factbook 0.1.1 → 0.1.2

data/Manifest.txt

@@ -4,11 +4,16 @@ README.md
 Rakefile
 lib/factbook.rb
 lib/factbook/page.rb
+lib/factbook/sect.rb
 lib/factbook/version.rb
 test/data/countrytemplate_au.html
 test/data/countrytemplate_be.html
 test/data/countrytemplate_br.html
+test/data/countrytemplate_ee.html
+test/data/countrytemplate_ls.html
 test/data/countrytemplate_mx.html
+test/data/countrytemplate_vt.html
+test/data/countrytemplate_xx.html
 test/helper.rb
 test/test_json.rb
 test/test_page.rb

data/README.md

@@ -21,8 +21,9 @@ offers free country profiles in the public domain (that is, no copyright(s), no
 
 ### Get country profile page as a hash (that is, structured data e.g. nested key/values)
 
-    page = Factbook::Page.new( 'br' )
-    pp page.data                      # pretty print hash
+    page = Factbook::Page.new( 'br' )   # br is the country code for Brazil
+    pp page.data                        # pretty print hash
+
 
 ### Save to disk as JSON
 
@@ -39,7 +40,9 @@ Just install the gem:
     $ gem install factbook
 
 
-## Ready-To-Use Public Domain Datasets (Generated by `factbook`)
+## Ready-To-Use Public Domain Datasets
+
+Datasets generated by `factbook` include:
 
 [openmundi/factbook.json](https://github.com/openmundi/factbook.json) - open (public domain)
 factbook country profiles in JSON for all the world's countries (using internet domain names

data/Rakefile

@@ -32,17 +32,301 @@ Hoe.spec 'factbook' do
 end
 
 
+=begin
+# errors to fix:
+saving a copy to europe/li-liechtenstein.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1882
+  found section 2 @ 13160
+  found section 3 @ 29355
+  found section 4 @ 46010
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+  found section 6 @ 64725
+
+aving a copy to europe/mc-monaco.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1446
+  found section 2 @ 12736
+  found section 3 @ 31192
+  found section 4 @ 47762
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+saving a copy to europe/sm-san-marino.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1379
+  found section 2 @ 12243
+  found section 3 @ 27349
+  found section 4 @ 46949
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+saving a copy to europe/va-vatican-city.html for debugging
+  found section 0 @ 38
+  found section 1 @ 2000
+  found section 2 @ 13093
+  found section 3 @ 19912
+  found section 4 @ 37264
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+  found section 6 @ 44353
+*** error: section not found -- <div id="CollapsiblePanel1_Trans"
+
+saving a copy to pacific/mh-marshall-islands.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1414
+  found section 2 @ 13404
+  found section 3 @ 34854
+  found section 4 @ 52734
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+saving a copy to pacific/pw-palau.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1338
+  found section 2 @ 12729
+  found section 3 @ 34145
+  found section 4 @ 51005
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+saving a copy to pacific/tv-tuvalu.html for debugging
+  found section 0 @ 38
+  found section 1 @ 1391
+  found section 2 @ 13580
+  found section 3 @ 33729
+  found section 4 @ 50390
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+saving a copy to africa/ss-south-sudan.html for debugging
+  found section 0 @ 38
+  found section 1 @ 2560
+  found section 2 @ 11342
+  found section 3 @ 26234
+  found section 4 @ 42271
+*** error: section not found -- <div id="CollapsiblePanel1_Energy"
+
+
+=end
+
+
 
 desc 'generate json for factbook.json repo'
 task :genjson do
   require 'factbook'
 
