sportdb-catalogs 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0e5965c765923646871f9c4b5544ea651c476614
+  data.tar.gz: 6387ea829d97c82a6aafada09f3caf7fa193a530
+SHA512:
+  metadata.gz: d36f04f85b69b4163c7262b50e690679a8133f409b3712e550e4cb4aaad74c7dbba9760e3d23718ff3e13274fb7d9a9bdaa2e2c1e5c052a43e9d461fb8db94b9
+  data.tar.gz: aa7666f61f3ed5964e1eb29cba7cf956510d98f63e9ea3c5192a9e7321a79ee5f185e2768208adfe05784b55d2e300a8bd82433ba8142678937652016f60ae42

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2019-06-29
+
+* Everything is new. First release.

data/Manifest.txt

@@ -0,0 +1,17 @@
+CHANGELOG.md
+Manifest.txt
+NOTES.md
+README.md
+Rakefile
+lib/sportdb/catalogs.rb
+lib/sportdb/catalogs/catalog.rb
+lib/sportdb/catalogs/config.rb
+lib/sportdb/catalogs/version.rb
+lib/sportdb/catalogs/wiki_index.rb
+test/helper.rb
+test/test_clubs.rb
+test/test_clubs_history.rb
+test/test_countries.rb
+test/test_leagues.rb
+test/test_national_teams.rb
+test/test_wiki_index.rb

