sportdb-formats 1.2.0 → 2.0.0

data/lib/sportdb/formats.rb

@@ -1,25 +1,51 @@
 ## 3rd party gems
 require 'sportdb/structs'
+require 'sportdb/parser'
+require 'date/formats'
 
 
 require 'zip'     ## todo/check: if zip is alreay included in a required module
 
 
+## note -  add cocos (code commons)
+##
+##  pulls in read_csv & parse_csv etc.
+require 'cocos'
+
+
+require 'logutils'
+module SportDb
+  ## logging machinery shortcut; use LogUtils for now
+  Logging = LogUtils::Logging
+end
+
+
 
 
 ###
 # our own code
 require_relative 'formats/version' # let version always go first
 
-require_relative 'formats/outline_reader'
 require_relative 'formats/datafile'
 require_relative 'formats/datafile_package'
 require_relative 'formats/package'
 
+require_relative 'formats/name_helper'
+
 
-require_relative 'formats/parser_helper'
 
-require_relative 'formats/lines_reader'
+## let's put test configuration in its own namespace / module
+module SportDb
+  class Test    ## todo/check: works with module too? use a module - why? why not?
+
+    ####
+    #  todo/fix:  find a better way to configure shared test datasets - why? why not?
+    #    note: use one-up (..) directory for now as default - why? why not?
+    def self.data_dir()        @data_dir ||= '../test'; end
+    def self.data_dir=( path ) @data_dir = path; end
+  end
+end   # module SportDb
+
 
 
 ###
@@ -29,13 +55,10 @@ module SportDb
 module Import
 
 class Configuration
-  ## note: add more configs (open class), see sportdb-structs for original config!!!
-
-  ## add 
   def world()        @world ||= WorldSearch.new( countries: DummyCountrySearch.new ); end
   def world=(world)  @world = world; end
 
-  ## tood/fix - add/move catalog here from   sportdb-catalogs!!!
+  ## todo/fix - add/move catalog here from   sportdb-catalogs!!!
   ## def catalog()         @catalog ||= Catalog.new;  end
   ## def catalog(catalog)  @catalog = catalog; end
 end # class Configuration
@@ -43,11 +66,62 @@ end # class Configuration
   ##  e.g. use config.catalog  -- keep Import.catalog as a shortcut (for "read-only" access)
   ## def self.catalog() config.catalog;  end
   def self.world()   config.world;    end
+
+  ## lets you use
+  ##   SportDb::Import.configure do |config|
+  ##      config.catalog_path = './catalog.db'
+  ##   end
+def self.configure()  yield( config ); end
+def self.config()  @config ||= Configuration.new;  end
 end   # module Import
 end   # module SportDb
 
+
 require_relative 'formats/search/world'
 require_relative 'formats/search/sport'
+require_relative 'formats/search/structs'
+
+
+
+module Sports
+  ## note: just forward to SportDb::Import configuration!!!!!
+  ##  keep Sports module / namespace "clean" - why? why not?
+  ##    that is, only include data structures (e.g. Match,League,etc) for now - why? why not?
+  def self.configure()  yield( config ); end
+  def self.config()  SportDb::Import.config; end
+end   # module Sports
+
+
+###
+#  csv (tabular dataset) support / machinery
+require_relative 'formats/csv/match_status_parser'
+require_relative 'formats/csv/goal'
+require_relative 'formats/csv/goal_parser_csv'
+require_relative 'formats/csv/match_parser_csv'
+
+
+### add convenience shortcut helpers
+module Sports
+  class Match
+    def self.read_csv( path, headers: nil, filters: nil, converters: nil, sep: nil )
+       SportDb::CsvMatchParser.read( path,
+                                       headers:    headers,
+                                       filters:    filters,
+                                       converters: converters,
+                                       sep:        sep )
+    end
+
+    def self.parse_csv( txt, headers: nil, filters: nil, converters: nil, sep: nil )
+       SportDb::CsvMatchParser.parse( txt,
+                                        headers:    headers,
+                                        filters:    filters,
+                                        converters: converters,
+                                        sep:        sep )
+    end
+  end # class Match
+end # module Sports
+
+
 
 
 
@@ -77,7 +151,7 @@ module SportDb
 
     Player       = ::Sports::Player
 
-    
+
     class Team
       ## add convenience lookup helper / method for name by season for now
       ##   use clubs history - for now kept separate from struct - why? why not?
@@ -91,14 +165,7 @@ module SportDb
 end     # module SportDb
 
