worldfootball 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 170277c7714f9b75e93176eb5fff6242fb6efb85051bc8977f7f635dbebf0513
-  data.tar.gz: 5b15d132765c3ee2df4cbdd847b43ba6c7e7bd617ed55bb5fe4dfabc0becb0e0
+  metadata.gz: 99623775fef73f0837946ba44625a572bbe5fee3a64aa6aa9a2f6f79702a0d01
+  data.tar.gz: 1ed058214bcca9fad1aac5b205e73c101a79a14ef979dbdee37c3a784fe03460
 SHA512:
-  metadata.gz: c95b4b2becf545be2c208a207e8980d06369148d18b0657cddfb81470331c828ee8492649908ece372fb996b9d1a6dfc8eeaa45c54a3757eba7fb6d02e363bf0
-  data.tar.gz: ca127cb3f69c861dba48b049ed6da30b9ecde1f3935b30422d6184869b650b5cafc056be7fa37c7198bbd72ad65bdd262e56c82631c62629f4bbb4222992a9c9
+  metadata.gz: 2b2ec98872c3cf9ae5b9f39cd6ac5bcd205ea35a4ea1282a575f8ea9256226f4395c4021b57417e6d77db38b474127b35cd2836aee3d381a8138b318cb588be0
+  data.tar.gz: dff2a077af11f10c6c0f1e923e42710b04b198a5c7a7677363a25bfa7e508ec56867d64c2df8f907a51584613b0d86a8f246f6727755fa1dfa1e6c1135962877

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.1.1
+### 0.1.2
 
 ### 0.0.1 / 2024-07-04
 

data/Manifest.txt

@@ -3,24 +3,16 @@ Manifest.txt
 README.md
 Rakefile
 bin/wfb
+config/leagues.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

data/README.md

@@ -11,7 +11,42 @@
 ## Usage
 
 
-To be done
+To get started use the `wfb` command-line tool.
+
+List all (pre-configured) leagues:
+
+```
+$ wfb leagues
+```
+
+Print the match schedue of a league (season). Let's try the English Premier League:
+
+```
+$ wfb eng.1 2024/25
+$ wfb eng.1 2024/25 --offline    # use cached (offline local) pages
+```
+
+Or try the DFB Pokal (that is, the German Cup):
+
+```
+$ wfb de.cup 2024/25 --offline    # use cached (offline local) pages
+```
+
+and so on.
+
+
+
+
+
+
+### More
+
+Debugging tips. List all cached (offline local) match schedule pages:
+
+```
+$ wfb cache
+```
+
 
 
 

data/Rakefile

@@ -19,8 +19,8 @@ Hoe.spec 'worldfootball' do
 
   self.extra_deps = [
     ## ['tzinfo'],
-    ['season-formats'], 
-    ['webget'],  
+    ['season-formats'],
+    ['webget'],
     ['nokogiri'],
     ['cocos'],  ## later pull in with sportsdb-writers
   ]
@@ -28,7 +28,7 @@ Hoe.spec 'worldfootball' do
   self.licenses = ['Public Domain']
 
   self.spec_extras = {
-   required_ruby_version: '>= 2.2.2'
+   required_ruby_version: '>= 3.1.0'
   }
 
 end

data/bin/wfb

@@ -9,18 +9,30 @@ require 'worldfootball'
 Webcache.root =  if File.exist?( '/sports/cache' )
                      puts "  setting web cache to >/sports/cache<"
                      '/sports/cache'
-                 else 
+                 else
                      './cache'
                  end
 
+## convert (default) output directory
+Worldfootball.config.convert.out_dir = if File.exist?( '/sports/cache.wfb')
+                                           puts "   setting convert out_dir to >/sports/cache.wfb<"
+                                           '/sports/cache.wfb'
+                                        else
+                                           '.' ## use working dir
+                                        end
 
 require 'optparse'
 
 
 module Worldfootball
-def self.main( args=ARGV )    
+def self.main( args=ARGV )
+
+opts = {
+    cached:  false,
+    convert: true,
+ }
+
 
-opts = {}
 parser = OptionParser.new do |parser|
   parser.banner = "Usage: #{$PROGRAM_NAME} [options]"
 
@@ -28,12 +40,27 @@ parser = OptionParser.new do |parser|
 ## check if git has a offline option?? (use same)
 ##             check for other tools - why? why not?
 
