worldfootball 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0dfb778159b88ccab0c79abd75512a5751e148c96f5f2c1ecec6a1ea95b4eaa7
-  data.tar.gz: 907c8f61a222068bc591260c6928f08c5ab76fc3fa0f826b8a83e4aba673f6a3
+  metadata.gz: 6bc6759b77de7fe44eccf59f09fd7b6cc3ddc4576612f4fb208c38a59a02536e
+  data.tar.gz: 912fe7d04165b50bc3e50f5e5a1ea554d7fd788d4d019c2b719c8625dd222a3e
 SHA512:
-  metadata.gz: 3d008e4768814d2d290d71a73a82f7d8b83812e75dffc6a34fa3a32778634b7160b1642d1741ba84546e89f127965f9822db7c77c47ba2b3c01adb679523256a
-  data.tar.gz: '09605deda7a4431e396747d2b8cca60f1aaae662249999e0b585427d53721328cf2d74beb063f4423034c0bee3e6caf1c3037e87a5ad948836a6f8371c0bfaf6'
+  metadata.gz: 74bf6c7e7a8aeaeb18d9bd1b74764328301b3aa3c309ca814ea494be704958a4f086e7bf94b1b1ea1ad9f974b7be31eb6e0d2a0c611b6c35b85caca06d8f6e71
+  data.tar.gz: 7cadf69fe3acafc2f976e3f5c980c8411e8758f5426559d56860c791b473debdb4e1067ad071de6704e7da3ccc434c3af14454bed6ba32ac825c2b491467db08

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.2.4
+### 0.2.5
 
 ### 0.0.1 / 2024-07-04
 

data/Manifest.txt

@@ -3,6 +3,7 @@ Manifest.txt
 README.md
 Rakefile
 bin/wfb
+config/leagues_africa.csv
 config/leagues_america.csv
 config/leagues_asia.csv
 config/leagues_europe.csv
@@ -22,6 +23,7 @@ lib/worldfootball/mods.rb
 lib/worldfootball/page.rb
 lib/worldfootball/page_report.rb
 lib/worldfootball/page_schedule.rb
+lib/worldfootball/page_team.rb
 lib/worldfootball/stages.rb
 lib/worldfootball/vacuum.rb
 lib/worldfootball/version.rb

data/bin/wfb

@@ -45,17 +45,17 @@ parser = OptionParser.new do |parser|
 
   parser.on( "--cache", "--cached", "--offline",
                "use cached data in #{Webcache.root}" ) do |cached|
-    opts[:cached] = cached
+    opts[:cached] = true
   end
 
   parser.on( "--[no-]convert",
                "turn on/off conversion to .csv in #{Worldfootball.config.convert.out_dir} - default is (#{opts[:convert]})" ) do |convert|
-    opts[:convert] = convert
+    opts[:convert] = convert   # true|false
   end
 
   parser.on( "--print", "--pp",
                  "pretty print cached data in #{Webcache.root}; no download & conversion") do |print|
-    opts[:cached] = true
+    opts[:cached]  = true
     opts[:convert] = false
   end
 

data/config/leagues_africa.csv

@@ -0,0 +1,8 @@
+key,         slug
+
+afl,         african-football-league-2023
+caf.cl,      caf-champions-league-2024-2025
+
+eg.1,           egy-premiership-2023-2024
+ma.1,           mar-botola-pro-1-2024-2025
+dz.1,          alg-ligue-1-2024-2025

data/config/leagues_america.csv

@@ -37,8 +37,19 @@ us.cup,  usa-u-s-open-cup-2024
 
 br.1,    bra-serie-a-2024
 br.2,    bra-serie-b-2024
+br.3,    bra-serie-c-2024-playoffs
+br.4,    bra-serie-d-2024
+
 br.cup,  bra-copa-do-brasil-2024
 
