sportdb-parser 0.6.15 → 0.6.16

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d907a1b09e04c9c17884afe7881961b597b547ca9ab742ecb6e06f89f8bfe151
-  data.tar.gz: da287bc13de7217bf3c6a2ffcfdd8d7f3d376baff413b79a58dd544bb2bfcc3a
+  metadata.gz: 3da9280d27bf1e4662eb10f9451679e4aace18b9a0e1bfa29dd1e7b6bcbdc5e5
+  data.tar.gz: e6786f648848cd075ef3e0f6d8d7fda2d31743f989653c0fcf2312a33a223357
 SHA512:
-  metadata.gz: 3be1466a2d4ef5a5d1129f6b0fa9f67c6258c5a1cc60aab831ac5c4c7121e691fa64a9f33e71508d91b9809bcdc1b77b152fc2f7c1580172937662865e8ee33e
-  data.tar.gz: fe14835fc3195b5e441bdd3f9763bfe1303aa471e041a908cafc027becfbfd5ffd2e9696948e2dd88647ef7de88ebabf39674e42ba6656144e478150822e699e
+  metadata.gz: 04250d17d120c12dc0b3980ff971b02fa178e617f35af70651f86011d9f5d4cad1d81df84a1f5af97ab73cb9023cc6cb190b13c420af71f3bcb2af7df6a526f1
+  data.tar.gz: 120486063a9a82891a63914654965b799aef774680695de8bda3bb52894399d0800b98efb852f87f672dbe303dc6c415b91a10a094989e94ddf3e319b3183cc9

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.6.15
+### 0.6.16
 ### 0.0.1 / 2024-07-12
 
 * Everything is new. First release.

data/lib/sportdb/parser/lexer.rb

@@ -290,6 +290,20 @@ end   # method tokenize_with_errors
 
 
 
+### add a QUICK_PLAYER_WITH_MINUTE  check
+QUICK_PLAYER_WITH_MINUTE_RE = %r{
+      \b
+         \d{1,3}      ## constrain numbers to 0 to 999!!!
+        (?: (?: 
+                \+\d{1,3}   
+            )?
+            |
+            (?: \?{2} | _{2} )  ## add support for n/a (not/available)
+        )           
+        '   ## must have minute marker!!!!
+}ix 
+ 
+
 def _tokenize_line( line )
   tokens = []
   errors = []   ## keep a list of errors - why? why not?
@@ -387,7 +401,12 @@ def _tokenize_line( line )
   
       offsets = [m.begin(0), m.end(0)]
       pos = offsets[1]    ## update pos
-    elsif (m = PLAYER_WITH_MINUTE_RE.match( line ))
+
+    ####  FIX/FIX/TODO
+    ### looks to hang in player with minute 
+    ###  FIX - improve / rework PLAYER_WITH_MINUTE_RE  regex!!!!
+    elsif (_quick = QUICK_PLAYER_WITH_MINUTE_RE.match(line) &&
+                m = PLAYER_WITH_MINUTE_RE.match( line ))
       ##  switch context to GOAL_RE (goalline(s)
       ##   split token (automagically) into two!! - player AND minute!!!
       @re = GOAL_RE
@@ -414,7 +433,7 @@ def _tokenize_line( line )
     end
   end
 
-  
+
 
   old_pos = -1   ## allows to backtrack to old pos (used in geo)
 

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

@@ -43,6 +43,28 @@ class Lexer
                 ## todo/check:  remove loakahead assertion here - why require space?
                 ## note: \b works only after non-alphanum e.g. )
 
+   ####
+   ## support short all-in-one e.g.
+   ##  e.g.      3-4 pen. 2-2 a.e.t. (1-1, 1-1) becomes
+   ##   3-4 pen. (2-2, 1-1, 1-1)            
+         
+   SCORE__P_ET_FT_HT_V2__RE = %r{
+          (?<score_more>
+               \b
+                (?<p1>\d{1,2}) - (?<p2>\d{1,2})
+                   [ ]* #{P_EN} [ ]+       
+                   \(
+               (?<et1>\d{1,2}) - (?<et2>\d{1,2})
+                   [ ]*, [ ]*
+               (?<ft1>\d{1,2}) - (?<ft2>\d{1,2})
+                   [ ]*, [ ]*
+               (?<ht1>\d{1,2}) - (?<ht2>\d{1,2})
+                   [ ]*
+                \)
+               (?=[ ,\]]|$)
+            )}ix       ## todo/check:  remove loakahead assertion here - why require space?
+                               ## note: \b works only after non-alphanum e.g. )
+
 
     ## e.g. 3-4 pen. 2-2 a.e.t. (1-1, 1-1)  or
     ##      3-4p 2-2aet (1-1, )     or
@@ -128,7 +150,8 @@ class Lexer
 ## check - find a better name for SCORE_MORE - SCORE_EX, SCORE_BIG, or ___ - why? why not?
 
 SCORE_MORE_RE = Regexp.union(
-  SCORE__P_ET_FT_HT__RE,  # e.g. 5-1 pen. 2-2 a.e.t. (1-1, 1-0)
+  SCORE__P_ET_FT_HT_V2__RE,  # e.g. 5-1 pen. (2-2, 1-1, 1-0)  
+  SCORE__P_ET_FT_HT__RE,    # e.g. 5-1 pen. 2-2 a.e.t. (1-1, 1-0)
   SCORE__P_FT_HT__RE,     # e.g. 5-1 pen. (1-1)
   SCORE__P_ET__RE,        # e.g. 2-2 a.e.t.  or  5-1 pen. 2-2 a.e.t.
   SCORE__P__RE,           # e.g. 5-1 pen.

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 = 6
-  PATCH = 15
+  PATCH = 16
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-parser
 version: !ruby/object:Gem::Version
-  version: 0.6.15
+  version: 0.6.16
 platform: ruby
 authors:
 - Gerald Bauer