sportdb 1.6.12 → 1.6.13

data/Manifest.txt

@@ -42,6 +42,7 @@ lib/sportdb/models/track.rb
 lib/sportdb/reader.rb
 lib/sportdb/schema.rb
 lib/sportdb/stats.rb
+lib/sportdb/title.rb
 lib/sportdb/utils.rb
 lib/sportdb/version.rb
 tasks/test.rb

data/lib/sportdb.rb

@@ -28,6 +28,7 @@ require 'worlddb'
 
 require 'sportdb/version'
 
+require 'sportdb/title'   ## fix - move to textutils gem
 require 'sportdb/models/forward'
 require 'sportdb/models/badge'
 require 'sportdb/models/city'

data/lib/sportdb/models/event.rb

@@ -48,7 +48,7 @@ class Event < ActiveRecord::Base
 
 
   def known_teams_table
-    @known_teams_table ||= build_match_table_for( teams )
+    @known_teams_table ||= TextUtils.build_title_table_for( teams )
   end # method known_teams_table
 
 end # class Event

data/lib/sportdb/models/league.rb

@@ -34,6 +34,8 @@ class League < ActiveRecord::Base
       end
     end
 
+    logger.debug " find league key: #{new_attributes[ :key ]}"
+
     rec = League.find_by_key( new_attributes[ :key ] )
     if rec.present?
       logger.debug "update League #{rec.id}-#{rec.key}:"

data/lib/sportdb/models/person.rb

@@ -28,6 +28,14 @@ class Person < ActiveRecord::Base
       if value =~ /^[a-z]{2}$/  ## assume two-letter country key e.g. at,de,mx,etc.
         value_country = Country.find_by_key!( value )
         new_attributes[ :country_id ] = value_country.id
+      elsif value =~ /^[A-Z]{3}$/  ## assume three-letter code e.g. AUS, MAL, etc.
+        new_attributes[ :code ] = value
+      elsif value =~ /^([0-9]{1,2})\s(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s([0-9]{4})$/  ## assume birthday
+        value_date_str = '%02d/%s/%d' % [$1, $2, $3]     ## move to matcher!!
+        value_date = Date.strptime( value_date_str, '%d/%b/%Y' )  ## %b - abbreviated month name (e.g. Jan,Feb, etc.)
+        logger.debug "   birthday #{value_date_str}  -  #{value_date}"
+        new_attributes[ :born_at ] = value_date
+        ## todo: convert to date
       else
         ## todo: assume title2 ??
         ## assume title2 if title2 is empty (not already in use)

data/lib/sportdb/models/track.rb

@@ -13,7 +13,7 @@ class Track < ActiveRecord::Base
   ### fix: move known_tracks_table to event!!! (e.g. scoped by event)
 
   def self.known_tracks_table
-    @@known_tracks_table ||= build_match_table_for( Track.all )
+    @@known_tracks_table ||= TextUtils.build_title_table_for( Track.all )
   end # method known_tracks_table
 
 
@@ -27,6 +27,8 @@ class Track < ActiveRecord::Base
       if value =~ /^[a-z]{2}$/  ## assume two-letter country key e.g. at,de,mx,etc.
         value_country = Country.find_by_key!( value )
         new_attributes[ :country_id ] = value_country.id
+      elsif value =~ /^[A-Z]{3}$/  ## assume three-letter code e.g. AUS, MAL, etc.
+        new_attributes[ :code ] = value
       else
         ## todo: assume title2 ??
         ## assume title2 if title2 is empty (not already in use)

data/lib/sportdb/reader.rb

@@ -94,7 +94,10 @@ class Reader
         elsif name =~ /\/squads/ || name =~ /\/rosters/  # e.g. 2013/squads.txt in formula1.db
           load_rosters( name )
         elsif name =~ /\/([0-9]{2})-/
-          load_records( name ) # e.g. 2013/04-gp-monaco.txt in formula1.db
+          race_pos = $1.to_i
+          # NB: assume @event is set from previous load 
+          race = Race.find_by_event_id_and_pos( @event.id, race_pos )
+          load_records( name, race_id: race.id ) # e.g. 2013/04-gp-monaco.txt in formula1.db
         elsif name =~ /^seasons/
           load_seasons( name )
         elsif name =~ /^leagues/
@@ -187,7 +190,11 @@ class Reader
 
   def load_seasons( name )
 