   countries = [
-    'au',
-    'be',
-    'br',
-    'mx',
-    'us'
+=begin
+     ['xx', 'world' ],     ## special code for the world
+
+     ['ee', 'europe/eu-european-union'],  ## special code for the european union
+     ['al', 'europe/al-albania' ],
+     ['an', 'europe/ad-andorra' ],
+     ['am', 'europe/am-armenia' ],
+     ['au', 'europe/at-austria' ],
+     ['aj', 'europe/az-azerbaijan' ],
+     ['bo', 'europe/by-belarus' ],
+     ['be', 'europe/be-belgium' ],
+     ['bk', 'europe/ba-bosnia-n-herzegovina' ],
+     ['bu', 'europe/bg-bulgaria' ],
+     ['hr', 'europe/hr-croatia' ],
+     ['cy', 'europe/cy-cyprus' ],
+     ['ez', 'europe/cz-czech-republic' ],
+     ['da', 'europe/dk-denmark' ],
+     ['en', 'europe/ee-estonia' ], 
+     ['fi', 'europe/fi-finland' ],
+     ['fr', 'europe/fr-france' ],
+     ['gg', 'europe/ge-georgia' ],
+     ['gm', 'europe/de-germany' ],
+     ['uk', 'europe/gb-great-britain' ],
+     ['gr', 'europe/gr-greece' ],
+     ['hu', 'europe/hu-hungary' ],
+     ['ic', 'europe/is-iceland' ],
+     ['ei', 'europe/ie-ireland' ],
+     ['it', 'europe/it-italy' ],
+     ['lg',   'europe/lv-latvia' ],
+#     ['ls',   'europe/li-liechtenstein' ],
+     ['lh',   'europe/lt-lithuania' ],
+     ['lu',   'europe/lu-luxembourg' ],
+     ['mk',   'europe/mk-macedonia' ],
+     ['mt',   'europe/mt-malta' ],
+     ['md',   'europe/md-moldova' ],
+#     ['mn',   'europe/mc-monaco' ],
+     ['mj',   'europe/me-montenegro' ],
+     ['nl',   'europe/nl-netherlands' ],
+     ['no',   'europe/no-norway' ],
+     ['pl',   'europe/pl-poland' ],
+     ['po',   'europe/pt-portugal' ],
+     ['ro',   'europe/ro-romania' ],
+     ['rs',   'europe/ru-russia' ],
+#     ['sm',   'europe/sm-san-marino' ],
+     ['ri',   'europe/rs-serbia' ],
+     ['lo',   'europe/sk-slovakia' ],
+     ['si',   'europe/si-slovenia' ],
+     ['sp',   'europe/es-spain' ],
+     ['sw',   'europe/se-sweden' ],
+     ['sz',   'europe/ch-switzerland' ],
+     ['tu',   'europe/tr-turkey' ],
+     ['up',   'europe/ua-ukraine' ],
+#     ['vt',   'europe/va-vatican-city' ],
+
+     ['ca',   'north-america/ca-canada' ],
+     ['us',   'north-america/us-united-states' ],
+     ['mx',   'north-america/mx-mexico' ],
+
+     ['ac',   'caribbean/ag-antigua-n-barbuda' ],
+     ['bf',   'caribbean/bs-bahamas' ],
+     ['bb',   'caribbean/bb-barbados' ],
+     ['cu',   'caribbean/cu-cuba' ],
+     ['do',   'caribbean/dm-dominica' ],
+     ['dr',   'caribbean/do-dominican-republic' ],
+     ['gj',   'caribbean/gd-grenada' ],
+     ['ha',   'caribbean/ht-haiti' ],
+     ['jm',   'caribbean/jm-jamaica' ],
+     ['sc',   'caribbean/kn-saint-kitts-n-nevis' ],
+     ['st',   'caribbean/lc-saint-lucia' ],
+     ['vc',   'caribbean/vc-saint-vincent-n-the-grenadines' ],
+     ['td',   'caribbean/tt-trinidad-n-tobago' ],
+
+     ['bh',   'central-america/bz-belize' ],
+     ['cs',   'central-america/cr-costa-rica' ],
+     ['es',   'central-america/sv-el-salvador' ],
+     ['gt',   'central-america/gt-guatemala' ],
+     ['ho',   'central-america/hn-honduras' ],
+     ['nu',   'central-america/ni-nicaragua' ],
+     ['pm',   'central-america/pa-panama' ],
+
+     ['ar',   'south-america/ar-argentina' ],
+     ['bl',   'south-america/bo-bolivia' ],
+     ['br',   'south-america/br-brazil' ],
+     ['ci',   'south-america/cl-chile' ],
+     ['co',   'south-america/co-colombia' ],
+     ['ec',   'south-america/ec-ecuador' ],
+     ['gy',   'south-america/gy-guyana' ],
+     ['pa',   'south-america/py-paraguay' ],
+     ['pe',   'south-america/pe-peru' ],
+     ['ns',   'south-america/sr-suriname' ],
+     ['uy',   'south-america/uy-uruguay' ],
+     ['ve',   'south-america/ve-venezuela' ],
+
+     ['ag',   'africa/dz-algeria' ],
+     ['ao',   'africa/ao-angola' ],
+     ['bn',   'africa/bj-benin' ],
+     ['bc',   'africa/bw-botswana' ],
+     ['uv',   'africa/bf-burkina-faso' ],
+     ['by',   'africa/bi-burundi' ],
+     ['cm',   'africa/cm-cameroon' ],
+     ['cv',   'africa/cv-cape-verde' ],
+     ['ct',   'africa/cf-central-african-republic' ],
+     ['cd',   'africa/td-chad' ],