data/NOTES.md

@@ -0,0 +1,5 @@
+# Notes
+
+## Todos
+
+

data/README.md

@@ -0,0 +1,141 @@
+# sportdb-catalogs - sport.db (search & find) catalogs for countries, leagues, clubs, national teams, and more
+
+
+* home  :: [github.com/sportdb/sport.db](https://github.com/sportdb/sport.db)
+* bugs  :: [github.com/sportdb/sport.db/issues](https://github.com/sportdb/sport.db/issues)
+* gem   :: [rubygems.org/gems/sportdb-catalogs](https://rubygems.org/gems/sportdb-catalogs)
+* rdoc  :: [rubydoc.info/gems/sportdb-catalogs](http://rubydoc.info/gems/sportdb-catalogs)
+* forum :: [opensport](http://groups.google.com/group/opensport)
+
+
+
+
+## Usage
+
+Let's use the [/clubs datasets](https://github.com/openfootball/clubs)
+(1500+ football clubs from around the world)
+to match name "variants" e.g. `Arsenal`  to canonical global unique
+names e.g. `Arsenal FC, London, England`:
+
+``` ruby
+require 'sportdb/catalogs'
+
+## note: requires a local copy of the football.db clubs datasets
+##          see https://github.com/openfootball/clubs
+SportDb::Import.config.clubs_dir = './clubs'
+
+CLUBS = SportDb::Import.catalog.clubs
+
+m = CLUBS.match( 'Arsenal' )
+m.size     # 3 club matches found
+#=> 3
+m[0].name; m[0].city; m[0].country
+#=> "Arsenal FC", "London", "England"
+m[1].name; m[1].city; m[1].country
+#=> "Arsenal Tula", "Tula", "Russia"
+m[2].name; m[2].city; m[2].country
+#=> "Arsenal de Sarandí", "Sarandí", "Argentina"
+
+
+m = CLUBS.match_by( name: 'Arsenal', country: 'eng' )
+# -or- try alternative names (and auto-generated spelling variants)
+m = CLUBS.match_by( name: 'Arsenal FC', country: 'eng' )
+m = CLUBS.match_by( name: 'Arsenal F.C.', country: 'eng' )
+m = CLUBS.match_by( name: '...A.r.s.e.n.a.l... F.C...', country: 'eng' )
+m.size     # 1 club match found
+#=> 1
+m[0].name; m[0].city; m[0].country
+#=> "Arsenal FC", "London", "England"
+
+m = CLUBS.match_by( name: 'Arsenal', country: 'ar' )
+# -or- try alternative names (and auto-generated spelling variants)
+m = CLUBS.match_by( name: 'Arsenal Sarandí', country: 'ar' )
+m = CLUBS.match_by( name: 'Arsenal Sarandi', country: 'ar' )
+m.size     # 1 club match found
+#=> 1
+m[0].name; m[0].city; m[0].country
+#=> "Arsenal de Sarandí", "Sarandí", "Argentina"
+
+
+# try some more
+m = CLUBS.match( 'AZ' )
+m[0].name; m[0].city; m[0].country
+#=> "AZ Alkmaar", "Alkmaar", "Netherlands"
+
+m = CLUBS.match( 'Bayern' )
+# -or- try alternative names (and auto-generated spelling variants)
+m = CLUBS.match( 'Bayern München' )
+m = CLUBS.match( 'Bayern Munchen' )
+m = CLUBS.match( 'Bayern Muenchen' )
+m[0].name; m[0].city; m[0].country
+#=> "Bayern München", "München", "Germany"
+
+# and so on
+# ...
+```
+
+Let's print all names that have duplicate (more than one) matching club:
+
+``` ruby
+CLUBS.mappings.each do |name, clubs|
+  if clubs.size > 1
+    puts "#{clubs.size} matching clubs for `#{name}`:"
+    clubs.each do |club|
+      puts "  - #{club.name}, #{club.city}, #{club.country.name} (#{club.country.key})"
+    end
+    puts
+  end
+end
+```
+
+resulting in:
+
+```
+2 matching clubs for `valencia`:
+  - Valencia FC, Léogâne, Haiti (ht)
+  - Valencia CF, Valencia, Spain (es)
+
+2 matching clubs for `apollon`:
+  - Apollon Limassol FC, , Cyprus (cy)
+  - Apollon Smyrnis FC, Athens, Greece (gr)
+
+3 matching clubs for `arsenal`:
+  - Arsenal FC, London, England (eng)
+  - Arsenal Tula, Tula, Russia (ru)
+  - Arsenal de Sarandí, Sarandí, Argentina (ar)
+
+2 matching clubs for `liverpool`:
+  - Liverpool FC, Liverpool, England (eng)
+  - Liverpool Montevideo, Montevideo, Uruguay (uy)
+
+2 matching clubs for `barcelona`:
+  - FC Barcelona, Barcelona, Spain (es)
+  - Barcelona Guayaquil, Guayaquil, Ecuador (ec)
+
+3 matching clubs for `nacional`:
+  - CD Nacional Madeira, Funchal, Portugal (pt)
+  - Club Nacional, Asunción, Paraguay (py)
+  - Nacional de Montevideo, Montevideo, Uruguay (uy)
+
+2 matching clubs for `sanjose`:
+  - San Jose Earthquakes, San Jose, United States (us)
+  - Club Deportivo San José, Oruro, Bolivia (bo)
+
+...
+```
+
+That's it.
+
+
+
+## License
+
+The `sportdb-catalogs` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+
+## Questions? Comments?
+
+Send them along to the
+[Open Sports & Friends Forum/Mailing List](http://groups.google.com/group/opensport).
+Thanks!

data/Rakefile

@@ -0,0 +1,34 @@
+require 'hoe'
+require './lib/sportdb/catalogs/version.rb'
+
+Hoe.spec 'sportdb-catalogs' do
+
+  self.version = SportDb::Module::Catalogs::VERSION
+
+  self.summary = "sportdb-catalogs - sport.db (search 'n' find) catalogs for countries, leagues, clubs, national teams, and more"
+  self.description = summary
+
+  self.urls = ['https://github.com/sportdb/sport.db']
+
+  self.author = 'Gerald Bauer'
+  self.email  = 'opensport@googlegroups.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'CHANGELOG.md'
+
+  self.licenses = ['Public Domain']
+
+  self.extra_deps = [
+    ['sportdb-formats',    '>= 1.1.3'],
+    ## dataset libs / gems
+    ['fifa',               '>= 2020.5.18'],    ## for (builtin/default) countries
+    ['footballdb-leagues', '>= 2020.7.7'],    ## for (builtin/default) leagues & cups
+    ['footballdb-clubs',   '>= 2020.7.7'],     ## for (builtin/default) clubs
+  ]
+
+  self.spec_extras = {
+   required_ruby_version: '>= 2.2.2'
+  }
+
+end