-    reader = HashReaderV2.new( name, include_path )
+    path = "#{include_path}/#{name}.yml"
+
+    logger.info "parsing data '#{name}' (#{path})..."
+
+    reader = HashReader.new( path )
 
 ####
 ## fix!!!!!
@@ -207,6 +214,7 @@ class Reader
         value.each do |item|
           season_attribs = {}
           
+          logger.debug "  find season key: #{item.to_s.strip}"
           season = Season.find_by_key( item.to_s.strip )
 
           ## check if it exists
@@ -231,9 +239,47 @@ class Reader
   
     end # each key,value
 
+    Prop.create_from_fixture!( name, path )
+
   end  # load_seasons
 
 
+  def fetch_event( name )
+    # get/fetch/find event from yml file
+
+    path = "#{include_path}/#{name}.yml"
+
+    logger.info "parsing data '#{name}' (#{path})..."
+
+
+    ## todo/fix: use h = HashFile.load( path ) or similar instead of HashReader!!
+
+    reader = HashReader.new( path )
+
+    event_attribs = {}
+
+    reader.each_typed do |key, value|
+
+      ## puts "processing event attrib >>#{key}<< >>#{value}<<..."
+
+      if key == 'league'
+        league = League.find_by_key!( value.to_s.strip )
+        event_attribs[ 'league_id' ] = league.id
+      elsif key == 'season'
+        season = Season.find_by_key!( value.to_s.strip )
+        event_attribs[ 'season_id' ] = season.id
+      else
+        # skip; do nothing
+      end
+    end # each key,value
+
+    league_id = event_attribs['league_id']
+    season_id = event_attribs['season_id']
+    
+    event = Event.find_by_league_id_and_season_id!( league_id, season_id )
+    event
+  end
+
 
   def load_event( name )
 
@@ -243,7 +289,11 @@ class Reader
 ##   use Event.create_or_update_from_hash_reader?? or similar
 #   move parsing code to model
 
-    reader = HashReaderV2.new( name, include_path )
+    path = "#{include_path}/#{name}.yml"
+
+    logger.info "parsing data '#{name}' (#{path})..."
+
+    reader = HashReader.new( path )
 
     event_attribs = {}
 
@@ -306,7 +356,12 @@ class Reader
   
     end # each key,value
 
-    event = Event.find_by_league_id_and_season_id( event_attribs['league_id'], event_attribs['season_id'])
+    league_id = event_attribs['league_id']
+    season_id = event_attribs['season_id']
+
+    logger.debug "find event - league_id: #{league_id}, season_id: #{season_id}"
+
+    event = Event.find_by_league_id_and_season_id( league_id, season_id )
 
     ## check if it exists
     if event.present?
@@ -320,6 +375,8 @@ class Reader
     
     event.update_attributes!( event_attribs )
 
+    Prop.create_from_fixture!( name, path )
+
   end  # load_event
 
 
@@ -351,7 +408,7 @@ class Reader
 
 
 
-  def load_records( name )
+  def load_records( name, more_attribs={} )
     path = "#{include_path}/#{name}.txt"
 
     logger.info "parsing data '#{name}' (#{path})..."
@@ -364,30 +421,66 @@ class Reader
     # @known_tracks = Track.known_tracks_table
 
     ## fix: add @known_teams  - for now; use teams (not scoped by event)
+    @known_teams   = TextUtils.build_title_table_for( Team.all )
+    ## and for now use all persons
+    @known_persons = TextUtils.build_title_table_for( Person.all )
 
-    load_records_worker( reader )
+    load_records_worker( reader, more_attribs )
 
     Prop.create_from_fixture!( name, path )
   end
 
-  def load_records_worker( reader )
+  def load_records_worker( reader, more_attribs )
 
     reader.each_line do |line|
       logger.debug "  line: >#{line}<"
 
-      ### fix: use new find_leading_pos!
-      # pos = find_game_pos!( line )  # alias -> rename to find_pos! or better use find_leading_pos!( line )
+      cut_off_end_of_line_comment!( line )
 
-      # match_person!( line )
+      state = find_record_leading_state!( line )
 
