worlddb 0.7.1 → 0.8.0

data/Manifest.txt

@@ -8,6 +8,7 @@ data/africa/1_codes/internet.yml
 data/africa/1_codes/iso3.yml
 data/africa/2_names/de.yml
 data/africa/3_more/en.wikipedia.yml
+data/africa/3_more/lang.yml
 data/africa/countries.txt
 data/america/1_codes/fifa.yml
 data/america/1_codes/internet.yml
@@ -16,6 +17,7 @@ data/america/1_codes/motor.yml
 data/america/2_names/de.yml
 data/america/2_names/es.yml
 data/america/3_more/en.wikipedia.yml
+data/america/3_more/lang.yml
 data/america/br/regions.txt
 data/america/ca/cities.txt
 data/america/ca/regions.txt
@@ -31,6 +33,7 @@ data/asia/1_codes/internet.yml
 data/asia/1_codes/iso3.yml
 data/asia/2_names/de.yml
 data/asia/3_more/en.wikipedia.yml
+data/asia/3_more/lang.yml
 data/asia/countries.txt
 data/asia/jp/cities.txt
 data/europe/1_codes/fifa.yml
@@ -40,6 +43,7 @@ data/europe/1_codes/motor.yml
 data/europe/2_names/de.yml
 data/europe/2_names/es.yml
 data/europe/3_more/en.wikipedia.yml
+data/europe/3_more/lang.yml
 data/europe/at/cities.txt
 data/europe/at/regions.txt
 data/europe/be/cities.txt
@@ -81,24 +85,29 @@ data/europe/se/cities.txt
 data/europe/tr/cities.txt
 data/europe/ua/cities.txt
 data/europe/wa/cities.txt
+data/langs.yml
 data/oceania/1_codes/fifa.yml
 data/oceania/1_codes/internet.yml
 data/oceania/1_codes/iso3.yml
 data/oceania/2_names/de.yml
 data/oceania/3_more/en.wikipedia.yml
+data/oceania/3_more/lang.yml
 data/oceania/au/cities.txt
 data/oceania/countries.txt
-data/tags.yml
+data/tags.1.yml
+data/tags.3.yml
 lib/worlddb.rb
 lib/worlddb/cli/opts.rb
 lib/worlddb/cli/runner.rb
 lib/worlddb/console.rb
 lib/worlddb/models/city.rb
 lib/worlddb/models/country.rb
+lib/worlddb/models/lang.rb
 lib/worlddb/models/prop.rb
 lib/worlddb/models/region.rb
 lib/worlddb/models/tag.rb
 lib/worlddb/models/tagging.rb
+lib/worlddb/models/usage.rb
 lib/worlddb/reader.rb
 lib/worlddb/readers/code_reader.rb
 lib/worlddb/readers/hash_reader.rb

data/Rakefile

@@ -77,7 +77,9 @@ namespace :dev do
 
 
   desc 'worlddb - test loading of builtin fixtures'
-  task :test => [:clean, :create, :import] 
+  task :test => [:clean, :create, :import]
 
+  desc 'worlddb - test loading of builtin fixtures (update)'
+  task :update => [:import]
 
 end  # namespace :dev

data/data/africa/3_more/lang.yml

@@ -0,0 +1,63 @@
+### official language mapping
+##  country code:  language codes
+
+ao: pt
+bf: fr
+bi: fr
+bj: fr
+bt: dz
+bw: en,tn
+cd: fr
+cf: fr
+cg: fr
+ci: fr
+cm: fr,en
+cv: pt
+dj: fr,ar,so
+dz: ar
+eg: ar
+er: ti,ar,en
+et: am,om
+ga: fr
+gh: en
+gm: en
+gn: fr
+gq: es,fr,pt
+gw: pt
+ke: sw,en
+km: ar,fr
+ls: en,st
+ly: ar
+ma: ar
+mg: mg,fr
+ml: fr
+mr: ar,fr
+mu: fr,en  # mfe
+mw: en,ny
+mz: pt
+
+### todo: check sf - no iso code found -- check again and add it if exists to na
+na: en,de
+ne: fr
+ng: en
+rw: rw,fr,en
+sc: fr,en  # crs
+sd: ar,en
+sl: en
+sn: fr
+so: so,ar
+st: pt
+ss: en
+sy: ar
+sz: en,ss
+td: fr,ar
+tg: fr
+tn: ar
+to: en
+tz: sw,en
+ug: en,sw
+za: zu,xh,af,st,tn,en
+zm: en
+zw: en,sn,nd
+
+

data/data/africa/countries.txt

@@ -52,11 +52,11 @@ st, São Tomé and Príncipe, STP,  1_001,  183_176,  São Tomé,  un|fifa|centr
 ###############
 ## Northern Africa
 
-dz, Algeria,   ALG,  2_381_740,  34_178_188,  un|fifa|ar|northern africa
-eg, Egypt,     EGY,  1_001_450,  82_868_000,  un|fifa|ar|northern africa|middle_east
-ma, Morocco,   MAR,    446_550,  34_859_364,  un|fifa|ar|northern africa
-ly, Libya,     LBY,  1_759_540,   6_310_434,  un|fifa|ar|northern africa
-tn, Tunisia,   TUN,    163_610,  10_486_339,  un|fifa|ar|northern africa
+dz, Algeria,   ALG,  2_381_740,  34_178_188,  un|fifa|northern africa
+eg, Egypt,     EGY,  1_001_450,  82_868_000,  un|fifa|northern africa|middle_east
+ma, Morocco,   MAR,    446_550,  34_859_364,  un|fifa|northern africa
+ly, Libya,     LBY,  1_759_540,   6_310_434,  un|fifa|northern africa
+tn, Tunisia,   TUN,    163_610,  10_486_339,  un|fifa|northern africa
 ss, South Sudan, SSD,  619_745,  8_260_490,     Juba,   un|fifa|northern africa
 sd, Sudan, SDN, 1_886_068,  30_894_000,    Khartoum,  un|fifa|northern africa
 

