factbook 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3375e7a8abcb8c6a1fea38aa05f5246cd7bdf22f
-  data.tar.gz: c2a3c6145dfc19bc71721e9114a33a22207287ec
+  metadata.gz: 9715102d9e477fecc63d0b77e0760c134c349edf
+  data.tar.gz: 26f7ec5f6f517013e96f477682d92b61bfcd3103
 SHA512:
-  metadata.gz: c8a3ad384249824f9e7a13b0c2e45839cc868b0f1bd2a9473257a3420b7a57430893c09573b54de74d4458bff1bded7b244f3c9f1d522df96d2fd5452c48a5e7
-  data.tar.gz: 357ccd90b6ecefc969309fd92a3b4e223beebd743bb27dcd13d1607496054c97d7b70995d737a4941288ce248289e02d15189b9e925cbd808801862b77dfcbbf
+  metadata.gz: 843926700c08da16bb1a7555ed321d187e08cc8403c2855e2c240668462b24d2127622f5cf8d980ca23804cca9a8ef982e910554fab90559d6c776ff97b42217
+  data.tar.gz: 31cf12c0d3e063b84f5be8794b1dcc9ad33ef6bc075bd478a10781c5408feef1766fc83ec6391603eee9eade7ea7d1e1d098ca27c63c90a7364866165d171118

data/Manifest.txt

@@ -2,7 +2,9 @@ HISTORY.md
 Manifest.txt
 README.md
 Rakefile
+data/categories.csv
 data/codes.csv
+data/codesxref.csv
 data/comparisons.csv
 lib/factbook.rb
 lib/factbook/builder.rb
@@ -17,6 +19,8 @@ lib/factbook/table.rb
 lib/factbook/utils.rb
 lib/factbook/utils_info.rb
 lib/factbook/version.rb
+script/testbr.rb
+script/testcodes.rb
 test/data/au.html
 test/data/au.yml
 test/data/be.html

data/README.md

@@ -22,80 +22,127 @@ 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)
 
 ```ruby
-
 page = Factbook::Page.new( 'br' )   # br is the country code for Brazil
 pp page.data                        # pretty print hash
-
 ```
 
-### Save to disk as JSON
+resulting in:
 
 ```ruby
-
-page = Factbook::Page.new( 'br' )
-File.open( 'br.json', 'w') do |f|
-  f.write page.to_json( pretty: true )
-end
-
+{"Introduction"=>
+  {"Background"=>
+    {"text"=>
+      "Following more than three centuries under Portuguese rule,
+       Brazil gained its independence in 1822, ..."}},
+ "Geography"=>
+  {"Location"=>{"text"=>"Eastern South America, bordering the Atlantic Ocean"},
+   "Geographic coordinates"=>{"text"=>"10 00 S, 55 00 W"},
+   "Map references"=>{"text"=>"South America"},
+   "Area"=>
+    {"total"=>{"text"=>"8,515,770 sq km"},
+     "land"=>{"text"=>"8,358,140 sq km"},
+     "water"=>{"text"=>"157,630 sq km"},
+     "note"=>
+      {"text"=>
+        "includes Arquipelago de Fernando de Noronha, Atol das Rocas, ..."}},
+   "Area - comparative"=>
+    {"text"=>"slightly smaller than the US"},
+   "Land boundaries"=>
+    {"total"=>{"text"=>"16,145 km"},
+     "border countries (10)"=>
+      {"text"=>
+        "Argentina 1,263 km, Bolivia 3,403 km, Colombia 1,790 km,
+        French Guiana 649 km, Guyana 1,308 km, Paraguay 1,371 km, Peru 2,659 km,
+        Suriname 515 km, Uruguay 1,050 km, Venezuela 2,137 km"}},
+   "Climate"=>{"text"=>"mostly tropical, but temperate in south"},
+   "Elevation extremes"=>
+    {"lowest point"=>{"text"=>"Atlantic Ocean 0 m"},
+     "highest point"=>{"text"=>"Pico da Neblina 2,994 m"}},
+   "Natural resources"=>
+    {"text"=>
+      "bauxite, gold, iron ore, manganese, nickel, phosphates, ..."},
+    ...
 ```
 
-### Options - Header, "Long" Category / Field Names
 
-#### Include Header Option - `header: true`
+### Save to disk as JSON
 
 ```ruby
-page = Factbook::Page.new( 'br', header: true )
+page = Factbook::Page.new( 'br' )
+File.open( 'br.json', 'w') do |f|
+  f.write page.to_json
+end
 ```
 
-will include a leading header section. Example:
-
-```json
-{
- "Header": {
-   "code": "au",
-   "generator": "factbook/0.1.2",
-   "last_built": "2014-08-24 12:55:39 +0200"
- }
- ...
-}
-```
 
-#### "Long" Category / Field Names Option - `fields: 'long'`
+### Print all codes
 
 ```ruby
-page = Factbook::Page.new( 'br', fields: 'long')
+Factbook.codes.each do |code|
+  pp code
+end
 ```
 