-      # match_teams!( line )
+      map_team!( line )
+      team_key = find_team!( line )
+      team = Team.find_by_key!( team_key )
+
+      map_person!( line )
+      person_key = find_person!( line )
+      person = Person.find_by_key!( person_key )
+
+      timeline = find_record_timeline!( line )
+
+      laps  = find_record_laps!( line )
+      
+      comment = find_record_comment!( line )
+
+      logger.debug "  line2: >#{line}<"
 
       record_attribs = {
-      #  pos:  pos,
-      #  team_key: team_key   # fix: use team_id
+        state:  state,
+        ## team_id: team.id,   ## NB: not needed for db 
+        person_id: person.id,
+        timeline: timeline,
+        comment: comment,
+        laps: laps
       }
 
-      pp record_attribs
+      record_attribs = record_attribs.merge( more_attribs )
+
+      ### check if record exists
+      record = Record.find_by_race_id_and_person_id( record_attribs[ :race_id ],
+                                                     record_attribs[ :person_id ])
+
+      if record.present?
+        logger.debug "update Record #{record.id}:"
+      else
+        logger.debug "create Record:"
+        record = Record.new
+      end
+
+      logger.debug record_attribs.to_json
+
+      record.update_attributes!( record_attribs )
+
     end # lines.each
 
   end # method load_record_worker
@@ -407,11 +500,15 @@ class Reader
     # @known_tracks = Track.known_tracks_table
 
     ## fix: add @known_teams  - for now; use teams (not scoped by event)
+    ## for now use all teams
+    @known_teams   = TextUtils.build_title_table_for( Team.all )
+    ## and for now use all persons
+    @known_persons = TextUtils.build_title_table_for( Person.all )
+
 
     load_rosters_worker( reader )
 
-    Prop.create_from_fixture!( name, path )
-  
+    Prop.create_from_fixture!( name, path )  
   end
 
   def load_rosters_worker( reader )
@@ -419,19 +516,40 @@ class Reader
     reader.each_line do |line|
       logger.debug "  line: >#{line}<"
 
-      ### fix: use new find_leading_pos!
-      pos = find_game_pos!( line )  # alias -> rename to find_pos! or better use find_leading_pos!( line )
+      cut_off_end_of_line_comment!( line )
+
+      pos = find_leading_pos!( line )
+
+      map_team!( line )
+      team_key = find_team!( line )
+      team = Team.find_by_key!( team_key )
+
+      map_person!( line )
+      person_key = find_person!( line )
+      person = Person.find_by_key!( person_key )
 
-      # match_person!( line )
+      logger.debug "  line2: >#{line}<"
 
-      # match_teams!( line )
+      ### check if roster record exists
+      roster = Roster.find_by_event_id_and_team_id_and_person_id( @event.id, team.id, person.id )
+
+      if roster.present?
+        logger.debug "update Roster #{roster.id}:"
+      else
+        logger.debug "create Roster:"
+        roster = Roster.new
+      end
 
       roster_attribs = {
-        pos:  pos,
-      #  team_key: team_key   # fix: use team_id
+        pos:       pos,
+        team_id:   team.id,
+        person_id: person.id,
+        event_id:  @event.id   # NB: reuse/fallthrough from races - make sure load_races goes first (to setup event)
       }
 
-      pp roster_attribs
+      logger.debug roster_attribs.to_json
+
+      roster.update_attributes!( roster_attribs )
     end # lines.each
 
   end # method load_rosters_worker
@@ -439,6 +557,11 @@ class Reader
 
 
   def load_races( name )
+    load_event( name )   # must have .yml file with same name for event definition
+    @event = fetch_event( name )
+
+    logger.info "  event: #{@event.key} >>#{@event.full_title}<<"
+
     path = "#{include_path}/#{name}.txt"
 
     logger.info "parsing data '#{name}' (#{path})..."
@@ -453,28 +576,46 @@ class Reader
     load_races_worker( reader )
 
     Prop.create_from_fixture!( name, path )
-  
   end
 
+
   def load_races_worker( reader )
 
     reader.each_line do |line|
       logger.debug "  line: >#{line}<"
 
-      ### fix: use new find_leading_pos!
-      pos = find_game_pos!( line )  # alias -> rename to find_pos! or better use find_leading_pos!( line )
+      cut_off_end_of_line_comment!( line )
+
+      pos = find_leading_pos!( line )
 