data/data/america/3_more/lang.yml

@@ -0,0 +1,60 @@
+### official language mapping
+##  country code:  language codes
+
+## north america
+
+ca: en,fr
+us: en,es
+mx: es
+
+### todo: group by regions
+## central america
+
+
+## carribean
+
+ag: en
+
+
+## south america
+
+ar: es
+ve: es
+br: pt
+bo: es,qu,ay
+
+
+
+tt: en
+uy: es
+vc: en
+bb: en
+bs: en
+bz: en
+cl: es
+co: es
+cr: es
+cu: es
+dm: en
+do: es
+ec: es
+gd: en
+gt: es
+gy: en
+hn: es
+ht: fr,ht
+jm: en
+kn: en
+lc: en
+ni: es
+pa: es
+pe: es
+pr: es,en
+py: es,gn
+sr: nl
+sv: es
+
+
+
+
+

data/data/america/countries.txt

@@ -15,26 +15,26 @@
   
 # area (in sq km), pop(ulation)
   
-ca, Canada,           CAN, 9_984_670,  34_278_406, en|fr|  un|fifa|north america|g8|g20|commonwealth
-us, United States,    USA, 9_629_091, 314_167_157, en|es|  un|fifa|north america|g8|g20
-mx, México [Mexico],  MEX, 1_972_550, 112_322_757, es|     un|fifa|north america|g5|g20
+ca, Canada,           CAN, 9_984_670,  34_278_406, un|fifa|north america|g8|g20|commonwealth
+us, United States,    USA, 9_629_091, 314_167_157, un|fifa|north america|g8|g20
+mx, México [Mexico],  MEX, 1_972_550, 112_322_757, un|fifa|north america|g5|g20
 
 #####################
 ## central america & caribbean islands
 
-bz, Belize,          BLZ,  22_966,    307_000,   un|fifa|en|es|central_america|commonwealth
-gt, Guatemala,       GUA, 108_889, 14_027_000,   un|fifa|es|central_america
-cr, Costa Rica,      CRC,  51_100,  4_579_000,   un|fifa|es|central_america
-hn, Honduras,        HON, 112_492,  7_466_000,   un|fifa|es|central_america
-sv, El Salvador,     SLV,  21_041,  6_163_000,   un|fifa|es|central_america
-ni, Nicaragua,       NCA, 130_373,  5_743_000,   un|fifa|es|central_america
-pa, Panamá [Panama], PAN,  75_417,  3_454_000,   un|fifa|es|central_america
+bz, Belize,          BLZ,  22_966,    307_000,   un|fifa|central_america|commonwealth
+gt, Guatemala,       GUA, 108_889, 14_027_000,   un|fifa|central_america
+cr, Costa Rica,      CRC,  51_100,  4_579_000,   un|fifa|central_america
+hn, Honduras,        HON, 112_492,  7_466_000,   un|fifa|central_america
+sv, El Salvador,     SLV,  21_041,  6_163_000,   un|fifa|central_america
+ni, Nicaragua,       NCA, 130_373,  5_743_000,   un|fifa|central_america
+pa, Panamá [Panama], PAN,  75_417,  3_454_000,   un|fifa|central_america
 
 
-cu, Cuba,         CUB,    109_886,  11_204_000,  un|fifa|es|caribbean
-jm, Jamaica,      JAM,     10_991,   2_719_000,  un|fifa|en|caribbean|commonwealth
-pr, Puerto Rico,  PUR,      8_870,   3_982_000, country:us, fifa|es|en|caribbean
-do, Dominican Republic, DOM,   48_671,  10_090_000,  un|fifa|es|caribbean
+cu, Cuba,         CUB,    109_886,  11_204_000,  un|fifa|caribbean
+jm, Jamaica,      JAM,     10_991,   2_719_000,  un|fifa|caribbean|commonwealth
+pr, Puerto Rico,  PUR,      8_870,   3_982_000, country:us, fifa|caribbean
+do, Dominican Republic, DOM,   48_671,  10_090_000,  un|fifa|caribbean
 ht, Haiti, HAI, 27_750, 9_719_932,  Port-au-Prince, un|fifa|caribbean
 
 ag, Antigua and Barbuda, ATG,  440,  81_799,    Saint John's,   un|fifa|caribbean|microstate|commonwealth
@@ -56,15 +56,15 @@ tt, Trinidad and Tobago, TRI,  5_131,  1_346_350,    Port of Spain,  un|fifa|car
 ##   - southern cone - see http://en.wikipedia.org/wiki/Southern_Cone
 ##   - andean states - see http://en.wikipedia.org/wiki/Andean_states
 
-ar, Argentina,     ARG, 2_780_400,  40_518_425, un|fifa|es|        south america|g20|southern_cone
-bo, Bolivia,       BOL, 1_098_581,  10_907_778, un|fifa|es|qu|ay|  south america|andean_states
-br, Brazil,        BRA, 8_514_215, 192_380_000, un|fifa|pt|        south america|g5|g20|southern_cone
-cl, Chile,         CHI,   755_696,  16_763_470, un|fifa|south america|es|southern_cone
-co, Colombia,      COL, 1_138_748,  46_413_791, un|fifa|south america|es|andean_states
-ec, Ecuador,       ECU,   258_238,  15_007_343, un|fifa|south america|es|qu|andean_states
-gy, Guyana,        GUY,   214_970,     752_940, un|fifa|south america|en|commonwealth
-pe, Peru,          PER, 1_285_220,  29_546_963, un|fifa|south america|es|andean_states
-sr, Suriname,      SUR,   163_820,     492_829, un|fifa|south america|nl
-py, Paraguay,      PAR,   406_752,   6_375_830, un|fifa|south america|es|southern_cone
-uy, Uruguay,       URU,   176_215,   3_510_386, un|fifa|south america|es|southern_cone
-ve, Venezuela,     VEN,   916_445,  28_833_845, un|fifa|south america|es|andean_states    ## add to andean too - why? why not?
+ar, Argentina,     ARG, 2_780_400,  40_518_425, un|fifa|south america|g20|southern_cone
+bo, Bolivia,       BOL, 1_098_581,  10_907_778, un|fifa|south america|andean_states
+br, Brazil,        BRA, 8_514_215, 192_380_000, un|fifa|south america|g5|g20|southern_cone
+cl, Chile,         CHI,   755_696,  16_763_470, un|fifa|south america|southern_cone
+co, Colombia,      COL, 1_138_748,  46_413_791, un|fifa|south america|andean_states
+ec, Ecuador,       ECU,   258_238,  15_007_343, un|fifa|south america|andean_states
+gy, Guyana,        GUY,   214_970,     752_940, un|fifa|south america|commonwealth
+pe, Peru,          PER, 1_285_220,  29_546_963, un|fifa|south america|andean_states
+sr, Suriname,      SUR,   163_820,     492_829, un|fifa|south america
+py, Paraguay,      PAR,   406_752,   6_375_830, un|fifa|south america|southern_cone
+uy, Uruguay,       URU,   176_215,   3_510_386, un|fifa|south america|southern_cone
+ve, Venezuela,     VEN,   916_445,  28_833_845, un|fifa|south america|andean_states    ## add to andean too - why? why not?

