sportdb-formats 1.0.6 → 1.1.4

data/test/test_datafile_package.rb

@@ -16,7 +16,7 @@ class TestDatafilePackage < MiniTest::Test
     ].each do |eng|
        assert eng.find( '2015-16/.conf.txt' ).read.start_with?( '= English Premier League 2015/16' )
        assert eng.find( '2017-18/.conf.txt' ).read.start_with?( '= English Premier League 2017/18' )
-       assert eng.find( '2015-16/1-premierleague-i.txt' ).read.start_with?( '= English Premier League 2015/16' )
+       assert eng.find( '2015-16/1-premierleague.txt' ).read.start_with?( '= English Premier League 2015/16' )
     end
 
     [Datafile::DirPackage.new( '../../../openfootball/austria' ),

data/test/test_regex.rb

@@ -9,9 +9,27 @@ require 'helper'
 
 class TestRegex < MiniTest::Test
 
+  HEADER_SEP_RE    = SportDb::MatchParser::HEADER_SEP_RE
+
+  def test_header_sep
+    assert_equal ['Round',    'Fr+Sa Dec 11+12'], 'Round    // Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 /// Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 -- Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 --- Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 ++ Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 +++ Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+    assert_equal ['Round 11', 'Fr+Sa Dec 11+12'], 'Round 11 || Fr+Sa Dec 11+12'.split( HEADER_SEP_RE )
+
+    assert_equal ['Final - Leg 1'], 'Final - Leg 1'.split( HEADER_SEP_RE  )
+    assert_equal ['Final | Leg 1'], 'Final | Leg 1'.split( HEADER_SEP_RE  )
+    assert_equal ['Final / Leg 1'], 'Final / Leg 1'.split( HEADER_SEP_RE  )
+    assert_equal ['Final, Leg 1'],  'Final, Leg 1'.split( HEADER_SEP_RE  )
+  end
+
+
   ADDR_MARKER_RE   = SportDb::Import::ClubReader::ADDR_MARKER_RE
   B_TEAM_MARKER_RE = SportDb::Import::ClubReader::B_TEAM_MARKER_RE
-  
+
   def test_addr
     assert  '~ Wien' =~ ADDR_MARKER_RE
     assert  'Wien ~' =~ ADDR_MARKER_RE
@@ -22,13 +40,13 @@ class TestRegex < MiniTest::Test
     assert 'Fischhofgasse 12 /// 1100 Wien' =~ ADDR_MARKER_RE
 
     assert_nil 'Fischhofgasse 12 + 1100 Wien' =~ ADDR_MARKER_RE
-    assert_nil 'Fischhofgasse 12++1100 Wien' =~ ADDR_MARKER_RE
+    assert_nil 'Fischhofgasse 12++1100 Wien' =~ ADDR_MARKER_RE   ## todo/fix: make it a match!!! why? why not?
     assert_nil 'Fischhofgasse 12 / 1100 Wien' =~ ADDR_MARKER_RE
-    assert_nil 'Fischhofgasse 12//1100 Wien' =~ ADDR_MARKER_RE
-    
+    assert_nil 'Fischhofgasse 12//1100 Wien' =~ ADDR_MARKER_RE   ## todo/fix: make it a match!!! why? why not?
+
     assert_nil 'Atlanta United FC, 2017,  Atlanta   › Georgia' =~ ADDR_MARKER_RE
   end
-  
+
   def test_b_team
     assert 'b)    Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert '(b)   Rapid Wien II' =~ B_TEAM_MARKER_RE
@@ -38,12 +56,12 @@ class TestRegex < MiniTest::Test
     assert '(ii.) Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert '2)    Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert '(2)   Rapid Wien II' =~ B_TEAM_MARKER_RE
- 
+
     assert_nil '(3)   Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert_nil '(iii) Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert_nil 'iii)  Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert_nil 'c)    Rapid Wien II' =~ B_TEAM_MARKER_RE
     assert_nil '(c)   Rapid Wien II' =~ B_TEAM_MARKER_RE
   end
-  
+
 end # class TestRegex