-      match_track!( line )
+      map_track!( line )
       track_key = find_track!( line )
+      track = Track.find_by_key!( track_key )
+
       date      = find_date!( line )
-      
+
+      logger.debug "  line2: >#{line}<"
+
+      ### check if games exists
+      race = Race.find_by_event_id_and_track_id( @event.id, track.id )
+
+      if race.present?
+        logger.debug "update race #{race.id}:"
+      else
+        logger.debug "create race:"
+        race = Race.new
+      end
+          
       race_attribs = {
-        pos:  pos,
-        track_key: track_key,   # fix: use track_id
-        start_at:  date
+        pos:      pos,
+        track_id: track.id,
+        start_at:  date,
+        event_id:  @event.id
       }
 
-      pp race_attribs
+      logger.debug race_attribs.to_json
+
+      race.update_attributes!( race_attribs )
     end # lines.each
 
   end # method load_races_worker

data/lib/sportdb/schema.rb

@@ -27,6 +27,7 @@ create_table :persons do |t|    # use people ? instead of persons (person/person
   t.string      :key,      :null => false   # import/export key
   t.string      :name,     :null => false
   t.string      :synonyms  # comma separated list of synonyms
+  t.string      :code       # three letter code (short title)
 
   ## todo: add gender flag (male/female -man/lady  how?)
   t.date        :born_at     # optional date of birth (birthday)
@@ -61,7 +62,8 @@ end
 create_table :tracks do |t|    # e.g. Formula 1 circuits or Apline Ski resorts/slops/pistes
   t.string      :key,      :null => false   # import/export key
   t.string      :title,     :null => false
-  t.string      :synonyms  # comma separated list of synonyms
+  t.string      :synonyms   # comma separated list of synonyms
+  t.string      :code       # three letter code (short title)
 
   t.references  :city
   t.references  :region

data/lib/sportdb/title.rb

@@ -0,0 +1,146 @@
+# encoding: utf-8
+
+################
+# todo: move module to textutils!!!
+
+### fix: move to textutils??
+
+
+## todo: rename to  TitleHelpers? TitleMatcher? TitleMapper? TitleMapping? TitleMappings? TitleFinder? TitleHelpers?
+#   or rename to KeyMapping?, KeyMapper?, KeyTable? etc.
+
+
+module TextUtils::TitleTable
+
+
+def build_title_table_for( records )
+    ## build known tracks table w/ synonyms e.g.
+    #
+    # [[ 'wolfsbrug', [ 'VfL Wolfsburg' ]],
+    #  [ 'augsburg',  [ 'FC Augsburg', 'Augi2', 'Augi3' ]],
+    #  [ 'stuttgart', [ 'VfB Stuttgart' ]] ]
+
+    known_titles = []
+
+    records.each_with_index do |rec,index|
+
+      title_candidates = []
+      title_candidates << rec.title
+
+      title_candidates += rec.synonyms.split('|') if rec.synonyms.present?
+
+
+      ## check if title includes subtitle e.g. Grand Prix Japan (Suzuka Circuit)
+      #  make subtitle optional by adding title w/o subtitle e.g. Grand Prix Japan
+
+      titles = []
+      title_candidates.each do |t|
+        titles << t
+        if t =~ /\(.+\)/
+          extra_title = t.gsub( /\(.+\)/, '' ) # remove/delete subtitles
+          extra_title.strip!   # strip leading n trailing withspaces too!
+          titles << extra_title
+        end
+      end
+
+
+      ## NB: sort here by length (largest goes first - best match)
+      #  exclude code and key (key should always go last)
+      titles = titles.sort { |left,right| right.length <=> left.length }
+      
+      ## escape for regex plus allow subs for special chars/accents
+      titles = titles.map { |title| TextUtils.title_esc_regex( title )  }
+
+      ## NB: only include code field - if defined
+      titles << rec.code          if rec.respond_to?(:code) && rec.code.present?
+
+      known_titles << [ rec.key, titles ]
+
+      ### fix: use plain logger
+      LogUtils::Logger.root.debug "  #{rec.class.name}[#{index+1}] #{rec.key} >#{titles.join('|')}<"
+    end
+
+    known_titles
+end
+
+
+
+def find_key_for!( name, line )
+  regex = /@@oo([^@]+?)oo@@/     # e.g. everything in @@ .... @@ (use non-greedy +? plus all chars but not @, that is [^@])
+
+  upcase_name   = name.upcase
+  downcase_name = name.downcase
+
+  if line =~ regex
+    value = "#{$1}"
+    ### fix: use plain logger
+    LogUtils::Logger.root.debug "   #{downcase_name}: >#{value}<"
+      
+    line.sub!( regex, "[#{upcase_name}]" )
+
+    return $1
+  else
+    return nil
+  end
+end
+
+
+def find_keys_for!( name, line )  # NB: keys (plural!) - will return array
+  counter = 1
+  keys = []
+
+  downcase_name = name.downcase
+
+  key = find_key_for!( "#{downcase_name}#{counter}", line )
+  while key.present?
+    keys << key
+    counter += 1
+    key = find_key_for!( "#{downcase_name}#{counter}", line )
+  end
+
+  keys
+end
+
+
+def map_titles_for!( name, line, title_table )
+  title_table.each do |rec|
+    key    = rec[0]
+    values = rec[1]
+    map_title_worker_for!( name, line, key, values )
+  end
+end
+
+
+def map_title_worker_for!( name, line, key, values )
+
+  downcase_name = name.downcase
+
+  values.each do |value|
+    ## nb: \b does NOT include space or newline for word boundry (only alphanums e.g. a-z0-9)
+    ## (thus add it, allows match for Benfica Lis.  for example - note . at the end)
+
+    ## check add $ e.g. (\b| |\t|$) does this work? - check w/ Benfica Lis.$
+    regex = /\b#{value}(\b| |\t|$)/   # wrap with world boundry (e.g. match only whole words e.g. not wac in wacker) 
+    if line =~ regex
+      ### fix: use plain logger
+      LogUtils::Logger.root.debug "     match for #{downcase_name}  >#{key}< >#{value}<"
+      # make sure @@oo{key}oo@@ doesn't match itself with other key e.g. wacker, wac, etc.
+      line.sub!( regex, "@@oo#{key}oo@@ " )    # NB: add one space char at end
+      return true    # break out after first match (do NOT continue)
+    end
+  end
+  return false
+end
+
+
+
+end # module TextUtils::TitleTable
+
+
+
+## auto-include methods
+
+module TextUtils
+  # make helpers available as class methods e.g. TextUtils.convert_unicode_dashes_to_plain_ascii
+  extend TitleTable  # lets us use TextUtils.build_title_table_for etc.
+end

