worldfootball 0.1.1 → 0.2.0

data/lib/worldfootball/leagues.rb

@@ -1,200 +1,148 @@
 
 
-require_relative 'leagues/europe'
-require_relative 'leagues/north_america'
-require_relative 'leagues/south_america'
-require_relative 'leagues/pacific'
-require_relative 'leagues/asia'
+module Worldfootball
+class LeagueConfig
+def initialize
+  @table = {}
+end
 
+class LeagueItem  # nested inside LeagueConfig
+  attr_reader :key, :slug
 
-module Worldfootball
+  def initialize( key:, slug: )
+    @key  = key
+    @slug = slug
 
-LEAGUES = [LEAGUES_EUROPE,
-           LEAGUES_NORTH_AMERICA,
-           LEAGUES_SOUTH_AMERICA,
-           LEAGUES_PACIFIC,
-           LEAGUES_ASIA].reduce({}) { |mem,h| mem.merge!( h ); mem }
+    @seasons  = nil
+  end
 
 
-class League
-    def initialize( key, data )
-      @key  = key
-      ## @data = data
+  def seasons
+     ## auto-(down)load on first request
 
-      @pages       = data[:pages]
-      @season_proc = data[:season] || ->(season) { nil }
-    end
+     @seasons ||= begin
+       ### todo/fix:
+       ##     use from cache if not older than 1 (or 5/10?) hour(s) or such
+       ##           why? why not?
+       Worldfootball::Metal.download_schedule( @slug )
+       page = Worldfootball::Page::Schedule.from_cache( @slug )
 
-    def key()   @key; end
-
-    def pages( season: )
-      ## note: return for no stages / simple case - just a string
-      ##   and for the stages case ALWAYS an array (even if it has only one page (with stage))
-
-      if @pages.is_a?( String )
-        # assume always "simple/regular" format w/o stages
-        slug = @pages
-        { slug: fill_slug( slug, season: season ) }
-      else
-         ## check for league format / stages
-         ##   return array (of strings) or nil (for no stages - "simple" format)
-         indices = @season_proc.call( season )
-         if indices.nil?
-           puts "!! ERROR - no configuration found for season >#{season}< for league >#{@key}< found; sorry"
-           exit 1
-         elsif indices.is_a?( Integer )  ## single number - single/regular format w/o stage
-          # note: starting with 0 (always use idx-1) !!!
-           slug = if @pages.is_a?( Array )
-                    @pages[indices-1]
-                  else ## assume hash (and key is page slug)
-                    @pages.keys[indices-1]
-                  end
-           { slug: fill_slug( slug, season: season ) }
-         else  ## assume regular case - array of integers
-           recs = []
-           indices.each do |idx|
-              slug = key = @pages.keys[idx-1]
-              recs << { slug:  fill_slug( slug, season: season ),
-                        stage: @pages[key] }  ## note: include mapping for page to stage name!!
-           end
-           recs
-        end
-      end
-    end # pages
-
-
-    ######
-    # helper method
-    def fill_slug( slug, season: )
-      ## note: fill-in/check for place holders too
-      slug = if slug.index( '{season}' )
-               slug.sub( '{season}', season.to_path( :long ) )  ## e.g. 2010-2011
-             elsif slug.index( '{end_year}' )
-               slug.sub( '{end_year}', season.end_year.to_s )   ## e.g. 2011
-             else
-               ## assume convenience fallback - append regular season
-               "#{slug}-#{season.to_path( :long )}"
-            end
-
-      puts "  slug=>#{slug}<"
-
-      slug
-    end
-  end # class League
+     ## pp page.seasons
+=begin
+[{:text=>"2024/2025", :ref=>"aut-oefb-cup-2024-2025"},
+ {:text=>"2023/2024", :ref=>"aut-oefb-cup-2023-2024"},
+ {:text=>"2022/2023", :ref=>"aut-oefb-cup-2022-2023"},
+ {:text=>"2021/2022", :ref=>"aut-oefb-cup-2021-2022"},
+=end
 
+     recs = page.seasons.map { |rec| [rec[:text], rec[:ref]] }
+     pp recs
+     puts "  #{recs.size} record(s)"
+     recs
 
+     seasons = {}
+     ## generate lookup table by season
+     recs.each do |text,slug|
 
