sportdb-models 1.18.0 → 1.18.1

data/lib/sportdb/lang.rb

@@ -1,216 +0,0 @@
-# encoding: utf-8
-
-module SportDb
-
-class Lang
-
-  include LogUtils::Logging
-
-  attr_reader :lang
-
-  def initialize
-    # fix/todo: load on demand; only if no fixtures loaded/configured use builtin
-    load_builtin_words
-  end
-
-
-  def load_builtin_words
-    builtin_words = {
-      'en' => 'fixtures/en',
-      'de' => 'fixtures/de',
-      'es' => 'fixtures/es',
-      'fr' => 'fixtures/fr',
-      'it' => 'fixtures/it',
-      'pt' => 'fixtures/pt',
-      'ro' => 'fixtures/ro'
-    }
-
-    load_words( builtin_words, SportDb.config_path )
-  end
-
-
-  def load_words( h, include_path )
-    @lang = 'en'   # make default lang english/en
-    @words = {}  # resets fixtures
-    @cache = {}  # reset cached values
-
-    h.each_with_index do |(key,value),i|
-      name = value
-      path = "#{include_path}/#{name}.yml"
-      logger.debug( "loading words #{key} (#{i+1}/#{h.size}) in '#{name}' (#{path})..." )
-      @words[ key ] = YAML.load( File.read_utf8( path ))
-    end
-
-    @classifier = TextUtils::Classifier.new
-    @words.each_with_index do |(key,value),i|
-      logger.debug "train classifier for #{key} (#{i+1}/#{@words.size})"
-      @classifier.train( key, value )
-    end
-    
-    @classifier.dump  # for debugging dump all words
-  end
-
-  def classify( text )
-    @classifier.classify( text )
-  end
-
-  def classify_file( path )
-    @classifier.classify_file( path )
-  end
-
-  def lang=(value)
-    logger.debug "setting lang to #{value}"
-    
-    if @lang != value
-      
-      ### todo: make reset cached values into method/function for reuse (see load_words)
-      # reset cached values on language change
-      logger.debug "reseting cached lang values (lang changed from #{@lang} to #{value})"
-
-      @cache = {}
-    end
-    
-    @lang = value
-    
-  end
-
-
-  def group
-    @cache[ :group ] ||= group_getter
-  end
-  
-  def round
-    @cache[ :round ] ||= round_getter
-  end
-
-  def knockout_round
-    @cache[ :knockout_round ] ||= knockout_round_getter
-  end
-  
-  def leg1
-    @cache[ :leg1 ] ||= leg1_getter
-  end
-  
-  def leg2
-    @cache[ :leg2 ] ||= leg2_getter
-  end
-
-
-
-  def regex_group
-    @cache [ :regex_group ] ||= regex_group_getter
-  end
-
-  def regex_round
-    @cache[ :regex_round ] ||= regex_round_getter
-  end
-
-  def regex_knockout_round
-    @cache[ :regex_knockout_round ] ||= regex_knockout_round_getter
-  end
-  
-  def regex_leg1
-    @cache[ :regex_leg1 ] ||= regex_leg1_getter
-  end
-  
-  def regex_leg2
-    @cache[ :regex_leg2 ] ||= regex_leg2_getter
-  end
-
-private
-  def group_getter
-    h = @words[ lang ]
-    values = ""   # NB: always construct a new string (do NOT use a reference to hash value)
-    values << h['group']
-    values
-  end
-
-  def round_getter
-    # e.g. Spieltag|Runde|Achtelfinale|Viertelfinale|Halbfinale|Finale
-    
-    ## fix/todo:
-    ##  sort by length first - to allow best match e.g.
-    ##    3rd place play-off  instead of Play-off ?? etc.  - why? why not?
-
-    h = @words[ lang ]
-    values = ""   # NB: always construct a new string (do NOT use a reference to hash value)
-    values << h['round']
-    
-    ### add knockout rounds values too
-    values << "|" << h['round32']
-    values << "|" << h['round16']
-    values << "|" << h['quarterfinals']
-    values << "|" << h['semifinals']
-    values << "|" << h['fifthplace']  if h['fifthplace']   # nb: allow empty/is optional!!
-    values << "|" << h['thirdplace']
-    values << "|" << h['final']
-    values << "|" << h['playoffs']    if h['playoffs']   # nb: allow empty/is optional!!
-    values
-  end
-
-  def leg1_getter
-    h = @words[ lang ]
-    values = ""  # NB: always construct a new string (do NOT use a reference to hash value)
-    values << h['leg1']
-    values
-  end
-
-  def leg2_getter
-    h = @words[ lang ]
-    values = ""  # NB: always construct a new string (do NOT use a reference to hash value)
-    values << h['leg2']
-    values
-  end
-
-  def knockout_round_getter
-    h = @words[ lang ]
-    values = ""  # NB: always construct a new string (do NOT use a reference to hash value)
-    values << h['round32']
-    values << "|" << h['round16']
-    values << "|" << h['quarterfinals']
-    values << "|" << h['semifinals']
-    values << "|" << h['fifthplace']  if h['fifthplace']   # nb: allow empty/is optional!!
-    values << "|" << h['thirdplace']
-    values << "|" << h['final']
-    values << "|" << h['playoffs']    if h['playoffs']   # nb: allow empty/is optional!!
-    values
-  end
-  
-  def regex_group_getter
-    ## todo: escape for regex?
-    ## NB: let's ignore case (that is, UPCASE,downcase); always use /i flag
-    /#{group}/i
-  end
-  
-  def regex_round_getter
-    ## todo: escape for regex?
-    ## todo: sort by length - biggest words go first? does regex match biggest word automatically?? - check
-    ##  todo/fix: make - optional e.g. convert to ( |-) or better [ \-] ??
-    ## NB: let's ignore case (that is, UPCASE,downcase); always use /i flag
-    /#{round}/i
-  end
-
-  def regex_knockout_round_getter
-    ## todo: escape for regex?
-    ## todo: sort by length - biggest words go first? does regex match biggest word automatically?? - check
-    ##  todo/fix: make - optional e.g. convert to ( |-) or better [ \-] ??
-    ## NB: let's ignore case (that is, UPCASE,downcase); always use /i flag
-    /#{knockout_round}/i
-  end
-
-  def regex_leg1_getter
-    ## todo: escape for regex?
-    ## NB: let's ignore case (that is, UPCASE,downcase); always use /i flag
-    /#{leg1}/i
-  end
-
-  def regex_leg2_getter
-    ## todo: escape for regex?
-    ## NB: let's ignore case (that is, UPCASE,downcase); always use /i flag
-    /#{leg2}/i
-  end
-
-end # class Lang
-
-
-end # module SportDb

