sportdb-parser 0.3.6 → 0.3.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7e55fb30d76a2b9ce61c129408590506d02fdfc0fdd699211d8255cd97bbdd30
-  data.tar.gz: 0b4af2b72f2375597ae4ff7e99925eb92971833c50e489064ca143706198b2b9
+  metadata.gz: eadc79627364072a1d05801fec096aca27e914f214639c4bbe6bbffca2acab0d
+  data.tar.gz: f052a6d668246082d9fbcc5b90c71b440048080dc423f9428a4560591e797080
 SHA512:
-  metadata.gz: e6f9c3fa8f3ac153208977662f6435858623a4b56d5506dd3238618fc23e34cc983c385325ce0346698ce2397e53b8c2ea3a16563caf1205d17be7448a2ae858
-  data.tar.gz: fd7a20830cd66a892db370e2f521139412266bc02821d6fed4ce36a7d8ac5c27913dcc4736c7a1834d46ed8c3156c5386e85bc57af9419dcac1f3d52b438f17d
+  metadata.gz: 394f74c596ad1a624d626757972911eee7e0b009df66d5cac7ed1508cb3b056ece6f7fbc1d3c310468d5d065ae22ba18a28d7f8992f333767f20279eb5ce2f78
+  data.tar.gz: ecaa4a25b3552e69013dea0cc9c87a91b3409cd02e86302f4387e658de6cdfadba2c82c7c31935d4f7c62aaab187a25ce6e85f9dc4239faa346838f5be8dce7b

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.3.6
+### 0.3.8
 
 ### 0.0.1 / 2024-07-12
 

data/Manifest.txt

@@ -3,6 +3,11 @@ Manifest.txt
 README.md
 Rakefile
 bin/fbtok
+config/rounds_de.txt
+config/rounds_en.txt
+config/rounds_es.txt
+config/rounds_misc.txt
+config/rounds_pt.txt
 lib/sportdb/parser.rb
 lib/sportdb/parser/fbtok/main.rb
 lib/sportdb/parser/lang.rb

data/config/rounds_de.txt

@@ -0,0 +1,93 @@
+###############
+#  rounds in deutsch (de) / german
+
+Vorrunde
+1. Vorrunde
+2. Vorrunde
+Gruppenphase
+Ligaphase
+Spiele            # in 2017/uy.1.txt -- double check if missing something
+                  # in 1960-61/it.1.txt
+
+
+Zwischenrunde
+
+Sechzehntelfinale
+Platzierungsspiel
+
+Qualifikation
+Qual. 3. Runde
+
+2. Aufstieg Halbfinale
+2. Aufstieg Finale
+
+Playoff-Runde
+Relegation
+Aufstieg
+Endrunde
+Aufstiegsrunde
+Aufstiegsrunde Zone A
+Entscheidung Zone B
+1. Aufstieg
+1. Aufstieg Zone A
+1. Aufstieg Zone B
+2. Aufstieg Zone A
+2. Aufstieg Zone B
+2. Aufstieg 1. Phase
+2. Aufstieg 2. Phase
+2. Aufstieg 3. Phase
+Direkter Aufstieg
+Direkter Abstieg
+3. Platz
+5. Platz
+7. Platz
+9. Platz
+11. Platz
+
+5.-8. Platz Playoffs
+9.-12. Platz Playoffs
+13.-16. Platz Playoffs
+
+
+Entscheidung 1. Runde
+Entscheidung 2. Runde
+
+
+Zwischenrunde Gr. B        ## move to group_de - why? why not?
+1. Runde Gruppe 1
+1. Runde Gruppe 2
+
+
+### todo/fix
+###   move to group - why? why not?
+Gruppe 1
+Gruppe 2
+Gruppe 3
+Gruppe 4
+Gruppe 5
+Gruppe 6
+Gruppe 7
+Gruppe 8
+Gruppe 9
+Gruppe 10
+Gruppe 11
+Gruppe 12
+Gruppe 13
+Gruppe 14
+Gruppe 15
+Gruppe 16
+
+
+Gruppe A
+Gruppe B
+Gruppe C
+Gruppe D
+Gruppe E
+Gruppe F
+Gruppe G
+Gruppe H
+Gruppe I
+Gruppe J
+Gruppe K
+Gruppe L
+