data/data/asia/3_more/lang.yml

@@ -0,0 +1,55 @@
+### official language mapping
+##  country code:  language codes
+
+ae: ar
+af: fa,ps
+am: hy
+az: az
+bd: bn
+bh: ar
+bn: ms
+cn: zh
+ge: ka
+hk: zh,en
+id: id
+il: he
+in: hi,en
+iq: ar,ku
+ir: fa
+jo: ar
+jp: ja
+kg: ky,ru
+kh: km
+kp: ko
+kr: ko,en
+kw: ar
+kz: kk,ru
+la: lo
+lb: ar,fr
+lk: si,ta
+lr: en
+mm: my
+mn: mn
+mv: dv
+my: ms
+np: ne
+om: ar
+ph: en,tl
+pk: en,ur
+ps: ar,he
+qa: ar
+sa: ar
+sg: en,ms,zh,ta
+th: th
+tj: tg,ru
+tl: pt # tet
+tm: tk
+tw: zh
+uz: uz # kaa
+vn: vi
+ye: ar
+
+
+
+
+

data/data/europe/3_more/lang.yml

@@ -0,0 +1,47 @@
+### europe
+
+ad: ca
+at: de
+ba: bs,hr,sr
+be: nl,fr,de
+ch: de,fr,it,rm
+bg: bg
+by: be,ru
+cy: el,tr
+cz: cs
+de: de
+dk: da
+ee: et
+es: ca,es,eu,gl
+fi: fi,sv,se
+fo: fo
+fr: fr
+gb: en,ga,cy,gd,kw
+gr: el
+hr: hr
+hu: hu
+ie: en,ga
+is: is
+it: it,de,fr
+li: de
+lt: lt
+lu: lb,fr,de
+lv: lv
+mc: fr
+md: ru,uk,ro
+mk: mk
+mt: mt,en
+nl: nl
+no: nb,nn,no,se
+pl: pl
+pt: pt
+ro: ro
+rs: sr
+ru: ru
+se: sv
+si: sl
+sk: sk
+sm: it
+tr: tr
+ua: uk
+va: it

data/data/europe/countries.txt

@@ -57,32 +57,32 @@ eu, European Union, EUR,  4_324_782, 503_492_041,  supra,  g20   # NB: no FIFA c
 
 ## todo: auto-add tag eu?? for supra:eu?
 
-at, Austria,      AUT,    83_871,  8_414_638,  supra:eu, un|fifa|uefa|de|        eu|euro|schengen|central_europe|western_europe
-be, Belgium,      BEL,    30_528, 11_007_020,  supra:eu, un|fifa|uefa|nl|fr|de|  eu|euro|schengen|benelux
+at, Austria,      AUT,    83_871,  8_414_638,  supra:eu, un|fifa|uefa|eu|euro|schengen|central_europe|western_europe
+be, Belgium,      BEL,    30_528, 11_007_020,  supra:eu, un|fifa|uefa|eu|euro|schengen|benelux
 cy, Cyprus,       CYP,     9_251,  1_099_341,  supra:eu, un|fifa|uefa|eu|euro|asia|western asia|middle_east|mediterranean|southern_europe|commonwealth 
-de, Germany,      GER,   357_050, 81_799_600,  supra:eu, un|fifa|uefa|de|        eu|euro|schengen|g8|g20|western europe|central_europe
+de, Germany,      GER,   357_050, 81_799_600,  supra:eu, un|fifa|uefa|eu|euro|schengen|g8|g20|western europe|central_europe
 ee, Estonia,      EST,    45_226,  1_340_194,  supra:eu, un|fifa|uefa|eu|euro|schengen|uefa|northern europe|baltic|eastern_europe
 es, Spain,        ESP,   506_030, 46_030_109,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe
 fi, Finland,      FIN,   338_145,  5_391_700,  supra:eu, un|fifa|uefa|eu|euro|schengen|northern europe|nordic
 fr, France,       FRA,   674_843, 65_821_885,  supra:eu, un|fifa|uefa|eu|euro|schengen|g8|g20|western_europe
-gr, Greece,       GRE,   131_990, 10_787_690,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe             # NB: ISO (GRC) <> FIFA (GRE)
+gr, Greece,       GRE,   131_990, 10_787_690,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe
 ie, Irland,       IRL,    70_273,  4_722_028,  supra:eu, un|fifa|uefa|eu|euro|northern europe|western_europe
 it, Italy,        ITA,   301_318, 60_681_514,  supra:eu, un|fifa|uefa|eu|euro|schengen|g8|g20|southern_europe
 lu, Luxembourg,   LUX,     2_586,    511_840,  supra:eu, un|fifa|uefa|eu|euro|schengen|benelux|western_europe
 mt, Malta,        MLT,       316,    417_608,  supra:eu, un|fifa|uefa|eu|euro|schengen|microstate|mediterranean|southern_europe|commonwealth
 nl, Netherlands,  NED,    41_526, 16_703_700,  supra:eu, un|fifa|uefa|eu|euro|schengen|benelux|western_europe
-pt, Portugal,     POR,    92_391, 10_647_763,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe                  # NB: ISO (PRT) <> FIFA (POR)
+pt, Portugal,     POR,    92_391, 10_647_763,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe
 sk, Slovakia,     SVK,    49_037,  5_440_078,  supra:eu, un|fifa|uefa|eu|euro|schengen|central_europe
 si, Slovenia,     SVN,    20_273,  2_048_951,  supra:eu, un|fifa|uefa|eu|euro|schengen|southern_europe|central_europe
 
