region-spotter 1.0.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ODU1OWZlNjI3Nzg3MGQ0ODAzNDJkZjQwNWZhZjNhNDQ2ZmQ5MWU2NA==
+  data.tar.gz: !binary |-
+    MzM3MDZkMDFhYTBkMDc5ZjY1YzM0ZTYyOWMwODA3NGZiNmMzNmEzNA==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    MWJhMTcyNGJiYzY3NjJjNGQ2ODNmYzg0MGZjNjIyODZiYjMzNmZkMzRmMjcw
+    MTk2NjBjZDM5Nzc5MmNhMGMzMTdjY2Q1MzU2YzAyY2ExODViYTI0ZWQ0YzRi
+    OTY1MWVlODBjYzI2ZTA3ZjczNzMwNzdkNTk3MTNhNDg5YjY1ZmQ=
+  data.tar.gz: !binary |-
+    NzlhMGZiMDk1MDhhOTllYTI1Y2E5YjZmOTBkZmYxYTc0OTk1Yjc3NjBjZTJi
+    ODFkMWE2ZjU4YmM2ZWYzM2Y3OGNmZTQ4ODMzMWVhNjU2NjY2NzFhODgyY2Q1
+    ZWJlNjJhZjU3ZWVlMDQ5ZGU2MzA2YzU2YjdjYTc2MGJlNjMwNDY=

data/CHANGELOG.mdown

@@ -0,0 +1,10 @@
+
+# ChangeLog
+
+## 1.0.1
+
+* Now works with mixed cases and special characters such as !#,.
+
+## 1.0.0
+
+* First version released to public

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+gem 'turn'
+gem 'shoulda'
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,42 @@
+PATH
+  remote: .
+  specs:
+    spotter (1.0.1)
+      hashrules (> 1.1.3, < 1.2)
+      titleize
+      unicode
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (3.2.13)
+      i18n (= 0.6.1)
+      multi_json (~> 1.0)
+    ansi (1.4.3)
+    bourne (1.4.0)
+      mocha (~> 0.13.2)
+    hashrules (1.1.4)
+    i18n (0.6.1)
+    metaclass (0.0.1)
+    mocha (0.13.3)
+      metaclass (~> 0.0.1)
+    multi_json (1.7.2)
+    shoulda (3.4.0)
+      shoulda-context (~> 1.0, >= 1.0.1)
+      shoulda-matchers (~> 1.0, >= 1.4.1)
+    shoulda-context (1.1.0)
+    shoulda-matchers (1.5.6)
+      activesupport (>= 3.0.0)
+      bourne (~> 1.3)
+    titleize (1.3.0)
+    turn (0.9.6)
+      ansi
+    unicode (0.4.4)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  shoulda
+  spotter!
+  turn

data/README.mdown

@@ -0,0 +1,64 @@
+
+# Spotter
+
+Robustly identify countries, states, islands, cities and whatnot from text. This is still BETA. Although it supports most countries and states, it still lacks regions and cities for the most part of the world. 
+
+## Description
+
+What if I ask you: "What region is 'ontario'", or "where is 'ca'"? I would answer: Ontario is a state in Canada as well as a city in California. CA is the ISO abbreviation for Canada, and also the abbreviation for California.
+
+The goal of this gem is such: Given a string, do your very best to identify all possible locations, and order them by significance. Provide as much information as possible; What kind of region is this? Country? City? Island? Continent?
+
+## Usage
+
+```ruby
+require 'spotter'
+
+spotter = Spotter.new
+
+results = spotter.identify('new york')
+
+puts results.first.to_s # => "United States, New York"
+
+puts results.first.regions[0].name # => "United States"
+puts results.first.regions[0].type # => "country"
+puts results.first.regions[1].name # => "New York"
+puts results.first.regions[1].type # => "state"
+```
+
+It can handle text in different cases, spellings, etc.
+
+```ruby
+spotter.identify('ontARIO, california').first.to_s 
+ # => "United States, California, San Bernardino, Ontario"
+
+spotter.identify('росСиЯ').first.to_s # => 'Russia'
+spotter.identify('ruSSia').first.to_s # => 'Russia'
+```
+
+It returns all matches found:
+
+```ruby
+results = spotter.identify('canada')
+puts results[0].to_s # => 'Canada'
+puts results[1].to_s # => 'United States, Kansas, Canada'
+```
+
+It works with abbreviations too:
+
+```ruby
+puts spotter.identify('se').first.to_s # => 'Sweden'
+```
+
+## Rake task
+
+You can also use the gem with the rake task `identify` as such:
+
+```
+rake identify['new york']
+```
+
+## TODO
+
+* Add support for more states, cities and other regions
+* Add support for html/bbcode tagging of search queries, showing identified parts of the string 

