factbook 1.1.1 → 2.0.1

data/lib/factbook/sect.rb

@@ -1,29 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-
-class Sect
-  include LogUtils::Logging
-
-  attr_accessor :title        ## use name instead of title - why? why not? 
-  attr_accessor :subsects
-  
-  def initialize
-    @subsects = []
-  end
-
-  def data
-    ## convert sects to hash
-    @data = {}
-    
-    subsects.each_with_index do |subsect,i|
-      @data[ subsect.title ] = subsect.data
-    end
-    @data
-  end
-
-
-end # class Sect
-
-end # module Factbook

data/lib/factbook/subsect.rb

@@ -1,18 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-
-class Subsect
-  include LogUtils::Logging
-
-  attr_accessor :title        ## use name instead of title - why? why not?
-  attr_accessor :data         ## hash holding data e.g. { 'text' => '...' etc. }
-
-  def initialize
-    @data = {}
-  end
-
-end # class Subsect
-
-end # module Factbook

data/lib/factbook/table.rb

@@ -1,52 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-##
-## make more "generic"  - why? why not?
-##   (re)use for other files ?? move to textutils ??
-
-##
-##  for now reads in rows with values separated by at least 3+ spaces e.g.:
-##   see www.cia.gov/library/publications/the-world-factbook/rankorder/rawdata_2119.txt
-## 1      China                      1,367,485,388                                     
-## 2      India                      1,251,695,584                                     
-## 3      European Union             513,949,445                                       
-## 4      United States              321,368,864                                       
-## 5      Indonesia                  255,993,674                                       
-## 6      Brazil                     204,259,812     
-
-
-class TableReader
-  include LogUtils::Logging
-
-
-def initialize( text )
-  @text = text
-end
-
-def read
-  recs = []
-
-  line_no = 0
-  @text.each_line do |line|
-    line_no +=1
-    line = line.strip   ## remove leading and trailing whitespace
-    if line.empty?
-      puts "** skipping empty line #{line_no}"
-      next
-    end
-
-    values = line.split( /[ ]{3,}/ )    ## split three or more spaces - use just two ?? why? why not??
-    
-    ## puts line
-    ## pp values
-    recs << values
-  end
-  recs
-end
-
-
-end # class TableReader
-
-end # module Factbook

data/lib/factbook/utils.rb

@@ -1,85 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-  module Utils
-
-########################################
-## todo: move to textutils - why, why not ?????
-
-def encode_utf8( text )
-
-  errors = []   ## also return list of encoding errors
-
-  ## note: factbook claims utf-8  - but includes invalid bytes in some pages
-  ##   encoding is likley wester/windows-
-
-  ## note:
-  ##   use �    - unknown/invalid unicode char
-  ##  fix/todo: use ASCII-8BIT instead of binnary
-  text = text.encode('UTF-8', 'binary', :invalid => :replace,
-                                        :undef   => :replace,
-                                        :replace => '�' )
-
-  ## check for replaced/invalid chars and log warrning
-  pos = text.index( '�' )
-  while pos
-    from = pos-10   ## tood/fix: use min/max to check for bounds - why? why not??
-    to   = pos+10
-    around = text[from..to]
-    puts "  pos #{pos}, from #{from}, to #{to}, around >#{around}<"
-    msg  = "invalid char on pos #{pos} around: >#{around}<"
-    puts msg
-    ## also log message / w timestamp
- 
-    errors << "#{Time.now} - #{msg}" 
-
-    pos = text.index( '�', pos+1 )
-  end
-
-  [text,errors]   ## return text and errors (list)
-end
-
-
-
-def values_to_csv( values )
-  buf = ""
-  values.each_with_index do |value,i|
-     buf << ','  if i > 0    ## add comma (except for first value)
-     ## note: allow optional $ sign e.g. $100,000,000
-     ##  !!!! todo/fix: allow optional minus e.g. -44,000
-     if value =~ /^\$?[1-9][,0-9]+[0-9]$/    ### find a better regex - why? why not??
-       ## check if number e.g. 17,098,242  or $17,098,242
-       ##   remove commas  17098242
-       buf << value.gsub( ',', '' )
-     elsif value.index( ',').nil?
-       ## add as is 1:1 (no commana)
-       buf << value
-     else
-       ## escape comma with double quote
-       #   e.g. Guam, The becomes "Guam, The"
-       buf << '"'
-       buf << value
-       buf << '"'
-     end
-  end
-  buf
-end
-
-
-def data_to_csv( recs, headers )
-  text = ""
-  
-  text << values_to_csv( headers )
-  text << "\n"
-  
-  recs.each do |rec|
-    text << values_to_csv( rec )
-    text << "\n"
-  end
-  
-  text
-end
-
-
-  end   # module Utils
-end     # module Factbook