data/lib/sportdb/catalogs.rb

@@ -0,0 +1,20 @@
+# encoding: utf-8
+
+### our own sportdb libs / gems
+require 'sportdb/formats'
+
+### "built-in" default dataset libs / gems
+require 'fifa'    ## get a list of all fifa countries with (three letter) codes
+require 'footballdb/leagues'
+require 'footballdb/clubs'
+
+
+###
+# our own code
+require 'sportdb/catalogs/version' # let version always go first
+require 'sportdb/catalogs/wiki_index'
+require 'sportdb/catalogs/catalog'
+require 'sportdb/catalogs/config'
+
+
+puts SportDb::Module::Catalogs.banner   # say hello

data/lib/sportdb/catalogs/catalog.rb

@@ -0,0 +1,105 @@
+
+module SportDb
+  module Import
+
+
+class Catalog
+  def config() Import.config; end
+
+
+  ## todo/check:  rename to country_mappings/index - why? why not?
+  ##    or countries_by_code or countries_by_key
+  def countries()      @countries      ||= build_country_index; end
+  def national_teams() @national_teams ||= build_national_team_index; end
+  def clubs()          @clubs          ||= build_club_index; end
+  def clubs_history()  @clubs_history  ||= build_club_history_index; end  ## note: used for now (only) lookups by season for now
+  def teams()          @teams          ||= build_team_index; end
+  def leagues()        @leagues        ||= build_league_index; end
+
+  def events()         @events         ||= build_event_index; end
+  def seasons()        @seasons        ||= build_season_index; end
+
+
+
+  def build_team_index() TeamIndex.new;  end
+
+  def build_country_index    ## todo/check: rename to setup_country_index or read_country_index - why? why not?
+    CountryIndex.new( Fifa.countries )
+  end
+
+  def build_national_team_index
+    ## auto-build national teams from Fifa.countries for now
+    teams = []
+    Fifa.countries.each do |country|
+      team = NationalTeam.new( key:        country.code.downcase,  ## note: use country code (fifa)
+                               name:       country.name,
+                               code:       country.code,           ## note: use country code (fifa)
+                               alt_names:  country.alt_names )
+      team.country = country
+
+      teams << team
+    end
+
+    NationalTeamIndex.new( teams )
+  end
+
+  def build_club_index
+    ## unify team names; team (builtin/known/shared) name mappings
+    ## cleanup team names - use local ("native") name with umlaut etc.
+    ## todo/fix: add to teamreader
+    ##              check that name and alt_names for a club are all unique (not duplicates)
+
+    clubs = if config.clubs_dir   ## check if clubs_dir is defined / set (otherwise it's nil)
+              ClubIndex.build( config.clubs_dir )
+            else   ## no clubs_dir set - try using builtin from footballdb-clubs
+              FootballDb::Import::build_club_index
+            end
+
+    if clubs.errors?
+      puts ""
+      puts "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
+      puts " #{clubs.errors.size} errors:"
+      pp clubs.errors
+      ## exit 1
+    end
+
+    clubs
+  end # method build_club_index
+
+  def build_club_history_index
+    if config.clubs_dir    ## (re)use clubs dir for now  - why? why not?
+      ClubHistoryIndex.build( config.clubs_dir )
+    else
+      puts "!! WARN - no clubs_dir set; for now NO built-in club histories in catalog; sorry - fix!!!!"
+      ClubHistoryIndex.new   ## return empty history index
+    end
+  end
+
+
+  def build_league_index
+    leagues = if config.leagues_dir   ## check if clubs_dir is defined / set (otherwise it's nil)
+                LeagueIndex.build( config.leagues_dir )
+              else   ## no leagues_dir set - try using builtin from footballdb-leagues
+                FootballDb::Import.build_league_index
+              end
+  end
+
+
+  def build_event_index
+    if config.leagues_dir    ## (re)use leagues dir for now - add separate seasons_dir - why? why not?
+      EventIndex.build( config.leagues_dir )
+    else
+      puts "!! WARN - no leagues_dir set; for now NO built-in events in catalog; sorry - fix!!!!"
+      EventIndex.new   ## return empty event index
+    end
+  end
+
+  def build_season_index
+    # note: for now always (re)use the events from the event (info) index
+    SeasonIndex.new( events )
+  end
+
+end  # class Catalog
+
+  end   # module Import
+end   # module SportDb