+## todo - add a single letter option for offline/cached
 
   parser.on( "--cache", "--cached", "--offline",
-               "use cached data in #{Webcache.root}" ) do |cached|
+               "use cached data in >#{Webcache.root}<" ) do |cached|
     opts[:cached] = cached
   end
+
+  parser.on( "--no-convert",
+               "turn off conversion to .csv in #{Worldfootball.config.convert.out_dir} - default is (#{!opts[:convert]})" ) do |convert|
+    opts[:convert] = !convert
+  end
+
+  parser.on( "--dry",
+               "dry run / show league page meta info" ) do |dry|
+    opts[:dry] = dry
+  end
 end
+
+
+
+
 parser.parse!( args )
 
 puts "OPTS:"
@@ -42,12 +69,19 @@ puts "ARGV:"
 p args
 
 
+### check special (built-in) commands first
+if ['cache'].include?( args[0] )
+    Worldfootball.list_pages
+    exit 0
+end
+
+
 if ['league', 'leagues', 'ls'].include?( args[0] || 'leagues' )
     keys = LEAGUES.keys
-     
+
     pp keys
     puts "   #{keys.size} league(s)"
-    
+
     # puts
     # puts " pages:"
     # pp Worldfootball::PAGES
@@ -59,33 +93,42 @@ end
 
 league_code = args[0].downcase
 
-league =  find_league( league_code )  ## league info lookup
- 
-season = Season(  args[1] || '2024/25' )
+league =  find_league!( league_code )  ## league info lookup
+
+if opts[:dry]
+    ## output more page meta info
+    puts "league meta:"
+    pp league
+end
+
+
+season = Season( args[1] || '2024/25' )
+
+pages = league.pages!( season: season )
 
-pages = league.pages( season: season )
 
+puts
 pp pages
 puts "   #{pages.size} page(s)"
 
 
-## wrap single page record into array
-pages = pages.is_a?( Array ) ? pages : [pages]
+if opts[:dry]
+    ## stop here if dry run
+    exit 0
+end
 
-if opts[:cached]  
+
+if opts[:cached]
      # do nothing
 else  ## download to cache
-    pages.each_with_index do |page_rec,i|
-        slug = page_rec[:slug]
-        puts "==> #{i+1}/#{pages.size} - #{league_code} @ #{slug}..."    
-        page = Metal.download_schedule( slug  )  
-    end  
+    pages.each_with_index do |(slug,_),i|
+        puts "==> #{i+1}/#{pages.size} - #{league_code} @ #{slug}..."
+        page = Metal.download_schedule( slug )
+    end
 end
 
 
-pages.each_with_index do |page_rec,i|
-    slug = page_rec[:slug]
-
+pages.each_with_index do |(slug,_),i|
     puts "==> #{i+1}/#{pages.size} - #{league_code} @ #{slug}..."
     page = Page::Schedule.from_cache( slug )
     matches = page.matches
@@ -94,11 +137,16 @@ pages.each_with_index do |page_rec,i|
 end
 
 
+if opts[:convert]
+    ## write out (export to) comma-separated values (.csv) datafile
+    convert( league: league_code,
+             season: season )
+end
 end   # def self.main
 end   # module Worldfootball
-    
+
 
 Worldfootball.main( ARGV )
 