-bg, Bulgaria,         BUL,  110_994,  7_364_570,  supra:eu, un|fifa|uefa|eu|eastern_europe|southeastern_europe              
+bg, Bulgaria,         BUL,  110_994,  7_364_570,  supra:eu, un|fifa|uefa|eu|eastern_europe|southeastern_europe
 dk, Denmark,          DEN,   43_094,  5_564_219,  supra:eu, un|fifa|uefa|eu|schengen|northern europe|scandinavia|nordic
 lv, Latvija [Latvia], LVA,   64_589,  2_245_357,  supra:eu, un|fifa|uefa|eu|schengen|northern europe|baltic
 lt, Lithuania,        LTU,   65_303,  3_207_060,  supra:eu, un|fifa|uefa|eu|schengen|northern europe|baltic
 pl, Poland,           POL,  312_683, 38_186_860,  supra:eu, un|fifa|uefa|eu|schengen|central_europe
 ro, Romania,          ROU,  238_391, 19_042_936,  supra:eu, un|fifa|uefa|eu|eastern_europe|southeastern_europe
 se, Sweden,           SWE,  449_964,  9_415_570,  supra:eu, un|fifa|uefa|eu|schengen|northern europe|scandinavia|nordic
-cz, Czech Republic,   CZE,   78_866, 10_535_811,  supra:eu, un|fifa|uefa|cs|sk|  eu|schengen|central_europe
+cz, Czech Republic,   CZE,   78_866, 10_535_811,  supra:eu, un|fifa|uefa|eu|schengen|central_europe
 hu, Hungary,          HUN,   93_030,  9_979_000,  supra:eu, un|fifa|uefa|eu|schengen|central_europe
 
 ## todo/check: make a distinction between uk and gb?
@@ -102,8 +102,8 @@ fo, Faroe Islands,  FRO,    1_399,      49_267,  country:dk,  fifa|uefa|northern
 ad, Andorra,     AND,         468,      85_082,  un|fifa|uefa|microstate|western_europe
 al, Albania,     ALB,      28_748,   3_002_859,  un|fifa|uefa|southern_europe|balkans|southeastern_europe
 by, Belarus,     BLR,     207_600,   9_643_566,  un|fifa|uefa|eastern_europe
-ch, Switzerland, SUI,      41_285,   7_866_500,  un|fifa|uefa|de|fr|it|rm|  schengen|western_europe|central_europe
-hr, Croatia,     CRO,      56_594,   4_290_612,  un|fifa|uefa|southern_europe|balkans|southeastern_europe     # NB: ISO (HRV) <> FIFA (CRO);  local name: Hrvatska
+ch, Switzerland, SUI,      41_285,   7_866_500,  un|fifa|uefa|schengen|western_europe|central_europe
+hr, Croatia,     CRO,      56_594,   4_290_612,  un|fifa|uefa|southern_europe|balkans|southeastern_europe
 rs, Serbia,      SRB,      88_361,   7_276_604,  un|fifa|uefa|southern_europe|balkans|southeastern_europe
 ru, Russia,       RUS, 17_098_242, 142_517_670,  un|fifa|uefa|asia|north asia|g8|g20
 tr, Turkey,       TUR,    783_562,  79_749_461,  un|fifa|uefa|asia|western asia|g20

data/data/langs.yml

@@ -0,0 +1,210 @@
+## list of languages
+##  use key / title e.g. en: English, de: Deutsch etc.
+
+## for a list see http://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
+
+
+### languages in europe
+
+sq: Albanian
+eu: Basque
+be: Belarusian
+bs: Bosnian
+br: Breton
+bg: Bulgarian
+ca: Catalan
+kw: Cornish
+co: Corsican
+hr: Croatian
+cs: Czech
+da: Danish
+nl: Dutch
+en: English
+et: Estonian
+fo: Faroese
+fi: Finnish
+fr: French
+gl: Galician
+de: German
+el: Greek
+hu: Hungarian
+ga: Irish
+is: Icelandic
+it: Italian
+lb: Luxembourgish
+lt: Lithuanian
+lv: Latvian
+mk: Macedonian
+mt: Maltese
+nb: Norwegian Bokmål
+nn: Norwegian Nynorsk
+no: Norwegian
+pl: Polish
+pt: Portuguese
+rm: Romansh
+ro: Romanian|Moldavian
+ru: Russian
+sc: Sardinian
+sr: Serbian
+gd: Scottish Gaelic|Gaelic
+es: Spanish|Castilian
+sv: Swedish
+sk: Slovak
+sl: Slovene
+tr: Turkish
+uk: Ukrainian 
+wa: Walloon
+cy: Welsh
+fy: Western Frisian
+yi: Yiddish
+kl: Kalaallisut|Greenlandic
+
+### america
+
+ay: Aymara
+cr: Cree
+gn: Guaraní
+ht: Haitian
+ik: Inupiaq
+iu: Inuktitut
+nv: Navajo
+oj: Ojibwe
+qu: Quechua
+
+
+### todo: group/sort by continent 
+### africa / asia / oceania
+
+ab: Abkhaz
+aa: Afar
+af: Afrikaans
+ak: Akan
+am: Amharic
+ar: Arabic
+an: Aragonese
+hy: Armenian
+as: Assamese
+av: Avaric
+ae: Avestan
+az: Azerbaijani
+bm: Bambara
+ba: Bashkir
+bn: Bengali
+bh: Bihari
+bi: Bislama
+my: Burmese
+ch: Chamorro
+ce: Chechen
+ny: Chichewa
+zh: Chinese
+cv: Chuvash
+dv: Divehi
+dz: Dzongkha
+ee: Ewe
+fj: Fijian
+ff: Fula
+ka: Georgian
+gu: Gujarati
+ha: Hausa
+he: Hebrew
+hz: Herero
+hi: Hindi
+ho: Hiri Motu
+id: Indonesian
+ig: Igbo
+ja: Japanese
+jv: Javanese
+kn: Kannada
+kr: Kanuri
+ks: Kashmiri
+kk: Kazakh
+km: Khmer|Cambodian
+ki: Kikuyu
+rw: Kinyarwanda
+ky: Kyrgyz
+kv: Komi
+kg: Kongo
+ko: Korean
+ku: Kurdish
+kj: Kwanyama
+lg: Ganda
+li: Limburgish
+ln: Lingala
+lo: Lao 
+lu: Luba-Katanga
+gv: Manx
+mg: Malagasy
+ms: Malay
+ml: Malayalam
+mi: Māori
+mr: Marathi
+mh: Marshallese
+mn: Mongolian
+na: Nauru
+nd: North Ndebele
+ne: Nepali
+ng: Ndonga
+ii: Nuosu
+nr: South Ndebele
+oc: Occitan
+om: Oromo
+or: Oriya
+os: Ossetian|Ossetic
+pa: Panjabi|Punjabi
+pi: Pāli
+fa: Persian
+ps: Pashto
+rn: Kirundi
+sa: Sanskrit
+sd: Sindhi
+se: Northern Sami
+sm: Samoan
+sg: Sango
+sn: Shona
+si: Sinhala
+so: Somali
+st: Southern Sotho
+su: Sundanese
+sw: Swahili
+ss: Swati
+ta: Tamil
+te: Telugu
+tg: Tajik
+th: Thai
+ti: Tigrinya
+bo: Tibetan
+tk: Turkmen
+tl: Tagalog
+tn: Tswana
+to: Tonga
+ts: Tsonga
+tt: Tatar
+tw: Twi
+ty: Tahitiani
+ug: Uighur
+ur: Urdu
+uz: Uzbek
+ve: Venda
+vi: Vietnamese
+wo: Wolof
+xh: Xhosa
+yo: Yoruba
+za: Zhuang
+zu: Zulu
+
+
+#####################
+## constructed languages
+
+## eo: Esperanto
+## ia: Interlingua
+## ie: Interlingue
+## io: Ido
+## vo: Volapük
+
+
+#########################
+## acient
+
+## la: Latin
+## cu: Old Church Slavonic|Old Bulgarian