-will change the category / field names to the long form  (that is, passing through unchanged from the source).
-e.g.
+resulting in:
 
 ```ruby
-page['econ']['budget_surplus_or_deficit']['text']
-page['econ']['labor_force_by_occupation']['agriculture']
-page['trans']['ports_and_terminals']['river_ports']
+#<struct Factbook::Codes::Code
+ code="af",
+ name="Afghanistan",
+ category="Countries",
+ region="South Asia">
+#<struct Factbook::Codes::Code
+ code="al",
+ name="Albania",
+ category="Countries",
+ region="Europe">
+#<struct Factbook::Codes::Code
+ code="ag",
+ name="Algeria",
+ category="Countries",
+ region="Africa">
+#<struct Factbook::Codes::Code
+ code="an",
+ name="Andorra",
+ category="Countries",
+ region="Europe">
+...
 ```
-becomes
 
-```ruby
-page['Economy']['Budget surplus (+) or deficit (-)']['text']
-page['Economy']['Labor force - by occupation']['agriculture']
-page['Transportation']['Ports and terminals']['river port(s)']
-```
+Note: You can filter codes by category e.g. Countries, Dependencies, Miscellaneous, Oceans, etc.
+and/or by region e.g. Africa, Europe, South Asia, Central America and Caribbean, etc.
 
-Note: You can - of course - use the options together e.g.
 
 ```ruby
-page = Factbook::Page.new( 'br', header: true, fields: 'long' )
-```
 
-or
-
-```ruby
-opts = {
-  header: true,
-  fields: 'long'
-}
-page = Factbook::Page.new( 'br', opts )
+assert_equal 261, Factbook.codes.size 
+
+## categories
+assert_equal 195, Factbook.codes.countries.size
+assert_equal  52, Factbook.codes.dependencies.size
+assert_equal   5, Factbook.codes.oceans.size
+assert_equal   1, Factbook.codes.world.size
+assert_equal   2, Factbook.codes.others.size
+assert_equal   6, Factbook.codes.misc.size
+    
+## regions
+assert_equal  55, Factbook.codes.europe.size
+assert_equal   9, Factbook.codes.south_asia.size
+assert_equal   6, Factbook.codes.central_asia.size
+assert_equal  22, Factbook.codes.east_n_souteast_asia.size
+assert_equal  19, Factbook.codes.middle_east.size
+assert_equal  56, Factbook.codes.africa.size
+assert_equal   7, Factbook.codes.north_america.size
+assert_equal  33, Factbook.codes.central_america_n_caribbean.size
+assert_equal  14, Factbook.codes.south_america.size
+assert_equal  30, Factbook.codes.australia_oceania.size
+assert_equal   4, Factbook.codes.antartica.size
+assert_equal   5, Factbook.codes.region('Oceans').size
+assert_equal   1, Factbook.codes.region('World').size
+
+## categories + regions
+assert_equal  45, Factbook.codes.countries.europe.size
+...
 ```
 
 

