ffi-icu 0.5.2 → 0.6.0

data/lib/ffi-icu/transliteration.rb

@@ -1,12 +1,13 @@
+# frozen_string_literal: true
+
 module ICU
   module Transliteration
-
     class << self
       def transliterate(translit_id, str, rules = nil)
-        t = Transliterator.new translit_id, rules
-        t.transliterate str
+        t = Transliterator.new(translit_id, rules)
+        t.transliterate(str)
       end
-      alias_method :translit, :transliterate
+      alias translit transliterate
 
       def available_ids
         enum_ptr = Lib.check_error do |error|
@@ -21,34 +22,34 @@ module ICU
     end
 
     class Transliterator
-
       def initialize(id, rules = nil, direction = :forward)
         rules_length = 0
 
         if rules
-          rules_length = rules.jlength + 1
+          rules_length = rules.size + 1
           rules = UCharPointer.from_string(rules)
         end
 
         parse_error = Lib::UParseError.new
         begin
           Lib.check_error do |status|
-            ptr = Lib.utrans_openU(UCharPointer.from_string(id), id.jlength, direction, rules, rules_length, @parse_error, status)
+            ptr = Lib.utrans_openU(UCharPointer.from_string(id), id.size, direction, rules, rules_length,
+                                   @parse_error, status)
             @tr = FFI::AutoPointer.new(ptr, Lib.method(:utrans_close))
           end
-        rescue ICU::Error => ex
-          raise ex, "#{ex.message} (#{parse_error})"
+        rescue ICU::Error => e
+          raise(e, "#{e.message} (#{parse_error})")
         end
       end
 
       def transliterate(from)
         # this is a bit unpleasant
 
-        unicode_size = from.unpack("U*").size
+        unicode_size = from.unpack('U*').size
         capacity     = unicode_size + 1
         buf          = UCharPointer.from_string(from, capacity)
-        limit        = FFI::MemoryPointer.new :int32
-        text_length  = FFI::MemoryPointer.new :int32
+        limit        = FFI::MemoryPointer.new(:int32)
+        text_length  = FFI::MemoryPointer.new(:int32)
 
         retried = false
 
@@ -63,9 +64,9 @@ module ICU
           end
         rescue BufferOverflowError
           new_size = text_length.get_int32(0)
-          $stderr.puts "BufferOverflowError, needs: #{new_size}" if $DEBUG
+          warn("BufferOverflowError, needs: #{new_size}") if $DEBUG
 
-          raise BufferOverflowError, "needed #{new_size}" if retried
+          raise(BufferOverflowError, "needed #{new_size}") if retried
 
           capacity = new_size + 1
 
@@ -78,9 +79,8 @@ module ICU
           retry
         end
 
-        buf.string text_length.get_int32(0)
+        buf.string(text_length.get_int32(0))
       end
-
-    end # Transliterator
-  end # Translit
-end # ICU
+    end
+  end
+end

data/lib/ffi-icu/uchar.rb

@@ -1,36 +1,35 @@
+# frozen_string_literal: true
+
 module ICU
   class UCharPointer < FFI::MemoryPointer
-
     UCHAR_TYPE = :uint16 # not sure how platform-dependent this is..
     TYPE_SIZE  = FFI.type_size(UCHAR_TYPE)
 
     def self.from_string(str, capacity = nil)
-      str   = str.encode("UTF-8") if str.respond_to? :encode
-      chars = str.unpack("U*")
+      str   = str.encode('UTF-8') if str.respond_to?(:encode)
+      chars = str.unpack('U*')
 
       if capacity
-        if capacity < chars.size
-          raise ArgumentError, "capacity is too small for string of #{chars.size} UChars"
-        end
+        raise(ArgumentError, "capacity is too small for string of #{chars.size} UChars") if capacity < chars.size
 
-        ptr = new capacity
+        ptr = new(capacity)
       else
-        ptr = new chars.size
+        ptr = new(chars.size)
       end
 
