factbook 1.1.1 → 2.0.1

data/data/comparisons.csv

@@ -1,75 +0,0 @@
-Num,Category,Name
-2147,Geography,Area
-2119,People and Society,Population
-2002,People and Society,Population growth rate
-2054,People and Society,Birth rate
-2066,People and Society,Death rate
-2112,People and Society,Net migration rate
-2223,People and Society,Maternal mortality rate
-2091,People and Society,Infant mortality rate
-2102,People and Society,Life expectancy at birth
-2127,People and Society,Total fertility rate
-2225,People and Society,Health expenditures
-2155,People and Society,HIV/AIDS - adult prevalence rate
-2156,People and Society,HIV/AIDS - people living with HIV/AIDS
-2157,People and Society,HIV/AIDS - deaths
-2228,People and Society,Obesity - adult prevalence rate
-2224,People and Society,Children under the age of 5 years underweight
-2206,People and Society,Education expenditures
-2229,People and Society,"Unemployment, youth ages 15-24"
-2001,Economy,GDP (purchasing power parity)
-2003,Economy,GDP - real growth rate
-2004,Economy,GDP - per capita (PPP)
-2260,Economy,Gross national saving
-2089,Economy,Industrial production growth rate
-2095,Economy,Labor force
-2129,Economy,Unemployment rate
-2172,Economy,Distribution of family income - Gini index
-2221,Economy,Taxes and other revenues
-2222,Economy,Budget surplus (+) or deficit (-)
-2186,Economy,Public debt
-2092,Economy,Inflation rate (consumer prices)
-2207,Economy,Central bank discount rate
-2208,Economy,Commercial bank prime lending rate
-2214,Economy,Stock of narrow money
-2215,Economy,Stock of broad money
-2211,Economy,Stock of domestic credit
-2200,Economy,Market value of publicly traded shares
-2187,Economy,Current account balance
-2078,Economy,Exports
-2087,Economy,Imports
-2188,Economy,Reserves of foreign exchange and gold
-2079,Economy,Debt - external
-2198,Economy,Stock of direct foreign investment - at home
-2199,Economy,Stock of direct foreign investment - abroad
-2232,Energy,Electricity - production
-2233,Energy,Electricity - consumption
-2234,Energy,Electricity - exports
-2235,Energy,Electricity - imports
-2236,Energy,Electricity - installed generating capacity
-2237,Energy,Electricity - from fossil fuels
-2239,Energy,Electricity - from nuclear fuels
-2238,Energy,Electricity - from hydroelectric plants
-2240,Energy,Electricity - from other renewable sources
-2241,Energy,Crude oil - production
-2242,Energy,Crude oil - exports
-2243,Energy,Crude oil - imports
-2244,Energy,Crude oil - proved reserves
-2245,Energy,Refined petroleum products - production
-2246,Energy,Refined petroleum products - consumption
-2247,Energy,Refined petroleum products - exports
-2248,Energy,Refined petroleum products - imports
-2249,Energy,Natural gas - production
-2250,Energy,Natural gas - consumption
-2251,Energy,Natural gas - exports
-2252,Energy,Natural gas - imports
-2253,Energy,Natural gas - proved reserves
-2150,Communications,Telephones - fixed lines
-2151,Communications,Telephones - mobile cellular
-2153,Communications,Internet users
-2053,Transportation,Airports
-2121,Transportation,Railways
-2085,Transportation,Roadways
-2093,Transportation,Waterways
-2108,Transportation,Merchant marine
-2034,Military,Military expenditures