-  def self.find_league( key )  ## league info lookup
-    data = LEAGUES[ key ]
-    if data.nil?
-      puts "!! ERROR - no league found for >#{key}<; add to leagues tables"
-      exit 1
-    end
-    League.new( key, data )   ## use a convenience wrapper for now
-  end
+##
+##  fix upstream?? - allow multi-year seasons? why? why not?
+##     for now ignore special case and collect more real-world cases/samples
+##             if possible
+##      ["2019-2021 Playoffs", "regionalliga-bayern-2019-2021-playoffs"],
+##      ["2019-2021", "regionalliga-bayern-2019-2021"],
+##
 
 
+        season, stage = text.split( ' ', 2 )
 
-### "reverse" lookup by page - returns league AND season
-##  note: "blind" season template para - might be season or start_year etc.
-##   e.g.  {season} or {start_year} becomes {}
+## todo/fix: add a waring here and auto log to logs.txt!!!!
+        next if season == '2019-2021'
 
-PAGE_VAR_RE = /{
-                [^}]+
-               }/x
+        season = Season.parse( season )
 
+        seasons[ season.key ] ||= []
+        seasons[ season.key] << [slug, stage]
+     end
+     seasons
+    end
+    @seasons
+  end
 
-def self.norm_slug( slug )
-    ## assume convenience fallback - append regular season
-    slug.index( '{' ) ? slug : "#{slug}-{season}"
-end
 
-PAGES ||=
- LEAGUES.reduce( {} ) do |pages, (key, data)|
-                                     if data[:pages].is_a?( String )
-                                       slug = data[:pages]
-                                       slug = Worldfootball.norm_slug( slug )
-                                       pages[ slug.sub( PAGE_VAR_RE, '{}') ] = { league: key, slug: slug }
-                                     elsif data[:pages].is_a?( Array )
-                                       data[:pages].each do |slug|
-                                        slug = Worldfootball.norm_slug( slug )
-                                         pages[ slug.sub( PAGE_VAR_RE, '{}') ] = { league: key, slug: slug }
-                                       end
-                                        ## elsif data[:pages].nil?
-                                        ## todo/fix: missing pages!!!
-                                     else ## assume hash
-                                      ## add stage to pages too - why? why not?
-                                       data[:pages].each do |slug, stage|
-                                         slug = Worldfootball.norm_slug( slug )
-                                         pages[ slug.sub( PAGE_VAR_RE, '{}') ] = { league: key, slug: slug, stage: stage }
-                                       end
-                                     end
-                                     pages
-                                    end
-
-# e.g. 2000 or 2000-2001
-SEASON_RE = /[0-9]{4}
-              (?:
-                -[0-9]{4}
-              )?
-            /x
-
-
-  def self.find_page!( slug )
-    page = find_page( slug )
-    if page.nil?
-      puts "!! ERROR: no mapping for page >#{slug}< found; sorry"
-
-      season_str = nil
-      norm = slug.sub( SEASON_RE ) do |match|  ## replace season with var placeholder {}
-                season_str = match   ## keep reference to season str
-                '{}'  ## replace with {}
-              end
-
-      puts "   season:      >#{season_str}<"
-      puts "   slug (norm): >#{norm}<"
-      puts
-      ## pp PAGES
-      exit 1
+  def pages!( season: )
+    pages = pages( season: season )
+    if pages.nil?
+       puts "!! ERROR - no season #{season} found for #{key}; seasons incl:"
+       puts seasons.keys.join( ', ' )
+       puts "  #{seasons.keys.size} season(s)"
+       exit 1
     end
-    page
+    pages
   end
 
+  def pages( season: )
+    ### lookup league pages/slugs by season
+    season = Season( season )
+
+    ## note: assume reverse chronological order
+    ##           reverse here
+    ##  e.g.
+    ##   [["aut-bundesliga-2023-2024-qualifikationsgruppe", "Qualifikationsgruppe"],
+    ##    ["aut-bundesliga-2023-2024-playoff", "Playoff"],
+    ##    ["aut-bundesliga-2023-2024-meistergruppe", "Meistergruppe"],
+    ##    ["aut-bundesliga-2023-2024", nil]]
+    ##   =>
+    ##   [["aut-bundesliga-2023-2024", nil],
+    ##     ["aut-bundesliga-2023-2024-meistergruppe", "Meistergruppe"],
+    ##     ["aut-bundesliga-2023-2024-playoff", "Playoff"],
+    ##     ["aut-bundesliga-2023-2024-qualifikationsgruppe", "Qualifikationsgruppe"]]
+    recs = seasons[season.key]
+    recs ?  recs.reverse : nil
+  end
+end # class LeagueItem
 