data/lib/factbook/utils_info.rb

@@ -1,102 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-  module Utils
-
-#######
-## find meta data (about page info)
-
-
-#### e.g. Page last updated on September 16, 2015
-
-MONTH_EN_TO_S={
-  'January'   => '1',
-  'February'  => '2',
-  'March'     => '3',
-  'April'     => '4',
-  'May'       => '5',
-  'June'      => '6',
-  'July'      => '7',
-  'August'    => '8',
-  'September' => '9',
-  'October'   => '10',
-  'November'  => '11',
-  'December'  => '12'
-}
-
-PAGE_LAST_UPDATED_REGEX = /
-                           Page \s last \s updated \s on \s
-                            (?<month_en>[a-z]+) \s
-                            (?<day>\d{1,2}), \s
-                            (?<year>\d{4})
-                          /imx
-
-def find_page_last_updated( html )
-  m = PAGE_LAST_UPDATED_REGEX.match( html )
-  if m
-    pp m
-    month_en = m[:month_en]
-    day      = m[:day]
-    year     = m[:year]
-    puts "** bingo - month #{month_en}, day #{day}, year #{year}"
-    
-    month = MONTH_EN_TO_S[ month_en ]
-    date_str = "#{year}-#{month}-#{day}"
-    pp date_str
-    date = Date.strptime( date_str, '%Y-%m-%d' )
-    date
-  else
-    nil
-  end
-end
-
-##
-## e.g. regioncode="eur" 
-##      countrycode="au"  
-##      countryname="Austria" 
-##      flagsubfield="" 
-##      countryaffiliation=""
-##      flagdescription="" 
-##      flagdescriptionnote="" 
-##      region="Europe" 
-##
-##   note: countryaffiliation may be empty
-
-
-
-PAGE_INFO_REGEX = /
-             regioncode=(?<q1>"|')(?<region_code>.+?)\k<q1>
-               \s+
-             countrycode=(?<q2>"|')(?<country_code>.+?)\k<q2>       ## is k<3> backref
-               \s+  
-              countryname=(?<q3>"|')(?<country>.+?)\k<q3>
-               \s+
-                [^>]+?  ## allow any attribs (note: non-greedy)
-              countryaffiliation=(?<q4>"|')(?<affiliation>.*?)\k<q4>     ## note: might be empty
-               \s+
-                [^>]+?  ## allow any attribs (note: non-greedy)
-              region=(?<q5>"|')(?<region>.+?)\k<q5>    ## check world - might be empty ?? or for ocean ??
-           /imx
-
-
-def find_page_info( html )
-  m = PAGE_INFO_REGEX.match( html )
-  if m
-    pp m
-
-    h = { country_code:        m[:country_code],
-          country_name:        m[:country],
-          country_affiliation: m[:affiliation],
-          region_code:         m[:region_code],
-          region_name:         m[:region] }
-    
-    puts "** bingo - #{h.inspect}"
-    h    ## return hash w/ name-value pairs
-  else
-    nil   ## or return empty struct with nils/empty strings - why?? why not??
-  end
-end
-
-
-  end   # module Utils
-end     # module Factbook