-        
+
 puts "bye"

data/config/leagues.csv

@@ -0,0 +1,16 @@
+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
+
+
+
+

data/lib/worldfootball/build-parse_score.rb

@@ -0,0 +1,156 @@
+module Worldfootball
+
+
+
+def self.parse_score( score_str )
+    ## add support for
+    ##   3-0 (0-0, 0-0) Wert.
+    ##   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? 
+  ## score_str = score_str.sub( /Wert\./i, 'awd.' )
+
+
+  comments = String.new     ## check - rename to/use status or such - why? why not?
+
+  ## split score
+  ft  = ''
+  ht  = ''
+  et  = ''
+  pen = ''
+
+
+  if score_str == '---'   ## in the future (no score yet) - was -:-
+    ft = ''
+    ht = ''
+  elsif score_str == 'n.gesp.' ||   ## cancelled (british) / canceled (us)
+        score_str == 'ausg.'   ||   ## todo/check: change to some other status ????
+        score_str == 'annull.'      ## todo/check: change to some other status (see ie 2012) ????
+    ft = '(*)'
+    ht = ''
+    comments = 'cancelled'
+  elsif score_str == 'abgebr.'  ## abandoned  -- waiting for replay?
+    ft = '(*)'
+    ht = ''
+    comments = 'abandoned'
+  elsif score_str == 'verl.'   ## postponed
+    ft = ''
+    ht = ''
+    comments = 'postponed'
+  # 5-4 (0-0, 1-1, 2-2) i.E.
+  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*
+                      \(([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*,[ ]*
+                        ([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*,[ ]*
+                       ([0-9]+) [ ]*-[ ]* ([0-9]+)\)
+                          [ ]*
+                       i\.E\.
+                     /x
+    pen = "#{$1}-#{$2}"
+    ht  = "#{$3}-#{$4}"
+    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 
+  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*
+                      \(([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*,[ ]*
+                       ([0-9]+) [ ]*-[ ]* ([0-9]+)\)
+                          [ ]*
+                       i\.E\.
+                     /x
+    pen = "#{$1}-#{$2}"
+    ht  = "#{$3}-#{$4}"
+    ft  = "#{$5}-#{$6}"
+    et  = ''
+  # 2-1 (1-0, 1-1) n.V
+  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
+                      [ ]*
+                    \(([0-9]+) [ ]*-[ ]* ([0-9]+)
+                       [ ]*,[ ]*
+                      ([0-9]+) [ ]*-[ ]* ([0-9]+)
+                      \)
+                       [ ]*
+                       n\.V\.
+                     /x
+    et  = "#{$1}-#{$2}"
+    ht  = "#{$3}-#{$4}"
+    ft  = "#{$5}-#{$6}"
+  ### 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]+)
+                      [ ]*
+                    \(([0-9]+) [ ]*-[ ]* ([0-9]+)
+                       [ ]*,[ ]*
+                      ([0-9]+) [ ]*-[ ]* ([0-9]+)  
+                       [ ]*,[ ]* 
+                      ([0-9]+) [ ]*-[ ]* ([0-9]+)
+                      \)
+                       [ ]*
+                       n\.V\.
+                     /x
+    et  = "#{$1}-#{$2}"
+    ht  = "#{$3}-#{$4}"
+    ft  = "#{$5}-#{$6}"
+
+    puts "!! WARN - auto-fix/patch score - >#{score_str}<"  
+    ### todo/fix - log auto-patch/fix - for double checking!!!!!
+  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*
+                      \(([0-9]+) [ ]*-[ ]* ([0-9]+)
+                      \)
+                     /x
+    ft = "#{$1}-#{$2}"
+    ht = "#{$3}-#{$4}"
+  elsif  score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
+                          [ ]*
+                          Wert\.    # ([a-z.]+)
+                       /x    ### assume awd. (awarded) always - why? why not?
+    ft = "#{$1}-#{$2} (*)"
+    ht = ''
+    comments = 'awd.'   # awarded - $3
+  ##  auto-fix/patch
+  ##   drop last scores (only use ft)
+  ##     3-0 (0-0, 0-0) awd.
+  elsif  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} (*)"
+    ht = ''
+    comments = 'awd.'   # awarded - $7
+    ## (auto) log case for double checking - why? why not?
+  elsif score_str =~ /^([0-9]+)-([0-9]+)$/
+     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 
+  elsif score_str =~ /^([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}<"  
+    ### todo/fix - log auto-patch/fix - for double checking!!!!!
+  else
+     puts "!! ERROR - unsupported score format >#{score_str}< - sorry; maybe add a score error fix/patch"
+     exit 1
+  end
+
+  [ht, ft, et, pen, comments]
+end
+end  # module Worldfootball

