sportdb 1.8.3 → 1.8.5

data/lib/sportdb/utils_date.rb

@@ -0,0 +1,222 @@
+# encoding: utf-8
+
+module SportDb
+  module FixtureHelpers
+
+  def is_postponed?( line )
+    # check if line include postponed marker e.g. =>
+    line =~ /=>/
+  end
+
+  def calculate_year( day, month, start_at )
+    if month >= start_at.month
+      # assume same year as start_at event (e.g. 2013 for 2013/14 season)
+      start_at.year
+    else
+      # assume year+1 as start_at event (e.g. 2014 for 2013/14 season)
+      start_at.year+1
+    end
+  end
+
+
+  def find_date!( line, opts={} )
+
+    ## NB: lets us pass in start_at/end_at date (for event)
+    #   for auto-complete year
+
+    # extract date from line
+    # and return it
+    # NB: side effect - removes date from line string
+    
+    # e.g. 2012-09-14 20:30   => YYYY-MM-DD HH:MM
+    #  nb: allow 2012-9-3 7:30 e.g. no leading zero required
+    regex_db = /\b(\d{4})-(\d{1,2})-(\d{1,2})\s+(\d{1,2}):(\d{2})\b/
+    
+    # e.g. 2012-09-14  w/ implied hours (set to 12:00)
+    #  nb: allow 2012-9-3 e.g. no leading zero required
+    regex_db2 = /\b(\d{4})-(\d{1,2})-(\d{1,2})\b/
+
+    # e.g. 14.09. 20:30  => DD.MM. HH:MM
+    #  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/
+
+    # e.g. 14.09.2012  => DD.MM.YYYY w/ implied hours (set to 12:00)
+    regex_de3 = /\b(\d{1,2})\.(\d{1,2})\.(\d{4})\b/
+
+    # e.g. 14.09.  => DD.MM. w/ implied year and implied hours (set to 12:00)
+    regex_de4 = /\b(\d{1,2})\.(\d{1,2})\.\s+/
+
+
+    # todo: make more generic for reuse
+    month_abbrev_en = 'Jan|Feb|March|Mar|April|Apr|May|June|Jun|July|Jul|Aug|Sept|Sep|Oct|Nov|Dec'
+    month_abbrev_en_to_i = {
+        'Jan' => 1,
+        'Feb' => 2,
+        'Mar' => 3, 'March' => 3,
+        'Apr' => 4, 'April' => 4,
+        'May' => 5,
+        'Jun' => 6, 'June' => 6,
+        'Jul' => 7, 'July' => 7,
+        'Aug' => 8,
+        'Sep' => 9, 'Sept' => 9,
+        'Oct' => 10,
+        'Nov' => 11,
+        'Dec' => 12 }
+
+
+    # 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/
+
+
+    # e.g.  Jun/12 14:00  w/ implied year H|HH:MM
+    regex_en2  = /\b(#{month_abbrev_en})\/(\d{1,2})\s+(\d{1,2}):(\d{2})\b/
+
+    # e.g.  Jun/12  w/ implied year and implied hours (set to 12:00)
+    regex_en21 = /\b(#{month_abbrev_en})\/(\d{1,2})\b/
+
+    # todo/fix - add de and es too!!
+    # note: in Austria - Jänner - in Deutschland Januar allow both ??
+    month_abbrev_de = 'J[aä]n|Feb|Mär|Apr|Mai|Jun|Jul|Aug|Sep|Okt|Nov|Dez'
+
+    month_abbrev_es = 'Enero|Ene|Feb|Marzo|Mar|Abril|Abr|Mayo|May|Junio|Jun|Julio|Jul|Agosto|Ago|Sept|Set|Sep|Oct|Nov|Dic'
+    month_abbrev_es_to_i = {
+        'Ene' => 1, 'Enero' => 1,
+        'Feb' => 2,
+        'Mar' => 3, 'Marzo' => 3,
+        'Abr' => 4, 'Abril' => 4,
+        'May' => 5, 'Mayo' => 5,
+        'Jun' => 6, 'Junio' => 6,
+        'Jul' => 7, 'Julio' => 7,
+        'Ago' => 8, 'Agosto' => 8,
+        'Sep' => 9, 'Set' => 9, 'Sept' => 9,
+        'Oct' => 10,
+        'Nov' => 11,
+        'Dic' => 12 }
+
+    # e.g.  12 Ene  w/ implied year and implied hours (set to 12:00)
+    regex_es21 = /\b(\d{1,2})\s(#{month_abbrev_es})\b/
+
+    if line =~ regex_db
+      value = '%d-%02d-%02d %02d:%02d' % [$1.to_i, $2.to_i, $3.to_i, $4.to_i, $5.to_i]
+      logger.debug "   date: >#{value}<"
+
+      ## todo: lets you configure year
+      ##  and time zone (e.g. cet, eet, utc, etc.)
+      
+      line.sub!( regex_db, '[DATE.DB]' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_db2
+      value = '%d-%02d-%02d 12:00' % [$1.to_i, $2.to_i, $3.to_i]
+      logger.debug "   date: >#{value}<"
+
+      line.sub!( regex_db2, '[DATE.DB2]' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_de2
+      value = '%d-%02d-%02d %02d:%02d' % [$3.to_i, $2.to_i, $1.to_i, $4.to_i, $5.to_i]
+      logger.debug "   date: >#{value}<"
+
+      ## todo: lets you configure year
+      ##  and time zone (e.g. cet, eet, utc, etc.)
+      
+      line.sub!( regex_de2, '[DATE.DE2]' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_de
+
+      year = calculate_year( $1.to_i, $2.to_i, opts[:start_at] )
+
+      value = '%d-%02d-%02d %02d:%02d' % [year, $2.to_i, $1.to_i, $3.to_i, $4.to_i]
+      logger.debug "   date: >#{value}<"
+
+      ## todo: lets you configure year
+      ##  and time zone (e.g. cet, eet, utc, etc.)
+      
+      line.sub!( regex_de, '[DATE.DE]' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_de3
+      value = '%d-%02d-%02d 12:00' % [$3.to_i, $2.to_i, $1.to_i]
+      logger.debug "   date: >#{value}<"
+
+      ## todo: lets you configure year
+      ##  and time zone (e.g. cet, eet, utc, etc.)
+      
+      line.sub!( regex_de3, '[DATE.DE3]' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_de4
+
+      year = calculate_year( $1.to_i, $2.to_i, opts[:start_at] )
+
+      value = '%d-%02d-%02d 12:00' % [year, $2.to_i, $1.to_i]
+      logger.debug "   date: >#{value}<"
+
+      ## todo: lets you configure year
+      ##  and time zone (e.g. cet, eet, utc, etc.)
+
+      ### NOTE: needs a trailing space
+      #   not if regex ends w/ whitespace e.g. /s+
+      #  make sure sub! adds a space at the end
+      #   e.g. '[DATE.DE4]' becomes '[DATE.DE4] '
+
+      line.sub!( regex_de4, '[DATE.DE4] ' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_en
+      value = '%d-%s-%02d %02d:%02d' % [$3.to_i, $2, $1.to_i, $4.to_i, $5.to_i]
+      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.)
+    elsif line =~ regex_en2
+      day     = $2.to_i
+      month   = month_abbrev_en_to_i[ $1 ]
+      year    = calculate_year( day, month, opts[:start_at] )
+      hours   = $3.to_i
+      minutes = $4.to_i
+
+      value = '%d-%02d-%02d %02d:%02d' % [year, month, day, hours, minutes]
+      logger.debug "   date: >#{value}<"
+
+      line.sub!( regex_en2, '[DATE.EN2] ' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_en21
+      day   = $2.to_i
+      month = month_abbrev_en_to_i[ $1 ]
+      year = calculate_year( day, month, opts[:start_at] )
+
+      value = '%d-%02d-%02d 12:00' % [year, month, day]
+      logger.debug "   date: >#{value}<"
+
+      line.sub!( regex_en21, '[DATE.EN21] ' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    elsif line =~ regex_es21
+      day   = $1.to_i
+      month = month_abbrev_es_to_i[ $2 ]
+      year = calculate_year( day, month, opts[:start_at] )
+
+      value = '%d-%02d-%02d 12:00' % [year, month, day]
+      logger.debug "   date: >#{value}<"
+
+      line.sub!( regex_es21, '[DATE.ES21] ' )
+
+      return DateTime.strptime( value, '%Y-%m-%d %H:%M' )
+    else
+      return nil
+    end
+  end
+
+  end # module FixtureHelpers
+end # module SportDb
+