data/test/test_csv_reader.rb

@@ -1,45 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_csv_reader.rb
-
-
-require 'helper'
-
-class TestCsvReader < MiniTest::Test
-
-  def setup
-    WorldDb.delete!
-    SportDb.delete!
-    SportDb.read_builtin
-  end
-
-  def test_bl_2014
-    de = Country.create!( key: 'de', name: 'Deutschland', code: 'GER', pop: 1, area: 1 )
-
-    teamreader = TestTeamReader.from_file( 'de-deutschland/teams', country_id: de.id )
-    teamreader.read()
-
-    leaguereader = TestLeagueReader.from_file( 'de-deutschland/leagues', country_id: de.id )
-    leaguereader.read()
-
-    eventreader = TestEventReader.from_file( 'de-deutschland/2013-14/1-bundesliga' )
-    eventreader.read
-
-    assert true   ## if we get here; assume everything ok
-
-    text = File.read_utf8( "#{SportDb.test_data_path}/csv/de-2013-14--1-bundesliga.txt" )
-
-    ## bl = Event.find_by_key!( 'de.2013/14' )
-
-    r = SportDb::CsvGameReader.from_string( 'de.2013/14', text )
-    r.read
-
-    ## assert_equal  10, bl.teams.count
-    ## assert_equal  36, bl.rounds.count
-    ## assert_equal 180, bl.games.count  # 36x5 = 180
-  end
-
-end # class TestCsvReader
-

