aloha_analyzer 0.4.1 → 0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3869d7aa9079ebe62bfc5ad8b91b3d05927611df
-  data.tar.gz: 2a8d0b981a38b7f026d48c94e407a26945c7508d
+  metadata.gz: b06a694c3bc71c5bb5a64f4b3b19da403a8675e8
+  data.tar.gz: 8701c32f2590721c7d35f6762c5da42263176beb
 SHA512:
-  metadata.gz: 7b57fb1039a935bae1bbc108f72628738c20e2f955c8c8ba20cdd6a33e0221698801ea59c8c2568aa5fa4f5754f90725a8b15036aacf0a9b1a5369533195f8f2
-  data.tar.gz: fd3cd8b4ef9191fe0af77636d2e56258692c9a1ca48dc4e6474466818fdbf17b8819296964b2cdf748411ddd5f8fb05cbcf2d1d2294f1aa21585f062b1aebec9
+  metadata.gz: abaf15344a29141864b3d550313486f3b1ee85e8b4bdcffe6cd86741e001da9f6a73173197a8ded6ffa147bed7cbe359b7f1428ce808e25fc0336b325ad5cebf
+  data.tar.gz: 0b395f8911cf4eac948878f7573eec1cb0faf79877aa2f6c6841343f791a86c5b287a3b554127b54eac8d1c098a17d6267cd0ef389e389f54cb7daeaedefad56

data/aloha_analyzer.gemspec

@@ -18,8 +18,9 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]
 
+  spec.add_development_dependency 'twitter_cldr', '~> 3.0'
   spec.add_development_dependency 'bundler', '~> 1.3'
   spec.add_development_dependency 'rake', '~> 10.3'
   spec.add_development_dependency 'rspec', '~> 2.14'
-  spec.add_development_dependency 'debugger', '~> 1.6'
+  spec.add_development_dependency 'byebug', '~> 3.1'
 end

data/lib/aloha_analyzer/language.rb

@@ -3,11 +3,12 @@ require 'yaml'
 module AlohaAnalyzer
   class Language
 
-    LANGUAGES        = YAML::load_file(File.join(File.dirname(__FILE__), 'yaml/language.yml'))
+    LANGUAGES        = YAML::load_file(File.join(File.dirname(__FILE__), 'yaml/languages.yml'))
+    ALIASES          = YAML::load_file(File.join(File.dirname(__FILE__), 'yaml/aliases.yml'))
     TOTAL_POPULATION = 790000000
 
     def self.all
-      LANGUAGES
+      LANGUAGES['languages']
     end
 
     def self.total
@@ -15,23 +16,15 @@ module AlohaAnalyzer
     end
 
     def self.aliases
-      {
-        'en-gb'   => 'en',
-        'zh-cn'   => 'zh',
-        'zh-tw'   => 'zh',
-        'zh-Hans' => 'zh',
-        'ca'      => 'es',
-        'xx-lc'   => 'en',
-        'gl'      => 'es',
-        'eu'      => 'es'
-      }
+      ALIASES['aliases']
     end
 
     def self.find_by_abbreviation(abbreviation)
-      all.each do |language|
-        return language if language['abbreviation'] == abbreviation
+      if LANGUAGES['languages'][abbreviation]
+        LANGUAGES['languages'][abbreviation]
+      else
+        raise "Could not find language abbreviation '#{abbreviation}'"
       end
-      raise "Could not find language abbreviation '#{abbreviation}'"
     end
   end
 end

data/lib/aloha_analyzer/version.rb

@@ -1,3 +1,3 @@
 module AlohaAnalyzer
-  VERSION = '0.4.1'
+  VERSION = '0.4.2'
 end