data/lib/worldfootball/build.rb

@@ -7,6 +7,9 @@ ROUND_TO_EN = {
   '2. Runde'      => 'Round 2',
   '3. Runde'      => 'Round 3',
   '4. Runde'      => 'Round 4',
+  '5. Runde'      => 'Round 5',
+  '6. Runde'      => 'Round 6',
+  '7. Runde'      => 'Round 7',
   'Achtelfinale'  => 'Round of 16',
   'Viertelfinale' => 'Quarterfinals',
   'Halbfinale'    => 'Semifinals',
@@ -20,9 +23,10 @@ ROUND_TO_EN = {
 def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such - why? why not?
    season = Season( season )  ## cast (ensure) season class (NOT string, integer, etc.)
 
-   raise ArgumentError, "league key as string expected"  unless league.is_a?(String)  ## note: do NOT pass in league struct! pass in key (string)
+   ## note: do NOT pass in league struct! pass in key (string)
+   raise ArgumentError, "league key as string expected"  unless league.is_a?(String)  
 
-   print "  #{rows.size} rows - build #{league} #{season}"
+   print "  #{rows.size} row(s) - Worldfootball.build #{league} #{season}"
    print " - #{stage}" unless stage.empty?
    print "\n"
 
@@ -47,44 +51,49 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
     print '[%03d] ' % (i+1)
     print row[:round]
 
-    if m = row[:round].match( /([0-9]+)\. Spieltag/ )
+    if (m = row[:round].match( /^(?<num>[0-9]+)\. Spieltag$/ ))
       ## todo/check: always use a string even if number (as a string eg. '1' etc.)
-      round = m[1]  ## note: keep as string (NOT number)
+      round = m[:num]  ## note: keep as string (NOT number)
       print " => #{round}"
     else
-      puts "!! ERROR: cannot find matchday number"
+      puts "!! ERROR: cannot find matchday number in >#{row[:round]}<:"
+      pp row
       exit 1
     end
     print "\n"
-  elsif row[:round] =~ /[1-9]\.[ ]Runde|
+   
+  ## note - must start line e.g. 
+  ##            do NOT match => Qual. 1. Runde  (1. Runde)!!!   
+  elsif row[:round] =~ /^(    
+                          [1-9]\.[ ]Runde|
                           Achtelfinale|
                           Viertelfinale|
                           Halbfinale|
                           Finale
-                          /x
+                         )$
+                        /x
     puts
     print '[%03d] ' % (i+1)
     print row[:round]
 
+    round = ROUND_TO_EN[ row[:round] ]
+    print " => #{round}"
+    print "\n"
 
-    ## do NOT translate rounds (to english) - keep in german / deutsch (de)
-    if ['at.cup', 'at.1',    ## at.1 - incl. europa league playoff
-        'de.cup'].include?( league )
-      round = row[:round]
-    else
-      round = ROUND_TO_EN[ row[:round] ]
-      if round.nil?
-        puts "!! ERROR: no mapping for round to english (en) found >#{row[:round]}<:"
-        pp row
-        exit 1
-      end
-      print " => #{round}"
+    if round.nil?
+      puts "!! ERROR: no mapping for round to english (en) found >#{row[:round]}<:"
+      pp row
+      exit 1
     end
-    print "\n"
   else
-    puts "!! ERROR: unknown round >#{row[:round]}< for league >#{league}<:"
+    puts
+    print '[%03d] ' % (i+1)
+    print row[:round]
+    print "\n"
+
+    puts "!! WARN: unknown round >#{row[:round]}< for league >#{league}<:"
     pp row
-    exit 1
+    round = row[:round]
   end
 
 
@@ -123,8 +132,6 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
     print "\n"
 