data/lib/sportdb/utils.rb

@@ -1,48 +1,6 @@
 # encoding: utf-8
 
-### some utils moved to worldbdb/utils for reuse
-
-
-### fix: move to textutils??
-
-
-def build_match_table_for( recs )
-    ## build known tracks table w/ synonyms e.g.
-    #
-    # [[ 'wolfsbrug', [ 'VfL Wolfsburg' ]],
-    #  [ 'augsburg',  [ 'FC Augsburg', 'Augi2', 'Augi3' ]],
-    #  [ 'stuttgart', [ 'VfB Stuttgart' ]] ]
- 
-    known_titles = []
-
-    recs.each_with_index do |rec,index|
-
-      titles = []
-      titles << rec.title
-      titles += rec.synonyms.split('|') if rec.synonyms.present?
-      
-      ## NB: sort here by length (largest goes first - best match)
-      #  exclude code and key (key should always go last)
-      titles = titles.sort { |left,right| right.length <=> left.length }
-      
-      ## escape for regex plus allow subs for special chars/accents
-      titles = titles.map { |title| TextUtils.title_esc_regex( title )  }
-
-      ## NB: only include code field - if defined
-      titles << rec.code          if rec.respond_to?(:code) && rec.code.present?
-
-      known_titles << [ rec.key, titles ]
-
-      ### fix:
-      ## plain logger
-
-      LogUtils::Logger.root.debug "  #{rec.class.name}[#{index+1}] #{rec.key} >#{titles.join('|')}<"
-    end
-
-    known_titles
-end
-
-
+### note: some utils moved to worldbdb/utils for reuse
 
 
 module SportDb::FixtureHelpers
@@ -116,11 +74,16 @@ module SportDb::FixtureHelpers
     return [title,pos]
   end
 
+
   def cut_off_end_of_line_comment!( line )
     #  cut off (that is, remove) optional end of line comment starting w/ #
     
-    line = line.sub( /#.*$/, '' )
-    line
+    line.sub!( /#.*$/ ) do |_|
+      logger.debug "   cutting off end of line comment - >>#{$&}<<"
+      ''
+    end
+    
+    # NB: line = line.sub  will NOT work - thus, lets use line.sub!
   end
 