data/data/categories.csv

@@ -0,0 +1,164 @@
+Num,Category,Name,Key
+,Introduction,Background,
+,Geography,Location,
+,Geography,Geographic coordinates,
+,Geography,Map references,
+,Geography,Area,
+,Geography,Area - comparative,
+,Geography,Land boundaries,
+,Geography,Coastline,
+,Geography,Maritime claims,
+,Geography,Climate,
+,Geography,Terrain,
+,Geography,Elevation extremes,
+,Geography,Natural resources,
+,Geography,Land use,
+,Geography,Irrigated land,
+,Geography,Total renewable water resources,
+,Geography,Freshwater withdrawal (domestic/industrial/agricultural),
+,Geography,Natural hazards,
+,Geography,Environment - current issues,
+,Geography,Environment - international agreements,
+,Geography,Geography - note,
+,People and Society,Nationality,
+,People and Society,Ethnic groups,
+,People and Society,Languages,
+,People and Society,Religions,
+,People and Society,Population,
+,People and Society,Age structure,
+,People and Society,Dependency ratios,
+,People and Society,Median age,
+,People and Society,Population growth rate,
+,People and Society,Birth rate,
+,People and Society,Death rate,
+,People and Society,Net migration rate,
+,People and Society,Urbanization,
+,People and Society,Major urban areas - population,
+,People and Society,Sex ratio,
+,People and Society,Infant mortality rate,
+,People and Society,Life expectancy at birth,
+,People and Society,Total fertility rate,
+,People and Society,Contraceptive prevalence rate,
+,People and Society,Health expenditures,
+,People and Society,Physicians density,
+,People and Society,Hospital bed density,
+,People and Society,Drinking water source,
+,People and Society,Sanitation facility access,
+,People and Society,HIV/AIDS - adult prevalence rate,
+,People and Society,HIV/AIDS - people living with HIV/AIDS,
+,People and Society,HIV/AIDS - deaths,
+,People and Society,Obesity - adult prevalence rate,
+,People and Society,Education expenditures,
+,People and Society,School life expectancy (primary to tertiary education),
+,People and Society,"Unemployment, youth ages 15-24",
+,Government,Country name,
+,Government,Government type,
+,Government,Capital,
+,Government,Administrative divisions,
+,Government,Independence,
+,Government,National holiday,
+,Government,Constitution,
+,Government,Legal system,
+,Government,International law organization participation,
+,Government,Suffrage,
+,Government,Executive branch,
+,Government,Legislative branch,
+,Government,Judicial branch,
+,Government,Political parties and leaders,
+,Government,Political pressure groups and leaders,
+,Government,International organization participation,
+,Government,Diplomatic representation in the US,
+,Government,Diplomatic representation from the US,
+,Government,Flag description,
+,Government,National symbol(s),
+,Government,National anthem,
+,Economy,Economy - overview,
+,Economy,GDP (purchasing power parity),
+,Economy,GDP (official exchange rate),
+,Economy,GDP - real growth rate,
+,Economy,GDP - per capita (PPP),
+,Economy,Gross national saving,
+,Economy,"GDP - composition, by end use",
+,Economy,"GDP - composition, by sector of origin",
+,Economy,Agriculture - products,
+,Economy,Industries,
+,Economy,Industrial production growth rate,
+,Economy,Labor force,
+,Economy,Labor force - by occupation,
+,Economy,Unemployment rate,
+,Economy,Population below poverty line,
+,Economy,Household income or consumption by percentage share,
+,Economy,Distribution of family income - Gini index,
+,Economy,Budget,
+,Economy,Taxes and other revenues,
+,Economy,Budget surplus (+) or deficit (-),
+,Economy,Public debt,
+,Economy,Fiscal year,
+,Economy,Inflation rate (consumer prices),
+,Economy,Commercial bank prime lending rate,
+,Economy,Stock of narrow money,
+,Economy,Stock of broad money,
+,Economy,Stock of domestic credit,
+,Economy,Market value of publicly traded shares,
+,Economy,Current account balance,
+,Economy,Exports,
+,Economy,Exports - commodities,
+,Economy,Exports - partners,
+,Economy,Imports,
+,Economy,Imports - commodities,
+,Economy,Imports - partners,
+,Economy,Reserves of foreign exchange and gold,
+,Economy,Debt - external,
+,Economy,Stock of direct foreign investment - at home,
+,Economy,Stock of direct foreign investment - abroad,
+,Economy,Exchange rates,
+,Energy,Electricity - production,
+,Energy,Electricity - consumption,
+,Energy,Electricity - exports,
+,Energy,Electricity - imports,
+,Energy,Electricity - installed generating capacity,
+,Energy,Electricity - from fossil fuels,
+,Energy,Electricity - from nuclear fuels,
+,Energy,Electricity - from hydroelectric plants,
+,Energy,Electricity - from other renewable sources,
+,Energy,Crude oil - production,
+,Energy,Crude oil - exports,
+,Energy,Crude oil - imports,
+,Energy,Crude oil - proved reserves,
+,Energy,Refined petroleum products - production,
+,Energy,Refined petroleum products - consumption,
+,Energy,Refined petroleum products - exports,
+,Energy,Refined petroleum products - imports,
+,Energy,Natural gas - production,
+,Energy,Natural gas - consumption,
+,Energy,Natural gas - exports,
+,Energy,Natural gas - imports,
+,Energy,Natural gas - proved reserves,
+,Energy,Carbon dioxide emissions from consumption of energy,
+,Communications,Telephones - fixed lines,
+,Communications,Telephones - mobile cellular,
+,Communications,Telephone system,
+,Communications,Broadcast media,
+,Communications,Radio broadcast stations,
+,Communications,Television broadcast stations,
+,Communications,Internet country code,
+,Communications,Internet users,
+,Transportation,Airports,
+,Transportation,Airports - with paved runways,
+,Transportation,Airports - with unpaved runways,
+,Transportation,Heliports,
+,Transportation,Pipelines,
+,Transportation,Railways,
+,Transportation,Roadways,
+,Transportation,Waterways,
+,Transportation,Merchant marine,
+,Transportation,Ports and terminals,
+,Military,Military branches,
+,Military,Military service age and obligation,
+,Military,Manpower available for military service,
+,Military,Manpower fit for military service,
+,Military,Manpower reaching militarily significant age annually,
+,Military,Military expenditures,
+,Transnational Issues,Disputes - international,
+,Transnational Issues,Refugees and internally displaced persons,
+,Transnational Issues,Illicit drugs,