data/data/oceania/3_more/lang.yml

@@ -0,0 +1,17 @@
+
+au: en
+nz: mi,en
+
+
+fj: en
+fm: en
+ki: en
+mh: en,mh
+nr: na,en
+pg: en,ho  # tpi
+pw: en,ja  # pau,sov,tox
+sb: en
+tv: en
+vu: bi,en,fr
+ws: sm,en
+

data/data/oceania/countries.txt

@@ -8,7 +8,7 @@
 ##  - Polynesia
 
 
-au, Australia, AUS,    7_686_850,  22_028_000,   un|fifa|en|g20|commonwealth
+au, Australia, AUS,    7_686_850,  22_028_000,   un|fifa|g20|commonwealth
 
 ##############
 ### Melanesia
@@ -34,7 +34,7 @@ ki, Kiribati, KIR, 811, 103_500,  Tarawa,  un|micronesia|microstate|commonwealth
 ## Polynesia
 ##   see http://en.wikipedia.org/wiki/Polynesia
 
-nz, New Zealand, NZL,    268_680,   4_108_037,   un|fifa|en|polynesia|commonwealth
+nz, New Zealand, NZL,    268_680,   4_108_037,   un|fifa|polynesia|commonwealth
 ws, Samoa, SAM,   2_831,  194_320,   Apia, un|fifa|polynesia|commonwealth
 to, Tonga, TGA,  748,  103_036,     Nuku'alofa,   un|fifa|polynesia|microstate|commonwealth
 tv, Tuvalu, TUV, 26,  10_544,   Funafuti,   un|polynesia|microstate|commonwealth      # nb: use ISO code; NOT fifa member

data/data/tags.1.yml

@@ -0,0 +1,40 @@
+### setup some grade 1 tags
+
+
+###
+# for 193 un members see www.un.org/en/members
+
+
+## some tags
+
+continents: africa, america, asia, europe, oceania
+
+####################
+# geo regions
+africa: northern africa, western africa, central africa, eastern africa, southern africa
+
+americas: north america, south america, central america, caribbean (islands)
+
+## check if yaml can handle key w/ space??
+south_america: andean states, southern cone
+
+europe: northern europe, southern europe, western europe, central europe, eastern europe, southeastern europe
+
+## more regions
+europe2: baltic (states), scandinavia, nordic (countries), balkans
+
+
+## get used for more than one continent
+more: middle east, indian ocean, atlantic ocean
+
+# orgs
+
+orgs: un, g5, g8, g20, eu, commonwealth, mercosur, nafta
+football: fifa, uefa, afc, ofc, caf, csf, concacaf
+
+europe3: benelux, euro, schengen
+
+misc: microstate
+
+# national regions
+brasil: s|South, se|Southeast, co|Centerwest, ne|Northeast, n|North

data/data/tags.3.yml

@@ -0,0 +1,23 @@
+### setup some grade 3 tags
+
+
+####
+
+# categorize countries into brackets by area
+area: area_1_000_000_n_up,
+      area_100_000_to_1_000_000,
+      area_1_000_to_100_000,
+      area_1_000_n_less    # microstate
+
+# include all
+area2: area_100_000_n_up, area_1_000_n_up
+
+
+# categorize countries into brackets by pop(ulation)
+pop: pop_100m_n_up,
+     pop_10m_to_100m,
+     pop_1m_to_10m,
+     pop_1m_n_less
+
+# include all
+pop2: pop_10m_n_up, pop_1m_n_up

data/lib/worlddb/models/country.rb

@@ -5,6 +5,9 @@ module WorldDB::Models
 class Country < ActiveRecord::Base
   self.table_name = 'countries'
 
+  has_many :usages
+  has_many :langs, :through => :usages # lang(uage)s through usages (that is, countries_langs) join table
+
   has_many :regions, :class_name => 'Region', :foreign_key => 'country_id'
   has_many :cities,  :class_name => 'City',   :foreign_key => 'country_id'
   

data/lib/worlddb/models/lang.rb

@@ -0,0 +1,15 @@
+# encoding: utf-8
+
+module WorldDB::Models
+
+  class Lang < ActiveRecord::Base
+    
+    has_many :usages  # join table for countries_langs
+    
+    has_many :countries, :through => :usages
+
+    validates :key, :format => { :with => /^[a-z]{2}$/, :message => 'expected two lowercase letters a-z' }
+
+  end  # class Lang
+
+end # module WorldDB::Models

data/lib/worlddb/models/tag.rb

@@ -10,17 +10,21 @@ module WorldDB::Models
     has_many :countries, :through => :taggings, :source => :taggable, :source_type => 'WorldDB::Models::Country', :class_name => 'Country'
     has_many :regions,   :through => :taggings, :source => :taggable, :source_type => 'WorldDB::Models::Region',  :class_name => 'Region'
 
