fbtxt-parser 0.9.0 → 0.9.1

data/lib/fbtxt/parser/token-date_duration.rb

@@ -1,171 +0,0 @@
-module Fbtxt
-class Lexer
-
-
-
-
-###
-#  date duration
-#   use - or + as separator
-#    in theory plus( +) only if dates
-#     are two days next to each other
-#
-#   otherwise  define new dates type in the future? why? why not?
-#
-#  check for plus (+) if dates are next to each other (t+1) - why? why not?
-
-#
-#  Sun Jun 23 - Wed Jun 26   -- YES
-#  Jun 23 - Jun 26           -- YES
-#  Jun 25 - 26        - why? why not???  - YES - see blow variant iii!!!
-
-#  Tue Jun 25 + Wed Jun 26   -- NO
-#  Jun 25 + Jun 26           -- NO
-#  Jun 25 .. 26        - why? why not???
-#  Jun 25 to 26        - why? why not???
-#  Jun 25 + 26        - add - why? why not???
-#  Sun-Wed Jun 23-26  -  add - why? why not???
-#  Wed+Thu Jun 26+27 2024  -  add - why? why not???
-#
-#  maybe use comma and plus for list of dates
-#    Tue Jun 25, Wed Jun 26, Thu Jun 27  ??
-#    Tue Jun 25 + Wed Jun 26 + Thu Jun 27  ??
-#
-#   add back optional comma (before) year - why? why not?
-#
-
-
-##
-#   todo add plus later on - why? why not?
-###   todo/fix  add optional comma (,) before year
-
-### regex note/tip/remindr -  \b () \b MUST always get enclosed in parantheses
-##                                     because alternation (|) has lowest priority/binding
-
-
-DURATION_I_RE =  %r{
-(?<duration>
-    \b
-  (?:
-   ## optional day name
-   ((?<day_name1>#{DAY_NAMES})
-      [ ]
-   )?
-   (?<month_name1>#{MONTH_NAMES})
-      [ ]
-   (?<day1>\d{1,2})
-   ## optional year
-   (  ,?   # optional comma
-      [ ]
-      (?<year1>\d{4})
-   )?
-
-   ## support + and -  (add .. or such - why??)
-   [ ]* - [ ]*
-
-   ## optional day name
-   ((?<day_name2>#{DAY_NAMES})
-      [ ]
-   )?
-   (?<month_name2>#{MONTH_NAMES})
-      [ ]
-   (?<day2>\d{1,2})
-   ## optional year
-   (  ,?   # optional comma
-      [ ]
-      (?<year2>\d{4})
-   )?
-  )
-   \b
-)}ix
-
-
-
-#   FIX - remove this variant
-#         "standardize on month day [year]" !!!!
-
-=begin
-###
-#   variant ii
-# e.g. 26 July - 27 July
-#      26 July,
-XXX_DURATION_II_RE =  %r{
-(?<duration>
-    \b
-  (?
-   ## optional day name
-   ((?<day_name1>#{DAY_NAMES})
-      [ ]
-   )?
-   (?<day1>\d{1,2})
-      [ ]
-   (?<month_name1>#{MONTH_NAMES})
-   ## optional year
-   (
-       [ ]
-      (?<year1>\d{4})
-   )?
-
-   ## support + and -  (add .. or such - why??)
-   [ ]*[-][ ]*
-
-   ## optional day name
-   ((?<day_name2>#{DAY_NAMES})
-      [ ]
-   )?
-   (?<day2>\d{1,2})
-      [ ]
-   (?<month_name2>#{MONTH_NAMES})
-   ## optional year
-   ( [ ]
-      (?<year2>\d{4})
-   )?
-  )
-   \b
-)}ix
-=end
-
-
-#  variant ii
-#  add support for shorthand
-#     August 16-18, 2011
-#     September 13-15, 2011
-#      October 18-20, 2011
-#      March 6-8 2012
-#      March 6-8
-#
-#   - add support for August 16+17 or such (and check 16+18)
-#       use <op> to check if day2 is a plus or range or such - why? why not?