data/lib/sportdb/catalogs/config.rb

@@ -0,0 +1,25 @@
+# encoding: utf-8
+
+module SportDb
+  module Import
+
+class Configuration
+  ## note: add more configs (open class), see sportdb-formats for original config!!!
+
+  ##
+  ##  todo: allow configure of countries_dir like clubs_dir
+  ##         "fallback" and use a default built-in world/countries.txt
+
+  ####
+  #  todo/check:  find a better way to configure club / team datasets - why? why not?
+  attr_accessor   :clubs_dir
+  ## def clubs_dir()      @clubs_dir; end   ### note: return nil if NOT set on purpose for now - why? why not?
+
+  attr_accessor   :leagues_dir
+  ## def leagues_dir()    @leagues_dir; end
+
+  def catalog()      @catalog ||= Catalog.new;  end
+end # class Configuration
+
+end   # module Import
+end   # module SportDb

data/lib/sportdb/catalogs/version.rb

@@ -0,0 +1,27 @@
+# encoding: utf-8
+
+
+module SportDb
+module Module
+module Catalogs
+
+  MAJOR = 1    ## todo: namespace inside version or something - why? why not??
+  MINOR = 0
+  PATCH = 0
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "sportdb-catalogs/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+  end
+
+  def self.root
+    File.expand_path( File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) )
+  end
+
+end # module Catalogs
+end # module Module
+end # module SportDb

data/lib/sportdb/catalogs/wiki_index.rb

@@ -0,0 +1,81 @@
+# encoding: utf-8
+
+module SportDb
+  module Import
+
+
+class WikiIndex
+
+  def self.build( path )
+    pack = Package.new( path )
+    recs = []
+    pack.each_clubs_wiki do |entry|
+      recs += WikiReader.parse( entry.read )
+    end
+    recs
+
+    new( recs )
+  end
+
+
+  include NameHelper
+  ## e.g. strip_lang, strip_year, normalize
+
+  ## fix/todo:
+  ##  also used / duplicated in ClubIndex#add_wiki !!!
+  def strip_wiki( name )     # todo/check: rename to strip_wikipedia_en - why? why not?
+    ## note: strip disambiguationn qualifier from wikipedia page name if present
+    ##        note: only remove year and foot... for now
+    ## e.g. FC Wacker Innsbruck (2002) => FC Wacker Innsbruck
+    ##      Willem II (football club)  => Willem II
+    ##
+    ## e.g. do NOT strip others !! e.g.
+    ##   América Futebol Clube (MG)
+    ##  only add more "special" cases on demand (that, is) if we find more
+    name = name.gsub( /\([12][^\)]+?\)/, '' ).strip  ## starting with a digit 1 or 2 (assuming year)
+    name = name.gsub( /\(foot[^\)]+?\)/, '' ).strip  ## starting with foot (assuming football ...)
+    name
+  end
+
+
+  def initialize( recs )
+    @pages_by_country = {}
+
+    ## todo/fix:
+    ##   check for duplicate recs - report and exit on dupliate!!!!!!
+    recs.each do |rec|
+      h = @pages_by_country[ rec.country.key ] ||= {}
+      h[ normalize( strip_wiki( rec.name )) ] = rec
+    end
+  end
+
+
+  def find_by( club: )    ## todo/check: use find_by_club - why? why not?
+    find_by_club( club )
+  end
+
+  def find_by_club( club )
+    rec = nil
+
+    ## get query params from club
+    names   = [club.name]+club.alt_names
+    country_key = club.country.key
+
+    h = @pages_by_country[ country_key ]
+    if h
+      ## todo/check: sort names ?
+      ##   sort by longest first (for best match)
+      names.each do |name|
+        ## note: normalize AND sanitize (e.g. remove/string year and lang e.g. (1946-2001), [en] too)
+        rec = h[ normalize( strip_year( strip_lang( name ))) ]
+        break if rec   ## bingo!! found - break on first match
+      end
+    end
+
+    rec  ## note: return nil if nothing found
+  end
+end  # class WikiIndex
+
+
+end   # module Import
+end   # module SportDb