data/Rakefile

@@ -0,0 +1,26 @@
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.libs << 'test'
+  t.test_files = FileList['test/**/*_test.rb']
+  t.verbose = true
+end
+
+task :default => :test
+
+
+desc "Attempt to identify region from string"
+task :identify, :string do |t,args|
+  require 'bundler/setup'
+  require 'spotter'
+
+  string = args[:string]
+  spotter = Spotter.new
+
+  results = spotter.identify(string)
+  puts "="*30
+  results.each do |result|
+    p result
+  end
+  puts "="*30
+end

data/app.gemspec

@@ -0,0 +1,19 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |gem|
+  gem.authors       = ['Mikael Wikman']
+  gem.email         = ['mikael@wikman.me']
+  gem.summary       = %q{Robustly identify countries, states, islands, cities and whatnot from text. This is still BETA}
+  gem.description   = %Q{What if I ask you: "What country is 'ontario'", or "where is 'ca'"? I would answer: Ontario is a state in Canada and a city in California. CA is the ISO abbreviation for Canada, and also the abbreviation for California.\nThe goal of this gem is such: Given a string, do your very best to identify all possible locations, and order them by significance. Provide as much information as possible; What kind of region is this? Country? City? Island? Continent?}
+  gem.homepage      = "https://github.com/mikaelwikman/spotter"
+
+  gem.files         = `git ls-files`.split("\n")
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|features)/})
+  gem.name          = "region-spotter"
+  gem.require_paths = ["lib"]
+  gem.version       = '1.0.1'
+  gem.add_dependency 'hashrules', '>1.1.3', '<1.2'
+  gem.add_dependency 'titleize'
+  gem.add_dependency 'unicode'
+end

data/data/argentina/misiones.rb

@@ -0,0 +1,9 @@
+
+match 'misiones', 'ar n' do
+  set subregion: 'misiones'
+  set subregion_type: 'province'
+
+  match 'puerto rico' do
+    set place: 'puerto rico'
+  end
+end

data/data/australia/new_south_wales.rb

@@ -0,0 +1,16 @@
+
+match 'new south wales' do
+  set subregion: 'new south wales'
+
+  match 'kentucky' do
+    set place: 'kentucky'
+  end
+
+  match 'maryland' do
+    set place: 'maryland'
+  end
+
+  match 'carroll' do
+    set place: 'carroll'
+  end
+end

data/data/australia/queensland.rb

@@ -0,0 +1,8 @@
+
+match 'queensland', w(/(au )?qld/) do
+  set subregion: 'queensland'
+
+  match 'texas' do
+    set place: 'texas'
+  end
+end

data/data/australia/western.rb

@@ -0,0 +1,8 @@
+
+match 'western province' do
+  set subregion: 'western province'
+
+  match 'denmark' do
+    set place: 'denmark'
+  end
+end

data/data/belgium/wallonia.rb

@@ -0,0 +1,8 @@
+
+match 'wallonia' do
+  set subregion: 'wallonia'
+
+  match w(/luxembo?urg/) do
+    set subsubregion: 'luxembourg'
+  end
+end

data/data/bermuda/ireland_island.rb

@@ -0,0 +1,4 @@
+
+match w(/ireland( island)?/) do
+  set subregion: 'ireland island'
+end

data/data/bolivia/cochabamba.rb

@@ -0,0 +1,8 @@
+
+match 'cochabamba' do
+  set subregion: 'cochabamba'
+
+  match w(/(g(e|é)rman )?jord(a|á)n/) do
+    set subsubregion: 'gérman jordán'
+  end
+end

data/data/bolivia/santa_cruz.rb

@@ -0,0 +1,8 @@
+
+match 'santa cruz' do
+  set subregion: 'santa cruz'
+
+  match 'florida' do
+    set subsubregion: 'florida'
+  end
+end

data/data/brazil/amazonas.rb

@@ -0,0 +1,4 @@
+
+match 'amazonas' do
+  set subregion: 'amazonas'
+end

data/data/brazil/mato_grosso_do_sul.rb

@@ -0,0 +1,8 @@
+
+match w(/mato grosso( do sul)?/) do
+  set subregion: 'mato grosso do sul'
+
+  match 'costa rica' do
+    set subsubregion: 'costa rica'
+  end
+end

