sportdb-parser 0.7.2 → 0.8.0

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

@@ -126,7 +126,7 @@ GEO_RE = Regexp.union(
                     SPACES_RE,
                     GEO_END_RE,
                     GEO_TEXT_RE,
-                    /  (?<sym> [,›>\[] ) /x,
+                    /  (?<sym> [,›>\[▪] ) /x,
                     ANY_RE,
                       )
 

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

@@ -92,14 +92,6 @@ START_GOAL_LINE_ALT_RE = %r{
 
 
 
-
-###
-##  e.g.  (-; Metzger)
-GOAL_NONE_RE = %r{ (?<goals_none>
-                        -[ ]*;
-                    )
-                 }x
-
 ###
 #  note - alternate goal separator dash (-) MUST have leading and trailing space!!!
 #    e.g.   (Metzger 83 - Krämer 29, 88, Cichy 33, Rahn 37)

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

@@ -263,6 +263,46 @@ ENCLOSED_NAME_RE = %r{
 
 
 
+###
+##  e.g.   -; ...   or
+##         None - ... or
+CARDS_NONE_LEFT_RE = %r{ (?<cards_none_left>
+                         ## (i) w/ semicolon (;)
+                            (?:  (?: - | \bnone)
+                                  [ ]* ;
+                            )
+                         ## (ii) w/ dash (-)
+                          | (?:   (?: ∅ | \bnone)
+                                  [ ]+ -        ##    space REQUIRED
+                                  (?=[ ]|\z)    ## positive lookahead - speace required
+                            )
+                    )}ix
+
+## e.g   ... ;-
+##    or ... ; None
+CARDS_NONE_RIGHT_RE = %r{ (?<cards_none_right>
+                        ## (i) w/ semicolon (;)
+                           (?:   ; [ ]*
+                               (?:   - | none\b)
+                           )
+                        ## (ii) w/ dash (-)
+                          | (?:
+                               (?<=[ ])      ## positive lookbehind - space required
+                                - [ ]+       ##    space REQUIRED
+                               (?:  ∅ | none\b)
+                            )
+                      )}ix
+
+
+CARDS_SEP_ALT_RE = %r{(?<cards_sep_alt>
+              (?<=[ ])      ## positive lookbehind - space required
+                -
+              (?=[ ]|\z)    ## positive lookahead - speace required
+             )}x
+
+
+
+
 
 
 end  # class Lexer

data/lib/sportdb/parser/token.rb

@@ -58,6 +58,35 @@ VS_RE = %r{
 }ix
 
 
+##
+## ▪SF  or ▪1,▪17, etc.
+##   note - only numbers and upcase allowed
+##                limited to two-letters for now - make more generic - why? why not?
+##                may add SF1, SF2, or such later !!!
+INLINE_ROUND_SHORT_RE = %r{
+         (?<inline_round_short>
+               ▪
+            (?<inline_round_text>
+                    [0-9]+
+                  | [A-Z]{1,2} [0-9]*
+              )
+          (?= [ ]|$)   # positive lookAHEAD for space (or end-of-line)
+        )}x
+
+###
+##  ▪ Replay
+##  ▪ 1st Leg
+INLINE_ROUND_BIG_RE = %r{
+       (?<inline_round_big>
+            ▪ [ ]
+             (?<inline_round_text>
+                [^\[\(@]+?  ## note - non-greedy
+                            ##   allow commas (,) or slash(/) - why? why not?
+              )
+          (?= [ ]{2}|$)   # positive lookAHEAD for TWO(!) spaces (or end-of-line)
+        )}x
+
+
 
 
 ##############
@@ -68,6 +97,10 @@ VS_RE = %r{
 
 RE = Regexp.union(
                     SPACES_RE,
+
+                    INLINE_ROUND_SHORT_RE,
+                    INLINE_ROUND_BIG_RE,
+
                     STATUS_RE,   ## match status e.g. [cancelled], etc.
 