data/lib/aloha_analyzer/yaml/aliases.yml

@@ -0,0 +1,559 @@
+aliases:
+  'ace':     'zh'
+  'ang':     'en'
+  'ar-001':  'ar'
+  'ca':      'es'
+  'cpe':     'en'
+  'cpf':     'fr'
+  'cpp':     'pt'
+  'crh':     'tr'
+  'de-at':   'de'
+  'de-ch':   'de'
+  'dum':     'nl'
+  'en-au':   'en'
+  'en-ca':   'en'
+  'en-gb':   'en'
+  'en-us':   'en'
+  'enm':     'en'
+  'es-419':  'es'
+  'es-es':   'es'
+  'es-mx':   'es'
+  'eu':      'es'
+  'fr-ca':   'fr'
+  'fr-ch':   'fr'
+  'frm':     'fr'
+  'fro':     'fr'
+  'gem':     'de'
+  'gl':      'es'
+  'gmh':     'de'
+  'goh':     'de'
+  'gsw':     'de'
+  'jpr':     'fa'
+  'jrb':     'ar'
+  'jv':      'id'
+  'msa':     'ms'
+  'nb':      'no'
+  'nds':     'de'
+  'nn':      'no'
+  'ota':     'tr'
+  'peo':     'fa'
+  'pt-br':   'pt'
+  'pt-pt':   'pt'
+  'shu':     'ar'
+  'tl':      'fil'
+  'xx-lc':   'en'
+  'zh-cn':   'zh'
+  'zh-hans': 'zh'
+  'zh-hant': 'zh'
+  'zh-tw':   'zh'
+  # 'aa':    'afar'
+  # 'ab':    'abkhazian'
+  # 'ach':   'acoli'
+  # 'ada':   'adangme'
+  # 'ady':   'adyghe'
+  # 'ae':    'avestan'
+  # 'af':    'afrikaans'
+  # 'afa':   'afro-asiatic language'
+  # 'afh':   'afrihili'
+  # 'agq':   'aghem'
+  # 'ain':   'ainu'
+  # 'ak':    'akan'
+  # 'akk':   'akkadian'
+  # 'ale':   'aleut'
+  # 'alg':   'algonquian language'
+  # 'alt':   'southern altai'
+  # 'am':    'amharic'
+  # 'an':    'aragonese'
+  # 'anp':   'angika'
+  # 'apa':   'apache language'
+  # 'arc':   'aramaic'
+  # 'arn':   'mapuche'
+  # 'arp':   'arapaho'
+  # 'art':   'artificial language'
+  # 'arw':   'arawak'
+  # 'as':    'assamese'
+  # 'asa':   'asu'
+  # 'ast':   'asturian'
+  # 'ath':   'athapascan language'
+  # 'aus':   'australian language'
+  # 'av':    'avaric'
+  # 'awa':   'awadhi'
+  # 'ay':    'aymara'
+  # 'az':    'azeri'
+  # 'ba':    'bashkir'
+  # 'bad':   'banda'
+  # 'bai':   'bamileke language'
+  # 'bal':   'baluchi'
+  # 'ban':   'balinese'
+  # 'bas':   'basaa'
+  # 'bat':   'baltic language'
+  # 'bax':   'bamun'
+  # 'bbj':   'ghomala'
+  # 'be':    'belarusian'
+  # 'bej':   'beja'
+  # 'bem':   'bemba'
+  # 'ber':   'berber'
+  # 'bez':   'bena'
+  # 'bfd':   'bafut'
+  # 'bg':    'bulgarian'
+  # 'bh':    'bihari'
+  # 'bho':   'bhojpuri'
+  # 'bi':    'bislama'
+  # 'bik':   'bikol'
+  # 'bin':   'bini'
+  # 'bkm':   'kom'
+  # 'bla':   'siksika'
+  # 'bm':    'bambara'
+  # 'bn':    'bengali'
+  # 'bnt':   'bantu'
+  # 'bo':    'tibetan'
+  # 'br':    'breton'
+  # 'bra':   'braj'
+  # 'brx':   'bodo'
+  # 'bs':    'bosnian'
+  # 'bss':   'akoose'
+  # 'btk':   'batak'
+  # 'bua':   'buriat'
+  # 'bug':   'buginese'
+  # 'bum':   'bulu'
+  # 'byn':   'blin'
+  # 'byv':   'medumba'
+  # 'cad':   'caddo'
+  # 'cai':   'central american indian language'
+  # 'car':   'carib'
+  # 'cau':   'caucasian language'
+  # 'cay':   'cayuga'
+  # 'cch':   'atsam'
+  # 'ce':    'chechen'
+  # 'ceb':   'cebuano'
+  # 'cel':   'celtic language'
+  # 'cgg':   'chiga'
+  # 'ch':    'chamorro'
+  # 'chb':   'chibcha'
+  # 'chg':   'chagatai'
+  # 'chk':   'chuukese'
+  # 'chm':   'mari'
+  # 'chn':   'chinook jargon'
+  # 'cho':   'choctaw'
+  # 'chp':   'chipewyan'
+  # 'chr':   'cherokee'
+  # 'chy':   'cheyenne'
+  # 'ckb':   'sorani kurdish'
+  # 'cmc':   'chamic language'
+  # 'co':    'corsican'
+  # 'cop':   'coptic'
+  # 'cr':    'cree'
+  # 'crp':   'creole or pidgin'
+  # 'csb':   'kashubian'