data/config/rounds_en.txt

@@ -0,0 +1,15 @@
+##########
+#  note - more english rounds here
+#    remove here if added to regex!!!
+
+Play-in round
+First semifinal
+Second semifinal
+
+Conference Semifinals
+Conference Finals
+Wildcard
+
+Elimination Final
+Quadrangular
+

data/config/rounds_es.txt

@@ -0,0 +1,19 @@
+#########
+#  rounds in español (es) / spanish
+
+Recalificación
+Reclasificación
+
+
+Preclasificación Nacional B
+
+Final Segunda Ronda
+Gran Final
+
+Interzone
+Zone A
+Zona B
+
+Final de Grupos
+Repechaje
+

data/config/rounds_misc.txt

@@ -0,0 +1,18 @@
+#######################
+#  more rounds  misc(ellaneous)
+
+District West I
+District West II
+District Noord
+District Oost
+District Zuid I
+District Zuid II
+
+Tussenronde
+Replay achtste finale
+Replay kwartfinale
+
+Replay 1e ronde
+Replay 2e ronde
+Replay halve finale
+Replay finale

data/config/rounds_pt.txt

@@ -0,0 +1,4 @@
+############################
+#  rounds in   português (pt) / portuguese
+
+Troféu do Interior

data/lib/sportdb/parser/lang.rb

@@ -150,8 +150,50 @@ ROUND_RE = %r{^(
 )$}ix
 
 
+####
+#  add more round names in different languages
+#    via txt files
+#
+#  for now must match case - maybe make caseinsensitive later - why? why not?
+def self.read_names( path )
+     txt = read_text( path )
+     names = [] # array of lines (with words)
+     txt.each_line do |line|
+       line = line.strip
+
+       next if line.empty?
+       next if line.start_with?( '#' )   ## skip comments too
+
+       ## strip inline (until end-of-line) comments too
+       ##   e.g. Janvier  Janv  Jan  ## check janv in use??
+       ##   =>   Janvier  Janv  Jan
+
+       line = line.sub( /#.*/, '' ).strip
+       ## pp line
+
+       names << line
+     end
+     names
+end
+
+
+def self.more_round_names
+   @more_round_name ||= begin
+                           names = []
+                           langs = ['en', 'de', 'es', 'pt', 'misc']
+                           ## sort names by length??
+                           langs.each do |lang|
+                             path = "#{SportDb::Module::Parser.root}/config/rounds_#{lang}.txt"
+                             names += read_names( path )
+                           end
+                           names
+                        end
+end
+
+
 def is_round?( text )
-    ROUND_RE.match?( text )
+    ROUND_RE.match?( text ) ||
+    self.class.more_round_names.include?( text )
 end
 
 ##

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

@@ -1,13 +1,13 @@
-module SportDb 
+module SportDb
 class Parser
-  
+
 
     ## todo/check: use ‹› (unicode chars) to mark optional parts in regex constant name - why? why not?
 
     #####
     #  english helpers (penalty, extra time, ...)
     ##   note - p must go last (shortest match)
-    #     pso = penalty shootout 
+    #     pso = penalty shootout
     P_EN  =  '(?: pso | pen\.? | p\.? )'     # e.g. p., p, pen, pen., PSO, etc.
     ET_EN =  '(?: aet | a\.e\.t\.? )'     # note: make last . optional (e.g a.e.t) allowed too
 