metadata

@@ -1,59 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-formats
 version: !ruby/object:Gem::Version
-  version: 1.0.6
+  version: 1.1.4
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-05-24 00:00:00.000000000 Z
+date: 2020-08-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: alphabets
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.0
-- !ruby/object:Gem::Dependency
-  name: date-formats
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.1
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.1
-- !ruby/object:Gem::Dependency
-  name: csvreader
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.2.4
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.2.4
-- !ruby/object:Gem::Dependency
-  name: sportdb-langs
+  name: sportdb-structs
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -122,11 +80,12 @@ files:
 - README.md
 - Rakefile
 - lib/sportdb/formats.rb
-- lib/sportdb/formats/config.rb
 - lib/sportdb/formats/country/country_index.rb
 - lib/sportdb/formats/country/country_reader.rb
 - lib/sportdb/formats/datafile.rb
 - lib/sportdb/formats/datafile_package.rb
+- lib/sportdb/formats/event/event_index.rb
+- lib/sportdb/formats/event/event_reader.rb
 - lib/sportdb/formats/goals.rb
 - lib/sportdb/formats/league/league_index.rb
 - lib/sportdb/formats/league/league_outline_reader.rb
@@ -136,26 +95,13 @@ files:
 - lib/sportdb/formats/match/mapper_teams.rb
 - lib/sportdb/formats/match/match_parser.rb
 - lib/sportdb/formats/match/match_parser_auto_conf.rb
-- lib/sportdb/formats/match/match_parser_csv.rb
-- lib/sportdb/formats/name_helper.rb
 - lib/sportdb/formats/outline_reader.rb
 - lib/sportdb/formats/package.rb
 - lib/sportdb/formats/parser_helper.rb
-- lib/sportdb/formats/score/score_formats.rb
-- lib/sportdb/formats/score/score_parser.rb
-- lib/sportdb/formats/season_utils.rb
-- lib/sportdb/formats/structs/country.rb
-- lib/sportdb/formats/structs/group.rb
-- lib/sportdb/formats/structs/league.rb
-- lib/sportdb/formats/structs/match.rb
-- lib/sportdb/formats/structs/matchlist.rb
-- lib/sportdb/formats/structs/round.rb
-- lib/sportdb/formats/structs/season.rb
-- lib/sportdb/formats/structs/standings.rb
-- lib/sportdb/formats/structs/team.rb
-- lib/sportdb/formats/structs/team_usage.rb
 - lib/sportdb/formats/team/club_index.rb
+- lib/sportdb/formats/team/club_index_history.rb
 - lib/sportdb/formats/team/club_reader.rb
+- lib/sportdb/formats/team/club_reader_history.rb
 - lib/sportdb/formats/team/club_reader_props.rb
 - lib/sportdb/formats/team/national_team_index.rb
 - lib/sportdb/formats/team/team_index.rb
@@ -163,37 +109,22 @@ files:
 - lib/sportdb/formats/version.rb
 - test/helper.rb
 - test/test_club_index.rb
+- test/test_club_index_history.rb
 - test/test_club_reader.rb
+- test/test_club_reader_history.rb
 - test/test_club_reader_props.rb
-- test/test_clubs.rb
-- test/test_conf.rb
 - test/test_country_index.rb
 - test/test_country_reader.rb
-- test/test_csv_match_parser.rb
-- test/test_csv_match_parser_utils.rb
-- test/test_csv_reader.rb
 - test/test_datafile.rb
 - test/test_datafile_package.rb
 - test/test_goals.rb
 - test/test_league_index.rb
 - test/test_league_outline_reader.rb
 - test/test_league_reader.rb
-- test/test_match.rb
-- test/test_match_auto.rb
-- test/test_match_auto_champs.rb
-- test/test_match_auto_euro.rb
-- test/test_match_auto_worldcup.rb
-- test/test_match_champs.rb
-- test/test_match_eng.rb
-- test/test_match_euro.rb
-- test/test_match_worldcup.rb
-- test/test_name_helper.rb
 - test/test_outline_reader.rb
 - test/test_package.rb
 - test/test_package_match.rb
 - test/test_regex.rb
-- test/test_scores.rb
-- test/test_season.rb
 - test/test_wiki_reader.rb
 homepage: https://github.com/sportdb/sport.db
 licenses:

