pilcrow 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 8108b88e41a63586b6e00894405b8792cf304e94
+  data.tar.gz: 5d6384c13a831952711112909bd9d4f0b0fd7064
+SHA512:
+  metadata.gz: 7041cb2642e83450e2b51940ab46add7ab7193e5a12254e1fc2592f0a57d6af7abdeaeeff0f4fd60ff0cbca324d2b285d2384dd6520a62855bebd2c25b293bed
+  data.tar.gz: f1f5d0bc6aa74ad46ecffca150a6a00f0cd9a0c0a4694a4f000e4db2ca3817bf65c9f63ba499343ee14fa54f57e3fff1614078d9553d7dcacb8b2110d0fd7630

data/Gemfile

@@ -0,0 +1,15 @@
+source "https://rubygems.org"
+
+gemspec
+
+ruby '1.9.3', engine: 'jruby', engine_version: '1.7.12'
+
+group :development, :test do
+  gem 'pry-nav'
+  gem 'rake'
+end
+
+group :test do
+  gem 'rspec'
+  gem 'rr'
+end

data/History.txt

@@ -0,0 +1,3 @@
+== 1.0.0
+
+* Birthday!

data/Rakefile

@@ -0,0 +1,18 @@
+# encoding: UTF-8
+
+require 'rubygems' unless ENV['NO_RUBYGEMS']
+
+require 'bundler'
+require 'rspec/core/rake_task'
+require 'rubygems/package_task'
+
+require './lib/pilcrow'
+
+Bundler::GemHelper.install_tasks
+
+task :default => :spec
+
+desc 'Run specs'
+RSpec::Core::RakeTask.new do |t|
+  t.pattern = './spec/**/*_spec.rb'
+end

data/bin/pilcrow

@@ -0,0 +1,9 @@
+#! /usr/bin/env ruby
+
+require 'pilcrow'
+
+locale = ARGV[0]
+text = ARGV[1] || ""
+text = STDIN.read if text.empty?
+
+STDOUT.write(Pilcrow.process(text, locale))

data/lib/pilcrow.rb

@@ -0,0 +1,37 @@
+# encoding: UTF-8
+
+require File.expand_path('../../vendor/icu4j-53_1.jar', __FILE__)
+
+java_import 'com.ibm.icu.util.ULocale'
+java_import 'com.ibm.icu.text.BreakIterator'
+
+module Pilcrow
+  class << self
+
+    def process(text, locale)
+      insert_markers(segment_text(text, locale))
+    end
+
+    private
+
+    def segment_text(text, locale)
+      brkiter = BreakIterator.getWordInstance(ULocale.new(locale))
+      brkiter.setText(text)
+      start = brkiter.first
+      segments = []
+
+      until (stop = brkiter.next) == BreakIterator::DONE
+        segments << text[start...stop]
+        start = stop
+      end
+
+      segments
+    end
+
+    def insert_markers(segments)
+      # pilcrow character: http://en.wikipedia.org/wiki/Pilcrow
+      segments.join("\u00B6")
+    end
+
+  end
+end

data/lib/pilcrow/version.rb

@@ -0,0 +1,5 @@
+# encoding: UTF-8
+
+module Pilcrow
+  VERSION = '1.0.0'
+end

data/pilcrow.gemspec

@@ -0,0 +1,19 @@
+$:.unshift File.join(File.dirname(__FILE__), 'lib')
+require 'pilcrow/version'  
+
+Gem::Specification.new do |s|
+  s.name     = "pilcrow"
+  s.version  = ::Pilcrow::VERSION
+  s.authors  = ["Cameron Dutro"]
+  s.email    = ["camertron@gmail.com"]
+  s.homepage = "http://github.com/camertron"
+
+  s.description = s.summary = "Automatically inserts non-with spaces between words in text from STDIN"
+
+  s.platform = Gem::Platform::RUBY
+  s.has_rdoc = true
+
+  s.require_path = 'lib'
+  s.files = Dir["{lib,spec,vendor}/**/*", "Gemfile", "History.txt", "README.md", "Rakefile", "pilcrow.gemspec"]
+  s.executables << 'pilcrow'
+end

metadata

@@ -0,0 +1,52 @@
+--- !ruby/object:Gem::Specification
+name: pilcrow
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Cameron Dutro
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2014-09-12 00:00:00.000000000 Z
+dependencies: []
+description: Automatically inserts non-with spaces between words in text from STDIN
+email:
+- camertron@gmail.com
+executables:
+- pilcrow
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/pilcrow.rb
+- lib/pilcrow/version.rb
+- vendor/icu4j-53_1.jar
+- Gemfile
+- History.txt
+- Rakefile
+- pilcrow.gemspec
+- bin/pilcrow
+homepage: http://github.com/camertron
+licenses: []
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: Automatically inserts non-with spaces between words in text from STDIN
+test_files: []