-      ptr.write_array_of_uint16 chars
+      ptr.write_array_of_uint16(chars)
 
       ptr
     end
 
     def initialize(size)
-      super UCHAR_TYPE, size
+      super(UCHAR_TYPE, size)
     end
 
     def resized_to(new_size)
-      raise "new_size must be larger than current size" if new_size < size
+      raise('new_size must be larger than current size') if new_size < size
 
-      resized = self.class.new new_size
+      resized = self.class.new(new_size)
       resized.put_bytes(0, get_bytes(0, size))
 
       resized
@@ -40,13 +39,11 @@ module ICU
       length ||= size / TYPE_SIZE
 
       wstring = read_array_of_uint16(length)
-      wstring.pack("U*")
+      wstring.pack('U*')
     end
 
     def length_in_uchars
       size / type_size
     end
-
-
-  end # UCharPointer
-end # ICU
+  end
+end

data/lib/ffi-icu/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module ICU
-  VERSION = "0.5.2"
+  VERSION = '0.6.0'
 end

data/lib/ffi-icu.rb

@@ -1,9 +1,9 @@
-require "rbconfig"
-require "ffi"
+require 'rbconfig'
+require 'ffi'
 
 module ICU
   def self.platform
-    os = RbConfig::CONFIG["host_os"]
+    os = RbConfig::CONFIG['host_os']
 
     case os
     when /darwin/
@@ -20,17 +20,16 @@ module ICU
   end
 end
 
-require "ffi-icu/core_ext/string"
-require "ffi-icu/lib"
-require "ffi-icu/lib/util"
-require "ffi-icu/uchar"
-require "ffi-icu/chardet"
-require "ffi-icu/collation"
-require "ffi-icu/locale"
-require "ffi-icu/transliteration"
-require "ffi-icu/normalization"
-require "ffi-icu/normalizer"
-require "ffi-icu/break_iterator"
-require "ffi-icu/number_formatting"
-require "ffi-icu/time_formatting"
-require "ffi-icu/duration_formatting"
+require 'ffi-icu/lib'
+require 'ffi-icu/lib/util'
+require 'ffi-icu/uchar'
+require 'ffi-icu/chardet'
+require 'ffi-icu/collation'
+require 'ffi-icu/locale'
+require 'ffi-icu/transliteration'
+require 'ffi-icu/normalization'
+require 'ffi-icu/normalizer'
+require 'ffi-icu/break_iterator'
+require 'ffi-icu/number_formatting'
+require 'ffi-icu/time_formatting'
+require 'ffi-icu/duration_formatting'