data/test/test_date.rb

@@ -1,100 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_date.rb
-
-require 'helper'
-
-class TestDate < MiniTest::Test
-
-  def test_date
-    data = [
-      [ '19.01.2013 22.00', '2013-01-19 22:00' ],
-      [ '21.01.2013 21.30', '2013-01-21 21:30' ],
-      [ '26.01.2013',       '2013-01-26' ],
-      [ '[26.01.2013]',     '2013-01-26' ],
-      [ '[21.1.]',          '2013-01-21 12:00' ]
-    ]
-
-    assert_dates( data, start_at: DateTime.new( 2013, 1, 1 ) )
-  end
-
-  def test_date_fr
-    data = [
-      [ '[Ven 08. Août]', '2014-08-08' ],
-      [ 'Ven 08. Août',   '2014-08-08' ],
-      [ 'Ven 8. Août',    '2014-08-08' ],
-      [ '[Sam 9. Août]', '2014-08-09' ],
-      [ '[Dim 10. Août]', '2014-08-10' ],
-      [ '[Sam 31. Janv]', '2015-01-31' ],
-      [ '[Sam 7. Févr]', '2015-02-07' ],
-      [ '[Sam 31. Jan]', '2015-01-31' ],
-      [ '[Sam 7. Fév]', '2015-02-07' ],
-    ]
-
-    assert_dates( data, start_at: DateTime.new( 2014, 8, 1 ) )
-  end
-
-  def test_date_en
-    data = [
-      [ 'Jun/12 2011 14:00', '2011-06-12 14:00' ],
-      [ 'Oct/12 2013 16:00', '2013-10-12 16:00' ],
-
-      [ 'Jan/26 2011',       '2011-01-26' ],
-      [ 'Jan/26 2011',       '2011-01-26 12:00' ],
-
-      [ 'Jan/26',            '2013-01-26' ],
-      [ 'Jan/26',            '2013-01-26 12:00' ],
-      [ '26 January',        '2013-01-26' ],
-      [ '26 January',        '2013-01-26 12:00' ],
-
-      [ 'Jun/13',            '2013-06-13' ],
-      [ 'Jun/13',            '2013-06-13 12:00' ],
-      [ '13 June',           '2013-06-13' ],
-      [ '13 June',           '2013-06-13 12:00' ]
-    ]
-    
-    assert_dates( data, start_at: DateTime.new( 2013, 1, 1 ) )
-  end
-
-
-private
-
-  def assert_dates( data, opts )
-    data.each do |rec|
-      line = rec[0]
-      str  = rec[1]
-      if str.index( ':' )
-        assert_datetime( DateTime.strptime( str, '%Y-%m-%d %H:%M' ), parse_date( line, opts ))
-      else
-        assert_date( DateTime.strptime( str, '%Y-%m-%d' ), parse_date( line, opts ))
-      end
-    end  
-  end
-
-  ## todo: check if assert_datetime or assert_date exist already? what is the best practice to check dates ???
-  def assert_date( exp, act )
-    assert_equal exp.year,  act.year
-    assert_equal exp.month, act.month 
-    assert_equal exp.day,   act.day
-  end
-
-  def assert_time( exp, act )
-    assert_equal exp.hour, act.hour
-    assert_equal exp.min,  act.min
-  end
-
-  def assert_datetime( exp, act )
-    assert_date( exp, act )
-    assert_time( exp, act )
-  end
-
-
-  def parse_date( line, opts={} )
-     # e.g. lets you pass in opts[:start_at] ???
-     finder = SportDb::DateFinder.new
-     finder.find!( line, opts )
-  end
-
-end # class TestScores