                     INLINE_WO_RE,    ## (inline) match status - w/o (walkout)

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 = 7
-  PATCH = 2
+  MINOR = 8
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/sportdb/parser.rb

@@ -6,8 +6,9 @@ require 'cocos'
 require_relative 'parser/version'
 
 
+require_relative 'parser/debuggable'    ## generic debug/logger helper
+
 
-## core machinery
 
 ##
 ## add shared/most basic regexes here
@@ -61,11 +62,12 @@ require_relative 'parser/token'
 
 
 require_relative 'parser/lexer_buffer'   ## incl. Tokens (aka TokenBuffer)
+require_relative 'parser/lexer_token'
 
 require_relative 'parser/lexer-prep_doc'
 require_relative 'parser/lexer-prep_line'
 
-require_relative 'parser/lexer_token'
+require_relative 'parser/lexer-logger'   ## e.g. _trace, _warn, _info, etc.
 require_relative 'parser/lexer-tokenize'
 require_relative 'parser/lexer-on_round_def'
 require_relative 'parser/lexer-on_group_def'
@@ -79,62 +81,58 @@ require_relative 'parser/lexer'
 
 ## note - use "embeded" racc parser runtime
 ##    MUST uncomment  require 'racc/parser'  in generated parser!!!
-require_relative 'parser/parser_runtime'
+require_relative 'parser/parser-runtime'
 
 require_relative 'parser/parser'   ## auto-generated by racc (from parser.y)
-require_relative 'parser/racc_parser'
-require_relative 'parser/racc_tree'
+require_relative 'parser/parser-top'
+
+require_relative 'parser/parse_tree--core'    ## incl. core extensions eg. as_json on Object/Array/Hash
+require_relative 'parser/parse_tree'
+require_relative 'parser/parse_tree-match'
+require_relative 'parser/parse_tree-props'
+
+
+## deprecated - remove old RaccMatchParser name sooner than later!!
+##    use Fbtxt.parse for "public" api
+RaccMatchParser = SportDb::Parser
 
 
 
 ###
 #  make parser api (easily) available - why? why not?
+#
+#  use Fbtxt.parse( txt ) &&
+#      Fbtxt.lex( txt)            -- or Fbtxt.tokenize?
+#
+#   Fbtxt.lex( txt,
+#                 flatten: true|false,        ## keep nested [] for lines (no NEWLINE tokens)
+#                 transform: true|false )     ## builtin transforms eg. merge DATE & TIME => DATETIME, etc.
+#
+#   how to deal with errors?
+##    always return   [tokens, errors] or such?
+##           or return a Result struct - why? why not?
 
-=begin
-module SportDb
-   def self.parser() @@parser ||= Parser.new; end
-   def self.parse( ... )
-   end
-   def self.tokenize( ... )
-   end
-end  # module SportDb
-=end
+
+
+module Fbtxt
+
+def self.lex( txt, flatten: true )      ## returns SportDb::LexerResult (ok?/tokens/errors)
+  lexer = SportDb::Lexer.new( txt )
+  ## move "wrapping" into result obj inside lexer - why? why not?
+  tokens, errors = lexer.tokenize_with_errors( flatten: flatten )
+  SportDb::LexerResult.new( tokens, errors )
+end
+
+def self.parse( txt )   ## returns SportDb::ParserResult (ok?/tree/errors)
+  parser = SportDb::Parser.new( txt )
+  ## move "wrapping" into result obj inside parser - why? why not?
+  tree, errors = parser.parse_with_errors
+  SportDb::ParserResult.new( tree, errors )
+end
+end #  module Fbtxt
 
 
 
-module SportDb
-class Parser
-####################
-#  "default" lexer & parser  (wraps RaccMatchParser)
-
-  def tokenize_with_errors( lines, debug: false )
-     lexer = Lexer.new( lines )
-     tokens, errors = lexer.tokenize_with_errors
-     [tokens, errors]
-  end
-
-  ### convience helper - ignore errors by default
-  def tokenize( lines, debug: false )
-    tokens, _ = tokenize_with_errors( lines, debug: debug )
-    tokens
-  end
-
-
-  def parse_with_errors( lines, debug: false )
-    ## todo/check - if lines needs to chack for array of lines and such
-    ##                        or handled by tokenizer???
-    parser = RaccMatchParser.new( lines )
-    tree, errors = parser.parse_with_errors
-    [tree, errors]
-  end
-
-  ### convience helper - ignore errors by default
-  def parse( lines, debug: false )
-    tree, _ = parse_with_errors( lines, debug: debug )
-    tree
-  end
-end  # class Parser
-end  # module SportDb
 