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: ffi-icu
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.6.0
 platform: ruby
 authors:
-- Jari Bakken
-autorequire:
+- Erick Guan
+- Damian Nelson
 bindir: bin
 cert_chain: []
-date: 2019-10-15 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: bigdecimal
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: ffi
   requirement: !ruby/object:Gem::Requirement
@@ -31,59 +45,37 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 1.0.9
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: stringio
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.9'
-  type: :development
+        version: '3.0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.9'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 12.3.3
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 12.3.3
-description: Provides charset detection, locale sensitive collation and more. Depends
-  on libicu.
-email: jari.bakken@gmail.com
+        version: '3.0'
+description: Provides charset detection, transiliteration, locale sensitive collation
+  and more. Depends on libicu. ICU operates on CLDR data.
+email: erickguanst@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files:
 - LICENSE
 - README.md
 files:
-- ".document"
-- ".gitignore"
-- ".rspec"
-- ".travis.yml"
 - Gemfile
 - LICENSE
 - README.md
 - Rakefile
-- benchmark/detect.rb
-- benchmark/shared.rb
-- build_icu.sh
 - ffi-icu.gemspec
 - lib/ffi-icu.rb
 - lib/ffi-icu/break_iterator.rb
 - lib/ffi-icu/chardet.rb
 - lib/ffi-icu/collation.rb
-- lib/ffi-icu/core_ext/string.rb
 - lib/ffi-icu/duration_formatting.rb
 - lib/ffi-icu/lib.rb
 - lib/ffi-icu/lib/util.rb
@@ -95,26 +87,13 @@ files:
 - lib/ffi-icu/transliteration.rb
 - lib/ffi-icu/uchar.rb
 - lib/ffi-icu/version.rb
-- spec/break_iterator_spec.rb
-- spec/chardet_spec.rb
-- spec/collation_spec.rb
-- spec/duration_formatting_spec.rb
-- spec/lib/version_info_spec.rb
-- spec/lib_spec.rb
-- spec/locale_spec.rb
-- spec/normalization_spec.rb
-- spec/normalizer_spec.rb
-- spec/number_formatting_spec.rb
-- spec/spec_helper.rb
-- spec/time_spec.rb
-- spec/transliteration_spec.rb
-- spec/uchar_spec.rb
-- test.c
-homepage: http://github.com/jarib/ffi-icu
+homepage: https://github.com/erickguan/ffi-icu
 licenses:
 - MIT
-metadata: {}
-post_install_message:
+metadata:
+  source_code_uri: https://github.com/erickguan/ffi-icu
+  changelog_uri: https://github.com/erickguan/ffi-icu/blob/master/CHANGELOG.md
+  rubygems_mfa_required: 'true'
 rdoc_options:
 - "--charset=UTF-8"
 require_paths:
@@ -123,29 +102,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 3.2.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.5.0
 requirements: []
-rubygems_version: 3.4.10
-signing_key:
+rubygems_version: 4.0.10
 specification_version: 4
-summary: Simple Ruby FFI wrappers for things I need from ICU.
-test_files:
-- spec/break_iterator_spec.rb
-- spec/chardet_spec.rb
-- spec/collation_spec.rb
-- spec/duration_formatting_spec.rb
-- spec/lib/version_info_spec.rb
-- spec/lib_spec.rb
-- spec/locale_spec.rb
-- spec/normalization_spec.rb
-- spec/normalizer_spec.rb
-- spec/number_formatting_spec.rb
-- spec/spec_helper.rb
-- spec/time_spec.rb
-- spec/transliteration_spec.rb
-- spec/uchar_spec.rb
+summary: Ruby FFI wrappers for International Components for Unicode (ICU).
+test_files: []

data/.document

@@ -1,5 +0,0 @@
-README.rdoc
-lib/**/*.rb
-bin/*
-features/**/*.feature
-LICENSE

data/.gitignore

@@ -1,23 +0,0 @@
-## MAC OS
-.DS_Store
-
-## TEXTMATE
-*.tmproj
-tmtags
-
-## EMACS
-*~
-\#*
-.\#*
-
-## VIM
-*.swp
-
-## PROJECT::GENERAL
-coverage
-rdoc
-pkg
-
-## PROJECT::SPECIFIC
-*.rbc
-Gemfile.lock

data/.rspec

@@ -1,2 +0,0 @@
---color
---require spec_helper

data/.travis.yml

@@ -1,28 +0,0 @@
-language: ruby
-os: linux
-dist: focal
-
-arch:
-  - amd64
-  - arm64
-
-rvm:
-  - 2.7
-  - 3.0
-  - 3.1
-  - ruby-head
-  - truffleruby
-
-before_script:
-  - sudo apt install -y icu-devtools g++
-  - sudo chmod +x build_icu.sh
-  - sudo $PWD/build_icu.sh versions
-  - sudo $PWD/build_icu.sh install 71.1
-  - export LD_LIBRARY_PATH=/usr/local/lib
-  - icuinfo
-  - yes | gem update --system --force
-  - gem install bundler
-
-jobs:
-  allow_failures:
-    - rvm: truffleruby

data/benchmark/detect.rb

@@ -1,14 +0,0 @@
-# encoding: utf-8
-
-require "benchmark"
-
-$LOAD_PATH.unshift "lib"
-require "ffi-icu"
-require "rchardet"
-
-TESTS = 1000
-
-Benchmark.bmbm do |results|
-  results.report("rchardet:") { TESTS.times { CharDet.detect("æåø") } }
-  results.report("ffi-icu:") { TESTS.times { ICU::CharDet.detect("æåø") } }
-end