data/data/codesxref.csv

@@ -0,0 +1,280 @@
+Name,GEC,A3,A2,NUM,STANAG,INTERNET
+Afghanistan,AF,AF,AFG,004,AFG,.af
+Akrotiri,AX,-,-,-,-,-
+Albania,AL,AL,ALB,008,ALB,.al
+Algeria,AG,DZ,DZA,012,DZA,.dz
+American Samoa,AQ,AS,ASM,016,ASM,.as
+Andorra,AN,AD,AND,020,AND,.ad
+Angola,AO,AO,AGO,024,AGO,.ao
+Anguilla,AV,AI,AIA,660,AIA,.ai
+Antarctica,AY,AQ,ATA,010,ATA,.aq
+Antigua and Barbuda,AC,AG,ATG,028,ATG,.ag
+Argentina,AR,AR,ARG,032,ARG,.ar
+Armenia,AM,AM,ARM,051,ARM,.am
+Aruba,AA,AW,ABW,533,ABW,.aw
+Ashmore and Cartier Islands,AT,-,-,-,AUS,-
+Australia,AS,AU,AUS,036,AUS,.au
+Austria,AU,AT,AUT,040,AUT,.at
+Azerbaijan,AJ,AZ,AZE,031,AZE,.az
+"Bahamas, The",BF,BS,BHS,044,BHS,.bs
+Bahrain,BA,BH,BHR,048,BHR,.bh
+Baker Island,FQ,-,-,-,UMI,-
+Bangladesh,BG,BD,BGD,050,BGD,.bd
+Barbados,BB,BB,BRB,052,BRB,.bb
+Bassas da India,BS,-,-,-,-,-
+Belarus,BO,BY,BLR,112,BLR,.by
+Belgium,BE,BE,BEL,056,BEL,.be
+Belize,BH,BZ,BLZ,084,BLZ,.bz
+Benin,BN,BJ,BEN,204,BEN,.bj
+Bermuda,BD,BM,BMU,060,BMU,.bm
+Bhutan,BT,BT,BTN,064,BTN,.bt
+Bolivia,BL,BO,BOL,068,BOL,.bo
+Bosnia and Herzegovina,BK,BA,BIH,070,BIH,.ba
+Botswana,BC,BW,BWA,072,BWA,.bw
+Bouvet Island,BV,BV,BVT,074,BVT,.bv
+Brazil,BR,BR,BRA,076,BRA,.br
+British Indian Ocean Territory,IO,IO,IOT,086,IOT,.io
+British Virgin Islands,VI,VG,VGB,092,VGB,.vg
+Brunei,BX,BN,BRN,096,BRN,.bn
+Bulgaria,BU,BG,BGR,100,BGR,.bg
+Burkina Faso,UV,BF,BFA,854,BFA,.bf
+Burma,BM,MM,MMR,104,MMR,.mm
+Burundi,BY,BI,BDI,108,BDI,.bi
+Cabo Verde,CV,CV,CPV,132,CPV,.cv
+Cambodia,CB,KH,KHM,116,KHM,.kh
+Cameroon,CM,CM,CMR,120,CMR,.cm
+Canada,CA,CA,CAN,124,CAN,.ca
+Cayman Islands,CJ,KY,CYM,136,CYM,.ky
+Central African Republic,CT,CF,CAF,140,CAF,.cf
+Chad,CD,TD,TCD,148,TCD,.td
+Chile,CI,CL,CHL,152,CHL,.cl
+China,CH,CN,CHN,156,CHN,.cn
+Christmas Island,KT,CX,CXR,162,CXR,.cx
+Clipperton Island,IP,-,-,-,FYP,-
+Cocos (Keeling) Islands,CK,CC,CCK,166,AUS,.cc
+Colombia,CO,CO,COL,170,COL,.co
+Comoros,CN,KM,COM,174,COM,.km
+"Congo, Democratic Republic of the",CG,CD,COD,180,COD,.cd
+"Congo, Republic of the",CF,CG,COG,178,COG,.cg
+Cook Islands,CW,CK,COK,184,COK,.ck
+Coral Sea Islands,CR,-,-,-,AUS,-
+Costa Rica,CS,CR,CRI,188,CRI,.cr
+Cote d'Ivoire,IV,CI,CIV,384,CIV,.ci
+Croatia,HR,HR,HRV,191,HRV,.hr
+Cuba,CU,CU,CUB,192,CUB,.cu
+Curacao,UC,CW,CUW,531,-,.cw
+Cyprus,CY,CY,CYP,196,CYP,.cy
+Czech Republic,EZ,CZ,CZE,203,CZE,.cz
+Denmark,DA,DK,DNK,208,DNK,.dk
+Dhekelia,DX,-,-,-,-,-
+Djibouti,DJ,DJ,DJI,262,DJI,.dj
+Dominica,DO,DM,DMA,212,DMA,.dm
+Dominican Republic,DR,DO,DOM,214,DOM,.do
+Ecuador,EC,EC,ECU,218,ECU,.ec
+Egypt,EG,EG,EGY,818,EGY,.eg
+El Salvador,ES,SV,SLV,222,SLV,.sv
+Equatorial Guinea,EK,GQ,GNQ,226,GNQ,.gq
+Eritrea,ER,ER,ERI,232,ERI,.er
+Estonia,EN,EE,EST,233,EST,.ee
+Ethiopia,ET,ET,ETH,231,ETH,.et
+Europa Island,EU,-,-,-,-,-
+Falkland Islands (Islas Malvinas),FK,FK,FLK,238,FLK,.fk
+Faroe Islands,FO,FO,FRO,234,FRO,.fo
+Fiji,FJ,FJ,FJI,242,FJI,.fj
+Finland,FI,FI,FIN,246,FIN,.fi
+France,FR,FR,FRA,250,FRA,.fr
+"France, Metropolitan",-,FX,FXX,249,-,.fx
+French Guiana,FG,GF,GUF,254,GUF,.gf
+French Polynesia,FP,PF,PYF,258,PYF,.pf
+French Southern and Antarctic Lands,FS,TF,ATF,260,ATF,.tf
+Gabon,GB,GA,GAB,266,GAB,.ga
