sportdb-parser 0.5.7 → 0.5.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: eb23029ea58744e513c4a6af7112ed46a3440540cb7fe77fd2b480c58bbd5b14
-  data.tar.gz: 2aba09728fa175dbde9e270ad7250ee047639c1b8641068bcb5d159cf7e0da34
+  metadata.gz: b3c102d758209b64a04033a772faad7cdaaa4631f5079e56b92dccdfc4b84292
+  data.tar.gz: 4b49b9a0234be96c552233b74fb4b2f8702b5d402d264382f2b13b9367515740
 SHA512:
-  metadata.gz: aa8dd925bdb7c3982ad18bba5f3864ee190535633043734186560e97a8692cfd589bf999e5e67fae3b23d3f625edd9608604b5fb3eb50222f84bd30a2dc97d0f
-  data.tar.gz: ac3e2c3a6c00a22e142db199c97842fad22f67f5c507456ff117ac82dde0ddcfa5ed0c4f0e0a23c78c491fb39ed9cc8d7058491c32bf645f5296ac76861b9aae
+  metadata.gz: 78faffba17eff5ff5dd4b665099cee8eff8addd5e8263433f0662da8a88bd4fa5fa80ed83968dcdb4b7c95ab4254508b156dc09c79ee2d58e556e20cf2168aba
+  data.tar.gz: 4a9a5546ccff399028a2e629a87e86e7c3ee505b7c5b16a15de0053918ddc8e7704c2c8c75517feaab0a9bb5648a8bcf63c66b2cc34800f9d41335748e336f66

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.5.7
+### 0.5.8
 ### 0.0.1 / 2024-07-12
 
 * Everything is new. First release.

data/Manifest.txt

@@ -9,6 +9,7 @@ config/rounds_misc.txt
 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
@@ -17,5 +18,4 @@ lib/sportdb/parser/token-score.rb
 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

data/lib/sportdb/parser/{tokenizer.rb → lexer.rb}

@@ -1,6 +1,6 @@
 
 module SportDb
-class Parser
+class Lexer
 
 
 
@@ -14,6 +14,20 @@ def log( msg )
 end
 
 
+  ###
+  ##  todo/fix -   use LangHelper or such
+  ##   e.g.     class Lexer
+  ##                include LangHelper
+  ##            end
+  ##
+  ##  merge back Lang into Lexer - why? why not?
+  ## 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
+
+
 ## transforms
 ##
 ##  Netherlands  1-2 (1-1)   England
@@ -107,15 +121,11 @@ end  # class Tokens
 
 
 
-### convience helper - ignore errors by default
-def tokenize( lines, debug: false )
-  tokens, _ = tokenize_with_errors( lines, debug: debug )
-  tokens
-end
+def debug?()  @debug == true; end
 
-def tokenize_with_errors( lines, debug: false )
+def initialize( lines, debug: false )
+   @debug = debug
 
-##
 ##  note - for convenience - add support
 ##         comments (incl. inline end-of-line comments) and empty lines here
 ##             why? why not?
@@ -137,33 +147,33 @@ def tokenize_with_errors( lines, debug: false )
     ##   strip lines with comments and empty lines striped / removed
     ##      keep empty lines? why? why not?
     ##      keep leading spaces (indent) - why?
-    txt = String.new
+    @txt = String.new
     txt_pre.each_line do |line|    ## preprocess
        line = line.strip
        next if line.empty? || line.start_with?('#')   ###  skip empty lines and comments
        
        line = line.sub( /#.*/, '' ).strip             ###  cut-off end-of line comments too
        
-       txt << line
-       txt << "\n"
+       @txt << line
+       @txt << "\n"
     end
-    
+end
+
 
+
+def tokenize_with_errors
     tokens_by_line = []   ## note: add tokens line-by-line (flatten later)
     errors         = []   ## keep a list of errors - why? why not?
   