 
-require_relative 'formats/goals'
-
-
-
-require_relative 'formats/match/mapper'
-require_relative 'formats/match/mapper_teams'
 require_relative 'formats/match/match_parser'
-require_relative 'formats/match/match_parser_auto_conf'
 require_relative 'formats/match/conf_parser'
 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-formats
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 2.0.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-22 00:00:00.000000000 Z
+date: 2024-08-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: sportdb-structs
@@ -16,28 +16,84 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.1
+        version: 0.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.1
+        version: 0.3.0
+- !ruby/object:Gem::Dependency
+  name: sportdb-parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+- !ruby/object:Gem::Dependency
+  name: date-formats
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.2
+- !ruby/object:Gem::Dependency
+  name: cocos
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+- !ruby/object:Gem::Dependency
+  name: logutils
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.6.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.6.1
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.4
+        version: 2.3.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.4
+        version: 2.3.2
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -87,23 +143,22 @@ files:
 - Rakefile
 - lib/sportdb/formats.rb
 - lib/sportdb/formats/country/country_reader.rb
+- lib/sportdb/formats/csv/goal.rb
+- lib/sportdb/formats/csv/goal_parser_csv.rb
+- lib/sportdb/formats/csv/match_parser_csv.rb
+- lib/sportdb/formats/csv/match_status_parser.rb
 - lib/sportdb/formats/datafile.rb
 - lib/sportdb/formats/datafile_package.rb
 - lib/sportdb/formats/event/event_reader.rb
-- lib/sportdb/formats/goals.rb
 - lib/sportdb/formats/ground/ground_reader.rb
 - lib/sportdb/formats/league/league_outline_reader.rb
 - lib/sportdb/formats/league/league_reader.rb
-- lib/sportdb/formats/lines_reader.rb
 - lib/sportdb/formats/match/conf_parser.rb
-- lib/sportdb/formats/match/mapper.rb
-- 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/outline_reader.rb
+- lib/sportdb/formats/name_helper.rb
 - lib/sportdb/formats/package.rb
-- lib/sportdb/formats/parser_helper.rb
 - lib/sportdb/formats/search/sport.rb
+- lib/sportdb/formats/search/structs.rb
 - lib/sportdb/formats/search/world.rb
 - lib/sportdb/formats/team/club_index_history.rb
 - lib/sportdb/formats/team/club_reader.rb
@@ -125,7 +180,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.2.2
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="