+"Gambia, The",GA,GM,GMB,270,GMB,.gm
+Gaza Strip,GZ,PS,PSE,275,PSE,.ps
+Georgia,GG,GE,GEO,268,GEO,.ge
+Germany,GM,DE,DEU,276,DEU,.de
+Ghana,GH,GH,GHA,288,GHA,.gh
+Gibraltar,GI,GI,GIB,292,GIB,.gi
+Glorioso Islands,GO,-,-,-,-,-
+Greece,GR,GR,GRC,300,GRC,.gr
+Greenland,GL,GL,GRL,304,GRL,.gl
+Grenada,GJ,GD,GRD,308,GRD,.gd
+Guadeloupe,GP,GP,GLP,312,GLP,.gp
+Guam,GQ,GU,GUM,316,GUM,.gu
+Guatemala,GT,GT,GTM,320,GTM,.gt
+Guernsey,GK,GG,GGY,831,UK,.gg
+Guinea,GV,GN,GIN,324,GIN,.gn
+Guinea-Bissau,PU,GW,GNB,624,GNB,.gw
+Guyana,GY,GY,GUY,328,GUY,.gy
+Haiti,HA,HT,HTI,332,HTI,.ht
+Heard Island and McDonald Islands,HM,HM,HMD,334,HMD,.hm
+Holy See (Vatican City),VT,VA,VAT,336,VAT,.va
+Honduras,HO,HN,HND,340,HND,.hn
+Hong Kong,HK,HK,HKG,344,HKG,.hk
+Howland Island,HQ,-,-,-,UMI,-
+Hungary,HU,HU,HUN,348,HUN,.hu
+Iceland,IC,IS,ISL,352,ISL,.is
+India,IN,IN,IND,356,IND,.in
+Indonesia,ID,ID,IDN,360,IDN,.id
+Iran,IR,IR,IRN,364,IRN,.ir
+Iraq,IZ,IQ,IRQ,368,IRQ,.iq
+Ireland,EI,IE,IRL,372,IRL,.ie
+Isle of Man,IM,IM,IMN,833,UK,.im
+Israel,IS,IL,ISR,376,ISR,.il
+Italy,IT,IT,ITA,380,ITA,.it
+Jamaica,JM,JM,JAM,388,JAM,.jm
+Jan Mayen,JN,-,-,-,SJM,-
+Japan,JA,JP,JPN,392,JPN,.jp
+Jarvis Island,DQ,-,-,-,UMI,-
+Jersey,JE,JE,JEY,832,UK,.je
+Johnston Atoll,JQ,-,-,-,UMI,-
+Jordan,JO,JO,JOR,400,JOR,.jo
+Juan de Nova Island,JU,-,-,-,-,-
+Kazakhstan,KZ,KZ,KAZ,398,KAZ,.kz
+Kenya,KE,KE,KEN,404,KEN,.ke
+Kingman Reef,KQ,-,-,-,UMI,-
+Kiribati,KR,KI,KIR,296,KIR,.ki
+"Korea, North",KN,KP,PRK,408,PRK,.kp
+"Korea, South",KS,KR,KOR,410,KOR,.kr
+Kosovo,KV,XK,XKS,-,-,-
+Kuwait,KU,KW,KWT,414,KWT,.kw
+Kyrgyzstan,KG,KG,KGZ,417,KGZ,.kg
+Laos,LA,LA,LAO,418,LAO,.la
+Latvia,LG,LV,LVA,428,LVA,.lv
+Lebanon,LE,LB,LBN,422,LBN,.lb
+Lesotho,LT,LS,LSO,426,LSO,.ls
+Liberia,LI,LR,LBR,430,LBR,.lr
+Libya,LY,LY,LBY,434,LBY,.ly
+Liechtenstein,LS,LI,LIE,438,LIE,.li
+Lithuania,LH,LT,LTU,440,LTU,.lt
+Luxembourg,LU,LU,LUX,442,LUX,.lu
+Macau,MC,MO,MAC,446,MAC,.mo
+Macedonia,MK,MK,MKD,807,FYR,.mk
+Madagascar,MA,MG,MDG,450,MDG,.mg
+Malawi,MI,MW,MWI,454,MWI,.mw
+Malaysia,MY,MY,MYS,458,MYS,.my
+Maldives,MV,MV,MDV,462,MDV,.mv
+Mali,ML,ML,MLI,466,MLI,.ml
+Malta,MT,MT,MLT,470,MLT,.mt
+Marshall Islands,RM,MH,MHL,584,MHL,.mh
+Martinique,MB,MQ,MTQ,474,MTQ,.mq
+Mauritania,MR,MR,MRT,478,MRT,.mr
+Mauritius,MP,MU,MUS,480,MUS,.mu
+Mayotte,MF,YT,MYT,175,FRA,.yt
+Mexico,MX,MX,MEX,484,MEX,.mx
+"Micronesia, Federated States of",FM,FM,FSM,583,FSM,.fm
+Midway Islands,MQ,-,-,-,UMI,-
+Moldova,MD,MD,MDA,498,MDA,.md
+Monaco,MN,MC,MCO,492,MCO,.mc
+Mongolia,MG,MN,MNG,496,MNG,.mn
+Montenegro,MJ,ME,MNE,499,MNE,.me
+Montserrat,MH,MS,MSR,500,MSR,.ms
+Morocco,MO,MA,MAR,504,MAR,.ma
+Mozambique,MZ,MZ,MOZ,508,MOZ,.mz
+Myanmar,-,-,-,-,-,-
+Namibia,WA,NA,NAM,516,NAM,.na
+Nauru,NR,NR,NRU,520,NRU,.nr
+Navassa Island,BQ,-,-,-,UMI,-
+Nepal,NP,NP,NPL,524,NPL,.np
+Netherlands,NL,NL,NLD,528,NLD,.nl
+Netherlands Antilles,NT, , , ,ANT,.an
+New Caledonia,NC,NC,NCL,540,NCL,.nc
+New Zealand,NZ,NZ,NZL,554,NZL,.nz
+Nicaragua,NU,NI,NIC,558,NIC,.ni
+Niger,NG,NE,NER,562,NER,.ne
+Nigeria,NI,NG,NGA,566,NGA,.ng
+Niue,NE,NU,NIU,570,NIU,.nu
+Norfolk Island,NF,NF,NFK,574,NFK,.nf
+Northern Mariana Islands,CQ,MP,MNP,580,MNP,.mp