+br.carioca,    bra-campeonato-carioca-2024-taca-guanabara-finals
+br.gauchao,    bra-campeonato-gaucho-2024-playoffs
+br.mineiro,     bra-campeonato-mineiro-2024-fase-final
+br.paranaense,  bra-campeonato-paranaense-2024-fase-final
+br.paulistao,   bra-campeonato-paulista-2024-playoffs
+
+
+
 
 co.1,    col-primera-a-2024-clausura
 co.2,    col-primera-b-2024-clausura

data/config/leagues_asia.csv

@@ -8,3 +8,4 @@ cn.1,    chn-super-league-2024
 
 kr.1,    kor-k-league-1-2024
 
+kz.1,    kaz-premier-liga-2024

data/config/leagues_europe.csv

@@ -13,6 +13,7 @@ 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.3.m,      aut-regionalliga-mitte-2024-2025
 at.cup,      aut-oefb-cup-2024-2025
 
 
@@ -20,6 +21,9 @@ ch.1,        sui-super-league-2024-2025
 ch.2,        sui-challenge-league-2024-2025
 ch.cup,      sui-cup-2024-2025
 
+# note - li no league, only cup
+#       most (all?) clubs play in switzerland
+li.cup,    lie-fl-1-cup-2024-2025
 
 hu.1,       hun-nb-i-2024-2025
 
@@ -44,7 +48,8 @@ eng.cup.l,   eng-league-cup-2024-2025
 
 
 sco.1,       sco-premiership-2024-2025
-
+wal.1,     wal-premier-league-2024-2025
+nir.1,      nir-premier-league-2024-2025
 ie.1,        irl-premier-division-2024
 
 
@@ -64,10 +69,16 @@ 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.1,      ita-serie-a-2024-2025
+it.2,      ita-serie-b-2024-2025
+it.3.a,    ita-serie-c-girone-a-2024-2025
+it.3.b,    ita-serie-c-girone-b-2024-2025
+it.3.c,    ita-serie-c-girone-c-2024-2025
 it.cup,   ita-coppa-italia-2024-2025
 
+sm.1,      smr-campionato-2024-2025
+
+
 pt.1,     por-primeira-liga-2024-2025
 pt.2,     por-segunda-liga-2024-2025
 
@@ -75,13 +86,21 @@ 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!!!
 
+ad.1,     and-1a-divisio-2024-2025
+
+gi.1,     gib-premier-divison-2024-2025
+
 
 ro.1,     rou-liga-1-2024-2025
 ro.cup,   rou-cupa-romaniei-2024-2025
 
+bg.1,     bul-parva-liga-2024-2025
+
 ru.1,     rus-premier-liga-2024-2025
 ru.2,     rus-premier-liga-2024-2025
 
+by.1,    blr-cempionat-2024
+
 ua.1,     ukr-premyer-liga-2024-2025
 
 
@@ -91,13 +110,32 @@ tr.2,    tur-1-lig-2024-2025
 
 gr.1,    gre-super-league-2024-2025
 
+cy.1,    cyp-first-division-2024-2025
+mt.1,    mlt-premier-league-2024-2025-opening
+
 hr.1,    cro-1-hnl-2024-2025
 ba.1,    bih-premier-liga-2024-2025
 
 al.1,    alb-kategoria-superiore-2024-2025
 
+mk.1,    mkd-1-mfl-2024-2025
+md.1,    mda-divizia-nationala-2024-2025-phase-i
+me.1,    mne-1-cfl-2024-2025
+rs.1,    srb-super-liga-2024-2025
+si.1,    svn-prvaliga-2024-2025
+
+## todo/fix - change to kos.1 - why? why not?
+xk.1,     kos-superliga-2024-2025
+kos.1,    kos-superliga-2024-2025
+
+
+am.1,      arm-premier-league-2024-2025
+az.1,      aze-premyer-liqasi-2024-2025
+ge.1,      geo-erovnuli-liga-2024
+
 
 is.1,   isl-urvalsdeild-2024
+fo.1,   fro-effodeildin-2024
 
 se.1,   swe-allsvenskan-2024
 se.2,   swe-superettan-2024
@@ -106,7 +144,9 @@ no.1,    nor-eliteserien-2024
 fi.1,    fin-veikkausliiga-2024-championship
 dk.1,    den-superliga-2024-2025
 
