sportdb-parser 0.6.0 → 0.6.2

data/lib/sportdb/parser/racc_parser.rb

@@ -68,12 +68,14 @@ def initialize( txt,  debug: false )
 
 
   def on_error(error_token_id, error_value, value_stack)
-    args = [error_token_id, error_value, value_stack]
+    ## auto-add error_token (as string)
+    error_token = Racc_token_to_s_table[error_token_id] 
+    args = [error_token, error_token_id, error_value, value_stack]
     puts
     puts "!! on parse error:"
     puts "args=#{args.pretty_inspect}"
 
-    @errors << "parse error on token: #{error_token_id} with value: #{error_value}, stack: #{value_stack.pretty_inspect}"
+    @errors << "parse error on token: #{error_token} (#{error_token_id}) with value: #{error_value}, stack: #{value_stack.pretty_inspect}" 
     ## exit 1  ##   exit for now  -  get and print more info about context etc.!!
   end
 

data/lib/sportdb/parser/token-date.rb

@@ -147,15 +147,15 @@ DATE_II_RE = %r{
 
 
 # e.g. iso-date  -  2011-08-25     
-##    todo/check - allow  2011-8-25  or 2011-8-3 / 2011-08-03 etc. - why? why not?
+##   note - allow/support ("shortcuts") e.g 2011-8-25  or 2011-8-3 / 2011-08-03 etc. 
 DATE_III_RE = %r{
 (?<date>
   \b
    (?<year>\d{4})
        -
-   (?<month>\d{2})
+   (?<month>\d{1,2})
        -
-   (?<day>\d{2})
+   (?<day>\d{1,2})
   \b
 )}ix
 
@@ -214,29 +214,36 @@ end
 #
 #  Sun Jun/23 - Wed Jun/26   -- YES
 #  Jun/23 - Jun/26           -- YES
-#  Tue Jun/25 + Wed Jun/26   -- YES
-#  Jun/25 + Jun/26           -- YES
-#
-#  Jun/25 - 26        - why? why not???
+#  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 comman and plus for list of dates
+#  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})
       [ ]
@@ -245,12 +252,13 @@ DURATION_I_RE =  %r{
       (?: \/|[ ] )
    (?<day1>\d{1,2})
    ## optional year
-   ( [ ]
+   (  ,?   # optional comma
+      [ ]
       (?<year1>\d{4})
    )?
 
    ## support + and -  (add .. or such - why??)
-   [ ]*[-][ ]*
+   [ ]* - [ ]*
 
    ## optional day name
    ((?<day_name2>#{DAY_NAMES})
@@ -260,20 +268,28 @@ DURATION_I_RE =  %r{
       (?: \/|[ ] )
    (?<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
-
-DURATION_II_RE =  %r{
+#      26 July, 
+XXX_DURATION_II_RE =  %r{
 (?<duration>
     \b
+  (?
    ## optional day name
    ((?<day_name1>#{DAY_NAMES})
       [ ]
@@ -282,7 +298,8 @@ DURATION_II_RE =  %r{
       [ ]
    (?<month_name1>#{MONTH_NAMES})
    ## optional year
-   ( [ ]
+   (  
+       [ ]
       (?<year1>\d{4})
    )?
 
@@ -300,16 +317,50 @@ DURATION_II_RE =  %r{
    ( [ ]
       (?<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 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
+   DURATION_II_RE,
 )
 
 

data/lib/sportdb/parser/token-minute.rb

@@ -26,14 +26,29 @@ GOAL_OG_RE = %r{
 }ix
 
 
+## minute variant for  N/A not/available
+##     todo/check - find a better syntax - why? why not?
+##
+##   note  "??".to_i(10) returns 0 or
+##         "__".to_i(10) returns 0
+##   quick hack - assume 0 for n/a for now 
+
+MINUTE_NA_RE = %r{
+   (?<minute>
+      (?<=[ (])	 # positive lookbehind for space or opening 
+        (?<value> \?{2} | _{2} )
+        '   ## must have minute marker!!!!
+    )
+}ix
+
 MINUTE_RE = %r{
      (?<minute>
        (?<=[ (])	 # positive lookbehind for space or opening ( e.g. (61') required
                      #    todo - add more lookbehinds e.g.  ,) etc. - why? why not?
-           (?<value>\d{1,3})      ## constrain numbers to 0 to 999!!!
-        (?: \+
-            (?<value2>\d{1,3})   
-        )?
+             (?<value>\d{1,3})      ## constrain numbers to 0 to 999!!!
+                   (?: \+
+                     (?<value2>\d{1,3})   
+                   )?           
         '     ## must have minute marker!!!!
      )
 }ix

data/lib/sportdb/parser/token-score.rb

@@ -17,7 +17,7 @@ class Lexer
     ##      3-4 pen.   2-2 a.e.t.
     ##               2-2 a.e.t.
     SCORE__P_ET__RE = %r{
-        (?<score>
+        (?<score_more>
            \b
             (?:
                (?<p1>\d{1,2}) - (?<p2>\d{1,2})
@@ -34,7 +34,7 @@ class Lexer
     ##  note: allow SPECIAL with penalty only
     ##      3-4 pen.
     SCORE__P__RE = %r{
-        (?<score>
+        (?<score_more>
            \b
               (?<p1>\d{1,2}) - (?<p2>\d{1,2})
                 [ ]* #{P_EN}
@@ -52,7 +52,7 @@ class Lexer
     ##               2-2 a.e.t. (1-1)
 