-    ## fix/todo: improve regex use   [a-z][a-z0-9] | [a-z][a-z0-9_ ]+[a-z0-9] to only allow spaces and underscore inbetween; do not allow digit as first char 
-    validates :key, :format => { :with => /^[a-z0-9_ ]{2,}$/, :message => 'expected two or more lowercase letters a-z or 0-9 digits or space or underscore' }
+    ## nb: only allow spaces and underscore inbetween; do not allow digit as first char
+    validates :key,  :format => { :with => /^[a-z]$|^[a-z][a-z0-9_ ]*[a-z0-9]$/, :message => 'expected one or more lowercase letters a-z or 0-9 digits or space or underscore' }
 
     scope :by_key,   order( 'key desc' )
     scope :by_title, order( 'title desc' )
+    scope :top,      where( 'grade=1' )
     
     before_save :on_before_save
 
     def on_before_save
       # replace space with underscore e.g. north america becomes north_america and so on
       self.slug = key.gsub( ' ', '_' )
+      
+      ## if title is empty auto fill w/ key
+      self.title = key   if title.blank?
     end
       
   end  # class Tag

data/lib/worlddb/models/usage.rb

@@ -0,0 +1,12 @@
+# encoding: utf-8
+
+module WorldDB::Models
+
+  class Usage < ActiveRecord::Base
+
+    belongs_to :country
+    belongs_to :lang
+
+  end  # class Usage
+
+end # module WorldDB::Models

data/lib/worlddb/reader.rb

@@ -41,7 +41,11 @@ class Reader
 
   def load_with_include_path( name, include_path )
 
-    if name =~ /\/fifa/
+    if name =~ /^lang/
+       load_langs_with_include_path( name, include_path )
+    elsif name =~ /\/lang/
+       load_usages_with_include_path( name, include_path )
+    elsif name =~ /\/fifa/
        load_xxx_with_include_path( 'fifa', name, include_path )
     elsif name =~ /\/iso3/
        load_xxx_with_include_path( 'iso3', name, include_path )
@@ -49,6 +53,8 @@ class Reader
        load_xxx_with_include_path( 'net', name, include_path )
     elsif name =~ /\/motor/
        load_xxx_with_include_path( 'motor', name, include_path )
+    elsif name =~ /^tag.*\.(\d)$/
+       load_tags_with_include_path( name, include_path, :grade => $1.to_i )
     elsif name =~ /^([a-z]{3,})\/countries/     # e.g. africa/countries or america/countries
       ## auto-add continent (from folder structure) as tag
       load_countries_with_include_path( name, include_path, :tags => $1 )
@@ -63,6 +69,7 @@ class Reader
       # todo/fix: exit w/ error
     end
   end
+  
 
   def load_builtin( name )  ## convenience helper (requires proper named files w/ convention)
     load_with_include_path( name, WorldDB.data_path )
@@ -102,6 +109,139 @@ class Reader
   end
 
 
+  def load_langs_with_include_path( name, include_path )
+    path = "#{include_path}/#{name}.yml"
+
+    puts "*** parsing data '#{name}' (#{path})..."
+
+    reader = HashReader.new( logger, path )
+
+    reader.each do |key, value|
+
+      puts "adding lang >>#{key}<< >>#{value}<<..."
+      
+      lang_key   = key.strip
+      lang_title = value.strip
+      
+      lang_attribs = {}
+        
+      ## check if it exists
+      lang = Lang.find_by_key( lang_key )
+      if lang.present?
+        puts "*** update lang #{lang.id}-#{lang.key}:"
+      else
+        puts "*** create lang:"
+        lang = Lang.new
+        lang_attribs[ :key ] = lang_key
+      end
+        
+      lang_attribs[ :title ] = lang_title
+        
+      puts lang_attribs.to_json
+   
+      lang.update_attributes!( lang_attribs )
+    end # each key,value
+
+    Prop.create_from_worlddb_fixture!( name, path )
+  end
+  
+  def load_langs_builtin( name )
+    load_langs_with_include_path( name, WorldDB.data_path )
+  end
+
+
+  def load_tags_with_include_path( name, include_path, more_values={} )
+    path = "#{include_path}/#{name}.yml"
+
+    puts "*** parsing data '#{name}' (#{path})..."
+
+    reader = HashReader.new( logger, path )
+
+    grade = 1
+    
+    if more_values[:grade].present?
+      grade = more_values[:grade].to_i
+    end
+
+    reader.each do |key, value|
+      ### split value by comma (e.g. northern america,southern america, etc.)
+      puts "adding grade #{grade} tags >>#{key}<< >>#{value}<<..."
+      tag_pairs = value.split(',')
+      tag_pairs.each do |pair|
+        ## split key|title
+        values = pair.split('|')
+        
+        key   = values[0]
+        ### remove (optional comment) from key (e.g. carribean (islands))
+        key = key.gsub( /\(.+\)/, '' )
+        ## remove leading n trailing space
+        key = key.strip
+        
+        title = values[1] || ''  # nb: title might be empty/missing
+        title = title.strip
+        
+        tag_attribs = {}
+        
+        ## check if it exists
+        ## todo/fix: add country_id for lookup?
+        tag = Tag.find_by_key( key )
+        if tag.present?
+          puts "*** update tag #{tag.id}-#{tag.key}:"
+        else
+          puts "*** create tag:"
+          tag = Tag.new
+          tag_attribs[ :key ] = key
+        end
+        
+        tag_attribs[ :title ] = title
+        tag_attribs[ :grade ] = grade
+        
+        puts tag_attribs.to_json
+   
+        tag.update_attributes!( tag_attribs )
+      end
+    end # each key,value
+
+    Prop.create_from_worlddb_fixture!( name, path )
+  end # method load_tags_with_include_path
+
+  def load_tags_builtin( name, include_path, more_values={} )
+    load_tags_with_include_path( name, WorldDB.data_path, more_values )
+  end
+
+
+  def load_usages_with_include_path( name, include_path )
+    path = "#{include_path}/#{name}.yml"
+
+    puts "*** parsing data '#{name}' (#{path})..."
+
+    reader = HashReader.new( logger, path )
+
+    reader.each do |key, value|
+      puts "   adding langs >>#{value}<<to country >>#{key}<<"
+      
+      country = Country.find_by_key!( key )
+      
+      lang_keys = value.split(',')
+      lang_keys.each do |lang_key|
+
+        ### remove (optional comment) from key (e.g. carribean (islands))
+        lang_key = lang_key.gsub( /\(.+\)/, '' )
+        ## remove leading n trailing space
+        lang_key = lang_key.strip
+
+        lang = Lang.find_by_key!( lang_key )
+        Usage.create!( country_id: country.id, lang_id: lang.id, official: true, minor: false )
+      end
+    end
+
+    Prop.create_from_worlddb_fixture!( name, path )
+  end
+  
+  def load_usages_builtin( name )
+    load_usages_with_include_path( name, WorldDB.data_path )
+  end
+
   def load_xxx_with_include_path( xxx, name, include_path )
     path = "#{include_path}/#{name}.yml"
 