 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-parser
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.8.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-06-08 00:00:00.000000000 Z
+date: 2026-07-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cocos
@@ -72,6 +72,8 @@ files:
 - README.md
 - Rakefile
 - lib/sportdb/parser.rb
+- lib/sportdb/parser/debuggable.rb
+- lib/sportdb/parser/lexer-logger.rb
 - lib/sportdb/parser/lexer-on_goal.rb
 - lib/sportdb/parser/lexer-on_group_def.rb
 - lib/sportdb/parser/lexer-on_prop_lineup.rb
@@ -85,10 +87,13 @@ files:
 - lib/sportdb/parser/lexer.rb
 - lib/sportdb/parser/lexer_buffer.rb
 - lib/sportdb/parser/lexer_token.rb
+- lib/sportdb/parser/parse_tree--core.rb
+- lib/sportdb/parser/parse_tree-match.rb
+- lib/sportdb/parser/parse_tree-props.rb
+- lib/sportdb/parser/parse_tree.rb
+- lib/sportdb/parser/parser-runtime.rb
+- lib/sportdb/parser/parser-top.rb
 - lib/sportdb/parser/parser.rb
-- lib/sportdb/parser/parser_runtime.rb
-- lib/sportdb/parser/racc_parser.rb
-- lib/sportdb/parser/racc_tree.rb
 - lib/sportdb/parser/token-date--helpers.rb
 - lib/sportdb/parser/token-date--names.rb
 - lib/sportdb/parser/token-date.rb

data/lib/sportdb/parser/racc_parser.rb

@@ -1,92 +0,0 @@
-
-####
-#   RaccMatchParser support machinery (incl. node classes/abstract syntax tree)
-
-class RaccMatchParser
-
-
-
-  def initialize( txt,  debug: false )
-    @tree   = []
-    @errors = []
-
-    lexer = SportDb::Lexer.new( txt, debug: debug )
-    ##  note - use tokenize_with_errors and add/collect tokenize errors
-    @tokens, @errors = lexer.tokenize_with_errors
-    ## pp @tokens
-
-  end
-
-
-  def debug( value ) @debug = value; end   ### fix: use setter-style e.g. debug=(value) !!!
-  def debug?()  @debug == true; end
-
-  ###
-  ###  fix-fix-fix   rename   to _trace
-  ##                   check lexer - add [debug] Parser -  or such!!!
-  ##
-  ## debug - trace / print message
-  def trace( msg )
-    puts " fix-fix-fix use _trace() in parser!!"
-    puts "  [parse] " + msg
-  end
-
-  def _trace( *args )
-    ## if debug?
-      print "[DEBUG] Parser -- "
-      args.each { |arg| puts args }
-    ## end
-  end
-
-
-  def next_token
-    tok = @tokens.shift
-   _trace( "next_token => #{tok.pretty_inspect}" )
-
-    ##  convert to racc format single char literal tokens e.g. '@' etc.
-    ##                  note - literal token MUST be string (NOT symbol)
-    ##    note - racc expects array with to items
-    ##               -  item[0] is the token id
-    ##               -  item[1] is the token value
-
-    ## note - returns nil for end-of-file !!!
-    tok = [tok.type, tok]   if tok
-
-    tok
-  end
-
-
-#  on_error do |error_token_id, error_value, value_stack|
-#      puts "Parse error on token: #{error_token_id}, value: #{error_value}"
-#  end
-
-  def parse_with_errors
-     _trace( "start parse:" )
-     do_parse
-     [@tree, @errors]
-  end
-
-  def parse  ## convenience shortcut (ignores errors)
-    tree, _ = parse_with_errors
-    tree
-  end
-
-
-  attr_reader :errors
-  def errors?()   @errors.size > 0; end
-
-
-  def on_error(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} >#{error_value.pretty_inspect}<, stack: #{value_stack.pretty_inspect}"
-  end
-
-
-end   # class RaccMatchParser