+  # 'cu':    'church slavic'
+  # 'cus':   'cushitic language'
+  # 'cv':    'chuvash'
+  # 'cy':    'welsh'
+  # 'dak':   'dakota'
+  # 'dar':   'dargwa'
+  # 'dav':   'taita'
+  # 'day':   'dayak'
+  # 'del':   'delaware'
+  # 'den':   'slave'
+  # 'dgr':   'dogrib'
+  # 'din':   'dinka'
+  # 'dje':   'zarma'
+  # 'doi':   'dogri'
+  # 'dra':   'dravidian language'
+  # 'dsb':   'lower sorbian'
+  # 'dua':   'duala'
+  # 'dv':    'divehi'
+  # 'dyo':   'jola-fonyi'
+  # 'dyu':   'dyula'
+  # 'dz':    'dzongkha'
+  # 'dzg':   'dazaga'
+  # 'ebu':   'embu'
+  # 'ee':    'ewe'
+  # 'efi':   'efik'
+  # 'egy':   'ancient egyptian'
+  # 'eka':   'ekajuk'
+  # 'el':    'greek'
+  # 'elx':   'elamite'
+  # 'eo':    'esperanto'
+  # 'et':    'estonian'
+  # 'eu':    'basque'
+  # 'ewo':   'ewondo'
+  # 'fan':   'fang'
+  # 'fat':   'fanti'
+  # 'ff':    'fulah'
+  # 'fiu':   'finno-ugrian language'
+  # 'fj':    'fijian'
+  # 'fo':    'faroese'
+  # 'fon':   'fon'
+  # 'frr':   'northern frisian'
+  # 'frs':   'eastern frisian'
+  # 'fur':   'friulian'
+  # 'fy':    'western frisian'
+  # 'ga':    'irish'
+  # 'gaa':   'ga'
+  # 'gay':   'gayo'
+  # 'gba':   'gbaya'
+  # 'gd':    'scottish gaelic'
+  # 'gez':   'geez'
+  # 'gil':   'gilbertese'
+  # 'gl':    'galician'
+  # 'gn':    'guarani'
+  # 'gon':   'gondi'
+  # 'gor':   'gorontalo'
+  # 'got':   'gothic'
+  # 'grb':   'grebo'
+  # 'grc':   'ancient greek'
+  # 'gu':    'gujarati'
+  # 'guz':   'gusii'
+  # 'gv':    'manx'
+  # 'gwi':   'gwichʼin'
+  # 'ha':    'hausa'
+  # 'hai':   'haida'
+  # 'haw':   'hawaiian'
+  # 'he':    'hebrew'
+  # 'hil':   'hiligaynon'
+  # 'him':   'himachali'
+  # 'hit':   'hittite'
+  # 'hmn':   'hmong'
+  # 'ho':    'hiri motu'
+  # 'hr':    'croatian'
+  # 'hsb':   'upper sorbian'
+  # 'ht':    'haitian'
+  # 'hup':   'hupa'
+  # 'hy':    'armenian'
+  # 'hz':    'herero'
+  # 'ia':    'interlingua'
+  # 'iba':   'iban'
+  # 'ibb':   'ibibio'
+  # 'ie':    'interlingue'
+  # 'ig':    'igbo'
+  # 'ii':    'sichuan yi'
+  # 'ijo':   'ijo'
+  # 'ik':    'inupiaq'
+  # 'ilo':   'iloko'
+  # 'inc':   'indic language'
+  # 'ine':   'indo-european language'
+  # 'inh':   'ingush'
+  # 'io':    'ido'
+  # 'ira':   'iranian language'
+  # 'iro':   'iroquoian language'
+  # 'is':    'icelandic'
+  # 'iu':    'inuktitut'
+  # 'jbo':   'lojban'
+  # 'jgo':   'ngomba'
+  # 'jmc':   'machame'
+  # 'ka':    'georgian'
+  # 'kaa':   'kara-kalpak'
+  # 'kab':   'kabyle'
+  # 'kac':   'kachin'
+  # 'kaj':   'jju'
+  # 'kam':   'kamba'
+  # 'kar':   'karen'
+  # 'kaw':   'kawi'
+  # 'kbd':   'kabardian'
+  # 'kbl':   'kanembu'
+  # 'kcg':   'tyap'
+  # 'kde':   'makonde'
+  # 'kea':   'kabuverdianu'
+  # 'kfo':   'koro'
+  # 'kg':    'kongo'
+  # 'kha':   'khasi'
+  # 'khi':   'khoisan language'
+  # 'kho':   'khotanese'
+  # 'khq':   'koyra chiini'
+  # 'ki':    'kikuyu'
+  # 'kj':    'kuanyama'
+  # 'kk':    'kazakh'
+  # 'kkj':   'kako'
+  # 'kl':    'kalaallisut'
+  # 'kln':   'kalenjin'
+  # 'km':    'khmer'
+  # 'kmb':   'kimbundu'
+  # 'kn':    'kannada'
+  # 'kok':   'konkani'
+  # 'kos':   'kosraean'
+  # 'kpe':   'kpelle'
+  # 'kr':    'kanuri'
+  # 'krc':   'karachay-balkar'
+  # 'krl':   'karelian'
+  # 'kro':   'kru'
+  # 'kru':   'kurukh'
+  # 'ks':    'kashmiri'
+  # 'ksb':   'shambala'
+  # 'ksf':   'bafia'
+  # 'ksh':   'colognian'
+  # 'ku':    'kurdish'
+  # 'kum':   'kumyk'
+  # 'kut':   'kutenai'