data/benchmark/shared.rb

@@ -1,17 +0,0 @@
-# encoding: utf-8
-
-require "benchmark"
-
-$LOAD_PATH.unshift "lib"
-require "ffi-icu"
-require "rchardet"
-
-TESTS = 1000
-
-$rchardet = CharDet::UniversalDetector.new
-$icu = ICU::CharDet::Detector.new
-
-Benchmark.bmbm do |results|
-  results.report("rchardet instance:") { TESTS.times { $rchardet.reset; $rchardet.feed("æåø"); $rchardet.result } }
-  results.report("ffi-icu instance:") { TESTS.times { $icu.detect("æåø")  } }
-end

data/build_icu.sh

@@ -1,53 +0,0 @@
-#!/usr/bin/env bash
-
-if [[ -x $(which icuinfo) ]]; then
-    echo System ICU version: $(icuinfo | grep -o '"version">[^<]\+' | grep -o '[^"><]\+$')
-else
-    echo 'System ICU not installed'
-fi
-
-if [[ "$1" == '' ]]; then
-    echo ''
-    echo 'Usage:'
-    echo ''
-    echo '1) bash icu-install.sh versions'
-    echo ''
-    echo '2) bash icu-install.sh install <version>'
-fi
-
-if [[ "$1" == 'versions' ]]; then
-    echo ''
-    echo 'Available ICU versions'
-    wget -O - https://icu.unicode.org/download 2>/dev/null | grep -P -o '(?<=http://site.icu-project.org/download/)\d+#TOC-ICU4C-Download.+;&gt;\K[\d.]+'
-fi
-
-if [[ "$2" != "" && "$1" == 'install' ]]; then
-    which g++ || sudo apt install -y g++
-
-    ICU_VERSION=$2
-    ICU_SRC_FILE="icu4c-$(echo $ICU_VERSION | sed -e 's/\./_/')-src.tgz"
-    echo "Trying to install ICU version: $ICU_VERSION"
-    if [[ ! -e "$ICU_SRC_FILE" ]]; then
-        wget "https://github.com/unicode-org/icu/releases/download/release-$(echo $ICU_VERSION | sed -e 's/\./-/')/$ICU_SRC_FILE"
-    fi
-    if [[ ! -e "$ICU_SRC_FILE" ]]; then
-        exit 1;
-    fi
-
-    ICU_SRC_FOLDER="icu-release-$(echo $ICU_VERSION | sed -e 's/\./-/')"
-    tar zxvf "$ICU_SRC_FILE"
-    which g++ || sudo apt install -y g++
-
-    if [[ ! -e "/opt/icu$ICU_VERSION" ]]; then
-        pushd icu/source
-            sudo mkdir "/opt/icu$ICU_VERSION"
-            ./configure --prefix="/opt/icu$ICU_VERSION" && make -j2 && sudo make install
-            ls -alh /opt/icu$ICU_VERSION/lib/
-            sudo cp -r /opt/icu$ICU_VERSION/lib/* /usr/local/lib
-        popd
-    else
-        echo "ICU already installed at (/opt/icu$ICU_VERSION)"
-    fi
-
-    rm -f "$ICU_SRC_FILE"
-fi

data/lib/ffi-icu/core_ext/string.rb

@@ -1,9 +0,0 @@
-class String
-  unless method_defined?(:bytesize)
-    alias_method :bytesize, :length
-  end
-
-  unless method_defined?(:jlength)
-    alias_method :jlength, :length
-  end
-end