@@ -262,9 +402,9 @@ private
             if area >= 1_000_000
               value_tag_keys << 'area_1_000_000_n_up'
             elsif area >= 100_000
-              value_tag_keys << 'area_1_000_000_n_100_000'
+              value_tag_keys << 'area_100_000_to_1_000_000'
             elsif area >= 1000
-              value_tag_keys << 'area_100_000_n_1_000'
+              value_tag_keys << 'area_1_000_to_100_000'
             else
               value_tag_keys << 'area_1_000_n_less' # microstate
             end
@@ -278,9 +418,9 @@ private
             if pop >= 100_000_000
               value_tag_keys << 'pop_100m_n_up'
             elsif pop >= 10_000_000
-              value_tag_keys << 'pop_100m_n_10m'
+              value_tag_keys << 'pop_10m_to_100m'
             elsif pop >= 1_000_000
-              value_tag_keys << 'pop_10m_n_1m'
+              value_tag_keys << 'pop_1m_to_10m'
             else
               value_tag_keys << 'pop_1m_n_less'
             end

data/lib/worlddb/readers/hash_reader.rb

@@ -39,11 +39,25 @@ class HashReader
     end
 
     ## quote implicit boolean types on,no,n,y
-    
-    text = text.gsub( /\b(ON|On|on|NO|No|no|N|n|Y|y)\b/ ) do |value|
-      puts "*** warn: hash reader - found implicit bool (#{$1}); adding quotes to turn into string; see yaml.org/refcard.html"
-      "'#{$1}'"  # add quotes to turn it into a string (not bool e.g. true|false)
+
+    ## nb: escape only if key e.g. no: or "free standing" value on its own line e.g.
+    ##   no: no
+
+    text = text.gsub( /^([ ]*)(ON|On|on|NO|No|no|N|n|Y|y)[ ]*:/ ) do |value|
+      puts "*** warn: hash reader - found implicit bool (#{$1}#{$2}) for key; adding quotes to turn into string; see yaml.org/refcard.html"
+      # nb: preserve leading spaces for structure - might be significant
+      "#{$1}'#{$2}':"  # add quotes to turn it into a string (not bool e.g. true|false)
     end
+
+    ## nb: value must be freestanding (only allow optional eol comment)
+    ##  do not escape if part of string sequence e.g.
+    ##  key: nb,nn,no,se   => nb,nn,'no',se  -- avoid!!
+
+    text = text.gsub( /:[ ]+(ON|On|on|NO|No|no|N|n|Y|y)[ ]*($| #.*$)/ ) do |value|
+      puts "*** warn: hash reader - found implicit bool (#{$1}) for value; adding quotes to turn into string; see yaml.org/refcard.html"
+      ": '#{$1}'"  # add quotes to turn it into a string (not bool e.g. true|false)
+    end
+
     
     @hash = YAML.load( text )
   end
@@ -58,7 +72,7 @@ class HashReader
       key   = key_wild.to_s.strip
       value = value_wild.to_s.strip
       
-      puts ">>#{key}<< >>#{value}<<"
+      puts "yaml key:#{key_wild.class.name} >>#{key}<<, value:#{value_wild.class.name} >>#{value}<<"
     
       yield( key, value )
     end

data/lib/worlddb/schema.rb

@@ -82,7 +82,8 @@ end
 create_table :tags do |t|
   t.string :key,  :null => false
   t.string :slug, :null => false
-  t.string :title    # todo: make required? 
+  t.string :title    # todo: make required?
+  t.integer :grade, :null => false, :default => 1  # grade/tier e.g. 1/2/3 for now
   ## todo: add parent or similar for hierachy (for tag stacks/packs)
   t.timestamps
 end
@@ -99,6 +100,21 @@ add_index :taggings, :tag_id
 add_index :taggings, [:taggable_id, :taggable_type]
 
 
+create_table :langs do |t|  # langs == languages (e.g. en/English, de/Deutsch, etc.)
+  t.string :key,   :null => false
+  t.string :title, :null => false
+  t.timestamps
+end
+
+create_table :usages do |t|  # join table for countries_langs
+  t.references :country,  :null => false
+  t.references :lang,     :null => false
+  t.boolean    :official, :null => false, :default => true  # is_official language in country
+  t.boolean    :minor,    :null => false, :default => false # spoken by minority 
+  t.float      :percent     # usage in percent e.g. 90.0, 0.55, etc.
+  t.timestamps
+end
+
 create_table :props do |t|
   t.string :key,   :null => false
   t.string :value, :null => false

data/lib/worlddb/version.rb

@@ -1,5 +1,5 @@
 
 module WorldDB
-  VERSION = '0.7.1'
+  VERSION = '0.8.0'
 end
 

data/lib/worlddb.rb

@@ -28,6 +28,8 @@ require 'worlddb/models/region'
 require 'worlddb/models/city'
 require 'worlddb/models/tag'
 require 'worlddb/models/tagging'
+require 'worlddb/models/lang'
+require 'worlddb/models/usage'
 require 'worlddb/schema'       # NB: requires worlddb/models (include WorldDB::Models)
 require 'worlddb/utils'
 require 'worlddb/readers/code_reader'
@@ -62,6 +64,9 @@ module WorldDB
   end
 
   def self.fixtures  # all builtin fixtures; helper for covenience
+     tag_fixtures  + 
+     country_fixtures +
+     lang_fixtures +
      africa_fixtures  +
      america_fixtures +
      europe_fixtures  +
@@ -69,16 +74,37 @@ module WorldDB
      oceania_fixtures
   end
 