+     ['cn',   'africa/km-comoros' ],
+     ['cf',   'africa/cg-congo' ],
+     ['cg',   'africa/cd-congo-dr' ],
+     ['iv',   'africa/ci-cote-d-ivoire' ],
+     ['dj',   'africa/dj-djibouti' ],
+     ['eg',   'africa/eg-egypt' ],
+     ['ek',   'africa/gq-equatorial-guinea' ],
+     ['er',   'africa/er-eritrea' ],
+     ['et',   'africa/et-ethiopia' ],
+     ['gb',   'africa/ga-gabon' ],
+     ['ga',   'africa/gm-gambia' ],
+     ['gh',   'africa/gh-ghana' ],
+     ['gv',   'africa/gn-guinea' ],
+     ['pu',   'africa/gw-guinea-bissau' ],
+     ['ke',   'africa/ke-kenya' ],
+     ['lt',   'africa/ls-lesotho' ],
+     ['li',   'africa/lr-liberia' ],
+     ['ly',   'africa/ly-libya' ],
+     ['ma',   'africa/mg-madagascar' ],
+     ['mi',   'africa/mw-malawi' ],
+     ['ml',   'africa/ml-mali' ],
+     ['mr',   'africa/mr-mauritania' ],
+     ['mp',   'africa/mu-mauritius' ],
+     ['mo',   'africa/ma-morocco' ],
+     ['mz',   'africa/mz-mozambique' ],
+     ['wa',   'africa/na-namibia' ],
+     ['ng',   'africa/ne-niger' ],
+     ['ni',   'africa/ng-nigeria' ],
+     ['rw',   'africa/rw-rwanda' ],
+     ['tp',   'africa/st-st-sao-tome-n-principe' ],
+     ['sg',   'africa/sn-senegal' ],
+     ['se',   'africa/sc-seychelles' ],
+     ['sl',   'africa/sl-sierra-leone' ],
+     ['so',   'africa/so-somalia' ],
+     ['sf',   'africa/za-south-africa' ],
+#     ['od',   'africa/ss-south-sudan' ],
+     ['su',   'africa/sd-sudan' ],
+     ['wz',   'africa/sz-swaziland' ],
+     ['tz',   'africa/tz-tanzania' ],
+     ['to',   'africa/tg-togo' ],
+     ['ts',   'africa/tn-tunisia' ],
+     ['ug',   'africa/ug-uganda' ],
+     ['za',   'africa/zm-zambia' ],
+     ['zi',   'africa/zw-zimbabwe' ],
+
+     ['ba',   'middle-east/bh-bahrain' ],
+     ['ir',   'middle-east/ir-iran' ],
+     ['iz',   'middle-east/iq-iraq' ],
+     ['is',   'middle-east/il-israel' ],
+     ['jo',   'middle-east/jo-jordan' ],
+     ['ku',   'middle-east/kw-kuwait' ],
+     ['le',   'middle-east/lb-lebanon' ],
+     ['mu',   'middle-east/om-oman' ],
+###  ['??',   'middle-east/ps-palestine' ],  -- incl. gaza strip n west bank 
+     ['qa',   'middle-east/qa-qatar' ],
+     ['sa',   'middle-east/sa-saudi-arabia' ],
+     ['sy',   'middle-east/sy-syria' ],
+     ['ae',   'middle-east/ae-united-arab-emirates' ],
+     ['ym',   'middle-east/ye-yemen' ],
+
+     ['af',   'asia/af-afghanistan' ],
+     ['bg',   'asia/bd-bangladesh' ],
+     ['bt',   'asia/bt-bhutan' ],
+     ['bx',   'asia/bn-brunei' ],
+     ['cb',   'asia/kh-cambodia' ],
+     ['ch',   'asia/cn-china' ],
+     ['in',   'asia/in-india' ],
+     ['id',   'asia/id-indonesia' ],
+     ['ja',   'asia/jp-japan' ],
+     ['kz',   'asia/kz-kazakhstan' ],
+     ['kg',   'asia/kg-kyrgyzstan' ],
+     ['la',   'asia/la-laos' ],
+     ['my',   'asia/my-malaysia' ],
+     ['mv',   'asia/mv-maldives' ],
+     ['mg',   'asia/mn-mongolia' ],
+     ['bm',   'asia/mm-myanmar' ],     ## still using Burma
+     ['np',   'asia/np-nepal' ],
+     ['kn',   'asia/kp-north-korea' ],
+     ['pk',   'asia/pk-pakistan' ],
+     ['rp',   'asia/ph-philippines' ],
+     ['sn',   'asia/sg-singapore' ],
+     ['ks',   'asia/kr-south-korea' ],
+     ['ce',   'asia/lk-sri-lanka' ],
+     ['tw',   'asia/tw-taiwan' ],
+     ['ti',   'asia/tj-tajikistan' ],
+     ['th',   'asia/th-thailand' ],
+     ['tt',   'asia/tl-timor-leste' ],
+     ['tx',   'asia/tm-turkmenistan' ],
+     ['uz',   'asia/uz-uzbekistan' ],
+     ['vm',   'asia/vn-vietnam' ],
+
+     ['as',   'pacific/au-australia' ],
+     ['fj',   'pacific/fj-fiji' ],
+     ['kr',   'pacific/ki-kiribati' ],
+#     ['rm',   'pacific/mh-marshall-islands' ],
+     ['fm',   'pacific/fm-micronesia' ],
+     ['nr',   'pacific/nr-nauru' ],
+     ['nz',   'pacific/nz-new-zealand' ],
+#     ['ps',   'pacific/pw-palau' ],
+     ['pp',   'pacific/pg-papua-new-guinea' ],
+     ['ws',   'pacific/ws-samoa' ],
+     ['bp',   'pacific/sb-solomon-islands' ],
+     ['tn',   'pacific/to-tonga' ],
+#     ['tv',   'pacific/tv-tuvalu' ],
+     ['nh',   'pacific/vu-vanuatu' ],
+
+=end
+
+
+
+=begin
+     ['',   'africa/' ],
+=end
   ]
 