@@ -26,7 +26,20 @@ class Parser
             (?<et1>\d{1,2}) - (?<et2>\d{1,2})
                [ ]* #{ET_EN}
                (?=[ \]]|$)
-        )}ix  
+        )}ix
+                ## todo/check:  remove loakahead assertion here - why require space?
+                ## note: \b works only after non-alphanum e.g. )
+
+
+    ##  note: allow SPECIAL with penalty only
+    ##      3-4 pen.
+    SCORE__P__RE = %r{
+        (?<score>
+           \b
+              (?<p1>\d{1,2}) - (?<p2>\d{1,2})
+                [ ]* #{P_EN}
+                (?=[ \]]|$)
+         )}ix
                 ## todo/check:  remove loakahead assertion here - why require space?
                 ## note: \b works only after non-alphanum e.g. )
 
@@ -89,8 +102,8 @@ class Parser
 
     ## e.g. 2-1 (1-1) or
     ##      2-1
- 
-    SCORE__FT_HT__RE = %r{      
+
+    SCORE__FT_HT__RE = %r{
             (?<score>
               \b
               (?<ft1>\d{1,2}) - (?<ft2>\d{1,2})
@@ -104,18 +117,18 @@ class Parser
                     ## note: \b works only after non-alphanum e.g. )
 
 
-                    
+
 #############################################
-# map tables 
+# map tables
 #  note: order matters; first come-first matched/served
 
-SCORE_RE = Regexp.union( 
+SCORE_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_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__FT_HT__RE        # e.g. 1-1 (1-0)
+  SCORE__P__RE,           # e.g. 5-1 pen.
+  SCORE__FT_HT__RE,        # e.g. 1-1 (1-0) or 1-1  -- note - must go last!!!
 )
 
 end  #  class Parser
-end  # module SportDb 
-  
+end  # module SportDb

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

@@ -47,6 +47,10 @@ TEXT_RE = %r{
                       [ ]?   ## make space optional too  - why? why not?
                              ##  yes - eg. 1st, 2nd, 5th etc.
                        \p{L}+
+                  |
+                ## opt 3 - add weirdo case
+                ##   e.g. 5.-8. Platz Playoffs  - keep - why? why not?
+                    \d+\.-\d+\.  [ ]? \p{L}+
                )
 
               (?:(?:  (?:[ ]
@@ -57,13 +61,18 @@ TEXT_RE = %r{
                   )?
                 (?:
                   \p{L} |
-                  [&/']
+                  [&/'°]
                     |
                  (?:
                    \d+
-                   (?![0-9.:h'/+-])
+                   (?!
+                     [0-9h'+-] |    ## protected break on 12h / 12' / 1-1
+                                    ##  check usege for 3+4 - possible? where ? why?
+                     (?:[.:]\d)     ## protected/exclude/break on 12.03 / 12:03
+                    )
                    ## negative lookahead for numbers
                    ##   note - include digits itself!!!
+                   ##   note - remove / (slash) e.g. allows UDI'19/Beter Bed
                  )|
                  \.
                )

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 = 3
-  PATCH = 6
+  PATCH = 8
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sportdb-parser
 version: !ruby/object:Gem::Version
-  version: 0.3.6
+  version: 0.3.8
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-10-09 00:00:00.000000000 Z
+date: 2024-10-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cocos
@@ -81,12 +81,22 @@ extra_rdoc_files:
 - CHANGELOG.md
 - Manifest.txt
 - README.md
+- config/rounds_de.txt
+- config/rounds_en.txt
+- config/rounds_es.txt
+- config/rounds_misc.txt
+- config/rounds_pt.txt
 files:
 - CHANGELOG.md
 - Manifest.txt
 - README.md
 - Rakefile
 - bin/fbtok
+- config/rounds_de.txt
+- config/rounds_en.txt
+- config/rounds_es.txt
+- config/rounds_misc.txt
+- config/rounds_pt.txt
 - lib/sportdb/parser.rb
 - lib/sportdb/parser/fbtok/main.rb
 - lib/sportdb/parser/lang.rb