worldfootball 0.1.2 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 99623775fef73f0837946ba44625a572bbe5fee3a64aa6aa9a2f6f79702a0d01
-  data.tar.gz: 1ed058214bcca9fad1aac5b205e73c101a79a14ef979dbdee37c3a784fe03460
+  metadata.gz: 78c749dd421814981a58c87104761091471a4ffe26a8261df132d77bca5ffb8f
+  data.tar.gz: 23a146156f4e38f0e92ef9689ed6a965b044e6ae2e489cffb5da56883c7e6e7a
 SHA512:
-  metadata.gz: 2b2ec98872c3cf9ae5b9f39cd6ac5bcd205ea35a4ea1282a575f8ea9256226f4395c4021b57417e6d77db38b474127b35cd2836aee3d381a8138b318cb588be0
-  data.tar.gz: dff2a077af11f10c6c0f1e923e42710b04b198a5c7a7677363a25bfa7e508ec56867d64c2df8f907a51584613b0d86a8f246f6727755fa1dfa1e6c1135962877
+  metadata.gz: 64e28d3ffdb1056f9db34459ca7d23ba2116a9aeb8130d3b81a310590fc0ad5079eff635664d153a2798b5e9765a10e7508311d0c899b82c1c59f98bedecc60c
+  data.tar.gz: 52ef6922b2b1e735a67b9aae8ecd409c3314aa3d2a48b056d2be2d272b85c4e48735e983dda88630c461a25354a5f6f9cb64eb0cb4d6f642cf873263da3af954

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.1.2
+### 0.2.0
 
 ### 0.0.1 / 2024-07-04
 

data/Manifest.txt

@@ -3,7 +3,8 @@ Manifest.txt
 README.md
 Rakefile
 bin/wfb
-config/leagues.csv
+config/leagues_asia.csv
+config/leagues_europe.csv
 lib/worldfootball.rb
 lib/worldfootball/build-parse_score.rb
 lib/worldfootball/build.rb

data/Rakefile

@@ -18,11 +18,9 @@ Hoe.spec 'worldfootball' do
   self.history_file = 'CHANGELOG.md'
 
   self.extra_deps = [
-    ## ['tzinfo'],
-    ['season-formats'],
+    ['football-timezones'],
     ['webget'],
     ['nokogiri'],
-    ['cocos'],  ## later pull in with sportsdb-writers
   ]
 
   self.licenses = ['Public Domain']

data/bin/wfb

@@ -15,7 +15,7 @@ Webcache.root =  if File.exist?( '/sports/cache' )
 
 ## convert (default) output directory
 Worldfootball.config.convert.out_dir = if File.exist?( '/sports/cache.wfb')
-                                           puts "   setting convert out_dir to >/sports/cache.wfb<"
+                                           puts "  setting convert out_dir to >/sports/cache.wfb<"
                                            '/sports/cache.wfb'
                                         else
                                            '.' ## use working dir
@@ -102,12 +102,16 @@ if opts[:dry]
 end
 
 
-season = Season( args[1] || '2024/25' )
+## note - default to latest season of league
+##              might be 2024/25 or 2024 or
+#                 for world cup 2022 or such
+season = Season( args[1] || league.seasons.keys[0] )
 
 pages = league.pages!( season: season )
 
 
 puts
+pp [league.key, season.key]
 pp pages
 puts "   #{pages.size} page(s)"
 

data/config/leagues_asia.csv

@@ -0,0 +1,6 @@
+key,   slug
+
+cn.1,   chn-super-league-2024
+jp.1,   jpn-j1-league-2024
+kr.1,   kor-k-league-1-2024
+