-
-DURATION_II_RE =  %r{
-(?<duration>
-    \b
-   (?:
-       (?<month_name1>#{MONTH_NAMES})
-           [ ]
-        (?<day1>\d{1,2})
-             -
-        (?<day2>\d{1,2})
-          (?:
-            ,?     ## optional comma
-            [ ]
-            (?<year1>\d{4})
-          )?     ## optional year
-   )
-   \b
-)}ix
-
-
-
-#############################################
-# map tables
-#  note: order matters; first come-first matched/served
-DURATION_RE = Regexp.union(
-   DURATION_I_RE,
-   DURATION_II_RE,
-)
-
-
-
-end  #   class Lexer
-end  # module Fbtxt

data/lib/fbtxt/parser/token-geo.rb

@@ -1,134 +0,0 @@
-module Fbtxt
-class Lexer
-
-
-##
-#  allow Cote'd Ivoir or such
-##   e.g. add '
-
-
-## todo/fix - make geo text regex more generic
-##               only care about two space rule
-
-
-GEO_TEXT_RE = %r{
-    ## must start with alpha (allow unicode letters!!)
-    (?<text>
-          ## positive lookbehind -  for now space (or beginning of line - for testing) only
-           ##  (MUST be fixed number of chars - no quantifier e.g. +? etc.)
-            (?<= [ ,›>\[\]]|^)
-            (?:
-                # opt 1 - start with alpha
-                 \p{L}+    ## all unicode letters (e.g. [a-z])
-                   |
-                # opt 2 - start with num!! -
-                     \d+  # check for num lookahead (MUST be space or dot)
-                      ## MAY be followed by (optional space) !
-                      ## MUST be follow by a to z!!!!
-                      [ ]?   ## make space optional too  - why? why not?
-                             ##  yes - eg. 1st, 2nd, 5th etc.
-                       \p{L}+
-                  |
-                ## opt 3 - add another weirdo case
-                ##   e.g.   's Gravenwezel-Schilde
-                ##   add more letters (or sequences here - why? why not?)
-                    '\p{L}+
-               )
-
-               ##
-               ## todo/check - find a different "more intuitive" regex/rule if possible?
-               ##    for single spaces only (and _/ MUST not be surround by spaces)
-
-              (?:
-                  (?:
-                    [ ]?   # only single (inline) space allowed - double spaces are breaks!!!
-                    (?:
-                       \p{L} | \d  | [.&'°]
-                        |
-                       (?: (?<! [ ])  ## no space allowed before (but possible after)
-                            [-]
-                       )
-                         |
-                       (?: (?<! [ ])  ## no spaces allowed around these characters
-                           [_/]
-                          (?! [ ])
-                       )
-                    )+
-                  )
-                  |
-              ## for now allow auto-add optional
-              ##   parenthesis enclosed closed text
-              ##   e.g. Dublin (Dalymount Park)
-              ##        Bucuresti (23 August)
-              ##        Paris (Parc des Princes)
-              ##        Ost-Berlin (Walter-Ulbricht)
-              ##        Athinai (OAKA - Maroussi)
-              ##
-              ##   or   Valencia (Spain) or Solna
-              (?:
-                    [ ]
-                    \(
-                        [^()\[\],;:›<>]+    ## todo - add more special chars
-                                            ##   maybe list only allowed ones??
-                                            ##   make pattern more strict - why? why not?
-                    \)
-              )
-          )*
-
-
-              ## must NOT end with space or dash(-)
-              ##  todo/fix - possible in regex here
-              ##     only end in alphanum a-z0-9 (not dot or & ???)
-
-            ## add lookahead/lookbehind
-           ##    must be space!!!
-           ##   (or comma or  start/end of string)
-           ##   kind of \b !!!
-            ## POSITIVE lookahead
-            (?=[ ,›>\[\]]|$)
-
-   )
-}ix
-
-
-
-
-
-
-##  note - add "hacky" check for comma that is followed by a prop(erty)
-##
-##  make sure to NOT match
-##      props  e.g.  att: 18000
-##   July 10 @ Paris, Parc des Princes, att: 18000
-##   July 10 @ Paris, Parc des Princes,   att: 18000
-##
-
-
-GEO_END_RE = %r{
-   (?<geo_end>
-        ,
-    )
-    ## POSITIVE lookahead for props
-    ##   todo/fix - use generic [a-z]+ - why? why not?
-    (?=
-        [ ]*  ## optional spaces
-         (?:     attendance|att
-              |  referee?s|refs?
