fbtok 0.1.2 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: efa16f747083c94f0a8fbb8df7ac3d1718ad2c204fca2008b711da35a7adf5ac
-  data.tar.gz: da8dfd82204875f23fc9efa236a1af79701e83047c5c3bf1fc34b4032371db51
+  metadata.gz: 191b44113dea92aebe49fb5717146c9cd0038afb448ba34c4dd828e6daeb869e
+  data.tar.gz: 7367ad2ae027d158371ac63fcbbe53271da84f1dabbd4a4f2111ebd658d0c2c7
 SHA512:
-  metadata.gz: 29635412c9fb671cc254fa735dbf994289a961d02b92ca2480e80f4021d7f0d5b154f3b6d00c10cf50b1bce6f950ab624cbb1865d1273595a9401ad9c66a9ad4
-  data.tar.gz: b81ed7ecffc27725bef9dbb0f9b448eac302b649e89b7ac7da68c556fff4b14a4243dfe736145210b4cabc3a4b1b30d6633ab7a4d9fcd9f4e8082fc88522b275
+  metadata.gz: 85d8e883d5fbe0654a5188b3c0d46b1be2f694a96a6fe9d70a6b88ce36d7676200165f82e999ef2b77dd2fc6f453da0dfd30b06e8ed4cc0a622e5a20329cb61e
+  data.tar.gz: 947f91db38384711f3fa734f7ef52b51068f01d78b9ecd953ac17caa94afe61e748971341ceafb0bcddf6a120b2d30324d6820ff77a675ded8d494b354614b43

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.1.2
+### 0.2.1
 ### 0.0.1 / 2025-01-02
 
 * Everything is new. First release.

data/Manifest.txt

@@ -5,6 +5,7 @@ Rakefile
 bin/fbchk
 bin/fbt
 bin/fbtok
+bin/fbtree
 bin/fbx
 lib/fbtok.rb
 lib/fbtok/linter.rb

data/Rakefile

@@ -2,7 +2,7 @@ require 'hoe'
 
 
 Hoe.spec 'fbtok' do
-  self.version = '0.1.2'
+  self.version = '0.2.1'
 
   self.summary = "fbtok - football.txt lint tools incl. tokenizer, parser & more"
   self.description = summary
@@ -19,9 +19,9 @@ Hoe.spec 'fbtok' do
   self.licenses = ['Public Domain']
 
   self.extra_deps = [
-     #  ['sportdb-parser',  '>= 0.2.2'],
      #  ['sportdb-structs', '>= 0.5.0'],
      #  ['logutils',        '>= 0.6.1'],
+     ['sportdb-parser',  '>= 0.5.1'],
      ['sportdb-formats', '>= 2.1.2'],
   ]
 

data/bin/fbtok

@@ -10,7 +10,6 @@ args = ARGV
 
 opts = {
     debug: true,
-    metal: false,
     file:  nil,
 }
 
@@ -27,11 +26,14 @@ parser = OptionParser.new do |parser|
     opts[:debug] = true
   end
 
+=begin
   parser.on( "--metal",
                  "turn off typed parse tree; show to the metal tokens"+
                    " (default: #{opts[:metal]})" ) do |metal|
     opts[:metal] = true
   end
+=end
+
 
   parser.on( "-f FILE", "--file FILE",
                 "read datafiles (pathspecs) via .csv file") do |file|
@@ -85,7 +87,7 @@ specs.each_with_index do |(paths, rec),i|
 
    paths.each_with_index do |path,j|
       puts "==> [#{j+1}/#{paths.size}] reading >#{path}<..."
-      linter.read( path, parse: !opts[:metal] )
+      linter.read( path, parse: false )  ## only tokenize (do NOT parse)
 
       errors += linter.errors    if linter.errors?
    end
@@ -94,10 +96,10 @@ specs.each_with_index do |(paths, rec),i|
       puts
       pp errors
       puts
-      puts "!!   #{errors.size} parse error(s) in #{paths.size} datafiles(s)"
+      puts "!!   #{errors.size} tokenize error(s) in #{paths.size} datafiles(s)"
    else
       puts
-      puts "OK   no parse errors found in #{paths.size} datafile(s)"
+      puts "OK   no tokenize errors found in #{paths.size} datafile(s)"
    end
 
    ## add errors to rec via rec['errors'] to allow

data/bin/fbtree

@@ -0,0 +1,66 @@
+#!/usr/bin/env ruby
+
+## tip: to test run:
+##   ruby -I ./lib bin/fbtree
+
+require 'fbtok'
+
+args = ARGV
+ 
+
+opts = {
+    debug: true,
+}
+
+parser = OptionParser.new do |parser|
+  parser.banner = "Usage: #{$PROGRAM_NAME} [options] PATH"
+
+
+  parser.on( "-q", "--quiet",
+             "less debug output/messages - default is (#{!opts[:debug]})" ) do |debug|
+    opts[:debug] = false
+  end
+  parser.on( "--verbose", "--debug",
+               "turn on verbose / debug output (default: #{opts[:debug]})" ) do |debug|
+    opts[:debug] = true
+  end
+end
+parser.parse!( args )
+
+puts "OPTS:"
+p opts
+puts "ARGV:"
+p args
+
+
+## todo/check - use packs or projects or such
+##                instead of specs - why? why not?
+   paths = if args.empty?
+             [
+               '../../../openfootball/euro/2021--europe/euro.txt',
+               '../../../openfootball/euro/2024--germany/euro.txt',
+             ]
+          else
+            ## check for directories
+            ##   and auto-expand
+            SportDb::Parser::Opts.expand_args( args )
+          end
+
+
+
+SportDb::Parser::Linter.debug = true    if opts[:debug]
+
+linter = SportDb::Parser::Linter.new
+
+
+paths.each_with_index do |path,i|
+
+  puts "==> [#{i+1}/#{paths.size}] reading >#{path}<..."
+
+  linter.read( path, parse: true )
+end
+
+
+puts "bye"
+
+

data/lib/fbtok/linter.rb

@@ -7,7 +7,7 @@ class Parser
 class Linter
 
 def self.debug=(value) @@debug = value; end
-def self.debug?() @@debug ||= false; end  ## note: default is FALSE
+def self.debug?()      @@debug ||= false; end  ## note: default is FALSE
 def debug?()  self.class.debug?; end
 