+  # 'kv':    'komi'
+  # 'kw':    'cornish'
+  # 'ky':    'kirghiz'
+  # 'la':    'latin'
+  # 'lad':   'ladino'
+  # 'lag':   'langi'
+  # 'lah':   'lahnda'
+  # 'lam':   'lamba'
+  # 'lb':    'luxembourgish'
+  # 'lez':   'lezghian'
+  # 'lg':    'ganda'
+  # 'li':    'limburgish'
+  # 'lkt':   'lakota'
+  # 'ln':    'lingala'
+  # 'lo':    'lao'
+  # 'lol':   'mongo'
+  # 'loz':   'lozi'
+  # 'lt':    'lithuanian'
+  # 'lu':    'luba-katanga'
+  # 'lua':   'luba-lulua'
+  # 'lui':   'luiseno'
+  # 'lun':   'lunda'
+  # 'luo':   'luo'
+  # 'lus':   'mizo'
+  # 'luy':   'luyia'
+  # 'lv':    'latvian'
+  # 'mad':   'madurese'
+  # 'maf':   'mafa'
+  # 'mag':   'magahi'
+  # 'mai':   'maithili'
+  # 'mak':   'makasar'
+  # 'man':   'mandingo'
+  # 'map':   'austronesian language'
+  # 'mas':   'masai'
+  # 'mde':   'maba'
+  # 'mdf':   'moksha'
+  # 'mdr':   'mandar'
+  # 'men':   'mende'
+  # 'mer':   'meru'
+  # 'mfe':   'morisyen'
+  # 'mg':    'malagasy'
+  # 'mga':   'middle irish'
+  # 'mgh':   'makhuwa-meetto'
+  # 'mgo':   'meta''
+  # 'mh':    'marshallese'
+  # 'mi':    'maori'
+  # 'mic':   'micmac'
+  # 'min':   'minangkabau'
+  # 'mis':   'miscellaneous language'
+  # 'mk':    'macedonian'
+  # 'mkh':   'mon-khmer language'
+  # 'ml':    'malayalam'
+  # 'mn':    'mongolian'
+  # 'mnc':   'manchu'
+  # 'mni':   'manipuri'
+  # 'mno':   'manobo language'
+  # 'mo':    'moldavian'
+  # 'moh':   'mohawk'
+  # 'mos':   'mossi'
+  # 'mr':    'marathi'
+  # 'mt':    'maltese'
+  # 'mua':   'mundang'
+  # 'mul':   'multiple languages'
+  # 'mun':   'munda language'
+  # 'mus':   'creek'
+  # 'mwl':   'mirandese'
+  # 'mwr':   'marwari'
+  # 'my':    'burmese'
+  # 'mye':   'myene'
+  # 'myn':   'mayan language'
+  # 'myv':   'erzya'
+  # 'na':    'nauru'
+  # 'nah':   'nahuatl'
+  # 'nai':   'north american indian language'
+  # 'nap':   'neapolitan'
+  # 'naq':   'nama'
+  # 'nd':    'north ndebele'
+  # 'ne':    'nepali'
+  # 'new':   'newari'
+  # 'ng':    'ndonga'
+  # 'nia':   'nias'
+  # 'nic':   'niger-kordofanian language'
+  # 'niu':   'niuean'
+  # 'nl-be': 'flemish'
+  # 'nmg':   'kwasio'
+  # 'nnh':   'ngiemboon'
+  # 'nog':   'nogai'
+  # 'non':   'old norse'
+  # 'nqo':   'n’ko'
+  # 'nr':    'south ndebele'
+  # 'nso':   'northern sotho'
+  # 'nub':   'nubian language'
+  # 'nus':   'nuer'
+  # 'nv':    'navajo'
+  # 'nwc':   'classical newari'
+  # 'ny':    'nyanja'
+  # 'nym':   'nyamwezi'
+  # 'nyn':   'nyankole'
+  # 'nyo':   'nyoro'
+  # 'nzi':   'nzima'
+  # 'oc':    'occitan'
+  # 'oj':    'ojibwa'
+  # 'om':    'oromo'
+  # 'or':    'oriya'
+  # 'os':    'ossetic'
+  # 'osa':   'osage'
+  # 'oto':   'otomian language'
+  # 'pa':    'punjabi'
+  # 'paa':   'papuan language'
+  # 'pag':   'pangasinan'
+  # 'pal':   'pahlavi'
+  # 'pam':   'pampanga'
+  # 'pap':   'papiamento'
+  # 'pau':   'palauan'
+  # 'phi':   'philippine language'
+  # 'phn':   'phoenician'
+  # 'pi':    'pali'
+  # 'pon':   'pohnpeian'
+  # 'pra':   'prakrit language'
+  # 'pro':   'old provençal'
+  # 'ps':    'pushto'
+  # 'qu':    'quechua'
+  # 'raj':   'rajasthani'
+  # 'rap':   'rapanui'
+  # 'rar':   'rarotongan'
+  # 'rm':    'romansh'
+  # 'rn':    'rundi'
+  # 'roa':   'romance language'
+  # 'rof':   'rombo'
+  # 'rom':   'romany'
+  # 'root':  'root'
+  # 'rup':   'aromanian'
+  # 'rw':    'kinyarwanda'
+  # 'rwk':   'rwa'
+  # 'sa':    'sanskrit'
+  # 'sad':   'sandawe'