-          )
-         :
-    )
-}ix
-
-
-
-
-GEO_RE = Regexp.union(
-                    SPACES_RE,
-                    GEO_END_RE,
-                    GEO_TEXT_RE,
-                    /  (?<sym> [,›>\[▪] ) /x,
-                    ANY_RE,
-                      )
-
-end # class Lexer
-end # module Fbtxt

data/lib/fbtxt/parser/token-goals--helpers.rb

@@ -1,114 +0,0 @@
-module Fbtxt
-class Lexer
-
-
-
-def self._build_goal_minute( m )
-    minute = {}
-
-    minute[:m]     =  m[:value].to_i(10)   ## always required
-
-    ## stoppage/injury time (offset)
-    minute[:offset] = m[:value2].to_i(10)   if m[:value2]
-
-    minute[:og]  = true       if m[:og]
-    minute[:pen] = true       if m[:pen]
-    minute[:freekick] = true  if m[:fk]
-    minute[:header] = true    if m[:hdr]
-
-    minute[:secs] = m[:secs].to_i(10)   if m[:secs]
-
-    minute
-end
-
-def self._build_goal_minute_na( m )
-    minute = {}
-
-    minute[:m]     =  '?'   ##  or use nil or 999 or -1 or ???
-
-    minute[:og]  = true       if m[:og]
-    minute[:pen] = true       if m[:pen]
-    minute[:freekick] = true  if m[:fk]
-    minute[:header] = true    if m[:hdr]
-
-    minute
-end
-
-
-
-def self._build_minute( m )
-    minute = {}
-    minute[:m]      = m[:value].to_i(10)   ## always required
-
-    ## stoppage/injury time (offset)
-    minute[:offset] = m[:value2].to_i(10)   if m[:value2]
-
-    minute
-end
-
-
-def self._build_goal_count( m )
-    count = {}
-    count[:count] = m[:value].to_i(10)        if m[:value]
-    count[:og]    = m[:og_value] ? m[:og_value].to_i(10) : 1      if m[:og]   ## check flag
-    count[:pen]   = m[:pen_value] ? m[:pen_value].to_i(10) : 1    if m[:pen]  ## check flag
-    count
-end
-
-def self._build_goal_type( m )
-    goal = {}
-    goal[:og]       = true  if m[:og]
-    goal[:pen]      = true  if m[:pen]
-    goal[:freekick] = true  if m[:fk]
-    goal[:header]   = true  if m[:hdr]
-    goal
-end
-
-
-def _build_goal_minute( m ) self.class._build_goal_minute( m ); end
-def _build_goal_minute_na( m ) self.class._build_goal_minute_na( m ); end
-def _build_minute( m ) self.class._build_minute( m ); end
-def _build_goal_count( m ) self.class._build_goal_count( m ); end
-def _build_goal_type( m ) self.class._build_goal_type( m ); end
-
-
-
-
-
-###
-# parse helpers
-
-def self._parse_goal_minute( str )
-    ## note - strip - leading/trailing spaces
-    m = GOAL_MINUTE_RE.match( str.strip )
-    if m && m.pre_match == '' && m.post_match == ''
-      _build_goal_minute( m )
-    elsif  m
-        ## note - match BUT not anchored to start and end-of-string!!!
-        ##  report, error somehow??
-      nil
-    else
-      nil  ## no match - return nil
-    end
-end
-
-def self._parse_goal_count( str )
-    ## note - strip - leading/trailing spaces
-    m = GOAL_COUNT_RE.match( str.strip )
-    if m && m.pre_match == '' && m.post_match == ''
-      _build_goal_count( m )
-    elsif  m
-        ## note - match BUT not anchored to start and end-of-string!!!
-        ##  report, error somehow??
-      nil
-    else
-      nil  ## no match - return nil
-    end
-end
-
-
-
-
-
-end   # class Lexer
-end   # module Fbtxt

data/lib/fbtxt/parser/token-goals.rb

@@ -1,306 +0,0 @@
-module Fbtxt
-class Lexer
-
-
-######################################################
-## goal mode
-##  note - must be enclosed in ()!!!
-##
-##          todo - add () in basics - why? why not?
-
-
-
-
-## note - assume lines starting with opening ( are goal lines!!!!
-##  note - use \A (instead of ^) - \A strictly matches the start of the string.
-##
-##   note -  check for negative lookahead
-##                 to exclude ord (numbers) e.g.  (1), (42), etc.!!!
-##
-##  todo/fix -- exclude (a), (h), (n)  - TEAM_AWAY, TEAM_HOME, TEAM_NEUTRAL tokens!!