data/test/helper.rb

@@ -0,0 +1,13 @@
+## note: use the local version of sportdb gems
+$LOAD_PATH.unshift( File.expand_path( '../sportdb-formats/lib' ))
+
+## minitest setup
+require 'minitest/autorun'
+
+
+## our own code
+require 'sportdb/catalogs'
+
+
+SportDb::Import.config.clubs_dir   = '../../../openfootball/clubs'
+SportDb::Import.config.leagues_dir = '../../../openfootball/leagues'

data/test/test_clubs.rb

@@ -0,0 +1,100 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_clubs.rb
+
+
+require 'helper'
+
+class TestClubs < MiniTest::Test
+
+   CLUBS = SportDb::Import.catalog.clubs
+
+
+  def test_match
+    pp CLUBS.errors
+
+    CLUBS.dump_duplicates
+
+    m = CLUBS.match( 'Rapid Wien' )
+    assert_equal 'SK Rapid Wien', m[0].name
+    assert_equal 'Austria',       m[0].country.name
+    assert_equal 'Wien',          m[0].city
+
+    m = CLUBS.match( 'rapid wien' )
+    assert_equal 'SK Rapid Wien', m[0].name
+    assert_equal 'Austria',       m[0].country.name
+    assert_equal 'Wien',          m[0].city
+
+    ## note: all dots (.) get always removed
+    m = CLUBS.match( '...r.a.p.i.d w.i.e.n...' )
+    assert_equal 'SK Rapid Wien', m[0].name
+    assert_equal 'Austria',       m[0].country.name
+    assert_equal 'Wien',          m[0].city
+
+    ## note: all spaces and dashes (-) get always removed
+    m = CLUBS.match( '--- r a p i d  w i e n ---' )
+    assert_equal 'SK Rapid Wien', m[0].name
+    assert_equal 'Austria',       m[0].country.name
+    assert_equal 'Wien',          m[0].city
+
+    m = CLUBS.match( 'RAPID WIEN' )
+    assert_equal 'SK Rapid Wien', m[0].name
+    assert_equal 'Austria',       m[0].country.name
+    assert_equal 'Wien',          m[0].city
+
+
+    c = CLUBS[ 'SK Rapid Wien' ]   ## check canoncial name match (only)
+    assert_equal 'SK Rapid Wien', c.name
+    assert_equal 'Austria',       c.country.name
+    assert_equal 'Wien',          c.city
+
+
+    m = CLUBS.match( 'Arsenal' )
+    assert_equal 3, m.size
+
+    m = CLUBS.match( 'ARSENAL' )
+    assert_equal 3, m.size
+
+    m = CLUBS.match_by( name: 'Arsenal', country: 'eng' )
+    assert_equal 1, m.size
+    assert_equal 'Arsenal FC', m[0].name
+    assert_equal 'England',    m[0].country.name
+    assert_equal 'London',     m[0].city
+
+    m = CLUBS.match_by( name: 'Arsenal', country: 'ar' )
+    assert_equal 1, m.size
+    assert_equal 'Arsenal de Sarandí', m[0].name
+    assert_equal 'Argentina',          m[0].country.name
+    assert_equal 'Sarandí',            m[0].city
+
+    m = CLUBS.match_by( name: 'Arsenal', country: 'ru' )
+    assert_equal 1, m.size
+    assert_equal 'Arsenal Tula', m[0].name
+    assert_equal 'Russia',       m[0].country.name
+    assert_equal 'Tula',         m[0].city
+
+
+    m = CLUBS.match( 'Arsenal FC' )
+    assert_equal 2, m.size
+
+    m = CLUBS.match( 'Arsenal F.C.' )
+    assert_equal 2, m.size
+
+    m = CLUBS.match( '...A.r.s.e.n.a.l... F.C...' )
+    assert_equal 2, m.size
+  end
+
+
+  def test_wikipedia    ## test wikipedia names and links/urls
+    m = CLUBS.match( 'Club Brugge KV' )
+    assert_equal 1, m.size
+    assert_equal 'Club Brugge KV', m[0].wikipedia
+    assert_equal 'https://en.wikipedia.org/wiki/Club_Brugge_KV', m[0].wikipedia_url
+
+    m = CLUBS.match( 'RSC Anderlecht' )
+    assert_equal 1, m.size
+    assert_equal 'R.S.C. Anderlecht', m[0].wikipedia
+    assert_equal 'https://en.wikipedia.org/wiki/R.S.C._Anderlecht', m[0].wikipedia_url
+  end
+
+end # class TestClubs