data/lib/sportdb/utils_group.rb

@@ -0,0 +1,50 @@
+# encoding: utf-8
+
+module SportDb
+  module FixtureHelpers
+
+  def is_group?( line )
+    # NB: check after is_round? (round may contain group reference!)
+    line =~ SportDb.lang.regex_group
+  end
+
+  def find_group_title_and_pos!( line )
+    ## group pos - for now support single digit e.g 1,2,3 or letter e.g. A,B,C or HEX
+    ## nb:  (?:)  = is for non-capturing group(ing)
+    regex = /(?:Group|Gruppe|Grupo)\s+((?:\d{1}|[A-Z]{1,3}))\b/
+    
+    match = regex.match( line )
+    
+    return [nil,nil] if match.nil?
+
+    pos = case match[1]
+          when 'A' then 1
+          when 'B' then 2
+          when 'C' then 3
+          when 'D' then 4
+          when 'E' then 5
+          when 'F' then 6
+          when 'G' then 7
+          when 'H' then 8
+          when 'I' then 9
+          when 'J' then 10
+          when 'K' then 11
+          when 'L' then 12
+          when 'HEX' then 666    # HEX for Hexagonal - todo/check: map to something else ??
+          else  match[1].to_i
+          end
+
+    title = match[0]
+
+    logger.debug "   title: >#{title}<"
+    logger.debug "   pos: >#{pos}<"
+      
+    line.sub!( regex, '[GROUP|TITLE+POS]' )
+
+    return [title,pos]
+  end
+
+
+
+  end # module FixtureHelpers
+end # module SportDb