-
-START_GOAL_LINE_RE = %r{
-                     \A
-                        [ ]*    ## ignore leading spaces (if any)
-                       \(
-
-                       # check NEGATIVE lookahead
-                       (?!
-                             ##  exclude (a), (h), (n)
-                             ##    TEAM_AWAY, TEAM_HOME, TEAM_NEUTRAL
-                             (?: a|h|n )
-                             \)
-                        )
-
- }xi
-
-
-
-#############
-##  check for goal compat(ility) "legacy" line
-##         e.g.
-## (6' Puskás 0-1, 9' Czibor 0-2, 11' Morlock 1-2, 18' Rahn 2-2,
-##   84' Rahn 3-2)
-## (6 Puskás 0-1, 9 Czibor 0-2, 11 Morlock 1-2, 18 Rahn 2-2,
-##  84 Rahn 3-2)
-
-
-START_GOAL_LINE_COMPAT_RE = %r{
-                   \A
-                        [ ]*    ## ignore leading spaces (if any)
-                      \(
-
-                      ## (i) check NEGATIVE lookahead
-                      ##    exclude score e.g. 1-1 etc.
-                          (?! [ ]* \b \d-\d \b)
-
-                      ## (ii) check POSITIVE lookahead
-                          (?= [ ]*
-                               \d{1,3}
-                                   '?    ## optional minute marker
-                                  (?: \+
-                                      \d{1,2}
-                                    '?    ## optional minute marker
-                                  )?
-                            )
-}xi
-
-
-
-###
-##  check for goal line (alternate syntax)
-##    (1-0 Player, 1-1 Player, ...)
-#    must start-off OR yes, include score
-##
-##    note - allow "centered" style e.g.
-##           (    Player 44' (p)  1-0
-##                                1-1 Player 64'   )
-START_GOAL_LINE_ALT_RE = %r{
-                     \A
-                        [ ]*    ## ignore leading spaces (if any)
-                      \(
-
-                      # check POSITIVE lookahead
-                       (?=  .*?         ## note - non-greedy
-                                \b \d-\d \b    ## score e.g. 0-1
-                         )
-                 }xi
-
-
-
-
-
-
-
-###
-#  note - alternate goal separator dash (-) MUST have leading and trailing space!!!
-#    e.g.   (Metzger 83 - Krämer 29, 88, Cichy 33, Rahn 37)
-#    e.g.   (Metzger - Krämer (2), Cichy, Rahn)
-#            (Brunnenmeier 17 - Gerwien 74)
-#            (Brunnenmeier - Gerwien)
-#    that is,  NOT allowed
-#    e.g.   (Metzger 83-Krämer 29, 88, Cichy 33, Rahn 37)
-#            (Brunnenmeier 17-Gerwien 74)
-#            (Brunnenmeier-Gerwien)
-#
-#   note - allow split by - e.g.
-#     Frankfurt   4-2 Schalke     (Kreß 45, Solz 55, Trimhold 58, Huberts 73 p -
-#                                  Berz 7, Herrmann 74)
-
-
-GOAL_SEP_ALT_RE = %r{
-          (?<goal_sep_alt>
-              (?<=[ ])   ## positive lookbehind - space required
-              -
-              (?=[ ]|\z)    ## positive lookahead - speace required
-             )}x
-
-
-## e.g.  (2)
-##       (2/p), (2/pen.), (3/2p), (3/ 2 pen.)
-##      -or-  (2,1pen), (3, 2 pens)
-##
-##       (p), (pen.) (2 pen.), (2p)
-##       (og), (o.g.),
-##        (2og), (2 o.g.), (2ogs)
-#
-##
-
-GOAL_COUNT_RE = %r{
-   (?<goal_count>
-      \(
-        (?:
-          ## opt penalties
-            (?<pen>
-              (?:  (?<pen_value> \d{1,2}) [ ]? )?
-                 (?:pens|pen\.?|p)
-           )
-            |
-          ## opt own goals (og)
-            (?<og>
-             (?: (?<og_value> \d{1,2}) [ ]? )?
-                (?:ogs?|o\.g\.|o)
-            )
-            |
-          ## opt fallback - classic count/number
-          (?:  (?<value> [1-9])
-                ## check for option penalties
-                (?<pen>
-                     [,/] [ ]*
-                     (?: (?<pen_value> \d{1,2}) [ ]? )?
-                     (?:pens|pen\.?|p)
-                )?