data/test/test_clubs_history.rb

@@ -0,0 +1,47 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_clubs_history.rb
+
+
+require 'helper'
+
+class TestClubsHistory < MiniTest::Test
+
+   CLUBS         = SportDb::Import.catalog.clubs
+   CLUBS_HISTORY = SportDb::Import.catalog.clubs_history
+
+
+  def test_at
+    pp CLUBS_HISTORY.mappings
+
+    puts CLUBS_HISTORY.find_name_by( name: 'WSG Tirol', season: '2019/20' )
+    puts CLUBS_HISTORY.find_name_by( name: 'WSG Tirol', season: '2018/9' )
+    puts CLUBS_HISTORY.find_name_by( name: 'WSG Tirol', season: '2017/8' )
+
+    club = CLUBS.find( 'WSG Wattens' )
+    pp club
+
+    assert_equal 'WSG Tirol',   club.name_by_season( '2019/20' )
+    assert_equal 'WSG Wattens', club.name_by_season( '2018/9' )
+    assert_equal 'WSG Wattens', club.name_by_season( '2017/8' )
+
+
+    club = CLUBS.find( 'Rapid Wien' )
+    pp club
+
+    assert_equal 'SK Rapid Wien', club.name_by_season( '2000/1' )
+    assert_equal 'SK Rapid Wien', club.name_by_season( '1891/2' )
+  end
+
+  def test_eng
+    club = CLUBS.find_by( name: 'Arsenal', country: 'ENG' )
+    pp club
+
+    assert_equal 'Arsenal FC',          club.name_by_season( '2000/1' )
+    assert_equal 'Arsenal FC',          club.name_by_season( '1927/8' )
+    assert_equal 'The Arsenal FC',      club.name_by_season( '1926/7' )
+    assert_equal 'Woolwich Arsenal FC', club.name_by_season( '1913/4' )
+    assert_equal 'Royal Arsenal FC',    club.name_by_season( '1891/2' )
+  end
+
+end # class TestClubsHistory

data/test/test_countries.rb

@@ -0,0 +1,33 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_countries.rb
+
+
+require 'helper'
+
+class TestCountries < MiniTest::Test
+
+  COUNTRIES = SportDb::Import.catalog.countries
+
+
+  def test_countries
+    ## pp COUNTRIES
+
+    eng = COUNTRIES.find( :eng )
+    assert_equal 'eng',      eng.key
+    assert_equal 'England',  eng.name
+    assert_equal 'ENG',      eng.code
+
+    at  = COUNTRIES.find( :at )
+    assert_equal 'at',       at.key
+    assert_equal 'Austria',  at.name
+    assert_equal 'AUT',      at.code
+
+    assert at == COUNTRIES.find( 'AT' )
+    assert at == COUNTRIES.find( 'at' )
+    assert at == COUNTRIES.find( 'AUT' )
+    assert at == COUNTRIES.find( 'aut' )
+    assert at == COUNTRIES.find( :aut )
+  end
+
+end # class TestCountries

data/test/test_leagues.rb

@@ -0,0 +1,38 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_leagues.rb
+
+
+require 'helper'
+
+class TestLeagues < MiniTest::Test
+
+  LEAGUES = SportDb::Import.catalog.leagues
+
+
+  def test_match
+    pp LEAGUES.errors
+
+    LEAGUES.dump_duplicates
+
+    m = LEAGUES.match( 'English Premier League' )
+    pp m
+    assert_equal 'Premier League',         m[0].name
+    assert_equal 'eng.1',                  m[0].key
+    assert_equal 'England',                m[0].country.name
+    assert_equal 'eng',                    m[0].country.key
+    assert                                 m[0].clubs?
+    assert                                 m[0].domestic?
+    assert_equal false,                    m[0].intl?
+    assert_equal false,                    m[0].national_teams?
+
+    m = LEAGUES.match( 'Euro' )
+    pp m
+    assert_equal 'Euro',                   m[0].name
+    assert_equal 'euro',                   m[0].key
+    assert                                 m[0].national_teams?
+    assert                                 m[0].intl?
+    assert_equal false,                    m[0].clubs?
+  end
+
+end # class TestLeagues