data/lib/sportdb/formats/config.rb

@@ -1,40 +0,0 @@
-# encoding: utf-8
-
-module SportDb
-  module Import
-
-class Configuration
-  ##
-  ##  todo: allow configure of countries_dir like clubs_dir
-  ##         "fallback" and use a default built-in world/countries.txt
-
-  attr_accessor   :catalog
-
-  attr_reader   :lang
-  def lang=(value)
-    ## check/todo: always use to_sym - why? needed?
-    DateFormats.lang  = value
-    ScoreFormats.lang = value
-    SportDb.lang.lang = value
-
-    ## todo/fix:  change SportDb.lang to SportDb.parser.lang or lang_parser or utils or someting !!!!
-    ##   use Sport.lang only as a read-only shortcut a la catalog for config.lang!!!!
-  end
-
-end # class Configuration
-
-
-## lets you use
-##   SportDb::Import.configure do |config|
-##      config.lang = 'it'
-##   end
-
-def self.configure()  yield( config ); end
-
-def self.config()  @config ||= Configuration.new;  end
-
-##  e.g. use config.catalog  -- keep Import.catalog as a shortcut (for "read-only" access)
-def self.catalog() config.catalog;  end
-
-end   # module Import
-end   # module SportDb

data/lib/sportdb/formats/match/match_parser_csv.rb

@@ -1,314 +0,0 @@
-# encoding: utf-8
-
-
-module SportDb
-  class CsvMatchParser
-
-  #############
-  # helpers
-  def self.find_seasons( path, col: 'Season', sep: nil, headers: nil )
-
-    ## check if headers incl. season if yes,has priority over col mapping
-    ##  e.g. no need to specify twice (if using headers)
-    col = headers[:season]    if headers && headers[:season]
-
-    seasons = Hash.new( 0 )   ## default value is 0
-
-    ## todo/fix: yes, use CsvHash.foreach  - why? why not?
-    ##                    use read_csv with block  to switch to foreach!!!!
-    rows = read_csv( path, sep: sep )
-
-    rows.each_with_index do |row,i|
-      puts "[#{i}] " + row.inspect  if i < 2
-
-      season = row[ col ]   ## column name defaults to 'Season'
-      seasons[ season ] += 1
-    end
-
-    pp seasons
-
-    ## note: only return season keys/names (not hash with usage counter)
-    seasons.keys
-  end
-
-
-  ##########
-  # main machinery
-
-  ##  todo/fix: use a generic "global" parse_csv method - why? why not?
-  ## def self.parse_csv( text, sep: ',' )    ## helper -lets you change the csv library in one place if needed/desired
-  ##   ## note:  do NOT symbolize keys - keep them as is!!!!!!
-  ##  ##   todo/fix: move "upstream" and remove symbolize keys too!!! - why? why not?
-  ##   CsvHash.parse( text, sep: sep )
-  ## end
-
-  def self.read( path, headers: nil, filters: nil, converters: nil, sep: nil )
-     txt = File.open( path, 'r:utf-8' ) {|f| f.read }   ## note: make sure to use (assume) utf-8
-     parse( txt, headers: headers,
-                 filters: filters,
-                 converters: converters,
-                 sep: sep )
-  end
-
-  def self.parse( txt, headers: nil, filters: nil, converters: nil, sep: nil )
-     new( txt ).parse( headers: headers,
-                        filters: filters,
-                        converters: converters,
-                        sep: sep )
-  end
-
-
-  def initialize( txt )
-    @txt = txt
-  end
-
-  def parse( headers: nil, filters: nil, converters: nil, sep: nil )
-
-    headers_mapping = {}
-
-    rows = parse_csv( @txt, sep: sep )
-
-    return []   if rows.empty?      ## no rows / empty?
-
-
-    ## fix/todo: use logger!!!!
-    ## pp csv
-
-    if headers   ## use user supplied headers if present
-      headers_mapping = headers_mapping.merge( headers )
-    else
-
-      ## note: returns an array of strings (header names)  - assume all rows have the same columns/fields!!!
-      headers = rows[0].keys
-      pp headers
-
-      # note: greece 2001-02 etc. use HT  -  check CVS reader  row['HomeTeam'] may not be nil but an empty string?
-      #   e.g. row['HomeTeam'] || row['HT'] will NOT work for now
-
-      if find_header( headers, ['Team 1']) && find_header( headers, ['Team 2'])
-         ## assume our own football.csv format, see github.com/footballcsv
-         headers_mapping[:team1]  = find_header( headers, ['Team 1'] )