+Norway,NO,NO,NOR,578,NOR,.no
+Oman,MU,OM,OMN,512,OMN,.om
+Pakistan,PK,PK,PAK,586,PAK,.pk
+Palau,PS,PW,PLW,585,PLW,.pw
+Palmyra Atoll,LQ,-,-,-,UMI,-
+Panama,PM,PA,PAN,591,PAN,.pa
+Papua New Guinea,PP,PG,PNG,598,PNG,.pg
+Paracel Islands,PF,-,-,-,-,-
+Paraguay,PA,PY,PRY,600,PRY,.py
+Peru,PE,PE,PER,604,PER,.pe
+Philippines,RP,PH,PHL,608,PHL,.ph
+Pitcairn Islands,PC,PN,PCN,612,PCN,.pn
+Poland,PL,PL,POL,616,POL,.pl
+Portugal,PO,PT,PRT,620,PRT,.pt
+Puerto Rico,RQ,PR,PRI,630,PRI,.pr
+Qatar,QA,QA,QAT,634,QAT,.qa
+Reunion,RE,RE,REU,638,REU,.re
+Romania,RO,RO,ROU,642,ROU,.ro
+Russia,RS,RU,RUS,643,RUS,.ru
+Rwanda,RW,RW,RWA,646,RWA,.rw
+Saint Barthelemy,TB,BL,BLM,652,-,.bl
+"Saint Helena, Ascension, and Tristan da Cunha",SH,SH,SHN,654,SHN,.sh
+Saint Kitts and Nevis,SC,KN,KNA,659,KNA,.kn
+Saint Lucia,ST,LC,LCA,662,LCA,.lc
+Saint Martin,RN,MF,MAF,663,-,.mf
+Saint Pierre and Miquelon,SB,PM,SPM,666,SPM,.pm
+Saint Vincent and the Grenadines,VC,VC,VCT,670,VCT,.vc
+Samoa,WS,WS,WSM,882,WSM,.ws
+San Marino,SM,SM,SMR,674,SMR,.sm
+Sao Tome and Principe,TP,ST,STP,678,STP,.st
+Saudi Arabia,SA,SA,SAU,682,SAU,.sa
+Senegal,SG,SN,SEN,686,SEN,.sn
+Serbia,RI,RS,SRB,688,-,.rs
+Seychelles,SE,SC,SYC,690,SYC,.sc
+Sierra Leone,SL,SL,SLE,694,SLE,.sl
+Singapore,SN,SG,SGP,702,SGP,.sg
+Sint Maarten,NN,SX,SXM,534,-,.sx
+Slovakia,LO,SK,SVK,703,SVK,.sk
+Slovenia,SI,SI,SVN,705,SVN,.si
+Solomon Islands,BP,SB,SLB,090,SLB,.sb
+Somalia,SO,SO,SOM,706,SOM,.so
+South Africa,SF,ZA,ZAF,710,ZAF,.za
+South Georgia and the Islands,SX,GS,SGS,239,SGS,.gs
+South Sudan,OD,SS,SSD,728,-,-
+Spain,SP,ES,ESP,724,ESP,.es
+Spratly Islands,PG,-,-,-,-,-
+Sri Lanka,CE,LK,LKA,144,LKA,.lk
+Sudan,SU,SD,SDN,729,SDN,.sd
+Suriname,NS,SR,SUR,740,SUR,.sr
+Svalbard,SV,SJ,SJM,744,SJM,.sj
+Swaziland,WZ,SZ,SWZ,748,SWZ,.sz
+Sweden,SW,SE,SWE,752,SWE,.se
+Switzerland,SZ,CH,CHE,756,CHE,.ch
+Syria,SY,SY,SYR,760,SYR,.sy
+Taiwan,TW,TW,TWN,158,TWN,.tw
+Tajikistan,TI,TJ,TJK,762,TJK,.tj
+Tanzania,TZ,TZ,TZA,834,TZA,.tz
+Thailand,TH,TH,THA,764,THA,.th
+Timor-Leste,TT,TL,TLS,626,TLS,.tl
+Togo,TO,TG,TGO,768,TGO,.tg
+Tokelau,TL,TK,TKL,772,TKL,.tk
+Tonga,TN,TO,TON,776,TON,.to
+Trinidad and Tobago,TD,TT,TTO,780,TTO,.tt
+Tromelin Island,TE,-,-,-,-,-
+Tunisia,TS,TN,TUN,788,TUN,.tn
+Turkey,TU,TR,TUR,792,TUR,.tr
+Turkmenistan,TX,TM,TKM,795,TKM,.tm
+Turks and Caicos Islands,TK,TC,TCA,796,TCA,.tc
+Tuvalu,TV,TV,TUV,798,TUV,.tv
+Uganda,UG,UG,UGA,800,UGA,.ug
+Ukraine,UP,UA,UKR,804,UKR,.ua
+United Arab Emirates,AE,AE,ARE,784,ARE,.ae
+United Kingdom,UK,GB,GBR,826,GBR,.uk
+United States,US,US,USA,840,USA,.us
+United States Minor Outlying Islands,-,UM,UMI,581,-,.um
+Uruguay,UY,UY,URY,858,URY,.uy
+Uzbekistan,UZ,UZ,UZB,860,UZB,.uz
+Vanuatu,NH,VU,VUT,548,VUT,.vu
+Venezuela,VE,VE,VEN,862,VEN,.ve
+Vietnam,VM,VN,VNM,704,VNM,.vn
+Virgin Islands,VQ,VI,VIR,850,VIR,.vi
+Virgin Islands (UK),-,-,-,-,-,.vg
+Virgin Islands (US),-,-,-,-,-,.vi
+Wake Island,WQ,-,-,-,UMI,-
+Wallis and Futuna,WF,WF,WLF,876,WLF,.wf
+West Bank,WE,PS,PSE,275,PSE,.ps
+Western Sahara,WI,EH,ESH,732,ESH,.eh
+Western Samoa,-,-,-,-,-,.ws
+World,-,-,-,-,-,-
+Yemen,YM,YE,YEM,887,YEM,.ye
+Zaire,-,-,-,-,-,-
+Zambia,ZA,ZM,ZMB,894,ZMB,.zm
+Zimbabwe,ZI,ZW,ZWE,716,ZWE,.zw