data/config/leagues_europe.csv

@@ -0,0 +1,75 @@
+key,         slug
+
+de.1,         bundesliga-2024-2025
+de.2,         2-bundesliga-2024-2025
+de.3,         3-liga-2024-2025
+de.4.bayern,  regionalliga-bayern-2024-2025
+de.cup,       dfb-pokal-2024-2025
+
+at.1,        aut-bundesliga-2024-2025
+at.2,        aut-2-liga-2024-2025
+at.3.o,      aut-regionalliga-ost-2024-2025
+at.cup,      aut-oefb-cup-2024-2025
+
+
+ch.1,        sui-super-league-2024-2025
+ch.2,        sui-challenge-league-2024-2025
+ch.cup,      sui-cup-2024-2025
+
+
+hu.1,       hun-nb-i-2024-2025
+
+cz.1,       cze-1-fotbalova-liga-2024-2025
+sk.1,       svk-super-liga-2024-2025
+
+pl.1,       pol-ekstraklasa-2024-2025
+
+
+
+eng.1,       eng-premier-league-2024-2025
+eng.2,       eng-championship-2024-2025
+eng.3,       eng-league-one-2024-2025
+eng.4,       eng-league-two-2024-2025
+eng.5,       eng-national-league-2024-2025
+eng.cup,     eng-fa-cup-2023-2024              ### update to 2024-2025 later!!!
+eng.cup.l,   eng-league-cup-2024-2025
+
+
+sco.1,       sco-premiership-2024-2025
+
+ie.1,        irl-premier-division-2024
+
+
+fr.1,       fra-ligue-1-2024-2025
+fr.2,       fra-ligue-2-2024-2025
+fr.cup,     fra-coupe-de-france-2023-2024     ### update to 2024-2025 later!!!
+
+
+lu.1,     lux-nationaldivision-2024-2025
+nl.1,     ned-eredivisie-2024-2025
+nl.2,     ned-eerste-divisie-2024-2025
+nl.cup,   ned-knvb-beker-2024-2025
+
+be.1,     bel-eerste-klasse-a-2024-2025
+be.2,     bel-eerste-klasse-b-2024-2025
+be.cup,   bel-beker-van-belgie-2024-2025
+
+
+it.1,     ita-serie-a-2024-2025
+it.2,     ita-serie-b-2024-2025
+it.cup,   ita-coppa-italia-2024-2025
+
+pt.1,     por-primeira-liga-2024-2025
+pt.2,     por-segunda-liga-2024-2025
+
+es.1,     esp-primera-division-2024-2025
+es.2,     esp-segunda-division-2024-2025
+es.cup,   esp-copa-del-rey-2023-2024        ##   update to 2024-2025 later!!!
+
+
+tr.1,    tur-sueperlig-2024-2025
+tr.2,    tur-1-lig-2024-2025
+
+gr.1,    gre-super-league-2024-2025
+
+hr.1,    cro-1-hnl-2024-2025

data/lib/worldfootball/build.rb

@@ -10,6 +10,8 @@ ROUND_TO_EN = {
   '5. Runde'      => 'Round 5',
   '6. Runde'      => 'Round 6',
   '7. Runde'      => 'Round 7',
+  '8. Runde'      => 'Round 8',
+  '9. Runde'      => 'Round 9',
   'Achtelfinale'  => 'Round of 16',
   'Viertelfinale' => 'Quarterfinals',
   'Halbfinale'    => 'Semifinals',
@@ -24,13 +26,16 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
    season = Season( season )  ## cast (ensure) season class (NOT string, integer, etc.)
 
    ## note: do NOT pass in league struct! pass in key (string)
-   raise ArgumentError, "league key as string expected"  unless league.is_a?(String)  
+   raise ArgumentError, "league key as string expected"  unless league.is_a?(String)
 
    print "  #{rows.size} row(s) - Worldfootball.build #{league} #{season}"
    print " - #{stage}" unless stage.empty?
    print "\n"
 
 
+   zone = find_zone!( league: league, season: season )
+
+
    ## note: use only first part from key for lookup
    ##    e.g. at.1  => at
    ##         eng.1 => eng
@@ -61,10 +66,10 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
       exit 1
     end
     print "\n"
-   
-  ## note - must start line e.g. 
-  ##            do NOT match => Qual. 1. Runde  (1. Runde)!!!   
-  elsif row[:round] =~ /^(    
+
+  ## note - must start line e.g.
+  ##            do NOT match => Qual. 1. Runde  (1. Runde)!!!
+  elsif row[:round] =~ /^(
                           [1-9]\.[ ]Runde|
                           Achtelfinale|
                           Viertelfinale|
@@ -103,12 +108,10 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
     team2_str = row[:team2]
     score_str = row[:score]
 
-    ## convert date from string e.g. 2019-25-10
-    date = Date.strptime( date_str, '%Y-%m-%d' )
 
 
     ### check for score_error; first (step 1) lookup by date
-    score_error = score_errors[ date.strftime('%Y-%m-%d') ]
+    score_error = score_errors[ date_str ]
     if score_error
       if team1_str == score_error[0] &&
          team2_str == score_error[1]
@@ -145,17 +148,44 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
     ht, ft, et, pen, comments = parse_score( score_str )
 
 
+   ###################
+   ### calculate date & times
+   ## convert date from string e.g. 2019-25-10
+   ## date = Date.strptime( date_str, '%Y-%m-%d' )
+
+   if time_str.nil? || time_str.empty?
+       ## no time
+       ##   assume  00:00:00T
+       time_str     = ''
+       timezone     = ''
+       utc          = ''
+   else
+      ## note - assume central european (summer) time (cet/cest) - UTC+1 or UTC+2
+      cet = CET.strptime( "#{date_str} #{time_str}", '%Y-%m-%d %H:%M' )
+
+      utc = cet.getutc   ## convert to utc
+      local =  zone.to_local( utc )  # convert to local via utc
+      ## overwrite old with local
+      date_str = local.strftime( '%Y-%m-%d' )
+      time_str = local.strftime( '%H:%M' )
+      timezone = local.strftime( '%Z/%z' )
+      utc      = utc.strftime( '%Y-%m-%dT%H:%MZ' )
+   end
+
+
     recs <<  [stage,
               round,
-              date.strftime( '%Y-%m-%d' ),
+              date_str,
               time_str,
+              timezone,
               team1_str,
               ft,
               ht,
               team2_str,
               et,              # extra: incl. extra time
               pen,             # extra: incl. penalties
-              comments]
+              comments,
+              utc]
    end  # each row
    recs
 end  # build

