sportdb-parser 0.5.9 → 0.6.1

data/lib/sportdb/parser/token.rb

@@ -7,13 +7,14 @@ class Lexer
 ##
 #  keep 18h30 - why? why not?
 #    add support for 6:30pm 8:20am etc. - why? why not?
-
+#
+#    check - only support h e.g. 18h30  or 18H30 too - why? why not?
+# e.g. 18.30 (or 18:30 or 18h30)
 TIME_RE = %r{
-    ## e.g. 18.30 (or 18:30 or 18h30)
     (?<time>  \b
-              (?<hour>\d{1,2})
+        (?:   (?<hour>\d{1,2})
                  (?: :|\.|h )
-              (?<minute>\d{2})
+              (?<minute>\d{2})) 
               \b
     )
 }ix
@@ -42,9 +43,12 @@ TIME_RE = %r{
 #   https://en.wikipedia.org/wiki/Time_zone
 #   https://en.wikipedia.org/wiki/List_of_UTC_offsets
 #   https://en.wikipedia.org/wiki/UTC−04:00  etc.
-
+#
+#  e.g. (UTC-2) or (CEST/UTC-2) etc.
+#    todo check - only allow upcase 
+#    or  (utc-2) and (cest/utc-2) too - why? why not?
+ 
 TIMEZONE_RE = %r{
-   ## e.g. (UTC-2) or (CEST/UTC-2) etc.
    (?<timezone>
       \(
            ## optional "local" timezone name eg. BRT or CEST etc.
@@ -60,6 +64,35 @@ TIMEZONE_RE = %r{
 
 
 
+## add wday / stand-alone week day - as separate regex or 
+##          use TEXT with is_wday? check or such with
+##                requirement of beginning of line (anchored to line) only??
+##       - why? why not?
+
+WDAY_RE = %r{
+(?<wday>
+  \b     # note - alternation (|) is lowest precedence (such 
+         #    parathenes required around \b()\b !!!
+         ## note - NOT case sensitive!!!    
+       (?<day_name>
+        (?-i:
+          Mon|Mo|
+          Tue|Tu|
+          Wed|We|
+          Thu|Th|
+          Fri|Fr|
+          Sat|Sa|
+          Sun|Su
+       ))
+  \b     ## todo/check - must be followed by two spaces or space + [( etc.
+         ##   to allow words starting with weekday abbrevations - why? why not?
+         ##     check if any names (teams, rounds, etc) come up in practice 
+         ##   or maybe remove three letter abbrevations Mon/Tue
+         ##    and keep only Mo/Tu/We etc. - why? why not?
+)}x    
+
+
+
 
 BASICS_RE = %r{
     ## e.g. (51) or (1) etc.  - limit digits of number???
@@ -78,179 +111,18 @@ BASICS_RE = %r{
     (?<spaces> [ ]{2,}) |
     (?<space>  [ ])
         |
-    (?<sym>[;,@|\[\]-])
-}ix
-
-
-## removed from basics
-=begin
-    (?<none>
-       (?<=[ \[]|^)	 # Positive lookbehind for space or [
-           -
-        (?=[ ]*;)   # positive lookahead for space
-    )
-       |
-   (?<vs>
-       (?<=[ ])	# Positive lookbehind for space
-       (?:
-          vs\.?|   ## allow optional dot (eg. vs. v.)
-          v\.?|
-          -
-       )   # not bigger match first e.g. vs than v etc.
-       (?=[ ])   # positive lookahead for space
-    )
-       |
- 
-    make - into a simple symbol !!!
-=end
-
-
-MINUTE_RE = %r{
-     (?<minute>
-       (?<=[ (])	 # Positive lookbehind for space or opening ( e.g. (61') required
-           (?<value>\d{1,3})      ## constrain numbers to 0 to 999!!!
-        (?: \+
-            (?<value2>\d{1,3})
-        )?
-        '     ## must have minute marker!!!!
-     )
-}ix
-
-
-##   goal types
-# (pen.) or (pen) or (p.) or (p)
-## (o.g.) or (og)
-GOAL_PEN_RE = %r{
-   (?<pen> \(
-           (?:pen|p)\.?
-           \)
+    (?<sym>  (?<=^|[ ])  ## positive lookahead 
+                  (?: ----|
+                      ---|
+                      --
+                  )
+             (?=[ ])   ## positive lookahead
     )
-}ix
-GOAL_OG_RE = %r{
-   (?<og> \(
-          (?:og|o\.g\.)
-          \)
-   )
-}ix
-
-
-
-
-
-
-PROP_BASICS_RE = %r{
-    (?<spaces> [ ]{2,}) |
-    (?<space>  [ ])
         |
-    (?<sym>[.;,\(\)\[\]-])   ## note - dot (.) is the (all-important) end-of-prop marker!!!
+    (?<sym> [;,/@|\[\]-] )
 }ix
 