-
+ee.1,    est-meistriliiga-2024
+lt.1,    ltu-a-lyga-2024
+lv.1,    lat-virsliga-2024
 
 
 uefa.cl,      champions-league-2024-2025

data/config/rounds.csv

@@ -1,5 +1,6 @@
 key,  name1, name2
 
+## de to en
 *,  1. Runde,      Round 1
 *,  2. Runde,      Round 2
 *,  3. Runde,      Round 3
@@ -14,3 +15,44 @@ key,  name1, name2
 *,  Halbfinale,    Semifinals
 *,  Finale,        Final
 
+*,  Spiel um Platz 3,   Match for 3rd place
+
+*,  Vorrunde,      Preliminary round
+
+*,  Qual. 1. Runde,  Qual. Round 1
+*,  Qual. 2. Runde,  Qual. Round 2
+
+
+
+## es to en
+*,  Recalificación,  Reclassification
+
+
+
+
+## misc - make more generic - why? why not?
+mx.1,  Qual. 1. Runde,  Play-in round 1
+mx.1,  Qual. 2. Runde,  Play-in round 2
+mx.2,  Qual. 1. Runde,  Play-in round 1
+mx.2,  Qual. 2. Runde,  Play-in round 2
+
+
+###
+##   quick fix - move groups to new groups column!!!!
+ar.1,   Gruppe A,  Group
+ar.1,   Gruppe B,  Group
+ar.1,   Gruppe C,  Group
+ar.1,   Gruppe D,  Group
+ar.1,   Gruppe E,  Group
+ar.1,   Gruppe F,  Group
+ar.1,   Gruppe 1,  Group
+ar.1,   Gruppe 2,  Group
+
+co.1,   Gruppe A,  Group
+co.1,   Gruppe B,  Group
+
+caf.cl, Gruppe A,  Group
+caf.cl, Gruppe B,  Group
+caf.cl, Gruppe C,  Group
+caf.cl, Gruppe D,  Group
+

data/lib/worldfootball/build-parse_score.rb

@@ -1,6 +1,17 @@
 module Worldfootball
 
 
+## add  WO
+##   br.mineiro 2024 - Descenso
+##
+##  W.O. or w/o (originally two words: "walk over"),
+##
+## [004] 3. Spieltag => 3
+## [004]    2024-03-22 | 00:00 | Atlético Patrocinense - MG | Ipatinga - MG          | WO
+## !! ERROR - unsupported score format >WO< - sorry; maybe add a score error fix/patch
+
+
+
 
 def self.parse_score( score_str )
     ## add support for
@@ -8,7 +19,7 @@ def self.parse_score( score_str )
     ##   3-0 (0-0, 0-0) awd.
 
   ## check for 0:3 Wert.   - change Wert. to awd.  (awarded)
-  ## todo/fix - use "hardcoded" Wert\. in regex - why? why not? 
+  ## todo/fix - use "hardcoded" Wert\. in regex - why? why not?
   ## score_str = score_str.sub( /Wert\./i, 'awd.' )
 