     SCORE__P_ET_FT_HT__RE = %r{
-          (?<score>
+          (?<score_more>
                \b
                (?:
                 (?<p1>\d{1,2}) - (?<p2>\d{1,2})
@@ -79,7 +79,7 @@ class Lexer
     ##   special case for case WITHOUT extra time!!
     ##     same as above (but WITHOUT extra time and pen required)
     SCORE__P_FT_HT__RE = %r{
-             (?<score>
+             (?<score_more>
                 \b
      (?<p1>\d{1,2}) - (?<p2>\d{1,2})
         [ ]* #{P_EN} [ ]+
@@ -99,36 +99,47 @@ class Lexer
             ## note: \b works only after non-alphanum e.g. )
 
 
-
-    ## e.g. 2-1 (1-1) or
-    ##      2-1
-
+    ##########
+    ## e.g. 2-1 (1-1)
     SCORE__FT_HT__RE = %r{
-            (?<score>
+            (?<score_more>
               \b
               (?<ft1>\d{1,2}) - (?<ft2>\d{1,2})
-               (?:
                    [ ]+ \( [ ]*
                 (?<ht1>\d{1,2}) - (?<ht2>\d{1,2})
                    [ ]* \)
-               )?   # note: make half time (HT) score optional for now
              (?=[ ,\]]|$)
              )}ix    ## todo/check:  remove loakahead assertion here - why require space?
                     ## note: \b works only after non-alphanum e.g. )
 
-
+    #####
+    ##      2-1
+    SCORE__FT__RE = %r{
+            (?<score>
+              \b
+              (?<ft1>\d{1,2}) - (?<ft2>\d{1,2})
+              \b
+             )}ix  
 
 #############################################
 # map tables
 #  note: order matters; first come-first matched/served
+#
+## check - find a better name for SCORE_MORE - SCORE_EX, SCORE_BIG, or ___ - why? why not?
 
-SCORE_RE = Regexp.union(
+SCORE_MORE_RE = Regexp.union(
   SCORE__P_ET_FT_HT__RE,  # e.g. 5-1 pen. 2-2 a.e.t. (1-1, 1-0)
   SCORE__P_FT_HT__RE,     # e.g. 5-1 pen. (1-1)
   SCORE__P_ET__RE,        # e.g. 2-2 a.e.t.  or  5-1 pen. 2-2 a.e.t.
   SCORE__P__RE,           # e.g. 5-1 pen.
-  SCORE__FT_HT__RE,        # e.g. 1-1 (1-0) or 1-1  -- note - must go last!!!
+  SCORE__FT_HT__RE,        # e.g. 1-1 (1-0)
+  ##  note - keep basic score as its own token!!!!
+  ##   that is, SCORE & SCORE_MORE
+  ### SCORE__FT__RE,           # e.g. 1-1  -- note - must go last!!!
 )
 
+SCORE_RE   =   SCORE__FT__RE
+  
+
 end  #  class Lexer
 end  # module SportDb

data/lib/sportdb/parser/token-status.rb

@@ -12,10 +12,33 @@ STATUS_RE = %r{
       (?:    
             ### opt 1 - allow long forms with note/comment for some stati
            (?: (?<status> awarded
+             ## e.g. [awarded match to Leones Negros by undue alignment; original result 1-2]
+             ##     [awarded 3-0 to Cafetaleros by undue alignment; originally ended 2-0]
+             ##     [awarded 3-0; originally 0-2, América used ineligible player (Federico Viñas)]
                             |
                           annulled
                             |
                           abandoned
+             ## e.g. [abandoned at 1-1 in 65' due to cardiac arrest Luton player Tom Lockyer]
+             ##      [abandoned at 0-0 in 6' due to waterlogged pitch]
+             ##     [abandoned at 5-0 in 80' due to attack on assistant referee by Cerro; result stood]
+             ##    [abandoned at 1-0 in 31']
+             ##    [abandoned at 0-1' in 85 due to crowd trouble]
+                            |
+                          postponed
+             ## e.g. [postponed due to problems with the screen of the stadium]
+             ##      [postponed by storm]
+             ##      [postponed due to tropical storm "Hanna"]
+             ##      [postponed from Sep 10-12 due to death Queen Elizabeth II]
+                           |
+                        suspended
+             ## e.g. [suspended at 0-0 in 12' due to storm]  
+             ##      [suspended at 84' by storm; result stood]
+                           |
+                         verified
+             ## e.g.  [verified 2:0 wo.]
+   
+
                ) [ ;,]* (?<status_note> [^\]]+ )
                  [ ]*
             )
@@ -34,12 +57,98 @@ STATUS_RE = %r{
                replay
                  |
                annulled
+                 |
+               suspended    ### todo/fix - add status upstream - why? why not?
+                            ###  move to note(s) - do NOT interpret as status - why? why not?
+                 |
+               verified     ### todo/fix - add status upstream (same as ??) - why? why not? 
+                            ###  move to note(s) - do NOT interpret as status - why? why not?
             )
       )
     \]
 }ix
 