 
@@ -23,35 +23,10 @@ end
 def errors?() @errors.size > 0; end
 
 
-
-  ## note:  colon (:) MUST be followed by one (or more) spaces
-  ##      make sure mon feb 12 18:10 will not match
-  ##        allow 1. FC Köln etc.
-  ##               Mainz 05:
-  ##           limit to 30 chars max
-  ##          only allow  chars incl. intl buut (NOT ()[]/;)
-  ##
-  ##   Group A:
-  ##   Group B:   - remove colon
-  ##    or lookup first
-
-  ATTRIB_RE = %r{^
-                   [ ]*?     # slurp leading spaces
-                (?<key>[^:|\]\[()\/; -]
-                       [^:|\]\[()\/;]{0,30}
-                 )
-                   [ ]*?     # slurp trailing spaces
-                   :[ ]+
-                (?<value>.+)
-                    [ ]*?   # slurp trailing spaces
-                   $
-                }ix
-
-
 #########
 ## parse - false (default) - tokenize (only)
 ##       - true            - tokenize & parse
-def read( path, parse: false )
+def read( path, parse: true )
   ## note: every (new) read call - resets errors list to empty
   @errors = []
 
@@ -62,9 +37,7 @@ def read( path, parse: false )
   h2 = nil
   orphans = 0    ## track paragraphs's with no heading
 
-  attrib_found = false
-
-
+ 
   nodes.each do |node|
     type = node[0]
 
@@ -88,7 +61,29 @@ def read( path, parse: false )
 
        lines = node[1]
 
+
        tree = []
+
+     if parse
+       ## flatten lines
+       txt  = []
+       lines.each_with_index do |line,i|
+          txt << line
+          txt << "\n"
+       end
+       txt = txt.join
+    
+       if debug?
+         puts "lines:"
+         pp txt   
+       end
+ 
+       ## todo/fix -  add/track parse errors!!!!!!
+       parser = RaccMatchParser.new( txt )   ## use own parser instance (not shared) - why? why not?
+       tree = parser.parse
+       pp tree  
+
+     else   ## process for tokenize only
        lines.each_with_index do |line,i|
 
         if debug?
@@ -96,36 +91,8 @@ def read( path, parse: false )
          puts "line >#{line}<"
         end
 
-
-        ## skip new (experimental attrib syntax)
-        if attrib_found == false &&
-            ATTRIB_RE.match?( line )
-          ## note: check attrib regex AFTER group def e.g.:
-          ##         Group A:
-          ##         Group B:  etc.
-          ##     todo/fix - change Group A: to Group A etc.
-          ##                       Group B: to Group B
-           attrib_found = true
-           ## logger.debug "skipping key/value line - >#{line}<"
-           next
-        end
-
-        if attrib_found
-          ## check if line ends with dot
-          ##  if not slurp up lines to the next do!!!
-          ## logger.debug "skipping key/value line - >#{line}<"
-          attrib_found = false   if line.end_with?( '.' )
-              # logger.debug "skipping key/value line (cont.) - >#{line}<"
-              next
-        end
-
-        t, error_messages  =  if parse
-                                  @parser.parse_with_errors( line )
-                              else
-                                  @parser.tokenize_with_errors( line )
-                              end
-
-
+        t, error_messages  =  @parser.tokenize_with_errors( line )
+                            
          if error_messages.size > 0
             ## add to "global" error list
             ##   make a triplet tuple (file / msg / line text)
@@ -137,12 +104,31 @@ def read( path, parse: false )
             end
          end
 
+          ## post-process tokens
+          ##  - check for round, group, etc.
+          t = t.map do |tok|
+            #############
+            ## pass 1
+            ##   replace all texts with keyword matches (e.g. group, round, leg, etc.)
+                if tok[0] == :TEXT
+                   text = tok[1]
+                    if @parser.is_group?( text )
+                           [:GROUP, text]
+                    elsif @parser.is_round?( text ) || @parser.is_leg?( text )
+                           [:ROUND, text]
+                    else
+                        tok  ## pass through as-is (1:1)
+                    end
+                else
+                   tok
+                end
+          end
+ 
          pp t   if debug?
 
          tree << t
        end
-
-       ## pp tree
+      end
     else
         pp node
         raise ArgumentError, "unsupported (node) type >#{type}<"

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: fbtok
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.1
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-01-02 00:00:00.000000000 Z
+date: 2025-01-17 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: sportdb-parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.5.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.5.1
 - !ruby/object:Gem::Dependency
   name: sportdb-formats
   requirement: !ruby/object:Gem::Requirement
@@ -64,6 +78,7 @@ executables:
 - fbchk
 - fbt
 - fbtok
+- fbtree
 - fbx
 extensions: []
 extra_rdoc_files:
@@ -78,6 +93,7 @@ files:
 - bin/fbchk
 - bin/fbt
 - bin/fbtok
+- bin/fbtree
 - bin/fbx
 - lib/fbtok.rb
 - lib/fbtok/linter.rb