 
-  def self.find_page( slug )
-    ## return league key and season
-    season_str = nil
-    norm = slug.sub( SEASON_RE ) do |match|  ## replace season with var placeholder {}
-              season_str = match   ## keep reference to season str
-              '{}'  ## replace with {}
-            end
+def add( recs )
+   recs.each do |rec|
+      @table[ rec['key'] ] = LeagueItem.new( key: rec['key'],
+                                             slug: rec['slug'] )
+   end
+end
+
+def [](key)  @table[key.to_s.downcase]; end
+def keys()   @table.keys; end
+def size()   @table.size; end
+end # class LeagueConfig
 
-    if season_str.nil?
-      puts "!! ERROR: no season found in page slug >#{slug}<; sorry"
-      exit 1
-    end
 
-    rec = PAGES[ norm ]
-    return nil  if rec.nil?
-
-
-    league_key = rec[:league]
-    slug_tmpl  = rec[:slug]
-    season = if slug_tmpl.index( '{start_year}' )
-               ## todo/check - season_str must be year (e.g. 2020 or such and NOT 2020-2021)
-               Season( "#{season_str.to_i}-#{season_str.to_i+1}" )
-             elsif slug_tmpl.index( '{end_year}' )
-               ## todo/check - season_str must be year (e.g. 2020 or such and NOT 2020-2021)
-               Season( "#{season_str.to_i-1}-#{season_str.to_i}" )
-             else  ## assume "regular" seasson - pass through as is
-               Season( season_str )
-             end
-
-    ## return hash table / record
-    { league: league_key,
-      season: season.key }
+LEAGUES = LeagueConfig.new
+['leagues_europe',
+ 'leagues_asia',].each do |name|
+  recs = read_csv( "#{Worldfootball.root}/config/#{name}.csv" )
+  pp recs
+  puts "   #{recs.size} league(s) in #{name}"
+  LEAGUES.add( recs )
+end
+
+
+###########
+#  (strict) lookup convenience helpers with error reporting
+#              AND abort if no lookup found
+def self.find_league!( league_code )
+  league = LEAGUES[ league_code ]
+  if league.nil?
+     puts "!! ERROR - no config found for #{league_code}; leagues incl:"
+     puts LEAGUES.keys.join( ', ' )
+     puts "  #{LEAGUES.size} leagues(s)"
+     exit 1
   end
+  league
+end
 
+def self.find_league_pages!( league:, season: )
+  league = find_league!( league )
+  pages  = league.pages!( season: season )
+  pages
+end
+end  # module Worldfootball
 
-end # module Worldfootball

data/lib/worldfootball/mods.rb

@@ -16,6 +16,9 @@ end
 
 
 
+MODS = {}
+
+=begin
 MODS = {
  'at' => {
     ## AT 1
@@ -42,7 +45,7 @@ MODS = {
    'Wellington Phoenix (R)' => 'Wellington Phoenix Reserves',
   },
 }
-
+=end
 
 
 ## fix/patch known score format errors in at/de cups
@@ -65,7 +68,11 @@ SCORE_ERRORS = {
     ## 2010/11
     '2010-11-24' => [ 'Ergotelis',    'Olympiakos Piräus', ['0-2 (0-0, 0-0, 0-0)', '0-2 (0-0)']],
     '2010-11-28' => [ 'Panserraikos', 'Aris Saloniki',     ['1-0 (1-0, 0-0, 0-0)', '1-0 (1-0)']],
-  }
+  },
+  'at.cup' => {
+     ## 2023/24
+     '2023-07-22' => [ 'SV Leobendorf', 'SV Horn', ['3-2 (2-0, 2-2, 3-2) n.V.', '3-2 (2-0, 2-2) n.V.']], 
+  }, 
 }
 
 

data/lib/worldfootball/page.rb

@@ -102,5 +102,14 @@ def assert( cond, msg )
   end
 end
 
+
+def log( msg )  ### append to log
+  File.open( './logs.txt', 'a:utf-8' ) do |f|
+    f.write( msg )
+    f.write( "\n" )
+  end
+end
+
+
 end # class Page
 end # module Worldfootball

data/lib/worldfootball/page_schedule.rb

@@ -24,6 +24,8 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
  # puts table.class.name  #=> Nokogiri::XML::Element
  # puts table.text
 
+ assert( table, 'no table.standard_tabelle found in schedule page!!')
+
  trs   = table.css( 'tr' )
  # puts trs.size
  i = 0
@@ -34,6 +36,9 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
  rows = []
 