data/lib/sportdb/formats/goals.rb

@@ -1,313 +0,0 @@
-
-module SportDb
-
-
-
-class GoalsPlayerStruct
-  ##
-  # note: player with own goal (o.g) gets listed on other team
-  #  (thus, player might have two entries if also scored for its own team)
-  #
-  attr_accessor :name
-  attr_accessor :minutes   # ary of minutes e.g. 30', 45+2', 72'
-
-  def initialize
-    @minutes = []
-  end
-
-  def pretty_print( printer ) 
-    buf = String.new
-    buf << "<GoalsPlayerStruct: #{@name} "
-    buf << @minutes.pretty_print_inspect
-    buf << ">"
-
-    printer.text( buf ) 
-  end
-end
-
-
-class GoalsMinuteStruct
-  attr_accessor :minute, :offset
-  attr_accessor :penalty, :owngoal    # flags
-
-  def initialize
-    @offset  = 0
-    @penalty = false
-    @owngoal = false
-  end
-
-  def pretty_print( printer ) 
-    buf = String.new
-    buf << "<GoalsMinuteStruct: #{@minute}"
-    buf << "+#{@offset}"    if @offset && @offset > 0
-    buf << "'"
-    buf << " (o.g.)"  if @owngoal
-    buf << " (pen.)"  if @penalty
-    buf << ">"
-
-    printer.text( buf ) 
-  end
-end
-
-
-class GoalStruct
-  ######
-  # flat struct for goals - one entry per goals
-  attr_accessor :name
-  attr_accessor :team   #  1 or 2 ? check/todo: add team1 or team2 flag?
-  attr_accessor :minute, :offset
-  attr_accessor :penalty, :owngoal
-  attr_accessor :score1, :score2  # gets calculated
-
-  ## add pos  for sequence number? e.g. 1,2,3,4  (1st goald, 2nd goal, etc.) ???
-
-
-  def initialize( **kwargs )    ## add/allow quick and dirty quick init with keywords
-    if kwargs.empty?
-      # do nothing
-    else
-      kwargs.each do |key,value|
-        send( "#{key}=", value )
-      end
-    end
-  end
-
-  def ==(o)
-    o.class == self.class && o.state == state
-  end
-
-  def state
-    [@name, @team, @minute, @offset, @penalty, @owngoal, @score1, @score2]
-  end
-
-
-  def pretty_print( printer ) 
-    buf = String.new
-    buf << "<GoalStruct: #{@score1}-#{@score2} #{@name} #{@minute}"
-    buf << "+#{@offset}"    if @offset && @offset > 0
-    buf << "'"
-    buf << " (o.g.)"  if @owngoal
-    buf << " (pen.)"  if @penalty
-    buf << " for #{@team}"     ### team 1 or 2 - use home/away
-    buf << ">"
-
-    printer.text( buf ) 
-  end
-
-
-end
-
-
-
-# todo: find a better name? to avoid confusing w/ GoalsParser? use MatchGoalsParser or similar?
-class GoalsFinder
-  include LogUtils::Logging
-
-
-  def initialize
-    # nothing here for now
-  end
-
-  def find!( line, opts={} )
-    # remove end-of-line comments
-    line = line.sub( /#.*$/ ) do |_|
-             logger.debug "   cutting off end of line comment - >>#{$&}<<"
-             ''
-           end
-
-    # remove [] if presents e.g. [Neymar 12']
-    line = line.gsub( /[\[\]]/, '' )
-    # remove (single match) if line starts w/ - (allow spaces)  e.g. [-;Neymar 12'] or [ - ;Neymar 12']
-    line = line.sub( /^[ ]*-[ ]*/, '' )
-
-    # split into left hand side (lhs) for team1 and
-    #            right hand side (rhs) for team2
-
-    values = line.split( ';' )
-
-    # note: allow empty right hand side (e.g. team2 did NOT score any goals e.g. 3-0 etc.)
-    lhs = values[0]
-    rhs = values[1]
-
-    lhs = lhs.strip   unless lhs.nil?
-    rhs = rhs.strip   unless rhs.nil?
-
-    parser = GoalsParser.new
-    ## todo/check: only call if not nil?
-
-    logger.debug "  lhs (team1): >#{lhs}<"
-    lhs_data = parser.parse!( lhs )
-    pp lhs_data
-
-    logger.debug "  rhs (team2): >#{rhs}<"
-    rhs_data = parser.parse!( rhs )
-    pp rhs_data
-
-    ### merge into flat goal structs
-    goals = []
-    lhs_data.each do |player|
-      player.minutes.each do |minute|
-        goal = GoalStruct.new
-        goal.name    = player.name
-        goal.team    = 1
-        goal.minute  = minute.minute
-        goal.offset  = minute.offset
-        goal.penalty = minute.penalty
-        goal.owngoal = minute.owngoal
-        goals << goal
-      end
-    end
-
-    rhs_data.each do |player|
-      player.minutes.each do |minute|
-        goal = GoalStruct.new
-        goal.name    = player.name
-        goal.team    = 2
-        goal.minute  = minute.minute
-        goal.offset  = minute.offset
-        goal.penalty = minute.penalty
-        goal.owngoal = minute.owngoal
-        goals << goal
-      end
-    end
-
-
-    # sort by minute + offset
-    goals = goals.sort do |l,r|
-      res = l.minute <=> r.minute
-      if res == 0
-        res =  l.offset <=> r.offset  # pass 2: sort by offset
-      end
-      res
-    end
-
-    ## calc score1,score2
-    score1 = 0
-    score2 = 0
-    goals.each do |goal|
-      if goal.team == 1
-        score1 += 1
-      elsif goal.team == 2
-        score2 += 1