+  # 'sah':   'sakha'
+  # 'sai':   'south american indian language'
+  # 'sal':   'salishan language'
+  # 'sam':   'samaritan aramaic'
+  # 'saq':   'samburu'
+  # 'sas':   'sasak'
+  # 'sat':   'santali'
+  # 'sba':   'ngambay'
+  # 'sbp':   'sangu'
+  # 'sc':    'sardinian'
+  # 'scn':   'sicilian'
+  # 'sco':   'scots'
+  # 'sd':    'sindhi'
+  # 'se':    'northern sami'
+  # 'see':   'seneca'
+  # 'seh':   'sena'
+  # 'sel':   'selkup'
+  # 'sem':   'semitic language'
+  # 'ses':   'koyraboro senni'
+  # 'sg':    'sango'
+  # 'sga':   'old irish'
+  # 'sgn':   'sign language'
+  # 'sh':    'serbo-croatian'
+  # 'shi':   'tachelhit'
+  # 'shn':   'shan'
+  # 'si':    'sinhala'
+  # 'sid':   'sidamo'
+  # 'sio':   'siouan language'
+  # 'sit':   'sino-tibetan language'
+  # 'sk':    'slovak'
+  # 'sl':    'slovenian'
+  # 'sla':   'slavic language'
+  # 'sm':    'samoan'
+  # 'sma':   'southern sami'
+  # 'smi':   'sami language'
+  # 'smj':   'lule sami'
+  # 'smn':   'inari sami'
+  # 'sms':   'skolt sami'
+  # 'sn':    'shona'
+  # 'snk':   'soninke'
+  # 'so':    'somali'
+  # 'sog':   'sogdien'
+  # 'son':   'songhai'
+  # 'sq':    'albanian'
+  # 'sr':    'serbian'
+  # 'srn':   'sranan tongo'
+  # 'srr':   'serer'
+  # 'ss':    'swati'
+  # 'ssa':   'nilo-saharan language'
+  # 'ssy':   'saho'
+  # 'st':    'southern sotho'
+  # 'su':    'sundanese'
+  # 'suk':   'sukuma'
+  # 'sus':   'susu'
+  # 'sux':   'sumerian'
+  # 'sv':    'swedish'
+  # 'sw':    'swahili'
+  # 'swb':   'comorian'
+  # 'swc':   'congo swahili'
+  # 'syc':   'classical syriac'
+  # 'syr':   'syriac'
+  # 'ta':    'tamil'
+  # 'tai':   'tai language'
+  # 'te':    'telugu'
+  # 'tem':   'timne'
+  # 'teo':   'teso'
+  # 'ter':   'tereno'
+  # 'tet':   'tetum'
+  # 'tg':    'tajik'
+  # 'ti':    'tigrinya'
+  # 'tig':   'tigre'
+  # 'tiv':   'tiv'
+  # 'tk':    'turkmen'
+  # 'tkl':   'tokelau'
+  # 'tlh':   'klingon'
+  # 'tli':   'tlingit'
+  # 'tmh':   'tamashek'
+  # 'tn':    'tswana'
+  # 'to':    'tongan'
+  # 'tog':   'nyasa tonga'
+  # 'tpi':   'tok pisin'
+  # 'trv':   'taroko'
+  # 'ts':    'tsonga'
+  # 'tsi':   'tsimshian'
+  # 'tt':    'tatar'
+  # 'tum':   'tumbuka'
+  # 'tup':   'tupi language'
+  # 'tut':   'altaic language'
+  # 'tvl':   'tuvalu'
+  # 'tw':    'twi'
+  # 'twq':   'tasawaq'
+  # 'ty':    'tahitian'
+  # 'tyv':   'tuvinian'
+  # 'tzm':   'central atlas tamazight'
+  # 'udm':   'udmurt'
+  # 'ug':    'uighur'
+  # 'uga':   'ugaritic'
+  # 'umb':   'umbundu'
+  # 'und':   'unknown language'
+  # 'ur':    'urdu'
+  # 'uz':    'uzbek'
+  # 'vai':   'vai'
+  # 've':    'venda'
+  # 'vi':    'vietnamese'
+  # 'vo':    'volapük'
+  # 'vot':   'votic'
+  # 'vun':   'vunjo'
+  # 'wa':    'walloon'
+  # 'wae':   'walser'
+  # 'wak':   'wakashan language'
+  # 'wal':   'wolaytta'
+  # 'war':   'waray'
+  # 'was':   'washo'
+  # 'wen':   'sorbian language'
+  # 'wo':    'wolof'
+  # 'xal':   'kalmyk'
+  # 'xh':    'xhosa'
+  # 'xog':   'soga'
+  # 'yao':   'yao'
+  # 'yap':   'yapese'
+  # 'yav':   'yangben'
+  # 'ybb':   'yemba'
+  # 'yi':    'yiddish'
+  # 'yo':    'yoruba'
+  # 'ypk':   'yupik language'
+  # 'yue':   'cantonese'
+  # 'za':    'zhuang'
+  # 'zap':   'zapotec'
+  # 'zbl':   'blissymbols'
+  # 'zen':   'zenaga'
+  # 'zgh':   'standard moroccan tamazight'
+  # 'znd':   'zande'
+  # 'zu':    'zulu'
+  # 'zun':   'zuni'
+  # 'zxx':   'no linguistic content'
+  # 'zza':   'zaza'