+
+  def self.tag_fixtures
+    ['tags.1', 'tags.3']
+  end
+  
+  def self.country_fixtures
+    ['africa/countries',
+     'america/countries',
+     'asia/countries',
+     'europe/countries',
+     'oceania/countries']
+  end
+
+  def self.lang_fixtures
+    ['langs',
+     'africa/3_more/lang',
+     'america/3_more/lang',
+     'asia/3_more/lang',
+     'europe/3_more/lang',
+     'oceania/3_more/lang'
+    ]
+  end
+
   def self.africa_fixtures
-    ['countries',
-    '1_codes/fifa',
-    '1_codes/internet',
-    '1_codes/iso3'].map { |path| "africa/#{path}" }
+    ['1_codes/fifa',
+     '1_codes/internet',
+     '1_codes/iso3'].map { |path| "africa/#{path}" }
   end
 
   def self.america_fixtures
-  ['countries',
-   '1_codes/fifa',
+  ['1_codes/fifa',
    '1_codes/internet',
    '1_codes/iso3',
    '1_codes/motor',
@@ -94,16 +120,14 @@ module WorldDB
   end
 
   def self.asia_fixtures
-  ['countries',
-   '1_codes/fifa',
+  ['1_codes/fifa',
    '1_codes/internet',
    '1_codes/iso3',
    'jp/cities'].map { |path| "asia/#{path}" }
   end
   
   def self.europe_fixtures
-  ['countries',
-   '1_codes/fifa',
+  ['1_codes/fifa',
    '1_codes/internet',
    '1_codes/iso3',
    '1_codes/motor',
@@ -150,11 +174,10 @@ module WorldDB
   end
 
   def self.oceania_fixtures
-   ['countries',
-   '1_codes/fifa',
-   '1_codes/internet',
-   '1_codes/iso3',
-   'au/cities'].map { |path| "oceania/#{path}" }
+   ['1_codes/fifa',
+    '1_codes/internet',
+    '1_codes/iso3',
+    'au/cities'].map { |path| "oceania/#{path}" }
   end
 
   ## todo/fix: rename to load/load_all - why? why not?? or just add an alias?
@@ -198,6 +221,8 @@ module WorldDB
       City.delete_all
       Region.delete_all
       Country.delete_all
+      Usage.delete_all
+      Lang.delete_all
       Prop.delete_all
     end
     
@@ -221,6 +246,8 @@ module WorldDB
       puts " #{'%5d' % City.where(d: true).count} districts"
       puts " #{'%5d' % Tag.count} tags"
       puts " #{'%5d' % Tagging.count} taggings"
+      puts " #{'%5d' % Lang.count} langs"
+      puts " #{'%5d' % Usage.count} usages"
     end
     
     def props

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: worlddb
 version: !ruby/object:Gem::Version 
-  hash: 1
+  hash: 63
   prerelease: 
   segments: 
   - 0
-  - 7
-  - 1
-  version: 0.7.1
+  - 8
+  - 0
+  version: 0.8.0
 platform: ruby
 authors: 
 - Gerald Bauer
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-12-08 00:00:00 Z
+date: 2012-12-09 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: activerecord
@@ -81,6 +81,7 @@ files:
 - data/africa/1_codes/iso3.yml
 - data/africa/2_names/de.yml
 - data/africa/3_more/en.wikipedia.yml
+- data/africa/3_more/lang.yml
 - data/africa/countries.txt
 - data/america/1_codes/fifa.yml
 - data/america/1_codes/internet.yml
@@ -89,6 +90,7 @@ files:
 - data/america/2_names/de.yml
 - data/america/2_names/es.yml
 - data/america/3_more/en.wikipedia.yml
+- data/america/3_more/lang.yml
 - data/america/br/regions.txt
 - data/america/ca/cities.txt
 - data/america/ca/regions.txt
@@ -104,6 +106,7 @@ files:
 - data/asia/1_codes/iso3.yml
 - data/asia/2_names/de.yml
 - data/asia/3_more/en.wikipedia.yml
+- data/asia/3_more/lang.yml
 - data/asia/countries.txt
 - data/asia/jp/cities.txt
 - data/europe/1_codes/fifa.yml
@@ -113,6 +116,7 @@ files:
 - data/europe/2_names/de.yml
 - data/europe/2_names/es.yml
 - data/europe/3_more/en.wikipedia.yml
+- data/europe/3_more/lang.yml
 - data/europe/at/cities.txt
 - data/europe/at/regions.txt
 - data/europe/be/cities.txt
@@ -154,24 +158,29 @@ files:
 - data/europe/tr/cities.txt
 - data/europe/ua/cities.txt
 - data/europe/wa/cities.txt
+- data/langs.yml
 - data/oceania/1_codes/fifa.yml
 - data/oceania/1_codes/internet.yml
 - data/oceania/1_codes/iso3.yml
 - data/oceania/2_names/de.yml
 - data/oceania/3_more/en.wikipedia.yml
+- data/oceania/3_more/lang.yml
 - data/oceania/au/cities.txt
 - data/oceania/countries.txt
-- data/tags.yml
+- data/tags.1.yml
+- data/tags.3.yml
 - lib/worlddb.rb
 - lib/worlddb/cli/opts.rb
 - lib/worlddb/cli/runner.rb
 - lib/worlddb/console.rb
 - lib/worlddb/models/city.rb
 - lib/worlddb/models/country.rb
+- lib/worlddb/models/lang.rb
 - lib/worlddb/models/prop.rb
 - lib/worlddb/models/region.rb
 - lib/worlddb/models/tag.rb
 - lib/worlddb/models/tagging.rb
+- lib/worlddb/models/usage.rb
 - lib/worlddb/reader.rb
 - lib/worlddb/readers/code_reader.rb
 - lib/worlddb/readers/hash_reader.rb

data/data/tags.yml

@@ -1,17 +0,0 @@
-
-###
-# for 193 un members see www.un.org/en/members
-
-
-## some tags
-
-continents: europe, america, asia, africa, oceania
-americas: north america, south america, central america, caribbean islands
-orgs: un, eu, mercosur, nafta
-football: uefa, afc, ofc, caf, csf, concacaf
-
-europe: benelux,euro
-
-
-# regions
-brasil: s|South,se|Southeast,co|Centerwest,ne|Northeast,n|North