 
@@ -204,15 +167,21 @@ module SportDb::FixtureHelpers
     #  nb: allow 2.3.2012 e.g. no leading zero required
     #  nb: allow hour as 20.30  or 3.30 instead of 03.30
     regex_de = /\b(\d{1,2})\.(\d{1,2})\.\s+(\d{1,2})[:.](\d{2})\b/
-    
+
     # e.g. 14.09.2012 20:30   => DD.MM.YYYY HH:MM
     #  nb: allow 2.3.2012 e.g. no leading zero required
     #  nb: allow hour as 20.30
     regex_de2 = /\b(\d{1,2})\.(\d{1,2})\.(\d{4})\s+(\d{1,2})[:.](\d{2})\b/
 
 
+    month_abbrev_en = "Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec"
+
+    # e.g. 12 May 2013 14:00  => D|DD.MMM.YYYY H|HH:MM
+    regex_en = /\b(\d{1,2})\s(#{month_abbrev_en})\s(\d{4})\s+(\d{1,2}):(\d{2})\b/
+
+
     if line =~ regex_db
-      value = "#{$1}-#{$2}-#{$3} #{$4}:#{$5}"
+      value = '%d-%02d-%02d %02d:%02d' % [$1, $2, $3, $4, $5]
       logger.debug "   date: >#{value}<"
 
       ## todo: lets you configure year
@@ -222,14 +191,14 @@ module SportDb::FixtureHelpers
 
       return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
     elsif line =~ regex_db2
-      value = "#{$1}-#{$2}-#{$3} 12:00"
+      value = '%d-%02d-%02d 12:00' % [$1, $2, $3]
       logger.debug "   date: >#{value}<"
-      
+
       line.sub!( regex_db2, '[DATE.DB2]' )
 
       return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
     elsif line =~ regex_de2
-      value = "#{$3}-#{$2}-#{$1} #{$4}:#{$5}"
+      value = '%d-%02d-%02d %02d:%02d' % [$3, $2, $1, $4, $5]
       logger.debug "   date: >#{value}<"
 
       ## todo: lets you configure year
@@ -243,8 +212,8 @@ module SportDb::FixtureHelpers
       #### fix/todo:
       #  get year from event start date!!!!
       #  do NOT hard code!!!!
-      
-      value = "2012-#{$2}-#{$1} #{$3}:#{$4}"
+
+      value = '2012-%02d-%02d %02d:%02d' % [$2, $1, $3, $4]
       logger.debug "   date: >#{value}<"
 
       ## todo: lets you configure year
@@ -253,13 +222,103 @@ module SportDb::FixtureHelpers
       line.sub!( regex_de, '[DATE.DE]' )
 
       return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_en
+      value = '%d-%s-%02d %02d:%02d' % [$3, $2, $1, $4, $5]
+      logger.debug "   date: >#{value}<"
+
+      line.sub!( regex_en, '[DATE.EN]' )
+
+      return DateTime.strptime( value, '%Y-%b-%d %H:%M' )   ## %b - abbreviated month name (e.g. Jan,Feb, etc.)
     else
       return nil
     end
   end
 