data/lib/aloha_analyzer/yaml/languages.yml

@@ -0,0 +1,187 @@
+languages:
+  'fr':
+    abbreviation: 'fr'
+    name:         French
+    population:   14_000_000
+    countries:    'France, Canada, Belgium, Switzerland'
+    greeting:     'bonjour!'
+  'en':
+    abbreviation: 'en'
+    name:         English
+    population:   238_000_000
+    countries:    'USA, UK, Canada, Ireland, Australia'
+    greeting:     'hello!'
+  'ar':
+    abbreviation: 'ar'
+    name:         Arabic
+    population:   42_000_000
+    countries:    'Egypt, Tunisia, Lebanon, United Arab Emirates'
+    greeting:     'مرحبا!'
+  'ja':
+    abbreviation: 'ja'
+    name:         Japanese
+    population:   106_580_000
+    countries:    'Japan, Brazil'
+    greeting:     '今日は!'
+  'es':
+    abbreviation: 'es'
+    name:         Spanish
+    population:   95_000_000
+    countries:    'Spain, Mexico, Argentina, Chile'
+    greeting:     '¡hola!'
+  'de':
+    abbreviation: 'de'
+    name:         German
+    population:   5_000_000
+    countries:    'Germany, Austria, Switzerland, Belgium'
+    greeting:     'hallo!'
+  'it':
+    abbreviation: 'it'
+    name:         Italian
+    population:   8_000_000
+    countries:    'Italy, Switzerland, Malta'
+    greeting:     'ciao!'
+  'id':
+    abbreviation: 'id'
+    name:         Indonesian
+    population:   20_000_000
+    countries:    'Indonesia'
+    greeting:     'halo!'
+  'pt':
+    abbreviation: 'pt'
+    name:         Portuguese
+    population:   42_000_000
+    countries:    'Portugal, Brazil, Macau'
+    greeting:     'olá!'
+  'ko':
+    abbreviation: 'ko'
+    name:         Korean
+    population:   7_000_000
+    countries:    'South Korea'
+    greeting:     '안녕하세요!'
+  'tr':
+    abbreviation: 'tr'
+    name:         Turkish
+    population:   14_000_000
+    countries:    'Turkey'
+    greeting:     'merhaba!'
+  'ru':
+    abbreviation: 'ru'
+    name:         Russian
+    population:   5_000_000
+    countries:    'Russia, Belarus, Kazakhstan, Kyrgyzstan'
+    greeting:     'привет!'
+  'nl':
+    abbreviation: 'nl'
+    name:         Dutch
+    population:   8_000_000
+    countries:    'Netherlands, Belgium'
+    greeting:     'hallo!'
+  'fil':
+    abbreviation: 'fil'
+    name:         Tagalog
+    countries:    'Philippines'
+    greeting:     'mabuhay!'
+    population:   8_000_000
+  'ms':
+    abbreviation: 'ms'
+    name:         Malay
+    population:   50_000_000
+    countries:    'Malaysia, Singapore, Brunei'
+    greeting:     'hello!'
+  'zh':
+    abbreviation: 'zh'
+    name:         Chinese
+    population:   20_000
+    countries:    'China, Hong-Kong, Macau'
+    greeting:     '你好!'
+  'hi':
+    abbreviation: 'hi'
+    name:         Hindi
+    population:   12_000_000
+    countries:    'India, Pakistan, Fiji'
+    greeting:     'नमस्ते!'
+  'no':
+    abbreviation: 'no'
+    name:         Norwegian
+    population:   300_000
+    countries:    'goddag'
+    greeting:     'hello!'
+  'sv':
+    abbreviation: 'sv'
+    name:         Swedish
+    population:   500_000
+    countries:    'Sweden'
+    greeting:     'god dag!'
+  'fi':
+    abbreviation: 'fi'
+    name:         Finnish
+    population:   100_000
+    countries:    'Finnish'
+    greeting:     ' terve!'
+  'da':
+    abbreviation: 'da'
+    name:         Danish
+    population:   200_000
+    countries:    'Danish'
+    greeting:     'hej!'
+  'pl':
+    abbreviation: 'pl'
+    name:         Polish
+    population:   300_000
+    countries:    'Poland'
+    greeting:     'cześć!'
+  'hu':
+    abbreviation: 'hu'
+    name:         Hungarian
+    population:   1_000_000
+    countries:    'Hungary'
+    greeting:     ' jó napot kívánok!'
+  'fa':
+    abbreviation: 'fa'
+    name:         Farsi
+    population:   1_000_000
+    countries:    'Iran, Afghanistan, Tajikistan'
+    greeting:     ' سلام!'
+  'he':
+    abbreviation: 'he'
+    name:         Hebrew
+    population:   1_000_000
+    countries:    'Israel'
+    greeting:     'שלום!'
+  'ur':
+    abbreviation: 'ur'
+    name:         Urdu
+    population:   1_000_000
+    countries:    'India, Pakistan, Fiji'
+    greeting:     'لسلام علیکم!'
+  'th':
+    abbreviation: 'th'
+    name:         Thai
+    population:   7_0000_000
+    countries:    'Thailand'
+    greeting:     'วัสดี!'
+  'uk':
+    abbreviation: 'uk'
+    name:         Ukranian
+    population:   1_0000_000
+    countries:    'Ukraine'
+    greeting:     'вітаю!'
+  'el':
+    abbreviation: 'el'
+    name:         Greek
+    population:   1_0000_000
+    countries:    'Greece, Cyprus'
+    greeting:     'γειά!'
+  'cs':
+    abbreviation: 'cs'
+    name:         Czech
+    population:   1_0000_000
+    countries:    'Czech Republic'
+    greeting:     ' ahoj!'
+  'ro':
+    abbreviation: 'ro'
+    name:         Romanian
+    population:   1_0000_000
+    countries:    'Romania, Serbia, Moldova'
+    greeting:     'salut!'