 
-## name different from text (does not allow number in name/text)
-##
-##  note - includes special handling for dot (.) if at the end of line!!!
-##            end-of-line dot (.) is the prop end-of-marker - do NOT eat-up!!!
-
-PROP_NAME_RE = %r{
-                 (?<prop_name> \b
-                   (?<name>
-                      \p{L}+       
-                       (?: \. (?: (?![ ]*$) )
-                        )?      ## edge case - check for end of prop marker! (e.g. Stop.)
-                      (?: 
-                          [ ]?    # only single spaces allowed inline!!!
-                          (?:
-                              (?:
-                                (?<=\p{L})   ## use lookbehind
-                                 [/'-]   ## must be surrounded by letters
-                                       ## e.g. One/Two NOT
-                                       ##      One/ Two or One / Two or One /Two etc.
-                                (?=\p{L})      ## use lookahead        
-                              )
-                                 |   
-                              (?:
-                                (?<=[ ])   ## use lookbehind  -- add letter (plus dot) or such - why? why not?
-                                 [']   ## must be surrounded by leading space and
-                                       ## traling letters  (e.g. UDI 'Beter Bed)
-                                (?=\p{L})      ## use lookahead        
-                              )   
-                                 |
-                              (?:
-                                (?<=\p{L})   ## use lookbehind
-                                 [']   ## must be surrounded by leading letter and
-                                       ## trailing space PLUS letter  (e.g. UDI' Beter Bed)
-                                (?=[ ]\p{L})      ## use lookahead (space WITH letter         
-                              )   
-                                 |
-                              (?: \p{L}+
-                                  (?: \. 
-                                      (?: (?![ ]*$) )
-                                  )?  ## last dot is delimiter!!!
-                              )
-                          )+
-                     )*
-                   )
-               ## add lookahead - must be non-alphanum (or dot)
-                  (?=[ .,;\]\)]|$)
-                  )
-}ix
-
-
-
-
-##############
-#  add support for props/ attributes e.g.
-# 
-#    Germany:    Neuer - Kimmich, Rüdiger, Tah [Y], Mittelstädt – Andrich [Y] (46' Groß),
-#      Kroos (80' Can) – Musiala (74' Müller), Gündogan,
-#      Wirtz (63' Sane) – Havertz (63' Füllkrug).
-#    Scotland:   Gunn – Porteous [R 44'], Hendry, Tierney (78' McKenna) – Ralston [Y],
-#      McTominay, McGregor (67' Gilmour), Robertson – Christie (82' Shankland),
-#      Adams (46' Hanley), McGinn (67' McLean).
-#
-## note:  colon (:) MUST be followed by one (or more) spaces
-##      make sure mon feb 12 18:10 will not match
-##        allow 1. FC Köln etc.
-##               Mainz 05:
-##           limit to 30 chars max
-##          only allow  chars incl. intl but (NOT ()[]/;)
-
-
-  PROP_KEY_RE = %r{ 
-                 (?<prop_key> \b
-                   (?<key>
-                       (?:\p{L}+
-                           |
-                           \d+  # check for num lookahead (MUST be space or dot)
-                        ## MUST be followed by (optional dot) and
-                        ##                      required space !!!
-                        ## MUST be follow by a to z!!!!
-                         \.?     ## optional dot
-                         [ ]?   ## make space optional too  - why? why not?
-                             ##  yes - eg. 1st, 2nd, 5th etc.
-                         \p{L}+
-                        )
-                        [\d\p{L}'/° -]*?   ## allow almost anyting 
-                                          ## fix - add negative lookahead 
-                                          ##         no space and dash etc.
-                                          ##    only allowed "inline" not at the end
-                                          ## must end with latter or digit!
-                   )
-                    [ ]*?     # slurp trailing spaces
-                     :
-                    (?=[ ]+)  ## possitive lookahead (must be followed by space!!)
-                   )
-                 }ix
-
-
-
-
-PROP_RE = Regexp.union(
-   PROP_BASICS_RE, 
-   MINUTE_RE,
-   PROP_NAME_RE,
-)
-
 
 
 RE = Regexp.union(  PROP_KEY_RE, ##  start with prop key (match will/should switch into prop mode!!!)
@@ -259,8 +131,11 @@ RE = Regexp.union(  PROP_KEY_RE, ##  start with prop key (match will/should swit
                      TIME_RE,
                      DURATION_RE,  # note - duration MUST match before date
                     DATE_RE,
-                    SCORE_RE,
-                    BASICS_RE, MINUTE_RE,
+                    WDAY_RE,   # allow standalone weekday name (e.g. Mo/Tu/etc.) - why? why not?
+                    SCORE_MORE_RE, 
+                    SCORE_RE,   ## note basic score e.g. 1-1 must go after SCORE_MORE_RE!!!
+                    BASICS_RE, 
+                    MINUTE_RE,
                     GOAL_OG_RE, GOAL_PEN_RE,
                      TEXT_RE )
 

data/lib/sportdb/parser/version.rb

@@ -3,8 +3,8 @@ module SportDb
   module Module
     module Parser
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
-  MINOR = 5
-  PATCH = 9
+  MINOR = 6
+  PATCH = 1
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/sportdb/parser.rb

@@ -21,6 +21,8 @@ require_relative 'parser/token-score'
 require_relative 'parser/token-date'
 require_relative 'parser/token-text'
 require_relative 'parser/token-status'
+require_relative 'parser/token-minute'
+require_relative 'parser/token-prop'    ## team prop(erty) mode (note - must be before token)
 require_relative 'parser/token'
 require_relative 'parser/lexer'
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-parser
 version: !ruby/object:Gem::Version
-  version: 0.5.9
+  version: 0.6.1
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-01-29 00:00:00.000000000 Z
+date: 2025-02-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cocos
@@ -102,6 +102,8 @@ files:
 - lib/sportdb/parser/racc_parser.rb
 - lib/sportdb/parser/racc_tree.rb
 - lib/sportdb/parser/token-date.rb
+- lib/sportdb/parser/token-minute.rb
+- lib/sportdb/parser/token-prop.rb
 - lib/sportdb/parser/token-score.rb
 - lib/sportdb/parser/token-status.rb
 - lib/sportdb/parser/token-text.rb