data/lib/factbook/almanac.rb

@@ -1,72 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-
-class Almanac
-
-  ## convenience helper ("factory") 
-  def self.from_json( codes, json_dir: '.' )
-    pages = JsonPageReader.new( json_dir ).read_pages( codes )
-    self.new( pages )
-  end
-
-
-  def initialize( pages )
-    @pages = pages
-  end
-
-  def render( template )
-    buf = ''
-    @pages.each do |page|
-      text = PageCtx.new( page, template ).render
-
-      puts text     ## for debugging write country profile to console (too)
-      buf << text
-    end
-    puts "count: #{@pages.count}"
-    buf   ## return buffered almanac text
-  end
-
-
-class PageCtx
-  attr_accessor :page
-
-  def initialize(page, template)
-    @page     = page
-    @template = template
-  end
-
-  ##############################
-  ## add some "view helpers"
-
-  def name
-    ##  -- calculate name (use long name if (short) name is not availabe e.g. none)
-    ##   e.g. Austria
-    if @name.nil?
-      @name = page.name
-      @name = page.name_long  if @name == 'none'
-    end
-    @name
-  end
-
-  def names( separator: ' • ' )
-    ##  e.g. Austria • Österreich
-    if @names.nil?
-      if page.name_local.blank? || page.name_local == 'none' || page.name_local == name
-        @names = [name]    ## no local (in its own non-english language) name
-      else
-        @names = [name, page.name_local]
-      end
-    end
-    @names.join( separator )
-  end
-
-  def render
-    ERB.new( @template).result( binding )
-  end
-end   ## PageCtx
-
-end ## Almanac
-
-end # module Factbook

data/lib/factbook/attributes.rb

@@ -1,74 +0,0 @@
-# encoding: utf-8
-
-
-module Factbook
-
-class Attributes
-
-  Attribute = Struct.new( :name,     
-                          :category,  ## e.g. Introduction, Geography, etc.
-                          :path,      ## note: is an array  e.g. ["Area - comparative"] or ["Area", "land"] etc.
-                        )
-
-  def self.from_yaml( path )
-
-    h = YAML.load_file( path )
-    pp h
-
-    attribs = []
-
-    ## note: use a copy (e.g. h.dup) for now (hash gets changed by build_attribs!!)
-    new_h = h.dup
-    new_h.each do |k,v|
-      category = k
-      build_attribs( attribs, category, [], v )
-    end
-
-    self.new( attribs )
-  end
-
-
-  def self.build_attribs( attribs, category, path, h )  
-     
-      ## assume it's an attribute definition hash
-      ##   note: !! exclude special cases:
-      ##      Capital           -- incl. name key itself
-      ##      National anthem
-     if h.has_key?( 'name' ) &&  ['Capital','National anthem'].include?( path[-1] ) == false
-       a = Attribute.new
-       a.name     = h['name']
-       a.category = category
-       a.path     = path
-
-       puts "  adding attribute >#{a.name}< using #{a.category} / #{a.path.inspect}"       
-       attribs << a
-       
-       ## note: make sure a modifable copy (of h) gets passed in
-       h.delete( 'name' )
-     end
-
-     return  if h.empty?    ## empty hash; nothing (more) to do; return     
-     
-     ## continue walking (recursive)
-     h.each do |k,v|
-       new_path = path.dup << k   ## note: create a new array (copy) 
-       build_attribs( attribs, category, new_path, v )
-    end
-  end   
-
-
-  def initialize( attribs )
-    @attribs = attribs
-  end
-  
-  def to_a() @attribs; end
-  def size() @attribs.size; end
-
-  def each
-    @attribs.each { |attrib| yield( attrib ) }
-  end
-
-end  # class Attributes
-
-end # module Factbook
-