data/spec/aloha_analyzer/language_spec.rb

@@ -2,19 +2,19 @@ require 'spec_helper'
 
 describe AlohaAnalyzer::Language do
   describe '.all' do
-    it 'returns an array' do
-      described_class.all.should be_a Array
+    it 'returns a Hash' do
+      described_class.all.should be_a Hash
     end
 
     it 'is not empty' do
-      described_class.all.should be_a Array
+      described_class.all.should_not be_empty
     end
   end
 
   describe '.total' do
     it 'returns the total number of language users' do
       total = 0
-      described_class.all.each do |language|
+      described_class.all.each do |abbreviation, language|
         total += language['population']
       end
       total.should eq described_class.total

data/spec/spec_helper.rb

@@ -1,5 +1,5 @@
 require 'rubygems'
-require 'debugger'
+require 'byebug'
 require 'bundler/setup'
 
 require 'aloha_analyzer'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: aloha_analyzer
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.2
 platform: ruby
 authors:
 - Matthieu Aussaguel
@@ -10,6 +10,20 @@ bindir: bin
 cert_chain: []
 date: 2014-05-19 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: twitter_cldr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -53,19 +67,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.14'
 - !ruby/object:Gem::Dependency
-  name: debugger
+  name: byebug
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '3.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '3.1'
 description: Analyze twitter followers languages
 email:
 - matthieu.aussaguel@gmail.com
@@ -85,7 +99,8 @@ files:
 - lib/aloha_analyzer/language.rb
 - lib/aloha_analyzer/user.rb
 - lib/aloha_analyzer/version.rb
-- lib/aloha_analyzer/yaml/language.yml
+- lib/aloha_analyzer/yaml/aliases.yml
+- lib/aloha_analyzer/yaml/languages.yml
 - spec/aloha_analyzer/language_spec.rb
 - spec/aloha_analyzer/user_spec.rb
 - spec/aloha_analyzer_spec.rb