-         headers_mapping[:team2]  = find_header( headers, ['Team 2'] )
-         headers_mapping[:date]   = find_header( headers, ['Date'] )
-
-         ## check for all-in-one full time (ft) and half time (ht9 scores?
-         headers_mapping[:score]  = find_header( headers, ['FT'] )
-         headers_mapping[:scorei] = find_header( headers, ['HT'] )
-
-         headers_mapping[:round]  = find_header( headers, ['Round'] )
-
-         ## optional headers - note: find_header returns nil if header NOT found
-         header_stage = find_header( headers, ['Stage'] )
-         headers_mapping[:stage]  =  header_stage   if header_stage
-      else
-         ## else try footballdata.uk and others
-         headers_mapping[:team1]  = find_header( headers, ['HomeTeam', 'HT', 'Home'] )
-         headers_mapping[:team2]  = find_header( headers, ['AwayTeam', 'AT', 'Away'] )
-         headers_mapping[:date]   = find_header( headers, ['Date'] )
-
-         ## note: FT = Full Time, HG = Home Goal, AG = Away Goal
-         headers_mapping[:score1] = find_header( headers, ['FTHG', 'HG'] )
-         headers_mapping[:score2] = find_header( headers, ['FTAG', 'AG'] )
-
-         ## check for half time scores ?
-         ##  note: HT = Half Time
-         headers_mapping[:score1i] = find_header( headers, ['HTHG'] )
-         headers_mapping[:score2i] = find_header( headers, ['HTAG'] )
-      end
-    end
-
-    pp headers_mapping
-
-    ### todo/fix: check headers - how?
-    ##  if present HomeTeam or HT required etc.
-    ##   issue error/warn is not present
-    ##
-    ## puts "*** !!! wrong (unknown) headers format; cannot continue; fix it; sorry"
-    ##    exit 1
-    ##
-
-    matches = []
-
-    rows.each_with_index do |row,i|
-
-      ## fix/todo: use logger!!!!
-      ## puts "[#{i}] " + row.inspect  if i < 2
-
-
-      ## todo/fix: move to its own (helper) method - filter or such!!!!
-       if filters    ## filter MUST match if present e.g. row['Season'] == '2017/2018'
-         skip = false
-         filters.each do |header, value|
-           if row[ header ] != value   ## e.g. row['Season']
-             skip = true
-             break
-           end
-         end
-         next if skip   ## if header values NOT matching
-       end
-
-
-      ## note:
-      ##   add converters after filters for now (why not before filters?)
-      if converters   ## any converters defined?
-        ## convert single proc shortcut to array with single converter
-        converters = [converters]    if converters.is_a?( Proc )
-
-        ## assumes array of procs
-        converters.each do |converter|
-          row = converter.call( row )
-        end
-      end
-
-
-
-      team1 = row[ headers_mapping[ :team1 ]]
-      team2 = row[ headers_mapping[ :team2 ]]
-
-
-      ## check if data present - if not skip (might be empty row)
-      if team1.nil? && team2.nil?
-        puts "*** WARN: skipping empty? row[#{i}] - no teams found:"
-        pp row
-        next
-      end
-
-      ## remove possible match played counters e.g. (4) (11) etc.
-      team1 = team1.sub( /\(\d+\)/, '' ).strip
-      team2 = team2.sub( /\(\d+\)/, '' ).strip
-
-
-
-      col = row[ headers_mapping[ :date ]]
-      col = col.strip   # make sure not leading or trailing spaces left over
-
-      if col.empty? || col == '-' || col == '?'
-         ## note: allow missing / unknown date for match
-         date = nil
-      else
-        ## remove possible weekday or weeknumber  e.g. (Fri) (4) etc.
-        col = col.sub( /\(W?\d{1,2}\)/, '' )  ## e.g. (W11), (4), (21) etc.
-        col = col.sub( /\(\w+\)/, '' )  ## e.g. (Fri), (Fr) etc.
-        col = col.strip   # make sure not leading or trailing spaces left over
-
-        if col =~ /^\d{2}\/\d{2}\/\d{4}$/
-          date_fmt = '%d/%m/%Y'   # e.g. 17/08/2002
-        elsif col =~ /^\d{2}\/\d{2}\/\d{2}$/
-          date_fmt = '%d/%m/%y'   # e.g. 17/08/02
-        elsif col =~ /^\d{4}-\d{2}-\d{2}$/      ## "standard" / default date format
-          date_fmt = '%Y-%m-%d'   # e.g. 1995-08-04
-        elsif col =~ /^\d{1,2} \w{3} \d{4}$/