 
-  def find_game_pos!( line )
+  def find_record_comment!( line )
+    # assume everything left after the last record marker,that is, ] is a record comment
+
+    regex = /]([^\]]+?)$/   # NB: use non-greedy +?
+
+    if line =~ regex
+      value = $1.strip
+      return nil if value.blank?   # skip whitespaces only
+
+      logger.debug "   comment: >#{value}<"
+
+      line.sub!( value, '[REC.COMMENT] ' )
+      return value
+    else
+      return nil
+    end
+  end
+
+
+  def find_record_timeline!( line )
+
+    #  +1 lap or +n laps
+    regex_laps = /\s+\+\d{1,2}\s(lap|laps)\b/
+
+    #  2:17:15.123
+    regex_time = /\b\d{1,2}:\d{2}:\d{2}\.\d{1,3}\b/
+
+    #  +40.1 secs
+    regex_secs = /\s+\+\d{1,3}\.\d{1,3}\s(secs)\b/   # NB: before \+ - boundry (\b) will not work 
+
+    # NB: $& contains the complete matched text
+
+    if line =~ regex_laps
+      value = $&.strip
+      logger.debug "   timeline.laps: >#{value}<"
+
+      line.sub!( value, '[REC.TIMELINE.LAPS] ' ) # NB: add trailing space
+      return value
+    elsif line =~ regex_time
+      value = $&.strip
+      logger.debug "   timeline.time: >#{value}<"
+
+      line.sub!( value, '[REC.TIMELINE.TIME] ' ) # NB: add trailing space
+      return value
+    elsif line =~ regex_secs
+      value = $&.strip
+      logger.debug "   timeline.secs: >#{value}<"
+
+      line.sub!( value, '[REC.TIMELINE.SECS] ' ) # NB: add trailing space
+      return value
+    else
+      return nil
+    end
+  end
+
+  def find_record_laps!( line )
+    # e.g.  first free-standing number w/ one or two digits e.g. 7 or 28 etc.
+    regex = /\b(\d{1,2})\b/
+    if line =~ regex
+      logger.debug "   laps: >#{$1}<"
+      
+      line.sub!( regex, '[REC.LAPS] ' ) # NB: add trailing space
+      return $1.to_i
+    else
+      return nil
+    end
+  end
+
+  def find_record_leading_state!( line )
+    # e.g.  1|2|3|etc or Ret  - must start line 
+    regex = /^[ \t]*(\d{1,3}|Ret)[ \t]+/
+    if line =~ regex
+      value = $1.dup
+      logger.debug "   state: >#{value}<"
+
+      line.sub!( regex, '[REC.STATE] ' ) # NB: add trailing space
+      return value
+    else
+      return nil
+    end
+  end
+
+
+  def find_leading_pos!( line )
     # extract optional game pos from line
     # and return it
     # NB: side effect - removes pos from line string
@@ -268,13 +327,17 @@ module SportDb::FixtureHelpers
     regex = /^[ \t]*\((\d{1,3})\)[ \t]+/
     if line =~ regex
       logger.debug "   pos: >#{$1}<"
-      
-      line.sub!( regex, '[POS] ' )
+
+      line.sub!( regex, '[POS] ' ) # NB: add trailing space
       return $1.to_i
     else
       return nil
     end
+  end
 
+  def find_game_pos!( line )
+    ## fix: add depreciation warning - remove - use find_leading_pos!
+    find_leading_pos!( line )
   end
 
   def find_scores!( line )
@@ -330,99 +393,62 @@ module SportDb::FixtureHelpers
   end # methdod find_scores!
 
 
-  ## todo/fix:
-  #   find a better name find_xxx_by_title ?? find_xxx_w_match_table? or similiar
-  #  move to its own file/module for easier maintance
-  #    include build_match_table_for
-  #  - lets us change internals e.g. lets improve matcher using a reverse index, for example
-
-  def find_xxx_worker!( name, line )
-    regex = /@@oo([^@]+?)oo@@/     # e.g. everything in @@ .... @@ (use non-greedy +? plus all chars but not @, that is [^@])
-
-    upcase_name   = name.upcase
-    downcase_name = name.downcase
-
-    if line =~ regex
-      value = "#{$1}"
-      logger.debug "   #{downcase_name}: >#{value}<"
-      
-      line.sub!( regex, "[#{upcase_name}]" )
-
-      return $1
-    else
-      return nil
-    end
-  end
-
-
-  def match_xxx_worker!( name, line, key, values )
-
-    downcase_name = name.downcase
 
-    values.each do |value|
-      ## nb: \b does NOT include space or newline for word boundry (only alphanums e.g. a-z0-9)
-      ## (thus add it, allows match for Benfica Lis.  for example - note . at the end)
-
-      ## check add $ e.g. (\b| |\t|$) does this work? - check w/ Benfica Lis.$
-      regex = /\b#{value}(\b| |\t|$)/   # wrap with world boundry (e.g. match only whole words e.g. not wac in wacker) 
-      if line =~ regex
-        logger.debug "     match for #{downcase_name}  >#{key}< >#{value}<"
-        # make sure @@oo{key}oo@@ doesn't match itself with other key e.g. wacker, wac, etc.
-        line.sub!( regex, "@@oo#{key}oo@@ " )    # NB: add one space char at end
-        return true    # break out after first match (do NOT continue)
-      end
-    end
-    return false
+  def find_teams!( line ) # NB: returns an array - note: plural! (teamsss)
+    TextUtils.find_keys_for!( 'team', line )
   end
-
-
-
-  def find_teams!( line )
-    counter = 1
-    teams = []
-
-    team = find_xxx_worker!( "team#{counter}", line )
-    while team.present?
-      teams << team
-      counter += 1
-      team = find_xxx_worker!( "team#{counter}", line )
-    end
-
-    teams
+  
+  def find_team!( line )  # NB: returns key (string or nil)
+    TextUtils.find_key_for!( 'team', line )
   end
 