data/lib/aloha_analyzer/yaml/language.yml

@@ -1,155 +0,0 @@
-- abbreviation: fr
-  name:       French
-  population: 14_000_000
-  countries: 'France, Canada, Belgium, Switzerland'
-  greeting: 'bonjour!'
-- abbreviation: en
-  name:       English
-  population: 238_000_000
-  countries: 'USA, UK, Canada, Ireland, Australia'
-  greeting: 'hello!'
-- abbreviation: ar
-  name:       Arabic
-  population: 42_000_000
-  countries: 'Egypt, Tunisia, Lebanon, United Arab Emirates'
-  greeting: 'مرحبا!'
-- abbreviation: ja
-  name:       Japanese
-  population: 106_580_000
-  countries: 'Japan, Brazil'
-  greeting: '今日は!'
-- abbreviation: es
-  name:       Spanish
-  population: 95_000_000
-  countries: 'Spain, Mexico, Argentina, Chile'
-  greeting: '¡hola!'
-- abbreviation: de
-  name:       German
-  population: 5_000_000
-  countries: 'Germany, Austria, Switzerland, Belgium'
-  greeting: 'hallo!'
-- abbreviation: it
-  name:       Italian
-  population: 8_000_000
-  countries: 'Italy, Switzerland, Malta'
-  greeting: 'ciao!'
-- abbreviation: id
-  name:       Indonesian
-  population: 20_000_000
-  countries: 'Indonesia'
-  greeting: 'halo!'
-- abbreviation: pt
-  name:       Portuguese
-  population: 42_000_000
-  countries: 'Portugal, Brazil, Macau'
-  greeting: 'olá!'
-- abbreviation: ko
-  name:       Korean
-  population: 7_000_000
-  countries: 'South Korea'
-  greeting: '안녕하세요!'
-- abbreviation: tr
-  name:       Turkish
-  population: 14_000_000
-  countries: 'Turkey'
-  greeting: 'merhaba!'
-- abbreviation: ru
-  name:       Russian
-  population: 5_000_000
-  countries: 'Russia, Belarus, Kazakhstan, Kyrgyzstan'
-  greeting: 'привет!'
-- abbreviation: nl
-  name:       Dutch
-  population: 8_000_000
-  countries: 'Netherlands, Belgium'
-  greeting: 'hallo!'
-- abbreviation: fil
-  name:       Tagalog
-  countries: 'Philippines'
-  greeting: 'mabuhay!'
-  population: 8_000_000
-- abbreviation: msa
-  name:       Malay
-  population: 50_000_000
-  countries: 'Malaysia, Singapore, Brunei'
-  greeting: 'hello!'
-- abbreviation: zh
-  name:       Chinese
-  population: 20_000
-  countries: 'China, Hong-Kong, Macau'
-  greeting: '你好!'
-- abbreviation: hi
-  name:       Hindi
-  population: 12_000_000
-  countries: 'India, Pakistan, Fiji'
-  greeting: 'नमस्ते!'
-- abbreviation: 'no'
-  name:       Norwegian
-  population: 300_000
-  countries: 'goddag'
-  greeting: 'hello!'
-- abbreviation: sv
-  name:       Swedish
-  population: 500_000
-  countries: 'Sweden'
-  greeting: 'god dag!'
-- abbreviation: fi
-  name:       Finnish
-  population: 100_000
-  countries: 'Finnish'
-  greeting: ' terve!'
-- abbreviation: da
-  name:       Danish
-  population: 200_000
-  countries: 'Danish'
-  greeting: 'hej!'
-- abbreviation: pl
-  name:       Polish
-  population: 300_000
-  countries: 'Poland'
-  greeting: 'cześć!'
-- abbreviation: hu
-  name:       Hungarian
-  population: 1_000_000
-  countries: 'Hungary'
-  greeting: ' jó napot kívánok!'
-- abbreviation: fa
-  name:       Farsi
-  population: 1_000_000
-  countries: 'Iran, Afghanistan, Tajikistan'
-  greeting: ' سلام!'
-- abbreviation: he
-  name:       Hebrew
-  population: 1_000_000
-  countries: 'Israel'
-  greeting: 'שלום!'
-- abbreviation: ur
-  name:       Urdu
-  population: 1_000_000
-  countries: 'India, Pakistan, Fiji'
-  greeting: 'لسلام علیکم!'
-- abbreviation: th
-  name:       Thai
-  population: 7_0000_000
-  countries: 'Thailand'
-  greeting: 'วัสดี!'
-- abbreviation: uk
-  name:       Ukranian
-  population: 1_0000_000
-  countries: 'Ukraine'
-  greeting: 'вітаю!'
-- abbreviation: el
-  name:       Greek
-  population: 1_0000_000
-  countries: 'Greece, Cyprus'
-  greeting: 'γειά!'
-- abbreviation: cs
-  name:       Czech
-  population: 1_0000_000
-  countries: 'Czech Republic'
-  greeting: ' ahoj!'
-- abbreviation: ro
-  name:       Romanian
-  population: 1_0000_000
-  countries: 'Romania, Serbia, Moldova'
-  greeting: 'salut!'