worldfootball 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 170277c7714f9b75e93176eb5fff6242fb6efb85051bc8977f7f635dbebf0513
-  data.tar.gz: 5b15d132765c3ee2df4cbdd847b43ba6c7e7bd617ed55bb5fe4dfabc0becb0e0
+  metadata.gz: 78c749dd421814981a58c87104761091471a4ffe26a8261df132d77bca5ffb8f
+  data.tar.gz: 23a146156f4e38f0e92ef9689ed6a965b044e6ae2e489cffb5da56883c7e6e7a
 SHA512:
-  metadata.gz: c95b4b2becf545be2c208a207e8980d06369148d18b0657cddfb81470331c828ee8492649908ece372fb996b9d1a6dfc8eeaa45c54a3757eba7fb6d02e363bf0
-  data.tar.gz: ca127cb3f69c861dba48b049ed6da30b9ecde1f3935b30422d6184869b650b5cafc056be7fa37c7198bbd72ad65bdd262e56c82631c62629f4bbb4222992a9c9
+  metadata.gz: 64e28d3ffdb1056f9db34459ca7d23ba2116a9aeb8130d3b81a310590fc0ad5079eff635664d153a2798b5e9765a10e7508311d0c899b82c1c59f98bedecc60c
+  data.tar.gz: 52ef6922b2b1e735a67b9aae8ecd409c3314aa3d2a48b056d2be2d272b85c4e48735e983dda88630c461a25354a5f6f9cb64eb0cb4d6f642cf873263da3af954

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.1.1
+### 0.2.0
 
 ### 0.0.1 / 2024-07-04
 

data/Manifest.txt

@@ -3,24 +3,17 @@ Manifest.txt
 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

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

@@ -18,17 +18,15 @@ Hoe.spec 'worldfootball' do
   self.history_file = 'CHANGELOG.md'
 
   self.extra_deps = [
-    ## ['tzinfo'],
-    ['season-formats'], 
-    ['webget'],  
+    ['football-timezones'],
+    ['webget'],
     ['nokogiri'],
-    ['cocos'],  ## later pull in with sportsdb-writers
   ]
 
   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 +93,46 @@ 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
+
+
+## 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 )
 
-pages = league.pages( season: season )
 
+puts
+pp [league.key, season.key]
 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 +141,16 @@ 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_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-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