   ## todo: check if find_team1 gets used?  if not remove it!!  use find_teams!
   def find_team1!( line )
-    find_xxx_worker!( 'team1', line )
+    TextUtils.find_key_for!( 'team1', line )
   end
-  
+
   def find_team2!( line )
-    find_xxx_worker!( 'team2', line )
+    TextUtils.find_key_for!( 'team2', line )
   end
 
- 
   ## todo/fix: pass in known_teams as a parameter? why? why not?
-  def match_teams!( line )
-    @known_teams.each do |rec|
-      key    = rec[0]
-      values = rec[1]
-      match_xxx_worker!( 'team', line, key, values )
-    end # each known_teams
-  end # method match_teams!
-
 
+  def map_teams!( line )
+    TextUtils.map_titles_for!( 'team', line, @known_teams )
+  end
+  
+  def map_team!( line )  # alias map_teams!
+    map_teams!( line )
+  end
 
   def find_track!( line )
-    find_xxx_worker!( 'track', line )
+    TextUtils.find_key_for!( 'track', line )
   end
 
   ## todo/fix: pass in known_tracks as a parameter? why? why not?
-  def match_track!( line )
-    @known_tracks.each do |rec|
-      key    = rec[0]
-      values = rec[1]
-      match_xxx_worker!( 'track', line, key, values )
-    end # each known_tracks
+  def map_track!( line )
+    TextUtils.map_titles_for!( 'track', line, @known_tracks )
+  end
+
+  def find_person!( line )
+    TextUtils.find_key_for!( 'person', line )
+  end
+
+  def map_person!( line )
+    TextUtils.map_titles_for!( 'person', line, @known_persons)
+  end
+
+
+
+  ## depreciated methods - use map_
+  def match_teams!( line )   ## fix: rename to map_teams!! - remove match_teams!
+    ## todo: issue depreciated warning
+    map_teams!( line )
+  end # method match_teams!
+
+  def match_track!( line )  ## fix: rename to map_track!!!
+    ## todo: issue depreciated warning
+    map_track!( line )
   end # method match_tracks!
 
 

data/lib/sportdb/version.rb

@@ -1,6 +1,6 @@
 
 module SportDb
-  VERSION = '1.6.12'
+  VERSION = '1.6.13'
 end
 
 ###########################################

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sportdb
 version: !ruby/object:Gem::Version
-  version: 1.6.12
+  version: 1.6.13
   prerelease: 
 platform: ruby
 authors:
@@ -13,7 +13,7 @@ date: 2013-06-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: worlddb
-  requirement: &77877370 !ruby/object:Gem::Requirement
+  requirement: &72775370 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '1.7'
   type: :runtime
   prerelease: false
-  version_requirements: *77877370
+  version_requirements: *72775370
 - !ruby/object:Gem::Dependency
   name: commander
-  requirement: &77877150 !ruby/object:Gem::Requirement
+  requirement: &72775150 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: 4.1.3
   type: :runtime
   prerelease: false
-  version_requirements: *77877150
+  version_requirements: *72775150
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &77876930 !ruby/object:Gem::Requirement
+  requirement: &72774930 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +43,10 @@ dependencies:
         version: '3.10'
   type: :development
   prerelease: false
-  version_requirements: *77876930
+  version_requirements: *72774930
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &77876710 !ruby/object:Gem::Requirement
+  requirement: &72774710 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,7 +54,7 @@ dependencies:
         version: '3.3'
   type: :development
   prerelease: false
-  version_requirements: *77876710
+  version_requirements: *72774710
 description: sportdb - sport.db command line tool
 email: opensport@googlegroups.com
 executables:
@@ -107,6 +107,7 @@ files:
 - lib/sportdb/reader.rb
 - lib/sportdb/schema.rb
 - lib/sportdb/stats.rb
+- lib/sportdb/title.rb
 - lib/sportdb/utils.rb
 - lib/sportdb/version.rb
 - tasks/test.rb