 
@@ -38,6 +49,11 @@ def self.parse_score( score_str )
     ft = ''
     ht = ''
     comments = 'postponed'
+  elsif score_str == 'WO'   # walk over
+    ##  W.O. or w/o (originally two words: "walk over"),
+    ft = '(*)'
+    ht = ''
+    comments = 'w/o'   ## use walkover - why? why not?
   # 5-4 (0-0, 1-1, 2-2) i.E.
   elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*
@@ -54,7 +70,7 @@ def self.parse_score( score_str )
     ft  = "#{$5}-#{$6}"
     et  = "#{$7}-#{$8}"
   # 3-2 (0-0, 1-1) i.E.   - note: no extra time!!! only ht,ft!!!
-  #                         "popular" in southamerica & mexico 
+  #                         "popular" in southamerica & mexico
   elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*
                       \(([0-9]+) [ ]*-[ ]* ([0-9]+)
@@ -80,14 +96,14 @@ def self.parse_score( score_str )
     et  = "#{$1}-#{$2}"
     ht  = "#{$3}-#{$4}"
     ft  = "#{$5}-#{$6}"
-  ### auto-patch fix drop last score 
+  ### auto-patch fix drop last score
   ## 1-3 (0-1, 1-1, 0-2) n.V.  => 1-3 (0-1, 1-1) n.V.
   elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
                       [ ]*
                     \(([0-9]+) [ ]*-[ ]* ([0-9]+)
                        [ ]*,[ ]*
-                      ([0-9]+) [ ]*-[ ]* ([0-9]+)  
-                       [ ]*,[ ]* 
+                      ([0-9]+) [ ]*-[ ]* ([0-9]+)
+                       [ ]*,[ ]*
                       ([0-9]+) [ ]*-[ ]* ([0-9]+)
                       \)
                        [ ]*
@@ -97,7 +113,7 @@ def self.parse_score( score_str )
     ht  = "#{$3}-#{$4}"
     ft  = "#{$5}-#{$6}"
 
-    puts "!! WARN - auto-fix/patch score - >#{score_str}<"  
+    puts "!! WARN - auto-fix/patch score - >#{score_str}<"
     ### todo/fix - log auto-patch/fix - for double checking!!!!!
   elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*
@@ -120,9 +136,9 @@ def self.parse_score( score_str )
                          [ ]*
                        \(([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*,[ ]*
-                        ([0-9]+) [ ]*-[ ]* ([0-9]+)   
-                       \)   
-                        [ ]* 
+                        ([0-9]+) [ ]*-[ ]* ([0-9]+)
+                       \)
+                        [ ]*
                         Wert\.    # ([a-z.]+)
                        /x    ### assume awd. (awarded) always - why? why not?
     ft = "#{$1}-#{$2} (*)"
@@ -133,19 +149,36 @@ def self.parse_score( score_str )
      ft = "#{$1}-#{$2}"     ## e.g. see luxemburg and others
      ht = ''
   ## auto-fix/patch
-  # 3-3 (0-3, 3-3)  =>  3-3 (0-3) - drop last score 
+  # 3-3 (0-3, 3-3)  =>  3-3 (0-3) - drop last score
   elsif score_str =~ /^([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*
                       \(([0-9]+) [ ]*-[ ]* ([0-9]+)
                           [ ]*,[ ]*
-                        ([0-9]+) [ ]*-[ ]* ([0-9]+)   
+                        ([0-9]+) [ ]*-[ ]* ([0-9]+)
                       \)$
                      /x
     ft = "#{$1}-#{$2}"
     ht = "#{$3}-#{$4}"
 
-    puts "!! WARN - auto-fix/patch score - >#{score_str}<"  
+    puts "!! WARN - auto-fix/patch score - >#{score_str}<"
     ### todo/fix - log auto-patch/fix - for double checking!!!!!
+  elsif score_str =~ /^([0-9]+) [ ]*-[ ]* ([0-9]+)
+                         [ ]*
+                       n\.V\.
+                      $/x
+    et  = "#{$1}-#{$2}"
+    ht  = ''
+    ft  = ''
+    puts "!! WARN - weird score n.V. only - >#{score_str}<"
+  elsif score_str =~ /^([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*
+                       i\.E\.
+                       $/x
+    pen = "#{$1}-#{$2}"
+    et  = ''
+    ht  = ''
+    ft  = ''
+    puts "!! WARN - weird score i.E. only - >#{score_str}<"
   else
      puts "!! ERROR - unsupported score format >#{score_str}< - sorry; maybe add a score error fix/patch"
      exit 1

data/lib/worldfootball/download.rb

@@ -38,7 +38,7 @@ class Metal
 
   def self.schedule_url( slug )  "#{BASE_URL}/alle_spiele/#{slug}/";  end
   def self.report_url( slug )    "#{BASE_URL}/spielbericht/#{slug}/"; end
-
+  def self.team_url( slug )   "#{BASE_URL}/teams/#{slug}/"; end
 