data/lib/factbook/builder.rb

@@ -1,214 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-class Builder     ## todo: change to PageBuilder ???
-  include LogUtils::Logging
-
-
-=begin
-def self.from_cc( cc, opts={} )  ## rename to from_file_for_country() or from_file_for_cc() or something - why?? why not??
-  ## check/todo: rename input_dir to just dir or to include ?
-  ##   (there's no output_dir)?? - why? why not?
-  input_dir = opts[:input_dir] || '.'
-  self.from_file( "#{input_dir}/#{cc}.html" )
-end
-=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
-
-
-attr_reader :html_ascii,     ## full "original" 1:1 page in "original/ascii8/binary" encoding
-            :html,           ## utf-8 encoded profile
-            :html_debug,     ## html w/ mapping markers - rename to html_markers - why? why not?
-            :info,            ## page info incl. country_name, region_name, last_updated etc.
-            :errors,          ## encoding erros etc.
-            :sects
-
-
-def initialize( html_ascii )
-  @html_ascii = html_ascii
-    
-  ## todo/fix: use/assume windows 12xx?? encoding - change encoding to utf-8  (from binary/ascii8bit)
-  @html, @info, @errors = Sanitizer.new.sanitize( @html_ascii )
-
-  @html_debug = map_sects( @html )
-  @html_debug = map_subsects( @html_debug )
-
-  html_sects = split_sects( @html_debug )
-  pp html_sects
-
-
-  @sects = []
-  html_sects.each do |html_sect|
-    html_sect_head = html_sect[0]
-    html_subsects  = html_sect[1]
-    puts html_sect_head
-    puts html_subsects.size
-    
-    ## get section title
-    ##  @SECTION{Economy}  => Economy
-    if html_sect_head =~ /@SECTION{(.+?)}/
-      title = $1.strip
-      puts title
-      sect = Sect.new
-      sect.title = title
-      ## get subsections
-      subsects = []
-      html_subsects.each do |html_subsect|
-        html_subsect_head = html_subsect[0]
-        html_subsect_body = html_subsect[1]
-        if html_subsect_head =~ /@SUBSECTION{(.+?)}/
-          title = $1.strip
-          title = title.sub( /:\z/, '' )    # remove trailing : if present
-          title = title.strip
-
-          puts title
-          subsect = Subsect.new
-          subsect.title = title     ## todo/fix: cut off trailing colon (:)
- 
-          b = Factbook::ItemBuilder.new( html_subsect_body, title )
-          h = b.read
-          subsect.data = h
-
-          subsects << subsect
-        else
-          ## warn/fix: no subsection title found
-        end
-      end
-      sect.subsects = subsects
-      @sects << sect
-    else
-      ## warn/fix:  no section title found
-    end   
-  end
-  
-  self  ## return self -- needed?? default (standard) anyway?? check and remove
-end
-
-
-
-def map_sects( html )
-   ## convert section titles
-   ##   from  <h2>..</h2>
-   ##   to "unified" marker
-
-  ## e.g.
-  ##  <h2 sectiontitle='Introduction' ccode='au'>Introduction ::  <span class='region'>AUSTRIA </span></h2>
-  ##  <h2>Introduction</h2>
-
-  title_regex= /<h2
-                 (?:\s[^>]+)?  ## allow optional attributes in h2
-                 >      
-                 \s*
-                   ([^<>]+?)  ## note: use non-greedy; do NOT allow tags inside for now
-                 \s*
-                 (?:\s::\s
-                   .+?       ## note: use non-greedy; allows tags inside
-                 )?          ## strip optional name (e.g.  :: AUSTRIA)
-                <\/h2>
-              /xim
-
-  html = html.gsub( title_regex ) do |m|
-     puts "** found section >#{$1}<:"
-     puts "   >|#{m}|<"
-
-     "\n\n@SECTION{#{$1}}\n\n"     
-  end
-  html
-end
-
-
-def map_subsects( html )
-   ## convert subsection titles
-   ##   from  <div id='field'>..</div>
-   ##   to "unified" marker
-
-  ## e.g.
-  ##  <div id='field' class='category'>Disputes - international:</div>
-
-  title_regex= /<div \s id='field'
-                     \s class='category'>
-                   \s*
-                   (.+?)                ## note: use non-greedy; allows tags inside - why? why not
-                   \s*
-                 <\/div>
-               /xim
-
-  html = html.gsub( title_regex ) do |m|
-     puts "** found subsection >#{$1}<:"
-     puts "   >|#{m}|<"
-
-     "\n@SUBSECTION{#{$1}}\n"     
-  end
-  html
-end
-
-
-
-def split_sects( html )
-  ####
-  #  split html in sections (divided by section headings)
-  #  e.g. remove optional prolog ??,
-  ##   [[heading,sect],
-  ##    [heading,sect],
-  ##    [heading,sect],...]
-
-  ## note: "wrap" regex in a capture group (just one)
-  ##   String#split will include all catpure groups in the result array
-
-  section_regex= /(@SECTION{.+?})/  ## note: use non-greedy -- check: need to escape {} ??
-     
-  chunks = html.split( section_regex )
-  
-  ## check if first item is a section or (html) prolog
-  #   if prolog (remove)
-  chunks.slice!(0)  unless chunks[0] =~ /@SECTION/  ## starts w/ @SECTION
-
-  pairs = chunks.each_slice(2).to_a
-
-  ## now split subsections
-  newpairs = []
-  pairs.each do |item|
-    ## todo: after cleanup prolog; remove @SECTION{} ?? - just keep title - why, why not??
-    newpairs << [item[0], split_subsects( item[1]) ]
-  end
-  newpairs
-end
-
-
-def split_subsects( html )
-  ####
-  #  split html in subsections (divided by subsection headings)
-  #  e.g. remove optional prolog ??,
-  ##   [[heading,sect],
-  ##    [heading,sect],
-  ##    [heading,sect],...]
-
-  ## note: "wrap" regex in a capture group (just one)
-  ##   String#split will include all catpure groups in the result array
-  
-  subsection_regex= /(@SUBSECTION{.+?})/  ## note: use non-greedy -- check: need to escape {} ??
-     
-  chunks = html.split( subsection_regex )
-
-  ## check if first item is a section or (html) prolog
-  #   if prolog (remove)
-  chunks.slice!(0)  unless chunks[0] =~ /@SUBSECTION/  ## starts w/ @SUBSECTION
-
-  pairs = chunks.each_slice(2).to_a
-  pairs
-end
-
-end # class Builder
-
-
-end # module Factbook