 
+
+ trs.each do |tr|
+
 ## ghost trs? what for? see for an example in bra
 ##    check for style display:none - why? why not?
 ##
@@ -45,10 +50,15 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
 ##          </td>
 ##          <td colspan="2"></td>
 ##        </tr>
-
-
- trs.each do |tr|
-
+  ##
+  #   <tr class="e2-parent" data-liga_id="530" data-gs_match_id="10259222" 
+  #       style="display:none;">
+  ##    <td colspan="2"></td>
+  ##    <td colspan="3">
+  ##      <span class="e2" data-liga_id="530" data-gs_match_id="10259222"></span>
+  ##    </td>
+  ##    <td colspan="2"></td>
+  ##  </tr>
    if tr['style'] && tr['style'].index( 'display') &&
                      tr['style'].index( 'none')
      puts "!! WARN: skipping ghost line >#{tr.text.strip}<"
@@ -58,6 +68,15 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
 
    i += 1
 
+    ## puts "[debug] row #{i} >#{tr.text.strip}<" 
+
+    ### note - assume for now match lines use tds
+    ##            and round lines use ths (NOT tds)!!
+    ##  e.g. <th colspan="7">8. Spieltag</th>
+
+    ths =  tr.css( 'th' )
+    tds =  tr.css( 'td' )
+    
    if tr.text.strip =~ /Spieltag/ ||
       tr.text.strip =~ /[1-9]\.[ ]Runde|
                            Qual\.[ ][1-9]\.[ ]Runde|  # see EL or CL Quali
@@ -68,8 +87,26 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
                            Halbfinale|
                            Finale|
                            Gruppe[ ][A-Z]|    # see CL
-                           Playoffs           # see EL Quali
+                           Gruppe[ ][1-9]|    # see slv-primera-division-2020-2021-clausura_3
+                           Playoffs|           # see EL Quali
+                           Entscheidungsspiel|   # see Serie A 2022-23 Entscheidung Abstieg
+                           Spiele|                # see Serie A 1960-61 Relegation
+                           3\.[ ]Platz|      # see bra-serie-a-2000-yellow-module-playoffs
+                           Spiel[ ]um[ ]Platz[ ]3|  # see campeonato-2009-cuadrangulares-deportivo-cuenca-cs-emelec
+                           Relegation|     # see egy-premiership-2013-2014-abstiegsplayoff    
+                           Copa[ ]Libertadores|  # see ecu-campeonato-2012-segunda-etapa-playoffs 
+                           Copa[ ]Sudamericana|  # see campeonato-2012-liguilla-final-playoffs-cs-emelec-ldu-quito
+                           Repechaje|  # see nca-liga-primera-2023-2024-clausura-playoffs 
+                           Final[ ]de[ ]Grupos|   # see hon-liga-nacional-2020-2021-clausura-playoffs  
+                           Gran[ ]Final|   # see liga-nacional-2020-2021-apertura-playoffs-finale-olimpia-motagua
+                           Finalrunde|  # see hon-liga-nacional-2019-2020-apertura-pentagonal
+                           Zona[ ]A|    # see gua-liga-nacional-2020-2021-clausura      
+                           Zona[ ]B|    # see liga-nacional-2020-2021-clausura-zona-a-comunicaciones-deportivo-malacateco    
+                           Interzone|    # see liga-nacional-2020-2021-clausura-zona-b-achuapa-sanarate
+                           Final[ ]Segunda[ ]Ronda|    # see crc-primera-division-2018-2019-apertura-playoffs
+                           Quadrangular      # see crc-primera-division-2016-2017-verano-playoffs
                            /x
+                          
      puts
      print '[%03d] ' % i
      ## print squish( tr.text )
@@ -77,8 +114,14 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
      print "\n"
 
      last_round = tr.text.strip
+   elsif ths.count > 0 && 
+         tds.count == 0
+       ## check for round NOT yet configured!!!
+       puts "!! WARN: found unregistered round line >#{tr.text.strip}<"
+       log( "!! WARN: found unregistered round line >#{tr.text.strip}< in page #{title}" )
+
+       last_round = tr.text.strip
    else   ## assume table row (tr) is match line
-     tds = tr.css( 'td' )
 
      date_str  = squish( tds[0].text )
      time_str  = squish( tds[1].text )
@@ -164,12 +207,21 @@ class Schedule < Page  ## note: use nested class for now - why? why not?
      score_str = score_str.gsub( ':', '-' )
 