 
-    ## check for 0:3 Wert.   - change Wert. to awd.  (awarded)
-    score_str = score_str.sub( /Wert\./i, 'awd.' )
 
     ## clean team name (e.g. remove (old))
     ##   and asciify (e.g. ’ to ' )
@@ -135,12 +142,9 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
     team2_str = mods[ team2_str ]   if mods[ team2_str ]
 
 
-
-
     ht, ft, et, pen, comments = parse_score( score_str )
 
 
-
     recs <<  [stage,
               round,
               date.strftime( '%Y-%m-%d' ),
@@ -155,91 +159,4 @@ def self.build( rows, season:, league:, stage: '' )   ## rename to fixup or such
    end  # each row
    recs
 end  # build
-
-
-
-def self.parse_score( score_str )
-  comments = String.new( '' )     ## check - rename to/use status or such - why? why not?
-
-  ## split score
-  ft  = ''
-  ht  = ''
-  et  = ''
-  pen = ''
-  if score_str == '---'   ## in the future (no score yet) - was -:-
-    ft = ''
-    ht = ''
-  elsif score_str == 'n.gesp.' ||   ## cancelled (british) / canceled (us)
-        score_str == 'ausg.'   ||   ## todo/check: change to some other status ????
-        score_str == 'annull.'      ## todo/check: change to some other status (see ie 2012) ????
-    ft = '(*)'
-    ht = ''
-    comments = 'cancelled'
-  elsif score_str == 'abgebr.'  ## abandoned  -- waiting for replay?
-    ft = '(*)'
-    ht = ''
-    comments = 'abandoned'
-  elsif score_str == 'verl.'   ## postponed
-    ft = ''
-    ht = ''
-    comments = 'postponed'
-  # 5-4 (0-0, 1-1, 2-2) i.E.
-  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
-                          [ ]*
-                      \(([0-9]+) [ ]*-[ ]* ([0-9]+)
-                          [ ]*,[ ]*
-                        ([0-9]+) [ ]*-[ ]* ([0-9]+)
-                          [ ]*,[ ]*
-                       ([0-9]+) [ ]*-[ ]* ([0-9]+)\)
-                          [ ]*
-                       i\.E\.
-                     /x
-    pen = "#{$1}-#{$2}"
-    ht  = "#{$3}-#{$4}"
-    ft  = "#{$5}-#{$6}"
-    et  = "#{$7}-#{$8}"
-  # 2-1 (1-0, 1-1) n.V
-  elsif score_str =~ /([0-9]+) [ ]*-[ ]* ([0-9]+)
-                      [ ]*
-                    \(([0-9]+) [ ]*-[ ]* ([0-9]+)
-                       [ ]*,[ ]*
-                      ([0-9]+) [ ]*-[ ]* ([0-9]+)
-                      \)
-                       [ ]*
-                       n\.V\.
-                     /x
-    et  = "#{$1}-#{$2}"
-    ht  = "#{$3}-#{$4}"
-    ft  = "#{$5}-#{$6}"
-  elsif score_str =~ /([0-9]+)
-                          [ ]*-[ ]*
-                      ([0-9]+)
-                          [ ]*
-                      \(([0-9]+)
-                          [ ]*-[ ]*
-                        ([0-9]+)
-                      \)
-                     /x
-    ft = "#{$1}-#{$2}"
-    ht = "#{$3}-#{$4}"
-  elsif  score_str =~ /([0-9]+)
-                         [ ]*-[ ]*
-                       ([0-9]+)
-                         [ ]*
-                        ([a-z.]+)
-                       /x
-    ft = "#{$1}-#{$2} (*)"
-    ht = ''
-    comments = $3
-  elsif score_str =~ /^([0-9]+)-([0-9]+)$/
-     ft = "#{$1}-#{$2}"     ## e.g. see luxemburg and others
-     ht = ''
-  else
-     puts "!! ERROR - unsupported score format >#{score_str}< - sorry; maybe add a score error fix/patch"
-     exit 1
-  end
-
-  [ht, ft, et, pen, comments]
-end
-
 end # module Worldfootball