fbtok 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0db5fb0d9cbda9ad626f4debbf27751f591c90684455e2e3cabc66162a02e3c6
-  data.tar.gz: cc4d1d160356785e54b99fb7033e078af9edf63cd60a469ab8bb2ad685603b7f
+  metadata.gz: 191b44113dea92aebe49fb5717146c9cd0038afb448ba34c4dd828e6daeb869e
+  data.tar.gz: 7367ad2ae027d158371ac63fcbbe53271da84f1dabbd4a4f2111ebd658d0c2c7
 SHA512:
-  metadata.gz: d688b40a4c97971eab87594a83ffe7966b245370944ac140950f0e935076d25c4317dfcb526ac0f22470c1027a7bc488812f37f07f6d1d413edb8e7c538c3f2b
-  data.tar.gz: beefaf087fe66d2ab3ecaae23cc786184e0558b3dd7bcc44e4e131cf70fca200a3f723060c42a2921d5cbef1f2b6513dc567dc693a7dd03bc2adcd8b7ad3a6e2
+  metadata.gz: 85d8e883d5fbe0654a5188b3c0d46b1be2f694a96a6fe9d70a6b88ce36d7676200165f82e999ef2b77dd2fc6f453da0dfd30b06e8ed4cc0a622e5a20329cb61e
+  data.tar.gz: 947f91db38384711f3fa734f7ef52b51068f01d78b9ecd953ac17caa94afe61e748971341ceafb0bcddf6a120b2d30324d6820ff77a675ded8d494b354614b43

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.2.0
+### 0.2.1
 ### 0.0.1 / 2025-01-02
 
 * Everything is new. First release.

data/Rakefile

@@ -2,7 +2,7 @@ require 'hoe'
 
 
 Hoe.spec 'fbtok' do
-  self.version = '0.2.0'
+  self.version = '0.2.1'
 
   self.summary = "fbtok - football.txt lint tools incl. tokenizer, parser & more"
   self.description = summary
@@ -21,7 +21,7 @@ Hoe.spec 'fbtok' do
   self.extra_deps = [
      #  ['sportdb-structs', '>= 0.5.0'],
      #  ['logutils',        '>= 0.6.1'],
-     ['sportdb-parser',  '>= 0.5.0'],
+     ['sportdb-parser',  '>= 0.5.1'],
      ['sportdb-formats', '>= 2.1.2'],
   ]
 

data/bin/fbtok

@@ -87,7 +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 )
+      linter.read( path, parse: false )  ## only tokenize (do NOT parse)
 
       errors += linter.errors    if linter.errors?
    end

data/bin/fbtree

@@ -5,150 +5,6 @@
 
 require 'fbtok'
 
-
-###
-## note - Linter for now nested inside Parser - keep? why? why not?
-class RaccLinter
-
-def self.debug=(value) @@debug = value; end
-def self.debug?() @@debug ||= false; end  ## note: default is FALSE
-def debug?()  self.class.debug?; end
-
-
-
-attr_reader :errors
-
-def initialize
-  @errors = []
-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 )
-  ## note: every (new) read call - resets errors list to empty
-  @errors = []
-
-  nodes = SportDb::OutlineReader.read( path )
-
-  ##  process nodes
-  h1 = nil
-  h2 = nil
-  orphans = 0    ## track paragraphs's with no heading
-
-  attrib_found = false
-
-
-  nodes.each do |node|
-    type = node[0]
-
-    if type == :h1
-        h1 = node[1]  ## get heading text
-        puts "  = Heading 1 >#{node[1]}<"
-    elsif type == :h2
-        if h1.nil?
-          puts "!! WARN - no heading for subheading; skipping parse"
-          next
-        end
-        h2 = node[1]  ## get heading text
-        puts "  == Heading 2 >#{node[1]}<"
-    elsif type == :p
-
-       if h1.nil?
-         orphans += 1    ## only warn once
-         puts "!! WARN - no heading for #{orphans} text paragraph(s); skipping parse"
-         next
-       end
-
-       lines = node[1]
-
-       txt  = []
-       lines.each_with_index do |line,i|
-
-        if debug?
-         puts
-         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
-
-        txt << line
-        txt << "\n"
-      end
-
-      ## flatten
-      txt = txt.join
-      pp txt   if debug?
-
-      parser = RaccMatchParser.new( txt )   ## use own parser instance (not shared) - why? why not?
-      tree = parser.parse
-      pp tree
-    else
-        pp node
-        raise ArgumentError, "unsupported (node) type >#{type}<"
-    end
-  end  # each node
-end  # read
-end  # class RaccLinter
-
-
-
-
-###############################################
-#  start with code
-
-
-
 args = ARGV
  
 
@@ -192,36 +48,19 @@ p args
 
 
 
+SportDb::Parser::Linter.debug = true    if opts[:debug]
+
+linter = SportDb::Parser::Linter.new
 
-errors = []
-linter = RaccLinter.new
 
 paths.each_with_index do |path,i|
 
   puts "==> [#{i+1}/#{paths.size}] reading >#{path}<..."
 
-  linter.read( path )
+  linter.read( path, parse: true )
 end
 
-puts "bye"
-
 
+puts "bye"
 
 
-__END__
-
-   if errors.size > 0
-      puts
-      pp errors
-      puts
-      puts "!!   #{errors.size} parse error(s) in #{paths.size} datafiles(s)"
-   else
-      puts
-      puts "OK   no parse errors found in #{paths.size} datafile(s)"
-   end
-
-   ## add errors to rec via rec['errors'] to allow
-   ##   for further processing/reporting
-   rec['errors'] = errors
-end
-

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  )
+def read( path, parse: true )
   ## note: every (new) read call - resets errors list to empty
   @errors = []
 
@@ -62,9 +37,7 @@ def read( path  )
   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  )
 
        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?
@@ -96,29 +91,6 @@ def read( path  )
          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  =  @parser.tokenize_with_errors( line )
                             
          if error_messages.size > 0
@@ -156,8 +128,7 @@ def read( path  )
 
          tree << t
        end
-
-       ## pp tree
+      end
     else
         pp node
         raise ArgumentError, "unsupported (node) type >#{type}<"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: fbtok
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-01-15 00:00:00.000000000 Z
+date: 2025-01-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: sportdb-parser
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.5.0
+        version: 0.5.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.5.0
+        version: 0.5.1
 - !ruby/object:Gem::Dependency
   name: sportdb-formats
   requirement: !ruby/object:Gem::Requirement