data/lib/worldfootball/config.rb

@@ -1,146 +1,11 @@
 module Worldfootball
 
-#################
-# todo/fix -  use timezone instead of offset !!!
-#  e.g
-=begin
-   TIMEZONES = {
-  'eng.1' => 'Europe/London',
-  'eng.2' => 'Europe/London',
-
-  'es.1'  => 'Europe/Madrid',
-
-  'de.1'  => 'Europe/Berlin',
-  'fr.1'  => 'Europe/Paris',
-  'it.1'  => 'Europe/Rome',
-  'nl.1'  => 'Europe/Amsterdam',
-
-  'pt.1'  => 'Europe/Lisbon',
-
-  ## todo/fix - pt.1
-  ##  one team in madeira!!! check for different timezone??
-  ##  CD Nacional da Madeira
-
-  'br.1'  => 'America/Sao_Paulo',
-  ## todo/fix - brazil has 4 timezones
-  ##           really only two in use for clubs
-  ##             west and east (amazonas et al)
-  ##           for now use west for all - why? why not?
-}
-=end
-
-## todo - find "proper/classic" timezone ("winter time")
-
-##  Brasilia - Distrito Federal, Brasil  (GMT-3)  -- summer time?
-##  Ciudad de México, CDMX, México       (GMT-5)  -- summer time?
-##  Londres, Reino Unido (GMT+1)
-##   Madrid -- ?
-##   Lisboa -- ?
-##   Moskow -- ?
-##
-## todo/check - quick fix timezone offsets for leagues for now
-##   - find something better - why? why not?
-## note: assume time is in GMT/UTC+1  - PLUS SUMMERTIME!!!
-##        todo/fix - consider summertime before conversion too!!!
-
-
-OFFSETS = {
-
-  ## fix - change to gmt/utc offset
-  ##        if offset == 1 (GMT/UTC+1)
-  ##           do NOTHING (default date/timezone of pages)
-
-  'eng' => 0,
- # 'eng.1' => 0,
- # 'eng.2' => 0,
- # 'eng.3' => 0,
- # 'eng.4' => 0,
- # 'eng.5' => 0,
-
-  'ie'  =>  0,
-  'sco' =>  0,
-
-  'pt' => 0,
- # 'pt.1'  => 0,
- # 'pt.2'  => 0,
-
-  'fi' => 2, # +2
-  'gr' => 2, # +2
-  'ro' =>  2, # +2
-  'ua' =>  2, # +2
-
-  'ru' =>  3,   # +3
-  'tr'   => 3,  # +3 turkey time/moscow time
-
-
-  'us'      => -5,   # (gmt-5) new york
-
-  'mx'      => -6,
- # 'mx.1'    => -6,
- # 'mx.2'    => -6,
- # 'mx.3'    => -6,
- # 'mx.cup'  => -6,
-
-  'cr' => -6,    # gmt-6
-  'gt' => -6,    # gmt-6
-  'hn' => -6,    # gmt-6
-  'sv' => -6,    # gmt-6
-  'ni' => -6,    # gmt-6
-
-  'uy' =>  -3,     #   gmt-3
-  'pe' =>  -5,     #  gmt-5
-  'ec' =>  -5,     #  gmt-5
-  'co' =>  -5,     #  gmt-5
-  'bo' =>  -4,     #  gmt-4
-  'cl' =>  -4,     #  gmt-4
-
-  'br'  => -4,    # gmt-3  - change to -3?
- # 'br.1'  => -4,
-  'ar'   => -4,   # gmt-3  - change to -3?
- # 'ar.1'  => -4,
-
-
-  'eg' =>   3,  # +3  (gmt+3)
-  'jp' =>   9,  # +9  (gmt+9)
-  'cn' =>   7,  # +7  (gmt+7)
-
-
-   ## note - central european time (cet) - no need for date auto-fix
-   'at' => 1,
-   'de' => 1,
-   'ch' => 1,
-   'hu' => 1,
-    'cz' => 1,
-    'pl' => 1,
-    'nl' => 1,
-    'lu' => 1,
-    'be' => 1,
-    'dk' => 1,
-    'se' => 1,
-    'it' => 1,
-    'fr' => 1,
-    'es' => 1,
-    ##   see https://en.wikipedia.org/wiki/Time_in_Europe
-
-
-  ################
-  ## int'l tournaments
-  # 'uefa.cl'
-  # 'uefa.el'
-  'uefa.cl'   => 1,
-  'uefa.el'   => 1,
-
-  'concacaf.cl'  => -6,   ### use mx time
-  'copa.l'       => -4,    ### use brazil time
-}
-
 
 ####
 # config for slug to local basename / directories
 #   e.g.
 #     aut-bundesliga-2023-2024  =>  austria/2023-24/1_bundesliga.txt
 
-
 ## add (timezone) offset here too - why? why not?
 LEAGUE_SETUPS  = {
   ## note - for now auto-generate  path via name (downcased)