data/spec/break_iterator_spec.rb

@@ -1,77 +0,0 @@
-# encoding: utf-8
-
-module ICU
-  describe BreakIterator do
-
-    it "should return available locales" do
-      locales = ICU::BreakIterator.available_locales
-      expect(locales).to be_an(Array)
-      expect(locales).to_not be_empty
-      expect(locales).to include("en_US")
-    end
-
-    it "finds all word boundaries in an English string" do
-      iterator = BreakIterator.new :word, "en_US"
-      iterator.text = "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua."
-      expect(iterator.to_a).to eq(
-        [0, 5, 6, 11, 12, 17, 18, 21, 22, 26, 27, 28, 39, 40, 51, 52, 56, 57, 58, 61, 62, 64, 65, 72, 73, 79, 80, 90, 91, 93, 94, 100, 101, 103, 104, 110, 111, 116, 117, 123, 124]
-      )
-    end
-
-    it "returns each substring" do
-      iterator = BreakIterator.new :word, "en_US"
-      iterator.text = "Lorem ipsum dolor sit amet."
-
-      expect(iterator.substrings).to eq(["Lorem", " ", "ipsum", " ", "dolor", " ", "sit", " ", "amet", "."])
-    end
-
-    it "returns the substrings of a non-ASCII string" do
-      iterator = BreakIterator.new :word, "th_TH"
-      iterator.text = "รู้อะไรไม่สู้รู้วิชา รู้รักษาตัวรอดเป็นยอดดี"
-
-      expect(iterator.substrings).to eq(
-        ["รู้", "อะไร", "ไม่สู้", "รู้", "วิชา", " ", "รู้", "รักษา", "ตัว", "รอด", "เป็น", "ยอดดี"]
-      )
-    end
-
-    it "finds all word boundaries in a non-ASCII string" do
-      iterator = BreakIterator.new :word, "th_TH"
-      iterator.text = "การทดลอง"
-      expect(iterator.to_a).to eq([0, 3, 8])
-    end
-
-    it "finds all sentence boundaries in an English string" do
-      iterator = BreakIterator.new :sentence, "en_US"
-      iterator.text = "This is a sentence. This is another sentence, with a comma in it."
-      expect(iterator.to_a).to eq([0, 20, 65])
-    end
-
-    it "can navigate back and forward" do
-      iterator = BreakIterator.new :word, "en_US"
-      iterator.text = "Lorem ipsum dolor sit amet."
-
-      expect(iterator.first).to eq(0)
-      iterator.next
-      expect(iterator.current).to eq(5)
-      expect(iterator.last).to eq(27)
-    end
-
-    it "fetches info about given offset" do
-      iterator = BreakIterator.new :word, "en_US"
-      iterator.text = "Lorem ipsum dolor sit amet."
-
-      expect(iterator.following(3)).to eq(5)
-      expect(iterator.preceding(6)).to eq(5)
-
-      expect(iterator).to be_boundary(5)
-      expect(iterator).to_not be_boundary(10)
-    end
-
-    it "returns an Enumerator if no block was given" do
-      iterator = BreakIterator.new :word, "nb"
-
-      expect(iterator.each).to be_kind_of(Enumerator)
-    end
-
-  end # BreakIterator
-end # ICU

data/spec/chardet_spec.rb

@@ -1,42 +0,0 @@
-# encoding: UTF-8
-
-describe ICU::CharDet::Detector do
-
-  let(:detector) { ICU::CharDet::Detector.new }
-
-  it "should recognize UTF-8" do
-    m = detector.detect("æåø")
-    expect(m.name).to eq("UTF-8")
-    expect(m.language).to be_a(String)
-  end
-
-  it "has a list of detectable charsets" do
-    cs = detector.detectable_charsets
-    expect(cs).to be_an(Array)
-    expect(cs).to_not be_empty
-
-    expect(cs.first).to be_a(String)
-  end
-
-  it "should disable / enable the input filter" do
-    expect(detector.input_filter_enabled?).to be_falsey
-    detector.input_filter_enabled = true
-    expect(detector.input_filter_enabled?).to be_truthy
-  end
-
-  it "should should set declared encoding" do
-    detector.declared_encoding = "UTF-8"
-  end
-
-  it "should detect several matching encodings" do
-    expect(detector.detect_all("foo bar")).to be_an(Array)
-  end
-
-  it "should support null bytes" do
-    # Create a utf-16 string and then force it to binary (ascii) to mimic data from net/http
-    string = "foo".encode("UTF-16").force_encoding("binary")
-    m = detector.detect(string)
-    expect(m.name).to eq("UTF-16BE")
-    expect(m.language).to be_a(String)
-  end
-end