      ## convert date from 25.10.2019 to 2019-25-10
-     date     = Date.strptime( date_str, '%d.%m.%Y' )
+
+     ## special case for '00.00.0000'
+     ##   CANNOT parse
+     ##   use empty date - why? why not?
+
+     date     = if date_str == '00.00.0000'
+                  nil
+                else 
+                  Date.strptime( date_str, '%d.%m.%Y' )
+                end
 
      ## note: keep structure flat for now
      ##        (AND not nested e.g. team:{text:,ref:}) - why? why not?
      rows << { round:      last_round,
-               date:       date.strftime( '%Y-%m-%d' ),
+               date:       date ? date.strftime( '%Y-%m-%d' ) : '',
                time:       time_str,
                team1:      team1_str,
                team1_ref:  team1_ref,

data/lib/worldfootball/vacuum.rb

@@ -6,13 +6,15 @@ MAX_HEADERS = [
 'Round',
 'Date',
 'Time',
+'Timezone',
 'Team 1',
 'FT',
 'HT',
 'Team 2',
 'ET',
 'P',
-'Comments']    ## e.g. awarded, cancelled/canceled, etc.
+'Comments',    ## e.g. awarded, cancelled/canceled, etc.
+'UTC']
 
 MIN_HEADERS = [   ## always keep even if all empty
 'Date',

data/lib/worldfootball/version.rb

@@ -1,8 +1,8 @@
 
 module Worldfootball
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
-  MINOR = 1
-  PATCH = 1
+  MINOR = 2
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/worldfootball.rb

@@ -1,34 +1,30 @@
 ## 3rd party (our own)
-require 'season/formats'   ## add season support
-require 'webget'           ## incl. webget, webcache, webclient, etc.
-
-require 'cocos'
-
-## 3rd party
+require 'football/timezones'  ## note - pulls in season/formats, cocos & tzinfo
+require 'webget'              ## incl. webget, webcache, webclient, etc.
 require 'nokogiri'
 
 
-
 ###
 # our own code
 require_relative 'worldfootball/version'
 require_relative 'worldfootball/leagues'
+
+require_relative 'worldfootball/config'    ## rename to setup/timezones/layouts or such?
 require_relative 'worldfootball/download'
 require_relative 'worldfootball/page'
 require_relative 'worldfootball/page_schedule'
 require_relative 'worldfootball/page_report'
+require_relative 'worldfootball/cache'
 
 
 require_relative 'worldfootball/mods'
 require_relative 'worldfootball/vacuum'
 require_relative 'worldfootball/build'
+require_relative 'worldfootball/build-parse_score'
 require_relative 'worldfootball/convert'
 require_relative 'worldfootball/convert_reports'
 
 
-require_relative 'worldfootball/generator'
-
-
 
 module Worldfootball
 
@@ -55,12 +51,6 @@ end   # module Worldfootball
 
 
 
-### for processing tool
-##   (auto-)add sportdb/writer  (pulls in sportdb/catalogs and gitti)
-#  require 'sportdb/writers'
-
-
-
 
 puts Worldfootball.banner    ## say hello
 

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: worldfootball
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-07-07 00:00:00.000000000 Z
+date: 2024-09-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: season-formats
+  name: football-timezones
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -52,20 +52,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: cocos
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -116,24 +102,17 @@ files:
 - README.md
 - Rakefile
 - bin/wfb
+- config/leagues_asia.csv
+- config/leagues_europe.csv
 - lib/worldfootball.rb
+- lib/worldfootball/build-parse_score.rb
 - lib/worldfootball/build.rb
+- lib/worldfootball/cache.rb
+- lib/worldfootball/config.rb
 - lib/worldfootball/convert.rb
 - lib/worldfootball/convert_reports.rb
 - lib/worldfootball/download.rb
-- lib/worldfootball/generator.rb
 - lib/worldfootball/leagues.rb
-- lib/worldfootball/leagues/asia.rb
-- lib/worldfootball/leagues/europe--british_isles.rb
-- lib/worldfootball/leagues/europe--central.rb
-- lib/worldfootball/leagues/europe--eastern.rb
-- lib/worldfootball/leagues/europe--northern.rb
-- lib/worldfootball/leagues/europe--southern.rb
-- lib/worldfootball/leagues/europe--western.rb
-- lib/worldfootball/leagues/europe.rb
-- lib/worldfootball/leagues/north_america.rb
-- lib/worldfootball/leagues/pacific.rb
-- lib/worldfootball/leagues/south_america.rb
 - lib/worldfootball/mods.rb
 - lib/worldfootball/page.rb
 - lib/worldfootball/page_report.rb
@@ -154,7 +133,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.2.2
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="