data/data/brazil/parana.rb

@@ -0,0 +1,9 @@
+
+match w(/paran(a|á)/) do
+  set subregion: 'paraná'
+
+  match w(/fl(o|ó)rida/) do
+    set subsubregion: 'flórida'
+    set subsubregion_type: 'municipality'
+  end
+end

data/data/brazil/sao_paulo.rb

@@ -0,0 +1,9 @@
+
+match w(/s(a|ã)o paulo/) do
+  set subregion: 'são paulo'
+
+  match w(/fl(o|ó)rida( paulista)?/) do
+    set subsubregion: 'flórida paulista'
+    set subsubregion_type: 'municipality'
+  end
+end

data/data/bulgaria/montana.rb

@@ -0,0 +1,8 @@
+
+match 'montana' do
+  set subregion: 'montana'
+
+  match 'jordan' do
+    set place: 'jordan'
+  end
+end

data/data/canada/alberta.rb

@@ -0,0 +1,20 @@
+
+match 'ab', 'alberta' do 
+  set subregion: 'alberta'
+
+  match 'calgary' do
+    set place: 'calgary'
+  end
+  
+  match 'new norway' do
+    set place: 'new norway'
+  end
+
+  match 'queensland' do
+    set place: 'queensland'
+  end
+
+  match w(/(new )?norway/) do
+    set place: 'new norway'
+  end
+end

data/data/canada/british_columbia.rb

@@ -0,0 +1,9 @@
+
+match 'british columbia' do
+  set subregion: 'british columbia'
+
+  match w(/wales( island)?/) do
+    set place: 'wales island'
+  end
+
+end

data/data/canada/manitoba.rb

@@ -0,0 +1,7 @@
+match 'manitoba', 'mb' do
+  set subregion: 'manitoba'
+
+  match 'norway house' do
+    set place: 'norway house'
+  end
+end

data/data/canada/new_brunswick.rb

@@ -0,0 +1,4 @@
+match 'new brunswick', w(/(ca )?nb/) do
+  set subregion: 'new brunswick'
+
+end

data/data/canada/newfoundland_and_labrador.rb

@@ -0,0 +1,8 @@
+
+match /newfoundland( and labrador)?/ do
+  set subregion: 'newfoundland and labrador'
+
+  match /portugal cove( st philip ?s)?/ do
+    set place: 'portugal cove-st. philip\'s'
+  end
+end

data/data/canada/northwest_territories.rb

@@ -0,0 +1,4 @@
+match 'northwest territories', w(/(ca )?nt/) do
+  set subregion: 'northwest territories'
+
+end

data/data/canada/nova_scotia.rb

@@ -0,0 +1,5 @@
+
+match 'nova scotia', w(/(ca )?ns/) do 
+  set subregion: 'nova scotia'
+
+end

data/data/canada/nunavut.rb

@@ -0,0 +1,5 @@
+
+match 'nunavut', w(/(ca )?nu/) do 
+  set subregion: 'nunavut'
+
+end

data/data/canada/ontario.rb

@@ -0,0 +1,28 @@
+
+match w(/(ca )?on/), 'ontario' do 
+  set subregion: 'ontario'
+
+  match 'gravenhurst' do
+    set place: 'gravenhurst'
+  end
+
+  match 'mississippi mills' do
+    set place: 'mississippi mills'
+  end
+
+  match 'jordan' do
+    set place: 'jordan'
+  end
+
+  match 'hawkesbury' do
+    set place: 'hawkesbury'
+  end
+
+  match 'london' do
+    set  place: 'london'
+  end
+
+  match 'long beach' do
+    set place: 'long beach'
+  end
+end

data/data/canada/prince_edward_island.rb

@@ -0,0 +1,5 @@
+
+match w(/prince edward( island)?/), w(/(ca )?pe/) do 
+  set subregion: 'prince edward island'
+
+end

data/data/canada/quebec.rb

@@ -0,0 +1,3 @@
+match 'qc', 'quebec' do
+  set subregion: 'quebec' 
+end

data/data/canada/saskatchewan.rb

@@ -0,0 +1,5 @@
+
+match 'saskatchewan', w(/(ca )?sk/) do 
+  set subregion: 'saskatchewan'
+
+end