data/lib/factbook/version.rb

@@ -1,22 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-  MAJOR = 1
-  MINOR = 1
-  PATCH = 1
-  VERSION = [MAJOR,MINOR,PATCH].join('.')
-
-  def self.version
-    VERSION
-  end
-
-  def self.banner
-    "factbook/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
-  end
-
-  def self.root
-    "#{File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )}"
-  end
-  
-end

data/script/almanac.rb

@@ -1,48 +0,0 @@
-# encoding: utf-8
-#
-#  use to run:
-#   ruby -I ./lib script/almanac.rb
-
-
-require 'factbook'
-
-
-TEMPLATE = <<EOS
-
-### <%= names %>
-
-<%= page.name_long=='none' ? '\-' : page.name_long %> › <%= page.map %> -- <%= page.location %> <br>
-<%= page.capital %> • <%= page.area %> • pop. <%= page.population %> 
-
-**Languages:** <%= page.languages %>
-**Major cities:** <%= page.major_cities %>
-**Ethnic groups:** <%= page.ethnic_groups %>
-**Religions:** <%= page.religions %>
-**Independence:** <%= page.independence %>
-
-**Internet:** `<%= page.internet %>` • <%= page.internet_users %> • <%= page.internet_users_rate %>
-**Telephones - mobile:** <%= page.telephones_mobile %> • <%= page.telephones_mobile_subscriptions %> subs./100
-
-EOS
-
-
-#########################
-### read all countries
-###   using local json (dump) files
-
-##  see github.com/factbook/factbook.json   (use git clone)
-json_dir = '../../factbook/factbook.json'
-codes    = Factbook.codes.countries
-## todo: add tawain and ?? from others - why, why not??
-
-pages   = Factbook::JsonPageReader.new( json_dir ).read_pages( codes )
-
-almanac = Factbook::Almanac.new( pages )
-
-## save to disk
-
-File.open( './tmp/ALMANAC.md', 'w' ) do |f|
-  f.write almanac.render( TEMPLATE )
-end
-
-puts "Done."

data/script/attributes.rb

@@ -1,34 +0,0 @@
-# encoding: utf-8
-#
-#  use to run:
-#   ruby -I ./lib script/attributes.rb
-
-
-#  e.g. prints attribute accessor shortcuts
-#
-#  ### Geography
-#
-#  - `location`  =>  Location
-#  - `coords`  =>  Geographic coordinates
-#  - `map`  =>  Map references
-#  ...
-
-require 'factbook'
-
-
-attribs= Factbook.attributes.to_a
-
-h = attribs.group_by { |a| a.category }
-
-pp h
-
-h.each do |k,v|
-  puts ""
-  puts "### #{k}"
-  puts ""
-  
-  v.each do |a|
-    puts "- `#{a.name}`  =>  #{a.path.join(' › ')}"
-  end
-end
-

data/script/build.rb

@@ -1,28 +0,0 @@
-# encoding: utf-8
-#
-#  use to run/test:
-#   ruby -I ./lib script/build.rb
-
-require 'factbook'
-
-DB_CONFIG = {
-  adapter:  'sqlite3',
-  database: './factbook.db'
-}
-
-ActiveRecord::Base.logger = Logger.new( STDOUT )
-ActiveRecord::Base.establish_connection( DB_CONFIG )
-
-Factbook::CreateDb.new.up    ## create tables
-
-importer = Factbook::Importer.new
-
-Factbook.codes.each do |code|
-  puts "Fetching #{code.code}- #{code.name}..."
-  page = Factbook::Page.new( code.code )
-
-  puts "Adding #{code.code}- #{code.name}..."
-  importer.import( page )
-end
-
-puts "Done."