data/test/test_national_teams.rb

@@ -0,0 +1,38 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_national_teams.rb
+
+
+require 'helper'
+
+class TestNationalTeams < MiniTest::Test
+
+  NATIONAL_TEAMS = SportDb::Import.catalog.national_teams
+
+
+  def test_find
+    t = NATIONAL_TEAMS.find( 'AUT' )
+    assert_equal 'Austria', t.name
+    assert_equal 'aut',     t.key
+    assert_equal 'AUT',     t.code
+
+
+    t = NATIONAL_TEAMS.find( 'England' )
+    assert_equal 'England', t.name
+    assert_equal 'eng',     t.key
+    assert_equal 'ENG',     t.code
+
+    ## note: all dots (.) get always removed
+    t = NATIONAL_TEAMS.find( '...e.n.g.l.a.n.d...' )
+    assert_equal 'England', t.name
+    assert_equal 'eng',     t.key
+    assert_equal 'ENG',     t.code
+
+    ## note: all spaces and dashes (-) get always removed
+    t = NATIONAL_TEAMS.find( '--- e n g l a n d ---' )
+    assert_equal 'England', t.name
+    assert_equal 'eng',     t.key
+    assert_equal 'ENG',     t.code
+  end
+
+end  # class TestNationalTeams

data/test/test_wiki_index.rb

@@ -0,0 +1,42 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_wiki_index.rb
+
+
+require 'helper'
+
+class TestWikiIndex < MiniTest::Test
+
+  Club      = SportDb::Import::Club
+
+  COUNTRIES = SportDb::Import.catalog.countries
+
+
+  def test_clubs
+    ## note: CANNOT run if no "custom" clubs_dir set
+    return  if SportDb::Import.config.clubs_dir.nil?
+
+    wiki = SportDb::Import::WikiIndex.build( SportDb::Import.config.clubs_dir )
+    ## pp wiki
+
+    ##############################################
+    ## test wikipedia names and links/urls
+    be = COUNTRIES.find( 'be' )
+
+    club = Club.new
+    club.name    = 'Club Brugge KV'
+    club.country = be
+
+    rec = wiki.find_by( club: club )
+    assert_equal 'Club Brugge KV', rec.name
+
+
+    club = Club.new
+    club.name    = 'RSC Anderlecht'
+    club.country = be
+
+    rec = wiki.find_by( club: club )
+    assert_equal 'R.S.C. Anderlecht', rec.name
+  end
+
+end # class TestWikiIndex

metadata

@@ -0,0 +1,152 @@
+--- !ruby/object:Gem::Specification
+name: sportdb-catalogs
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-08-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: sportdb-formats
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.1.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.1.3
+- !ruby/object:Gem::Dependency
+  name: fifa
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.5.18
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.5.18
+- !ruby/object:Gem::Dependency
+  name: footballdb-leagues
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.7.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.7.7
+- !ruby/object:Gem::Dependency
+  name: footballdb-clubs
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.7.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2020.7.7
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+description: sportdb-catalogs - sport.db (search 'n' find) catalogs for countries,
+  leagues, clubs, national teams, and more
+email: opensport@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- CHANGELOG.md
+- Manifest.txt
+- NOTES.md
+- README.md
+files:
+- CHANGELOG.md
+- Manifest.txt
+- NOTES.md
+- README.md
+- Rakefile
+- lib/sportdb/catalogs.rb
+- lib/sportdb/catalogs/catalog.rb
+- lib/sportdb/catalogs/config.rb
+- lib/sportdb/catalogs/version.rb
+- lib/sportdb/catalogs/wiki_index.rb
+- test/helper.rb
+- test/test_clubs.rb
+- test/test_clubs_history.rb
+- test/test_countries.rb
+- test/test_leagues.rb
+- test/test_national_teams.rb
+- test/test_wiki_index.rb
+homepage: https://github.com/sportdb/sport.db
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.2.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2
+signing_key: 
+specification_version: 4
+summary: sportdb-catalogs - sport.db (search 'n' find) catalogs for countries, leagues,
+  clubs, national teams, and more
+test_files: []