data/lib/factbook/builder_item.rb

@@ -1,92 +0,0 @@
-# encoding: utf-8
-
-module Factbook
-
-class ItemBuilder       ## renameto ItemReader, ItemParser - why? why not??
-  include LogUtils::Logging
-  include NormalizeHelper    ##  e.g. normalize_category
-  
-def initialize( html, name )
-  @html = html
-  @name = name     # add category/field name e.g. Area, Location, etc.
-end
-  
-def read
-  ## return hash from html snippet
-  doc = Nokogiri::HTML.fragment( @html )
-
-  data = {}
-  last_node = nil     ## track last hash (always use text key)
-  last_node_data_count = 0
-
-  ## note:
-  ##   skip whitespace text nodes (e.g. \n\n etc); just use divs
-  doc.children.filter('div').each_with_index do |child,i|
-
-    if child['class'] == 'category_data'
-       text = child.text    ## fix/todo: use strip
-       puts "category_data: >#{text}<"
-       
-       if last_node.nil?
-          ## assume its the very first entry; use implied/auto-created category
-          data['text'] = ''
-          last_node = data     
-          last_node_data_count = 0
-       end
-
-       ### first category_data element?
-      if last_node_data_count == 0
-         if last_node['text'] == ''
-            last_node['text'] = text
-         else   ### possible ??? if data_count is zero - not should not include any data
-            ## todo: issue warning here - why? why not??
-            last_node['text'] += " #{text}"    ## append w/o separator
-         end
-      else
-        if @name == 'Demographic profile'  ## special case (use space a sep)
-            last_node['text'] += " #{text}"   ## append without (w/o) separator
-        else
-            last_node['text'] += " ++ #{text}"   ## append with ++ separator
-        end
-      end
-      last_node_data_count += 1
-
-    elsif child['class'].nil?    ## div without any class e.g. <div>..</div>
-                                 ##   assume category and category_data pair w/ spans
-      spans = child.children.filter('span')
-      if spans.size > 2
-        puts "*** warn: expected two (or one) spans; got #{spans.inspect}"
-      end
-      
-      ## pp spans
-      
-      span_key   = spans[0]  ## assume 1st entry is span.category
-      span_value = spans[1]  ## assume 2nd entry is span.category_data
-      
-      key   = normalize_category( span_key.text )
-
-      ## note: allow optional category_data for now
-      value = span_value ? span_value.text : nil
-      
-      puts "key: >#{key}<, value: >#{value}< : #{value.class.name}"
-
-      ## start new pair
-      last_node = data[key] = { 'text' => value }
-      last_node_data_count =  value ? 1 : 0    ## note: set to 1 if value present
-    else
-      puts "*** warn: item builder -- unknow css class in #{child.inspect}"
-    end
-    
-    ## pp child
-    ## css = child['class']
-    ## puts "[#{i}] #{child.name}  class='>#{css}< : #{css.class.name}' >#{child.text}<"
-  end
-  
-  pp data
-  data
-end
-
-  
-end # class ItemBuilder
-
-end # module Factbook