-      else
-        # todo: should not happen: issue warning
-      end
-      goal.score1 = score1
-      goal.score2 = score2
-    end
-
-    logger.debug "  #{goals.size} goals:"
-    pp goals
-
-    goals
-  end
-
-end  # class GoalsFinder
-
-
-class GoalsParser
-  include LogUtils::Logging
-
-
-  # note: use ^ for start of string only!!!
-  # - for now slurp everything up to digits (inlc. spaces - use strip to remove)
-  # todo/check: use/rename to NAME_UNTIL_REGEX ??? ( add lookahead for spaces?)
-  NAME_REGEX = /^
-                [^0-9]+
-               /x
-
-
-  # todo/check: change to MINUTE_REGEX ??
-  # add MINUTE_SKIP_REGEX or MINUTE_SEP_REGEX /^[ ,]+/
-  # todo/fix:  split out  penalty and owngoal flag in PATTERN constant for reuse
-  MINUTES_REGEX = /^      # note: use ^ for start of string only!!!
-                    (?<minute>[0-9]{1,3})
-                    (?:\+
-                      (?<offset>[1-9]{1})
-                    )?
-                    '
-                    (?:[ ]*
-                      \(
-                      (?<type>P|pen\.|o\.g\.)
-                      \)
-                    )?
-                  /x
-
-
-
-  def initialize
-    # nothing here for now
-  end
-
-  def parse!( line, opts={} )
-
-    ## for now assume
-    ##    everything up-to  0-9 and , and () is part of player name
-
-    ## try parsing lhs
-    ##  todo: check for  empty -    remove (make it same as empty string)
-
-    players = []
-
-    name = get_player_name!( line )
-    while name
-      logger.debug "  found player name >#{name}< - remaining >#{line}<"
-
-      player = GoalsPlayerStruct.new
-      player.name = name
-
-      minute_hash = get_minute_hash!( line )
-      while minute_hash
-        logger.debug "  found minutes >#{minute_hash.inspect}< - remaining >#{line}<"
-
-        minute = GoalsMinuteStruct.new
-        minute.minute = minute_hash[:minute].to_i
-        minute.offset = minute_hash[:offset].to_i  if minute_hash[:offset]
-        if minute_hash[:type]
-          minute.owngoal = true  if minute_hash[:type] =~ /o\.g\./
-          minute.penalty = true  if minute_hash[:type] =~ /P|pen\./
-        end
-        player.minutes << minute
-
-        # remove commas and spaces (note: use ^ for start of string only!!!)
-        line.sub!( /^[ ,]+/, '' )
-        minute_hash = get_minute_hash!( line )
-      end
-
-      players << player
-      name = get_player_name!( line )
-    end
-
-    players
-  end   # method parse!
-
-private
-  def get_player_name!( line )
-    m = NAME_REGEX.match( line )
-    if m
-      ## remove from line
-      line.slice!( 0...m[0].length )
-      m[0].strip    # remove leading and trailing spaces
-    else
-      nil
-    end
-  end
-
-  def get_minute_hash!( line )
-    m = MINUTES_REGEX.match( line ) # note: use ^ for start of string only!!!
-    if m
-      h = {}
-      # - note: do NOT forget to turn name into symbol for lookup in new hash (name.to_sym)
-      m.names.each { |n| h[n.to_sym] = m[n] } # or use match_data.names.zip( match_data.captures ) - more cryptic but "elegant"??
-
-      ## remove matched string from line
-      line.slice!( 0...m[0].length )
-      h
-    else
-      nil
-    end
-  end
-
-end # class GoalsParser
-
-end # module SportDb

data/lib/sportdb/formats/lines_reader.rb

@@ -1,47 +0,0 @@
-
-module SportDb
-
-class LinesReader   ## change to LinesEnumerator - why? why not?
-        def initialize( lines )
-            @iter = lines.each  ## get (external) enumerator (same as to_enum)
-            @lineno = 0
-        end
-    
-        def each( &blk )
-        ## note - StopIteration is rescued (automagically) by Kernel#loop.
-        ##            no need to rescue ourselves here
-            loop do
-              line = @iter.next   ## note - raises StopIteration  
-              blk.call( line )
-            end
-        end
-    
-        def each_with_index( &blk )
-            ## note - StopIteration is rescued (automagically) by Kernel#loop.
-                loop do
-                  line = @iter.next   ## note - raises StopIteration 
-                  blk.call( line, @lineno )
-                  @lineno += 1
-                end
-        end
-        
-        def peek
-            begin  
-              @iter.peek
-            rescue StopIteration
-                nil
-            end
-        end
-    
-        def next
-            ## todo/check - do NOT catch StopIteration for next - why? why not?
-            begin
-                line = @iter.next
-                @lineno += 1
-                line
-            rescue StopIteration
-                nil
-            end
-        end    
-end  # class LinesReader  
-end # module SportDb