-    txt.each_line do |line|
+    @txt.each_line do |line|
         line = line.rstrip   ## note - MUST remove/strip trailing newline (spaces optional)!!!
  
-        more_tokens, more_errors = _tokenize_line( line, debug: debug )
+        more_tokens, more_errors = _tokenize_line( line )
         
         tokens_by_line  << more_tokens   
         errors          += more_errors
     end # each line
 
-
-
-
     tokens_by_line = tokens_by_line.map do |tokens|
         #############
         ## pass 1
@@ -246,11 +256,11 @@ end   # method tokenize_with_errors
 
 
 
-def _tokenize_line( line, debug: false )
+def _tokenize_line( line )
   tokens = []
   errors = []   ## keep a list of errors - why? why not?
 
-  puts ">#{line}<"    if debug
+  puts ">#{line}<"    if debug?
 
   pos = 0
   ## track last offsets - to report error on no match
@@ -265,7 +275,7 @@ def _tokenize_line( line, debug: false )
 
 
   while m = @re.match( line, pos )
-    if debug
+    if debug?
       pp m
       puts "pos: #{pos}"
     end
@@ -274,10 +284,10 @@ def _tokenize_line( line, debug: false )
     if offsets[0] != pos
       ## match NOT starting at start/begin position!!!
       ##  report parse error!!!
-      msg =  "!! WARN - parse error - skipping >#{line[pos..(offsets[0]-1)]}< @#{offsets[0]},#{offsets[1]} in line >#{line}<"
+      msg =  "!! WARN - parse error (tokenize) - skipping >#{line[pos..(offsets[0]-1)]}< @#{offsets[0]},#{offsets[1]} in line >#{line}<"
       puts msg
 
-      errors << "parse error - skipping >#{line[pos..(offsets[0]-1)]}< @#{offsets[0]},#{offsets[1]}"
+      errors << "parse error (tokenize) - skipping >#{line[pos..(offsets[0]-1)]}< @#{offsets[0]},#{offsets[1]} in line >#{line}<"
       log( msg )
     end
 
@@ -288,7 +298,7 @@ def _tokenize_line( line, debug: false )
 
     pos = offsets[1]
 
-    pp offsets   if debug
+    pp offsets   if debug?
 
     ##
     ## note: racc requires pairs e.g. [:TOKEN, VAL]
@@ -331,7 +341,7 @@ def _tokenize_line( line, debug: false )
             when '-' then [:'-']
             when '.' then 
                 ## switch back to top-level mode!!
-                puts "  LEAVE PROP_RE MODE, BACK TO TOP_LEVEL/RE"  if debug
+                puts "  LEAVE PROP_RE MODE, BACK TO TOP_LEVEL/RE"  if debug?
                 @re = RE 
                 [:'.']
             else
@@ -352,7 +362,7 @@ def _tokenize_line( line, debug: false )
         elsif m[:prop_key]
            ##  switch context  to PROP_RE
            @re = PROP_RE
-           puts "  ENTER PROP_RE MODE"  if debug
+           puts "  ENTER PROP_RE MODE"  if debug?
            [:PROP, m[:key]]
         elsif m[:text]
           [:TEXT, m[:text]]   ## keep pos - why? why not?
@@ -462,7 +472,7 @@ def _tokenize_line( line, debug: false )
 
     tokens << t    if t
 
-    if debug
+    if debug?
       print ">"
       print "*" * pos
       puts "#{line[pos..-1]}<"
@@ -475,13 +485,12 @@ def _tokenize_line( line, debug: false )
     puts msg
     log( msg )
 
-    errors << "parse error - skipping >#{line[offsets[1]..-1]}< @#{offsets[1]},#{line.size}"
+    errors << "parse error (tokenize) - skipping >#{line[offsets[1]..-1]}< @#{offsets[1]},#{line.size} in line >#{line}<"
   end
 
 
   [tokens,errors]
 end
 
-
-end  # class Parser
+end  # class Lexer
 end # module SportDb