-          date_fmt = '%d %b %Y'   # e.g. 8 Jul 2017
-        else
-          puts "*** !!! wrong (unknown) date format >>#{col}<<; cannot continue; fix it; sorry"
-          ## todo/fix: add to errors/warns list - why? why not?
-          exit 1
-        end
-
-        ## todo/check: use date object (keep string?) - why? why not?
-        ##  todo/fix: yes!! use date object!!!! do NOT use string
-        date = Date.strptime( col, date_fmt ).strftime( '%Y-%m-%d' )
-      end
-
-
-      round   = nil
-      ## check for (optional) round / matchday
-      if headers_mapping[ :round ]
-        col = row[ headers_mapping[ :round ]]
-        ## todo: issue warning if not ? or - (and just empty string) why? why not
-        round = col.to_i  if col =~ /^\d{1,2}$/     # check format - e.g. ignore ? or - or such non-numbers for now
-      end
-
-
-      score1  = nil
-      score2  = nil
-      score1i = nil
-      score2i = nil
-
-      ## check for full time scores ?
-      if headers_mapping[ :score1 ] && headers_mapping[ :score2 ]
-        ft = [ row[ headers_mapping[ :score1 ]],
-               row[ headers_mapping[ :score2 ]] ]
-
-        ## todo/fix: issue warning if not ? or - (and just empty string) why? why not
-        score1 = ft[0].to_i  if ft[0] =~ /^\d{1,2}$/
-        score2 = ft[1].to_i  if ft[1] =~ /^\d{1,2}$/
-      end
-
-      ## check for half time scores ?
-      if headers_mapping[ :score1i ] && headers_mapping[ :score2i ]
-        ht = [ row[ headers_mapping[ :score1i ]],
-               row[ headers_mapping[ :score2i ]] ]
-
-        ## todo/fix: issue warning if not ? or - (and just empty string) why? why not
-        score1i = ht[0].to_i  if ht[0] =~ /^\d{1,2}$/
-        score2i = ht[1].to_i  if ht[1] =~ /^\d{1,2}$/
-      end
-
-      ## check for all-in-one full time scores?
-      if headers_mapping[ :score ]
-        ft = row[ headers_mapping[ :score ] ]
-        if ft =~ /^\d{1,2}[\-:]\d{1,2}$/   ## sanity check scores format
-          scores = ft.split( /[\-:]/ )
-          score1 = scores[0].to_i
-          score2 = scores[1].to_i
-        end
-        ## todo/fix: issue warning if non-empty!!! and not matching format!!!!
-      end
-
-      if headers_mapping[ :scorei ]
-        ht = row[ headers_mapping[ :scorei ] ]
-        if ht =~ /^\d{1,2}[\-:]\d{1,2}$/   ## sanity check scores format
-          scores = ht.split( /[\-:]/)   ## allow 1-1 and 1:1
-          score1i = scores[0].to_i
-          score2i = scores[1].to_i
-        end
-        ## todo/fix: issue warning if non-empty!!! and not matching format!!!!
-      end
-
-
-      ## try some optional headings / columns
-      stage = nil
-      if headers_mapping[ :stage ]
-        col = row[ headers_mapping[ :stage ]]
-        ## todo/fix: check can col be nil e.g. col.nil? possible?
-        stage =  if col.nil? || col.empty? || col == '-' || col == 'n/a'
-                    ## note: allow missing stage for match / defaults to "regular"
-                    nil
-                 elsif col == '?'
-                     ## note: default explicit unknown to unknown for now AND not regular - why? why not?
-                    '?'   ## todo/check: use unkown and NOT ?  - why? why not?
-                 else
-                    col
-                 end
-      end
-
-
-      match = Import::Match.new( date:    date,
-                                 team1:   team1,   team2:   team2,
-                                 score1:  score1,  score2:  score2,
-                                 score1i: score1i, score2i: score2i,
-                                 round:   round,
-                                 stage:   stage )
-      matches << match
-    end
-
-    ## pp matches
-    matches
-  end
-
-
-  private
-
-  def find_header( headers, candidates )
-     ## todo/fix: use find_first from enumare of similar ?! - why? more idiomatic code?
-
-    candidates.each do |candidate|
-       return candidate   if headers.include?( candidate ) ## bingo!!!
-    end
-    nil  ## no matching header  found!!!
-  end
-
-  end # class CsvMatchParser
-  end # module SportDb
-