data/lib/factbook/builder.rb

@@ -18,6 +18,10 @@ end
 
 def self.from_file( path )
   html_ascii = File.read( path )    ## fix/todo: use ASCII8BIT/binary reader !!!!!
+  self.from_string( html_ascii )
+end
+
+def self.from_string( html_ascii )   ## note: expects ASCII-7BIT/BINARY encoding
   self.new( html_ascii )
 end
 
@@ -27,7 +31,8 @@ attr_reader :html_ascii,     ## full "original" 1:1 page in "original/ascii8/bin
             :html_debug,     ## html w/ mapping markers - rename to html_markers - why? why not?
             :page_info,      ## incl. country_name, region_name, last_updated etc.
             :errors,          ## encoding erros etc.
-            :page
+            :sects
+
 
 def initialize( html_ascii )
   @html_ascii = html_ascii
@@ -42,8 +47,7 @@ def initialize( html_ascii )
   pp html_sects
 
 
-  page = Page.new
-  sects = []
+  @sects = []
   html_sects.each do |html_sect|
     html_sect_head = html_sect[0]
     html_subsects  = html_sect[1]
@@ -81,15 +85,11 @@ def initialize( html_ascii )
         end
       end
       sect.subsects = subsects
-      sects << sect
+      @sects << sect
     else
       ## warn/fix:  no section title found
     end   
   end
-  page.sects = sects
-  @page = page
-
-  pp page
   
   self  ## return self -- needed?? default (standard) anyway?? check and remove
 end

data/lib/factbook/page.rb

@@ -28,12 +28,47 @@ module Factbook
 class Page
   include LogUtils::Logging
 
-  attr_accessor :sects
-  
-  def initialize
-    @sects = []
+  attr_reader :sects    ## "structured" access e.g. sects/subsects/etc.
+  attr_reader :data     ## "plain" access with vanilla hash
+
+
+  ## standard version  (note: requires https)
+  SITE_BASE = 'https://www.cia.gov/library/publications/the-world-factbook/geos/{code}.html'
+
+  def initialize( code, opts={} )
+    ### keep code - why? why not??  (use page_info/info e.g. info.country_code??)
+    
+    if opts[:html]    ## note: expects ASCII-7BIT/BINARY encoding
+       ## for debugging and testing allow "custom" passed-in html page
+      html = opts[:html]
+    else
+      url_string =  SITE_BASE.gsub( '{code}', code )
+      ## note: expects ASCII-7BIT/BINARY encoding
+      html = fetch_page( url_string )   ## use PageFetcher class - why?? why not??
+    end
+    
+    b = Builder.from_string( html )
+    @sects = b.sects
+
+    @data = {}    
+    @sects.each do |sect|
+      @data[ sect.title ] = sect.data
+    end
+
+    self  ## return self (check - not needed??)
   end
 
+
+  def to_json( opts={} )  ## convenience helper for data.to_json; note: pretty print by default!
+    if opts[:minify]
+      data.to_json
+    else
+      ## was: -- opts[:pretty] || opts[:pp] 
+      JSON.pretty_generate( data )   ## note: pretty print by default!
+    end
+  end
+
+
   def [](key)  ### convenience shortcut
     # lets you use
     #   page['geo']
@@ -45,20 +80,30 @@ class Page
     data[key]
   end
 