data/lib/sportdb/utils_map.rb

@@ -0,0 +1,37 @@
+# encoding: utf-8
+
+module SportDb
+  module FixtureHelpers
+
+
+  def find_ground!( line )
+    TextUtils.find_key_for!( 'ground', line )
+  end
+
+  ## todo/fix: pass in known_grounds as a parameter? why? why not?
+  def map_ground!( line )
+    TextUtils.map_titles_for!( 'ground', line, @known_grounds )
+  end
+
+
+  def find_track!( line )
+    TextUtils.find_key_for!( 'track', line )
+  end
+
+  ## todo/fix: pass in known_tracks as a parameter? why? why not?
+  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
+
+
+  end # module FixtureHelpers
+end # module SportDb
+

data/lib/sportdb/utils_record.rb

@@ -0,0 +1,91 @@
+# encoding: utf-8
+
+module SportDb
+  module FixtureHelpers
+
+
+  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
+
+
+  end # module FixtureHelpers
+end # module SportDb

data/lib/sportdb/utils_round.rb

@@ -0,0 +1,94 @@
+# encoding: utf-8
+
+module SportDb
+  module FixtureHelpers
+
+  def is_round?( line )
+    line =~ SportDb.lang.regex_round
+  end
+
+  def is_knockout_round?( line )
+
+    ## todo: check for adding ignore case for regex (e.g. 1st leg/1st Leg)
+
+    if line =~ SportDb.lang.regex_leg1
+      logger.debug "  two leg knockout; skip knockout flag on first leg"
+      false
+    elsif line =~ SportDb.lang.regex_knockout_round
+      logger.debug "   setting knockout flag to true"
+      true
+    elsif line =~ /K\.O\.|K\.o\.|Knockout/
+        ## NB: add two language independent markers, that is, K.O. and Knockout
+      logger.debug "   setting knockout flag to true (lang independent marker)"
+      true
+    else
+      false
+    end
+  end
+
+  def find_round_title2!( line )
+    # assume everything after // is title2 - strip off leading n trailing whitespaces
+    regex = /\/{2,}\s*(.+)\s*$/
+    if line =~ regex
+      logger.debug "   title2: >#{$1}<"
+      
+      line.sub!( regex, '[ROUND|TITLE2]' )
+      return $1
+    else
+      return nil    # no round title2 found (title2 is optional)
+    end
+  end
+
+
+  def find_round_title!( line )
+    # assume everything left is the round title
+    #  extract all other items first (round title2, round pos, group title n pos, etc.)
+
+    buf = line.dup
+    logger.debug "  find_round_title! line-before: >>#{buf}<<"
+
+    buf.gsub!( /\[.+?\]/, '' )   # e.g. remove [ROUND|POS], [ROUND|TITLE2], [GROUP|TITLE+POS] etc.
+    buf.sub!( /\s+[\/\-]{1,}\s+$/, '' )    # remove optional trailing / or / chars (left over from group)
+    buf.strip!    # remove leading and trailing whitespace
+
+    logger.debug "  find_round_title! line-after: >>#{buf}<<"
+
+    ### bingo - assume what's left is the round title
+
+    logger.debug "   title: >>#{buf}<<"
+    line.sub!( buf, '[ROUND|TITLE]' )
+
+    buf
+  end
+
+
+  def find_round_pos!( line )
+    ## fix/todo:
+    ##  if no round found assume last_pos+1 ??? why? why not?
+
+    # extract optional round pos from line
+    # e.g.  (1)   - must start line 
+    regex_pos = /^[ \t]*\((\d{1,3})\)[ \t]+/
+
+    ## find free standing number
+    regex_num = /\b(\d{1,3})\b/
+
+    if line =~ regex_pos
+      logger.debug "   pos: >#{$1}<"
+      
+      line.sub!( regex_pos, '[ROUND|POS] ' )  ## NB: add back trailing space that got swallowed w/ regex -> [ \t]+
+      return $1.to_i
+    elsif line =~ regex_num
+      ## assume number in title is pos (e.g. Jornada 3, 3 Runde etc.)
+      ## NB: do NOT remove pos from string (will get removed by round title)
+      logger.debug "   pos: >#{$1}<"
+      return $1.to_i
+    else
+      ## fix: add logger.warn no round pos found in line
+      return nil
+    end
+  end # method find_round_pos!
+
+
+  end # module FixtureHelpers
+end # module SportDb