data/lib/worldfootball/convert.rb

@@ -37,9 +37,6 @@ def self.convert( league:, season: )
     end
 
 
-  recs = fix_dates( recs, league: league.key )
-
-
 ##   note:  sort matches by date before saving/writing!!!!
 ##     note: for now assume date in string in 1999-11-30 format (allows sort by "simple" a-z)
 ## note: assume date is third column!!! (stage/round/date/...)
@@ -60,63 +57,5 @@ recs.each do |rec|
    puts "write #{out_path}..."
    write_csv( out_path, recs, headers: headers )
 end
-
-
-## helper to fix dates to use local timezone (and not utc/london time)
-def self.fix_dates( rows, league: )
-
-  ## check: rename (optional) offset to time_offset or such?
-  ##   note - retry with league_country (e.g. eng.1 => eng etc.)
-  offset = OFFSETS[ league ] ||
-           OFFSETS[ league.split('.')[0] ]
-
-  if offset.nil?
-      puts "!! ERROR - no timezone/offset configured for league >#{league}<:"
-      pp rows[0]  ## print first row too (for dates etc.)
-      exit 1
-  end
-
-
-   ## todo/check - rename offset to timezone
-   ##   or utc_offset or such - why? why not
-
-   ## note - assume central european time (cet) - GMT/UTC+1
-   ##           e.g. offset = 1 for cet (and 0 for gmt/london) etc.
-   diff_cet  =  offset-1
-
-   return rows   if diff_cet == 0   ## no need to convert if in cet
-
-   rows.map { |row| _fix_date( row, offset ) }
-end
-
-
-def self._fix_date( row, offset )
-  ## note: time (column) required for fix
-  return row    if row[3].nil? || row[3].empty?
-
-  ## note - assume central european time (cet) - GMT/UTC+1
-  diff_cet  =  offset-1
-
-  return row   if diff_cet == 0
-
-
-
-  col = row[2]
-  if col =~ /^\d{4}-\d{2}-\d{2}$/
-    date_fmt = '%Y-%m-%d'   # e.g. 2002-08-17
-  else
-    puts "!!! ERROR - wrong (unknown) date format >>#{col}<<; cannot continue; fix it; sorry"
-    ## todo/fix: add to errors/warns list - why? why not?
-    exit 1
-  end
-
-  date = DateTime.strptime( "#{row[2]} #{row[3]}", "#{date_fmt} %H:%M" )
-  ## NOTE - MUST be -7/24.0!!!! or such to work
-  date = date + (diff_cet/24.0)
-
-  row[2] = date.strftime( date_fmt )  ## overwrite "old"
-  row[3] = date.strftime( '%H:%M' )
-  row   ## return row for possible pipelining - why? why not?
-end
-
 end # module Worldfootball
+

data/lib/worldfootball/leagues.rb

@@ -73,7 +73,7 @@ class LeagueItem  # nested inside LeagueConfig
     pages = pages( season: season )
     if pages.nil?
        puts "!! ERROR - no season #{season} found for #{key}; seasons incl:"
-       pp seasons.keys
+       puts seasons.keys.join( ', ' )
        puts "  #{seasons.keys.size} season(s)"
        exit 1
     end
@@ -116,11 +116,13 @@ end # class LeagueConfig
 
 
 LEAGUES = LeagueConfig.new
-recs = read_csv( "#{Worldfootball.root}/config/leagues.csv" )
-pp recs
-puts "   #{recs.size} league(s)"
-LEAGUES.add( recs )
-
+['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
 
 
 ###########
@@ -130,7 +132,7 @@ def self.find_league!( league_code )
   league = LEAGUES[ league_code ]
   if league.nil?
      puts "!! ERROR - no config found for #{league_code}; leagues incl:"
-     pp LEAGUES.keys
+     puts LEAGUES.keys.join( ', ' )
      puts "  #{LEAGUES.size} leagues(s)"
      exit 1
   end

data/lib/worldfootball/page.rb

@@ -106,7 +106,7 @@ end
 def log( msg )  ### append to log
   File.open( './logs.txt', 'a:utf-8' ) do |f|
     f.write( msg )
-    f.write( "\n" ) 
+    f.write( "\n" )
   end
 end
 

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 = 2
+  MINOR = 2
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/worldfootball.rb

@@ -1,18 +1,14 @@
 ## 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'

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: worldfootball
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-09 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
@@ -116,7 +102,8 @@ files:
 - README.md
 - Rakefile
 - bin/wfb
-- config/leagues.csv
+- config/leagues_asia.csv
+- config/leagues_europe.csv
 - lib/worldfootball.rb
 - lib/worldfootball/build-parse_score.rb
 - lib/worldfootball/build.rb

data/config/leagues.csv

@@ -1,16 +0,0 @@
-key,         slug
-
-de.1,         bundesliga-2024-2025
-de.2,         2-bundesliga-2024-2025
-de.3,         3-liga-2024-2025
-de.4.bayern,  regionalliga-bayern-2024-2025
-de.cup,       dfb-pokal-2024-2025
-
-at.1,        aut-bundesliga-2024-2025
-at.2,        aut-2-liga-2024-2025
-at.3.o,      aut-regionalliga-ost-2024-2025
-at.cup,      aut-oefb-cup-2024-2025
-
-
-
-