 ##
 ## note:
@@ -49,6 +49,19 @@ class Metal
 ##      301 Moved Permanently location=https://www.weltfussball.de/
 
 
+def self.download_team( slug, cache: true )
+  url  = team_url( slug )
+
+  ## check check first
+  if cache && Webcache.cached?( url )
+     puts "  reuse local (cached) copy >#{Webcache.url_to_id( url )}<"
+  else
+    download_page( url )
+  end
+end
+
+
+
 # url = "https://www.weltfussball.de/alle_spiele/eng-league-one-#{season}/"
 # url = "https://www.weltfussball.de/alle_spiele/eng-league-two-#{season}/"
 #        https://www.weltfussball.de/alle_spiele/eng-national-league-2019-2020/
@@ -62,7 +75,6 @@ class Metal
 #        https://www.weltfussball.de/alle_spiele/tur-sueperlig-2019-2020/
 #        https://www.weltfussball.de/alle_spiele/tur-1-lig-2019-2020/
 
-
   def self.download_schedule( slug )
     url = schedule_url( slug )
     download_page( url )

data/lib/worldfootball/leagues.rb

@@ -120,7 +120,8 @@ end # class LeagueConfig
 
 
 LEAGUES = LeagueConfig.new
-['leagues_america',
+['leagues_africa',
+ 'leagues_america',
  'leagues_asia',
  'leagues_europe',
  'leagues_middle_east',

data/lib/worldfootball/page.rb

@@ -8,7 +8,9 @@ module Worldfootball
   end
 
   def initialize( html )
-    @html = html
+    ## todo/fix - fix upstream in wget!!!! why? why not?
+    ##    normalize unicode (to nfc - ruby's default norm form)
+    @html = html.unicode_normalize
   end
 
   def doc

data/lib/worldfootball/page_team.rb

@@ -0,0 +1,22 @@
+
+module Worldfootball
+  class Page
+
+class Team < Page  ## note: use nested class for now - why? why not?
+
+  def self.from_cache( slug )
+    url  = Metal.team_url( slug )
+    html = Webcache.read( url )
+    new( html )
+  end
+
+
+
+
+######
+## helpers
+
+end # class Team
+
+  end # class Page
+end # module Worldfootball

data/lib/worldfootball/version.rb

@@ -2,7 +2,7 @@
 module Worldfootball
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
   MINOR = 2
-  PATCH = 4
+  PATCH = 5
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/worldfootball.rb

@@ -16,6 +16,7 @@ require_relative 'worldfootball/download'
 require_relative 'worldfootball/page'
 require_relative 'worldfootball/page_schedule'
 require_relative 'worldfootball/page_report'
+require_relative 'worldfootball/page_team'
 require_relative 'worldfootball/cache'
 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: worldfootball
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-15 00:00:00.000000000 Z
+date: 2024-10-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: football-timezones
@@ -102,6 +102,7 @@ files:
 - README.md
 - Rakefile
 - bin/wfb
+- config/leagues_africa.csv
 - config/leagues_america.csv
 - config/leagues_asia.csv
 - config/leagues_europe.csv
@@ -121,6 +122,7 @@ files:
 - lib/worldfootball/page.rb
 - lib/worldfootball/page_report.rb
 - lib/worldfootball/page_schedule.rb
+- lib/worldfootball/page_team.rb
 - lib/worldfootball/stages.rb
 - lib/worldfootball/vacuum.rb
 - lib/worldfootball/version.rb