data/test/test_lang.rb

@@ -1,130 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_lang.rb
-#  or better
-#     rake -I ./lib test
-
-require 'helper'
-
-class TestLang < MiniTest::Test
-
-  def test_getters
-
-     lang = SportDb.lang
-     lang.lang = 'en'
-
-     group = 'Group'
-
-     round = 'Round|Matchday|Week'
-     round << '|Round of 32|Last 32'
-     round << '|Round of 16|Last 16|8th finals'
-     round << '|Quarterfinals|Quarter-finals|Quarters|Quarterfinal|Last 8'
-     round << '|Semifinals|Semi-finals|Semis|Last 4'
-     round << '|Fifth place match|Fifth place|5th place match|5th place final|5th place|Match for fifth place|Match for 5th place'
-     round << '|Third place match|Third-place match|Third place|3rd place match|3rd place final|3rd place|Match for third place|Match for 3rd place|Third-place play-off|Third place play-off'
-     round << '|Final|Finals'
-     round << '|Playoff|Playoffs|Play-off|Play-offs|Play-off for quarter-finals'
-
-     knockout_round = 'Round of 32|Last 32'
-     knockout_round << '|Round of 16|Last 16|8th finals'
-     knockout_round << '|Quarterfinals|Quarter-finals|Quarters|Quarterfinal|Last 8'
-     knockout_round << '|Semifinals|Semi-finals|Semis|Last 4'
-     knockout_round << '|Fifth place match|Fifth place|5th place match|5th place final|5th place|Match for fifth place|Match for 5th place'
-     knockout_round << '|Third place match|Third-place match|Third place|3rd place match|3rd place final|3rd place|Match for third place|Match for 3rd place|Third-place play-off|Third place play-off'
-     knockout_round << '|Final|Finals'
-     knockout_round << '|Playoff|Playoffs|Play-off|Play-offs|Play-off for quarter-finals'
-
-     assert_equal group, lang.group
-     assert_equal round, lang.round
-     assert_equal knockout_round, lang.knockout_round
-
-     # NB: call twice to test caching with ||=
-     assert_equal group, lang.group
-     assert_equal round, lang.round
-     assert_equal knockout_round, lang.knockout_round
-
-  end
-  
-  def test_getters_de
-     lang = SportDb.lang
-     lang.lang = 'de'
-
-     group = 'Gruppe'
-
-     round = 'Spieltag|Runde'
-     round << '|Sechzehntelfinale|1/16 Finale'
-     round << '|Achtelfinale|1/8 Finale'
-     round << '|Viertelfinale|1/4 Finale'
-     round << '|Halbfinale|Semifinale|1/2 Finale'
-     round << '|Spiel um Platz 5'
-     round << '|Spiel um Platz 3'
-     round << '|Finale|Endspiel'
-
-     knockout_round = 'Sechzehntelfinale|1/16 Finale'
-     knockout_round << '|Achtelfinale|1/8 Finale'
-     knockout_round << '|Viertelfinale|1/4 Finale'
-     knockout_round << '|Halbfinale|Semifinale|1/2 Finale'
-     knockout_round << '|Spiel um Platz 5'
-     knockout_round << '|Spiel um Platz 3'
-     knockout_round << '|Finale|Endspiel'
-
-
-     assert_equal group, lang.group
-     assert_equal round, lang.round
-     assert_equal knockout_round, lang.knockout_round
-
-     # NB: call twice to test caching with ||=
-
-     assert_equal group, lang.group
-     assert_equal round, lang.round
-     assert_equal knockout_round, lang.knockout_round
-  end
-
-  def test_regex_knockout_round
-     lang = SportDb.lang
-     lang.lang = 'en'
-
-     lines = [
-      '(4) Quarter-finals',
-      '(5) Semi-finals',
-      '(6) Final',
-      '(1) Play-off 1st Leg // 11–15 October',
-      '(2) Play-off 2nd Leg // 15-19 November',
-      '(1) Play-off for quarter-finals',
-      '(4) Match for fifth place',
-      '(5) Match for third place',
-      ## check for ALL UPCASE too
-      '(4) QUARTER-FINALS',
-      '(5) SEMI-FINALS',
-      '(6) FINAL'
-     ]
-     
-     lines.each do |line|
-       assert( line =~ lang.regex_knockout_round )
-     end
-
-  end
-  
-  def test_regex_knockout_round_de
-    lang = SportDb.lang
-    lang.lang = 'de'
-
-    lines = [
-      '(1)  Achtelfinale              // Di+Mi 14.+15. & 21.+22. Feb 2012',
-      '(2)  Achtelfinale Rückspiele   // Di+Mi 6.+7. & 13.+14. März 2012',
-      '(3)  Viertelfinale             // Di+Mi 27.+28. März 2012',
-      '(4)  Viertelfinale Rückspiele  // Di+Mi 3.+4.   April 2012',
-      '(5)  Halbfinale                // Di+Mi 17.+18. April 2012',
-      '(6)  Halbfinale Rückspiele     // Di+Mi 24.+25. April 2012',
-      '(7)  Finale                    // Sa 19. Mai 2012'
-    ]
-
-     lines.each do |line|
-       assert( line =~ lang.regex_knockout_round )
-     end
-
-  end
-
-end # class TestLang