data/script/counter.rb

@@ -1,145 +0,0 @@
-# encoding: utf-8
-#
-#  use to run:
-#   ruby -I ./lib script/counter.rb
-
-require 'factbook'
-
-
-c = Factbook::Counter.new
-
-##  see github.com/factbook/factbook.json   (use git clone)
-json_dir = '../../factbook/factbook.json'
-codes    = Factbook.codes
-
-pages   = Factbook::JsonPageReader.new( json_dir ).read_pages( codes )
- 
-pages.each do |page|
-  c.count( page )
-end
-
-h = c.data
-pp h
-    
-### save to json
-puts "saving a copy to categories.json for debugging"
-File.open( "tmp/categories.json", 'w' ) do |f|
-  f.write JSON.pretty_generate( h )
-end
-
-
-
-SKIP_CATEGORIES_LINES=<<EOS
-
-######
-### france plus 5 overseas regions/departments
-
-##  metropolitan France
-## metropolitan France - total
-overseas departments
-French Guiana
-French Guiana - total
-Guadeloupe
-Guadeloupe and Martinique
-Martinique
-Mayotte
-Reunion
-
-
-###############
-### more
-
-Iles Eparses
-Ile Amsterdam
-Ile Amsterdam (Ile Amsterdam et Ile Saint-Paul)
-Ile Amsterdam et Ile Saint-Paul
-Ile Saint Paul
-Ile Saint-Paul (Ile Amsterdam et Ile Saint-Paul)
-Iles Crozet
-Iles Kerguelen
-Adelie Land
-Bassas da India
-Bassas da India (Iles Eparses)
-Bassas da India, Europa Island, Glorioso Islands, Juan de Nova Island (Iles Eparses)
-Europa Island
-Europa Island (Iles Eparses)
-Europa Island, Glorioso Islands, Juan de Nova Island
-Europa Island and Juan de Nova Island (Iles Eparses)
-Europa Island, Glorioso Islands, Juan de Nova Island (Iles Eparses)
-Glorioso Islands
-Glorioso Islands (Iles Eparses)
-Glorioso Island (Iles Eparses)
-Juan de Nova Island
-Juan de Nova Island (Iles Eparses)
-Tromelin Island
-Tromelin Island (Iles Eparses)
-Saint Helena
-Ascension Island
-Ascension
-Tristan da Cunha
-Tristan da Cunha island group
-Baker Island
-Baker, Howland, and Jarvis Islands
-Baker, Howland, and Jarvis Islands, and Johnston Atoll
-Baker, Howland, and Jarvis Islands, and Kingman Reef
-Howland Island
-Jarvis Island
-Johnston Atoll
-Johnston Atoll and Kingman Reef
-Kingman Reef
-Midway Islands
-Midway Islands, Johnston, and Palmyra Atolls
-Midway Islands and Palmyra Atoll
-Palmyra Atoll
-note on Palmyra Atoll
-EOS
-
-##   allow empty lines and skip comments
-SKIP_CATEGORIES = SKIP_CATEGORIES_LINES.split("\n").select { |item| !(item =~ /^\s*$/ || item =~ /^\s*#/) }
-    
-
-def print_categories( data )
-  data.each do |k,v|
-  
-    puts ""
-    puts "## #{k} _(#{v[:count]})_"
-    puts ""
-
-    walk_categories( v, 1 )
-  end
-end
-
-def walk_categories( data, level )
-  data.each do |k,v|
-    next if k == :count || k == :codes   ## skip "virtual" count entry (added for stats)
-  
-    ## skip (sub)country entries e.g. Baker Island, Ile Amsterdam, etc.
-    next if  SKIP_CATEGORIES.include?( k )
-  
-    print "     " * (level-1)   if level > 1    ## add 4 spaces indents per extra level
-    print "- "
-
-    print "**"                  if level == 1    ## mark as bold 
-    print k
-    print "**"                  if level == 1
-
-    print " _("
-    print v[:count]
-    if v[:codes]     ##  add codes if present
-      print " - "
-      print v[:codes]
-    end   
-    print ")_"
-
-    print "\n"
- 
-    walk_categories( v, level+1)
-  end
-end
-
-
-
-print_categories( c.data )
-
-puts "Done."
-