 
+
+
+###
+## todo/fix - move to token-note.rb (standalone) file 
+
+NOTE_RE = %r{
+    \[ 
+   (?<note>
+     (?:  ##  starting with ___   PLUS requiring more text
+       (?:
+          nb:
+          ##  e.g. [NB: between top-8 of regular season]
+          #        [NB: América, Morelia and Tigres qualified on better record regular season]
+          #        [NB: Celaya qualified on away goals]
+          #        [NB: Alebrijes qualified on away goal]
+          #        [NB: Leones Negros qualified on away goals]
+          #
+          # todo/fix:
+          # add "top-level" NB: version
+          ##   with full (end-of) line note - why? why not?
+          |
+          (?: originally[ ])? scheduled
+          ## e.g. [originally scheduled to play in Mexico City] 
+          |
+          rescheduled
+          ## e.g.  [Rescheduled due to earthquake occurred in Mexico on September 19]
+          |
+          remaining
+          ## e.g. [remaining 79']   
+          ##      [remaining 84'] 
+          ##      [remaining 59']   
+          ##      [remaining 5']
+          |
+          played  
+          ## e.g. [played in Macaé-RJ]
+          ##      [played in Caxias do Sul-RS]
+          ##      [played in Sete Lagoas-MG]
+          ##      [played in Uberlândia-MG]
+          ##      [played in Brasília-DF]
+          ##      [played in Vöcklabruck]
+          ##      [played in Pasching]
+          |
+          declared
+          ## e.g.  [declared void]
+          |
+          inter-group
+          ## e.g. [inter-group A-B]
+          ##      [inter-group C-D]
+       )
+      [ ]
+      [^\]]+?    ## slurp all to next ] - (use non-greedy) 
+     )
+      |
+     (?:
+       ## starting with in  - do NOT allow digits
+       ##   name starting with in possible - why? why not?
+           in[ ]
+            [^0-9\]]+?
+       ## e.g. [In Estadio La Corregidora] 
+       ##      [in Unidad Deportiva Centenario]
+       ##      [in Estadio Olímpico Universitario]
+       ##      [in Estadio Victoria]
+       ##      [in UD José Brindis]
+       ##      [in Colomos Alfredo "Pistache" Torres stadium]
+     )
+       |
+      (?:
+         ## e.g. Spain wins on penalties
+         ##       1860 München wins on penalties etc.
+         ##   must start with digit 1-9 or letter
+         ##     todo - add more special chars - why? why not?
+            [1-9\p{L}][0-9\p{L} .-]+?    
+            [ ]wins[ ]on[ ]penalties
+             [^\]]*?   ## use non-greedy
+      )
+   )
+   \] 
+}ix    
+
+
 end  #  class Lexer
 end  # module SportDb
   

data/lib/sportdb/parser/token.rb

@@ -111,7 +111,15 @@ BASICS_RE = %r{
     (?<spaces> [ ]{2,}) |
     (?<space>  [ ])
         |
-    (?<sym>[;,/@|\[\]-])
+    (?<sym>  (?<=^|[ ])  ## positive lookahead 
+                  (?: ----|
+                      ---|
+                      --
+                  )
+             (?=[ ])   ## positive lookahead
+    )
+        |
+    (?<sym> [;,/@|\[\]-] )
 }ix
 
 
@@ -119,14 +127,17 @@ BASICS_RE = %r{
 
 RE = Regexp.union(  PROP_KEY_RE, ##  start with prop key (match will/should switch into prop mode!!!)
                     STATUS_RE,
+                    NOTE_RE,
                     TIMEZONE_RE,
                      TIME_RE,
                      DURATION_RE,  # note - duration MUST match before date
                     DATE_RE,
                     WDAY_RE,   # allow standalone weekday name (e.g. Mo/Tu/etc.) - why? why not?
-                    SCORE_RE,
+                    SCORE_MORE_RE, 
+                    SCORE_RE,   ## note basic score e.g. 1-1 must go after SCORE_MORE_RE!!!
                     BASICS_RE, 
                     MINUTE_RE,
+                    MINUTE_NA_RE,   ## note - add/allow not/available (n/a,na) minutes hack for now
                     GOAL_OG_RE, GOAL_PEN_RE,
                      TEXT_RE )
 

data/lib/sportdb/parser/version.rb

@@ -4,7 +4,7 @@ module SportDb
     module Parser
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
   MINOR = 6
-  PATCH = 0
+  PATCH = 2
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-parser
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.2
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-01-30 00:00:00.000000000 Z
+date: 2025-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cocos