-
-  def data
-    ## note: cache data hash on first build for now
-    if @data.nil?
-      ## convert sects to hash
-      @data = {}
-    
-      sects.each_with_index do |sect,i|
-        @data[ sect.title ] = sect.data
-      end
+private
+  def fetch_page( url_string )
+
+    worker = Fetcher::Worker.new
+    response = worker.get_response( url_string )
+
+    if response.code == '200'
+      t = response.body
+      ###
+      # NB: Net::HTTP will NOT set encoding UTF-8 etc.
+      # will mostly be ASCII
+       # - try to change encoding to UTF-8 ourselves
+      logger.debug "t.encoding.name (before): #{t.encoding.name}"
+      #####
+      # NB: ASCII-8BIT == BINARY == Encoding Unknown; Raw Bytes Here
+      t
+    else
+      logger.error "fetch HTTP - #{response.code} #{response.message}"
+      ## todo/fix: raise http exception (see fetcher)  -- why? why not??
+      fail "fetch HTTP - #{response.code} #{response.message}"
+      nil
     end
-    @data
   end
-    
+
 
 =begin
 def self.from_url( cc, cn )

data/lib/factbook/version.rb

@@ -4,7 +4,7 @@ module Factbook
 
   MAJOR = 1
   MINOR = 0
-  PATCH = 0
+  PATCH = 1
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/script/testbr.rb

@@ -0,0 +1,10 @@
+# encoding: utf-8
+#
+#  use to run/test:
+#   ruby -I ./lib script/testbr.rb
+
+require 'factbook'
+
+page = Factbook::Page.new( 'br' )   # br is the country code for Brazil
+pp page.data                        # pretty print hash
+

data/script/testcodes.rb

@@ -0,0 +1,11 @@
+# encoding: utf-8
+#
+#  use to run/test:
+#   ruby -I ./lib script/testcodes.rb
+
+require 'factbook'
+
+Factbook.codes.each do |code|
+  pp code
+end
+

data/test/test_builder.rb

@@ -16,15 +16,13 @@ class TestBuilder < MiniTest::Test
 
   def test_build
     
-    ['au','be'].each do |cc|
+    ['au','be'].each do |code|
        ## use/fix: ASCII-8BIT (e.g.keep as is) -???
        ## fix/todo: use ASCII8BIT/binary reader ??
-      b = Factbook::Builder.from_file( "#{Factbook.root}/test/data/src/#{cc}.html" )
+      b = Factbook::Builder.from_file( "#{Factbook.root}/test/data/src/#{code}.html" )
+      pp b.sects
 
-      pp b.page
-      pp b.page.data
-
-      File.open( "./tmp/#{cc}.debug.html", 'w' ) do |f|
+      File.open( "./tmp/#{code}.debug.html", 'w' ) do |f|
         f.write b.html_debug
       end
     end

data/test/test_fields.rb

@@ -10,8 +10,9 @@ require 'helper'
 class TestFields < MiniTest::Test
 
   def read_test_page( code )
-    b = Factbook::Builder.from_file( "#{Factbook.root}/test/data/src/#{code}.html" )
-    b.page    
+    html = File.read( "#{Factbook.root}/test/data/src/#{code}.html" )
+    page = Factbook::Page.new( code, html: html )
+    page    
   end
 
   def test_fields_full

data/test/test_json.rb

@@ -26,9 +26,8 @@ class TestJson < MiniTest::Test
 
      codes.each do |code|
        
-       b = Factbook::Builder.from_file( "#{Factbook.root}/test/data/src/#{code}.html" )
-
-       page = b.page    
+       html = File.read( "#{Factbook.root}/test/data/src/#{code}.html" ) 
+       page = Factbook::Page.new( code, html: html )    
        
        h = page.data
        pp h
@@ -36,9 +35,10 @@ class TestJson < MiniTest::Test
        ### save to json
        puts "saving a copy to #{code}.json for debugging"
        File.open( "tmp/#{code}.json", 'w' ) do |f|
-        f.write JSON.pretty_generate( h )
+         f.write JSON.pretty_generate( h )
+         ## f.write page.to_json
       end
      end
   end
 
-end # class TestOldJson
+end # class TestJson

data/test/test_page.rb

@@ -27,15 +27,9 @@ class TestPage < MiniTest::Test
         code       = rec[0]
         sects_size = rec[1]
 
-        b = Factbook::Builder.from_file( "#{Factbook.root}/test/data/src/#{code}.html" )
-        page = b.page
+        html = File.read( "#{Factbook.root}/test/data/src/#{code}.html" )
+        page = Factbook::Page.new( code, html: html )
        
-        ##  page = Factbook::OldPage.new( code )    
-        ## page.html = File.read( "#{Factbook.root}/test/data/old/countrytemplate_#{code}.html" )
-
-        ## print first 600 chars
-        ## pp page.html[0..600]
-
         assert_equal sects_size, page.sects.size
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: factbook
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-26 00:00:00.000000000 Z
+date: 2015-10-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logutils
@@ -94,7 +94,9 @@ files:
 - Manifest.txt
 - README.md
 - Rakefile
+- data/categories.csv
 - data/codes.csv
+- data/codesxref.csv
 - data/comparisons.csv
 - lib/factbook.rb
 - lib/factbook/builder.rb
@@ -109,6 +111,8 @@ files:
 - lib/factbook/utils.rb
 - lib/factbook/utils_info.rb
 - lib/factbook/version.rb
+- script/testbr.rb
+- script/testcodes.rb
 - test/data/au.html
 - test/data/au.yml
 - test/data/be.html