-           )
-         )
-      \)
-)}ix
-
-
-
-
-##
-## note - inline \b check in MINUTE_RE excludes
-##      85pen  or 90+4pen or 38p
-##        (possible and NOT excluded in GOAL_MINUTE_RE  !!!)
-##
-##  minute with optional stoppage (offset)
-
-MINUTE_RE = %r{
-     (?<minute>
-               \b
-             (?<value>\d{1,3})      ## constrain numbers to 0 to 999!!!
-                \b
-                '?    ## optional minute marker
-
-                (?: \+ (?<value2>\d{1,2})
-                       \b
-                      '?    ## optional minute marker
-                 )?
-      )
-}ix
-
-
-
-##
-##  keep separate? or add simply inside GOAL_MINUTE_RE - why? why not?
-##   fix-fix-fix - move into GOAL_MINUTE_RE !!!
-
-GOAL_MINUTE_NA_RE = %r{
-     (?<goal_minute_na>
-
-       # positive lookbehind
-       (?<=[ ,;])
-
-       (?<value> \?{1,2})
-            '?    ## optional minute marker
-     ## note - add goal minute qualifiers here inline!!!
-        (?:
-            (?: [ ]? (?<og>   (?: \((?:og|o\.g\.|o)\))   ## allow (og)
-                                   |
-                              (?: (?:og|o\.g\.|o))      ## allow plain og
-                      )
-            )
-            |
-            (?: [ ]? (?<pen>  (?: \((?:pen\.?|p)\))   ## allow ()
-                                   |
-                              (?: (?:pen\.?|p))
-                      )
-            )
-            |
-            ## add experimental header qualifier
-            (?: [ ]? (?<hdr> \( (?:hdr\.?|h ) \) | (?: hdr\.?|h ) ))
-            |
-            ## add experimental free kick qualifier
-            (?: [ ]? (?<fk> \( (?:fk\.?|f ) \) | (?: fk\.?|f) ))
-        )?
-
-     ## note - check positive lookahead
-     (?=[ ,;)]|$)
-   )
-}ix
-
-
-##   goal types
-# (pen.) or (pen) or (p.) or (p)
-## (o.g.) or (og)
-##   todo/check - keep case-insensitive
-##                   or allow OG or P or PEN or
-##                   only lower case - why? why not?
-##
-##  add (gg) for golden goal - why? why not?
-##  add (sg) for silver goal - why? why not??
-
-GOAL_MINUTE_RE = %r{
-     (?<goal_minute>
-               \b
-             (?<value>\d{1,3})      ## constrain numbers to 0 to 999!!!
-                '?    ## optional minute marker
-
-                 (?: \+ (?<value2>\d{1,2})
-                      '?    ## optional minute marker
-                 )?
-
-        ## note - add goal minute qualifiers here inline!!!
-        (?:
-            (?: [ ]? (?<og>   (?: \((?:og|o\.g\.|o)\))   ## allow (og)
-                                   |
-                              (?: (?:og|o\.g\.|o))      ## allow plain og
-                      )
-            )
-            |
-            (?: [ ]? (?<pen>  (?: \((?:pen\.?|p)\))   ## allow ()
-                                   |
-                              (?: (?:pen\.?|p))
-                      )
-            )
-            |
-            ## add experimental header qualifier
-            (?: [ ]? (?<hdr> \( (?:hdr\.?|h ) \) | (?: hdr\.?|h ) ))
-            |
-            ## add experimental free kick qualifier
-            (?: [ ]? (?<fk> \( (?:fk\.?|f ) \) | (?: fk\.?|f) ))
-        )?
-
-        ##  add experimental seconds
-        ##    e.g. (95 secs) or (95sec) etc.
-        (?: [ ]*  \(
-                      (?<secs>\d{1,3})
-                         [ ]?secs?
-                   \)
-        )?
-     )
-
-     ## note - check positive lookahead
-     (?=[ ,;)]|$)
-}ix
-
-
-
-
-
-###
-## more regex  for goal alt
-
-
-GOAL_TYPE_RE = %r{
-     (?<goal_type>
-               \(
-                 (?:
-                      (?<og>  og|o\.g\.|o )
-                         |
-                      (?<pen> pen\.?|p )
-                         |
-                     ## add experimental header qualifier
-                      (?<hdr>  hdr\.?|h )
-                         |
-                     ## add experimental free kick qualifier
-                       (?<fk>  fk\.?|f )
-                  )
-                \)
-)}xi
-
-
-
-
-end  # class Lexer
-end # module Fbtxt