sportdb-parser 0.5.9 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 43f5fed1d5709a2bd2642046f1e3d367212c5ebcc71084f1a17b00738e5036de
-  data.tar.gz: 3082d8cf6879adb3735e2dc28a9213dbc5f0781438d0e4248244ac10d02085b5
+  metadata.gz: 9af6317b144478400067502e60de2f8d6232ebf6e036b0f99b78f9c29922dba2
+  data.tar.gz: 7066483378693f6376f9c30ec71e5d4172c817c11025dd4e669da6d581b6ad54
 SHA512:
-  metadata.gz: 50176108fb5d9c81ce7234a7abbdbc4e29aaf25af37005d442d0b351ea699c93dee02293d975a340d2e9f03a13c76836aa30d0278e6a6a82ba28fbbba313f50c
-  data.tar.gz: 90b3f15722d7540f70ebb10718a643473e19de09a15e014f70e65b815ff4ed014c4c953266918dbca2baf34da94bd5681e403d27cc2b97f643781bf6f714e23f
+  metadata.gz: '039fdc82039d05ae8f51847a79dd77c0a657e316e8b0705a28bdf2f8e594f37531ea07a230c9e1a9133f96293975190dba070f50515d58bc9926e4ef3e8e152f'
+  data.tar.gz: e0f6483cd26ba7ef4800ecf76efd6f05e01e3a2458dbc6b65fe6582654c8d28627facbfc8228655e361df84c43418c9583826908cdcf3d61bf06d186288c56fa

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.5.9
+### 0.6.0
 ### 0.0.1 / 2024-07-12
 
 * Everything is new. First release.

data/Manifest.txt

@@ -14,6 +14,8 @@ lib/sportdb/parser/parser.rb
 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

data/lib/sportdb/parser/lexer.rb

@@ -247,6 +247,11 @@ def tokenize_with_errors
     ## flatten tokens
     tokens = []
     tokens_by_line.each do |tok|
+
+         if debug?
+           pp tok
+         end
+
          tokens  += tok 
          tokens  << [:NEWLINE, "\n"]   ## auto-add newlines
     end
@@ -260,7 +265,7 @@ def _tokenize_line( line )
   tokens = []
   errors = []   ## keep a list of errors - why? why not?
 
-  puts ">#{line}<"    if debug?
+  puts "line: >#{line}<"    if debug?
 
   pos = 0
   ## track last offsets - to report error on no match
@@ -275,10 +280,10 @@ def _tokenize_line( line )
 
 
   while m = @re.match( line, pos )
-    if debug?
-      pp m
-      puts "pos: #{pos}"
-    end
+#    if debug?
+#      pp m
+#      puts "pos: #{pos}"
+#    end
     offsets = [m.begin(0), m.end(0)]
 
     if offsets[0] != pos
@@ -298,7 +303,7 @@ def _tokenize_line( line )
 
     pos = offsets[1]
 
-    pp offsets   if debug?
+#    pp offsets   if debug?
 
     ##
     ## note: racc requires pairs e.g. [:TOKEN, VAL]
@@ -306,12 +311,8 @@ def _tokenize_line( line )
 
 
   t = if @re == PROP_RE
-         if m[:space]
-              ## skip space
-              nil
-         elsif m[:spaces]
-              ## skip spaces
-              nil
+         if m[:space] || m[:spaces]
+              nil    ## skip space(s)
          elsif m[:prop_name]
                if m[:name] == 'Y'
                  [:YELLOW_CARD, m[:name]]
@@ -339,11 +340,11 @@ def _tokenize_line( line )
             when '(' then [:'(']
             when ')' then [:')']
             when '-' then [:'-']
-            when '.' then 
-                ## switch back to top-level mode!!
-                puts "  LEAVE PROP_RE MODE, BACK TO TOP_LEVEL/RE"  if debug?
-                @re = RE 
-                [:'.']
+           # when '.' then 
+           #     ## switch back to top-level mode!!
+           #     puts "  LEAVE PROP_RE MODE, BACK TO TOP_LEVEL/RE"  if debug?
+           #     @re = RE 
+           #     [:'.']
             else
               nil  ## ignore others (e.g. brackets [])
             end
@@ -353,12 +354,8 @@ def _tokenize_line( line )
              nil 
          end
       else  ## assume TOP_LEVEL (a.k.a. RE) machinery
-        if m[:space]
-           ## skip space
-           nil
-        elsif m[:spaces]
-           ## skip spaces
-           nil
+        if m[:space] || m[:spaces]
+           nil   ## skip space(s)
         elsif m[:prop_key]
            ##  switch context  to PROP_RE
            @re = PROP_RE
@@ -397,6 +394,7 @@ def _tokenize_line( line )
  ## map month names
  ## note - allow any/upcase JULY/JUL etc. thus ALWAYS downcase for lookup
             date[:y] = m[:year].to_i(10)  if m[:year]
+            date[:m] = m[:month].to_i(10)  if m[:month]
             date[:m] = MONTH_MAP[ m[:month_name].downcase ]   if m[:month_name]
             date[:d]  = m[:day].to_i(10)   if m[:day]
             date[:wday] = DAY_MAP[ m[:day_name].downcase ]   if m[:day_name]
@@ -417,6 +415,8 @@ def _tokenize_line( line )
             duration[:end][:wday] = DAY_MAP[ m[:day_name2].downcase ]   if m[:day_name2]
             ## note - for debugging keep (pass along) "literal" duration
             [:DURATION, [m[:duration], duration]]
+        elsif m[:wday]    ## standalone weekday e.g. Mo/Tu/We/etc.
+             [:WDAY, [m[:wday], { wday: DAY_MAP[ m[:day_name].downcase ] } ]]
         elsif m[:num]   ## fix - change to ord (for ordinal number!!!)
               ## note -  strip enclosing () and convert to integer
              [:ORD, [m[:num], { value: m[:value].to_i(10) } ]]
@@ -454,6 +454,7 @@ def _tokenize_line( line )
           case sym
           when ',' then [:',']
           when ';' then [:';']
+          when '/' then [:'/']
           when '@' then [:'@']
           when '|' then [:'|']
           when '[' then [:'[']
@@ -472,11 +473,11 @@ def _tokenize_line( line )
 
     tokens << t    if t
 
-    if debug?
-      print ">"
-      print "*" * pos
-      puts "#{line[pos..-1]}<"
-    end
+#    if debug?
+#      print ">"
+#      print "*" * pos
+#      puts "#{line[pos..-1]}<"
+#    end
   end
 
   ## check if no match in end of string
@@ -489,6 +490,24 @@ def _tokenize_line( line )
   end
 
 
+   ##
+   ## if in prop mode continue if   last token is [,-]
+   ##        otherwise change back to "standard" mode
+   if @re == PROP_RE
+     if [:',', :'-'].include?( tokens[-1][0] )
+        ## continue/stay in PROP_RE mode
+        ##  todo/check - auto-add PROP_CONT token or such
+        ##                to help parser with possible NEWLINE
+        ##                  conflicts  - why? why not?
+     else
+        ## switch back to top-level mode!!
+        puts "  LEAVE PROP_RE MODE, BACK TO TOP_LEVEL/RE"  if debug?
+        @re = RE 
+        ## note - auto-add PROP_END (<PROP_END>)
+        tokens << [:PROP_END, "<PROP_END>"]    
+     end
+   end
+  
   [tokens,errors]
 end