   countries.each do |country|
@@ -51,29 +335,37 @@ task :genjson do
 end
 
 
-def gen_json_for( code )
-  Dir.mkdir( 'tmp' )       unless Dir.exists?( 'tmp' )
-  Dir.mkdir( 'tmp/html' )  unless Dir.exists?( 'tmp/html' )
-  Dir.mkdir( 'tmp/json' )  unless Dir.exists?( 'tmp/json' )
+def gen_json_for( country )
+
+  country_code = country[0]
+  country_path = country[1]
+
+  path_html = "tmp/html/#{country_path}.html"
+  path_json = "tmp/json/#{country_path}.json"
 
-  page = Factbook::Page.new( code )    
+  ## make sure path exist
+  FileUtils.mkdir_p( File.dirname( path_html ) )
+  FileUtils.mkdir_p( File.dirname( path_json ) )
+
+
+  page = Factbook::Page.new( country_code )
 
   ## print first 600 chars
   pp page.html[0..600]
 
   ## save for debuging
-    
-  puts "saving a copy to #{code}.html for debugging"
-  File.open( "tmp/html/#{code}.html", 'w') do |f|
+  
+  puts "saving a copy to #{country_path}.html for debugging"
+  File.open( path_html, 'w') do |f|
       f.write( page.html )
   end
 
   h = page.data
-  pp h
-    
+  ## pp h
+
   ### save to json
-  puts "saving a copy to #{code}.json for debugging"
-  File.open( "tmp/json/#{code}.json", 'w') do |f|
+  puts "saving a copy to #{country_path}.json for debugging"
+  File.open( path_json, 'w') do |f|
     f.write( JSON.pretty_generate( h ) )
   end
 end