("itrans"),      // 12
-    rb::str_to_sym("slp1"),        // 13
-    rb::str_to_sym("velthuis"),    // 14
-    rb::str_to_sym("hk")           // 15
+    RB_NIL,                  // 0
+    str2sym!("devanagari"),  // 1
+    str2sym!("bengali") ,    // 2
+    str2sym!("gurmukhi"),    // 3
+    str2sym!("gujarati"),    // 4
+    str2sym!("oriya"),       // 5
+    str2sym!("tamil"),       // 6
+    str2sym!("telugu"),      // 7
+    str2sym!("kannada"),     // 8
+    str2sym!("malayalam"),   // 9
+    str2sym!("iast"),        // 10
+    str2sym!("kolkata"),     // 11
+    str2sym!("itrans"),      // 12
+    str2sym!("slp1"),        // 13
+    str2sym!("velthuis"),    // 14
+    str2sym!("hk")           // 15
   ];
 }
 
 fn rbstr_detect_scheme(_rself: Value, s: Value) -> Value {
-  let r_str = rb::rbstr_to_str(&s);
-  let result = detect::detect_scheme(r_str);
+  let result = detect::detect_scheme(&rbstr2str!(&s));
   return RUBY_RESULTS[result];
 }
 

data/src/lib.rs

@@ -2,6 +2,5 @@
 extern crate ruby_sys;
 extern crate regex;
 
-mod rb;
-// Exports a Sanscript::Detect::Rust module
+#[macro_use] mod rb;
 pub mod detect;

data/src/rb.rs

@@ -1,47 +1,51 @@
-use std::ffi::{CStr, CString};
-
-use ruby_sys::{class, string, symbol, util};
+use ruby_sys::class;
 use ruby_sys::value::RubySpecialConsts::Nil;
 
 pub use ruby_sys::types::{CallbackPtr, Value};
 pub const RB_NIL: Value = Value { value: Nil as usize };
 
 //
-// Helper functions for dealing with Ruby and CStrings
+// Helper functions/macros for dealing with Ruby and CStrings
 //
 
-fn str_to_cstr(s: &str) -> CString {
-  CString::new(s).unwrap()
+macro_rules! str2cstr {
+  ($s:expr) => { ::std::ffi::CString::new($s).unwrap() }
+}
+
+macro_rules! str2cstrp {
+  ($s:expr) => { str2cstr!($s).as_ptr() }
 }
 
-pub fn rbstr_to_str<'a>(s: *const Value) -> &'a str {
-  unsafe {
-    let c_strp = string::rb_string_value_cstr(s);
-    CStr::from_ptr(c_strp).to_str().unwrap()
+macro_rules! rbstr2cstrp {
+  ($s:expr) => { ::ruby_sys::string::rb_string_value_cstr($s) }
+}
+
+macro_rules! rbstr2str {
+  ($s:expr) => {
+    unsafe { ::std::ffi::CStr::from_ptr(rbstr2cstrp!($s)).to_str().unwrap() }
   }
 }
 
-pub fn str_to_sym(s: &str) -> Value {
-  let c_str = str_to_cstr(s);
-  unsafe {
-    let id = util::rb_intern(c_str.as_ptr());
-    symbol::rb_id2sym(id)
+macro_rules! str2rbid {
+  ($s:expr) => { ::ruby_sys::util::rb_intern(str2cstrp!($s)) }
+}
+
+macro_rules! str2sym {
+  ($s:expr) => {
+    unsafe { ::ruby_sys::symbol::rb_id2sym(str2rbid!($s)) }
   }
 }
 
 pub fn define_module(name: &str) -> Value {
-  let c_str = str_to_cstr(name);
-  unsafe { class::rb_define_module(c_str.as_ptr()) }
+  unsafe { class::rb_define_module(str2cstrp!(name)) }
 }
 
 pub fn define_module_under(parent: &Value, name: &str) -> Value {
-  let c_str = str_to_cstr(name);
-  unsafe { class::rb_define_module_under(*parent, c_str.as_ptr()) }
+  unsafe { class::rb_define_module_under(*parent, str2cstrp!(name)) }
 }
 
 pub fn define_method(module: &Value, name: &str, method: CallbackPtr, argc: i32) {
-  let c_str = str_to_cstr(name);
-  unsafe { class::rb_define_method(*module, c_str.as_ptr(), method, argc) }
+  unsafe { class::rb_define_method(*module, str2cstrp!(name), method, argc) }
 }
 
 pub fn extend_object(object: &Value, module: &Value) {

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sanscript
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.8.1
 platform: ruby
 authors:
 - Tim Bellefleur
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-11-23 00:00:00.000000000 Z
+date: 2017-01-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -30,14 +30,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '11.3'
+        version: '12'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '11.3'
+        version: '12'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -53,19 +53,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3.5'
 - !ruby/object:Gem::Dependency
-  name: codeclimate-test-reporter
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0.8'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
@@ -188,6 +188,7 @@ files:
 - lib/sanscript.rb
 - lib/sanscript/benchmark.rb
 - lib/sanscript/detect.rb
+- lib/sanscript/detect/constants.rb
 - lib/sanscript/detect/ruby24.rb
 - lib/sanscript/detect/ruby2x.rb
 - lib/sanscript/detect/rust.rb