sportdb-parser 0.5.7 → 0.5.8

data/lib/sportdb/parser/racc_parser.rb

@@ -8,13 +8,15 @@ class RaccMatchParser
 def initialize( txt,  debug: false )
     ## puts "==> txt:"
     ## puts txt
-   
-    parser = SportDb::Parser.new
+ 
+    @tree   = [] 
+    @errors = []
+
     ### todo:
     ##  -  pass along debug flag
-    ##  -   use tokenize_with_errors and add/collect tokenize errors
-
-    @tokens = parser.tokenize( txt )
+    lexer = SportDb::Lexer.new( txt )
+    ##  note - use tokenize_with_errors and add/collect tokenize errors
+    @tokens, @errors = lexer.tokenize_with_errors
     ## pp @tokens
     
     ## quick hack - convert to racc format single char literal tokens e.g. '@' etc.
@@ -49,19 +51,30 @@ def initialize( txt,  debug: false )
 #      puts "Parse error on token: #{error_token_id}, value: #{error_value}"
 #  end  
 
-  def parse    
+  def parse_with_errors    
      trace( "start parse:" )
-     @tree = [] 
      do_parse
-     @tree
+     [@tree, @errors]
+  end
+
+  def parse  ## convenience shortcut (ignores errors)
+    tree, _ = parse_with_errors
+    tree 
   end
 
 
-  def on_error(*args)
+  attr_reader :errors
+  def errors?()   @errors.size > 0; end
+
+
+  def on_error(error_token_id, error_value, value_stack)
+    args = [error_token_id, error_value, value_stack]
     puts
     puts "!! on parse error:"
     puts "args=#{args.pretty_inspect}"
-    exit 1  ##   exit for now  -  get and print more info about context etc.!!
+
+    @errors << "parse error on 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/racc_tree.rb

@@ -66,7 +66,7 @@ RoundDef   = Struct.new( :name, :date, :duration )  do
     printer.text( "<RoundDef " )
     printer.text( self.name )
     printer.text( " date=" + self.date.pretty_inspect ) if date
-    printer.text( " durattion=" + self.duration.pretty_inspect ) if duration
+    printer.text( " duration=" + self.duration.pretty_inspect ) if duration
     printer.text( ">" )
   end
 end

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

@@ -1,5 +1,5 @@
 module SportDb
-class Parser
+class Lexer
 
 
 
@@ -297,6 +297,6 @@ DURATION_RE = Regexp.union(
 
 
 
-end  #   class Parser
+end  #   class Lexer
 end  # module SportDb
 

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

@@ -1,5 +1,5 @@
 module SportDb
-class Parser
+class Lexer
 
 
     ## todo/check: use ‹› (unicode chars) to mark optional parts in regex constant name - why? why not?
@@ -130,5 +130,5 @@ SCORE_RE = Regexp.union(
   SCORE__FT_HT__RE,        # e.g. 1-1 (1-0) or 1-1  -- note - must go last!!!
 )
 
-end  #  class Parser
+end  #  class Lexer
 end  # module SportDb

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

@@ -1,5 +1,5 @@
 module SportDb
-class Parser
+class Lexer
   
 ##  (match) status
 ##    note: english usage - cancelled (in UK), canceled (in US)
@@ -40,6 +40,6 @@ STATUS_RE = %r{
 }ix
 
 
-end  #  class Parser
+end  #  class Lexer
 end  # module SportDb
   

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

@@ -1,5 +1,5 @@
 module SportDb
-class Parser
+class Lexer
 
 
 ##  note - do NOT allow single alpha text for now
@@ -129,5 +129,5 @@ TEXT_RE = %r{
 }ix
 
 
-end # class Parser
+end # class Lexer
 end # module SportDb

data/lib/sportdb/parser/token.rb

@@ -1,7 +1,7 @@
 
 
 module SportDb
-class Parser
+class Lexer
 
 
 ##
@@ -265,5 +265,5 @@ RE = Regexp.union(  PROP_KEY_RE, ##  start with prop key (match will/should swit
                      TEXT_RE )
 
 
-end  # class Parser
+end  # class Lexer
 end # module SportDb

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 = 5
-  PATCH = 7
+  PATCH = 8
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/lib/sportdb/parser.rb

@@ -22,7 +22,7 @@ require_relative 'parser/token-date'
 require_relative 'parser/token-text'
 require_relative 'parser/token-status'
 require_relative 'parser/token'
-require_relative 'parser/tokenizer'
+require_relative 'parser/lexer'
 
 require_relative 'parser/parser'   ## auto-generated by racc (from parser.y)
 require_relative 'parser/racc_parser'
@@ -46,18 +46,37 @@ end  # module SportDb
 
 
 module SportDb
-###
-##  todo/fix -   use LangHelper or such
-##   e.g.     class Parser
-##                include LangHelper
-##            end
 class Parser
-  ## keep "old" access to checking for group, round & friends
-  ##    for now for compatibility
-  def is_group?( text )  Lang.is_group?( text ); end
-  def is_round?( text )  Lang.is_round?( text ); end
-  def is_leg?( text )    Lang.is_leg?( text ); end
-end
+####################
+#  "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: 0.5.7
+  version: 0.5.8
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-01-22 00:00:00.000000000 Z
+date: 2025-01-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cocos
@@ -97,6 +97,7 @@ files:
 - config/rounds_pt.txt
 - lib/sportdb/parser.rb
 - lib/sportdb/parser/lang.rb
+- lib/sportdb/parser/lexer.rb
 - lib/sportdb/parser/parser.rb
 - lib/sportdb/parser/racc_parser.rb
 - lib/sportdb/parser/racc_tree.rb
@@ -105,7 +106,6 @@ files:
 - lib/sportdb/parser/token-status.rb
 - lib/sportdb/parser/token-text.rb
 - lib/sportdb/parser/token.rb
-- lib/sportdb/parser/tokenizer.rb
 - lib/sportdb/parser/version.rb
 homepage: https://github.com/sportdb/sport.db
 licenses: